| { |
| "best_global_step": 500, |
| "best_metric": 0.6061989665031433, |
| "best_model_checkpoint": "topic_classifier_model/run-m5alrfwj/checkpoint-500", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 1250, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.852, |
| "eval_loss": 0.6556681394577026, |
| "eval_runtime": 3.5365, |
| "eval_samples_per_second": 282.762, |
| "eval_steps_per_second": 17.814, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.2926628589630127, |
| "learning_rate": 3.6834458632458664e-05, |
| "loss": 0.4736, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.872, |
| "eval_loss": 0.6061989665031433, |
| "eval_runtime": 2.8624, |
| "eval_samples_per_second": 349.36, |
| "eval_steps_per_second": 22.01, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.877, |
| "eval_loss": 0.6755268573760986, |
| "eval_runtime": 2.776, |
| "eval_samples_per_second": 360.235, |
| "eval_steps_per_second": 22.695, |
| "step": 750 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.07131870090961456, |
| "learning_rate": 1.231085102096821e-05, |
| "loss": 0.2149, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.881, |
| "eval_loss": 0.6423977017402649, |
| "eval_runtime": 2.756, |
| "eval_samples_per_second": 362.842, |
| "eval_steps_per_second": 22.859, |
| "step": 1000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.879, |
| "eval_loss": 0.6394979953765869, |
| "eval_runtime": 7.4793, |
| "eval_samples_per_second": 133.701, |
| "eval_steps_per_second": 8.423, |
| "step": 1250 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1250, |
| "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": 73536517621056.0, |
| "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": 6.130901902872614e-05, |
| "metric": "eval/loss", |
| "num_train_epochs": 5, |
| "per_device_train_batch_size": 4, |
| "seed": 40 |
| } |
| } |
|
|
