| { |
| "best_global_step": 1392, |
| "best_metric": 0.7880541086196899, |
| "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1392", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 1392, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6359832635983264, |
| "eval_loss": 2.0701308250427246, |
| "eval_model_preparation_time": 0.0031, |
| "eval_runtime": 215.6864, |
| "eval_samples_per_second": 68.702, |
| "eval_steps_per_second": 8.591, |
| "step": 464 |
| }, |
| { |
| "epoch": 1.0775862068965518, |
| "grad_norm": 49.15087890625, |
| "learning_rate": 2.4052863436123347e-06, |
| "loss": 3.5107, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8090160615467674, |
| "eval_loss": 1.0770337581634521, |
| "eval_model_preparation_time": 0.0031, |
| "eval_runtime": 213.0035, |
| "eval_samples_per_second": 69.567, |
| "eval_steps_per_second": 8.699, |
| "step": 928 |
| }, |
| { |
| "epoch": 2.1551724137931036, |
| "grad_norm": 57.83103561401367, |
| "learning_rate": 1.7444933920704845e-06, |
| "loss": 1.3776, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8484275880685652, |
| "eval_loss": 0.7880541086196899, |
| "eval_model_preparation_time": 0.0031, |
| "eval_runtime": 213.1605, |
| "eval_samples_per_second": 69.516, |
| "eval_steps_per_second": 8.693, |
| "step": 1392 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2320, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 3.7270953003136205e+18, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
