| { | |
| "best_metric": 0.5298831429205758, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-3207", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 4276, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4677268475210477, | |
| "grad_norm": 12.974456787109375, | |
| "learning_rate": 1.1101348047567246e-05, | |
| "loss": 0.5482, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9354536950420954, | |
| "grad_norm": 6.763242721557617, | |
| "learning_rate": 9.955698094257931e-06, | |
| "loss": 0.4949, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.47264614701271057, | |
| "eval_matthews_correlation": 0.46472372045336796, | |
| "eval_runtime": 0.7997, | |
| "eval_samples_per_second": 1304.217, | |
| "eval_steps_per_second": 82.53, | |
| "step": 1069 | |
| }, | |
| { | |
| "epoch": 1.4031805425631432, | |
| "grad_norm": 21.93242835998535, | |
| "learning_rate": 8.810048140948619e-06, | |
| "loss": 0.3822, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.8709073900841908, | |
| "grad_norm": 23.08902359008789, | |
| "learning_rate": 7.664398187639304e-06, | |
| "loss": 0.3651, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5118151903152466, | |
| "eval_matthews_correlation": 0.5238946707778435, | |
| "eval_runtime": 0.7256, | |
| "eval_samples_per_second": 1437.525, | |
| "eval_steps_per_second": 90.965, | |
| "step": 2138 | |
| }, | |
| { | |
| "epoch": 2.3386342376052385, | |
| "grad_norm": 0.19134408235549927, | |
| "learning_rate": 6.5187482343299915e-06, | |
| "loss": 0.2818, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.8063610851262863, | |
| "grad_norm": 25.71369743347168, | |
| "learning_rate": 5.373098281020679e-06, | |
| "loss": 0.2996, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.739141583442688, | |
| "eval_matthews_correlation": 0.5298831429205758, | |
| "eval_runtime": 0.7927, | |
| "eval_samples_per_second": 1315.739, | |
| "eval_steps_per_second": 83.259, | |
| "step": 3207 | |
| }, | |
| { | |
| "epoch": 3.2740879326473338, | |
| "grad_norm": 4.724560260772705, | |
| "learning_rate": 4.227448327711365e-06, | |
| "loss": 0.2348, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.7418147801683816, | |
| "grad_norm": 2.277522563934326, | |
| "learning_rate": 3.0817983744020528e-06, | |
| "loss": 0.2181, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.830931544303894, | |
| "eval_matthews_correlation": 0.5138995234247261, | |
| "eval_runtime": 0.7983, | |
| "eval_samples_per_second": 1306.597, | |
| "eval_steps_per_second": 82.68, | |
| "step": 4276 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5345, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 258412847731296.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.2246998000876558e-05, | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 8, | |
| "seed": 6 | |
| } | |
| } | |