| { | |
| "best_metric": 0.7488882712618121, | |
| "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-2\\checkpoint-591", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 591, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6784454644765522e-06, | |
| "loss": 0.564, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6989994441356309, | |
| "eval_loss": 0.5322139859199524, | |
| "eval_runtime": 125.0015, | |
| "eval_samples_per_second": 57.567, | |
| "eval_steps_per_second": 0.456, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.258834098357414e-06, | |
| "loss": 0.5261, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7388827126181212, | |
| "eval_loss": 0.496852844953537, | |
| "eval_runtime": 124.8189, | |
| "eval_samples_per_second": 57.652, | |
| "eval_steps_per_second": 0.457, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.392227322382761e-07, | |
| "loss": 0.5052, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7488882712618121, | |
| "eval_loss": 0.48156076669692993, | |
| "eval_runtime": 124.658, | |
| "eval_samples_per_second": 57.726, | |
| "eval_steps_per_second": 0.457, | |
| "step": 591 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 985, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 133009215775884.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.8786599620319323, | |
| "learning_rate": 2.09805683059569e-06, | |
| "num_train_epochs": 5, | |
| "temperature": 9 | |
| } | |
| } | |