| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0001094715716012498, | |
| "eval_steps": 1, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.649052386708327e-05, | |
| "grad_norm": 3.23372220993042, | |
| "learning_rate": 0.0010000000474974513, | |
| "loss": 1.8488, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.649052386708327e-05, | |
| "eval_loss": 2.09584379196167, | |
| "eval_runtime": 1870.07, | |
| "eval_samples_per_second": 6.17, | |
| "eval_steps_per_second": 6.17, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.298104773416654e-05, | |
| "grad_norm": 3.9737770557403564, | |
| "learning_rate": 0.0020000000949949026, | |
| "loss": 2.2878, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.298104773416654e-05, | |
| "eval_loss": 1.8284188508987427, | |
| "eval_runtime": 1784.9342, | |
| "eval_samples_per_second": 6.465, | |
| "eval_steps_per_second": 6.465, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001094715716012498, | |
| "grad_norm": 3.4407198429107666, | |
| "learning_rate": 0.003000000026077032, | |
| "loss": 1.9633, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001094715716012498, | |
| "eval_loss": 3.4792585372924805, | |
| "eval_runtime": 1849.5831, | |
| "eval_samples_per_second": 6.239, | |
| "eval_steps_per_second": 6.239, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 3, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 217473780547584.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |