| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 19.693464588460486, |
| "global_step": 18000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.09, |
| "learning_rate": 4.726477024070022e-05, |
| "loss": 9.1433, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.09, |
| "eval_loss": 8.796442985534668, |
| "eval_runtime": 3.8329, |
| "eval_samples_per_second": 2301.909, |
| "eval_steps_per_second": 36.004, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.19, |
| "learning_rate": 4.452954048140044e-05, |
| "loss": 8.6087, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.19, |
| "eval_loss": 8.433659553527832, |
| "eval_runtime": 3.759, |
| "eval_samples_per_second": 2347.193, |
| "eval_steps_per_second": 36.712, |
| "step": 2000 |
| }, |
| { |
| "epoch": 3.28, |
| "learning_rate": 4.179431072210066e-05, |
| "loss": 8.279, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.28, |
| "eval_loss": 8.201327323913574, |
| "eval_runtime": 3.7567, |
| "eval_samples_per_second": 2348.629, |
| "eval_steps_per_second": 36.735, |
| "step": 3000 |
| }, |
| { |
| "epoch": 4.38, |
| "learning_rate": 3.9059080962800876e-05, |
| "loss": 8.0793, |
| "step": 4000 |
| }, |
| { |
| "epoch": 4.38, |
| "eval_loss": 8.072661399841309, |
| "eval_runtime": 3.7318, |
| "eval_samples_per_second": 2364.306, |
| "eval_steps_per_second": 36.98, |
| "step": 4000 |
| }, |
| { |
| "epoch": 5.47, |
| "learning_rate": 3.6323851203501094e-05, |
| "loss": 7.9475, |
| "step": 5000 |
| }, |
| { |
| "epoch": 5.47, |
| "eval_loss": 7.999021530151367, |
| "eval_runtime": 3.764, |
| "eval_samples_per_second": 2344.05, |
| "eval_steps_per_second": 36.663, |
| "step": 5000 |
| }, |
| { |
| "epoch": 6.56, |
| "learning_rate": 3.358862144420131e-05, |
| "loss": 7.8577, |
| "step": 6000 |
| }, |
| { |
| "epoch": 6.56, |
| "eval_loss": 7.939911365509033, |
| "eval_runtime": 3.6792, |
| "eval_samples_per_second": 2398.058, |
| "eval_steps_per_second": 37.508, |
| "step": 6000 |
| }, |
| { |
| "epoch": 7.66, |
| "learning_rate": 3.085339168490153e-05, |
| "loss": 7.7935, |
| "step": 7000 |
| }, |
| { |
| "epoch": 7.66, |
| "eval_loss": 7.911438941955566, |
| "eval_runtime": 3.6878, |
| "eval_samples_per_second": 2392.511, |
| "eval_steps_per_second": 37.421, |
| "step": 7000 |
| }, |
| { |
| "epoch": 8.75, |
| "learning_rate": 2.811816192560175e-05, |
| "loss": 7.7466, |
| "step": 8000 |
| }, |
| { |
| "epoch": 8.75, |
| "eval_loss": 7.892585277557373, |
| "eval_runtime": 3.7467, |
| "eval_samples_per_second": 2354.877, |
| "eval_steps_per_second": 36.832, |
| "step": 8000 |
| }, |
| { |
| "epoch": 9.85, |
| "learning_rate": 2.538293216630197e-05, |
| "loss": 7.7115, |
| "step": 9000 |
| }, |
| { |
| "epoch": 9.85, |
| "eval_loss": 7.864039421081543, |
| "eval_runtime": 3.6874, |
| "eval_samples_per_second": 2392.746, |
| "eval_steps_per_second": 37.425, |
| "step": 9000 |
| }, |
| { |
| "epoch": 10.94, |
| "learning_rate": 2.264770240700219e-05, |
| "loss": 7.6821, |
| "step": 10000 |
| }, |
| { |
| "epoch": 10.94, |
| "eval_loss": 7.849886417388916, |
| "eval_runtime": 3.6752, |
| "eval_samples_per_second": 2400.679, |
| "eval_steps_per_second": 37.549, |
| "step": 10000 |
| }, |
| { |
| "epoch": 12.04, |
| "learning_rate": 1.9912472647702408e-05, |
| "loss": 7.6611, |
| "step": 11000 |
| }, |
| { |
| "epoch": 12.04, |
| "eval_loss": 7.837656021118164, |
| "eval_runtime": 3.6572, |
| "eval_samples_per_second": 2412.526, |
| "eval_steps_per_second": 37.734, |
| "step": 11000 |
| }, |
| { |
| "epoch": 13.13, |
| "learning_rate": 1.7177242888402626e-05, |
| "loss": 7.64, |
| "step": 12000 |
| }, |
| { |
| "epoch": 13.13, |
| "eval_loss": 7.833044528961182, |
| "eval_runtime": 3.7781, |
| "eval_samples_per_second": 2335.296, |
| "eval_steps_per_second": 36.526, |
| "step": 12000 |
| }, |
| { |
| "epoch": 14.22, |
| "learning_rate": 1.4442013129102846e-05, |
| "loss": 7.6245, |
| "step": 13000 |
| }, |
| { |
| "epoch": 14.22, |
| "eval_loss": 7.824341297149658, |
| "eval_runtime": 3.6826, |
| "eval_samples_per_second": 2395.856, |
| "eval_steps_per_second": 37.473, |
| "step": 13000 |
| }, |
| { |
| "epoch": 15.32, |
| "learning_rate": 1.1706783369803063e-05, |
| "loss": 7.6114, |
| "step": 14000 |
| }, |
| { |
| "epoch": 15.32, |
| "eval_loss": 7.818795680999756, |
| "eval_runtime": 3.7376, |
| "eval_samples_per_second": 2360.637, |
| "eval_steps_per_second": 36.923, |
| "step": 14000 |
| }, |
| { |
| "epoch": 16.41, |
| "learning_rate": 8.971553610503283e-06, |
| "loss": 7.6037, |
| "step": 15000 |
| }, |
| { |
| "epoch": 16.41, |
| "eval_loss": 7.814483642578125, |
| "eval_runtime": 3.7397, |
| "eval_samples_per_second": 2359.276, |
| "eval_steps_per_second": 36.901, |
| "step": 15000 |
| }, |
| { |
| "epoch": 17.51, |
| "learning_rate": 6.2363238512035015e-06, |
| "loss": 7.5976, |
| "step": 16000 |
| }, |
| { |
| "epoch": 17.51, |
| "eval_loss": 7.810541152954102, |
| "eval_runtime": 3.6527, |
| "eval_samples_per_second": 2415.442, |
| "eval_steps_per_second": 37.78, |
| "step": 16000 |
| }, |
| { |
| "epoch": 18.6, |
| "learning_rate": 3.50109409190372e-06, |
| "loss": 7.5917, |
| "step": 17000 |
| }, |
| { |
| "epoch": 18.6, |
| "eval_loss": 7.808047771453857, |
| "eval_runtime": 3.6988, |
| "eval_samples_per_second": 2385.398, |
| "eval_steps_per_second": 37.31, |
| "step": 17000 |
| }, |
| { |
| "epoch": 19.69, |
| "learning_rate": 7.658643326039388e-07, |
| "loss": 7.589, |
| "step": 18000 |
| }, |
| { |
| "epoch": 19.69, |
| "eval_loss": 7.805490493774414, |
| "eval_runtime": 3.6528, |
| "eval_samples_per_second": 2415.393, |
| "eval_steps_per_second": 37.779, |
| "step": 18000 |
| } |
| ], |
| "max_steps": 18280, |
| "num_train_epochs": 20, |
| "total_flos": 2.5151586400512e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
