diff --git "a/checkpoint-1602720/trainer_state.json" "b/checkpoint-1602720/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1602720/trainer_state.json" @@ -0,0 +1,18973 @@ +{ + "best_metric": 3.86246395111084, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/superlative-quantifier/transformer/0/checkpoints/checkpoint-839520", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 1602720, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.9711, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8278, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1878, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9759, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8138, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7059, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6086, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5325, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4552, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4133, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3622, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3082, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2687, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2198, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1772, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1454, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1079, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.085, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.047, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0306, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0104, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 4.9751, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9471, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9286, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9167, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.8888, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8661, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8471, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8478, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8119, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 4.8025, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7976, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7792, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7653, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7642, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7433, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7381, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7044, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7012, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6823, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6762, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6713, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6646, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6464, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.649, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6315, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6346, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6322, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6021, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 4.5927, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.6013, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.6008, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5739, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 4.568, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.568, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5501, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5569, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5304, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 4.5402, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5328, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5286, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5045, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5216, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4922, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.5019, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5007, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.4948, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4747, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4661, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4628, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4757, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4691, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4524, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4639, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4655, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4485, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4442, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4354, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4371, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4196, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4225, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4174, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4285, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4162, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.3958, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4023, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.3994, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.4042, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.3984, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925394549003088e-05, + "loss": 4.3863, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.386, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3769, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3676, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3609, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3663, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920364618377149e-05, + "loss": 4.3753, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919526023626097e-05, + "loss": 4.3637, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.3511, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.3498, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3557, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3561, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3469, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914496093000158e-05, + "loss": 4.3431, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.3339, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3438, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3218, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3276, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3311, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3216, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3192, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3178, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3114, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3145, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3093, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3057, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3127, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3104, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019237232558704e-05, + "loss": 4.3045, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010851285048184e-05, + "loss": 4.3067, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900246533753767e-05, + "loss": 4.2943, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899407939002715e-05, + "loss": 4.2952, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.2859, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.2857, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.2855, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2837, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2813, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2814, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2815, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2674, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2785, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.276, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2568, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2509, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.257, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2721, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2743, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885995336627002e-05, + "loss": 4.2565, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.2559, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2615, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2612, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2526, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2456, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2478, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.242, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2393, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2484, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.232, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876774070126176e-05, + "loss": 4.2431, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875935475375124e-05, + "loss": 4.2382, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.2249, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.208662033081055, + "eval_runtime": 301.5703, + "eval_samples_per_second": 1265.347, + "eval_steps_per_second": 39.543, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2253, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.2172, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2312, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2223, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2263, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870066949998133e-05, + "loss": 4.2108, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869229993127454e-05, + "loss": 4.2056, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683913983764027e-05, + "loss": 4.1937, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675528036253507e-05, + "loss": 4.2244, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667142088742986e-05, + "loss": 4.2125, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.2055, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.2116, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642017003818885e-05, + "loss": 4.1979, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633631056308365e-05, + "loss": 4.1935, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625245108797845e-05, + "loss": 4.1902, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616859161287324e-05, + "loss": 4.1903, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608473213776804e-05, + "loss": 4.189, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860008726626628e-05, + "loss": 4.1836, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591701318755764e-05, + "loss": 4.1948, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583315371245244e-05, + "loss": 4.2006, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574929423734724e-05, + "loss": 4.1842, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566543476224204e-05, + "loss": 4.1769, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558157528713684e-05, + "loss": 4.1808, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854978796000689e-05, + "loss": 4.1819, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854140201249637e-05, + "loss": 4.1752, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853301606498585e-05, + "loss": 4.165, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.1673, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851626054876854e-05, + "loss": 4.1778, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850787460125802e-05, + "loss": 4.1537, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.84994886537475e-05, + "loss": 4.1594, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.1674, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.84827331375302e-05, + "loss": 4.1669, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847436356882341e-05, + "loss": 4.1702, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846597762131289e-05, + "loss": 4.1628, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845759167380237e-05, + "loss": 4.1595, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844920572629185e-05, + "loss": 4.1656, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844081977878133e-05, + "loss": 4.1431, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843243383127081e-05, + "loss": 4.1522, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842404788376029e-05, + "loss": 4.1383, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841566193624977e-05, + "loss": 4.1425, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.8407292367542976e-05, + "loss": 4.1452, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398906420032456e-05, + "loss": 4.1477, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839053685132567e-05, + "loss": 4.1452, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838215090381515e-05, + "loss": 4.1386, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837376495630463e-05, + "loss": 4.1402, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836537900879411e-05, + "loss": 4.1436, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835700944008732e-05, + "loss": 4.1453, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.83486234925768e-05, + "loss": 4.13, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834023754506628e-05, + "loss": 4.1252, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833185159755576e-05, + "loss": 4.1365, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832346565004524e-05, + "loss": 4.1456, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831509608133845e-05, + "loss": 4.1264, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830671013382793e-05, + "loss": 4.1272, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829832418631741e-05, + "loss": 4.1259, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828993823880689e-05, + "loss": 4.118, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828155229129637e-05, + "loss": 4.1248, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273166343785856e-05, + "loss": 4.1108, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264780396275336e-05, + "loss": 4.1255, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256394448764816e-05, + "loss": 4.1236, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248024880058025e-05, + "loss": 4.1194, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239638932547505e-05, + "loss": 4.1026, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231269363840714e-05, + "loss": 4.124, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222883416330194e-05, + "loss": 4.0984, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214497468819674e-05, + "loss": 4.1127, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206111521309154e-05, + "loss": 4.1155, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197725573798634e-05, + "loss": 4.1149, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189339626288114e-05, + "loss": 4.0983, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180953678777594e-05, + "loss": 4.097, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172567731267074e-05, + "loss": 4.0945, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816419816256029e-05, + "loss": 4.1065, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815581221504977e-05, + "loss": 4.1065, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814742626753924e-05, + "loss": 4.1019, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813904032002872e-05, + "loss": 4.1092, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813067075132194e-05, + "loss": 4.1088, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812228480381141e-05, + "loss": 4.1061, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811389885630089e-05, + "loss": 4.0909, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810551290879037e-05, + "loss": 4.1023, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809712696127985e-05, + "loss": 4.1013, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808875739257306e-05, + "loss": 4.0813, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808037144506255e-05, + "loss": 4.1002, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807198549755203e-05, + "loss": 4.0849, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806359955004151e-05, + "loss": 4.1073, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805521360253099e-05, + "loss": 4.0924, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804682765502047e-05, + "loss": 4.0729, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.8038458086313677e-05, + "loss": 4.0904, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8030072138803156e-05, + "loss": 4.0817, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021686191292636e-05, + "loss": 4.0945, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013300243782116e-05, + "loss": 4.0862, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004930675075325e-05, + "loss": 4.0808, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996544727564805e-05, + "loss": 4.084, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988158780054285e-05, + "loss": 4.0752, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979772832543765e-05, + "loss": 4.0704, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971386885033245e-05, + "loss": 4.0677, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963000937522725e-05, + "loss": 4.073, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795463136881594e-05, + "loss": 4.084, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794624542130542e-05, + "loss": 4.0745, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.79378594737949e-05, + "loss": 4.065, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792947352628438e-05, + "loss": 4.0657, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792108757877386e-05, + "loss": 4.0732, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791270163126334e-05, + "loss": 4.0772, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790431568375282e-05, + "loss": 4.071, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.78959297362423e-05, + "loss": 4.0674, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788756016753551e-05, + "loss": 4.0622, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787917422002499e-05, + "loss": 4.0726, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787078827251447e-05, + "loss": 4.0499, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786240232500395e-05, + "loss": 4.0614, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854032756297166e-05, + "loss": 4.065, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845646808786646e-05, + "loss": 4.057, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837260861276126e-05, + "loss": 4.0565, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828874913765606e-05, + "loss": 4.0558, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782048896625508e-05, + "loss": 4.0568, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781210301874456e-05, + "loss": 4.0557, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780371707123404e-05, + "loss": 4.0563, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779533112372352e-05, + "loss": 4.0525, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778696155501673e-05, + "loss": 4.0653, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777857560750621e-05, + "loss": 4.0618, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770206038799423e-05, + "loss": 4.0568, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761820091288903e-05, + "loss": 4.0574, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753434143778383e-05, + "loss": 4.0543, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774504819626786e-05, + "loss": 4.0507, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773666224875734e-05, + "loss": 4.0436, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772827630124682e-05, + "loss": 4.0439, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77198903537363e-05, + "loss": 4.05, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771150440622578e-05, + "loss": 4.0502, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770313483751899e-05, + "loss": 4.0466, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769474889000847e-05, + "loss": 4.0476, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768636294249795e-05, + "loss": 4.0436, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767797699498743e-05, + "loss": 4.0436, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766960742628064e-05, + "loss": 4.0437, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766122147877012e-05, + "loss": 4.0494, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.76528355312596e-05, + "loss": 4.0342, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764444958374909e-05, + "loss": 4.026, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763606363623857e-05, + "loss": 4.0306, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762769406753178e-05, + "loss": 4.0483, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761930812002126e-05, + "loss": 4.0478, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761092217251074e-05, + "loss": 4.0396, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760253622500022e-05, + "loss": 4.0371, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594166656293426e-05, + "loss": 4.0449, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585780708782906e-05, + "loss": 4.0434, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577394761272386e-05, + "loss": 4.0398, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569008813761866e-05, + "loss": 4.0311, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560639245055075e-05, + "loss": 4.0327, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552253297544555e-05, + "loss": 4.0347, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543867350034035e-05, + "loss": 4.0245, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753548140252352e-05, + "loss": 4.042, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752711183381673e-05, + "loss": 4.0229, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751872588630621e-05, + "loss": 4.0347, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751033993879569e-05, + "loss": 4.032, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750195399128517e-05, + "loss": 4.0213, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.04117488861084, + "eval_runtime": 300.9126, + "eval_samples_per_second": 1268.112, + "eval_steps_per_second": 39.629, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749356804377465e-05, + "loss": 4.0234, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748518209626413e-05, + "loss": 4.0193, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747679614875361e-05, + "loss": 4.0258, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468410201243084e-05, + "loss": 4.0231, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460024253732563e-05, + "loss": 4.0318, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451638306222043e-05, + "loss": 4.0144, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744325235871152e-05, + "loss": 4.0132, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434866411201e-05, + "loss": 4.0007, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742648046369049e-05, + "loss": 4.0342, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741809451617997e-05, + "loss": 4.0204, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740970856866945e-05, + "loss": 4.0099, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740133899996266e-05, + "loss": 4.0255, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739296943125587e-05, + "loss": 4.0068, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738458348374535e-05, + "loss": 4.0111, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737619753623483e-05, + "loss": 4.0008, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736781158872431e-05, + "loss": 4.0028, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735942564121379e-05, + "loss": 4.007, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735103969370327e-05, + "loss": 3.9983, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734265374619275e-05, + "loss": 4.014, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733426779868223e-05, + "loss": 4.0176, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325898229975444e-05, + "loss": 4.0052, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317512282464924e-05, + "loss": 4.0014, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309126334954404e-05, + "loss": 4.0022, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300740387443884e-05, + "loss": 4.0061, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729237081873709e-05, + "loss": 3.9953, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728398487122657e-05, + "loss": 3.9955, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727559892371605e-05, + "loss": 3.9895, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726722935500926e-05, + "loss": 4.0065, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725884340749874e-05, + "loss": 3.9787, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725045745998822e-05, + "loss": 3.9901, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.72420715124777e-05, + "loss": 3.9955, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723370194377091e-05, + "loss": 3.9993, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.72253159962604e-05, + "loss": 3.9997, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721693004874988e-05, + "loss": 3.9966, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720854410123936e-05, + "loss": 3.9915, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200174532532566e-05, + "loss": 4.0003, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191788585022046e-05, + "loss": 3.984, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183402637511526e-05, + "loss": 3.9876, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175016690001006e-05, + "loss": 3.9747, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166647121294215e-05, + "loss": 3.9834, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158261173783695e-05, + "loss": 3.9792, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149875226273175e-05, + "loss": 3.9912, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141489278762655e-05, + "loss": 3.9838, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133119710055864e-05, + "loss": 3.9803, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712473376254535e-05, + "loss": 3.9835, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711634781503483e-05, + "loss": 3.9847, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710796186752431e-05, + "loss": 3.9866, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709959229881752e-05, + "loss": 3.9734, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091206351307e-05, + "loss": 3.966, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708282040379648e-05, + "loss": 3.9862, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707443445628596e-05, + "loss": 3.9869, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706606488757917e-05, + "loss": 3.9771, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705767894006865e-05, + "loss": 3.9754, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704929299255813e-05, + "loss": 3.9695, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704090704504761e-05, + "loss": 3.9669, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703253747634082e-05, + "loss": 3.9763, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024151528830305e-05, + "loss": 3.9621, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015765581319785e-05, + "loss": 3.9754, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007379633809265e-05, + "loss": 3.9747, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6999010065102474e-05, + "loss": 3.9679, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990624117591954e-05, + "loss": 3.957, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982238170081434e-05, + "loss": 3.9787, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973852222570914e-05, + "loss": 3.9555, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696548265386412e-05, + "loss": 3.9678, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69570967063536e-05, + "loss": 3.9672, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694871075884308e-05, + "loss": 3.9727, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694032481133256e-05, + "loss": 3.9535, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693195524262577e-05, + "loss": 3.9591, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692356929511526e-05, + "loss": 3.947, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691518334760474e-05, + "loss": 3.9665, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690679740009422e-05, + "loss": 3.9677, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689842783138743e-05, + "loss": 3.9607, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689004188387691e-05, + "loss": 3.9679, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688165593636639e-05, + "loss": 3.9693, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687326998885587e-05, + "loss": 3.9721, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864900420149076e-05, + "loss": 3.952, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856530851442285e-05, + "loss": 3.9638, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848144903931765e-05, + "loss": 3.9662, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839758956421245e-05, + "loss": 3.9469, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831373008910725e-05, + "loss": 3.9616, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822987061400205e-05, + "loss": 3.9505, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681460111388969e-05, + "loss": 3.9743, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806215166379165e-05, + "loss": 3.9596, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797829218868645e-05, + "loss": 3.9401, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678945965016186e-05, + "loss": 3.9516, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678107370265134e-05, + "loss": 3.9525, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772687755140814e-05, + "loss": 3.9611, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676431818643403e-05, + "loss": 3.9554, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675594861772724e-05, + "loss": 3.9495, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674756267021672e-05, + "loss": 3.9513, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.67391767227062e-05, + "loss": 3.9471, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673079077519568e-05, + "loss": 3.9432, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672240482768516e-05, + "loss": 3.934, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671401888017464e-05, + "loss": 3.9469, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705649311467855e-05, + "loss": 3.957, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697263363957335e-05, + "loss": 3.9491, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688877416446815e-05, + "loss": 3.937, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668049146893629e-05, + "loss": 3.9421, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667210552142577e-05, + "loss": 3.9428, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666371957391525e-05, + "loss": 3.9533, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665533362640473e-05, + "loss": 3.9451, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664694767889421e-05, + "loss": 3.9438, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663857811018742e-05, + "loss": 3.9357, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66301921626769e-05, + "loss": 3.95, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621806215166383e-05, + "loss": 3.9246, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613420267655863e-05, + "loss": 3.9411, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660505069894907e-05, + "loss": 3.9382, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659666475143855e-05, + "loss": 3.9379, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658827880392803e-05, + "loss": 3.9338, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657989285641751e-05, + "loss": 3.934, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657152328771072e-05, + "loss": 3.937, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.65631373402002e-05, + "loss": 3.9355, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655475139268968e-05, + "loss": 3.9387, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654636544517916e-05, + "loss": 3.9356, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653799587647237e-05, + "loss": 3.9417, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652960992896185e-05, + "loss": 3.9447, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521240360255066e-05, + "loss": 3.9393, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512854412744546e-05, + "loss": 3.9401, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504468465234026e-05, + "loss": 3.9359, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496082517723506e-05, + "loss": 3.9284, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487696570212986e-05, + "loss": 3.93, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479310622702466e-05, + "loss": 3.9297, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470924675191946e-05, + "loss": 3.9278, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462538727681426e-05, + "loss": 3.9375, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454169158974635e-05, + "loss": 3.9278, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445783211464115e-05, + "loss": 3.9341, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437397263953595e-05, + "loss": 3.9305, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429011316443075e-05, + "loss": 3.9274, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642064174773629e-05, + "loss": 3.9263, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641225580022577e-05, + "loss": 3.9388, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640386985271525e-05, + "loss": 3.9211, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639548390520473e-05, + "loss": 3.9178, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638711433649794e-05, + "loss": 3.9139, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637872838898742e-05, + "loss": 3.9317, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637035882028063e-05, + "loss": 3.9358, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636197287277011e-05, + "loss": 3.9326, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635358692525959e-05, + "loss": 3.9234, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634520097774907e-05, + "loss": 3.9356, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633681503023855e-05, + "loss": 3.9278, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632842908272803e-05, + "loss": 3.9322, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632004313521751e-05, + "loss": 3.9213, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631165718770699e-05, + "loss": 3.9257, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303287619000204e-05, + "loss": 3.9252, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294918050293413e-05, + "loss": 3.9143, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286532102782893e-05, + "loss": 3.9314, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278146155272373e-05, + "loss": 3.9211, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626976020776185e-05, + "loss": 3.9241, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626137426025133e-05, + "loss": 3.9247, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625298831274081e-05, + "loss": 3.9129, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9685909748077393, + "eval_runtime": 306.4929, + "eval_samples_per_second": 1245.024, + "eval_steps_per_second": 38.908, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624460236523029e-05, + "loss": 3.9193, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.6236216417719766e-05, + "loss": 3.9155, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622784684901298e-05, + "loss": 3.9183, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621946090150246e-05, + "loss": 3.9175, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621109133279568e-05, + "loss": 3.9305, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620270538528516e-05, + "loss": 3.9118, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619431943777464e-05, + "loss": 3.9069, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618593349026412e-05, + "loss": 3.8987, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617754754275359e-05, + "loss": 3.9249, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616916159524307e-05, + "loss": 3.9206, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616077564773255e-05, + "loss": 3.9011, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615238970022203e-05, + "loss": 3.9228, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614402013151524e-05, + "loss": 3.9063, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613563418400472e-05, + "loss": 3.9084, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.61272482364942e-05, + "loss": 3.9035, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611886228898368e-05, + "loss": 3.9009, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611047634147316e-05, + "loss": 3.9039, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610209039396265e-05, + "loss": 3.8998, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609370444645213e-05, + "loss": 3.9137, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085318498941607e-05, + "loss": 3.9154, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076948930234816e-05, + "loss": 3.9097, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068562982724296e-05, + "loss": 3.9045, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060177035213776e-05, + "loss": 3.8998, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051807466506985e-05, + "loss": 3.9103, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043421518996465e-05, + "loss": 3.8961, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035035571485945e-05, + "loss": 3.8985, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026649623975425e-05, + "loss": 3.8925, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018280055268634e-05, + "loss": 3.9068, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009894107758114e-05, + "loss": 3.8844, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.60015081602476e-05, + "loss": 3.8935, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599313859154081e-05, + "loss": 3.9029, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598475264403029e-05, + "loss": 3.8997, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597636669651977e-05, + "loss": 3.9035, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596798074900925e-05, + "loss": 3.9026, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595959480149873e-05, + "loss": 3.8971, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595120885398821e-05, + "loss": 3.905, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594282290647769e-05, + "loss": 3.8921, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593443695896717e-05, + "loss": 3.8862, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592606739026038e-05, + "loss": 3.8821, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591768144274986e-05, + "loss": 3.8898, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590929549523934e-05, + "loss": 3.8866, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590090954772882e-05, + "loss": 3.8999, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892539979022034e-05, + "loss": 3.8897, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884154031511514e-05, + "loss": 3.8881, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.5875768084000994e-05, + "loss": 3.8946, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867382136490474e-05, + "loss": 3.887, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585901256778368e-05, + "loss": 3.8986, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585062662027316e-05, + "loss": 3.8832, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584224067276264e-05, + "loss": 3.8683, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583385472525212e-05, + "loss": 3.9009, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582548515654533e-05, + "loss": 3.8933, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581711558783854e-05, + "loss": 3.8915, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580872964032802e-05, + "loss": 3.8828, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580034369281751e-05, + "loss": 3.8808, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579195774530699e-05, + "loss": 3.8764, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578357179779647e-05, + "loss": 3.8869, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577518585028595e-05, + "loss": 3.8753, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576679990277543e-05, + "loss": 3.8815, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.57584139552649e-05, + "loss": 3.8915, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750044386558117e-05, + "loss": 3.8776, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741658439047596e-05, + "loss": 3.8681, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733272491537076e-05, + "loss": 3.8916, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572488654402655e-05, + "loss": 3.8675, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716516975319765e-05, + "loss": 3.875, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708147406612975e-05, + "loss": 3.8849, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569976145910246e-05, + "loss": 3.888, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569137551159194e-05, + "loss": 3.8644, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568298956408142e-05, + "loss": 3.874, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.56746036165709e-05, + "loss": 3.8576, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566623404786411e-05, + "loss": 3.8841, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565784810035359e-05, + "loss": 3.8784, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564946215284307e-05, + "loss": 3.8771, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564107620533255e-05, + "loss": 3.8804, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563269025782202e-05, + "loss": 3.8832, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.56243043103115e-05, + "loss": 3.8888, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561591836280098e-05, + "loss": 3.8663, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.56075487940942e-05, + "loss": 3.8797, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559916284658368e-05, + "loss": 3.882, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559077689907316e-05, + "loss": 3.8602, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558239095156264e-05, + "loss": 3.8774, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557400500405212e-05, + "loss": 3.8688, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.55656190565416e-05, + "loss": 3.8862, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555723310903108e-05, + "loss": 3.8777, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554884716152056e-05, + "loss": 3.8582, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554047759281377e-05, + "loss": 3.87, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553209164530325e-05, + "loss": 3.868, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552370569779273e-05, + "loss": 3.8799, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551531975028221e-05, + "loss": 3.869, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550696656037915e-05, + "loss": 3.8657, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549858061286863e-05, + "loss": 3.8694, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549019466535811e-05, + "loss": 3.8687, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548180871784759e-05, + "loss": 3.8622, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547342277033707e-05, + "loss": 3.8513, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546503682282655e-05, + "loss": 3.8668, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545666725411976e-05, + "loss": 3.8767, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544828130660924e-05, + "loss": 3.8731, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543989535909872e-05, + "loss": 3.8512, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.54315094115882e-05, + "loss": 3.8636, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542312346407768e-05, + "loss": 3.8627, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541473751656716e-05, + "loss": 3.873, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540635156905664e-05, + "loss": 3.8653, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539796562154612e-05, + "loss": 3.8652, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538959605283933e-05, + "loss": 3.8563, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538121010532882e-05, + "loss": 3.8723, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372840536622026e-05, + "loss": 3.8467, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364454589111506e-05, + "loss": 3.8629, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5356068641600986e-05, + "loss": 3.858, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347682694090466e-05, + "loss": 3.8598, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339296746579946e-05, + "loss": 3.854, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330927177873155e-05, + "loss": 3.8624, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322541230362635e-05, + "loss": 3.8535, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314155282852115e-05, + "loss": 3.8586, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305769335341595e-05, + "loss": 3.8607, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297383387831075e-05, + "loss": 3.8581, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5288997440320555e-05, + "loss": 3.865, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280611492810035e-05, + "loss": 3.8663, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527224192410325e-05, + "loss": 3.86, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526385597659273e-05, + "loss": 3.867, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525547002908221e-05, + "loss": 3.8594, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247084081571684e-05, + "loss": 3.851, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238698134061164e-05, + "loss": 3.8515, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230312186550644e-05, + "loss": 3.8544, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221926239040124e-05, + "loss": 3.8539, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213540291529604e-05, + "loss": 3.8625, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520517072282281e-05, + "loss": 3.8519, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519678477531229e-05, + "loss": 3.86, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518839882780177e-05, + "loss": 3.8512, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518001288029125e-05, + "loss": 3.852, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517162693278074e-05, + "loss": 3.8525, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516324098527022e-05, + "loss": 3.8646, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515487141656343e-05, + "loss": 3.8492, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514648546905291e-05, + "loss": 3.8414, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513809952154239e-05, + "loss": 3.8378, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512971357403187e-05, + "loss": 3.8561, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512134400532508e-05, + "loss": 3.8602, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511295805781456e-05, + "loss": 3.8596, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510457211030404e-05, + "loss": 3.8519, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509618616279352e-05, + "loss": 3.8612, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087816594086726e-05, + "loss": 3.8542, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079430646576206e-05, + "loss": 3.8566, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507104469906569e-05, + "loss": 3.8495, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506265875155517e-05, + "loss": 3.853, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505427280404465e-05, + "loss": 3.8544, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504588685653413e-05, + "loss": 3.84, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503751728782734e-05, + "loss": 3.8592, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502913134031682e-05, + "loss": 3.8524, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.50207453928063e-05, + "loss": 3.8497, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501235944529578e-05, + "loss": 3.8482, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500398987658899e-05, + "loss": 3.8461, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.92685604095459, + "eval_runtime": 305.5392, + "eval_samples_per_second": 1248.91, + "eval_steps_per_second": 39.029, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499560392907847e-05, + "loss": 3.8437, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498721798156795e-05, + "loss": 3.8447, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497883203405743e-05, + "loss": 3.8482, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497044608654691e-05, + "loss": 3.8465, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496206013903639e-05, + "loss": 3.8586, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495367419152587e-05, + "loss": 3.8423, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494528824401535e-05, + "loss": 3.8333, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493690229650483e-05, + "loss": 3.8343, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928532727798047e-05, + "loss": 3.8503, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492014678028752e-05, + "loss": 3.848, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911760832777e-05, + "loss": 3.8334, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490337488526648e-05, + "loss": 3.8493, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489500531655969e-05, + "loss": 3.8396, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488661936904917e-05, + "loss": 3.8418, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487823342153865e-05, + "loss": 3.8326, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486984747402813e-05, + "loss": 3.8316, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486146152651761e-05, + "loss": 3.8328, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853075579007095e-05, + "loss": 3.8318, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844689631496575e-05, + "loss": 3.8462, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836303683986055e-05, + "loss": 3.8475, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827950494082993e-05, + "loss": 3.8426, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481956454657247e-05, + "loss": 3.8369, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481117859906195e-05, + "loss": 3.8313, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480279265155143e-05, + "loss": 3.8392, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479440670404091e-05, + "loss": 3.8319, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478602075653039e-05, + "loss": 3.8326, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477763480901987e-05, + "loss": 3.8249, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476926524031308e-05, + "loss": 3.8367, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476087929280256e-05, + "loss": 3.8227, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475249334529205e-05, + "loss": 3.8209, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474410739778153e-05, + "loss": 3.8377, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473573782907474e-05, + "loss": 3.8333, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472735188156422e-05, + "loss": 3.8407, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.47189659340537e-05, + "loss": 3.8378, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471057998654318e-05, + "loss": 3.8271, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470219403903266e-05, + "loss": 3.8385, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469380809152214e-05, + "loss": 3.8312, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468543852281535e-05, + "loss": 3.8193, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467705257530483e-05, + "loss": 3.8158, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466866662779431e-05, + "loss": 3.8215, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466028068028379e-05, + "loss": 3.8231, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651911111577e-05, + "loss": 3.836, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464352516406648e-05, + "loss": 3.8249, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463513921655596e-05, + "loss": 3.8228, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462675326904544e-05, + "loss": 3.8323, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461838370033865e-05, + "loss": 3.8251, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460999775282813e-05, + "loss": 3.8329, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460161180531761e-05, + "loss": 3.8165, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459322585780709e-05, + "loss": 3.8006, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458483991029657e-05, + "loss": 3.8354, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457645396278605e-05, + "loss": 3.832, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456808439407926e-05, + "loss": 3.8267, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455969844656874e-05, + "loss": 3.82, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455131249905822e-05, + "loss": 3.8163, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.45429265515477e-05, + "loss": 3.8132, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534556982840916e-05, + "loss": 3.8212, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526171035330396e-05, + "loss": 3.8139, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517785087819876e-05, + "loss": 3.8177, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509399140309356e-05, + "loss": 3.8266, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450101319279883e-05, + "loss": 3.8191, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492643624092045e-05, + "loss": 3.8068, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484257676581525e-05, + "loss": 3.8297, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475871729071e-05, + "loss": 3.8055, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446748578156048e-05, + "loss": 3.8088, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4459116212853694e-05, + "loss": 3.8246, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450730265343174e-05, + "loss": 3.827, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442344317832654e-05, + "loss": 3.801, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4433958370322134e-05, + "loss": 3.812, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425572422811614e-05, + "loss": 3.7968, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441720285410482e-05, + "loss": 3.8222, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.44088169065943e-05, + "loss": 3.8213, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440043095908378e-05, + "loss": 3.8111, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439204501157326e-05, + "loss": 3.8192, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438367544286647e-05, + "loss": 3.8193, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437528949535595e-05, + "loss": 3.8321, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436690354784543e-05, + "loss": 3.8066, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435851760033491e-05, + "loss": 3.8183, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435013165282439e-05, + "loss": 3.8226, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434176208411761e-05, + "loss": 3.7983, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433337613660709e-05, + "loss": 3.8191, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432499018909657e-05, + "loss": 3.8102, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431660424158605e-05, + "loss": 3.8231, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430821829407553e-05, + "loss": 3.8185, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299848725368737e-05, + "loss": 3.8011, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291462777858217e-05, + "loss": 3.8054, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283076830347696e-05, + "loss": 3.8055, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274690882837176e-05, + "loss": 3.824, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266321314130386e-05, + "loss": 3.8089, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257935366619865e-05, + "loss": 3.8062, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249549419109345e-05, + "loss": 3.8075, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424116347159883e-05, + "loss": 3.8112, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423277752408831e-05, + "loss": 3.8036, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422440795538152e-05, + "loss": 3.7922, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216022007871e-05, + "loss": 3.8093, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420763606036048e-05, + "loss": 3.8153, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419925011284996e-05, + "loss": 3.8158, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419088054414317e-05, + "loss": 3.7929, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418249459663265e-05, + "loss": 3.8047, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417410864912213e-05, + "loss": 3.8043, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416572270161161e-05, + "loss": 3.8106, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415733675410109e-05, + "loss": 3.811, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41489671853943e-05, + "loss": 3.8072, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414058123788378e-05, + "loss": 3.7995, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132195290373266e-05, + "loss": 3.8109, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123809342862746e-05, + "loss": 3.7889, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115439774155955e-05, + "loss": 3.804, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107053826645435e-05, + "loss": 3.7971, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098667879134915e-05, + "loss": 3.8061, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090281931624395e-05, + "loss": 3.7906, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081895984113875e-05, + "loss": 3.8074, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073526415407084e-05, + "loss": 3.7978, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065140467896564e-05, + "loss": 3.8001, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056754520386044e-05, + "loss": 3.8024, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048368572875524e-05, + "loss": 3.7997, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4039982625365004e-05, + "loss": 3.8063, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403161305665822e-05, + "loss": 3.8136, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402324348795143e-05, + "loss": 3.8056, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401485754044091e-05, + "loss": 3.8088, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400647159293039e-05, + "loss": 3.8032, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399808564541987e-05, + "loss": 3.7964, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398969969790935e-05, + "loss": 3.7895, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398131375039883e-05, + "loss": 3.8028, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397292780288831e-05, + "loss": 3.7976, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396454185537778e-05, + "loss": 3.8032, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395615590786726e-05, + "loss": 3.7983, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394778633916048e-05, + "loss": 3.8014, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393940039164996e-05, + "loss": 3.7976, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393101444413944e-05, + "loss": 3.7952, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392262849662892e-05, + "loss": 3.7947, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391425892792213e-05, + "loss": 3.8069, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905872980411606e-05, + "loss": 3.798, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897487032901086e-05, + "loss": 3.7877, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889101085390566e-05, + "loss": 3.7806, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388073151668378e-05, + "loss": 3.8031, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872345569173255e-05, + "loss": 3.8034, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863959621662735e-05, + "loss": 3.8046, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855573674152215e-05, + "loss": 3.8006, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847204105445424e-05, + "loss": 3.8044, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383881815793491e-05, + "loss": 3.7965, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383043221042439e-05, + "loss": 3.8049, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382204626291387e-05, + "loss": 3.7921, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381367669420708e-05, + "loss": 3.7966, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380529074669656e-05, + "loss": 3.795, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379690479918604e-05, + "loss": 3.7914, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378851885167552e-05, + "loss": 3.8039, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378014928296873e-05, + "loss": 3.7993, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377176333545821e-05, + "loss": 3.7962, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376337738794769e-05, + "loss": 3.7931, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375499144043717e-05, + "loss": 3.7962, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.9026734828948975, + "eval_runtime": 308.8515, + "eval_samples_per_second": 1235.516, + "eval_steps_per_second": 38.611, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374662187173038e-05, + "loss": 3.7904, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3738235924219865e-05, + "loss": 3.7898, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.3729849976709345e-05, + "loss": 3.7947, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721464029198824e-05, + "loss": 3.7913, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.3713094460492034e-05, + "loss": 3.8061, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.3704708512981514e-05, + "loss": 3.7901, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.3696322565470993e-05, + "loss": 3.782, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.3687936617960473e-05, + "loss": 3.7797, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.3679550670449953e-05, + "loss": 3.7974, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367118110174316e-05, + "loss": 3.7947, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366279515423264e-05, + "loss": 3.7845, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365440920672212e-05, + "loss": 3.7947, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364603963801533e-05, + "loss": 3.7902, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363765369050482e-05, + "loss": 3.7874, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.36292677429943e-05, + "loss": 3.7812, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362088179548378e-05, + "loss": 3.7767, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361249584797326e-05, + "loss": 3.7817, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360410990046274e-05, + "loss": 3.7784, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359572395295222e-05, + "loss": 3.7915, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.35873380054417e-05, + "loss": 3.7966, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357896843673491e-05, + "loss": 3.7927, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357058248922439e-05, + "loss": 3.7845, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356219654171387e-05, + "loss": 3.7827, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355381059420335e-05, + "loss": 3.7842, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354542464669283e-05, + "loss": 3.7781, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3537055077986036e-05, + "loss": 3.7833, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528669130475516e-05, + "loss": 3.7686, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3520283182964996e-05, + "loss": 3.7892, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351189723545448e-05, + "loss": 3.7761, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350352766674769e-05, + "loss": 3.7701, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349514171923717e-05, + "loss": 3.7807, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348675577172665e-05, + "loss": 3.7865, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347836982421613e-05, + "loss": 3.7925, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347000025550934e-05, + "loss": 3.7852, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346161430799882e-05, + "loss": 3.7754, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.34532283604883e-05, + "loss": 3.7884, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344484241297778e-05, + "loss": 3.7849, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343647284427099e-05, + "loss": 3.7662, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342808689676047e-05, + "loss": 3.7681, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341970094924995e-05, + "loss": 3.7696, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411315001739436e-05, + "loss": 3.7761, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402945433032645e-05, + "loss": 3.7842, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394559485522125e-05, + "loss": 3.7763, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3386173538011605e-05, + "loss": 3.7711, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377787590501085e-05, + "loss": 3.7818, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369418021794294e-05, + "loss": 3.7742, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3361032074283774e-05, + "loss": 3.7871, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352646126773254e-05, + "loss": 3.7653, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3344260179262734e-05, + "loss": 3.7481, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333589061055594e-05, + "loss": 3.7879, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332750466304542e-05, + "loss": 3.78, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.33191187155349e-05, + "loss": 3.7795, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331073276802439e-05, + "loss": 3.7731, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.33023631993176e-05, + "loss": 3.7691, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329397725180708e-05, + "loss": 3.7623, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328559130429656e-05, + "loss": 3.7709, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327720535678604e-05, + "loss": 3.7653, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326883578807925e-05, + "loss": 3.7707, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326044984056873e-05, + "loss": 3.7753, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325206389305821e-05, + "loss": 3.7693, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324367794554768e-05, + "loss": 3.7631, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.32353083768409e-05, + "loss": 3.7788, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322692242933038e-05, + "loss": 3.7602, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321853648181986e-05, + "loss": 3.7598, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321015053430934e-05, + "loss": 3.7749, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320178096560255e-05, + "loss": 3.7787, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319339501809203e-05, + "loss": 3.7525, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185009070581506e-05, + "loss": 3.7659, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176623123070986e-05, + "loss": 3.7504, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.31682535543642e-05, + "loss": 3.7706, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315986760685368e-05, + "loss": 3.7715, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151481659343155e-05, + "loss": 3.7686, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143095711832635e-05, + "loss": 3.7697, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313472614312585e-05, + "loss": 3.7721, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312634019561533e-05, + "loss": 3.7811, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311795424810481e-05, + "loss": 3.7594, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310956830059429e-05, + "loss": 3.7747, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3101198731887506e-05, + "loss": 3.774, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309281278437698e-05, + "loss": 3.7512, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308442683686646e-05, + "loss": 3.7731, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307604088935594e-05, + "loss": 3.762, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067671320649155e-05, + "loss": 3.7755, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305928537313863e-05, + "loss": 3.7725, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305089942562811e-05, + "loss": 3.7569, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304251347811759e-05, + "loss": 3.7541, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034143909410804e-05, + "loss": 3.7591, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025757961900284e-05, + "loss": 3.7777, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3017372014389764e-05, + "loss": 3.7601, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008986066879244e-05, + "loss": 3.7616, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300061649817245e-05, + "loss": 3.7604, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299223055066193e-05, + "loss": 3.7656, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298384460315141e-05, + "loss": 3.7581, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297545865564089e-05, + "loss": 3.7445, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296707270813037e-05, + "loss": 3.7626, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295870313942358e-05, + "loss": 3.7691, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295031719191306e-05, + "loss": 3.7694, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294193124440254e-05, + "loss": 3.7491, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293354529689202e-05, + "loss": 3.7557, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292517572818524e-05, + "loss": 3.7599, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291678978067472e-05, + "loss": 3.7633, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.29084038331642e-05, + "loss": 3.7692, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290001788565368e-05, + "loss": 3.7552, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289164831694689e-05, + "loss": 3.7601, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288326236943637e-05, + "loss": 3.7627, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287487642192585e-05, + "loss": 3.7456, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286649047441533e-05, + "loss": 3.7567, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858120905708536e-05, + "loss": 3.7517, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.2849734958198016e-05, + "loss": 3.7638, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.2841349010687496e-05, + "loss": 3.7468, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2832963063176976e-05, + "loss": 3.7616, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282459349447019e-05, + "loss": 3.7519, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281620754695967e-05, + "loss": 3.7567, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280782159944915e-05, + "loss": 3.7556, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279943565193863e-05, + "loss": 3.7584, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279106608323184e-05, + "loss": 3.7576, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278268013572132e-05, + "loss": 3.7698, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277431056701453e-05, + "loss": 3.7607, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276592461950401e-05, + "loss": 3.764, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275753867199349e-05, + "loss": 3.7538, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274915272448297e-05, + "loss": 3.7572, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274076677697245e-05, + "loss": 3.7478, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273238082946193e-05, + "loss": 3.7536, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272399488195141e-05, + "loss": 3.7552, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.2715608934440896e-05, + "loss": 3.7581, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2707239365734105e-05, + "loss": 3.7554, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698853418223585e-05, + "loss": 3.7536, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690467470713065e-05, + "loss": 3.7521, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.2682081523202545e-05, + "loss": 3.7547, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.2673711954495754e-05, + "loss": 3.7505, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2665326006985234e-05, + "loss": 3.7587, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.2656940059474714e-05, + "loss": 3.7528, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.2648554111964194e-05, + "loss": 3.7475, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.26401845432574e-05, + "loss": 3.7346, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263179859574688e-05, + "loss": 3.761, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262341264823636e-05, + "loss": 3.7578, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261502670072584e-05, + "loss": 3.7621, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260664075321533e-05, + "loss": 3.7554, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259827118450854e-05, + "loss": 3.7581, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258988523699802e-05, + "loss": 3.7521, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.25814992894875e-05, + "loss": 3.7658, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257311334197698e-05, + "loss": 3.7474, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256474377327019e-05, + "loss": 3.7531, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255635782575967e-05, + "loss": 3.7508, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254797187824915e-05, + "loss": 3.7504, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253958593073863e-05, + "loss": 3.7608, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253121636203184e-05, + "loss": 3.7516, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252283041452132e-05, + "loss": 3.7601, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.25144444670108e-05, + "loss": 3.7441, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250605851950028e-05, + "loss": 3.7546, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.887089967727661, + "eval_runtime": 307.8401, + "eval_samples_per_second": 1239.575, + "eval_steps_per_second": 38.738, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249767257198976e-05, + "loss": 3.7516, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2489286624479237e-05, + "loss": 3.7463, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480900676968716e-05, + "loss": 3.7506, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472514729458196e-05, + "loss": 3.7488, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464128781947676e-05, + "loss": 3.7626, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455742834437156e-05, + "loss": 3.7466, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447356886926636e-05, + "loss": 3.7428, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2438970939416116e-05, + "loss": 3.7357, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430601370709325e-05, + "loss": 3.7547, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422215423198805e-05, + "loss": 3.7513, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413829475688285e-05, + "loss": 3.7421, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405443528177765e-05, + "loss": 3.7522, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239709033827471e-05, + "loss": 3.7463, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238870439076419e-05, + "loss": 3.7455, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238031844325367e-05, + "loss": 3.7375, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237193249574315e-05, + "loss": 3.7365, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236354654823263e-05, + "loss": 3.7396, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235516060072211e-05, + "loss": 3.7381, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234677465321159e-05, + "loss": 3.7482, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233838870570107e-05, + "loss": 3.7539, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233001913699428e-05, + "loss": 3.7518, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232163318948376e-05, + "loss": 3.7452, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231324724197324e-05, + "loss": 3.7419, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230486129446272e-05, + "loss": 3.7429, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296491725755935e-05, + "loss": 3.7394, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288105778245415e-05, + "loss": 3.7431, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279719830734895e-05, + "loss": 3.7262, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2271333883224375e-05, + "loss": 3.749, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262964314517584e-05, + "loss": 3.7355, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254578367007064e-05, + "loss": 3.729, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246192419496544e-05, + "loss": 3.7385, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237806471986024e-05, + "loss": 3.749, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222943690327923e-05, + "loss": 3.7446, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222105095576871e-05, + "loss": 3.746, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221266500825819e-05, + "loss": 3.7333, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220427906074767e-05, + "loss": 3.7479, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219590949204089e-05, + "loss": 3.7417, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218752354453037e-05, + "loss": 3.7278, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217913759701985e-05, + "loss": 3.7281, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217075164950933e-05, + "loss": 3.7294, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216238208080254e-05, + "loss": 3.7349, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215399613329202e-05, + "loss": 3.743, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.21456101857815e-05, + "loss": 3.7347, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213722423827098e-05, + "loss": 3.7332, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128854669564186e-05, + "loss": 3.7391, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120468722053666e-05, + "loss": 3.7329, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112082774543146e-05, + "loss": 3.7463, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103696827032626e-05, + "loss": 3.7298, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209532725832584e-05, + "loss": 3.7056, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208694131081532e-05, + "loss": 3.75, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.20785553633048e-05, + "loss": 3.7395, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207016941579428e-05, + "loss": 3.7404, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206179984708749e-05, + "loss": 3.733, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205341389957697e-05, + "loss": 3.7304, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204502795206645e-05, + "loss": 3.7226, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203664200455593e-05, + "loss": 3.7324, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202827243584914e-05, + "loss": 3.728, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201988648833862e-05, + "loss": 3.7291, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.20115005408281e-05, + "loss": 3.735, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200311459331758e-05, + "loss": 3.7317, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994745024610796e-05, + "loss": 3.7219, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986359077100276e-05, + "loss": 3.7394, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1977973129589756e-05, + "loss": 3.7196, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969587182079236e-05, + "loss": 3.724, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1961217613372445e-05, + "loss": 3.7359, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952831665861925e-05, + "loss": 3.7377, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1944445718351405e-05, + "loss": 3.7147, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1936059770840885e-05, + "loss": 3.7237, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927690202134094e-05, + "loss": 3.7127, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919304254623574e-05, + "loss": 3.7321, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910918307113054e-05, + "loss": 3.7334, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902532359602534e-05, + "loss": 3.7307, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189416279089575e-05, + "loss": 3.7282, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188577684338523e-05, + "loss": 3.7315, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187739089587471e-05, + "loss": 3.7431, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186900494836419e-05, + "loss": 3.7237, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.18606353796574e-05, + "loss": 3.7344, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185224943214688e-05, + "loss": 3.7345, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184386348463636e-05, + "loss": 3.7154, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183549391592957e-05, + "loss": 3.7306, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182710796841905e-05, + "loss": 3.7294, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181872202090853e-05, + "loss": 3.7328, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181033607339801e-05, + "loss": 3.736, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180196650469122e-05, + "loss": 3.7184, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.17935805571807e-05, + "loss": 3.7178, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178519460967018e-05, + "loss": 3.7236, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177680866215966e-05, + "loss": 3.7336, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176843909345287e-05, + "loss": 3.7235, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176005314594235e-05, + "loss": 3.7243, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175166719843183e-05, + "loss": 3.7245, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174328125092131e-05, + "loss": 3.7296, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734895303410785e-05, + "loss": 3.7187, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726525734704e-05, + "loss": 3.7059, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171813978719348e-05, + "loss": 3.7256, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170975383968296e-05, + "loss": 3.729, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170138427097618e-05, + "loss": 3.7324, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169299832346566e-05, + "loss": 3.7122, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168461237595514e-05, + "loss": 3.718, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167622642844461e-05, + "loss": 3.7226, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667856859737826e-05, + "loss": 3.7257, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659470912227306e-05, + "loss": 3.7318, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651084964716786e-05, + "loss": 3.7215, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164269901720626e-05, + "loss": 3.7209, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634329448499475e-05, + "loss": 3.726, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625943500988955e-05, + "loss": 3.7086, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617557553478435e-05, + "loss": 3.7204, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609171605967915e-05, + "loss": 3.7104, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160080203726113e-05, + "loss": 3.7295, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159241608975061e-05, + "loss": 3.71, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.1584030142240084e-05, + "loss": 3.7235, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575644194729564e-05, + "loss": 3.7154, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156727462602278e-05, + "loss": 3.7165, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155888867851226e-05, + "loss": 3.7211, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155050273100173e-05, + "loss": 3.7226, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154211678349121e-05, + "loss": 3.7204, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153374721478443e-05, + "loss": 3.7334, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152537764607764e-05, + "loss": 3.7198, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151699169856712e-05, + "loss": 3.735, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.15086057510566e-05, + "loss": 3.7177, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1500219803546084e-05, + "loss": 3.7171, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149183385603556e-05, + "loss": 3.7156, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148344790852504e-05, + "loss": 3.714, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147506196101452e-05, + "loss": 3.7147, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466676013504e-05, + "loss": 3.723, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458306444797206e-05, + "loss": 3.7168, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449920497286686e-05, + "loss": 3.7207, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441534549776166e-05, + "loss": 3.7178, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433148602265646e-05, + "loss": 3.7166, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424779033558855e-05, + "loss": 3.7183, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416393086048335e-05, + "loss": 3.7168, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140800713853782e-05, + "loss": 3.7139, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.13996211910273e-05, + "loss": 3.7144, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139125162232051e-05, + "loss": 3.6986, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138286567480999e-05, + "loss": 3.7236, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137447972729947e-05, + "loss": 3.7221, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136609377978895e-05, + "loss": 3.7254, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135772421108216e-05, + "loss": 3.7157, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134933826357164e-05, + "loss": 3.7231, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134095231606112e-05, + "loss": 3.7197, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.13325663685506e-05, + "loss": 3.7293, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132419679984381e-05, + "loss": 3.7099, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131581085233329e-05, + "loss": 3.7149, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307424904822776e-05, + "loss": 3.7159, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299038957312256e-05, + "loss": 3.7167, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290669388605465e-05, + "loss": 3.7199, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1282283441094945e-05, + "loss": 3.7187, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273897493584425e-05, + "loss": 3.7236, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265511546073905e-05, + "loss": 3.7086, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.1257141977367114e-05, + "loss": 3.7204, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.877600908279419, + "eval_runtime": 304.6484, + "eval_samples_per_second": 1252.562, + "eval_steps_per_second": 39.143, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.1248756029856594e-05, + "loss": 3.7075, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1240370082346074e-05, + "loss": 3.7146, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1231984134835553e-05, + "loss": 3.7098, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122361456612876e-05, + "loss": 3.7136, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121522861861824e-05, + "loss": 3.7255, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120684267110773e-05, + "loss": 3.7144, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119845672359721e-05, + "loss": 3.7071, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119008715489042e-05, + "loss": 3.7053, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.11817012073799e-05, + "loss": 3.712, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117331525986938e-05, + "loss": 3.7195, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116492931235886e-05, + "loss": 3.7057, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115655974365207e-05, + "loss": 3.7155, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148190174945276e-05, + "loss": 3.7173, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139804227434756e-05, + "loss": 3.7067, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1131418279924236e-05, + "loss": 3.7047, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1123032332413716e-05, + "loss": 3.7005, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114646384903196e-05, + "loss": 3.7048, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110626043739268e-05, + "loss": 3.7043, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109787448988216e-05, + "loss": 3.7098, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108948854237164e-05, + "loss": 3.7219, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108111897366485e-05, + "loss": 3.7185, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107273302615433e-05, + "loss": 3.7095, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106434707864381e-05, + "loss": 3.7053, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105596113113329e-05, + "loss": 3.7073, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.10475915624265e-05, + "loss": 3.7079, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103920561491598e-05, + "loss": 3.707, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103081966740546e-05, + "loss": 3.693, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102243371989494e-05, + "loss": 3.7146, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101406415118815e-05, + "loss": 3.7027, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005678203677637e-05, + "loss": 3.6956, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0997292256167117e-05, + "loss": 3.6982, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988906308656597e-05, + "loss": 3.7172, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980536739949806e-05, + "loss": 3.7127, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0972150792439286e-05, + "loss": 3.7098, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963764844928766e-05, + "loss": 3.6995, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955378897418245e-05, + "loss": 3.7102, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0947009328711455e-05, + "loss": 3.7108, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938623381200935e-05, + "loss": 3.6952, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930237433690414e-05, + "loss": 3.693, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921851486179894e-05, + "loss": 3.6942, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913481917473104e-05, + "loss": 3.7015, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0905095969962583e-05, + "loss": 3.7053, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089671002245207e-05, + "loss": 3.7054, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088834045374528e-05, + "loss": 3.6982, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087995450623476e-05, + "loss": 3.7049, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087156855872424e-05, + "loss": 3.6999, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086318261121372e-05, + "loss": 3.7109, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085481304250693e-05, + "loss": 3.6997, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084642709499641e-05, + "loss": 3.6725, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083804114748589e-05, + "loss": 3.7126, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082965519997537e-05, + "loss": 3.7068, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082128563126858e-05, + "loss": 3.7117, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081289968375806e-05, + "loss": 3.6992, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080451373624754e-05, + "loss": 3.6938, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.0796127788737024e-05, + "loss": 3.6925, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078775822003023e-05, + "loss": 3.699, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077937227251971e-05, + "loss": 3.6988, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077098632500919e-05, + "loss": 3.6915, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076260037749867e-05, + "loss": 3.7027, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075421442998815e-05, + "loss": 3.7007, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074584486128136e-05, + "loss": 3.6853, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073745891377084e-05, + "loss": 3.7064, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072907296626032e-05, + "loss": 3.6882, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072070339755353e-05, + "loss": 3.6874, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071231745004301e-05, + "loss": 3.7012, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070393150253249e-05, + "loss": 3.7061, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069554555502198e-05, + "loss": 3.6826, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068717598631519e-05, + "loss": 3.6927, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.0678790038804667e-05, + "loss": 3.6794, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0670404091294147e-05, + "loss": 3.6979, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0662018143783627e-05, + "loss": 3.7012, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653632196273106e-05, + "loss": 3.6977, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0645262627566316e-05, + "loss": 3.6936, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636876680055796e-05, + "loss": 3.6993, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0628490732545275e-05, + "loss": 3.713, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620121163838485e-05, + "loss": 3.687, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611735216327965e-05, + "loss": 3.7052, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603349268817444e-05, + "loss": 3.7023, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059496332130693e-05, + "loss": 3.6846, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058659375260014e-05, + "loss": 3.6997, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057822418389335e-05, + "loss": 3.6965, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056983823638283e-05, + "loss": 3.7001, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056145228887231e-05, + "loss": 3.704, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055306634136179e-05, + "loss": 3.6827, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054468039385127e-05, + "loss": 3.6862, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053629444634075e-05, + "loss": 3.6883, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052790849883023e-05, + "loss": 3.7011, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.05195225513197e-05, + "loss": 3.6903, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051115298261292e-05, + "loss": 3.695, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.05027670351024e-05, + "loss": 3.6942, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049438108759188e-05, + "loss": 3.69, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.0486011518885094e-05, + "loss": 3.6902, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.0477625571374574e-05, + "loss": 3.6734, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0469239623864054e-05, + "loss": 3.6913, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046085367635353e-05, + "loss": 3.6942, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045248410764674e-05, + "loss": 3.703, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044409816013622e-05, + "loss": 3.6818, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.04357122126257e-05, + "loss": 3.6852, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427326265115176e-05, + "loss": 3.6921, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041895669640839e-05, + "loss": 3.6917, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041057074889787e-05, + "loss": 3.6963, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040218480138735e-05, + "loss": 3.6939, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039379885387683e-05, + "loss": 3.6904, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038542928517005e-05, + "loss": 3.6898, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037704333765953e-05, + "loss": 3.6811, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.0368657390149e-05, + "loss": 3.685, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036027144263848e-05, + "loss": 3.6809, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.03519018739317e-05, + "loss": 3.6989, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0343515926421177e-05, + "loss": 3.678, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033512997891065e-05, + "loss": 3.6906, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032674403140013e-05, + "loss": 3.6851, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0318374462693346e-05, + "loss": 3.6916, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0309988515182826e-05, + "loss": 3.6867, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301602567672305e-05, + "loss": 3.6913, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0293216620161785e-05, + "loss": 3.6884, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284847051455e-05, + "loss": 3.7031, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027647748274821e-05, + "loss": 3.6857, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026809153523769e-05, + "loss": 3.702, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025970558772717e-05, + "loss": 3.6859, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025131964021665e-05, + "loss": 3.6868, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242933692706123e-05, + "loss": 3.6839, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234547745195603e-05, + "loss": 3.6853, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022616179768508e-05, + "loss": 3.6825, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021777585017456e-05, + "loss": 3.6889, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020940628146778e-05, + "loss": 3.6826, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020102033395726e-05, + "loss": 3.6918, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019263438644674e-05, + "loss": 3.6931, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018424843893622e-05, + "loss": 3.684, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017587887022943e-05, + "loss": 3.6883, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016749292271891e-05, + "loss": 3.6923, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015910697520839e-05, + "loss": 3.6805, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015072102769787e-05, + "loss": 3.6864, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014235145899108e-05, + "loss": 3.6661, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013396551148056e-05, + "loss": 3.6937, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012557956397004e-05, + "loss": 3.6923, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011719361645952e-05, + "loss": 3.6948, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010882404775273e-05, + "loss": 3.6833, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010043810024221e-05, + "loss": 3.6915, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009205215273169e-05, + "loss": 3.6871, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008366620522117e-05, + "loss": 3.6958, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007529663651438e-05, + "loss": 3.6804, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006691068900386e-05, + "loss": 3.6839, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005852474149334e-05, + "loss": 3.6844, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005013879398282e-05, + "loss": 3.6893, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004176922527603e-05, + "loss": 3.6867, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003338327776551e-05, + "loss": 3.6865, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002499733025499e-05, + "loss": 3.6965, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001661138274447e-05, + "loss": 3.6764, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0008241814037687e-05, + "loss": 3.6945, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.869957447052002, + "eval_runtime": 302.5568, + "eval_samples_per_second": 1261.221, + "eval_steps_per_second": 39.414, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999855866527166e-05, + "loss": 3.6818, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9991469919016646e-05, + "loss": 3.6819, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9983083971506126e-05, + "loss": 3.6848, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974698023995606e-05, + "loss": 3.6834, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.9966312076485086e-05, + "loss": 3.696, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.9957926128974566e-05, + "loss": 3.6834, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.9949540181464046e-05, + "loss": 3.6773, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9941154233953526e-05, + "loss": 3.6754, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932784665246735e-05, + "loss": 3.682, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9924398717736215e-05, + "loss": 3.6924, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9916012770225695e-05, + "loss": 3.6789, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9907626822715175e-05, + "loss": 3.684, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989927363281212e-05, + "loss": 3.6873, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.98908876853016e-05, + "loss": 3.6761, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988250173779108e-05, + "loss": 3.6749, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987411579028056e-05, + "loss": 3.6711, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986572984277004e-05, + "loss": 3.6771, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985734389525952e-05, + "loss": 3.6715, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848957947749e-05, + "loss": 3.6811, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984057200023848e-05, + "loss": 3.6907, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983220243153169e-05, + "loss": 3.6869, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982381648402117e-05, + "loss": 3.6766, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981543053651065e-05, + "loss": 3.6771, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980704458900013e-05, + "loss": 3.6787, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979867502029334e-05, + "loss": 3.6754, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790289072782825e-05, + "loss": 3.6787, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781903125272305e-05, + "loss": 3.6647, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773517177761785e-05, + "loss": 3.6862, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9765147609054994e-05, + "loss": 3.6756, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9756761661544474e-05, + "loss": 3.6626, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748375714033954e-05, + "loss": 3.6689, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973998976652343e-05, + "loss": 3.6878, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973162019781664e-05, + "loss": 3.6841, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972323425030612e-05, + "loss": 3.6821, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.97148483027956e-05, + "loss": 3.6724, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9706462355285076e-05, + "loss": 3.6741, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969809278657829e-05, + "loss": 3.687, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968970683906778e-05, + "loss": 3.6655, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968132089155726e-05, + "loss": 3.6631, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967295132285047e-05, + "loss": 3.667, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966456537533995e-05, + "loss": 3.6689, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965617942782943e-05, + "loss": 3.6794, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.96477934803189e-05, + "loss": 3.671, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9639423911612116e-05, + "loss": 3.6747, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9631037964101596e-05, + "loss": 3.6717, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9622652016591076e-05, + "loss": 3.6688, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961426606908055e-05, + "loss": 3.6863, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605896500373765e-05, + "loss": 3.6692, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959752693166698e-05, + "loss": 3.6472, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958914098415646e-05, + "loss": 3.6824, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958075503664594e-05, + "loss": 3.6748, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957236908913542e-05, + "loss": 3.6827, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.95639831416249e-05, + "loss": 3.6717, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9555597194114374e-05, + "loss": 3.6645, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547211246603854e-05, + "loss": 3.6633, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953884167789707e-05, + "loss": 3.6685, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953045573038655e-05, + "loss": 3.6743, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952206978287602e-05, + "loss": 3.6585, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.95136838353655e-05, + "loss": 3.6785, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950531426665872e-05, + "loss": 3.6708, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.94969283191482e-05, + "loss": 3.6586, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948854237163768e-05, + "loss": 3.676, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.948015642412716e-05, + "loss": 3.659, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471786855420375e-05, + "loss": 3.6594, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946340090790985e-05, + "loss": 3.6717, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945501496039933e-05, + "loss": 3.6782, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944662901288881e-05, + "loss": 3.6494, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438259444182024e-05, + "loss": 3.6678, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.94298734966715e-05, + "loss": 3.6536, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942148754916098e-05, + "loss": 3.6688, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941311798045419e-05, + "loss": 3.6741, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940473203294367e-05, + "loss": 3.6653, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939634608543315e-05, + "loss": 3.6711, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938796013792263e-05, + "loss": 3.6671, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937957419041211e-05, + "loss": 3.6867, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937118824290159e-05, + "loss": 3.6563, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936280229539107e-05, + "loss": 3.6759, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935443272668428e-05, + "loss": 3.6713, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934604677917376e-05, + "loss": 3.6623, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933766083166324e-05, + "loss": 3.6703, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932929126295645e-05, + "loss": 3.6692, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932090531544593e-05, + "loss": 3.6699, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931251936793541e-05, + "loss": 3.6766, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930413342042489e-05, + "loss": 3.6558, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929574747291438e-05, + "loss": 3.6615, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928736152540386e-05, + "loss": 3.6618, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927897557789334e-05, + "loss": 3.6762, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927058963038282e-05, + "loss": 3.6587, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.9262220061676026e-05, + "loss": 3.6654, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.9253834114165506e-05, + "loss": 3.6692, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9245448166654986e-05, + "loss": 3.6636, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.9237062219144466e-05, + "loss": 3.6628, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.9228692650437675e-05, + "loss": 3.6472, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9220323081730884e-05, + "loss": 3.6614, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211937134220364e-05, + "loss": 3.667, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9203551186709844e-05, + "loss": 3.6725, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9195165239199324e-05, + "loss": 3.6554, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918677929168881e-05, + "loss": 3.6585, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917839334417829e-05, + "loss": 3.6614, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.917000739666777e-05, + "loss": 3.6672, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916163782796098e-05, + "loss": 3.6682, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915325188045046e-05, + "loss": 3.666, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914486593293994e-05, + "loss": 3.6674, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913647998542942e-05, + "loss": 3.6595, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912811041672263e-05, + "loss": 3.6566, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911972446921211e-05, + "loss": 3.6555, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911133852170159e-05, + "loss": 3.6569, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910295257419107e-05, + "loss": 3.6716, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909458300548428e-05, + "loss": 3.6501, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086197057973764e-05, + "loss": 3.6601, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9077811110463244e-05, + "loss": 3.6533, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9069425162952724e-05, + "loss": 3.6653, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9061055594245933e-05, + "loss": 3.6602, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905266964673541e-05, + "loss": 3.6636, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904428369922489e-05, + "loss": 3.6616, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903589775171437e-05, + "loss": 3.6745, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902752818300758e-05, + "loss": 3.6617, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901915861430079e-05, + "loss": 3.6709, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901077266679027e-05, + "loss": 3.6611, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900238671927975e-05, + "loss": 3.6608, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899400077176923e-05, + "loss": 3.6583, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898561482425872e-05, + "loss": 3.6584, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.89772288767482e-05, + "loss": 3.6536, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896884292923768e-05, + "loss": 3.662, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896047336053089e-05, + "loss": 3.6568, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895208741302037e-05, + "loss": 3.6651, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943717844313576e-05, + "loss": 3.6602, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8935331896803056e-05, + "loss": 3.6602, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926945949292536e-05, + "loss": 3.6599, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8918560001782016e-05, + "loss": 3.6662, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8910174054271496e-05, + "loss": 3.6512, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8901788106760976e-05, + "loss": 3.6599, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.8893402159250456e-05, + "loss": 3.6365, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.8885016211739936e-05, + "loss": 3.668, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887664664303315e-05, + "loss": 3.6652, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886826069552263e-05, + "loss": 3.6708, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859874748012105e-05, + "loss": 3.6537, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8851488800501585e-05, + "loss": 3.6663, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.88431192317948e-05, + "loss": 3.6597, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883473328428428e-05, + "loss": 3.674, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.8826347336773754e-05, + "loss": 3.6524, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817961389263234e-05, + "loss": 3.6567, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880959182055645e-05, + "loss": 3.6563, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880120587304592e-05, + "loss": 3.6691, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879281992553541e-05, + "loss": 3.6554, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878443397802489e-05, + "loss": 3.658, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8776064409318105e-05, + "loss": 3.6671, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876767846180758e-05, + "loss": 3.6542, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875929251429706e-05, + "loss": 3.6672, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8668715953826904, + "eval_runtime": 304.3634, + "eval_samples_per_second": 1253.735, + "eval_steps_per_second": 39.18, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750922945590274e-05, + "loss": 3.6467, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742536998079754e-05, + "loss": 3.6582, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873415105056923e-05, + "loss": 3.6532, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872576510305871e-05, + "loss": 3.6606, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871737915554819e-05, + "loss": 3.6748, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870899320803767e-05, + "loss": 3.6546, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870060726052715e-05, + "loss": 3.6498, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869222131301663e-05, + "loss": 3.6487, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868385174430984e-05, + "loss": 3.6573, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867546579679932e-05, + "loss": 3.6642, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.86670798492888e-05, + "loss": 3.6524, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865869390177828e-05, + "loss": 3.6582, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865034071187522e-05, + "loss": 3.6625, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.86419547643647e-05, + "loss": 3.6511, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863356881685418e-05, + "loss": 3.648, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862518286934366e-05, + "loss": 3.6431, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861679692183314e-05, + "loss": 3.6541, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860841097432262e-05, + "loss": 3.6491, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.86000250268121e-05, + "loss": 3.6492, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859163907930158e-05, + "loss": 3.6636, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.85832695105948e-05, + "loss": 3.6622, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857488356308428e-05, + "loss": 3.6539, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856649761557376e-05, + "loss": 3.6501, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855811166806324e-05, + "loss": 3.6531, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8549742099356446e-05, + "loss": 3.653, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.8541372530649655e-05, + "loss": 3.6513, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.8532986583139135e-05, + "loss": 3.6375, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.8524600635628615e-05, + "loss": 3.6572, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.8516214688118095e-05, + "loss": 3.6545, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507828740607575e-05, + "loss": 3.6376, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8499442793097055e-05, + "loss": 3.6455, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8491056845586535e-05, + "loss": 3.6563, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.8482670898076015e-05, + "loss": 3.6557, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847430132936923e-05, + "loss": 3.6571, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846591538185871e-05, + "loss": 3.6503, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845752943434819e-05, + "loss": 3.6452, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844914348683767e-05, + "loss": 3.6645, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844077391813088e-05, + "loss": 3.6377, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843238797062036e-05, + "loss": 3.6374, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842400202310984e-05, + "loss": 3.6402, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841561607559932e-05, + "loss": 3.6453, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840724650689253e-05, + "loss": 3.6495, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839886055938201e-05, + "loss": 3.6469, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839047461187149e-05, + "loss": 3.6505, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838208866436097e-05, + "loss": 3.6469, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373719095654184e-05, + "loss": 3.6437, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365333148143664e-05, + "loss": 3.6559, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356947200633144e-05, + "loss": 3.6493, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348561253122624e-05, + "loss": 3.6247, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834019168441583e-05, + "loss": 3.6555, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833180573690531e-05, + "loss": 3.651, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832341978939479e-05, + "loss": 3.6595, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831503384188427e-05, + "loss": 3.6449, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830664789437375e-05, + "loss": 3.6404, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829827832566696e-05, + "loss": 3.6359, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828989237815644e-05, + "loss": 3.6425, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828150643064592e-05, + "loss": 3.6464, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.82731204831354e-05, + "loss": 3.6343, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826473453562489e-05, + "loss": 3.6502, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825634858811436e-05, + "loss": 3.6469, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824796264060384e-05, + "loss": 3.6358, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823957669309332e-05, + "loss": 3.6472, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823120712438653e-05, + "loss": 3.6351, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822282117687601e-05, + "loss": 3.6378, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821443522936549e-05, + "loss": 3.6413, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820604928185497e-05, + "loss": 3.6541, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819767971314818e-05, + "loss": 3.6299, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818929376563766e-05, + "loss": 3.6452, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818090781812714e-05, + "loss": 3.6247, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172521870616626e-05, + "loss": 3.6465, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8164152301909835e-05, + "loss": 3.648, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155766354399315e-05, + "loss": 3.6451, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8147380406888795e-05, + "loss": 3.6423, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138994459378275e-05, + "loss": 3.6456, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8130608511867755e-05, + "loss": 3.6584, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.8122222564357235e-05, + "loss": 3.6353, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.8113852995650444e-05, + "loss": 3.6518, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.8105467048139924e-05, + "loss": 3.6406, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.8097081100629404e-05, + "loss": 3.6393, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.8088695153118884e-05, + "loss": 3.6451, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808032558441209e-05, + "loss": 3.641, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807193963690158e-05, + "loss": 3.6481, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806355368939106e-05, + "loss": 3.6558, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805516774188054e-05, + "loss": 3.6276, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804678179437002e-05, + "loss": 3.6374, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.80383958468595e-05, + "loss": 3.6361, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.803000989934898e-05, + "loss": 3.6499, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802162395183846e-05, + "loss": 3.6343, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801325438313167e-05, + "loss": 3.6448, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800486843562115e-05, + "loss": 3.6408, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799648248811063e-05, + "loss": 3.6397, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798811291940384e-05, + "loss": 3.6351, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797972697189332e-05, + "loss": 3.6274, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.79713410243828e-05, + "loss": 3.6334, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796295507687228e-05, + "loss": 3.6444, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954569129361764e-05, + "loss": 3.6514, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946183181851244e-05, + "loss": 3.6281, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793779723434072e-05, + "loss": 3.635, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929427665633933e-05, + "loss": 3.6376, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7921041718123413e-05, + "loss": 3.6392, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912655770612893e-05, + "loss": 3.6419, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904269823102367e-05, + "loss": 3.6417, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895883875591847e-05, + "loss": 3.6422, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7887497928081326e-05, + "loss": 3.6344, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7879111980570806e-05, + "loss": 3.6374, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7870726033060286e-05, + "loss": 3.6275, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.78623564643535e-05, + "loss": 3.6339, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785397051684298e-05, + "loss": 3.6439, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784558456933246e-05, + "loss": 3.6315, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783721500062567e-05, + "loss": 3.6357, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782882905311515e-05, + "loss": 3.6296, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782044310560463e-05, + "loss": 3.6389, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781205715809411e-05, + "loss": 3.6374, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780367121058359e-05, + "loss": 3.6387, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779528526307307e-05, + "loss": 3.6396, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778691569436628e-05, + "loss": 3.653, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777852974685576e-05, + "loss": 3.6368, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777014379934524e-05, + "loss": 3.6426, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776175785183472e-05, + "loss": 3.643, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.77533719043242e-05, + "loss": 3.6309, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774498595681368e-05, + "loss": 3.638, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773660000930317e-05, + "loss": 3.629, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772821406179265e-05, + "loss": 3.6312, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719844493085856e-05, + "loss": 3.6364, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7711458545575336e-05, + "loss": 3.6355, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.7703072598064816e-05, + "loss": 3.6397, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.7694703029358025e-05, + "loss": 3.6359, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.7686317081847505e-05, + "loss": 3.6411, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.7677931134336985e-05, + "loss": 3.6309, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.7669545186826465e-05, + "loss": 3.6434, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.7661159239315945e-05, + "loss": 3.6302, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.7652773291805424e-05, + "loss": 3.6353, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7644387344294904e-05, + "loss": 3.6116, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7636001396784384e-05, + "loss": 3.6437, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.76276318280776e-05, + "loss": 3.6386, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761924588056708e-05, + "loss": 3.65, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610859933056553e-05, + "loss": 3.6302, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760247398554603e-05, + "loss": 3.6428, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759410441683925e-05, + "loss": 3.6355, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758571846932873e-05, + "loss": 3.6535, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.75773325218182e-05, + "loss": 3.6292, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756894657430768e-05, + "loss": 3.6324, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.75605770056009e-05, + "loss": 3.6322, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755219105809038e-05, + "loss": 3.6436, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754380511057986e-05, + "loss": 3.6328, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753541916306934e-05, + "loss": 3.6325, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.7527049594362554e-05, + "loss": 3.641, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751866364685203e-05, + "loss": 3.636, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751027769934151e-05, + "loss": 3.6407, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8640494346618652, + "eval_runtime": 304.2369, + "eval_samples_per_second": 1254.256, + "eval_steps_per_second": 39.196, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750190813063472e-05, + "loss": 3.6229, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.74935221831242e-05, + "loss": 3.6343, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7485136235613676e-05, + "loss": 3.6332, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476750288103156e-05, + "loss": 3.6352, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7468364340592636e-05, + "loss": 3.6488, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459978393082116e-05, + "loss": 3.6305, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.7451592445571596e-05, + "loss": 3.6306, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744322287686481e-05, + "loss": 3.6266, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743483692935429e-05, + "loss": 3.6309, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742645098184377e-05, + "loss": 3.6375, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741806503433325e-05, + "loss": 3.6349, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740967908682273e-05, + "loss": 3.6338, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740130951811594e-05, + "loss": 3.6392, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739292357060542e-05, + "loss": 3.6253, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.73845376230949e-05, + "loss": 3.625, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737615167558438e-05, + "loss": 3.6171, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736776572807386e-05, + "loss": 3.6319, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735937978056334e-05, + "loss": 3.6251, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735099383305282e-05, + "loss": 3.6264, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.73426078855423e-05, + "loss": 3.6368, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733423831683551e-05, + "loss": 3.6403, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325852369324996e-05, + "loss": 3.6313, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317466421814476e-05, + "loss": 3.6273, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7309080474303956e-05, + "loss": 3.6304, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7300710905597165e-05, + "loss": 3.629, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7292324958086645e-05, + "loss": 3.6293, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7283939010576125e-05, + "loss": 3.6119, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7275553063065605e-05, + "loss": 3.6336, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7267183494358814e-05, + "loss": 3.6315, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7258797546848294e-05, + "loss": 3.6134, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.7250411599337774e-05, + "loss": 3.6227, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7242025651827254e-05, + "loss": 3.6357, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723365608312046e-05, + "loss": 3.6279, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722528651441368e-05, + "loss": 3.6368, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721690056690316e-05, + "loss": 3.6275, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720851461939264e-05, + "loss": 3.6219, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720012867188212e-05, + "loss": 3.6455, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.71917427243716e-05, + "loss": 3.6134, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718335677686108e-05, + "loss": 3.6173, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717497082935056e-05, + "loss": 3.6196, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716658488184004e-05, + "loss": 3.6197, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715821531313325e-05, + "loss": 3.6233, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714982936562273e-05, + "loss": 3.6262, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714144341811221e-05, + "loss": 3.6262, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713305747060168e-05, + "loss": 3.6243, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.71246879018949e-05, + "loss": 3.62, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116301954384384e-05, + "loss": 3.6313, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107916006873863e-05, + "loss": 3.6252, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709953005936334e-05, + "loss": 3.6036, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709116049065655e-05, + "loss": 3.6326, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708277454314603e-05, + "loss": 3.6261, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707438859563551e-05, + "loss": 3.635, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7066002648124986e-05, + "loss": 3.6207, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.70576330794182e-05, + "loss": 3.6209, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704924713190768e-05, + "loss": 3.6115, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704087756320089e-05, + "loss": 3.6168, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703249161569037e-05, + "loss": 3.6276, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702410566817985e-05, + "loss": 3.6143, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701571972066934e-05, + "loss": 3.626, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700733377315881e-05, + "loss": 3.6219, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699894782564829e-05, + "loss": 3.617, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699056187813777e-05, + "loss": 3.6235, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6982192309430986e-05, + "loss": 3.6136, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697380636192046e-05, + "loss": 3.6167, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696542041440994e-05, + "loss": 3.6185, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695703446689942e-05, + "loss": 3.6289, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.69486485193889e-05, + "loss": 3.6097, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694026257187838e-05, + "loss": 3.6226, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693187662436786e-05, + "loss": 3.6036, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692349067685734e-05, + "loss": 3.6225, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915121108150555e-05, + "loss": 3.6233, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906735160640035e-05, + "loss": 3.6251, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.6898349213129515e-05, + "loss": 3.6194, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.6889963265618995e-05, + "loss": 3.6189, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.6881577318108475e-05, + "loss": 3.6373, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873191370597955e-05, + "loss": 3.6128, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6864821801891164e-05, + "loss": 3.6344, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6856435854380644e-05, + "loss": 3.6153, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6848049906870124e-05, + "loss": 3.6149, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.6839663959359604e-05, + "loss": 3.6248, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683129439065281e-05, + "loss": 3.6164, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682290844314229e-05, + "loss": 3.6254, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681452249563177e-05, + "loss": 3.6318, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680613654812126e-05, + "loss": 3.6114, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679775060061074e-05, + "loss": 3.6112, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678936465310022e-05, + "loss": 3.6131, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.67809787055897e-05, + "loss": 3.6258, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677259275807917e-05, + "loss": 3.6136, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676422318937239e-05, + "loss": 3.6241, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675583724186187e-05, + "loss": 3.6185, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674745129435134e-05, + "loss": 3.6185, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673906534684082e-05, + "loss": 3.6124, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673069577813404e-05, + "loss": 3.6051, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672230983062352e-05, + "loss": 3.6089, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6713923883113e-05, + "loss": 3.6225, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670553793560248e-05, + "loss": 3.6263, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669716836689569e-05, + "loss": 3.6077, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668878241938517e-05, + "loss": 3.6123, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6680396471874646e-05, + "loss": 3.6173, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6672010524364126e-05, + "loss": 3.6225, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6663624576853606e-05, + "loss": 3.622, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6655255008146815e-05, + "loss": 3.6158, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.6646869060636295e-05, + "loss": 3.6187, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638483113125775e-05, + "loss": 3.6135, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6630097165615255e-05, + "loss": 3.6119, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6621711218104735e-05, + "loss": 3.6092, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613325270594215e-05, + "loss": 3.615, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604939323083695e-05, + "loss": 3.6175, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596553375573175e-05, + "loss": 3.6092, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658820018567012e-05, + "loss": 3.6108, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.65798142381596e-05, + "loss": 3.6075, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657142829064908e-05, + "loss": 3.6145, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656304234313856e-05, + "loss": 3.6179, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655465639562804e-05, + "loss": 3.6147, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654627044811752e-05, + "loss": 3.6177, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653790087941073e-05, + "loss": 3.6319, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652951493190021e-05, + "loss": 3.6184, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652112898438969e-05, + "loss": 3.618, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651274303687917e-05, + "loss": 3.6192, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650435708936865e-05, + "loss": 3.6106, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649597114185813e-05, + "loss": 3.6196, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6487585194347615e-05, + "loss": 3.6027, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6479199246837095e-05, + "loss": 3.6103, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470829678130304e-05, + "loss": 3.6166, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462443730619784e-05, + "loss": 3.6175, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645407416191299e-05, + "loss": 3.6136, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644568821440247e-05, + "loss": 3.6169, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643730226689195e-05, + "loss": 3.6158, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642891631938143e-05, + "loss": 3.6121, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642053037187091e-05, + "loss": 3.6161, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641216080316412e-05, + "loss": 3.6132, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.64037748556536e-05, + "loss": 3.6108, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639538890814308e-05, + "loss": 3.5926, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638700296063257e-05, + "loss": 3.623, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637861701312205e-05, + "loss": 3.616, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637024744441526e-05, + "loss": 3.6256, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636186149690474e-05, + "loss": 3.6111, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635347554939422e-05, + "loss": 3.6165, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.63450896018837e-05, + "loss": 3.6143, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633670365437318e-05, + "loss": 3.632, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632833408566639e-05, + "loss": 3.6032, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631994813815587e-05, + "loss": 3.6113, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631156219064535e-05, + "loss": 3.6105, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630317624313483e-05, + "loss": 3.6196, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629479029562431e-05, + "loss": 3.6109, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628640434811379e-05, + "loss": 3.6128, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627801840060327e-05, + "loss": 3.613, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269632453092747e-05, + "loss": 3.6202, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261262884385956e-05, + "loss": 3.6177, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.86246395111084, + "eval_runtime": 304.19, + "eval_samples_per_second": 1254.45, + "eval_steps_per_second": 39.202, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625289331567917e-05, + "loss": 3.6056, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624450736816865e-05, + "loss": 3.6103, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236121420658125e-05, + "loss": 3.6125, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.6227735473147605e-05, + "loss": 3.6151, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6219349525637085e-05, + "loss": 3.6226, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.6210963578126565e-05, + "loss": 3.6088, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6202577630616045e-05, + "loss": 3.6129, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619420806190926e-05, + "loss": 3.6041, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618582211439874e-05, + "loss": 3.6066, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617743616688822e-05, + "loss": 3.6164, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.61690502193777e-05, + "loss": 3.6125, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616066427186718e-05, + "loss": 3.6121, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615229470316039e-05, + "loss": 3.6217, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614390875564987e-05, + "loss": 3.5992, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613552280813935e-05, + "loss": 3.6056, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612713686062883e-05, + "loss": 3.5972, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611875091311831e-05, + "loss": 3.6116, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611036496560779e-05, + "loss": 3.6029, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6101995396901e-05, + "loss": 3.6073, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609360944939048e-05, + "loss": 3.6153, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608522350187996e-05, + "loss": 3.6181, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.6076837554369445e-05, + "loss": 3.6118, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068451606858925e-05, + "loss": 3.6047, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6060082038152134e-05, + "loss": 3.6112, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051696090641614e-05, + "loss": 3.6127, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6043310143131094e-05, + "loss": 3.6077, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6034924195620574e-05, + "loss": 3.5934, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602655462691378e-05, + "loss": 3.6101, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601816867940326e-05, + "loss": 3.6091, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600978273189274e-05, + "loss": 3.592, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600139678438222e-05, + "loss": 3.603, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.59930108368717e-05, + "loss": 3.6132, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598464126816491e-05, + "loss": 3.6078, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597625532065439e-05, + "loss": 3.617, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596786937314388e-05, + "loss": 3.6071, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595948342563336e-05, + "loss": 3.6018, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595109747812284e-05, + "loss": 3.6254, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594271153061231e-05, + "loss": 3.5901, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593432558310179e-05, + "loss": 3.597, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592593963559127e-05, + "loss": 3.6022, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591757006688449e-05, + "loss": 3.5995, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5909200498177696e-05, + "loss": 3.6023, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900814550667176e-05, + "loss": 3.6106, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892428603156656e-05, + "loss": 3.6034, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5884042655646136e-05, + "loss": 3.6059, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875656708135616e-05, + "loss": 3.5968, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5867270760625096e-05, + "loss": 3.6089, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858884813114576e-05, + "loss": 3.6072, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850515244407785e-05, + "loss": 3.5832, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842145675701e-05, + "loss": 3.6102, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583375972819048e-05, + "loss": 3.606, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582537378067996e-05, + "loss": 3.6118, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5816987833169434e-05, + "loss": 3.6002, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5808601885658914e-05, + "loss": 3.5992, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5800215938148394e-05, + "loss": 3.5968, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579184636944161e-05, + "loss": 3.5929, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578346042193108e-05, + "loss": 3.6077, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577507447442057e-05, + "loss": 3.5946, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576668852691005e-05, + "loss": 3.605, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575830257939953e-05, + "loss": 3.5995, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574991663188901e-05, + "loss": 3.5996, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574153068437849e-05, + "loss": 3.6003, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.57331611156717e-05, + "loss": 3.5972, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572477516816118e-05, + "loss": 3.5992, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571638922065066e-05, + "loss": 3.5894, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570800327314014e-05, + "loss": 3.6134, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569961732562962e-05, + "loss": 3.5934, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569124775692283e-05, + "loss": 3.5948, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568286180941231e-05, + "loss": 3.5862, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567447586190179e-05, + "loss": 3.5994, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566608991439127e-05, + "loss": 3.6023, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.5657720345684483e-05, + "loss": 3.6056, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649334398173963e-05, + "loss": 3.6018, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5640948450663443e-05, + "loss": 3.5989, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563256250315292e-05, + "loss": 3.6134, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.56241765556424e-05, + "loss": 3.5952, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561580698693561e-05, + "loss": 3.614, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560742103942509e-05, + "loss": 3.5983, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559903509191457e-05, + "loss": 3.5937, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559064914440405e-05, + "loss": 3.6034, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558227957569726e-05, + "loss": 3.5962, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557389362818674e-05, + "loss": 3.6049, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556550768067622e-05, + "loss": 3.6137, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555712173316571e-05, + "loss": 3.5956, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554873578565519e-05, + "loss": 3.5854, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554034983814467e-05, + "loss": 3.594, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553198026943788e-05, + "loss": 3.6036, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552359432192736e-05, + "loss": 3.5965, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551520837441684e-05, + "loss": 3.6012, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550682242690632e-05, + "loss": 3.5989, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.54984364793958e-05, + "loss": 3.5987, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549005053188527e-05, + "loss": 3.592, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5481680963178486e-05, + "loss": 3.5834, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473295015667966e-05, + "loss": 3.5916, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464909068157446e-05, + "loss": 3.5981, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5456523120646926e-05, + "loss": 3.6124, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544815355194014e-05, + "loss": 3.5855, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543976760442962e-05, + "loss": 3.5945, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5431381656919095e-05, + "loss": 3.5981, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5422995709408575e-05, + "loss": 3.599, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5414609761898055e-05, + "loss": 3.6009, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540624019319127e-05, + "loss": 3.5975, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.5397854245680744e-05, + "loss": 3.603, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.5389468298170224e-05, + "loss": 3.5918, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.5381082350659704e-05, + "loss": 3.5927, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5372696403149184e-05, + "loss": 3.5895, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5364310455638664e-05, + "loss": 3.5963, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5355924508128144e-05, + "loss": 3.5987, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.5347538560617623e-05, + "loss": 3.5908, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533918537071457e-05, + "loss": 3.5929, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533079942320405e-05, + "loss": 3.5844, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532241347569353e-05, + "loss": 3.5939, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531402752818301e-05, + "loss": 3.5991, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530564158067249e-05, + "loss": 3.5988, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529725563316197e-05, + "loss": 3.5952, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528888606445518e-05, + "loss": 3.6042, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528050011694466e-05, + "loss": 3.6029, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527211416943414e-05, + "loss": 3.6027, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526372822192362e-05, + "loss": 3.5999, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.52553422744131e-05, + "loss": 3.593, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524695632690258e-05, + "loss": 3.5963, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5238570379392064e-05, + "loss": 3.586, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5230184431881544e-05, + "loss": 3.5912, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522183124197848e-05, + "loss": 3.5956, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521344529446796e-05, + "loss": 3.5964, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520505934695744e-05, + "loss": 3.5958, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519667339944692e-05, + "loss": 3.594, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.51882874519364e-05, + "loss": 3.5976, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517991788322961e-05, + "loss": 3.5919, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517153193571909e-05, + "loss": 3.6008, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516314598820857e-05, + "loss": 3.5942, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515476004069805e-05, + "loss": 3.5944, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514637409318753e-05, + "loss": 3.5699, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513800452448075e-05, + "loss": 3.6036, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512961857697023e-05, + "loss": 3.5936, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121232629459707e-05, + "loss": 3.6066, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5112846681949187e-05, + "loss": 3.5947, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5104477113242396e-05, + "loss": 3.5949, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5096091165731876e-05, + "loss": 3.5976, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5087705218221356e-05, + "loss": 3.6093, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5079319270710836e-05, + "loss": 3.5836, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5070933323200315e-05, + "loss": 3.5942, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5062547375689795e-05, + "loss": 3.5903, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.5054161428179275e-05, + "loss": 3.5967, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.5045791859472484e-05, + "loss": 3.5958, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503740591196197e-05, + "loss": 3.5946, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502901996445145e-05, + "loss": 3.5946, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502063401694093e-05, + "loss": 3.6032, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501226444823414e-05, + "loss": 3.5958, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.862630844116211, + "eval_runtime": 303.7007, + "eval_samples_per_second": 1256.471, + "eval_steps_per_second": 39.266, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500387850072362e-05, + "loss": 3.5949, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.49954925532131e-05, + "loss": 3.5911, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498710660570257e-05, + "loss": 3.5895, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497872065819205e-05, + "loss": 3.5982, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497033471068153e-05, + "loss": 3.5995, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496194876317101e-05, + "loss": 3.5971, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495356281566049e-05, + "loss": 3.5921, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494519324695371e-05, + "loss": 3.581, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493680729944319e-05, + "loss": 3.587, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492842135193267e-05, + "loss": 3.6024, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492003540442215e-05, + "loss": 3.591, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491164945691163e-05, + "loss": 3.59, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490327988820484e-05, + "loss": 3.6059, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489489394069432e-05, + "loss": 3.5809, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.48865079931838e-05, + "loss": 3.5842, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487812204567328e-05, + "loss": 3.5792, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486973609816276e-05, + "loss": 3.5912, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486135015065224e-05, + "loss": 3.5828, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485298058194545e-05, + "loss": 3.5902, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484459463443493e-05, + "loss": 3.5964, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483620868692441e-05, + "loss": 3.5974, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4827822739413893e-05, + "loss": 3.5937, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481943679190337e-05, + "loss": 3.5833, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481106722319658e-05, + "loss": 3.5922, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480268127568606e-05, + "loss": 3.5959, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479429532817554e-05, + "loss": 3.5869, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478590938066502e-05, + "loss": 3.5765, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477753981195823e-05, + "loss": 3.5892, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476915386444771e-05, + "loss": 3.5904, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476076791693719e-05, + "loss": 3.5736, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475238196942667e-05, + "loss": 3.5834, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474401240071988e-05, + "loss": 3.5903, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473562645320936e-05, + "loss": 3.5922, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472724050569884e-05, + "loss": 3.5952, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471885455818833e-05, + "loss": 3.5892, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471046861067781e-05, + "loss": 3.5888, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4702099041971016e-05, + "loss": 3.6013, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.4693713094460496e-05, + "loss": 3.5718, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.4685327146949976e-05, + "loss": 3.5785, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.4676941199439456e-05, + "loss": 3.5868, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.4668571630732665e-05, + "loss": 3.5749, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4660185683222145e-05, + "loss": 3.5866, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.4651799735711625e-05, + "loss": 3.5887, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.4643413788201105e-05, + "loss": 3.5843, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4635027840690585e-05, + "loss": 3.586, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626658271983794e-05, + "loss": 3.5823, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461827232447328e-05, + "loss": 3.5871, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460988637696276e-05, + "loss": 3.5945, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460150042945224e-05, + "loss": 3.5593, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459313086074545e-05, + "loss": 3.5882, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458474491323493e-05, + "loss": 3.5896, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457635896572441e-05, + "loss": 3.5938, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456797301821388e-05, + "loss": 3.5849, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.45596034495071e-05, + "loss": 3.5788, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455121750199658e-05, + "loss": 3.5812, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454283155448606e-05, + "loss": 3.5724, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453444560697553e-05, + "loss": 3.5878, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452605965946502e-05, + "loss": 3.5765, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4517690090758234e-05, + "loss": 3.5906, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4509304143247714e-05, + "loss": 3.5785, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450091819573719e-05, + "loss": 3.5816, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449253224822667e-05, + "loss": 3.5788, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448414630071615e-05, + "loss": 3.5806, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4475776732009357e-05, + "loss": 3.5783, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467390784498836e-05, + "loss": 3.5727, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4459004836988316e-05, + "loss": 3.5908, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450618889477796e-05, + "loss": 3.5813, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442249320771005e-05, + "loss": 3.573, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4433863373260485e-05, + "loss": 3.5689, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442547742574997e-05, + "loss": 3.5846, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441709147823945e-05, + "loss": 3.5804, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440872190953266e-05, + "loss": 3.5896, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440033596202214e-05, + "loss": 3.5785, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439195001451162e-05, + "loss": 3.585, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.43835640670011e-05, + "loss": 3.5929, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437517811949058e-05, + "loss": 3.5782, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436680855078379e-05, + "loss": 3.5929, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435842260327327e-05, + "loss": 3.5811, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435003665576275e-05, + "loss": 3.5747, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434165070825223e-05, + "loss": 3.5859, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433328113954544e-05, + "loss": 3.5785, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4324895192034926e-05, + "loss": 3.5814, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4316509244524406e-05, + "loss": 3.5973, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4308123297013886e-05, + "loss": 3.5805, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4299737349503366e-05, + "loss": 3.5675, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4291351401992846e-05, + "loss": 3.5752, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4282965454482326e-05, + "loss": 3.5837, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4274595885775535e-05, + "loss": 3.583, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4266209938265015e-05, + "loss": 3.5787, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4257823990754495e-05, + "loss": 3.5808, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4249438043243975e-05, + "loss": 3.5825, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4241052095733455e-05, + "loss": 3.5723, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4232682527026664e-05, + "loss": 3.5623, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4224296579516144e-05, + "loss": 3.5734, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4215910632005624e-05, + "loss": 3.5758, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420752468449511e-05, + "loss": 3.5951, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419915511578832e-05, + "loss": 3.5661, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.41907691682778e-05, + "loss": 3.5756, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418238322076728e-05, + "loss": 3.5796, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417399727325676e-05, + "loss": 3.5789, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416561132574624e-05, + "loss": 3.5841, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415724175703945e-05, + "loss": 3.5802, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414885580952893e-05, + "loss": 3.5782, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414046986201841e-05, + "loss": 3.5766, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413208391450789e-05, + "loss": 3.5731, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412369796699737e-05, + "loss": 3.5716, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411532839829058e-05, + "loss": 3.5778, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4106942450780064e-05, + "loss": 3.5812, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4098556503269544e-05, + "loss": 3.573, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409017055575902e-05, + "loss": 3.5723, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408180098705223e-05, + "loss": 3.5696, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407341503954171e-05, + "loss": 3.5741, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406502909203119e-05, + "loss": 3.5785, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056643144520666e-05, + "loss": 3.5807, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048257197010146e-05, + "loss": 3.5758, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403988762830336e-05, + "loss": 3.5839, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403150168079284e-05, + "loss": 3.5873, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4023115733282315e-05, + "loss": 3.5822, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.40147297857718e-05, + "loss": 3.5824, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400636021706501e-05, + "loss": 3.5788, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399797426955449e-05, + "loss": 3.5748, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398958832204397e-05, + "loss": 3.5668, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398120237453345e-05, + "loss": 3.5755, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.3972832805826667e-05, + "loss": 3.5765, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396444685831614e-05, + "loss": 3.5778, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395606091080562e-05, + "loss": 3.5801, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.39476749632951e-05, + "loss": 3.5752, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393928901578458e-05, + "loss": 3.5759, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393091944707779e-05, + "loss": 3.5725, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392253349956727e-05, + "loss": 3.5817, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391414755205675e-05, + "loss": 3.5758, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3905761604546235e-05, + "loss": 3.5774, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897392035839444e-05, + "loss": 3.5543, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3889006088328924e-05, + "loss": 3.579, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3880620140818404e-05, + "loss": 3.58, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3872234193307884e-05, + "loss": 3.5861, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3863848245797364e-05, + "loss": 3.5785, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385547867709057e-05, + "loss": 3.5711, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384709272958005e-05, + "loss": 3.5813, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383870678206953e-05, + "loss": 3.5929, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383032083455901e-05, + "loss": 3.5675, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382193488704849e-05, + "loss": 3.5809, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381354893953797e-05, + "loss": 3.5729, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380516299202745e-05, + "loss": 3.5798, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379679342332067e-05, + "loss": 3.5769, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378840747581015e-05, + "loss": 3.577, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.378002152829963e-05, + "loss": 3.5757, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377163558078911e-05, + "loss": 3.582, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376324963327859e-05, + "loss": 3.5814, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.862931966781616, + "eval_runtime": 452.5375, + "eval_samples_per_second": 843.225, + "eval_steps_per_second": 26.351, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.37548800645718e-05, + "loss": 3.5686, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374649411706128e-05, + "loss": 3.5761, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373810816955076e-05, + "loss": 3.5701, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.372972222204024e-05, + "loss": 3.5819, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.372133627452972e-05, + "loss": 3.5839, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371296670582293e-05, + "loss": 3.5752, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370458075831241e-05, + "loss": 3.5738, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369619481080189e-05, + "loss": 3.5613, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.3687808863291373e-05, + "loss": 3.5714, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367943929458458e-05, + "loss": 3.5825, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367105334707406e-05, + "loss": 3.571, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366266739956354e-05, + "loss": 3.5775, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365428145205302e-05, + "loss": 3.5846, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364591188334623e-05, + "loss": 3.5638, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363752593583571e-05, + "loss": 3.5665, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362913998832519e-05, + "loss": 3.5638, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.362075404081467e-05, + "loss": 3.5737, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.3612368093304145e-05, + "loss": 3.5667, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360399852459736e-05, + "loss": 3.5698, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359561257708684e-05, + "loss": 3.5773, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358722662957633e-05, + "loss": 3.5786, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.35788406820658e-05, + "loss": 3.5763, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.357045473455528e-05, + "loss": 3.5664, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.3562085165848496e-05, + "loss": 3.5708, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.3553699218337976e-05, + "loss": 3.5816, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354531327082745e-05, + "loss": 3.5702, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353692732331693e-05, + "loss": 3.5581, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352854137580641e-05, + "loss": 3.5711, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.352017180709962e-05, + "loss": 3.567, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.35117858595891e-05, + "loss": 3.5606, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350339991207858e-05, + "loss": 3.5647, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.3495013964568065e-05, + "loss": 3.5719, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.3486644395861274e-05, + "loss": 3.5718, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.3478258448350754e-05, + "loss": 3.5783, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.3469872500840234e-05, + "loss": 3.5715, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.3461486553329714e-05, + "loss": 3.5701, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.3453100605819194e-05, + "loss": 3.584, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.3444714658308674e-05, + "loss": 3.5574, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343634508960188e-05, + "loss": 3.5605, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342795914209136e-05, + "loss": 3.5665, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341957319458084e-05, + "loss": 3.5544, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.341118724707032e-05, + "loss": 3.5704, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340281767836353e-05, + "loss": 3.5697, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339443173085302e-05, + "loss": 3.5673, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.33860457833425e-05, + "loss": 3.567, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337765983583198e-05, + "loss": 3.5682, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.336927388832146e-05, + "loss": 3.5662, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.336088794081094e-05, + "loss": 3.5756, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335251837210415e-05, + "loss": 3.5459, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334413242459363e-05, + "loss": 3.5642, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333574647708311e-05, + "loss": 3.5777, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332736052957259e-05, + "loss": 3.5774, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331897458206207e-05, + "loss": 3.5668, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331058863455155e-05, + "loss": 3.558, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.3302219065844756e-05, + "loss": 3.5639, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.3293833118334236e-05, + "loss": 3.5554, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.3285447170823716e-05, + "loss": 3.5708, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.3277061223313196e-05, + "loss": 3.5582, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326867527580268e-05, + "loss": 3.5697, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.326028932829216e-05, + "loss": 3.5644, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325191975958537e-05, + "loss": 3.5664, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324353381207485e-05, + "loss": 3.5602, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323514786456433e-05, + "loss": 3.566, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.3226761917053805e-05, + "loss": 3.5573, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.3218375969543285e-05, + "loss": 3.5529, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.3209990022032765e-05, + "loss": 3.5739, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320162045332598e-05, + "loss": 3.5669, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.3193234505815454e-05, + "loss": 3.5544, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.3184848558304934e-05, + "loss": 3.5515, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317646261079442e-05, + "loss": 3.5649, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316809304208764e-05, + "loss": 3.5635, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315970709457711e-05, + "loss": 3.5757, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315132114706659e-05, + "loss": 3.56, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314293519955607e-05, + "loss": 3.5688, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313456563084928e-05, + "loss": 3.5751, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312617968333876e-05, + "loss": 3.5563, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311779373582824e-05, + "loss": 3.572, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310940778831772e-05, + "loss": 3.5701, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.31010218408072e-05, + "loss": 3.5602, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309263589329668e-05, + "loss": 3.5637, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308426632458989e-05, + "loss": 3.5606, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.3075880377079374e-05, + "loss": 3.5684, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.3067494429568854e-05, + "loss": 3.5783, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.3059108482058334e-05, + "loss": 3.5612, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.3050722534547814e-05, + "loss": 3.5503, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.3042352965841023e-05, + "loss": 3.5592, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.30339670183305e-05, + "loss": 3.5655, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302558107081998e-05, + "loss": 3.5649, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301719512330946e-05, + "loss": 3.5658, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300880917579894e-05, + "loss": 3.5605, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.300043960709215e-05, + "loss": 3.5688, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299205365958163e-05, + "loss": 3.5532, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298366771207111e-05, + "loss": 3.5489, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297528176456059e-05, + "loss": 3.5568, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296691219585381e-05, + "loss": 3.5567, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295852624834329e-05, + "loss": 3.5734, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.295014030083277e-05, + "loss": 3.5587, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294175435332225e-05, + "loss": 3.5564, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293338478461546e-05, + "loss": 3.5652, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292499883710494e-05, + "loss": 3.56, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291661288959442e-05, + "loss": 3.5672, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.29082269420839e-05, + "loss": 3.5655, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289984099457338e-05, + "loss": 3.5589, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289145504706286e-05, + "loss": 3.5577, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.2883085478356066e-05, + "loss": 3.5617, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.2874699530845546e-05, + "loss": 3.553, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.2866313583335026e-05, + "loss": 3.5573, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285792763582451e-05, + "loss": 3.5661, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.284955806711772e-05, + "loss": 3.5564, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.28411721196072e-05, + "loss": 3.5544, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283278617209668e-05, + "loss": 3.5527, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282440022458616e-05, + "loss": 3.5572, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281603065587937e-05, + "loss": 3.5638, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280764470836885e-05, + "loss": 3.5627, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279925876085833e-05, + "loss": 3.5571, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279087281334781e-05, + "loss": 3.569, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278250324464102e-05, + "loss": 3.5686, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.27741172971305e-05, + "loss": 3.5639, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276573134961998e-05, + "loss": 3.5675, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275734540210946e-05, + "loss": 3.5601, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.2748959454598946e-05, + "loss": 3.5568, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274057350708842e-05, + "loss": 3.5515, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.2732203938381635e-05, + "loss": 3.5592, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.2723817990871115e-05, + "loss": 3.5532, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271543204336059e-05, + "loss": 3.5635, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270704609585007e-05, + "loss": 3.5658, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.2698676527143284e-05, + "loss": 3.5631, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2690290579632764e-05, + "loss": 3.5579, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268190463212224e-05, + "loss": 3.5541, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267351868461172e-05, + "loss": 3.5665, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.26651327371012e-05, + "loss": 3.5602, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265676316839441e-05, + "loss": 3.5588, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264837722088389e-05, + "loss": 3.5368, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.263999127337337e-05, + "loss": 3.5614, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.263160532586285e-05, + "loss": 3.5637, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262323575715606e-05, + "loss": 3.5688, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261484980964554e-05, + "loss": 3.5606, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260646386213502e-05, + "loss": 3.5545, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.25980779146245e-05, + "loss": 3.561, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258969196711398e-05, + "loss": 3.5763, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258130601960346e-05, + "loss": 3.5511, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257293645089667e-05, + "loss": 3.5615, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256455050338615e-05, + "loss": 3.5554, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255616455587564e-05, + "loss": 3.5612, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254777860836512e-05, + "loss": 3.5618, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.25393926608546e-05, + "loss": 3.5594, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253102309214781e-05, + "loss": 3.5568, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.2522637144637287e-05, + "loss": 3.5685, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.2514251197126767e-05, + "loss": 3.5614, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.863281488418579, + "eval_runtime": 302.9998, + "eval_samples_per_second": 1259.377, + "eval_steps_per_second": 39.356, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.2505865249616247e-05, + "loss": 3.5527, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.2497495680909456e-05, + "loss": 3.5611, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.2489109733398936e-05, + "loss": 3.5528, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.2480723785888416e-05, + "loss": 3.5648, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.2472337838377895e-05, + "loss": 3.5662, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.2463951890867375e-05, + "loss": 3.5627, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245558232216059e-05, + "loss": 3.5551, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244719637465007e-05, + "loss": 3.5446, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243881042713955e-05, + "loss": 3.554, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.243042447962903e-05, + "loss": 3.5674, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.242205491092224e-05, + "loss": 3.5556, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.241366896341172e-05, + "loss": 3.5571, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.24052830159012e-05, + "loss": 3.5705, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239689706839068e-05, + "loss": 3.5498, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.238851112088016e-05, + "loss": 3.5504, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.238012517336964e-05, + "loss": 3.5452, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237175560466285e-05, + "loss": 3.5547, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236336965715233e-05, + "loss": 3.55, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.235498370964181e-05, + "loss": 3.5553, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234659776213129e-05, + "loss": 3.5577, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.2338228193424505e-05, + "loss": 3.5698, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.2329842245913985e-05, + "loss": 3.5577, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.2321456298403465e-05, + "loss": 3.5509, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.2313070350892945e-05, + "loss": 3.5572, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.2304700782186154e-05, + "loss": 3.5586, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.2296314834675634e-05, + "loss": 3.5555, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.2287928887165114e-05, + "loss": 3.5422, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.2279542939654594e-05, + "loss": 3.5527, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.22711733709478e-05, + "loss": 3.5514, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.226278742343728e-05, + "loss": 3.5443, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.225440147592676e-05, + "loss": 3.5425, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.224601552841624e-05, + "loss": 3.5597, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.223762958090572e-05, + "loss": 3.5533, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.222926001219894e-05, + "loss": 3.5648, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.222087406468842e-05, + "loss": 3.5556, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.22124881171779e-05, + "loss": 3.5538, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220410216966737e-05, + "loss": 3.5633, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.219571622215685e-05, + "loss": 3.5434, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.218734665345007e-05, + "loss": 3.5495, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.217896070593955e-05, + "loss": 3.5455, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.217057475842902e-05, + "loss": 3.5388, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.21621888109185e-05, + "loss": 3.5535, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.2153819242211716e-05, + "loss": 3.5541, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.2145433294701196e-05, + "loss": 3.5496, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.2137047347190676e-05, + "loss": 3.5532, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.2128661399680156e-05, + "loss": 3.5508, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.2120275452169636e-05, + "loss": 3.5558, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.2111889504659116e-05, + "loss": 3.5547, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.2103519935952325e-05, + "loss": 3.5323, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.2095133988441805e-05, + "loss": 3.5506, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.2086748040931285e-05, + "loss": 3.5582, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.2078362093420765e-05, + "loss": 3.5589, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.2069992524713974e-05, + "loss": 3.5506, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.2061606577203454e-05, + "loss": 3.5422, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.2053220629692934e-05, + "loss": 3.5515, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.2044834682182414e-05, + "loss": 3.54, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.203646511347563e-05, + "loss": 3.55, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202807916596511e-05, + "loss": 3.5427, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.201969321845459e-05, + "loss": 3.5565, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.201130727094407e-05, + "loss": 3.55, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.200293770223728e-05, + "loss": 3.5489, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.199455175472676e-05, + "loss": 3.5421, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.198616580721624e-05, + "loss": 3.5495, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.197779623850945e-05, + "loss": 3.5415, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.196941029099893e-05, + "loss": 3.5412, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.196102434348841e-05, + "loss": 3.5538, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.195263839597789e-05, + "loss": 3.5531, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.1944268827271104e-05, + "loss": 3.5407, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.1935882879760584e-05, + "loss": 3.5349, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.1927496932250064e-05, + "loss": 3.5489, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.1919110984739544e-05, + "loss": 3.5495, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.191074141603275e-05, + "loss": 3.5562, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190235546852223e-05, + "loss": 3.5432, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189396952101171e-05, + "loss": 3.5545, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188558357350119e-05, + "loss": 3.5547, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.187719762599067e-05, + "loss": 3.5483, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186882805728388e-05, + "loss": 3.5536, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.186044210977336e-05, + "loss": 3.5499, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185205616226284e-05, + "loss": 3.5501, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184367021475232e-05, + "loss": 3.5454, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183530064604554e-05, + "loss": 3.5465, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182691469853502e-05, + "loss": 3.551, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.18185287510245e-05, + "loss": 3.5626, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.181014280351398e-05, + "loss": 3.5456, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.180175685600346e-05, + "loss": 3.5332, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.1793387287296666e-05, + "loss": 3.5436, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.1785001339786146e-05, + "loss": 3.5497, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.1776615392275626e-05, + "loss": 3.5506, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.1768229444765106e-05, + "loss": 3.551, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.1759859876058315e-05, + "loss": 3.5461, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.1751473928547795e-05, + "loss": 3.5502, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.1743087981037275e-05, + "loss": 3.5381, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173470203352676e-05, + "loss": 3.5323, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.172633246481997e-05, + "loss": 3.5377, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.171794651730945e-05, + "loss": 3.5428, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.170956056979893e-05, + "loss": 3.5576, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.170117462228841e-05, + "loss": 3.5416, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.169278867477789e-05, + "loss": 3.5365, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.16844191060711e-05, + "loss": 3.5545, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.167603315856058e-05, + "loss": 3.5454, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.166764721105006e-05, + "loss": 3.5522, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.165926126353954e-05, + "loss": 3.5496, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.165089169483275e-05, + "loss": 3.5399, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164250574732223e-05, + "loss": 3.5438, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.1634119799811715e-05, + "loss": 3.5448, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.1625733852301195e-05, + "loss": 3.5327, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.1617364283594405e-05, + "loss": 3.5453, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.1608978336083884e-05, + "loss": 3.5472, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.1600592388573364e-05, + "loss": 3.5428, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.1592206441062844e-05, + "loss": 3.5366, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.1583836872356054e-05, + "loss": 3.5404, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.1575450924845533e-05, + "loss": 3.5365, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.1567064977335013e-05, + "loss": 3.5477, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.155867902982449e-05, + "loss": 3.548, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.15503094611177e-05, + "loss": 3.5409, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.154192351360718e-05, + "loss": 3.5506, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.153353756609667e-05, + "loss": 3.5549, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.152515161858615e-05, + "loss": 3.5457, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.151676567107563e-05, + "loss": 3.55, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.150839610236884e-05, + "loss": 3.5475, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.150001015485832e-05, + "loss": 3.541, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.14916242073478e-05, + "loss": 3.5321, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.148323825983727e-05, + "loss": 3.545, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.147485231232675e-05, + "loss": 3.541, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.146648274361997e-05, + "loss": 3.5451, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.145809679610945e-05, + "loss": 3.5459, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.144971084859892e-05, + "loss": 3.5501, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144132490108841e-05, + "loss": 3.5401, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143295533238162e-05, + "loss": 3.5383, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.14245693848711e-05, + "loss": 3.5529, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.1416183437360576e-05, + "loss": 3.5462, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.1407797489850056e-05, + "loss": 3.5428, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.1399411542339536e-05, + "loss": 3.5225, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.1391041973632745e-05, + "loss": 3.544, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.1382656026122225e-05, + "loss": 3.5496, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.1374270078611705e-05, + "loss": 3.554, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.1365884131101185e-05, + "loss": 3.5467, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.1357514562394394e-05, + "loss": 3.5367, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.1349128614883874e-05, + "loss": 3.5467, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.134074266737336e-05, + "loss": 3.5581, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133235671986284e-05, + "loss": 3.5408, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.132398715115605e-05, + "loss": 3.5434, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.131560120364553e-05, + "loss": 3.5417, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130721525613501e-05, + "loss": 3.5464, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129882930862449e-05, + "loss": 3.5453, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.12904597399177e-05, + "loss": 3.5459, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.128207379240718e-05, + "loss": 3.5382, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127368784489666e-05, + "loss": 3.5578, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.126530189738614e-05, + "loss": 3.5415, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.864553689956665, + "eval_runtime": 302.5939, + "eval_samples_per_second": 1261.067, + "eval_steps_per_second": 39.409, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.125693232867935e-05, + "loss": 3.5239, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124854638116883e-05, + "loss": 3.5434, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.1240160433658314e-05, + "loss": 3.537, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.1231774486147794e-05, + "loss": 3.5519, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.1223388538637274e-05, + "loss": 3.5513, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121501896993048e-05, + "loss": 3.5517, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120663302241996e-05, + "loss": 3.5376, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119824707490944e-05, + "loss": 3.5297, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.118986112739892e-05, + "loss": 3.5341, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.118149155869213e-05, + "loss": 3.5565, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117310561118161e-05, + "loss": 3.5398, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116471966367109e-05, + "loss": 3.5431, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115633371616057e-05, + "loss": 3.5511, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114796414745378e-05, + "loss": 3.5405, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113957819994326e-05, + "loss": 3.5312, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113119225243275e-05, + "loss": 3.5325, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112280630492223e-05, + "loss": 3.5348, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111443673621544e-05, + "loss": 3.5363, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.110605078870492e-05, + "loss": 3.5396, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.10976648411944e-05, + "loss": 3.5437, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.108927889368388e-05, + "loss": 3.5564, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.108089294617336e-05, + "loss": 3.5413, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107250699866284e-05, + "loss": 3.5397, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.1064137429956046e-05, + "loss": 3.5396, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.1055751482445526e-05, + "loss": 3.545, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.1047365534935006e-05, + "loss": 3.5363, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.1038979587424486e-05, + "loss": 3.5306, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.10306100187177e-05, + "loss": 3.5361, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102222407120718e-05, + "loss": 3.5376, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.101383812369666e-05, + "loss": 3.5293, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100545217618614e-05, + "loss": 3.5271, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.099708260747935e-05, + "loss": 3.5472, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.098869665996883e-05, + "loss": 3.5386, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.098031071245831e-05, + "loss": 3.5436, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.097192476494779e-05, + "loss": 3.5469, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.096353881743727e-05, + "loss": 3.5373, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.095515286992675e-05, + "loss": 3.5449, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.094678330121996e-05, + "loss": 3.5303, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.093839735370944e-05, + "loss": 3.5324, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.093001140619892e-05, + "loss": 3.5298, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.09216254586884e-05, + "loss": 3.5286, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091323951117788e-05, + "loss": 3.5313, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090485356366736e-05, + "loss": 3.5435, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.0896483994960575e-05, + "loss": 3.5297, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.0888098047450055e-05, + "loss": 3.5395, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.087971209993953e-05, + "loss": 3.5339, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087132615242901e-05, + "loss": 3.5388, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.0862956583722224e-05, + "loss": 3.5411, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.0854570636211704e-05, + "loss": 3.5205, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084618468870118e-05, + "loss": 3.5324, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083779874119066e-05, + "loss": 3.5411, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082941279368014e-05, + "loss": 3.5455, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.082104322497335e-05, + "loss": 3.5317, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.081265727746283e-05, + "loss": 3.5297, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.080427132995231e-05, + "loss": 3.5372, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.079588538244179e-05, + "loss": 3.5225, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.0787515813735e-05, + "loss": 3.5339, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.077912986622448e-05, + "loss": 3.5279, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.077074391871396e-05, + "loss": 3.5404, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076235797120344e-05, + "loss": 3.5317, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.075398840249665e-05, + "loss": 3.5339, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074560245498613e-05, + "loss": 3.5255, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073721650747561e-05, + "loss": 3.5369, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072883055996509e-05, + "loss": 3.5211, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.0720460991258307e-05, + "loss": 3.5308, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.0712075043747787e-05, + "loss": 3.5375, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.0703689096237267e-05, + "loss": 3.5399, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.0695303148726746e-05, + "loss": 3.5232, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.0686933580019956e-05, + "loss": 3.5242, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.0678547632509436e-05, + "loss": 3.532, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.0670161684998915e-05, + "loss": 3.5314, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.0661775737488395e-05, + "loss": 3.5424, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.0653406168781605e-05, + "loss": 3.5268, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.0645020221271084e-05, + "loss": 3.5417, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.0636634273760564e-05, + "loss": 3.536, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.0628248326250044e-05, + "loss": 3.5357, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.061987875754326e-05, + "loss": 3.5368, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061149281003274e-05, + "loss": 3.5356, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060310686252222e-05, + "loss": 3.5358, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.05947209150117e-05, + "loss": 3.5284, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058635134630491e-05, + "loss": 3.5319, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057796539879439e-05, + "loss": 3.5329, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.056957945128387e-05, + "loss": 3.5471, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.056119350377335e-05, + "loss": 3.5287, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.055280755626283e-05, + "loss": 3.5245, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.054443798755604e-05, + "loss": 3.5239, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053605204004552e-05, + "loss": 3.5362, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.0527666092535e-05, + "loss": 3.5322, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051928014502448e-05, + "loss": 3.5377, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.051091057631769e-05, + "loss": 3.5286, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.050252462880717e-05, + "loss": 3.535, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0494138681296654e-05, + "loss": 3.5234, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0485752733786134e-05, + "loss": 3.5186, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477383165079343e-05, + "loss": 3.5185, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0468997217568823e-05, + "loss": 3.5254, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0460611270058303e-05, + "loss": 3.5408, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0452225322547783e-05, + "loss": 3.5342, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0443839375037263e-05, + "loss": 3.5221, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0435469806330475e-05, + "loss": 3.5346, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0427083858819955e-05, + "loss": 3.5338, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0418697911309435e-05, + "loss": 3.5334, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.0410311963798915e-05, + "loss": 3.535, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0401942395092124e-05, + "loss": 3.5248, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0393556447581607e-05, + "loss": 3.5282, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0385170500071087e-05, + "loss": 3.5337, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.0376784552560567e-05, + "loss": 3.5163, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.0368398605050047e-05, + "loss": 3.5278, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0360029036343256e-05, + "loss": 3.5362, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0351643088832736e-05, + "loss": 3.5233, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0343257141322216e-05, + "loss": 3.5231, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.03348711938117e-05, + "loss": 3.5287, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.032650162510491e-05, + "loss": 3.5209, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.031811567759439e-05, + "loss": 3.5362, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.030972973008387e-05, + "loss": 3.531, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.030134378257335e-05, + "loss": 3.5221, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.029295783506283e-05, + "loss": 3.5403, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.028458826635604e-05, + "loss": 3.5396, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.027620231884552e-05, + "loss": 3.5305, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0267816371335e-05, + "loss": 3.5378, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.025943042382448e-05, + "loss": 3.5308, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.025106085511769e-05, + "loss": 3.5261, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.024267490760717e-05, + "loss": 3.521, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0234288960096653e-05, + "loss": 3.5254, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0225903012586133e-05, + "loss": 3.5285, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0217533443879342e-05, + "loss": 3.5289, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0209147496368822e-05, + "loss": 3.5271, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0200761548858302e-05, + "loss": 3.5375, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0192375601347782e-05, + "loss": 3.5271, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0184006032640995e-05, + "loss": 3.5239, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0175620085130475e-05, + "loss": 3.5354, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0167234137619955e-05, + "loss": 3.5322, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.0158848190109428e-05, + "loss": 3.5279, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0150462242598908e-05, + "loss": 3.5131, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0142092673892124e-05, + "loss": 3.5249, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0133706726381604e-05, + "loss": 3.537, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.012532077887108e-05, + "loss": 3.5366, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.011693483136056e-05, + "loss": 3.5286, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.0108565262653776e-05, + "loss": 3.5234, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0100179315143256e-05, + "loss": 3.5323, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0091793367632733e-05, + "loss": 3.5439, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0083407420122213e-05, + "loss": 3.5268, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.007503785141543e-05, + "loss": 3.5307, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.00666519039049e-05, + "loss": 3.5257, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.005826595639438e-05, + "loss": 3.5283, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.004988000888386e-05, + "loss": 3.5289, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0041510440177077e-05, + "loss": 3.5375, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0033124492666554e-05, + "loss": 3.5213, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0024738545156034e-05, + "loss": 3.5413, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0016352597645514e-05, + "loss": 3.53, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.0007983028938723e-05, + "loss": 3.5217, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 3.8653202056884766, + "eval_runtime": 318.1208, + "eval_samples_per_second": 1199.516, + "eval_steps_per_second": 37.486, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.9999597081428203e-05, + "loss": 3.5273, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9991211133917686e-05, + "loss": 3.5221, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.9982825186407166e-05, + "loss": 3.5343, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9974455617700375e-05, + "loss": 3.5337, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9966069670189855e-05, + "loss": 3.5376, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9957683722679335e-05, + "loss": 3.5234, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9949297775168815e-05, + "loss": 3.5154, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9940911827658295e-05, + "loss": 3.5186, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.9932542258951508e-05, + "loss": 3.5432, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.9924156311440988e-05, + "loss": 3.5272, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.9915770363930467e-05, + "loss": 3.5233, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.9907384416419947e-05, + "loss": 3.534, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.9899014847713157e-05, + "loss": 3.5248, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.989062890020264e-05, + "loss": 3.5182, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.988224295269212e-05, + "loss": 3.5209, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.98738570051816e-05, + "loss": 3.5186, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.986548743647481e-05, + "loss": 3.5219, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.985710148896429e-05, + "loss": 3.5204, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.984871554145377e-05, + "loss": 3.5321, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.984032959394325e-05, + "loss": 3.5428, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.983196002523646e-05, + "loss": 3.5269, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.982357407772594e-05, + "loss": 3.521, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.981518813021542e-05, + "loss": 3.5279, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.98068021827049e-05, + "loss": 3.5311, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.979843261399811e-05, + "loss": 3.5212, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9790046666487594e-05, + "loss": 3.5189, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9781660718977074e-05, + "loss": 3.5208, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9773274771466553e-05, + "loss": 3.5291, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9764888823956033e-05, + "loss": 3.5118, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.9756519255249243e-05, + "loss": 3.5115, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9748133307738722e-05, + "loss": 3.5318, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.9739747360228202e-05, + "loss": 3.5287, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9731361412717686e-05, + "loss": 3.5289, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9722975465207166e-05, + "loss": 3.5317, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9714605896500375e-05, + "loss": 3.5215, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706219948989855e-05, + "loss": 3.5294, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9697834001479335e-05, + "loss": 3.515, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9689448053968815e-05, + "loss": 3.5215, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.9681078485262027e-05, + "loss": 3.5141, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.9672692537751507e-05, + "loss": 3.5121, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.9664306590240987e-05, + "loss": 3.5215, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9655920642730467e-05, + "loss": 3.5288, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9647551074023676e-05, + "loss": 3.5176, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9639165126513156e-05, + "loss": 3.5229, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.963077917900264e-05, + "loss": 3.5226, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.962239323149212e-05, + "loss": 3.5237, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.96140072839816e-05, + "loss": 3.5274, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.960563771527481e-05, + "loss": 3.5104, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.959725176776429e-05, + "loss": 3.5117, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.958886582025377e-05, + "loss": 3.5253, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.958047987274325e-05, + "loss": 3.5324, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.957211030403646e-05, + "loss": 3.5182, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.956372435652594e-05, + "loss": 3.5187, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.955533840901542e-05, + "loss": 3.5242, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.95469524615049e-05, + "loss": 3.5086, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.953858289279811e-05, + "loss": 3.5161, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9530196945287593e-05, + "loss": 3.5128, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9521810997777073e-05, + "loss": 3.5247, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9513425050266553e-05, + "loss": 3.5211, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9505055481559762e-05, + "loss": 3.5212, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9496669534049242e-05, + "loss": 3.5091, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.9488283586538722e-05, + "loss": 3.5244, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.9479897639028202e-05, + "loss": 3.5069, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.9471528070321414e-05, + "loss": 3.5173, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.9463142122810894e-05, + "loss": 3.5231, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.9454756175300374e-05, + "loss": 3.5265, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.9446370227789854e-05, + "loss": 3.5066, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.9438000659083063e-05, + "loss": 3.5118, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.9429614711572547e-05, + "loss": 3.5129, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.9421228764062027e-05, + "loss": 3.5224, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.9412842816551507e-05, + "loss": 3.5207, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.9404473247844716e-05, + "loss": 3.517, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9396087300334196e-05, + "loss": 3.5242, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9387701352823676e-05, + "loss": 3.5282, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.9379315405313156e-05, + "loss": 3.5178, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.9370945836606368e-05, + "loss": 3.5223, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9362559889095848e-05, + "loss": 3.5215, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9354173941585328e-05, + "loss": 3.5253, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.93457879940748e-05, + "loss": 3.5101, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9337418425368017e-05, + "loss": 3.5179, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9329032477857497e-05, + "loss": 3.5178, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.932064653034698e-05, + "loss": 3.5343, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9312260582836454e-05, + "loss": 3.5182, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9303874635325934e-05, + "loss": 3.5077, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.929550506661915e-05, + "loss": 3.5112, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.928711911910863e-05, + "loss": 3.5164, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9278733171598106e-05, + "loss": 3.5246, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9270347224087586e-05, + "loss": 3.5229, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9261977655380802e-05, + "loss": 3.5131, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9253591707870275e-05, + "loss": 3.5196, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9245205760359755e-05, + "loss": 3.5133, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9236819812849235e-05, + "loss": 3.5034, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.922845024414245e-05, + "loss": 3.5026, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.9220064296631927e-05, + "loss": 3.5169, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.9211678349121407e-05, + "loss": 3.5238, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9203292401610887e-05, + "loss": 3.5191, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9194906454100367e-05, + "loss": 3.5076, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.918653688539358e-05, + "loss": 3.5181, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.917815093788306e-05, + "loss": 3.5197, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.916976499037254e-05, + "loss": 3.5189, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.916137904286202e-05, + "loss": 3.5195, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.915300947415523e-05, + "loss": 3.5136, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.914462352664471e-05, + "loss": 3.5126, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.913623757913419e-05, + "loss": 3.5213, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9127851631623672e-05, + "loss": 3.5055, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.9119465684113152e-05, + "loss": 3.5108, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.911109611540636e-05, + "loss": 3.5221, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.910271016789584e-05, + "loss": 3.5129, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.909432422038532e-05, + "loss": 3.5084, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.90859382728748e-05, + "loss": 3.5158, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.9077568704168013e-05, + "loss": 3.5104, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.9069182756657493e-05, + "loss": 3.517, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9060796809146973e-05, + "loss": 3.5151, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9052410861636453e-05, + "loss": 3.512, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9044041292929662e-05, + "loss": 3.5219, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9035655345419142e-05, + "loss": 3.5258, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9027269397908626e-05, + "loss": 3.5156, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9018883450398105e-05, + "loss": 3.5267, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.9010513881691315e-05, + "loss": 3.5166, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.9002127934180795e-05, + "loss": 3.5115, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8993741986670274e-05, + "loss": 3.5048, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8985356039159754e-05, + "loss": 3.5115, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8976986470452967e-05, + "loss": 3.5129, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.8968600522942447e-05, + "loss": 3.5154, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8960214575431927e-05, + "loss": 3.5176, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8951828627921407e-05, + "loss": 3.5188, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8943459059214616e-05, + "loss": 3.5155, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8935073111704096e-05, + "loss": 3.5086, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.892668716419358e-05, + "loss": 3.5198, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.891830121668306e-05, + "loss": 3.5189, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8909931647976268e-05, + "loss": 3.5111, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8901545700465748e-05, + "loss": 3.5012, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8893159752955228e-05, + "loss": 3.5105, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.8884773805444708e-05, + "loss": 3.5223, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.8876387857934188e-05, + "loss": 3.5241, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.886800191042367e-05, + "loss": 3.5087, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.885963234171688e-05, + "loss": 3.5102, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.885124639420636e-05, + "loss": 3.5226, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.884286044669584e-05, + "loss": 3.5249, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.883447449918532e-05, + "loss": 3.5156, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8826104930478533e-05, + "loss": 3.5132, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8817718982968013e-05, + "loss": 3.5124, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8809333035457493e-05, + "loss": 3.5136, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8800947087946973e-05, + "loss": 3.5122, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8792577519240182e-05, + "loss": 3.5249, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8784191571729662e-05, + "loss": 3.509, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8775805624219142e-05, + "loss": 3.5274, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8767419676708625e-05, + "loss": 3.5181, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.8759050108001834e-05, + "loss": 3.5054, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.8664448261260986, + "eval_runtime": 333.7097, + "eval_samples_per_second": 1143.482, + "eval_steps_per_second": 35.735, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.8750664160491314e-05, + "loss": 3.5131, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742278212980794e-05, + "loss": 3.5139, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8733892265470274e-05, + "loss": 3.5202, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8725506317959754e-05, + "loss": 3.5199, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8717136749252966e-05, + "loss": 3.5243, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8708750801742446e-05, + "loss": 3.5096, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700364854231926e-05, + "loss": 3.504, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8691978906721406e-05, + "loss": 3.4966, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8683609338014615e-05, + "loss": 3.5285, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8675223390504095e-05, + "loss": 3.5165, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.866683744299358e-05, + "loss": 3.5096, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.865845149548306e-05, + "loss": 3.5194, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650081926776268e-05, + "loss": 3.51, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8641695979265748e-05, + "loss": 3.5082, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8633310031755228e-05, + "loss": 3.5048, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8624924084244708e-05, + "loss": 3.5087, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8616538136734184e-05, + "loss": 3.506, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.86081685680274e-05, + "loss": 3.5065, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.859978262051688e-05, + "loss": 3.5204, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8591396673006353e-05, + "loss": 3.5297, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8583010725495833e-05, + "loss": 3.5139, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8574624777985317e-05, + "loss": 3.5059, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.856625520927853e-05, + "loss": 3.5145, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8557869261768006e-05, + "loss": 3.516, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8549483314257486e-05, + "loss": 3.5093, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8541097366746966e-05, + "loss": 3.5036, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.853272779804018e-05, + "loss": 3.5046, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524341850529658e-05, + "loss": 3.5171, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8515955903019138e-05, + "loss": 3.4953, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8507569955508618e-05, + "loss": 3.4973, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499184007998098e-05, + "loss": 3.5158, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8490814439291307e-05, + "loss": 3.5123, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8482428491780787e-05, + "loss": 3.5189, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.847404254427027e-05, + "loss": 3.5134, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.846565659675975e-05, + "loss": 3.5085, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.845728702805296e-05, + "loss": 3.5162, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.844890108054244e-05, + "loss": 3.4997, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.844051513303192e-05, + "loss": 3.5111, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.84321291855214e-05, + "loss": 3.4975, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.842375961681461e-05, + "loss": 3.5024, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.841537366930409e-05, + "loss": 3.5055, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.840698772179357e-05, + "loss": 3.5125, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.839860177428305e-05, + "loss": 3.5094, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.839021582677253e-05, + "loss": 3.5055, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.838184625806574e-05, + "loss": 3.5101, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.837346031055522e-05, + "loss": 3.5083, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8365074363044704e-05, + "loss": 3.5116, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8356688415534184e-05, + "loss": 3.4971, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.8348318846827393e-05, + "loss": 3.4974, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8339932899316873e-05, + "loss": 3.5102, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331546951806353e-05, + "loss": 3.5154, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8323161004295833e-05, + "loss": 3.5064, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8314791435589045e-05, + "loss": 3.5038, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8306405488078525e-05, + "loss": 3.5041, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8298019540568005e-05, + "loss": 3.4968, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8289633593057485e-05, + "loss": 3.5041, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8281264024350694e-05, + "loss": 3.4993, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8272878076840174e-05, + "loss": 3.5104, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8264492129329657e-05, + "loss": 3.5082, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8256106181819137e-05, + "loss": 3.5075, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8247720234308617e-05, + "loss": 3.4953, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8239350665601827e-05, + "loss": 3.5133, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8230964718091306e-05, + "loss": 3.4934, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8222578770580786e-05, + "loss": 3.5047, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214192823070266e-05, + "loss": 3.5107, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.820582325436348e-05, + "loss": 3.5123, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.819743730685296e-05, + "loss": 3.4945, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.818905135934244e-05, + "loss": 3.4988, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.818066541183192e-05, + "loss": 3.498, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8172295843125128e-05, + "loss": 3.5063, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.816390989561461e-05, + "loss": 3.5075, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.815552394810409e-05, + "loss": 3.5041, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.814713800059357e-05, + "loss": 3.5111, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.813876843188678e-05, + "loss": 3.5119, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.813038248437626e-05, + "loss": 3.5095, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.812199653686574e-05, + "loss": 3.5008, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.811361058935522e-05, + "loss": 3.5122, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8105224641844703e-05, + "loss": 3.5104, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8096838694334183e-05, + "loss": 3.4931, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8088469125627392e-05, + "loss": 3.5133, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8080083178116872e-05, + "loss": 3.5002, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8071697230606352e-05, + "loss": 3.5221, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8063311283095832e-05, + "loss": 3.5048, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8054941714389045e-05, + "loss": 3.4893, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8046555766878525e-05, + "loss": 3.5046, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.8038169819368005e-05, + "loss": 3.4999, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.8029783871857485e-05, + "loss": 3.5121, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8021414303150694e-05, + "loss": 3.5062, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013028355640174e-05, + "loss": 3.5024, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8004642408129657e-05, + "loss": 3.5066, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996256460619137e-05, + "loss": 3.4977, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7987886891912346e-05, + "loss": 3.4922, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7979500944401826e-05, + "loss": 3.4913, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971114996891306e-05, + "loss": 3.5009, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7962729049380786e-05, + "loss": 3.5111, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7954359480674e-05, + "loss": 3.505, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.794597353316348e-05, + "loss": 3.4963, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.793758758565296e-05, + "loss": 3.5038, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.792920163814243e-05, + "loss": 3.5049, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7920832069435647e-05, + "loss": 3.5085, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7912446121925127e-05, + "loss": 3.5066, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.790406017441461e-05, + "loss": 3.5022, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7895674226904084e-05, + "loss": 3.4997, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.78873046581973e-05, + "loss": 3.5082, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.787891871068678e-05, + "loss": 3.4888, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.787053276317626e-05, + "loss": 3.5002, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7862146815665736e-05, + "loss": 3.5047, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7853777246958952e-05, + "loss": 3.4985, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.7845391299448432e-05, + "loss": 3.4949, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7837005351937905e-05, + "loss": 3.5017, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7828619404427385e-05, + "loss": 3.4969, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.78202498357206e-05, + "loss": 3.501, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.781186388821008e-05, + "loss": 3.5042, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7803477940699558e-05, + "loss": 3.499, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795091993189038e-05, + "loss": 3.5113, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7786722424482253e-05, + "loss": 3.5113, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7778336476971733e-05, + "loss": 3.5025, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.776995052946121e-05, + "loss": 3.5091, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.776156458195069e-05, + "loss": 3.5078, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.775317863444017e-05, + "loss": 3.4975, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.774480906573338e-05, + "loss": 3.4935, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.773642311822286e-05, + "loss": 3.4952, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.772803717071234e-05, + "loss": 3.5013, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.771965122320182e-05, + "loss": 3.5037, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711265275691302e-05, + "loss": 3.5056, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.770289570698451e-05, + "loss": 3.5044, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.769450975947399e-05, + "loss": 3.4989, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.768612381196347e-05, + "loss": 3.5031, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.767773786445295e-05, + "loss": 3.5015, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7669368295746164e-05, + "loss": 3.5084, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7660982348235644e-05, + "loss": 3.5003, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7652596400725124e-05, + "loss": 3.4881, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7644210453214603e-05, + "loss": 3.4937, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7635840884507813e-05, + "loss": 3.5096, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7627454936997293e-05, + "loss": 3.5093, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619068989486773e-05, + "loss": 3.5015, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.7610683041976252e-05, + "loss": 3.4976, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.7602297094465736e-05, + "loss": 3.5126, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.7593927525758945e-05, + "loss": 3.5073, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.7585541578248425e-05, + "loss": 3.5058, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577155630737905e-05, + "loss": 3.5017, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7568769683227385e-05, + "loss": 3.4999, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560400114520597e-05, + "loss": 3.5012, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552014167010077e-05, + "loss": 3.4956, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7543628219499557e-05, + "loss": 3.5136, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535242271989037e-05, + "loss": 3.4976, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7526856324478517e-05, + "loss": 3.5111, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7518486755771726e-05, + "loss": 3.5034, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7510100808261206e-05, + "loss": 3.4924, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.867966413497925, + "eval_runtime": 303.4404, + "eval_samples_per_second": 1257.549, + "eval_steps_per_second": 39.299, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.750171486075069e-05, + "loss": 3.5007, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.749332891324017e-05, + "loss": 3.4991, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.748495934453338e-05, + "loss": 3.5025, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.747657339702286e-05, + "loss": 3.506, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.746818744951234e-05, + "loss": 3.5118, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.745980150200182e-05, + "loss": 3.4967, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.745143193329503e-05, + "loss": 3.4908, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.744304598578451e-05, + "loss": 3.4849, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.743466003827399e-05, + "loss": 3.5158, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.742627409076347e-05, + "loss": 3.5029, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.741788814325295e-05, + "loss": 3.4928, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.740951857454616e-05, + "loss": 3.5105, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.7401132627035643e-05, + "loss": 3.491, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7392746679525123e-05, + "loss": 3.4982, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7384360732014603e-05, + "loss": 3.4902, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7375991163307812e-05, + "loss": 3.4932, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.7367605215797292e-05, + "loss": 3.4969, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.7359219268286772e-05, + "loss": 3.4915, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.7350833320776252e-05, + "loss": 3.5061, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.7342447373265735e-05, + "loss": 3.5142, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7334077804558944e-05, + "loss": 3.4999, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7325691857048424e-05, + "loss": 3.4947, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317305909537904e-05, + "loss": 3.5034, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7308919962027384e-05, + "loss": 3.5025, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7300550393320597e-05, + "loss": 3.4934, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.7292164445810077e-05, + "loss": 3.4933, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7283778498299557e-05, + "loss": 3.4873, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7275392550789037e-05, + "loss": 3.5048, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7267022982082246e-05, + "loss": 3.4808, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7258637034571726e-05, + "loss": 3.4879, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7250251087061206e-05, + "loss": 3.5015, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.724186513955069e-05, + "loss": 3.5028, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7233495570843898e-05, + "loss": 3.504, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7225109623333378e-05, + "loss": 3.5006, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7216723675822858e-05, + "loss": 3.4929, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.7208337728312338e-05, + "loss": 3.506, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7199951780801815e-05, + "loss": 3.4894, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.719158221209503e-05, + "loss": 3.4946, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.718319626458451e-05, + "loss": 3.4828, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.7174810317073984e-05, + "loss": 3.4901, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7166424369563464e-05, + "loss": 3.4886, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.715805480085668e-05, + "loss": 3.5033, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.714966885334616e-05, + "loss": 3.4952, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.7141282905835636e-05, + "loss": 3.4927, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7132896958325116e-05, + "loss": 3.4991, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.7124527389618332e-05, + "loss": 3.4975, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.7116141442107812e-05, + "loss": 3.4969, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7107755494597288e-05, + "loss": 3.4858, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.7099369547086768e-05, + "loss": 3.4804, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.7090999978379984e-05, + "loss": 3.5043, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.7082614030869457e-05, + "loss": 3.5007, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7074228083358937e-05, + "loss": 3.4942, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7065842135848417e-05, + "loss": 3.4931, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.7057456188337897e-05, + "loss": 3.4889, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.704908661963111e-05, + "loss": 3.4856, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.704070067212059e-05, + "loss": 3.4914, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.703231472461007e-05, + "loss": 3.4869, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.702392877709955e-05, + "loss": 3.4967, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.701555920839276e-05, + "loss": 3.4936, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.7007173260882242e-05, + "loss": 3.4906, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.6998787313371722e-05, + "loss": 3.4842, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6990401365861202e-05, + "loss": 3.5025, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.698203179715441e-05, + "loss": 3.4806, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.697364584964389e-05, + "loss": 3.4902, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.696525990213337e-05, + "loss": 3.4931, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.695687395462285e-05, + "loss": 3.5004, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6948504385916063e-05, + "loss": 3.48, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6940118438405543e-05, + "loss": 3.4885, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6931732490895023e-05, + "loss": 3.4818, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.6923346543384503e-05, + "loss": 3.496, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6914976974677712e-05, + "loss": 3.4947, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6906591027167196e-05, + "loss": 3.4929, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6898205079656676e-05, + "loss": 3.4957, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6889819132146156e-05, + "loss": 3.4961, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6881449563439365e-05, + "loss": 3.5015, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6873063615928845e-05, + "loss": 3.4853, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.6864677668418325e-05, + "loss": 3.4988, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6856291720907804e-05, + "loss": 3.501, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6847905773397284e-05, + "loss": 3.4826, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.6839536204690497e-05, + "loss": 3.4962, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.6831150257179977e-05, + "loss": 3.4875, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6822764309669457e-05, + "loss": 3.5097, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6814378362158937e-05, + "loss": 3.4933, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6806008793452146e-05, + "loss": 3.4764, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.679762284594163e-05, + "loss": 3.4881, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.678923689843111e-05, + "loss": 3.49, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.678085095092059e-05, + "loss": 3.4993, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6772481382213798e-05, + "loss": 3.494, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764095434703278e-05, + "loss": 3.4884, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6755709487192758e-05, + "loss": 3.4902, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6747323539682238e-05, + "loss": 3.4893, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.673895397097545e-05, + "loss": 3.4814, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.673056802346493e-05, + "loss": 3.4738, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.672218207595441e-05, + "loss": 3.4895, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.671379612844389e-05, + "loss": 3.4969, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.67054265597371e-05, + "loss": 3.4932, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6697040612226583e-05, + "loss": 3.4831, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.6688654664716063e-05, + "loss": 3.4903, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.6680268717205543e-05, + "loss": 3.4883, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6671899148498752e-05, + "loss": 3.4994, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6663513200988232e-05, + "loss": 3.4911, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.6655127253477712e-05, + "loss": 3.4912, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.6646741305967192e-05, + "loss": 3.4846, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.6638371737260404e-05, + "loss": 3.4963, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6629985789749884e-05, + "loss": 3.4754, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6621599842239364e-05, + "loss": 3.49, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.6613213894728844e-05, + "loss": 3.4882, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.6604844326022053e-05, + "loss": 3.4879, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.6596458378511537e-05, + "loss": 3.4797, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.6588072431001017e-05, + "loss": 3.4912, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6579686483490496e-05, + "loss": 3.483, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.6571300535979976e-05, + "loss": 3.4876, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6562930967273186e-05, + "loss": 3.4906, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6554545019762665e-05, + "loss": 3.4871, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6546159072252145e-05, + "loss": 3.4956, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.653777312474163e-05, + "loss": 3.4982, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.6529403556034838e-05, + "loss": 3.4926, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.6521017608524318e-05, + "loss": 3.4957, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.6512631661013798e-05, + "loss": 3.491, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6504245713503278e-05, + "loss": 3.4812, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.649587614479649e-05, + "loss": 3.4853, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.648749019728597e-05, + "loss": 3.4848, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.647910424977545e-05, + "loss": 3.4859, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.647071830226493e-05, + "loss": 3.4933, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.646233235475441e-05, + "loss": 3.4873, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.645396278604762e-05, + "loss": 3.4942, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.64455768385371e-05, + "loss": 3.4891, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.6437190891026582e-05, + "loss": 3.4863, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.6428804943516062e-05, + "loss": 3.4863, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.642043537480927e-05, + "loss": 3.4996, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.641204942729875e-05, + "loss": 3.4854, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.640366347978823e-05, + "loss": 3.4811, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.639527753227771e-05, + "loss": 3.4754, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6386907963570924e-05, + "loss": 3.4947, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6378522016060404e-05, + "loss": 3.4956, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6370136068549884e-05, + "loss": 3.4913, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.6361750121039364e-05, + "loss": 3.4845, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.6353380552332573e-05, + "loss": 3.5009, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.6344994604822053e-05, + "loss": 3.4898, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.6336608657311536e-05, + "loss": 3.4934, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.632822270980101e-05, + "loss": 3.4864, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.631983676229049e-05, + "loss": 3.4894, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6311467193583705e-05, + "loss": 3.4878, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6303081246073185e-05, + "loss": 3.4808, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.629469529856266e-05, + "loss": 3.4999, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.628630935105214e-05, + "loss": 3.4882, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.6277939782345357e-05, + "loss": 3.4946, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.6269553834834837e-05, + "loss": 3.4917, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.626116788732431e-05, + "loss": 3.4793, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.8683371543884277, + "eval_runtime": 303.4509, + "eval_samples_per_second": 1257.505, + "eval_steps_per_second": 39.298, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.625278193981379e-05, + "loss": 3.4858, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6244395992303274e-05, + "loss": 3.4891, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6236010044792754e-05, + "loss": 3.4885, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6227624097282234e-05, + "loss": 3.492, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219254528575443e-05, + "loss": 3.5024, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6210868581064923e-05, + "loss": 3.4864, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6202482633554403e-05, + "loss": 3.4778, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6194096686043883e-05, + "loss": 3.4739, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6185727117337095e-05, + "loss": 3.4975, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177341169826575e-05, + "loss": 3.4944, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6168955222316055e-05, + "loss": 3.475, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6160569274805535e-05, + "loss": 3.4994, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152199706098744e-05, + "loss": 3.4806, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6143813758588228e-05, + "loss": 3.4872, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6135427811077708e-05, + "loss": 3.4811, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127041863567187e-05, + "loss": 3.4814, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6118672294860397e-05, + "loss": 3.481, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6110286347349877e-05, + "loss": 3.4797, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6101900399839356e-05, + "loss": 3.4931, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6093514452328836e-05, + "loss": 3.4991, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.608514488362205e-05, + "loss": 3.49, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.607675893611153e-05, + "loss": 3.4841, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.606837298860101e-05, + "loss": 3.4874, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.605998704109049e-05, + "loss": 3.4934, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6051617472383698e-05, + "loss": 3.4804, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6043231524873178e-05, + "loss": 3.4836, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.603484557736266e-05, + "loss": 3.4764, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.602645962985214e-05, + "loss": 3.4916, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.601809006114535e-05, + "loss": 3.4705, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.600970411363483e-05, + "loss": 3.4748, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.600131816612431e-05, + "loss": 3.4898, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.599293221861379e-05, + "loss": 3.4859, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5984562649907003e-05, + "loss": 3.4905, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.5976176702396483e-05, + "loss": 3.4897, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5967790754885963e-05, + "loss": 3.4804, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5959404807375442e-05, + "loss": 3.4914, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5951018859864922e-05, + "loss": 3.48, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.594264929115813e-05, + "loss": 3.4762, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934263343647615e-05, + "loss": 3.4742, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5925877396137095e-05, + "loss": 3.4787, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5917491448626575e-05, + "loss": 3.4754, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5909121879919784e-05, + "loss": 3.4914, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5900735932409264e-05, + "loss": 3.4815, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5892349984898744e-05, + "loss": 3.4804, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5883964037388224e-05, + "loss": 3.4911, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5875594468681436e-05, + "loss": 3.4791, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867208521170916e-05, + "loss": 3.4894, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5858822573660396e-05, + "loss": 3.4747, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850436626149876e-05, + "loss": 3.4591, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842067057443085e-05, + "loss": 3.4959, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.583368110993257e-05, + "loss": 3.4871, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.582529516242205e-05, + "loss": 3.4865, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.581690921491153e-05, + "loss": 3.4793, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5808539646204738e-05, + "loss": 3.4751, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5800153698694217e-05, + "loss": 3.473, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5791767751183697e-05, + "loss": 3.4792, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783381803673177e-05, + "loss": 3.4746, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.577501223496639e-05, + "loss": 3.4788, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.576662628745587e-05, + "loss": 3.4878, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.575824033994535e-05, + "loss": 3.4778, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.574985439243483e-05, + "loss": 3.4696, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.574148482372804e-05, + "loss": 3.492, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5733098876217522e-05, + "loss": 3.4682, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5724712928707002e-05, + "loss": 3.4737, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716326981196482e-05, + "loss": 3.4832, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.570795741248969e-05, + "loss": 3.4881, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.569957146497917e-05, + "loss": 3.468, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.569118551746865e-05, + "loss": 3.4781, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.568279956995813e-05, + "loss": 3.4663, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.5674430001251344e-05, + "loss": 3.4863, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5666044053740824e-05, + "loss": 3.4812, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5657658106230303e-05, + "loss": 3.4818, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5649272158719783e-05, + "loss": 3.4807, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5640902590012993e-05, + "loss": 3.4827, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5632516642502476e-05, + "loss": 3.492, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624130694991956e-05, + "loss": 3.4717, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5615744747481436e-05, + "loss": 3.4843, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607375178774645e-05, + "loss": 3.4877, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5598989231264125e-05, + "loss": 3.4686, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5590603283753605e-05, + "loss": 3.4853, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582217336243085e-05, + "loss": 3.4774, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.557383138873256e-05, + "loss": 3.4926, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5565461820025777e-05, + "loss": 3.4835, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557075872515257e-05, + "loss": 3.4661, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5548689925004737e-05, + "loss": 3.4766, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540303977494214e-05, + "loss": 3.4765, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.553193440878743e-05, + "loss": 3.4888, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.552354846127691e-05, + "loss": 3.4778, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515162513766383e-05, + "loss": 3.4745, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5506776566255863e-05, + "loss": 3.4761, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498390618745343e-05, + "loss": 3.4814, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.549002105003856e-05, + "loss": 3.4717, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5481635102528035e-05, + "loss": 3.4602, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473249155017515e-05, + "loss": 3.4772, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5464863207506995e-05, + "loss": 3.486, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.545649363880021e-05, + "loss": 3.4846, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448107691289684e-05, + "loss": 3.4664, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5439721743779167e-05, + "loss": 3.4821, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5431335796268647e-05, + "loss": 3.4757, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5422966227561856e-05, + "loss": 3.4856, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5414580280051336e-05, + "loss": 3.4794, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5406194332540816e-05, + "loss": 3.4808, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5397808385030296e-05, + "loss": 3.4731, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.538943881632351e-05, + "loss": 3.4831, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.538105286881299e-05, + "loss": 3.4628, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.537266692130247e-05, + "loss": 3.48, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.536428097379195e-05, + "loss": 3.4728, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5355911405085158e-05, + "loss": 3.4757, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5347525457574638e-05, + "loss": 3.4684, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.533913951006412e-05, + "loss": 3.4824, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.53307535625536e-05, + "loss": 3.467, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.532238399384681e-05, + "loss": 3.4752, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.531399804633629e-05, + "loss": 3.479, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.530561209882577e-05, + "loss": 3.4736, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.529722615131525e-05, + "loss": 3.4839, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.528884020380473e-05, + "loss": 3.4843, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5280470635097942e-05, + "loss": 3.4787, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272084687587422e-05, + "loss": 3.4851, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5263698740076902e-05, + "loss": 3.4774, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255312792566382e-05, + "loss": 3.472, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.524694322385959e-05, + "loss": 3.4705, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5238557276349075e-05, + "loss": 3.4736, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5230171328838555e-05, + "loss": 3.4781, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5221785381328035e-05, + "loss": 3.4812, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5213415812621244e-05, + "loss": 3.4756, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205029865110724e-05, + "loss": 3.4821, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5196643917600204e-05, + "loss": 3.473, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188257970089684e-05, + "loss": 3.4743, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5179888401382896e-05, + "loss": 3.4757, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5171502453872376e-05, + "loss": 3.4861, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5163116506361856e-05, + "loss": 3.4766, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5154730558851336e-05, + "loss": 3.4671, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5146360990144545e-05, + "loss": 3.4618, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5137975042634025e-05, + "loss": 3.4814, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5129589095123508e-05, + "loss": 3.4806, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5121203147612988e-05, + "loss": 3.4815, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5112833578906197e-05, + "loss": 3.4743, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5104447631395677e-05, + "loss": 3.4859, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096061683885157e-05, + "loss": 3.476, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5087675736374637e-05, + "loss": 3.4818, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.507930616766785e-05, + "loss": 3.4736, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.507092022015733e-05, + "loss": 3.478, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.506253427264681e-05, + "loss": 3.4778, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.505414832513629e-05, + "loss": 3.467, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.50457787564295e-05, + "loss": 3.4849, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.503739280891898e-05, + "loss": 3.4827, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029006861408462e-05, + "loss": 3.4795, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5020620913897942e-05, + "loss": 3.4749, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.501225134519115e-05, + "loss": 3.471, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.870182514190674, + "eval_runtime": 303.1388, + "eval_samples_per_second": 1258.799, + "eval_steps_per_second": 39.338, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500386539768063e-05, + "loss": 3.475, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499547945017011e-05, + "loss": 3.475, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498709350265959e-05, + "loss": 3.4777, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497870755514907e-05, + "loss": 3.4788, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970337986442283e-05, + "loss": 3.4903, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4961952038931763e-05, + "loss": 3.4766, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953566091421243e-05, + "loss": 3.4626, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4945180143910723e-05, + "loss": 3.4663, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4936810575203932e-05, + "loss": 3.4817, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928424627693416e-05, + "loss": 3.4811, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920038680182896e-05, + "loss": 3.4652, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911652732672372e-05, + "loss": 3.4827, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903283163965585e-05, + "loss": 3.4727, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4894897216455065e-05, + "loss": 3.4729, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886511268944545e-05, + "loss": 3.4681, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878125321434024e-05, + "loss": 3.4686, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869755752727237e-05, + "loss": 3.4679, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861369805216717e-05, + "loss": 3.4659, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4852983857706197e-05, + "loss": 3.4829, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844597910195673e-05, + "loss": 3.4855, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836228341488886e-05, + "loss": 3.4786, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482784239397837e-05, + "loss": 3.4725, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819456446467846e-05, + "loss": 3.4744, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811070498957326e-05, + "loss": 3.479, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802700930250538e-05, + "loss": 3.4711, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794314982740018e-05, + "loss": 3.4727, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4785929035229495e-05, + "loss": 3.463, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777543087718978e-05, + "loss": 3.4756, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476917351901219e-05, + "loss": 3.4628, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476078757150167e-05, + "loss": 3.4581, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752401623991147e-05, + "loss": 3.4798, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744015676480627e-05, + "loss": 3.4736, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.473564610777384e-05, + "loss": 3.4825, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.472726016026332e-05, + "loss": 3.4797, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.47188742127528e-05, + "loss": 3.469, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.471048826524228e-05, + "loss": 3.4785, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702118696535492e-05, + "loss": 3.4711, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469373274902497e-05, + "loss": 3.4629, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468534680151445e-05, + "loss": 3.4574, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4676960854003932e-05, + "loss": 3.4637, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668591285297144e-05, + "loss": 3.4636, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.466020533778662e-05, + "loss": 3.4795, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.46518193902761e-05, + "loss": 3.4684, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464343344276558e-05, + "loss": 3.4677, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635063874058793e-05, + "loss": 3.4808, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626677926548273e-05, + "loss": 3.4675, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618291979037753e-05, + "loss": 3.4752, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4609906031527233e-05, + "loss": 3.4612, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601536462820442e-05, + "loss": 3.4456, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593150515309922e-05, + "loss": 3.4836, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4584764567799402e-05, + "loss": 3.478, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576378620288885e-05, + "loss": 3.4744, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568009051582095e-05, + "loss": 3.467, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559623104071575e-05, + "loss": 3.4628, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551237156561054e-05, + "loss": 3.4601, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542851209050534e-05, + "loss": 3.4655, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534481640343747e-05, + "loss": 3.4654, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526095692833227e-05, + "loss": 3.4678, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517709745322707e-05, + "loss": 3.4745, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509323797812187e-05, + "loss": 3.4675, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4500954229105396e-05, + "loss": 3.458, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492568281594876e-05, + "loss": 3.4804, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484182334084356e-05, + "loss": 3.4563, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447579638657384e-05, + "loss": 3.4589, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467426817867048e-05, + "loss": 3.4745, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459040870356528e-05, + "loss": 3.477, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450654922846008e-05, + "loss": 3.4518, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442268975335488e-05, + "loss": 3.466, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.44338994066287e-05, + "loss": 3.4534, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442551345911818e-05, + "loss": 3.4735, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441712751160766e-05, + "loss": 3.4724, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440874156409714e-05, + "loss": 3.4648, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440037199539035e-05, + "loss": 3.4704, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439198604787983e-05, + "loss": 3.4688, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438360010036931e-05, + "loss": 3.4854, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375214152858793e-05, + "loss": 3.4611, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4366844584152002e-05, + "loss": 3.474, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358458636641482e-05, + "loss": 3.4746, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350072689130962e-05, + "loss": 3.4552, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4341686741620442e-05, + "loss": 3.4742, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333317172913654e-05, + "loss": 3.4683, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4324931225403134e-05, + "loss": 3.478, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316545277892614e-05, + "loss": 3.4738, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308159330382094e-05, + "loss": 3.4551, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.429977338287157e-05, + "loss": 3.459, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291403814164783e-05, + "loss": 3.4594, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283017866654263e-05, + "loss": 3.4807, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274631919143743e-05, + "loss": 3.4652, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266245971633223e-05, + "loss": 3.4626, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4257876402926436e-05, + "loss": 3.4633, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249490455415915e-05, + "loss": 3.4724, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241104507905392e-05, + "loss": 3.4609, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4232718560394872e-05, + "loss": 3.4468, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224348991688088e-05, + "loss": 3.4665, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4215963044177568e-05, + "loss": 3.4698, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207577096667044e-05, + "loss": 3.4749, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199191149156524e-05, + "loss": 3.4555, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190821580449737e-05, + "loss": 3.4683, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182435632939217e-05, + "loss": 3.4652, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174049685428697e-05, + "loss": 3.4721, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165663737918177e-05, + "loss": 3.4694, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415729416921139e-05, + "loss": 3.4703, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4148908221700866e-05, + "loss": 3.4628, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140522274190346e-05, + "loss": 3.4708, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132136326679826e-05, + "loss": 3.45, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.412375037916931e-05, + "loss": 3.4648, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115380810462518e-05, + "loss": 3.4596, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4106994862951998e-05, + "loss": 3.4698, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098608915441478e-05, + "loss": 3.4529, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090222967930958e-05, + "loss": 3.4718, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.408185339922417e-05, + "loss": 3.4587, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.407346745171365e-05, + "loss": 3.4638, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.406508150420313e-05, + "loss": 3.4649, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405669555669261e-05, + "loss": 3.4622, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404832598798582e-05, + "loss": 3.4715, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.40399400404753e-05, + "loss": 3.4766, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.403155409296478e-05, + "loss": 3.4681, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023168145454263e-05, + "loss": 3.4721, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014798576747472e-05, + "loss": 3.4685, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006412629236952e-05, + "loss": 3.4582, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998026681726432e-05, + "loss": 3.4532, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.398964073421591e-05, + "loss": 3.4652, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981271165509124e-05, + "loss": 3.4642, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3972885217998604e-05, + "loss": 3.4661, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964499270488084e-05, + "loss": 3.4651, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956113322977564e-05, + "loss": 3.468, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947743754270773e-05, + "loss": 3.4621, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939357806760253e-05, + "loss": 3.4628, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3930971859249733e-05, + "loss": 3.4601, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922585911739216e-05, + "loss": 3.4715, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914216343032425e-05, + "loss": 3.4655, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905830395521905e-05, + "loss": 3.4547, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897444448011385e-05, + "loss": 3.4481, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889058500500865e-05, + "loss": 3.4712, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880688931794078e-05, + "loss": 3.4688, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872302984283558e-05, + "loss": 3.4694, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3863917036773038e-05, + "loss": 3.4662, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855531089262518e-05, + "loss": 3.4739, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847161520555727e-05, + "loss": 3.4645, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838775573045207e-05, + "loss": 3.4729, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830389625534687e-05, + "loss": 3.4622, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.382200367802417e-05, + "loss": 3.465, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3813617730513647e-05, + "loss": 3.4607, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380524816180686e-05, + "loss": 3.4611, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.379686221429634e-05, + "loss": 3.4719, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788476266785816e-05, + "loss": 3.4703, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780090319275296e-05, + "loss": 3.4692, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.377172075056851e-05, + "loss": 3.4622, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376333480305799e-05, + "loss": 3.4648, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8717551231384277, + "eval_runtime": 304.0029, + "eval_samples_per_second": 1255.221, + "eval_steps_per_second": 39.227, + "step": 1602720 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.070566535216296e+18, + "trial_name": null, + "trial_params": null +}