| { | |
| "best_metric": 0.07271432131528854, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.03939528241493081, | |
| "eval_steps": 25, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00019697641207465407, | |
| "grad_norm": 3.348949670791626, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.0606, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019697641207465407, | |
| "eval_loss": 0.360129714012146, | |
| "eval_runtime": 10.5317, | |
| "eval_samples_per_second": 4.748, | |
| "eval_steps_per_second": 0.665, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00039395282414930814, | |
| "grad_norm": 3.371903657913208, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.0354, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005909292362239622, | |
| "grad_norm": 2.8037610054016113, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.9175, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007879056482986163, | |
| "grad_norm": 1.5464385747909546, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.5709, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009848820603732703, | |
| "grad_norm": 1.5053009986877441, | |
| "learning_rate": 0.00015, | |
| "loss": 0.5139, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011818584724479244, | |
| "grad_norm": 1.4200072288513184, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.5191, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013788348845225785, | |
| "grad_norm": 1.2713923454284668, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.5693, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0015758112965972325, | |
| "grad_norm": 2.9913175106048584, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.4701, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0017727877086718866, | |
| "grad_norm": 3.1078169345855713, | |
| "learning_rate": 0.00027, | |
| "loss": 0.4946, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0019697641207465405, | |
| "grad_norm": 1.0796478986740112, | |
| "learning_rate": 0.0003, | |
| "loss": 0.552, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0021667405328211946, | |
| "grad_norm": 0.8546186685562134, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.4502, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0023637169448958487, | |
| "grad_norm": 1.210360050201416, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.4655, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002560693356970503, | |
| "grad_norm": 1.6150785684585571, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.4661, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002757669769045157, | |
| "grad_norm": 0.7436849474906921, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.366, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002954646181119811, | |
| "grad_norm": 0.7962251901626587, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.4605, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003151622593194465, | |
| "grad_norm": 0.9352697134017944, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.382, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003348599005269119, | |
| "grad_norm": 0.9323279857635498, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.5812, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0035455754173437733, | |
| "grad_norm": 0.8441579937934875, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.4787, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003742551829418427, | |
| "grad_norm": 1.0008450746536255, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.3968, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003939528241493081, | |
| "grad_norm": 0.7684171199798584, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.3796, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004136504653567736, | |
| "grad_norm": 1.0816248655319214, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.4181, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004333481065642389, | |
| "grad_norm": 0.8110284209251404, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.3604, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004530457477717044, | |
| "grad_norm": 2.4406509399414062, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.4562, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004727433889791697, | |
| "grad_norm": 1.13535475730896, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.4112, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004924410301866351, | |
| "grad_norm": 0.845367968082428, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.4399, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004924410301866351, | |
| "eval_loss": 0.11439956724643707, | |
| "eval_runtime": 12.8261, | |
| "eval_samples_per_second": 3.898, | |
| "eval_steps_per_second": 0.546, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005121386713941006, | |
| "grad_norm": 0.7668648362159729, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.4863, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005318363126015659, | |
| "grad_norm": 0.8414048552513123, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.4708, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005515339538090314, | |
| "grad_norm": 0.9618905782699585, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.4237, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0057123159501649675, | |
| "grad_norm": 0.7617946267127991, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.3429, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005909292362239622, | |
| "grad_norm": 1.3151721954345703, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.5637, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006106268774314276, | |
| "grad_norm": 1.2373560667037964, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.4711, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.00630324518638893, | |
| "grad_norm": 0.9699512124061584, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.3827, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.006500221598463584, | |
| "grad_norm": 1.1460570096969604, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.4132, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.006697198010538238, | |
| "grad_norm": 1.2482142448425293, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.4066, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.006894174422612892, | |
| "grad_norm": 1.0130342245101929, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.4401, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007091150834687547, | |
| "grad_norm": 1.153891921043396, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.3825, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0072881272467622, | |
| "grad_norm": 1.4242093563079834, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.3514, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007485103658836854, | |
| "grad_norm": 0.8260576725006104, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.38, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.007682080070911508, | |
| "grad_norm": 1.6134790182113647, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.3237, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.007879056482986162, | |
| "grad_norm": 1.4775500297546387, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.503, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008076032895060816, | |
| "grad_norm": 1.2248170375823975, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.3367, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.008273009307135471, | |
| "grad_norm": 5.347848415374756, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.3759, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.008469985719210125, | |
| "grad_norm": 1.2572146654129028, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.3936, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.008666962131284778, | |
| "grad_norm": 1.1421171426773071, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.2144, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.008863938543359432, | |
| "grad_norm": 0.9987139701843262, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.217, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009060914955434088, | |
| "grad_norm": 1.9025821685791016, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.2224, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.009257891367508741, | |
| "grad_norm": 0.7751299738883972, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.1837, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.009454867779583395, | |
| "grad_norm": 2.193005084991455, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.1896, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.009651844191658049, | |
| "grad_norm": 1.596818447113037, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.2651, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.009848820603732702, | |
| "grad_norm": 10.099899291992188, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.4042, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009848820603732702, | |
| "eval_loss": 0.14771892130374908, | |
| "eval_runtime": 10.3847, | |
| "eval_samples_per_second": 4.815, | |
| "eval_steps_per_second": 0.674, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010045797015807358, | |
| "grad_norm": 2.2570748329162598, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 0.6271, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.010242773427882011, | |
| "grad_norm": 1.3872201442718506, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 0.47, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.010439749839956665, | |
| "grad_norm": 0.9401403665542603, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 0.443, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.010636726252031319, | |
| "grad_norm": 0.6595192551612854, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 0.3299, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.010833702664105974, | |
| "grad_norm": 0.527516782283783, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 0.2561, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.011030679076180628, | |
| "grad_norm": 0.5898721814155579, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 0.3284, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.011227655488255281, | |
| "grad_norm": 0.6567277908325195, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 0.3464, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.011424631900329935, | |
| "grad_norm": 0.6930991411209106, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 0.3655, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.01162160831240459, | |
| "grad_norm": 0.6276407241821289, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 0.3158, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.011818584724479244, | |
| "grad_norm": 0.6224534511566162, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 0.3519, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.012015561136553898, | |
| "grad_norm": 0.6579044461250305, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 0.3508, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.012212537548628551, | |
| "grad_norm": 0.5916846394538879, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 0.3069, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.012409513960703205, | |
| "grad_norm": 0.6183111071586609, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 0.2878, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.01260649037277786, | |
| "grad_norm": 0.6713694334030151, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 0.3213, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.012803466784852514, | |
| "grad_norm": 0.8130861520767212, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 0.3197, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.013000443196927168, | |
| "grad_norm": 0.4906407594680786, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 0.2504, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.013197419609001821, | |
| "grad_norm": 0.6218925714492798, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.2868, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.013394396021076477, | |
| "grad_norm": 0.6536829471588135, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 0.2905, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.01359137243315113, | |
| "grad_norm": 0.5276692509651184, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 0.2757, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.013788348845225784, | |
| "grad_norm": 0.8190099000930786, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 0.3012, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.013985325257300438, | |
| "grad_norm": 0.7881957292556763, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 0.2993, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.014182301669375093, | |
| "grad_norm": 0.8249359726905823, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 0.3406, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.014379278081449747, | |
| "grad_norm": 0.9758163690567017, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 0.2938, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.0145762544935244, | |
| "grad_norm": 0.6984056234359741, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 0.2965, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.014773230905599054, | |
| "grad_norm": 0.8371394276618958, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 0.3191, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.014773230905599054, | |
| "eval_loss": 0.0825795829296112, | |
| "eval_runtime": 10.3801, | |
| "eval_samples_per_second": 4.817, | |
| "eval_steps_per_second": 0.674, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.014970207317673708, | |
| "grad_norm": 0.6708223223686218, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 0.3168, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.015167183729748363, | |
| "grad_norm": 0.6277792453765869, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 0.2699, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.015364160141823017, | |
| "grad_norm": 1.0930883884429932, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 0.3786, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.01556113655389767, | |
| "grad_norm": 0.6358778476715088, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 0.3144, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.015758112965972324, | |
| "grad_norm": 0.7981488108634949, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 0.3314, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.015955089378046978, | |
| "grad_norm": 0.7823123335838318, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 0.2656, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.01615206579012163, | |
| "grad_norm": 0.6537957787513733, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 0.316, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.01634904220219629, | |
| "grad_norm": 0.6539929509162903, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 0.2713, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.016546018614270942, | |
| "grad_norm": 1.0729496479034424, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 0.2545, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.016742995026345596, | |
| "grad_norm": 0.7264039516448975, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 0.3414, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.01693997143842025, | |
| "grad_norm": 0.7242591977119446, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.275, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.017136947850494903, | |
| "grad_norm": 0.860544741153717, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 0.2932, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.017333924262569557, | |
| "grad_norm": 0.851104199886322, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 0.2768, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.01753090067464421, | |
| "grad_norm": 0.8001173138618469, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 0.2581, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.017727877086718864, | |
| "grad_norm": 1.0649043321609497, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 0.3063, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.017924853498793518, | |
| "grad_norm": 0.90488201379776, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 0.2846, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.018121829910868175, | |
| "grad_norm": 0.955570638179779, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 0.3494, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.01831880632294283, | |
| "grad_norm": 1.2587333917617798, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 0.2484, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.018515782735017482, | |
| "grad_norm": 0.7618815898895264, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 0.2205, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.018712759147092136, | |
| "grad_norm": 0.8597466945648193, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 0.2238, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.01890973555916679, | |
| "grad_norm": 1.390031099319458, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 0.2533, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.019106711971241443, | |
| "grad_norm": 0.9729688763618469, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 0.1609, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.019303688383316097, | |
| "grad_norm": 0.6992880702018738, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 0.1844, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.01950066479539075, | |
| "grad_norm": 1.1221824884414673, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 0.2346, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.019697641207465404, | |
| "grad_norm": 2.233081817626953, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 0.4078, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.019697641207465404, | |
| "eval_loss": 0.11340178549289703, | |
| "eval_runtime": 12.7864, | |
| "eval_samples_per_second": 3.91, | |
| "eval_steps_per_second": 0.547, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01989461761954006, | |
| "grad_norm": 1.3194266557693481, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 0.4517, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.020091594031614715, | |
| "grad_norm": 1.0158177614212036, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 0.4222, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.02028857044368937, | |
| "grad_norm": 0.84644615650177, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 0.3635, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.020485546855764022, | |
| "grad_norm": 0.6677044630050659, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 0.2531, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.020682523267838676, | |
| "grad_norm": 0.5319753289222717, | |
| "learning_rate": 0.00015, | |
| "loss": 0.2562, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.02087949967991333, | |
| "grad_norm": 0.5926326513290405, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 0.3177, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.021076476091987983, | |
| "grad_norm": 0.8615707755088806, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 0.2798, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.021273452504062637, | |
| "grad_norm": 0.5553646683692932, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 0.3154, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.021470428916137294, | |
| "grad_norm": 0.42339223623275757, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 0.2716, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.021667405328211948, | |
| "grad_norm": 0.46130532026290894, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 0.217, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0218643817402866, | |
| "grad_norm": 0.42555496096611023, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 0.2988, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.022061358152361255, | |
| "grad_norm": 0.47253310680389404, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 0.2824, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.02225833456443591, | |
| "grad_norm": 0.7298460602760315, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 0.2986, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.022455310976510563, | |
| "grad_norm": 0.575012743473053, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 0.2342, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.022652287388585216, | |
| "grad_norm": 0.5378597974777222, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 0.2058, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.02284926380065987, | |
| "grad_norm": 0.8967413902282715, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 0.3315, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.023046240212734524, | |
| "grad_norm": 0.6629744172096252, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 0.3345, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.02324321662480918, | |
| "grad_norm": 0.5112919807434082, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 0.2614, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.023440193036883834, | |
| "grad_norm": 0.34445106983184814, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 0.2409, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.023637169448958488, | |
| "grad_norm": 0.5876243710517883, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 0.2454, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02383414586103314, | |
| "grad_norm": 0.5282692909240723, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 0.283, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.024031122273107795, | |
| "grad_norm": 0.8354734778404236, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 0.3019, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.02422809868518245, | |
| "grad_norm": 0.5572185516357422, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 0.2843, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.024425075097257103, | |
| "grad_norm": 0.4937724173069, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.2486, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.024622051509331756, | |
| "grad_norm": 0.658233106136322, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 0.2915, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.024622051509331756, | |
| "eval_loss": 0.07672200351953506, | |
| "eval_runtime": 10.6957, | |
| "eval_samples_per_second": 4.675, | |
| "eval_steps_per_second": 0.654, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.02481902792140641, | |
| "grad_norm": 0.6942847967147827, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 0.3618, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.025016004333481067, | |
| "grad_norm": 0.9075064063072205, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 0.3206, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.02521298074555572, | |
| "grad_norm": 0.5630618333816528, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 0.2901, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.025409957157630374, | |
| "grad_norm": 0.5655243396759033, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 0.2592, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.025606933569705028, | |
| "grad_norm": 0.6408135890960693, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 0.3255, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02580390998177968, | |
| "grad_norm": 0.4605986177921295, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 0.2667, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.026000886393854335, | |
| "grad_norm": 0.6698881387710571, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 0.2609, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.02619786280592899, | |
| "grad_norm": 0.5498625636100769, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 0.2256, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.026394839218003643, | |
| "grad_norm": 0.5972995162010193, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 0.2337, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.0265918156300783, | |
| "grad_norm": 0.9262932538986206, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 0.4045, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.026788792042152954, | |
