| { | |
| "best_metric": 0.12910686958067819, | |
| "best_model_checkpoint": "./output/modernBERT-base-sentiment-v2/checkpoint-8", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 16, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.8373, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.12910686958067819, | |
| "eval_loss": 1.8330078125, | |
| "eval_precision": 0.16504066117321736, | |
| "eval_recall": 0.1890018282051825, | |
| "eval_runtime": 8.3441, | |
| "eval_samples_per_second": 239.691, | |
| "eval_steps_per_second": 0.12, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.8336, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.875, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.8364, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.12910686958067819, | |
| "eval_loss": 1.8330078125, | |
| "eval_precision": 0.16504066117321736, | |
| "eval_recall": 0.1890018282051825, | |
| "eval_runtime": 0.2749, | |
| "eval_samples_per_second": 7276.302, | |
| "eval_steps_per_second": 3.638, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 16, | |
| "total_flos": 1489153141243904.0, | |
| "train_loss": 1.836273193359375, | |
| "train_runtime": 55.8529, | |
| "train_samples_per_second": 572.934, | |
| "train_steps_per_second": 0.286 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 16, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 5.0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1489153141243904.0, | |
| "train_batch_size": 1024, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |