| { | |
| "best_global_step": 873, | |
| "best_metric": 0.09125778079032898, | |
| "best_model_checkpoint": "siglip2-finetune-full/checkpoint-873", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 873, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7899548289954829, | |
| "eval_loss": 0.7594003081321716, | |
| "eval_model_preparation_time": 0.0023, | |
| "eval_runtime": 118.1364, | |
| "eval_samples_per_second": 78.706, | |
| "eval_steps_per_second": 9.845, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 1.718213058419244, | |
| "grad_norm": 9.803659439086914, | |
| "learning_rate": 9.064398541919807e-05, | |
| "loss": 1.3365, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9234243923424392, | |
| "eval_loss": 0.2726958692073822, | |
| "eval_model_preparation_time": 0.0023, | |
| "eval_runtime": 117.6867, | |
| "eval_samples_per_second": 79.006, | |
| "eval_steps_per_second": 9.882, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9732200473220047, | |
| "eval_loss": 0.09125778079032898, | |
| "eval_model_preparation_time": 0.0023, | |
| "eval_runtime": 117.7794, | |
| "eval_samples_per_second": 78.944, | |
| "eval_steps_per_second": 9.874, | |
| "step": 873 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 873, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2.3373994572069765e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |