| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9924812030075187, | |
| "eval_steps": 500, | |
| "global_step": 66, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15037593984962405, | |
| "grad_norm": 0.5201665759086609, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0025, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3007518796992481, | |
| "grad_norm": 0.1790522187948227, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6023, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.45112781954887216, | |
| "grad_norm": 0.19227077066898346, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5238, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6015037593984962, | |
| "grad_norm": 0.167165145277977, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5075, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7518796992481203, | |
| "grad_norm": 0.15390199422836304, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4849, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9022556390977443, | |
| "grad_norm": 0.15909235179424286, | |
| "learning_rate": 0.0002, | |
| "loss": 0.473, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 198, | |
| "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": 5.72299041350615e+16, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |