| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.4, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04, |
| "learning_rate": 4.8e-05, |
| "loss": 2.3721, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 1.8562, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_loss": 1.995707631111145, |
| "eval_rouge2_fmeasure": 0.2129, |
| "eval_rouge2_precision": 0.2635, |
| "eval_rouge2_recall": 0.2168, |
| "eval_runtime": 3900.1086, |
| "eval_samples_per_second": 0.077, |
| "eval_steps_per_second": 0.038, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 2.1063, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 4.2e-05, |
| "loss": 1.8923, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_loss": 1.7682132720947266, |
| "eval_rouge2_fmeasure": 0.2466, |
| "eval_rouge2_precision": 0.2599, |
| "eval_rouge2_recall": 0.3043, |
| "eval_runtime": 7803.2087, |
| "eval_samples_per_second": 0.038, |
| "eval_steps_per_second": 0.019, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 4e-05, |
| "loss": 1.7652, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 3.8e-05, |
| "loss": 1.909, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.24, |
| "eval_loss": 1.7092610597610474, |
| "eval_rouge2_fmeasure": 0.2531, |
| "eval_rouge2_precision": 0.2638, |
| "eval_rouge2_recall": 0.3093, |
| "eval_runtime": 7685.9909, |
| "eval_samples_per_second": 0.039, |
| "eval_steps_per_second": 0.02, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 3.6e-05, |
| "loss": 1.686, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 3.4000000000000007e-05, |
| "loss": 1.6912, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_loss": 1.66864812374115, |
| "eval_rouge2_fmeasure": 0.2679, |
| "eval_rouge2_precision": 0.3245, |
| "eval_rouge2_recall": 0.2789, |
| "eval_runtime": 3975.5587, |
| "eval_samples_per_second": 0.075, |
| "eval_steps_per_second": 0.038, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 3.2000000000000005e-05, |
| "loss": 1.7482, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 3e-05, |
| "loss": 1.7148, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 1.6291550397872925, |
| "eval_rouge2_fmeasure": 0.267, |
| "eval_rouge2_precision": 0.3113, |
| "eval_rouge2_recall": 0.2944, |
| "eval_runtime": 5016.1567, |
| "eval_samples_per_second": 0.06, |
| "eval_steps_per_second": 0.03, |
| "step": 50 |
| } |
| ], |
| "max_steps": 125, |
| "num_train_epochs": 1, |
| "total_flos": 2160163867852800.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
