| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.571428571428571, | |
| "eval_steps": 500, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 16229.494205476607, | |
| "learning_rate": 2e-05, | |
| "loss": 63.281, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "eval_loss": 31.527084350585938, | |
| "eval_runtime": 0.8623, | |
| "eval_samples_per_second": 24.353, | |
| "eval_steps_per_second": 1.16, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 20846.304790427996, | |
| "learning_rate": 1e-05, | |
| "loss": 53.5176, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 24.949296951293945, | |
| "eval_runtime": 0.8352, | |
| "eval_samples_per_second": 25.143, | |
| "eval_steps_per_second": 1.197, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "eval_loss": 24.174694061279297, | |
| "eval_runtime": 0.8231, | |
| "eval_samples_per_second": 25.515, | |
| "eval_steps_per_second": 1.215, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "step": 9, | |
| "total_flos": 2409879306240.0, | |
| "train_loss": 42.482702043321396, | |
| "train_runtime": 189.679, | |
| "train_samples_per_second": 6.643, | |
| "train_steps_per_second": 0.047 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 9, | |
| "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": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2409879306240.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |