| { |
| "best_metric": 0.5165560626605169, |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-4276", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 6414, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.23, |
| "learning_rate": 2.2593712965969752e-05, |
| "loss": 0.6136, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 2.068352417953335e-05, |
| "loss": 0.5687, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 1.877333539309695e-05, |
| "loss": 0.5475, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 1.686314660666055e-05, |
| "loss": 0.5604, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.5529224276542664, |
| "eval_matthews_correlation": 0.4471137769925502, |
| "eval_runtime": 0.7648, |
| "eval_samples_per_second": 1363.699, |
| "eval_steps_per_second": 86.293, |
| "step": 2138 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 1.4952957820224147e-05, |
| "loss": 0.4684, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 1.3042769033787746e-05, |
| "loss": 0.4493, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 1.1132580247351345e-05, |
| "loss": 0.4875, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.87, |
| "learning_rate": 9.222391460914944e-06, |
| "loss": 0.4503, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.8003203272819519, |
| "eval_matthews_correlation": 0.5165560626605169, |
| "eval_runtime": 0.748, |
| "eval_samples_per_second": 1394.336, |
| "eval_steps_per_second": 88.232, |
| "step": 4276 |
| }, |
| { |
| "epoch": 2.1, |
| "learning_rate": 7.3122026744785425e-06, |
| "loss": 0.3587, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.34, |
| "learning_rate": 5.402013888042142e-06, |
| "loss": 0.279, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.57, |
| "learning_rate": 3.4918251016057417e-06, |
| "loss": 0.2666, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.81, |
| "learning_rate": 1.5816363151693402e-06, |
| "loss": 0.2792, |
| "step": 6000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.0243171453475952, |
| "eval_matthews_correlation": 0.4896234097252215, |
| "eval_runtime": 0.8044, |
| "eval_samples_per_second": 1296.561, |
| "eval_steps_per_second": 82.045, |
| "step": 6414 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 6414, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 97694965234188.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": { |
| "learning_rate": 2.4503901752406154e-05, |
| "num_train_epochs": 3, |
| "per_device_train_batch_size": 4, |
| "seed": 11 |
| } |
| } |
|
|
