| { | |
| "best_metric": 0.41818181818181815, | |
| "best_model_checkpoint": "roberta-Questions-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current/checkpoint-422", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 844, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 475.60015869140625, | |
| "learning_rate": 2.0872026879361993e-05, | |
| "loss": 0.5219, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6110397946084724, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.4811629056930542, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 6.4472, | |
| "eval_samples_per_second": 120.828, | |
| "eval_steps_per_second": 7.6, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 5.935336589813232, | |
| "learning_rate": 1.3914684586241329e-05, | |
| "loss": 0.5152, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6713735558408216, | |
| "eval_f1": 0.41818181818181815, | |
| "eval_loss": 0.5361036062240601, | |
| "eval_precision": 0.6715328467153284, | |
| "eval_recall": 0.30363036303630364, | |
| "eval_runtime": 6.0743, | |
| "eval_samples_per_second": 128.246, | |
| "eval_steps_per_second": 8.067, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 7.51805305480957, | |
| "learning_rate": 6.957342293120664e-06, | |
| "loss": 0.4977, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6097560975609756, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.4554288983345032, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 5.9395, | |
| "eval_samples_per_second": 131.156, | |
| "eval_steps_per_second": 8.25, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 5.534423828125, | |
| "learning_rate": 0.0, | |
| "loss": 0.4749, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6161745827984596, | |
| "eval_f1": 0.032362459546925564, | |
| "eval_loss": 0.47242072224617004, | |
| "eval_precision": 0.8333333333333334, | |
| "eval_recall": 0.0165016501650165, | |
| "eval_runtime": 6.1591, | |
| "eval_samples_per_second": 126.48, | |
| "eval_steps_per_second": 7.956, | |
| "step": 844 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 844, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 1.114287760918584e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |