| { | |
| "best_metric": 0.3621212121212121, | |
| "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-2\\checkpoint-55", | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 385, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.5441792724155395e-05, | |
| "loss": 0.036, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.3621212121212121, | |
| "eval_loss": 0.035133831202983856, | |
| "eval_runtime": 3.3771, | |
| "eval_samples_per_second": 586.31, | |
| "eval_steps_per_second": 4.738, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.286816060346283e-05, | |
| "loss": 0.0354, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.3621212121212121, | |
| "eval_loss": 0.0350903756916523, | |
| "eval_runtime": 3.3705, | |
| "eval_samples_per_second": 587.442, | |
| "eval_steps_per_second": 4.747, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.0294528482770263e-05, | |
| "loss": 0.0353, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3621212121212121, | |
| "eval_loss": 0.03502834588289261, | |
| "eval_runtime": 3.355, | |
| "eval_samples_per_second": 590.167, | |
| "eval_steps_per_second": 4.769, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 7.720896362077698e-06, | |
| "loss": 0.0353, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3621212121212121, | |
| "eval_loss": 0.035031162202358246, | |
| "eval_runtime": 3.3196, | |
| "eval_samples_per_second": 596.459, | |
| "eval_steps_per_second": 4.82, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.1472642413851315e-06, | |
| "loss": 0.0352, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.3621212121212121, | |
| "eval_loss": 0.03497819975018501, | |
| "eval_runtime": 3.3426, | |
| "eval_samples_per_second": 592.36, | |
| "eval_steps_per_second": 4.787, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 2.5736321206925658e-06, | |
| "loss": 0.0352, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.3621212121212121, | |
| "eval_loss": 0.03496537730097771, | |
| "eval_runtime": 3.3354, | |
| "eval_samples_per_second": 593.638, | |
| "eval_steps_per_second": 4.797, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0353, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.3621212121212121, | |
| "eval_loss": 0.034974899142980576, | |
| "eval_runtime": 3.3525, | |
| "eval_samples_per_second": 590.606, | |
| "eval_steps_per_second": 4.773, | |
| "step": 385 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 385, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "total_flos": 5884067175000.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.04724864888100444, | |
| "learning_rate": 1.801542484484796e-05, | |
| "num_train_epochs": 7, | |
| "temperature": 8 | |
| } | |
| } | |