| { | |
| "best_global_step": 1250, | |
| "best_metric": 0.1083846390247345, | |
| "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1250", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.0611472129821777, | |
| "learning_rate": 0.000125, | |
| "loss": 0.3823, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9238423842384238, | |
| "eval_loss": 0.21214079856872559, | |
| "eval_model_preparation_time": 0.0022, | |
| "eval_runtime": 258.6139, | |
| "eval_samples_per_second": 77.328, | |
| "eval_steps_per_second": 9.667, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 16.998748779296875, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.2123, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9609460946094609, | |
| "eval_loss": 0.1083846390247345, | |
| "eval_model_preparation_time": 0.0022, | |
| "eval_runtime": 260.9561, | |
| "eval_samples_per_second": 76.634, | |
| "eval_steps_per_second": 9.58, | |
| "step": 1250 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1250, | |
| "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": 3.349884810869195e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |