| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.0, |
| "global_step": 2475, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 3e-05, |
| "loss": 1.8887, |
| "step": 275 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 52.092806342544016, |
| "eval_f1": 61.062173113283656, |
| "eval_runtime": 3.5591, |
| "eval_samples_per_second": 2409.9, |
| "eval_steps_per_second": 7.586, |
| "step": 275 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 1.0166, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 51.544829194357, |
| "eval_f1": 61.20871417240919, |
| "eval_runtime": 3.0486, |
| "eval_samples_per_second": 2813.392, |
| "eval_steps_per_second": 8.856, |
| "step": 550 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3e-05, |
| "loss": 0.8084, |
| "step": 825 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_exact_match": 52.745715285064705, |
| "eval_f1": 61.686663146219274, |
| "eval_runtime": 3.0412, |
| "eval_samples_per_second": 2820.232, |
| "eval_steps_per_second": 8.878, |
| "step": 825 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 3e-05, |
| "loss": 0.661, |
| "step": 1100 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_exact_match": 52.302669931211376, |
| "eval_f1": 61.55649613642499, |
| "eval_runtime": 3.0099, |
| "eval_samples_per_second": 2849.557, |
| "eval_steps_per_second": 8.97, |
| "step": 1100 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 3e-05, |
| "loss": 0.5426, |
| "step": 1375 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_exact_match": 52.209397225136996, |
| "eval_f1": 61.19204443173771, |
| "eval_runtime": 3.0395, |
| "eval_samples_per_second": 2821.812, |
| "eval_steps_per_second": 8.883, |
| "step": 1375 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4487, |
| "step": 1650 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_exact_match": 54.10982861140259, |
| "eval_f1": 62.138631414166056, |
| "eval_runtime": 3.0046, |
| "eval_samples_per_second": 2854.628, |
| "eval_steps_per_second": 8.986, |
| "step": 1650 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 3e-05, |
| "loss": 0.3729, |
| "step": 1925 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_exact_match": 54.28471493529206, |
| "eval_f1": 62.01717049776823, |
| "eval_runtime": 2.9983, |
| "eval_samples_per_second": 2860.629, |
| "eval_steps_per_second": 9.005, |
| "step": 1925 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 3e-05, |
| "loss": 0.3054, |
| "step": 2200 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_exact_match": 53.65512416928996, |
| "eval_f1": 61.57642196405224, |
| "eval_runtime": 3.0344, |
| "eval_samples_per_second": 2826.588, |
| "eval_steps_per_second": 8.898, |
| "step": 2200 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 3e-05, |
| "loss": 0.2554, |
| "step": 2475 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_exact_match": 55.2640783490731, |
| "eval_f1": 62.4332153138502, |
| "eval_runtime": 3.0011, |
| "eval_samples_per_second": 2857.957, |
| "eval_steps_per_second": 8.997, |
| "step": 2475 |
| } |
| ], |
| "max_steps": 2750, |
| "num_train_epochs": 10, |
| "total_flos": 298038669082624.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
