| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.5595075488090515, | |
| "learning_rate": 0.000482, | |
| "loss": 0.4307, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.566727340221405, | |
| "learning_rate": 0.000462, | |
| "loss": 0.0524, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.2078760862350464, | |
| "learning_rate": 0.000442, | |
| "loss": 0.026, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.25045984983444214, | |
| "learning_rate": 0.000422, | |
| "loss": 0.0261, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.20396892726421356, | |
| "learning_rate": 0.000402, | |
| "loss": 0.0199, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.08542954921722412, | |
| "learning_rate": 0.000382, | |
| "loss": 0.028, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 0.17754589021205902, | |
| "learning_rate": 0.000362, | |
| "loss": 0.0154, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.10964138805866241, | |
| "learning_rate": 0.000342, | |
| "loss": 0.0158, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "grad_norm": 1.3268883228302002, | |
| "learning_rate": 0.000322, | |
| "loss": 0.0156, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.16379483044147491, | |
| "learning_rate": 0.000302, | |
| "loss": 0.0157, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "grad_norm": 0.1214568242430687, | |
| "learning_rate": 0.00028199999999999997, | |
| "loss": 0.0125, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 0.13405731320381165, | |
| "learning_rate": 0.000262, | |
| "loss": 0.0129, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "grad_norm": 0.016486013308167458, | |
| "learning_rate": 0.000242, | |
| "loss": 0.0125, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "grad_norm": 1.5530146360397339, | |
| "learning_rate": 0.000222, | |
| "loss": 0.0117, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.1322641223669052, | |
| "learning_rate": 0.000202, | |
| "loss": 0.0137, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "grad_norm": 0.15241874754428864, | |
| "learning_rate": 0.000182, | |
| "loss": 0.0108, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "grad_norm": 0.05570691078901291, | |
| "learning_rate": 0.000162, | |
| "loss": 0.0108, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "grad_norm": 0.059169329702854156, | |
| "learning_rate": 0.00014199999999999998, | |
| "loss": 0.0113, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "grad_norm": 0.0516737699508667, | |
| "learning_rate": 0.000122, | |
| "loss": 0.0093, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.22752004861831665, | |
| "learning_rate": 0.000102, | |
| "loss": 0.0097, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "grad_norm": 0.28640028834342957, | |
| "learning_rate": 8.2e-05, | |
| "loss": 0.0092, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "grad_norm": 0.053172893822193146, | |
| "learning_rate": 6.2e-05, | |
| "loss": 0.0087, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "grad_norm": 0.0015004288870841265, | |
| "learning_rate": 4.2000000000000004e-05, | |
| "loss": 0.0091, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "grad_norm": 0.0008665521745570004, | |
| "learning_rate": 2.2e-05, | |
| "loss": 0.0087, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.002254044869914651, | |
| "learning_rate": 2e-06, | |
| "loss": 0.0088, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1558177088783744e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |