| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003199488081906895, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.265984109209193e-05, | |
| "grad_norm": 0.9969995617866516, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.9588, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.265984109209193e-05, | |
| "eval_loss": 0.8528421521186829, | |
| "eval_runtime": 6712.1472, | |
| "eval_samples_per_second": 2.941, | |
| "eval_steps_per_second": 1.47, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.531968218418386e-05, | |
| "grad_norm": 1.190828561782837, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 5.243, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001279795232762758, | |
| "grad_norm": 1.4397765398025513, | |
| "learning_rate": 0.0001, | |
| "loss": 5.3963, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00017063936436836772, | |
| "grad_norm": 1.6313406229019165, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 5.5734, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00021329920546045967, | |
| "grad_norm": 2.044528007507324, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 5.304, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002559590465525516, | |
| "grad_norm": 2.162430763244629, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.6854, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002986188876446435, | |
| "grad_norm": 2.0912225246429443, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 4.6928, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00034127872873673543, | |
| "grad_norm": 2.985011100769043, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 4.4166, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00038393856982882736, | |
| "grad_norm": 2.7205920219421387, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.8685, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00042659841092091935, | |
| "grad_norm": 4.159798622131348, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 4.0564, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004692582520130113, | |
| "grad_norm": 4.382631778717041, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 3.5491, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0005119180931051031, | |
| "grad_norm": 3.656183958053589, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.3898, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005545779341971951, | |
| "grad_norm": 3.396904230117798, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 3.3838, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.000597237775289287, | |
| "grad_norm": 2.346179485321045, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 3.0043, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0006398976163813789, | |
| "grad_norm": 2.402644395828247, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.357, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006825574574734709, | |
| "grad_norm": 2.4477994441986084, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 3.5046, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0007252172985655628, | |
| "grad_norm": 2.0487022399902344, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 3.5617, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0007678771396576547, | |
| "grad_norm": 2.190971612930298, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.5747, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0008105369807497467, | |
| "grad_norm": 2.8272922039031982, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.9758, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0008531968218418387, | |
| "grad_norm": 2.4170966148376465, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 3.2795, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008958566629339306, | |
| "grad_norm": 2.1180191040039062, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.2033, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0009385165040260225, | |
| "grad_norm": 2.2295899391174316, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 3.5037, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0009811763451181145, | |
| "grad_norm": 2.3293685913085938, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 2.943, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0010238361862102063, | |
| "grad_norm": 2.344874858856201, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.3558, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010664960273022983, | |
| "grad_norm": 2.393409252166748, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 3.4156, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010664960273022983, | |
| "eval_loss": 0.40573301911354065, | |
| "eval_runtime": 6738.675, | |
| "eval_samples_per_second": 2.929, | |
| "eval_steps_per_second": 1.465, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0011091558683943902, | |
| "grad_norm": 2.535912275314331, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 3.8808, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0011518157094864822, | |
| "grad_norm": 2.5588672161102295, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.8454, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001194475550578574, | |
| "grad_norm": 2.523439884185791, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 2.9184, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.001237135391670666, | |
| "grad_norm": 2.095428943634033, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 2.7021, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0012797952327627579, | |
| "grad_norm": 2.7387797832489014, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.2581, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00132245507385485, | |
| "grad_norm": 2.6308884620666504, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 2.7427, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0013651149149469417, | |
| "grad_norm": 2.636615037918091, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 3.285, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0014077747560390338, | |
| "grad_norm": 2.369776487350464, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.0001, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0014504345971311256, | |
| "grad_norm": 2.6059372425079346, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 3.2904, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0014930944382232176, | |
| "grad_norm": 2.669086456298828, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 3.2649, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0015357542793153094, | |
| "grad_norm": 2.914031505584717, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.3064, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0015784141204074015, | |
| "grad_norm": 2.5457451343536377, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 3.0397, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0016210739614994933, | |
| "grad_norm": 2.2913217544555664, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 3.371, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0016637338025915853, | |
| "grad_norm": 2.8556880950927734, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2176, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0017063936436836774, | |
| "grad_norm": 2.8370909690856934, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 2.9915, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0017490534847757692, | |
| "grad_norm": 2.672523260116577, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 2.6975, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0017917133258678612, | |
| "grad_norm": 3.1466898918151855, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.7516, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.001834373166959953, | |
| "grad_norm": 2.774160861968994, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 3.1729, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.001877033008052045, | |
| "grad_norm": 3.153118133544922, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 3.5701, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.001919692849144137, | |
| "grad_norm": 2.9490132331848145, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.1243, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.001962352690236229, | |
| "grad_norm": 2.9602949619293213, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 3.3011, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0020050125313283208, | |
| "grad_norm": 3.293994188308716, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 3.8062, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0020476723724204126, | |
| "grad_norm": 3.6145431995391846, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.4406, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.002090332213512505, | |
| "grad_norm": 3.6309499740600586, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 3.7389, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0021329920546045967, | |
| "grad_norm": 6.612607955932617, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 4.4957, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0021329920546045967, | |
| "eval_loss": 0.36898791790008545, | |
| "eval_runtime": 6736.9928, | |
| "eval_samples_per_second": 2.93, | |
| "eval_steps_per_second": 1.465, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0021756518956966885, | |
| "grad_norm": 2.0145974159240723, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.936, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0022183117367887803, | |
| "grad_norm": 2.300792694091797, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 2.594, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0022609715778808726, | |
| "grad_norm": 2.504664659500122, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 3.2795, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0023036314189729644, | |
| "grad_norm": 2.2121381759643555, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.048, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.002346291260065056, | |
| "grad_norm": 2.259291648864746, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 3.2254, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.002388951101157148, | |
| "grad_norm": 1.8380450010299683, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 2.4056, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0024316109422492403, | |
| "grad_norm": 2.1234822273254395, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.4289, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.002474270783341332, | |
| "grad_norm": 2.341116189956665, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 2.3872, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.002516930624433424, | |
| "grad_norm": 1.9476566314697266, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 2.5924, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0025595904655255157, | |
| "grad_norm": 1.962724208831787, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.3415, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.002602250306617608, | |
| "grad_norm": 1.9540096521377563, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 2.3737, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0026449101477097, | |
| "grad_norm": 1.9087435007095337, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 2.4536, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0026875699888017916, | |
| "grad_norm": 1.9457799196243286, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.9324, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0027302298298938835, | |
| "grad_norm": 1.9675488471984863, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 2.0784, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0027728896709859757, | |
| "grad_norm": 2.1437301635742188, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 2.8246, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0028155495120780675, | |
| "grad_norm": 1.9913514852523804, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.6997, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0028582093531701594, | |
| "grad_norm": 2.4888172149658203, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 3.0651, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.002900869194262251, | |
| "grad_norm": 2.113009214401245, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 2.7241, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0029435290353543434, | |
| "grad_norm": 2.0075302124023438, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.4798, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0029861888764464353, | |
| "grad_norm": 2.1354432106018066, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 2.7381, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.003028848717538527, | |
| "grad_norm": 2.062131881713867, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 3.0546, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.003071508558630619, | |
| "grad_norm": 1.9684584140777588, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.5997, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.003114168399722711, | |
| "grad_norm": 2.1718146800994873, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 3.16, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.003156828240814803, | |
| "grad_norm": 3.034888982772827, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 2.7699, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.003199488081906895, | |
| "grad_norm": 2.44492244720459, | |
| "learning_rate": 0.0, | |
| "loss": 2.8338, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.003199488081906895, | |
| "eval_loss": 0.35533958673477173, | |
| "eval_runtime": 6736.7641, | |
| "eval_samples_per_second": 2.93, | |
| "eval_steps_per_second": 1.465, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.877352954934067e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |