| { | |
| "best_metric": 0.7679266259032796, | |
| "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-0\\checkpoint-985", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 985, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.505784710419649e-06, | |
| "loss": 0.6127, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7258198999444135, | |
| "eval_loss": 0.5620561838150024, | |
| "eval_runtime": 127.1936, | |
| "eval_samples_per_second": 56.575, | |
| "eval_steps_per_second": 0.448, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.004627768335719e-06, | |
| "loss": 0.5562, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7523624235686492, | |
| "eval_loss": 0.5172325372695923, | |
| "eval_runtime": 127.1167, | |
| "eval_samples_per_second": 56.609, | |
| "eval_steps_per_second": 0.448, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.5034708262517894e-06, | |
| "loss": 0.5297, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7601445247359644, | |
| "eval_loss": 0.49815818667411804, | |
| "eval_runtime": 127.1505, | |
| "eval_samples_per_second": 56.594, | |
| "eval_steps_per_second": 0.448, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.0023138841678596e-06, | |
| "loss": 0.5189, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7659811006114509, | |
| "eval_loss": 0.488542765378952, | |
| "eval_runtime": 127.0937, | |
| "eval_samples_per_second": 56.62, | |
| "eval_steps_per_second": 0.448, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.011569420839298e-07, | |
| "loss": 0.5117, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7679266259032796, | |
| "eval_loss": 0.4839724898338318, | |
| "eval_runtime": 127.1766, | |
| "eval_samples_per_second": 56.583, | |
| "eval_steps_per_second": 0.448, | |
| "step": 985 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1182, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "total_flos": 221342066021952.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.9772734766942756, | |
| "learning_rate": 3.0069416525035787e-06, | |
| "num_train_epochs": 6, | |
| "temperature": 16 | |
| } | |
| } | |