| { | |
| "best_global_step": 1250, | |
| "best_metric": 0.13630688190460205, | |
| "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": 16.568904876708984, | |
| "learning_rate": 6.249999999999999e-07, | |
| "loss": 0.3408, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9169958497924896, | |
| "eval_loss": 0.1934153288602829, | |
| "eval_model_preparation_time": 0.0027, | |
| "eval_runtime": 479.9201, | |
| "eval_samples_per_second": 41.672, | |
| "eval_steps_per_second": 5.209, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 26.358617782592773, | |
| "learning_rate": 2.0833333333333333e-07, | |
| "loss": 0.1463, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9444472223611181, | |
| "eval_loss": 0.13630688190460205, | |
| "eval_model_preparation_time": 0.0027, | |
| "eval_runtime": 480.8571, | |
| "eval_samples_per_second": 41.59, | |
| "eval_steps_per_second": 5.199, | |
| "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": 3.3500523218608374e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |