| { |
| "best_metric": 2.52870512008667, |
| "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_data_aug_wnli/checkpoint-435", |
| "epoch": 6.0, |
| "global_step": 2610, |
| "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": 0.6415, |
| "step": 435 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.1267605633802817, |
| "eval_loss": 2.52870512008667, |
| "eval_runtime": 0.0842, |
| "eval_samples_per_second": 843.551, |
| "eval_steps_per_second": 11.881, |
| "step": 435 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 4.8e-05, |
| "loss": 0.4894, |
| "step": 870 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.1267605633802817, |
| "eval_loss": 3.51229190826416, |
| "eval_runtime": 0.0843, |
| "eval_samples_per_second": 842.039, |
| "eval_steps_per_second": 11.86, |
| "step": 870 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 4.7e-05, |
| "loss": 0.4427, |
| "step": 1305 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.09859154929577464, |
| "eval_loss": 4.8804216384887695, |
| "eval_runtime": 0.084, |
| "eval_samples_per_second": 845.122, |
| "eval_steps_per_second": 11.903, |
| "step": 1305 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.4026, |
| "step": 1740 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.09859154929577464, |
| "eval_loss": 7.240967750549316, |
| "eval_runtime": 0.0843, |
| "eval_samples_per_second": 841.758, |
| "eval_steps_per_second": 11.856, |
| "step": 1740 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 4.5e-05, |
| "loss": 0.3707, |
| "step": 2175 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.08450704225352113, |
| "eval_loss": 10.576957702636719, |
| "eval_runtime": 0.086, |
| "eval_samples_per_second": 825.14, |
| "eval_steps_per_second": 11.622, |
| "step": 2175 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.3376, |
| "step": 2610 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.09859154929577464, |
| "eval_loss": 7.2100701332092285, |
| "eval_runtime": 0.0846, |
| "eval_samples_per_second": 839.513, |
| "eval_steps_per_second": 11.824, |
| "step": 2610 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 2610, |
| "total_flos": 1.0467306136141824e+16, |
| "train_loss": 0.44740789420759997, |
| "train_runtime": 1259.761, |
| "train_samples_per_second": 2208.355, |
| "train_steps_per_second": 17.265 |
| } |
| ], |
| "max_steps": 21750, |
| "num_train_epochs": 50, |
| "total_flos": 1.0467306136141824e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