| "grad_norm": 0.7597740888595581, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 0.3238, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.026985768454227607, | |
| "grad_norm": 0.6598590612411499, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 0.2864, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.02718274486630226, | |
| "grad_norm": 1.9483425617218018, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 0.2428, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.027379721278376914, | |
| "grad_norm": 0.6512977480888367, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 0.2453, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.027576697690451568, | |
| "grad_norm": 0.864540159702301, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 0.2991, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.027773674102526222, | |
| "grad_norm": 0.7853538393974304, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 0.2653, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.027970650514600875, | |
| "grad_norm": 0.6818575263023376, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 0.2376, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.02816762692667553, | |
| "grad_norm": 0.8303399085998535, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.2446, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.028364603338750186, | |
| "grad_norm": 0.4680931270122528, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 0.1331, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.02856157975082484, | |
| "grad_norm": 0.6611976623535156, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 0.1828, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.028758556162899494, | |
| "grad_norm": 0.5369855761528015, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 0.1183, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.028955532574974147, | |
| "grad_norm": 0.8444812893867493, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 0.1247, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.0291525089870488, | |
| "grad_norm": 0.8747226595878601, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 0.1633, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.029349485399123455, | |
| "grad_norm": 0.8830420970916748, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 0.1816, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.029546461811198108, | |
| "grad_norm": 3.1225264072418213, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 0.2376, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.029546461811198108, | |
| "eval_loss": 0.08567950874567032, | |
| "eval_runtime": 9.1661, | |
| "eval_samples_per_second": 5.455, | |
| "eval_steps_per_second": 0.764, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.029743438223272762, | |
| "grad_norm": 0.9880196452140808, | |
| "learning_rate": 4.659698863221513e-05, | |
| "loss": 0.3546, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.029940414635347416, | |
| "grad_norm": 0.7226404547691345, | |
| "learning_rate": 4.481448235912671e-05, | |
| "loss": 0.2702, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.030137391047422073, | |
| "grad_norm": 0.8038386702537537, | |
| "learning_rate": 4.306073275629044e-05, | |
| "loss": 0.3077, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.030334367459496726, | |
| "grad_norm": 0.6242251396179199, | |
| "learning_rate": 4.133621928133665e-05, | |
| "loss": 0.2612, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.03053134387157138, | |
| "grad_norm": 0.6672581434249878, | |
| "learning_rate": 3.964141339903026e-05, | |
| "loss": 0.2917, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.030728320283646034, | |
| "grad_norm": 0.5822924375534058, | |
| "learning_rate": 3.797677845237696e-05, | |
| "loss": 0.3038, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.030925296695720687, | |
| "grad_norm": 0.5603398680686951, | |
| "learning_rate": 3.634276953594982e-05, | |
| "loss": 0.2806, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.03112227310779534, | |
| "grad_norm": 0.526652991771698, | |
| "learning_rate": 3.473983337147118e-05, | |
| "loss": 0.3352, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.031319249519869995, | |
| "grad_norm": 0.5369526147842407, | |
| "learning_rate": 3.316840818568315e-05, | |
| "loss": 0.2806, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.03151622593194465, | |
| "grad_norm": 0.4179346263408661, | |
| "learning_rate": 3.162892359054098e-05, | |
| "loss": 0.2744, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0317132023440193, | |
| "grad_norm": 0.6778124570846558, | |
| "learning_rate": 3.0121800465761293e-05, | |
| "loss": 0.2826, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.031910178756093956, | |
| "grad_norm": 0.37569910287857056, | |
| "learning_rate": 2.8647450843757897e-05, | |
| "loss": 0.2533, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.03210715516816861, | |
| "grad_norm": 0.33460506796836853, | |
| "learning_rate": 2.7206277796996144e-05, | |
| "loss": 0.2703, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.03230413158024326, | |
| "grad_norm": 0.5205643177032471, | |
| "learning_rate": 2.5798675327796993e-05, | |
| "loss": 0.3269, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.03250110799231792, | |
| "grad_norm": 0.8476812243461609, | |
| "learning_rate": 2.4425028260620715e-05, | |
| "loss": 0.3097, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.03269808440439258, | |
| "grad_norm": 0.48694828152656555, | |
| "learning_rate": 2.3085712136859668e-05, | |
| "loss": 0.2699, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.03289506081646723, | |
| "grad_norm": 0.7992863655090332, | |
| "learning_rate": 2.178109311216913e-05, | |
| "loss": 0.2547, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.033092037228541885, | |
| "grad_norm": 0.489131361246109, | |
| "learning_rate": 2.0511527856363912e-05, | |
| "loss": 0.2847, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.03328901364061654, | |
| "grad_norm": 0.7267995476722717, | |
| "learning_rate": 1.927736345590839e-05, | |
| "loss": 0.1622, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.03348599005269119, | |
| "grad_norm": 0.4803732633590698, | |
| "learning_rate": 1.8078937319026654e-05, | |
| "loss": 0.2689, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.033682966464765846, | |
| "grad_norm": 0.4199903905391693, | |
| "learning_rate": 1.6916577083458228e-05, | |
| "loss": 0.299, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.0338799428768405, | |
| "grad_norm": 0.36284616589546204, | |
| "learning_rate": 1.579060052688548e-05, | |
| "loss": 0.262, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.03407691928891515, | |
| "grad_norm": 0.4913172423839569, | |
| "learning_rate": 1.4701315480056164e-05, | |
| "loss": 0.2382, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.03427389570098981, | |
| "grad_norm": 0.701080322265625, | |
| "learning_rate": 1.3649019742625623e-05, | |
| "loss": 0.2878, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.03447087211306446, | |
| "grad_norm": 0.4284681975841522, | |
| "learning_rate": 1.2634001001741373e-05, | |
| "loss": 0.2711, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.03447087211306446, | |
| "eval_loss": 0.07281436771154404, | |
| "eval_runtime": 11.8755, | |
| "eval_samples_per_second": 4.21, | |
| "eval_steps_per_second": 0.589, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.034667848525139114, | |
| "grad_norm": 0.5271365642547607, | |
| "learning_rate": 1.1656536753392287e-05, | |
| "loss": 0.2571, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.03486482493721377, | |
| "grad_norm": 0.4727443754673004, | |
| "learning_rate": 1.0716894226543953e-05, | |
| "loss": 0.2677, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.03506180134928842, | |
| "grad_norm": 0.37858378887176514, | |
| "learning_rate": 9.815330310080887e-06, | |
| "loss": 0.2534, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.035258777761363075, | |
| "grad_norm": 0.4432028830051422, | |
| "learning_rate": 8.952091482575824e-06, | |
| "loss": 0.3306, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.03545575417343773, | |
| "grad_norm": 0.4843367636203766, | |
| "learning_rate": 8.127413744904804e-06, | |
| "loss": 0.2407, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03565273058551238, | |
| "grad_norm": 0.5236724615097046, | |
| "learning_rate": 7.34152255572697e-06, | |
| "loss": 0.2688, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.035849706997587036, | |
| "grad_norm": 0.688205897808075, | |
| "learning_rate": 6.594632769846353e-06, | |
| "loss": 0.3668, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.036046683409661696, | |
| "grad_norm": 0.4552861452102661, | |
| "learning_rate": 5.886948579472778e-06, | |
| "loss": 0.275, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.03624365982173635, | |
| "grad_norm": 0.5080707669258118, | |
| "learning_rate": 5.218663458397715e-06, | |
| "loss": 0.2851, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.036440636233811004, | |
| "grad_norm": 0.43050211668014526, | |
| "learning_rate": 4.589960109100444e-06, | |
| "loss": 0.2722, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.03663761264588566, | |
| "grad_norm": 0.548950731754303, | |
| "learning_rate": 4.001010412799138e-06, | |
| "loss": 0.2045, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.03683458905796031, | |
| "grad_norm": 0.42442962527275085, | |
| "learning_rate": 3.451975382460109e-06, | |
| "loss": 0.3006, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.037031565470034965, | |
| "grad_norm": 0.5989577174186707, | |
| "learning_rate": 2.9430051187785962e-06, | |
| "loss": 0.1922, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.03722854188210962, | |
| "grad_norm": 0.528300404548645, | |
| "learning_rate": 2.4742387691426445e-06, | |
| "loss": 0.2248, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.03742551829418427, | |
| "grad_norm": 0.5548564195632935, | |
| "learning_rate": 2.0458044895916513e-06, | |
| "loss": 0.2838, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.037622494706258926, | |
| "grad_norm": 0.6061025857925415, | |
| "learning_rate": 1.6578194097797258e-06, | |
| "loss": 0.2634, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.03781947111833358, | |
| "grad_norm": 0.6724241971969604, | |
| "learning_rate": 1.3103896009537207e-06, | |
| "loss": 0.3241, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.03801644753040823, | |
| "grad_norm": 0.629009485244751, | |
| "learning_rate": 1.0036100469542786e-06, | |
| "loss": 0.2181, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.03821342394248289, | |
| "grad_norm": 0.6329449415206909, | |
| "learning_rate": 7.375646182482875e-07, | |
| "loss": 0.1653, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.03841040035455754, | |
| "grad_norm": 0.5899990200996399, | |
| "learning_rate": 5.123260489995229e-07, | |
| "loss": 0.2021, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.038607376766632194, | |
| "grad_norm": 0.6992418169975281, | |
| "learning_rate": 3.2795591718381975e-07, | |
| "loss": 0.1811, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.03880435317870685, | |
| "grad_norm": 0.7541390657424927, | |
| "learning_rate": 1.8450462775428942e-07, | |
| "loss": 0.1525, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.0390013295907815, | |
| "grad_norm": 0.5883744955062866, | |
| "learning_rate": 8.201139886109264e-08, | |
| "loss": 0.143, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.039198306002856155, | |
| "grad_norm": 0.8709452748298645, | |
| "learning_rate": 2.0504251129649374e-08, | |
| "loss": 0.1841, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.03939528241493081, | |
| "grad_norm": 0.9281623363494873, | |
| "learning_rate": 0.0, | |
| "loss": 0.2595, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03939528241493081, | |
| "eval_loss": 0.07271432131528854, | |
| "eval_runtime": 12.7749, | |
| "eval_samples_per_second": 3.914, | |
| "eval_steps_per_second": 0.548, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.47763455488426e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |