| { |
| "best_global_step": 1878, |
| "best_metric": 0.8070130348205566, |
| "best_model_checkpoint": "classifier-clinc-MBbase-distilled/run-3/checkpoint-1878", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 1878, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8803225806451613, |
| "eval_loss": 2.851562261581421, |
| "eval_runtime": 8.7066, |
| "eval_samples_per_second": 356.05, |
| "eval_steps_per_second": 11.141, |
| "step": 313 |
| }, |
| { |
| "epoch": 1.5974440894568689, |
| "grad_norm": 22.713924407958984, |
| "learning_rate": 1.468583599574015e-05, |
| "loss": 7.2917, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9370967741935484, |
| "eval_loss": 1.3482674360275269, |
| "eval_runtime": 8.8149, |
| "eval_samples_per_second": 351.677, |
| "eval_steps_per_second": 11.004, |
| "step": 626 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9458064516129032, |
| "eval_loss": 1.0475715398788452, |
| "eval_runtime": 9.4956, |
| "eval_samples_per_second": 326.469, |
| "eval_steps_per_second": 10.215, |
| "step": 939 |
| }, |
| { |
| "epoch": 3.194888178913738, |
| "grad_norm": 3.1599416732788086, |
| "learning_rate": 9.361022364217253e-06, |
| "loss": 0.8805, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9519354838709677, |
| "eval_loss": 0.9085509777069092, |
| "eval_runtime": 8.7553, |
| "eval_samples_per_second": 354.07, |
| "eval_steps_per_second": 11.079, |
| "step": 1252 |
| }, |
| { |
| "epoch": 4.792332268370607, |
| "grad_norm": 4.04980993270874, |
| "learning_rate": 4.0362087326943564e-06, |
| "loss": 0.4496, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9532258064516129, |
| "eval_loss": 0.8273545503616333, |
| "eval_runtime": 8.7297, |
| "eval_samples_per_second": 355.11, |
| "eval_steps_per_second": 11.111, |
| "step": 1565 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9535483870967741, |
| "eval_loss": 0.8070130348205566, |
| "eval_runtime": 10.1059, |
| "eval_samples_per_second": 306.751, |
| "eval_steps_per_second": 9.598, |
| "step": 1878 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1878, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 665835745748832.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": { |
| "alpha": 0.3917157288742445, |
| "num_train_epochs": 6, |
| "temperature": 3.2114012903927867 |
| } |
| } |
|
|
