| { | |
| "best_global_step": 1566, | |
| "best_metric": 0.33024775981903076, | |
| "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1566", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1566, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.31928480204342274, | |
| "grad_norm": 5.945098876953125, | |
| "learning_rate": 0.00035158311345646437, | |
| "loss": 2.9737, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6385696040868455, | |
| "grad_norm": 6.650278091430664, | |
| "learning_rate": 0.0001866754617414248, | |
| "loss": 1.602, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9578544061302682, | |
| "grad_norm": 4.597949504852295, | |
| "learning_rate": 2.1767810026385228e-05, | |
| "loss": 0.5841, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9026727080380846, | |
| "eval_loss": 0.33024775981903076, | |
| "eval_model_preparation_time": 0.0023, | |
| "eval_runtime": 620.5266, | |
| "eval_samples_per_second": 80.736, | |
| "eval_steps_per_second": 10.093, | |
| "step": 1566 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1566, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 4.197493203467913e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |