| { | |
| "best_global_step": 942, | |
| "best_metric": 0.40608102083206177, | |
| "best_model_checkpoint": "siglip2-finetune-full/checkpoint-942", | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 942, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7139154704944178, | |
| "eval_loss": 0.5481679439544678, | |
| "eval_model_preparation_time": 0.0027, | |
| "eval_runtime": 124.3671, | |
| "eval_samples_per_second": 40.332, | |
| "eval_steps_per_second": 5.042, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7567783094098883, | |
| "eval_loss": 0.48407095670700073, | |
| "eval_model_preparation_time": 0.0027, | |
| "eval_runtime": 124.5024, | |
| "eval_samples_per_second": 40.288, | |
| "eval_steps_per_second": 5.036, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.733652312599681, | |
| "eval_loss": 0.4816523790359497, | |
| "eval_model_preparation_time": 0.0027, | |
| "eval_runtime": 122.2853, | |
| "eval_samples_per_second": 41.019, | |
| "eval_steps_per_second": 5.127, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 3.1847133757961785, | |
| "grad_norm": 33.35067367553711, | |
| "learning_rate": 2.477578475336323e-06, | |
| "loss": 0.5312, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7651515151515151, | |
| "eval_loss": 0.4302399456501007, | |
| "eval_model_preparation_time": 0.0027, | |
| "eval_runtime": 123.8512, | |
| "eval_samples_per_second": 40.5, | |
| "eval_steps_per_second": 5.063, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7811004784688995, | |
| "eval_loss": 0.4116573631763458, | |
| "eval_model_preparation_time": 0.0027, | |
| "eval_runtime": 124.6627, | |
| "eval_samples_per_second": 40.237, | |
| "eval_steps_per_second": 5.03, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7830940988835726, | |
| "eval_loss": 0.40608102083206177, | |
| "eval_model_preparation_time": 0.0027, | |
| "eval_runtime": 126.8136, | |
| "eval_samples_per_second": 39.554, | |
| "eval_steps_per_second": 4.944, | |
| "step": 942 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 942, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "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": 2.520705402238206e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |