| { | |
| "best_metric": 0.5374663942789677, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1072", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1340, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4915260076522827, | |
| "eval_matthews_correlation": 0.42108781728525657, | |
| "eval_runtime": 2.7721, | |
| "eval_samples_per_second": 376.249, | |
| "eval_steps_per_second": 23.809, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.8656716417910446, | |
| "grad_norm": 10.045269966125488, | |
| "learning_rate": 9.237680217440977e-06, | |
| "loss": 0.4722, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.4820975959300995, | |
| "eval_matthews_correlation": 0.48823698718987535, | |
| "eval_runtime": 2.747, | |
| "eval_samples_per_second": 379.683, | |
| "eval_steps_per_second": 24.026, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.5226131677627563, | |
| "eval_matthews_correlation": 0.49626557567073315, | |
| "eval_runtime": 2.7715, | |
| "eval_samples_per_second": 376.332, | |
| "eval_steps_per_second": 23.814, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 3.7313432835820897, | |
| "grad_norm": 3.9226198196411133, | |
| "learning_rate": 3.739061040392777e-06, | |
| "loss": 0.2716, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.5235798954963684, | |
| "eval_matthews_correlation": 0.5374663942789677, | |
| "eval_runtime": 2.8991, | |
| "eval_samples_per_second": 359.771, | |
| "eval_steps_per_second": 22.766, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.5622767806053162, | |
| "eval_matthews_correlation": 0.5241753618868132, | |
| "eval_runtime": 2.7405, | |
| "eval_samples_per_second": 380.587, | |
| "eval_steps_per_second": 24.083, | |
| "step": 1340 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1340, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 191499476809020.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.4736299394489178e-05, | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 32, | |
| "seed": 11 | |
| } | |
| } | |