| { | |
| "best_global_step": 892, | |
| "best_metric": 0.7297645875990197, | |
| "best_model_checkpoint": "outputs/vit5-spam-multiclass/checkpoint-892", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 892, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.4986908435821533, | |
| "learning_rate": 4.998771926094749e-05, | |
| "loss": 0.4131, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8878386893509767, | |
| "eval_f1": 0.6754635713978917, | |
| "eval_loss": 0.33189064264297485, | |
| "eval_precision": 0.8548849592374463, | |
| "eval_recall": 0.6077483668350012, | |
| "eval_runtime": 3.0572, | |
| "eval_samples_per_second": 519.102, | |
| "eval_steps_per_second": 16.355, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 10.55453872680664, | |
| "learning_rate": 4.995077872180951e-05, | |
| "loss": 0.2462, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8960302457466919, | |
| "eval_f1": 0.7297645875990197, | |
| "eval_loss": 0.3140903413295746, | |
| "eval_precision": 0.8464987361646404, | |
| "eval_recall": 0.6676163391360883, | |
| "eval_runtime": 3.0644, | |
| "eval_samples_per_second": 517.89, | |
| "eval_steps_per_second": 16.317, | |
| "step": 892 | |
| } | |
| ], | |
| "logging_steps": 446, | |
| "max_steps": 44600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "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": 0.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |