| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9935205183585313, | |
| "eval_steps": 500, | |
| "global_step": 115, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08639308855291576, | |
| "grad_norm": 408.058349609375, | |
| "learning_rate": 1.2e-05, | |
| "loss": 9.3465, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17278617710583152, | |
| "grad_norm": 1.8677339553833008, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 1.8486, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2591792656587473, | |
| "grad_norm": 0.6196443438529968, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 0.4004, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34557235421166305, | |
| "grad_norm": 0.8679957985877991, | |
| "learning_rate": 0.000132, | |
| "loss": 0.3089, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4319654427645788, | |
| "grad_norm": 0.4516398310661316, | |
| "learning_rate": 0.000172, | |
| "loss": 0.2921, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5183585313174947, | |
| "grad_norm": 1.6636766195297241, | |
| "learning_rate": 0.00019994896932810338, | |
| "loss": 0.4872, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6047516198704104, | |
| "grad_norm": 0.6236905455589294, | |
| "learning_rate": 0.0001990432055368971, | |
| "loss": 0.3284, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6911447084233261, | |
| "grad_norm": 0.8019087314605713, | |
| "learning_rate": 0.00019701524265130086, | |
| "loss": 0.4159, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7775377969762419, | |
| "grad_norm": 0.460245817899704, | |
| "learning_rate": 0.0001938880583011413, | |
| "loss": 0.2771, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8639308855291576, | |
| "grad_norm": 0.2711161673069, | |
| "learning_rate": 0.00018969708473466529, | |
| "loss": 0.2995, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9503239740820735, | |
| "grad_norm": 0.5418670773506165, | |
| "learning_rate": 0.000184489807357009, | |
| "loss": 0.2693, | |
| "step": 110 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 345, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.1844961129332736e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |