| { |
| "best_global_step": 3750, |
| "best_metric": 0.31374436616897583, |
| "best_model_checkpoint": "Fashion-Mnist-SigLIP2/checkpoint-3750", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 3750, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.26666666666666666, |
| "grad_norm": 9.494325637817383, |
| "learning_rate": 0.00018385650224215247, |
| "loss": 0.9674, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "grad_norm": 6.167793273925781, |
| "learning_rate": 0.00016591928251121076, |
| "loss": 0.6265, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 5.353821754455566, |
| "learning_rate": 0.00014798206278026908, |
| "loss": 0.5464, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8283, |
| "eval_loss": 0.46604594588279724, |
| "eval_model_preparation_time": 0.003, |
| "eval_runtime": 687.6086, |
| "eval_samples_per_second": 87.259, |
| "eval_steps_per_second": 10.907, |
| "step": 1875 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 3.131957530975342, |
| "learning_rate": 0.00013004484304932735, |
| "loss": 0.4901, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 3.037127733230591, |
| "learning_rate": 0.00011210762331838565, |
| "loss": 0.4272, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 2.186342716217041, |
| "learning_rate": 9.417040358744396e-05, |
| "loss": 0.3883, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.8666666666666667, |
| "grad_norm": 5.017179489135742, |
| "learning_rate": 7.623318385650225e-05, |
| "loss": 0.3628, |
| "step": 3500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8862833333333333, |
| "eval_loss": 0.31374436616897583, |
| "eval_model_preparation_time": 0.003, |
| "eval_runtime": 680.7322, |
| "eval_samples_per_second": 88.14, |
| "eval_steps_per_second": 11.018, |
| "step": 3750 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 5625, |
| "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": 1.005132625330176e+19, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
