| { |
| "best_metric": 0.36926180124282837, |
| "best_model_checkpoint": "bert-base-uncased-mrpc/checkpoint-58", |
| "epoch": 9.0, |
| "global_step": 261, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 4.9e-05, |
| "loss": 0.5716, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7475490196078431, |
| "eval_combined_score": 0.795625799637002, |
| "eval_f1": 0.8437025796661609, |
| "eval_loss": 0.5020303726196289, |
| "eval_runtime": 0.4937, |
| "eval_samples_per_second": 826.343, |
| "eval_steps_per_second": 8.101, |
| "step": 29 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 4.8e-05, |
| "loss": 0.3969, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8406862745098039, |
| "eval_combined_score": 0.8615727936744317, |
| "eval_f1": 0.8824593128390597, |
| "eval_loss": 0.36926180124282837, |
| "eval_runtime": 0.4931, |
| "eval_samples_per_second": 827.442, |
| "eval_steps_per_second": 8.112, |
| "step": 58 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 4.7e-05, |
| "loss": 0.2182, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8235294117647058, |
| "eval_combined_score": 0.851764705882353, |
| "eval_f1": 0.88, |
| "eval_loss": 0.5412256717681885, |
| "eval_runtime": 0.4943, |
| "eval_samples_per_second": 825.443, |
| "eval_steps_per_second": 8.093, |
| "step": 87 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.1135, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8259803921568627, |
| "eval_combined_score": 0.8503799668015354, |
| "eval_f1": 0.8747795414462081, |
| "eval_loss": 0.5103858709335327, |
| "eval_runtime": 0.4963, |
| "eval_samples_per_second": 822.006, |
| "eval_steps_per_second": 8.059, |
| "step": 116 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 4.5e-05, |
| "loss": 0.0772, |
| "step": 145 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8186274509803921, |
| "eval_combined_score": 0.8420409982174688, |
| "eval_f1": 0.8654545454545455, |
| "eval_loss": 0.6428085565567017, |
| "eval_runtime": 0.4896, |
| "eval_samples_per_second": 833.251, |
| "eval_steps_per_second": 8.169, |
| "step": 145 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.049, |
| "step": 174 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8259803921568627, |
| "eval_combined_score": 0.8492559052346252, |
| "eval_f1": 0.8725314183123878, |
| "eval_loss": 0.6365715265274048, |
| "eval_runtime": 0.4959, |
| "eval_samples_per_second": 822.818, |
| "eval_steps_per_second": 8.067, |
| "step": 174 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 4.3e-05, |
| "loss": 0.0356, |
| "step": 203 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.8357843137254902, |
| "eval_combined_score": 0.8627027005200762, |
| "eval_f1": 0.8896210873146623, |
| "eval_loss": 0.8413543105125427, |
| "eval_runtime": 0.4949, |
| "eval_samples_per_second": 824.358, |
| "eval_steps_per_second": 8.082, |
| "step": 203 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 4.2e-05, |
| "loss": 0.0335, |
| "step": 232 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8137254901960784, |
| "eval_combined_score": 0.8406606545057047, |
| "eval_f1": 0.867595818815331, |
| "eval_loss": 0.8573394417762756, |
| "eval_runtime": 0.4937, |
| "eval_samples_per_second": 826.354, |
| "eval_steps_per_second": 8.102, |
| "step": 232 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 4.1e-05, |
| "loss": 0.0234, |
| "step": 261 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.8308823529411765, |
| "eval_combined_score": 0.8582272461223296, |
| "eval_f1": 0.8855721393034827, |
| "eval_loss": 0.8893145322799683, |
| "eval_runtime": 0.4919, |
| "eval_samples_per_second": 829.453, |
| "eval_steps_per_second": 8.132, |
| "step": 261 |
| }, |
| { |
| "epoch": 9.0, |
| "step": 261, |
| "total_flos": 4342911143510016.0, |
| "train_loss": 0.16875747611239494, |
| "train_runtime": 157.0108, |
| "train_samples_per_second": 1168.072, |
| "train_steps_per_second": 9.235 |
| } |
| ], |
| "max_steps": 1450, |
| "num_train_epochs": 50, |
| "total_flos": 4342911143510016.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
