| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03990547390867882, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00019952736954339408, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.499999999999999e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019952736954339408, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1848.0137, | |
| "eval_samples_per_second": 9.135, | |
| "eval_steps_per_second": 4.568, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00039905473908678817, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005985821086301823, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2499999999999998e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007981094781735763, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009976368477169705, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.75e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011971642172603646, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013966915868037586, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2499999999999995e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0015962189563471527, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0017957463258905467, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.75e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001995273695433941, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002194801064977335, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.25e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002394328434520729, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002593855804064123, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.75e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0027933831736075172, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010499999999999999, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002992910543150911, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001125, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0031924379126943053, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0033919652822376996, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012749999999999998, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0035914926517810935, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000135, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0037910200213244877, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001425, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003990547390867882, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004190074760411276, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014998857713672935, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00438960212995467, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014995431202643217, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004589129499498064, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000149897215106593, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004788656869041458, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001498173037694868, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004988184238584852, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001497146023568809, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005187711608128246, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014958914215262048, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005387238977671641, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014944096137309914, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0055867663472150345, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014927010515561776, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.005786293716758428, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014907662554463532, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005985821086301822, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001488605814759156, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006185348455845217, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014862203875857477, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.006384875825388611, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001483610700550354, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0065844031949320045, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014807775485889264, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.006783930564475399, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001477721794706997, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.006983457934018793, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001474444369716801, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007182985303562187, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001470946271953739, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.007382512673105581, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014672285669722765, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0075820400426489755, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014632923872213652, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.007781567412192369, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014591389316994876, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.007981094781735764, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001454769465589431, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008180622151279158, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014501853198729012, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.008380149520822552, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014453878909250904, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.008579676890365946, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014403786400893302, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.00877920425990934, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014351590932319504, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.008978731629452733, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014297308402774875, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009178258998996129, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001424095534724375, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.009377786368539523, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014182548931412757, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.009577313738082916, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001412210694644195, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.00977684110762631, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014059647803545467, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.009976368477169704, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001399519052838329, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009976368477169704, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1847.8631, | |
| "eval_samples_per_second": 9.136, | |
| "eval_steps_per_second": 4.568, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010175895846713098, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013928754755265842, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.010375423216256492, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013860360721173193, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.010574950585799886, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001379002925959068, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.010774477955343281, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001371778179416281, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.010974005324886675, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013643640332167438, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.011173532694430069, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013567627457812106, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.011373060063973463, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013489766325354695, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.011572587433516857, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013410080652050412, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.01177211480306025, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001332859471092728, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.011971642172603644, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013245333323392333, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01217116954214704, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001316032185167079, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.012370696911690434, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013073586191080457, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.012570224281233828, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012985152762143778, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.012769751650777221, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012895048502539882, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.012969279020320615, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012803300858899104, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.013168806389864009, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001270993777844248, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.013368333759407403, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001261498770046874, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.013567861128950798, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012518479547691435, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.013767388498494192, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012420442717428804, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.013966915868037586, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012320907072649044, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01416644323758098, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001221990293287378, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.014365970607124374, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012117461064942435, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.014565497976667768, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012013612673640363, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.014765025346211161, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011908389392193547, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.014964552715754557, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011801823272632844, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.015164080085297951, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011693946776030599, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.015363607454841345, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011584792762612703, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.015563134824384739, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011474394481749035, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.015762662193928134, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011362785561825406, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.015962189563471528, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001125, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.016161716933014922, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011136072151847529, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.016361244302558316, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011021036720894179, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.01656077167210171, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010904928748046599, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.016760299041645103, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001078778360091808, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.016959826411188497, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010669636963055245, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.01715935378073189, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010550524823068502, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.017358881150275285, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010430483463669551, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.01755840851981868, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001030954945061934, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.017757935889362073, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001018775962158975, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.017957463258905466, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010065151074942516, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01815699062844886, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.941761158428674e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.018356517997992258, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.817627457812105e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.01855604536753565, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.692787785420525e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.018755572737079045, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.567280168627493e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.01895510010662244, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.441142838268905e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.019154627476165833, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.314414216997507e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.019354154845709227, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.187132907578987e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.01955368221525262, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.059337681133192e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.019753209584796014, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.931067465324085e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.01995273695433941, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.802361332501978e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01995273695433941, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2915.8692, | |
| "eval_samples_per_second": 5.79, | |
| "eval_steps_per_second": 2.895, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.020152264323882802, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.673258487801731e-05, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.020351791693426196, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.54379825720049e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.02055131906296959, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.414020075538605e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.020750846432512984, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.2839634745074e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.020950373802056377, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.153668070607437e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.02114990117159977, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.023173553080938e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.02134942854114317, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.89251967182208e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.021548955910686562, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.761746225268758e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.021748483280229956, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.630893048279627e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.02194801064977335, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.022147538019316744, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.369106951720373e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.022347065388860138, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.238253774731244e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.02254659275840353, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.10748032817792e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.022746120127946926, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.976826446919059e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.02294564749749032, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.846331929392562e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.023145174867033713, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.7160365254926e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.023344702236577107, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.585979924461394e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.0235442296061205, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.45620174279951e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.023743756975663895, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.326741512198266e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.02394328434520729, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.197638667498022e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.024142811714750686, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.068932534675913e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.02434233908429408, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9406623188668055e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.024541866453837474, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.812867092421013e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.024741393823380867, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.685585783002493e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.02494092119292426, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.558857161731093e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.025140448562467655, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4327198313725064e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.02533997593201105, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.307212214579474e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.025539503301554443, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.182372542187895e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.025739030671097837, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.058238841571326e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.02593855804064123, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.934848925057484e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.026138085410184624, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.812240378410248e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.026337612779728018, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.690450549380659e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.026537140149271412, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.569516536330447e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.026736667518814806, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.449475176931499e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.026936194888358203, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3303630369447554e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.027135722257901597, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.212216399081918e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.02733524962744499, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.095071251953399e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.027534776996988385, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.978963279105821e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.02773430436653178, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.863927848152472e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.027933831736075172, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.750000000000001e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.028133359105618566, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.637214438174593e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.02833288647516196, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.525605518250964e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.028532413844705354, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.415207237387297e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.028731941214248748, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3060532239693994e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.02893146858379214, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.198176727367156e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.029130995953335535, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.091610607806452e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.02933052332287893, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.986387326359637e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.029530050692422323, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8825389350575624e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.02972957806196572, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.78009706712622e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.029929105431509114, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6790929273509545e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.029929105431509114, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3233.9846, | |
| "eval_samples_per_second": 5.22, | |
| "eval_steps_per_second": 2.61, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.030128632801052508, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.579557282571196e-05, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.030328160170595902, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4815204523085654e-05, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.030527687540139296, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.385012299531262e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.03072721490968269, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2900622215575197e-05, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.030926742279226083, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1966991411008938e-05, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.031126269648769477, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1049514974601175e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.031325797018312874, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0148472378562215e-05, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.03152532438785627, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.926413808919542e-05, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.03172485175739966, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8396781483292098e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.031924379126943056, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7546666766076655e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03212390649648645, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.671405289072718e-05, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.032323433866029844, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5899193479495857e-05, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.03252296123557324, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5102336746453053e-05, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.03272248860511663, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4323725421878949e-05, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.032922015974660025, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3563596678325606e-05, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.03312154334420342, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2822182058371878e-05, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.03332107071374681, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2099707404093203e-05, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.03352059808329021, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1396392788268052e-05, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.0337201254528336, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0712452447341582e-05, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.033919652822376994, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0048094716167095e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03411918019192039, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.40352196454532e-06, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.03431870756146378, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.778930535580474e-06, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.034518234931007176, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.174510685872415e-06, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.03471776230055057, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5904465275624884e-06, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.034917289670093964, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.026915972251254e-06, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.03511681703963736, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.484090676804926e-06, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.03531634440918075, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.962135991066971e-06, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.035515871778724145, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.461210907490951e-06, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.03571539914826754, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.981468012709877e-06, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.03591492651781093, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.523053441056876e-06, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03611445388735433, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.086106830051236e-06, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.03631398125689772, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.670761277863485e-06, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.036513508626441114, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.277143302772342e-06, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.036713035995984515, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9053728046260825e-06, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.03691256336552791, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.555563028319885e-06, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.0371120907350713, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.227820529300264e-06, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.0373116181046147, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9222451411073645e-06, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.03751114547415809, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6389299449645733e-06, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.037710672843701484, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3779612414252017e-06, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.03791020021324488, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1394185240843983e-06, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03810972758278827, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.233744553646754e-07, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.038309254952331666, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.298948443822228e-07, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.03850878232187506, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.590386269008512e-07, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.038708309691418454, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.108578473795032e-07, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.03890783706096185, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8539764311908407e-07, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.03910736443050524, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8269623051318515e-07, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.039306891800048635, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.027848934069625e-07, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.03950641916959203, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.568797356781784e-08, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.03970594653913542, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.142286327065478e-08, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.03990547390867882, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03990547390867882, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3092.4174, | |
| "eval_samples_per_second": 5.459, | |
| "eval_steps_per_second": 2.73, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 17, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1936167234633728e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |