| { | |
| "best_metric": 0.1652834266424179, | |
| "best_model_checkpoint": "gemma_sequence_classification/checkpoint-618", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1030, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.2220354527235031, | |
| "eval_pearson": 0.9313447217769323, | |
| "eval_runtime": 19.3784, | |
| "eval_samples_per_second": 48.095, | |
| "eval_steps_per_second": 6.038, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.2142479419708252, | |
| "eval_pearson": 0.9564116534995298, | |
| "eval_runtime": 19.0857, | |
| "eval_samples_per_second": 48.832, | |
| "eval_steps_per_second": 6.13, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 2.4271844660194173, | |
| "grad_norm": 1.4725639820098877, | |
| "learning_rate": 5.145631067961165e-05, | |
| "loss": 0.3426, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.1652834266424179, | |
| "eval_pearson": 0.9715602494395954, | |
| "eval_runtime": 18.9227, | |
| "eval_samples_per_second": 49.253, | |
| "eval_steps_per_second": 6.183, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.25449901819229126, | |
| "eval_pearson": 0.9749936144613789, | |
| "eval_runtime": 19.4287, | |
| "eval_samples_per_second": 47.97, | |
| "eval_steps_per_second": 6.022, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 4.854368932038835, | |
| "grad_norm": 0.3754734396934509, | |
| "learning_rate": 2.912621359223301e-06, | |
| "loss": 0.0318, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.21454918384552002, | |
| "eval_pearson": 0.9717832815868759, | |
| "eval_runtime": 19.1817, | |
| "eval_samples_per_second": 48.588, | |
| "eval_steps_per_second": 6.1, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1030, | |
| "total_flos": 6.696757888652698e+16, | |
| "train_loss": 0.18185023025980274, | |
| "train_runtime": 1350.5171, | |
| "train_samples_per_second": 24.306, | |
| "train_steps_per_second": 0.763 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1030, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 6.696757888652698e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |