| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0506228989519478, | |
| "eval_steps": 8, | |
| "global_step": 8, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006327862368993475, | |
| "eval_loss": 4.022780895233154, | |
| "eval_runtime": 85.0755, | |
| "eval_samples_per_second": 6.265, | |
| "eval_steps_per_second": 3.138, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018983587106980424, | |
| "grad_norm": 1.016599416732788, | |
| "learning_rate": 3e-05, | |
| "loss": 3.1283, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03796717421396085, | |
| "grad_norm": 1.0906339883804321, | |
| "learning_rate": 6e-05, | |
| "loss": 2.94, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0506228989519478, | |
| "eval_loss": 3.2956628799438477, | |
| "eval_runtime": 85.1034, | |
| "eval_samples_per_second": 6.263, | |
| "eval_steps_per_second": 3.137, | |
| "step": 8 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 90, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 8, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.123319490904064e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |