| { |
| "best_metric": 0.15625, |
| "best_model_checkpoint": "/kaggle/working/checkpoint-17", |
| "epoch": 1.4852941176470589, |
| "eval_steps": 500, |
| "global_step": 17, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.47058823529411764, |
| "eval_accuracy": 0.03125, |
| "eval_f1": 0.010416666666666666, |
| "eval_loss": 2.347832679748535, |
| "eval_precision": 0.00625, |
| "eval_recall": 0.03125, |
| "eval_runtime": 5.3844, |
| "eval_samples_per_second": 5.943, |
| "eval_steps_per_second": 1.486, |
| "eval_top_10_accuracy": 1.0, |
| "eval_top_1_accuracy": 0.03125, |
| "eval_top_5_accuracy": 0.46875, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.4852941176470589, |
| "eval_accuracy": 0.15625, |
| "eval_f1": 0.09895833333333333, |
| "eval_loss": 2.3559300899505615, |
| "eval_precision": 0.13671875, |
| "eval_recall": 0.15625, |
| "eval_runtime": 5.5018, |
| "eval_samples_per_second": 5.816, |
| "eval_steps_per_second": 1.454, |
| "eval_top_10_accuracy": 1.0, |
| "eval_top_1_accuracy": 0.15625, |
| "eval_top_5_accuracy": 0.5, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.4852941176470589, |
| "step": 17, |
| "total_flos": 3.3895374930837504e+17, |
| "train_loss": 2.3516208424287686, |
| "train_runtime": 111.1739, |
| "train_samples_per_second": 2.447, |
| "train_steps_per_second": 0.153 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 17, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 20, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.3895374930837504e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
