| { |
| "best_metric": 0.5597109794616699, |
| "best_model_checkpoint": "/tmp/model/checkpoint-2000", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 0.6258, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.541, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 2.5e-05, |
| "loss": 0.5089, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.5764, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 0.594, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 5e-05, |
| "loss": 0.5734, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 4.9074074074074075e-05, |
| "loss": 0.5597, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 4.814814814814815e-05, |
| "loss": 0.6287, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 4.722222222222222e-05, |
| "loss": 0.5691, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 4.62962962962963e-05, |
| "loss": 0.5908, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 4.5370370370370374e-05, |
| "loss": 0.5939, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 4.4444444444444447e-05, |
| "loss": 0.5421, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 4.351851851851852e-05, |
| "loss": 0.579, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 4.259259259259259e-05, |
| "loss": 0.5718, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 0.5933, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 4.074074074074074e-05, |
| "loss": 0.5588, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 3.981481481481482e-05, |
| "loss": 0.5778, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 3.888888888888889e-05, |
| "loss": 0.5536, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 3.7962962962962964e-05, |
| "loss": 0.5748, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 3.7037037037037037e-05, |
| "loss": 0.5504, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7525, |
| "eval_auc": 0.3925796167656633, |
| "eval_f1": 0.0, |
| "eval_loss": 0.5597109794616699, |
| "eval_precision": 0.0, |
| "eval_recall": 0.0, |
| "eval_runtime": 3049.9931, |
| "eval_samples_per_second": 1.311, |
| "eval_steps_per_second": 0.082, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 6000, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 3727725453312000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
