| { |
| "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": 8.2829, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.09, |
| "eval_loss": 7.862854957580566, |
| "eval_runtime": 8.3401, |
| "eval_samples_per_second": 1057.901, |
| "eval_steps_per_second": 16.547, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.19, |
| "learning_rate": 4.452954048140044e-05, |
| "loss": 7.6392, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.19, |
| "eval_loss": 7.756640911102295, |
| "eval_runtime": 8.275, |
| "eval_samples_per_second": 1066.219, |
| "eval_steps_per_second": 16.677, |
| "step": 2000 |
| }, |
| { |
| "epoch": 3.28, |
| "learning_rate": 4.179431072210066e-05, |
| "loss": 7.4879, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.28, |
| "eval_loss": 7.715595245361328, |
| "eval_runtime": 8.2125, |
| "eval_samples_per_second": 1074.342, |
| "eval_steps_per_second": 16.804, |
| "step": 3000 |
| }, |
| { |
| "epoch": 4.38, |
| "learning_rate": 3.9059080962800876e-05, |
| "loss": 7.4085, |
| "step": 4000 |
| }, |
| { |
| "epoch": 4.38, |
| "eval_loss": 7.6904520988464355, |
| "eval_runtime": 8.2902, |
| "eval_samples_per_second": 1064.264, |
| "eval_steps_per_second": 16.646, |
| "step": 4000 |
| }, |
| { |
| "epoch": 5.47, |
| "learning_rate": 3.6323851203501094e-05, |
| "loss": 7.3528, |
| "step": 5000 |
| }, |
| { |
| "epoch": 5.47, |
| "eval_loss": 7.6683526039123535, |
| "eval_runtime": 8.2932, |
| "eval_samples_per_second": 1063.881, |
| "eval_steps_per_second": 16.64, |
| "step": 5000 |
| }, |
| { |
| "epoch": 6.56, |
| "learning_rate": 3.358862144420131e-05, |
| "loss": 7.3099, |
| "step": 6000 |
| }, |
| { |
| "epoch": 6.56, |
| "eval_loss": 7.6456756591796875, |
| "eval_runtime": 8.2108, |
| "eval_samples_per_second": 1074.565, |
| "eval_steps_per_second": 16.807, |
| "step": 6000 |
| }, |
| { |
| "epoch": 7.66, |
| "learning_rate": 3.085339168490153e-05, |
| "loss": 7.2768, |
| "step": 7000 |
| }, |
| { |
| "epoch": 7.66, |
| "eval_loss": 7.635733604431152, |
| "eval_runtime": 8.2718, |
| "eval_samples_per_second": 1066.63, |
| "eval_steps_per_second": 16.683, |
| "step": 7000 |
| }, |
| { |
| "epoch": 8.75, |
| "learning_rate": 2.811816192560175e-05, |
| "loss": 7.2502, |
| "step": 8000 |
| }, |
| { |
| "epoch": 8.75, |
| "eval_loss": 7.628890037536621, |
| "eval_runtime": 8.2137, |
| "eval_samples_per_second": 1074.176, |
| "eval_steps_per_second": 16.801, |
| "step": 8000 |
| }, |
| { |
| "epoch": 9.85, |
| "learning_rate": 2.538293216630197e-05, |
| "loss": 7.2288, |
| "step": 9000 |
| }, |
| { |
| "epoch": 9.85, |
| "eval_loss": 7.607583522796631, |
| "eval_runtime": 8.3598, |
| "eval_samples_per_second": 1055.408, |
| "eval_steps_per_second": 16.508, |
| "step": 9000 |
| }, |
| { |
| "epoch": 10.94, |
| "learning_rate": 2.264770240700219e-05, |
| "loss": 7.1375, |
| "step": 10000 |
| }, |
| { |
| "epoch": 10.94, |
| "eval_loss": 7.213150501251221, |
| "eval_runtime": 8.22, |
| "eval_samples_per_second": 1073.361, |
| "eval_steps_per_second": 16.788, |
| "step": 10000 |
| }, |
| { |
| "epoch": 12.04, |
| "learning_rate": 1.9912472647702408e-05, |
| "loss": 6.9675, |
| "step": 11000 |
| }, |
| { |
| "epoch": 12.04, |
| "eval_loss": 7.0395402908325195, |
| "eval_runtime": 8.2128, |
| "eval_samples_per_second": 1074.296, |
| "eval_steps_per_second": 16.803, |
| "step": 11000 |
| }, |
| { |
| "epoch": 13.13, |
| "learning_rate": 1.7177242888402626e-05, |
| "loss": 6.8891, |
| "step": 12000 |
| }, |
| { |
| "epoch": 13.13, |
| "eval_loss": 6.947587966918945, |
| "eval_runtime": 8.2276, |
| "eval_samples_per_second": 1072.371, |
| "eval_steps_per_second": 16.773, |
| "step": 12000 |
| }, |
| { |
| "epoch": 14.22, |
| "learning_rate": 1.4442013129102846e-05, |
| "loss": 6.8349, |
| "step": 13000 |
| }, |
| { |
| "epoch": 14.22, |
| "eval_loss": 6.882002353668213, |
| "eval_runtime": 8.216, |
| "eval_samples_per_second": 1073.882, |
| "eval_steps_per_second": 16.797, |
| "step": 13000 |
| }, |
| { |
| "epoch": 15.32, |
| "learning_rate": 1.1706783369803063e-05, |
| "loss": 6.7952, |
| "step": 14000 |
| }, |
| { |
| "epoch": 15.32, |
| "eval_loss": 6.837276458740234, |
| "eval_runtime": 8.2097, |
| "eval_samples_per_second": 1074.706, |
| "eval_steps_per_second": 16.809, |
| "step": 14000 |
| }, |
| { |
| "epoch": 16.41, |
| "learning_rate": 8.971553610503283e-06, |
| "loss": 6.7664, |
| "step": 15000 |
| }, |
| { |
| "epoch": 16.41, |
| "eval_loss": 6.805047512054443, |
| "eval_runtime": 8.2203, |
| "eval_samples_per_second": 1073.312, |
| "eval_steps_per_second": 16.788, |
| "step": 15000 |
| }, |
| { |
| "epoch": 17.51, |
| "learning_rate": 6.2363238512035015e-06, |
| "loss": 6.7444, |
| "step": 16000 |
| }, |
| { |
| "epoch": 17.51, |
| "eval_loss": 6.779191493988037, |
| "eval_runtime": 8.2441, |
| "eval_samples_per_second": 1070.226, |
| "eval_steps_per_second": 16.739, |
| "step": 16000 |
| }, |
| { |
| "epoch": 18.6, |
| "learning_rate": 3.50109409190372e-06, |
| "loss": 6.7268, |
| "step": 17000 |
| }, |
| { |
| "epoch": 18.6, |
| "eval_loss": 6.760980606079102, |
| "eval_runtime": 8.2098, |
| "eval_samples_per_second": 1074.685, |
| "eval_steps_per_second": 16.809, |
| "step": 17000 |
| }, |
| { |
| "epoch": 19.69, |
| "learning_rate": 7.658643326039388e-07, |
| "loss": 6.7164, |
| "step": 18000 |
| }, |
| { |
| "epoch": 19.69, |
| "eval_loss": 6.750948905944824, |
| "eval_runtime": 8.2106, |
| "eval_samples_per_second": 1074.59, |
| "eval_steps_per_second": 16.808, |
| "step": 18000 |
| } |
| ], |
| "max_steps": 18280, |
| "num_train_epochs": 20, |
| "total_flos": 7.308771564796416e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
