| { | |
| "best_global_step": 170, | |
| "best_metric": 0.6184515357017517, | |
| "best_model_checkpoint": "bert_base_train_book_ent_15p_s_init_cola/checkpoint-170", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 340, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.1766574382781982, | |
| "learning_rate": 4.9029411764705883e-05, | |
| "loss": 0.6207, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6912751793861389, | |
| "eval_loss": 0.6185039281845093, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 0.8903, | |
| "eval_samples_per_second": 1171.53, | |
| "eval_steps_per_second": 5.616, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.5290485620498657, | |
| "learning_rate": 4.8029411764705886e-05, | |
| "loss": 0.6093, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6912751793861389, | |
| "eval_loss": 0.6191949248313904, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 0.8909, | |
| "eval_samples_per_second": 1170.701, | |
| "eval_steps_per_second": 5.612, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.8824849128723145, | |
| "learning_rate": 4.702941176470588e-05, | |
| "loss": 0.61, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6912751793861389, | |
| "eval_loss": 0.6199177503585815, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 0.9094, | |
| "eval_samples_per_second": 1146.898, | |
| "eval_steps_per_second": 5.498, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.128862738609314, | |
| "learning_rate": 4.6029411764705885e-05, | |
| "loss": 0.6103, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6912751793861389, | |
| "eval_loss": 0.618511438369751, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 0.904, | |
| "eval_samples_per_second": 1153.724, | |
| "eval_steps_per_second": 5.531, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.0845144987106323, | |
| "learning_rate": 4.502941176470589e-05, | |
| "loss": 0.6113, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6912751793861389, | |
| "eval_loss": 0.6184515357017517, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 0.8926, | |
| "eval_samples_per_second": 1168.527, | |
| "eval_steps_per_second": 5.602, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.6451035737991333, | |
| "learning_rate": 4.4029411764705884e-05, | |
| "loss": 0.6094, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6912751793861389, | |
| "eval_loss": 0.6199439764022827, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 0.8889, | |
| "eval_samples_per_second": 1173.306, | |
| "eval_steps_per_second": 5.625, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 1.6885813474655151, | |
| "learning_rate": 4.302941176470589e-05, | |
| "loss": 0.6098, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6912751793861389, | |
| "eval_loss": 0.6215131878852844, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 0.889, | |
| "eval_samples_per_second": 1173.173, | |
| "eval_steps_per_second": 5.624, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.6558329463005066, | |
| "learning_rate": 4.202941176470588e-05, | |
| "loss": 0.6113, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6912751793861389, | |
| "eval_loss": 0.6247884035110474, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 0.8876, | |
| "eval_samples_per_second": 1175.115, | |
| "eval_steps_per_second": 5.633, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.49616092443466187, | |
| "learning_rate": 4.1029411764705886e-05, | |
| "loss": 0.6098, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6912751793861389, | |
| "eval_loss": 0.6285766959190369, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 0.9282, | |
| "eval_samples_per_second": 1123.701, | |
| "eval_steps_per_second": 5.387, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.553864061832428, | |
| "learning_rate": 4.002941176470588e-05, | |
| "loss": 0.6106, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6912751793861389, | |
| "eval_loss": 0.6254100799560547, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 0.8992, | |
| "eval_samples_per_second": 1159.91, | |
| "eval_steps_per_second": 5.56, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 340, | |
| "total_flos": 1.12493131719168e+16, | |
| "train_loss": 0.6112596624037798, | |
| "train_runtime": 186.9033, | |
| "train_samples_per_second": 2287.547, | |
| "train_steps_per_second": 9.096 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 1700, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 5 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.12493131719168e+16, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |