| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.8, | |
| "eval_steps": 500, | |
| "global_step": 12, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.17948530614376068, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 8.9023, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.33971741795539856, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 8.7931, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.4960370361804962, | |
| "learning_rate": 0.0001, | |
| "loss": 8.6895, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.5553238391876221, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 5.3485, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.7772231698036194, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 8.4708, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.7240044474601746, | |
| "learning_rate": 0.0, | |
| "loss": 8.4396, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "step": 12, | |
| "total_flos": 33316935156720.0, | |
| "train_loss": 8.10729185740153, | |
| "train_runtime": 84.0152, | |
| "train_samples_per_second": 2.381, | |
| "train_steps_per_second": 0.143 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 12, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 33316935156720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |