| { | |
| "best_global_step": 1494, | |
| "best_metric": 0.1536320447921753, | |
| "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1494", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1494, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.6693440428380187, | |
| "grad_norm": 38.35798263549805, | |
| "learning_rate": 2.5405037440435672e-06, | |
| "loss": 1.3068, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.939136262723579, | |
| "eval_loss": 0.28792640566825867, | |
| "eval_model_preparation_time": 0.0024, | |
| "eval_runtime": 460.2975, | |
| "eval_samples_per_second": 51.864, | |
| "eval_steps_per_second": 12.968, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 1.3386880856760375, | |
| "grad_norm": 27.482799530029297, | |
| "learning_rate": 2.029952348536419e-06, | |
| "loss": 0.311, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9621748418715704, | |
| "eval_loss": 0.1536320447921753, | |
| "eval_model_preparation_time": 0.0024, | |
| "eval_runtime": 461.078, | |
| "eval_samples_per_second": 51.776, | |
| "eval_steps_per_second": 12.946, | |
| "step": 1494 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2988, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 4.000051065885106e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |