| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.153846153846154, | |
| "eval_steps": 500, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 1.047078013420105, | |
| "learning_rate": 0.00016, | |
| "loss": 9.5015, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.4615384615384617, | |
| "grad_norm": 1.4213268756866455, | |
| "learning_rate": 0.00012, | |
| "loss": 9.1618, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 3.6923076923076925, | |
| "grad_norm": 1.623157024383545, | |
| "learning_rate": 8e-05, | |
| "loss": 8.7262, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 4.923076923076923, | |
| "grad_norm": 1.7331207990646362, | |
| "learning_rate": 4e-05, | |
| "loss": 8.3712, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 2.034743547439575, | |
| "learning_rate": 0.0, | |
| "loss": 8.0607, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "step": 10, | |
| "total_flos": 86603100263016.0, | |
| "train_loss": 8.76425724029541, | |
| "train_runtime": 482.9591, | |
| "train_samples_per_second": 1.015, | |
| "train_steps_per_second": 0.021 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 86603100263016.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |