| { | |
| "best_global_step": 1548, | |
| "best_metric": 0.028825150802731514, | |
| "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1548", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1548, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.6459948320413437, | |
| "grad_norm": 1.310089111328125, | |
| "learning_rate": 0.00013991989319092122, | |
| "loss": 0.5537, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9111407443326464, | |
| "eval_loss": 0.28554126620292664, | |
| "eval_model_preparation_time": 0.0022, | |
| "eval_runtime": 320.8872, | |
| "eval_samples_per_second": 77.121, | |
| "eval_steps_per_second": 9.642, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 1.2919896640826873, | |
| "grad_norm": 1.1912801265716553, | |
| "learning_rate": 7.316421895861149e-05, | |
| "loss": 0.1901, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.937984496124031, | |
| "grad_norm": 2.1367239952087402, | |
| "learning_rate": 6.408544726301736e-06, | |
| "loss": 0.0761, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9912312603547905, | |
| "eval_loss": 0.028825150802731514, | |
| "eval_model_preparation_time": 0.0022, | |
| "eval_runtime": 319.9983, | |
| "eval_samples_per_second": 77.335, | |
| "eval_steps_per_second": 9.669, | |
| "step": 1548 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1548, | |
| "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": 4.1455663870514504e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |