| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03536693191865606, | |
| "eval_steps": 8, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0035366931918656055, | |
| "eval_loss": 4.540555000305176, | |
| "eval_runtime": 8.8184, | |
| "eval_samples_per_second": 13.494, | |
| "eval_steps_per_second": 6.804, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010610079575596816, | |
| "grad_norm": 3.1070003509521484, | |
| "learning_rate": 3e-05, | |
| "loss": 4.5239, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.021220159151193633, | |
| "grad_norm": 3.322465419769287, | |
| "learning_rate": 6e-05, | |
| "loss": 4.4687, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028293545534924844, | |
| "eval_loss": 4.284606456756592, | |
| "eval_runtime": 8.5088, | |
| "eval_samples_per_second": 13.986, | |
| "eval_steps_per_second": 7.052, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03183023872679045, | |
| "grad_norm": 2.4278759956359863, | |
| "learning_rate": 9e-05, | |
| "loss": 4.1655, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1378569745858560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |