| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.34023503077783995, | |
| "eval_steps": 100, | |
| "global_step": 38, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008953553441522105, | |
| "grad_norm": 0.36430689692497253, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5867, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008953553441522105, | |
| "eval_loss": 1.6258726119995117, | |
| "eval_runtime": 56.5706, | |
| "eval_samples_per_second": 6.664, | |
| "eval_steps_per_second": 1.679, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01790710688304421, | |
| "grad_norm": 0.346722275018692, | |
| "learning_rate": 4e-05, | |
| "loss": 1.8107, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.026860660324566313, | |
| "grad_norm": 0.33874014019966125, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4672, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03581421376608842, | |
| "grad_norm": 0.3448643684387207, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7636, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04476776720761052, | |
| "grad_norm": 0.3282066583633423, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6535, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.053721320649132626, | |
| "grad_norm": 0.3014908730983734, | |
| "learning_rate": 0.00012, | |
| "loss": 1.5771, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06267487409065473, | |
| "grad_norm": 0.32604771852493286, | |
| "learning_rate": 0.00014, | |
| "loss": 1.552, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07162842753217684, | |
| "grad_norm": 0.2597745954990387, | |
| "learning_rate": 0.00016, | |
| "loss": 1.4559, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08058198097369894, | |
| "grad_norm": 0.27925363183021545, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3562, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08953553441522104, | |
| "grad_norm": 0.30343925952911377, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5509, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09848908785674315, | |
| "grad_norm": 0.2793353796005249, | |
| "learning_rate": 0.00019937122098932428, | |
| "loss": 1.4532, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10744264129826525, | |
| "grad_norm": 0.2764800190925598, | |
| "learning_rate": 0.00019749279121818235, | |
| "loss": 1.3795, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11639619473978735, | |
| "grad_norm": 0.25808510184288025, | |
| "learning_rate": 0.00019438833303083678, | |
| "loss": 1.5303, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12534974818130945, | |
| "grad_norm": 0.2491457313299179, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 1.485, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13430330162283155, | |
| "grad_norm": 0.22570456564426422, | |
| "learning_rate": 0.00018467241992282843, | |
| "loss": 1.4586, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14325685506435368, | |
| "grad_norm": 0.24603070318698883, | |
| "learning_rate": 0.000178183148246803, | |
| "loss": 1.4246, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15221040850587578, | |
| "grad_norm": 0.2065669447183609, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.316, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16116396194739788, | |
| "grad_norm": 0.23284702003002167, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 1.4792, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17011751538891998, | |
| "grad_norm": 0.2532147765159607, | |
| "learning_rate": 0.00015320320765153367, | |
| "loss": 1.6496, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17907106883044208, | |
| "grad_norm": 0.3514811098575592, | |
| "learning_rate": 0.00014338837391175582, | |
| "loss": 1.3896, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18802462227196418, | |
| "grad_norm": 0.23653051257133484, | |
| "learning_rate": 0.00013302790619551674, | |
| "loss": 1.4108, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1969781757134863, | |
| "grad_norm": 0.23037055134773254, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 1.4471, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2059317291550084, | |
| "grad_norm": 0.22145314514636993, | |
| "learning_rate": 0.00011119644761033078, | |
| "loss": 1.4897, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2148852825965305, | |
| "grad_norm": 0.20780210196971893, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2546, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2238388360380526, | |
| "grad_norm": 0.21545733511447906, | |
| "learning_rate": 8.880355238966923e-05, | |
| "loss": 1.3577, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2327923894795747, | |
| "grad_norm": 0.20867308974266052, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 1.4935, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2417459429210968, | |
| "grad_norm": 0.20432667434215546, | |
| "learning_rate": 6.697209380448333e-05, | |
| "loss": 1.2985, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2506994963626189, | |
| "grad_norm": 0.20409992337226868, | |
| "learning_rate": 5.6611626088244194e-05, | |
| "loss": 1.3887, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.259653049804141, | |
| "grad_norm": 0.19983279705047607, | |
| "learning_rate": 4.6796792348466356e-05, | |
| "loss": 1.2571, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2686066032456631, | |
| "grad_norm": 0.20466941595077515, | |
| "learning_rate": 3.7651019814126654e-05, | |
| "loss": 1.4783, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2775601566871852, | |
| "grad_norm": 0.1904105693101883, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 1.2726, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.28651371012870736, | |
| "grad_norm": 0.19994252920150757, | |
| "learning_rate": 2.181685175319702e-05, | |
| "loss": 1.3431, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.29546726357022945, | |
| "grad_norm": 0.20978009700775146, | |
| "learning_rate": 1.5327580077171587e-05, | |
| "loss": 1.5459, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.30442081701175155, | |
| "grad_norm": 0.20526275038719177, | |
| "learning_rate": 9.903113209758096e-06, | |
| "loss": 1.1755, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.31337437045327365, | |
| "grad_norm": 0.20616187155246735, | |
| "learning_rate": 5.611666969163243e-06, | |
| "loss": 1.6515, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32232792389479575, | |
| "grad_norm": 0.21263156831264496, | |
| "learning_rate": 2.5072087818176382e-06, | |
| "loss": 1.3846, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.33128147733631785, | |
| "grad_norm": 0.19717688858509064, | |
| "learning_rate": 6.287790106757396e-07, | |
| "loss": 1.3304, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.34023503077783995, | |
| "grad_norm": 0.2078697234392166, | |
| "learning_rate": 0.0, | |
| "loss": 1.4625, | |
| "step": 38 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 38, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 2.3183977611264e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |