| { |
| "best_metric": 0.584678053855896, |
| "best_model_checkpoint": "add_BERT_24_mrpc/checkpoint-29", |
| "epoch": 6.0, |
| "global_step": 174, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 3.9200000000000004e-05, |
| "loss": 0.6554, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7009803921568627, |
| "eval_combined_score": 0.7572180248246088, |
| "eval_f1": 0.8134556574923548, |
| "eval_loss": 0.584678053855896, |
| "eval_runtime": 0.7789, |
| "eval_samples_per_second": 523.804, |
| "eval_steps_per_second": 5.135, |
| "step": 29 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3.8400000000000005e-05, |
| "loss": 0.6027, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6985294117647058, |
| "eval_combined_score": 0.7567835028748342, |
| "eval_f1": 0.8150375939849624, |
| "eval_loss": 0.592502772808075, |
| "eval_runtime": 0.7816, |
| "eval_samples_per_second": 522.024, |
| "eval_steps_per_second": 5.118, |
| "step": 58 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3.76e-05, |
| "loss": 0.5423, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.6887254901960784, |
| "eval_combined_score": 0.7468205023945063, |
| "eval_f1": 0.804915514592934, |
| "eval_loss": 0.6009986996650696, |
| "eval_runtime": 0.7825, |
| "eval_samples_per_second": 521.386, |
| "eval_steps_per_second": 5.112, |
| "step": 87 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 3.680000000000001e-05, |
| "loss": 0.4401, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.696078431372549, |
| "eval_combined_score": 0.7505549389567148, |
| "eval_f1": 0.8050314465408805, |
| "eval_loss": 0.6617496609687805, |
| "eval_runtime": 0.7798, |
| "eval_samples_per_second": 523.205, |
| "eval_steps_per_second": 5.129, |
| "step": 116 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 3.6e-05, |
| "loss": 0.2731, |
| "step": 145 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.6348039215686274, |
| "eval_combined_score": 0.674954542046264, |
| "eval_f1": 0.7151051625239007, |
| "eval_loss": 0.9531154036521912, |
| "eval_runtime": 0.7861, |
| "eval_samples_per_second": 519.042, |
| "eval_steps_per_second": 5.089, |
| "step": 145 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 3.52e-05, |
| "loss": 0.16, |
| "step": 174 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.6985294117647058, |
| "eval_combined_score": 0.7514904610492845, |
| "eval_f1": 0.8044515103338632, |
| "eval_loss": 1.0282580852508545, |
| "eval_runtime": 0.7848, |
| "eval_samples_per_second": 519.861, |
| "eval_steps_per_second": 5.097, |
| "step": 174 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 174, |
| "total_flos": 3143269802311680.0, |
| "train_loss": 0.44560779374221277, |
| "train_runtime": 154.5382, |
| "train_samples_per_second": 1186.762, |
| "train_steps_per_second": 9.383 |
| } |
| ], |
| "max_steps": 1450, |
| "num_train_epochs": 50, |
| "total_flos": 3143269802311680.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
