| { | |
| "best_global_step": 1970, | |
| "best_metric": 0.13895583152770996, | |
| "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1970", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1970, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5076142131979695, | |
| "grad_norm": 8.941224098205566, | |
| "learning_rate": 0.000153125, | |
| "loss": 1.4212, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8340634920634921, | |
| "eval_loss": 0.5306099653244019, | |
| "eval_model_preparation_time": 0.003, | |
| "eval_runtime": 415.7745, | |
| "eval_samples_per_second": 75.762, | |
| "eval_steps_per_second": 9.471, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 1.015228426395939, | |
| "grad_norm": 8.13437557220459, | |
| "learning_rate": 0.00010104166666666668, | |
| "loss": 0.686, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.5228426395939088, | |
| "grad_norm": 7.881953239440918, | |
| "learning_rate": 4.8958333333333335e-05, | |
| "loss": 0.3992, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9532063492063492, | |
| "eval_loss": 0.13895583152770996, | |
| "eval_model_preparation_time": 0.003, | |
| "eval_runtime": 418.2101, | |
| "eval_samples_per_second": 75.321, | |
| "eval_steps_per_second": 9.416, | |
| "step": 1970 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1970, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 5.278477735286784e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |