| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.96, | |
| "eval_steps": 500, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 49.5, | |
| "learning_rate": 0.0003, | |
| "loss": 3.2644, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 143.0, | |
| "learning_rate": 2.8647450843757897e-05, | |
| "loss": 4.3629, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 2.263831377029419, | |
| "eval_runtime": 0.1012, | |
| "eval_samples_per_second": 98.826, | |
| "eval_steps_per_second": 29.648, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "step": 6, | |
| "total_flos": 96668442181632.0, | |
| "train_loss": 3.916761557261149, | |
| "train_runtime": 4.2749, | |
| "train_samples_per_second": 23.392, | |
| "train_steps_per_second": 1.404 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 6, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 96668442181632.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |