| { | |
| "best_metric": 1.0016170740127563, | |
| "best_model_checkpoint": "distilbert_sa_GLUE_Experiment_data_aug_qnli_192/checkpoint-16604", | |
| "epoch": 6.0, | |
| "global_step": 99624, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.9000240905805834e-05, | |
| "loss": 0.5035, | |
| "step": 16604 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5701995240710233, | |
| "eval_loss": 1.0016170740127563, | |
| "eval_runtime": 2.0613, | |
| "eval_samples_per_second": 2650.266, | |
| "eval_steps_per_second": 10.673, | |
| "step": 16604 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.800072271741749e-05, | |
| "loss": 0.2645, | |
| "step": 33208 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5723961193483434, | |
| "eval_loss": 1.2295063734054565, | |
| "eval_runtime": 2.0134, | |
| "eval_samples_per_second": 2713.378, | |
| "eval_steps_per_second": 10.927, | |
| "step": 33208 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.700108407612624e-05, | |
| "loss": 0.1684, | |
| "step": 49812 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5826468973091707, | |
| "eval_loss": 1.3803638219833374, | |
| "eval_runtime": 2.0205, | |
| "eval_samples_per_second": 2703.803, | |
| "eval_steps_per_second": 10.888, | |
| "step": 49812 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.600150566128644e-05, | |
| "loss": 0.1171, | |
| "step": 66416 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5791689547867472, | |
| "eval_loss": 1.5434190034866333, | |
| "eval_runtime": 2.1806, | |
| "eval_samples_per_second": 2505.22, | |
| "eval_steps_per_second": 10.089, | |
| "step": 66416 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.50019874728981e-05, | |
| "loss": 0.085, | |
| "step": 83020 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5791689547867472, | |
| "eval_loss": 1.5555695295333862, | |
| "eval_runtime": 2.0169, | |
| "eval_samples_per_second": 2708.667, | |
| "eval_steps_per_second": 10.908, | |
| "step": 83020 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.40024090580583e-05, | |
| "loss": 0.064, | |
| "step": 99624 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5731283177741168, | |
| "eval_loss": 1.7283711433410645, | |
| "eval_runtime": 2.0328, | |
| "eval_samples_per_second": 2687.445, | |
| "eval_steps_per_second": 10.823, | |
| "step": 99624 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 99624, | |
| "total_flos": 3.145274644727071e+17, | |
| "train_loss": 0.2004248596794259, | |
| "train_runtime": 16743.2029, | |
| "train_samples_per_second": 12693.243, | |
| "train_steps_per_second": 49.584 | |
| } | |
| ], | |
| "max_steps": 830200, | |
| "num_train_epochs": 50, | |
| "total_flos": 3.145274644727071e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |