| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015996160921378868, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00031992321842757736, | |
| "eval_loss": 1.8430436849594116, | |
| "eval_runtime": 153.2735, | |
| "eval_samples_per_second": 34.35, | |
| "eval_steps_per_second": 4.3, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031992321842757737, | |
| "grad_norm": 2.4950242042541504, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 6.7553, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006398464368551547, | |
| "grad_norm": 4.571041107177734, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 5.4044, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009597696552827321, | |
| "grad_norm": 4.416581630706787, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 4.8963, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012796928737103095, | |
| "grad_norm": 3.993983268737793, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 5.1191, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015996160921378868, | |
| "grad_norm": 4.616549015045166, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 4.7698, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.015996160921378868, | |
| "eval_loss": 1.1898785829544067, | |
| "eval_runtime": 80.8462, | |
| "eval_samples_per_second": 65.124, | |
| "eval_steps_per_second": 8.151, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.870786583704371e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |