| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016909744240118367, | |
| "eval_steps": 8, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "eval_loss": 1.5858615636825562, | |
| "eval_runtime": 170.9718, | |
| "eval_samples_per_second": 14.564, | |
| "eval_steps_per_second": 7.282, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "grad_norm": 35.398643493652344, | |
| "learning_rate": 6e-05, | |
| "loss": 6.2493, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "grad_norm": 67.38201141357422, | |
| "learning_rate": 0.00012, | |
| "loss": 6.1214, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013527795392094695, | |
| "eval_loss": 1.5703749656677246, | |
| "eval_runtime": 170.9801, | |
| "eval_samples_per_second": 14.563, | |
| "eval_steps_per_second": 7.282, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "grad_norm": 112.6830062866211, | |
| "learning_rate": 0.00018, | |
| "loss": 6.1368, | |
| "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": 3267323221770240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |