| { | |
| "best_global_step": 626, | |
| "best_metric": 0.027753479778766632, | |
| "best_model_checkpoint": "siglip2-finetune-full/checkpoint-626", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 626, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9401, | |
| "eval_loss": 0.1987909972667694, | |
| "eval_model_preparation_time": 0.0036, | |
| "eval_runtime": 204.0582, | |
| "eval_samples_per_second": 49.006, | |
| "eval_steps_per_second": 6.126, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 1.5974440894568689, | |
| "grad_norm": 9.541287422180176, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.3678, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9918, | |
| "eval_loss": 0.027753479778766632, | |
| "eval_model_preparation_time": 0.0036, | |
| "eval_runtime": 204.2755, | |
| "eval_samples_per_second": 48.954, | |
| "eval_steps_per_second": 6.119, | |
| "step": 626 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 626, | |
| "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": 1.67522104221696e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |