| { |
| "best_global_step": 250, |
| "best_metric": 0.3948093354701996, |
| "best_model_checkpoint": "topic_classifier_model/run-9816kcc3/checkpoint-250", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.879, |
| "eval_loss": 0.3948093354701996, |
| "eval_runtime": 2.6827, |
| "eval_samples_per_second": 372.763, |
| "eval_steps_per_second": 23.484, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 39.29621887207031, |
| "learning_rate": 7.500895564789535e-06, |
| "loss": 0.5523, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.879, |
| "eval_loss": 0.4520011842250824, |
| "eval_runtime": 2.7875, |
| "eval_samples_per_second": 358.749, |
| "eval_steps_per_second": 22.601, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 36735140779680.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": { |
| "_wandb": { |
| "cli_version": "0.21.3", |
| "m": [], |
| "python_version": "3.12.11", |
| "t": { |
| "1": [ |
| 1, |
| 2, |
| 3, |
| 5, |
| 11, |
| 12, |
| 41, |
| 49, |
| 51, |
| 53, |
| 71, |
| 98, |
| 100, |
| 105 |
| ], |
| "12": "0.21.3", |
| "13": "linux-x86_64", |
| "3": [ |
| 14 |
| ], |
| "4": "3.12.11", |
| "5": "0.21.3", |
| "6": "4.56.1", |
| "8": [ |
| 1, |
| 12 |
| ] |
| } |
| }, |
| "assignments": {}, |
| "learning_rate": 1.1240103243940362e-05, |
| "metric": "eval/loss", |
| "num_train_epochs": 6, |
| "per_device_train_batch_size": 4, |
| "seed": 2 |
| } |
| } |
|
|
