| { | |
| "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": 0.8950845003128052, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.9575, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.265984109209193e-05, | |
| "eval_loss": 0.8528293371200562, | |
| "eval_runtime": 3346.3891, | |
| "eval_samples_per_second": 5.899, | |
| "eval_steps_per_second": 2.949, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.531968218418386e-05, | |
| "grad_norm": 1.1442168951034546, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 5.2451, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001279795232762758, | |
| "grad_norm": 1.394640564918518, | |
| "learning_rate": 0.0001, | |
| "loss": 5.3981, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00017063936436836772, | |
| "grad_norm": 1.6339935064315796, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 5.5776, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00021329920546045967, | |
| "grad_norm": 2.0181682109832764, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 5.31, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002559590465525516, | |
| "grad_norm": 2.081012487411499, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.69, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002986188876446435, | |
| "grad_norm": 2.091360092163086, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 4.7037, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00034127872873673543, | |
| "grad_norm": 2.663072109222412, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 4.4144, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00038393856982882736, | |
| "grad_norm": 2.2715742588043213, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.8637, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00042659841092091935, | |
| "grad_norm": 4.384383201599121, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 4.0411, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004692582520130113, | |
| "grad_norm": 4.320742607116699, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 3.5344, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0005119180931051031, | |
| "grad_norm": 3.698866844177246, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.3832, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005545779341971951, | |
| "grad_norm": 3.1251349449157715, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 3.359, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.000597237775289287, | |
| "grad_norm": 2.3781769275665283, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 3.002, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0006398976163813789, | |
| "grad_norm": 2.4765355587005615, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.3571, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006825574574734709, | |
| "grad_norm": 2.4396748542785645, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 3.4887, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0007252172985655628, | |
| "grad_norm": 2.1020894050598145, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 3.5473, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0007678771396576547, | |
| "grad_norm": 2.180967330932617, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.5701, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0008105369807497467, | |
| "grad_norm": 2.0794942378997803, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.9633, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0008531968218418387, | |
| "grad_norm": 2.3405985832214355, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 3.264, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008958566629339306, | |
| "grad_norm": 2.1136486530303955, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.1988, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0009385165040260225, | |
| "grad_norm": 2.2635881900787354, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 3.4865, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0009811763451181145, | |
| "grad_norm": 2.510779619216919, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 2.9429, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0010238361862102063, | |
| "grad_norm": 2.3888373374938965, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.348, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010664960273022983, | |
| "grad_norm": 3.272702932357788, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 3.4122, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010664960273022983, | |
| "eval_loss": 0.4052564203739166, | |
| "eval_runtime": 3346.521, | |
| "eval_samples_per_second": 5.899, | |
| "eval_steps_per_second": 2.949, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0011091558683943902, | |
| "grad_norm": 3.144263982772827, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 3.8628, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0011518157094864822, | |
| "grad_norm": 2.507157325744629, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.8496, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001194475550578574, | |
| "grad_norm": 2.559713125228882, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 2.8976, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.001237135391670666, | |
| "grad_norm": 2.1491596698760986, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 2.703, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0012797952327627579, | |
| "grad_norm": 2.6858789920806885, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.2626, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00132245507385485, | |
| "grad_norm": 2.5397956371307373, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 2.7342, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0013651149149469417, | |
| "grad_norm": 2.6062099933624268, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 3.3048, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0014077747560390338, | |
| "grad_norm": 2.4756972789764404, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.9948, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0014504345971311256, | |
| "grad_norm": 2.7714602947235107, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 3.2915, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0014930944382232176, | |
| "grad_norm": 2.65149188041687, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 3.2514, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0015357542793153094, | |
| "grad_norm": 2.8307254314422607, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.299, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0015784141204074015, | |
| "grad_norm": 2.442545175552368, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 3.0294, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0016210739614994933, | |
| "grad_norm": 2.2670016288757324, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 3.3772, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0016637338025915853, | |
| "grad_norm": 2.8332643508911133, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2163, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0017063936436836774, | |
| "grad_norm": 2.668203830718994, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 2.9927, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0017490534847757692, | |
| "grad_norm": 2.528712034225464, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 2.7003, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0017917133258678612, | |
| "grad_norm": 3.2600278854370117, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.7579, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.001834373166959953, | |
| "grad_norm": 2.814138412475586, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 3.1766, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.001877033008052045, | |
| "grad_norm": 3.453101873397827, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 3.5888, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.001919692849144137, | |
| "grad_norm": 2.941481828689575, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.1291, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.001962352690236229, | |
| "grad_norm": 3.0425057411193848, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 3.3131, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0020050125313283208, | |
| "grad_norm": 3.546339750289917, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 3.8228, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0020476723724204126, | |
| "grad_norm": 3.8112733364105225, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.4266, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.002090332213512505, | |
| "grad_norm": 3.7606093883514404, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 3.7293, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0021329920546045967, | |
| "grad_norm": 6.579668045043945, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 4.5136, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0021329920546045967, | |
| "eval_loss": 0.3695688843727112, | |
| "eval_runtime": 3346.9603, | |
| "eval_samples_per_second": 5.898, | |
| "eval_steps_per_second": 2.949, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0021756518956966885, | |
| "grad_norm": 2.0142173767089844, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.9362, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0022183117367887803, | |
| "grad_norm": 2.2668869495391846, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 2.5948, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0022609715778808726, | |
| "grad_norm": 2.5661771297454834, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 3.2879, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0023036314189729644, | |
| "grad_norm": 2.1952974796295166, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.054, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.002346291260065056, | |
| "grad_norm": 2.2668612003326416, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 3.2251, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.002388951101157148, | |
| "grad_norm": 1.8296819925308228, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 2.4021, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0024316109422492403, | |
| "grad_norm": 2.153315782546997, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.4252, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.002474270783341332, | |
| "grad_norm": 2.292271614074707, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 2.3999, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.002516930624433424, | |
| "grad_norm": 1.9195157289505005, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 2.5964, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0025595904655255157, | |
| "grad_norm": 1.9605921506881714, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.3407, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.002602250306617608, | |
| "grad_norm": 1.9012995958328247, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 2.368, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0026449101477097, | |
| "grad_norm": 1.9466537237167358, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 2.4592, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0026875699888017916, | |
| "grad_norm": 1.8879311084747314, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.9293, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0027302298298938835, | |
| "grad_norm": 1.9396064281463623, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 2.0808, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0027728896709859757, | |
| "grad_norm": 2.0695531368255615, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 2.8054, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0028155495120780675, | |
| "grad_norm": 2.0114097595214844, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.7048, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0028582093531701594, | |
| "grad_norm": 2.431223154067993, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 3.0252, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.002900869194262251, | |
| "grad_norm": 2.1020631790161133, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 2.7235, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0029435290353543434, | |
| "grad_norm": 2.0261971950531006, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.4901, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0029861888764464353, | |
| "grad_norm": 2.127995729446411, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 2.7434, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.003028848717538527, | |
| "grad_norm": 1.97040855884552, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 3.0585, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.003071508558630619, | |
| "grad_norm": 1.9737168550491333, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.5883, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.003114168399722711, | |
| "grad_norm": 2.150047540664673, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 3.1533, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.003156828240814803, | |
| "grad_norm": 2.6070427894592285, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 2.7457, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.003199488081906895, | |
| "grad_norm": 2.3490138053894043, | |
| "learning_rate": 0.0, | |
| "loss": 2.8359, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.003199488081906895, | |
| "eval_loss": 0.3554416000843048, | |
| "eval_runtime": 3346.2309, | |
| "eval_samples_per_second": 5.899, | |
| "eval_steps_per_second": 2.95, | |
| "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 | |
| } | |