Spaces:
Sleeping
Sleeping
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.649122807017545, | |
| "eval_steps": 500, | |
| "global_step": 16500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002912280701754386, | |
| "loss": 0.3858, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002824561403508772, | |
| "loss": 0.0819, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00027368421052631573, | |
| "loss": 0.046, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.006535602733492851, | |
| "eval_rouge1": 0.9974420190995907, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.9974420190995907, | |
| "eval_rougeLsum": 0.9974420190995907, | |
| "eval_runtime": 155.5569, | |
| "eval_samples_per_second": 37.697, | |
| "eval_steps_per_second": 9.424, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0002649122807017544, | |
| "loss": 0.0317, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00025614035087719294, | |
| "loss": 0.0132, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00024736842105263154, | |
| "loss": 0.0103, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.00893484242260456, | |
| "eval_rouge1": 0.997612551159618, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.997612551159618, | |
| "eval_rougeLsum": 0.997612551159618, | |
| "eval_runtime": 159.0943, | |
| "eval_samples_per_second": 36.859, | |
| "eval_steps_per_second": 9.215, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.00023859649122807015, | |
| "loss": 0.015, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.00022982456140350875, | |
| "loss": 0.0078, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.00022105263157894733, | |
| "loss": 0.0075, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.00021228070175438596, | |
| "loss": 0.0105, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.002929441863670945, | |
| "eval_rouge1": 0.9982946793997272, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.9982946793997272, | |
| "eval_rougeLsum": 0.9982946793997272, | |
| "eval_runtime": 155.9353, | |
| "eval_samples_per_second": 37.605, | |
| "eval_steps_per_second": 9.401, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 0.00020350877192982454, | |
| "loss": 0.0159, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 0.00019473684210526314, | |
| "loss": 0.0121, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 0.00018596491228070172, | |
| "loss": 0.0105, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.0014885533601045609, | |
| "eval_rouge1": 0.9986357435197817, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.9986357435197817, | |
| "eval_rougeLsum": 0.9986357435197817, | |
| "eval_runtime": 159.1866, | |
| "eval_samples_per_second": 36.837, | |
| "eval_steps_per_second": 9.209, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.00017719298245614035, | |
| "loss": 0.0136, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 0.00016842105263157892, | |
| "loss": 0.0067, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.00015964912280701753, | |
| "loss": 0.0052, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 0.00015087719298245613, | |
| "loss": 0.0032, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.002013931516557932, | |
| "eval_rouge1": 0.9982946793997272, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.9982946793997272, | |
| "eval_rougeLsum": 0.9982946793997272, | |
| "eval_runtime": 158.9827, | |
| "eval_samples_per_second": 36.885, | |
| "eval_steps_per_second": 9.221, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 0.0001421052631578947, | |
| "loss": 0.0036, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 0.0001333333333333333, | |
| "loss": 0.0028, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 0.00012456140350877192, | |
| "loss": 0.0023, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.008263664320111275, | |
| "eval_rouge1": 0.997612551159618, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.997612551159618, | |
| "eval_rougeLsum": 0.997612551159618, | |
| "eval_runtime": 165.6672, | |
| "eval_samples_per_second": 35.396, | |
| "eval_steps_per_second": 8.849, | |
| "step": 10260 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 0.00011578947368421051, | |
| "loss": 0.0045, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 0.00010701754385964911, | |
| "loss": 0.0031, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 9.82456140350877e-05, | |
| "loss": 0.0013, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.003634733846411109, | |
| "eval_rouge1": 0.9982946793997272, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.9982946793997272, | |
| "eval_rougeLsum": 0.9982946793997272, | |
| "eval_runtime": 165.5178, | |
| "eval_samples_per_second": 35.428, | |
| "eval_steps_per_second": 8.857, | |
| "step": 11970 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 8.94736842105263e-05, | |
| "loss": 0.0017, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 8.07017543859649e-05, | |
| "loss": 0.0008, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 7.19298245614035e-05, | |
| "loss": 0.0017, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 6.315789473684209e-05, | |
| "loss": 0.0012, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.0013940236531198025, | |
| "eval_rouge1": 0.9982946793997272, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.9982946793997272, | |
| "eval_rougeLsum": 0.9982946793997272, | |
| "eval_runtime": 166.5345, | |
| "eval_samples_per_second": 35.212, | |
| "eval_steps_per_second": 8.803, | |
| "step": 13680 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 5.4385964912280694e-05, | |
| "loss": 0.0024, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 4.561403508771929e-05, | |
| "loss": 0.0015, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 3.684210526315789e-05, | |
| "loss": 0.0012, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.0021317724604159594, | |
| "eval_rouge1": 0.9982946793997272, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.9982946793997272, | |
| "eval_rougeLsum": 0.9982946793997272, | |
| "eval_runtime": 166.3607, | |
| "eval_samples_per_second": 35.249, | |
| "eval_steps_per_second": 8.812, | |
| "step": 15390 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 2.807017543859649e-05, | |
| "loss": 0.0008, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 1.9298245614035086e-05, | |
| "loss": 0.0004, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 1.0526315789473683e-05, | |
| "loss": 0.0006, | |
| "step": 16500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 17100, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 4237085908942848.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |