| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03003003003003003, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006006006006006006, | |
| "grad_norm": 0.831743061542511, | |
| "learning_rate": 1e-05, | |
| "loss": 3.0774, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006006006006006006, | |
| "eval_loss": 3.1709842681884766, | |
| "eval_runtime": 73.2445, | |
| "eval_samples_per_second": 3.836, | |
| "eval_steps_per_second": 1.925, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012012012012012012, | |
| "grad_norm": 0.8687347769737244, | |
| "learning_rate": 2e-05, | |
| "loss": 3.0936, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012012012012012012, | |
| "eval_loss": 3.1444201469421387, | |
| "eval_runtime": 2.3134, | |
| "eval_samples_per_second": 121.465, | |
| "eval_steps_per_second": 60.948, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.018018018018018018, | |
| "grad_norm": 0.818413257598877, | |
| "learning_rate": 3e-05, | |
| "loss": 3.1959, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.024024024024024024, | |
| "grad_norm": 0.8591678738594055, | |
| "learning_rate": 4e-05, | |
| "loss": 3.1703, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.024024024024024024, | |
| "eval_loss": 3.105576276779175, | |
| "eval_runtime": 2.3729, | |
| "eval_samples_per_second": 118.422, | |
| "eval_steps_per_second": 59.422, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03003003003003003, | |
| "grad_norm": 0.8256561756134033, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9195, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 649047740252160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |