| { |
| "best_global_step": 496, |
| "best_metric": 0.4644159972667694, |
| "best_model_checkpoint": "/kaggle/working/timesformer-merl-weighted-loss/checkpoint-496", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 496, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 47094.69921875, |
| "learning_rate": 2.6693548387096773e-05, |
| "loss": 0.8913, |
| "step": 248 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8913813459268005, |
| "eval_loss": 0.4863474369049072, |
| "eval_runtime": 424.1926, |
| "eval_samples_per_second": 1.997, |
| "eval_steps_per_second": 0.5, |
| "step": 248 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 113207.671875, |
| "learning_rate": 2.002688172043011e-05, |
| "loss": 0.3051, |
| "step": 496 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.911452184179457, |
| "eval_loss": 0.4644159972667694, |
| "eval_runtime": 427.0729, |
| "eval_samples_per_second": 1.983, |
| "eval_steps_per_second": 0.496, |
| "step": 496 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1240, |
| "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": 9.85173806856418e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
