| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1059322033898305, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00211864406779661, | |
| "grad_norm": 6772.94736433113, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 5.4426, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0211864406779661, | |
| "grad_norm": 43.76552598391156, | |
| "learning_rate": 5.263157894736842e-05, | |
| "loss": 6.5697, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0423728813559322, | |
| "grad_norm": 1.4214989301078385, | |
| "learning_rate": 0.00010526315789473683, | |
| "loss": 5.8015, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0635593220338983, | |
| "grad_norm": 1.8559172078320925, | |
| "learning_rate": 0.00015789473684210527, | |
| "loss": 4.6978, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0847457627118644, | |
| "grad_norm": 0.9523887604864526, | |
| "learning_rate": 0.00021052631578947367, | |
| "loss": 3.9616, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1059322033898305, | |
| "grad_norm": 0.5313592686196623, | |
| "learning_rate": 0.0002631578947368421, | |
| "loss": 3.2816, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1888, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1236428742721536.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |