| { | |
| "best_global_step": 1574, | |
| "best_metric": 1.3910918235778809, | |
| "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1574", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1574, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.6353240152477764, | |
| "grad_norm": 46.04074478149414, | |
| "learning_rate": 4.0263954997836435e-06, | |
| "loss": 2.9627, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5230524642289348, | |
| "eval_loss": 1.8255969285964966, | |
| "eval_model_preparation_time": 0.0023, | |
| "eval_runtime": 558.5967, | |
| "eval_samples_per_second": 45.041, | |
| "eval_steps_per_second": 5.63, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 1.2706480304955527, | |
| "grad_norm": 61.133846282958984, | |
| "learning_rate": 2.9446127217654696e-06, | |
| "loss": 1.9954, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.9059720457433291, | |
| "grad_norm": 61.12163162231445, | |
| "learning_rate": 1.8628299437472957e-06, | |
| "loss": 1.6743, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.622456279809221, | |
| "eval_loss": 1.3910918235778809, | |
| "eval_model_preparation_time": 0.0023, | |
| "eval_runtime": 558.2588, | |
| "eval_samples_per_second": 45.069, | |
| "eval_steps_per_second": 5.634, | |
| "step": 1574 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2361, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.216428849971036e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |