| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002531560116114224, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.3754134881522986e-05, | |
| "grad_norm": 4.89381217956543, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.8117, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.3754134881522986e-05, | |
| "eval_loss": 1.4206814765930176, | |
| "eval_runtime": 2761.2734, | |
| "eval_samples_per_second": 9.035, | |
| "eval_steps_per_second": 4.518, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.750826976304597e-05, | |
| "grad_norm": 3.2238664627075195, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.5532, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010126240464456896, | |
| "grad_norm": 3.240180253982544, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4341, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013501653952609194, | |
| "grad_norm": 2.933100461959839, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 1.1723, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00016877067440761493, | |
| "grad_norm": 2.8057668209075928, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 1.012, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00020252480928913792, | |
| "grad_norm": 2.675827741622925, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.8673, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002362789441706609, | |
| "grad_norm": 2.9692628383636475, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.743, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002700330790521839, | |
| "grad_norm": 2.7837095260620117, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.704, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003037872139337069, | |
| "grad_norm": 2.2439792156219482, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6491, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00033754134881522986, | |
| "grad_norm": 1.8346399068832397, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.6559, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00037129548369675285, | |
| "grad_norm": 1.8229111433029175, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.6018, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00040504961857827583, | |
| "grad_norm": 2.420116901397705, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.666, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0004388037534597988, | |
| "grad_norm": 1.892528772354126, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.5869, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0004725578883413218, | |
| "grad_norm": 1.9345523118972778, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.6242, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0005063120232228448, | |
| "grad_norm": 1.8276655673980713, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.6091, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005400661581043678, | |
| "grad_norm": 1.4461370706558228, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.5649, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005738202929858908, | |
| "grad_norm": 2.1501457691192627, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.6251, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0006075744278674137, | |
| "grad_norm": 1.8506277799606323, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6026, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006413285627489368, | |
| "grad_norm": 1.8709357976913452, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.558, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0006750826976304597, | |
| "grad_norm": 1.5602527856826782, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.5937, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007088368325119828, | |
| "grad_norm": 1.809094786643982, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5577, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0007425909673935057, | |
| "grad_norm": 1.3502001762390137, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.5118, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0007763451022750287, | |
| "grad_norm": 1.3252819776535034, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.5418, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0008100992371565517, | |
| "grad_norm": 2.3276662826538086, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5613, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0008438533720380747, | |
| "grad_norm": 1.6444724798202515, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.5491, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0008438533720380747, | |
| "eval_loss": 0.5483559370040894, | |
| "eval_runtime": 2777.4398, | |
| "eval_samples_per_second": 8.983, | |
| "eval_steps_per_second": 4.492, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0008776075069195976, | |
| "grad_norm": 1.2517900466918945, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.49, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0009113616418011207, | |
| "grad_norm": 1.1255788803100586, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4652, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0009451157766826436, | |
| "grad_norm": 1.3350865840911865, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.5945, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0009788699115641666, | |
| "grad_norm": 1.255922555923462, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.4186, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0010126240464456897, | |
| "grad_norm": 1.1698178052902222, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4548, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0010463781813272125, | |
| "grad_norm": 1.1624618768692017, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.5209, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0010801323162087356, | |
| "grad_norm": 1.9189029932022095, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.5466, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0011138864510902586, | |
| "grad_norm": 1.1308246850967407, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.445, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0011476405859717816, | |
| "grad_norm": 1.261982798576355, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.4534, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0011813947208533045, | |
| "grad_norm": 1.2305161952972412, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.4823, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0012151488557348275, | |
| "grad_norm": 1.3532754182815552, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4471, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0012489029906163505, | |
| "grad_norm": 1.5262309312820435, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.5651, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0012826571254978736, | |
| "grad_norm": 1.0819740295410156, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.5211, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0013164112603793964, | |
| "grad_norm": 1.3941339254379272, | |
| "learning_rate": 5e-05, | |
| "loss": 0.46, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0013501653952609194, | |
| "grad_norm": 1.6077882051467896, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.5456, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0013839195301424425, | |
| "grad_norm": 1.1812937259674072, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.4872, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0014176736650239655, | |
| "grad_norm": 1.304977536201477, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4647, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0014514277999054883, | |
| "grad_norm": 1.7109375, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.5107, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0014851819347870114, | |
| "grad_norm": 1.3880994319915771, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.4708, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0015189360696685344, | |
| "grad_norm": 1.2330398559570312, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4897, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0015526902045500575, | |
| "grad_norm": 1.0758552551269531, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.4025, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0015864443394315803, | |
| "grad_norm": 1.2690551280975342, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.5129, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0016201984743131033, | |
| "grad_norm": 1.5134022235870361, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3607, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0016539526091946264, | |
| "grad_norm": 1.6051034927368164, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.5501, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0016877067440761494, | |
| "grad_norm": 4.110562324523926, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.7889, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0016877067440761494, | |
| "eval_loss": 0.4801631271839142, | |
| "eval_runtime": 2778.0051, | |
| "eval_samples_per_second": 8.981, | |
| "eval_steps_per_second": 4.491, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0017214608789576722, | |
| "grad_norm": 2.1474967002868652, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.6069, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0017552150138391953, | |
| "grad_norm": 1.1795744895935059, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.473, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0017889691487207183, | |
| "grad_norm": 1.3834023475646973, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.5656, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0018227232836022414, | |
| "grad_norm": 1.2573689222335815, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5592, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0018564774184837642, | |
| "grad_norm": 1.0423628091812134, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.537, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0018902315533652872, | |
| "grad_norm": 1.135725736618042, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.4532, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0019239856882468103, | |
| "grad_norm": 1.1951916217803955, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5232, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0019577398231283333, | |
| "grad_norm": 1.4549823999404907, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.4819, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0019914939580098563, | |
| "grad_norm": 1.3570860624313354, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.4457, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0020252480928913794, | |
| "grad_norm": 1.134557843208313, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4754, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.002059002227772902, | |
| "grad_norm": 1.164859414100647, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.4898, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.002092756362654425, | |
| "grad_norm": 1.095713496208191, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.5173, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.002126510497535948, | |
| "grad_norm": 1.2956494092941284, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4378, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.002160264632417471, | |
| "grad_norm": 1.5956240892410278, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.4518, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.002194018767298994, | |
| "grad_norm": 1.0486266613006592, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.4689, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.002227772902180517, | |
| "grad_norm": 0.9784994721412659, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4384, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0022615270370620402, | |
| "grad_norm": 1.2614351511001587, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.3726, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0022952811719435633, | |
| "grad_norm": 1.102088451385498, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.4358, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.002329035306825086, | |
| "grad_norm": 1.3074065446853638, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.3848, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.002362789441706609, | |
| "grad_norm": 1.1175683736801147, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.4579, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.002396543576588132, | |
| "grad_norm": 1.3784244060516357, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.5005, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.002430297711469655, | |
| "grad_norm": 1.2491179704666138, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.4487, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.002464051846351178, | |
| "grad_norm": 1.6952537298202515, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.4381, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.002497805981232701, | |
| "grad_norm": 1.4215257167816162, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.4436, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.002531560116114224, | |
| "grad_norm": 1.003847360610962, | |
| "learning_rate": 0.0, | |
| "loss": 0.4054, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.002531560116114224, | |
| "eval_loss": 0.46333596110343933, | |
| "eval_runtime": 2779.4243, | |
| "eval_samples_per_second": 8.976, | |
| "eval_steps_per_second": 4.488, | |
| "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": 3.0150141079977984e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |