| { | |
| "best_metric": 0.6848270226096431, | |
| "best_model_checkpoint": "model_checkpoints/fine-tuned_blog-authorship-gender/deberta-v3-small/checkpoint-858", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 858, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 25.72825813293457, | |
| "learning_rate": 3.3372183372183376e-05, | |
| "loss": 0.6674, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6743204011612562, | |
| "eval_f1": 0.5927392739273928, | |
| "eval_loss": 0.6185831427574158, | |
| "eval_runtime": 262.6549, | |
| "eval_samples_per_second": 14.426, | |
| "eval_steps_per_second": 3.609, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 12.697623252868652, | |
| "learning_rate": 1.6705516705516705e-05, | |
| "loss": 0.5889, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6946423858537872, | |
| "eval_f1": 0.6848270226096431, | |
| "eval_loss": 0.5841246843338013, | |
| "eval_runtime": 262.83, | |
| "eval_samples_per_second": 14.416, | |
| "eval_steps_per_second": 3.607, | |
| "step": 858 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1287, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 908891196438528.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |