| { |
| "best_global_step": 10, |
| "best_metric": 0.7071229219436646, |
| "best_model_checkpoint": "distilbert_rand_10_v1_rte/checkpoint-10", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 60, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 2.1104700565338135, |
| "learning_rate": 4.9e-05, |
| "loss": 0.7329, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.47653429602888087, |
| "eval_loss": 0.7071229219436646, |
| "eval_runtime": 0.1272, |
| "eval_samples_per_second": 2177.181, |
| "eval_steps_per_second": 15.72, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.0915528535842896, |
| "learning_rate": 4.8e-05, |
| "loss": 0.6816, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.49458483754512633, |
| "eval_loss": 0.7139835357666016, |
| "eval_runtime": 0.1336, |
| "eval_samples_per_second": 2073.871, |
| "eval_steps_per_second": 14.974, |
| "step": 20 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.939078152179718, |
| "learning_rate": 4.7e-05, |
| "loss": 0.6469, |
| "step": 30 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.5306859205776173, |
| "eval_loss": 0.7382882833480835, |
| "eval_runtime": 0.1356, |
| "eval_samples_per_second": 2042.926, |
| "eval_steps_per_second": 14.75, |
| "step": 30 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 3.8303518295288086, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.5658, |
| "step": 40 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.5342960288808665, |
| "eval_loss": 0.8602527976036072, |
| "eval_runtime": 0.1382, |
| "eval_samples_per_second": 2004.998, |
| "eval_steps_per_second": 14.477, |
| "step": 40 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 1.504719614982605, |
| "learning_rate": 4.5e-05, |
| "loss": 0.4515, |
| "step": 50 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.49097472924187724, |
| "eval_loss": 0.9618232846260071, |
| "eval_runtime": 0.1388, |
| "eval_samples_per_second": 1995.997, |
| "eval_steps_per_second": 14.412, |
| "step": 50 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 9.033975601196289, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.3334, |
| "step": 60 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.5018050541516246, |
| "eval_loss": 1.2717946767807007, |
| "eval_runtime": 0.1468, |
| "eval_samples_per_second": 1887.432, |
| "eval_steps_per_second": 13.628, |
| "step": 60 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 60, |
| "total_flos": 989531467960320.0, |
| "train_loss": 0.5686906655629476, |
| "train_runtime": 21.9893, |
| "train_samples_per_second": 5661.854, |
| "train_steps_per_second": 22.738 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 50, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 5 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 989531467960320.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
