| { |
| "best_metric": 0.4384092092514038, |
| "best_model_checkpoint": "bert-base-uncased-mnli/checkpoint-6136", |
| "epoch": 9.0, |
| "global_step": 27612, |
| "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": 0.5194, |
| "step": 3068 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8306673458991339, |
| "eval_loss": 0.44682058691978455, |
| "eval_runtime": 11.7523, |
| "eval_samples_per_second": 835.157, |
| "eval_steps_per_second": 6.552, |
| "step": 3068 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 4.8e-05, |
| "loss": 0.3445, |
| "step": 6136 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8427916454406521, |
| "eval_loss": 0.4384092092514038, |
| "eval_runtime": 11.6281, |
| "eval_samples_per_second": 844.073, |
| "eval_steps_per_second": 6.622, |
| "step": 6136 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 4.7e-05, |
| "loss": 0.2341, |
| "step": 9204 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8414671421293938, |
| "eval_loss": 0.49464237689971924, |
| "eval_runtime": 11.6455, |
| "eval_samples_per_second": 842.816, |
| "eval_steps_per_second": 6.612, |
| "step": 9204 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.1625, |
| "step": 12272 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8388181355068772, |
| "eval_loss": 0.5478587746620178, |
| "eval_runtime": 11.6369, |
| "eval_samples_per_second": 843.434, |
| "eval_steps_per_second": 6.617, |
| "step": 12272 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 4.5e-05, |
| "loss": 0.1218, |
| "step": 15340 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8357615894039735, |
| "eval_loss": 0.6348403096199036, |
| "eval_runtime": 11.6977, |
| "eval_samples_per_second": 839.05, |
| "eval_steps_per_second": 6.582, |
| "step": 15340 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.0968, |
| "step": 18408 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8314824248599083, |
| "eval_loss": 0.6619517207145691, |
| "eval_runtime": 11.7032, |
| "eval_samples_per_second": 838.657, |
| "eval_steps_per_second": 6.579, |
| "step": 18408 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 4.3e-05, |
| "loss": 0.0799, |
| "step": 21476 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.828731533367295, |
| "eval_loss": 0.7071842551231384, |
| "eval_runtime": 11.638, |
| "eval_samples_per_second": 843.356, |
| "eval_steps_per_second": 6.616, |
| "step": 21476 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 4.2e-05, |
| "loss": 0.0675, |
| "step": 24544 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8306673458991339, |
| "eval_loss": 0.7658949494361877, |
| "eval_runtime": 11.6403, |
| "eval_samples_per_second": 843.193, |
| "eval_steps_per_second": 6.615, |
| "step": 24544 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 4.1e-05, |
| "loss": 0.0592, |
| "step": 27612 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.8304635761589404, |
| "eval_loss": 0.7978113889694214, |
| "eval_runtime": 11.7438, |
| "eval_samples_per_second": 835.763, |
| "eval_steps_per_second": 6.557, |
| "step": 27612 |
| }, |
| { |
| "epoch": 9.0, |
| "step": 27612, |
| "total_flos": 4.6496322950057165e+17, |
| "train_loss": 0.18730783994415784, |
| "train_runtime": 11190.3342, |
| "train_samples_per_second": 1754.648, |
| "train_steps_per_second": 13.708 |
| } |
| ], |
| "max_steps": 153400, |
| "num_train_epochs": 50, |
| "total_flos": 4.6496322950057165e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
