| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 40.0, | |
| "global_step": 13680, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 4.817251461988304e-05, | |
| "loss": 2.8952, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 4.634502923976608e-05, | |
| "loss": 2.0346, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 4.451754385964912e-05, | |
| "loss": 1.4152, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 4.269005847953216e-05, | |
| "loss": 1.009, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 4.086257309941521e-05, | |
| "loss": 0.6471, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 3.9035087719298244e-05, | |
| "loss": 0.4255, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 3.7207602339181284e-05, | |
| "loss": 0.2694, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 3.538011695906433e-05, | |
| "loss": 0.1837, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 3.355263157894737e-05, | |
| "loss": 0.1477, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 3.172514619883041e-05, | |
| "loss": 0.0993, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 16.08, | |
| "learning_rate": 2.989766081871345e-05, | |
| "loss": 0.0836, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 17.54, | |
| "learning_rate": 2.8070175438596492e-05, | |
| "loss": 0.0599, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 2.6242690058479535e-05, | |
| "loss": 0.0526, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 20.47, | |
| "learning_rate": 2.4415204678362576e-05, | |
| "loss": 0.0451, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 21.93, | |
| "learning_rate": 2.2587719298245616e-05, | |
| "loss": 0.038, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 23.39, | |
| "learning_rate": 2.0760233918128656e-05, | |
| "loss": 0.0299, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 24.85, | |
| "learning_rate": 1.8932748538011696e-05, | |
| "loss": 0.036, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 26.32, | |
| "learning_rate": 1.7105263157894737e-05, | |
| "loss": 0.0213, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 27.78, | |
| "learning_rate": 1.527777777777778e-05, | |
| "loss": 0.0195, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 29.24, | |
| "learning_rate": 1.3450292397660819e-05, | |
| "loss": 0.0168, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 30.7, | |
| "learning_rate": 1.162280701754386e-05, | |
| "loss": 0.0137, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 32.16, | |
| "learning_rate": 9.795321637426901e-06, | |
| "loss": 0.0132, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 33.63, | |
| "learning_rate": 7.967836257309943e-06, | |
| "loss": 0.0103, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 35.09, | |
| "learning_rate": 6.140350877192982e-06, | |
| "loss": 0.0085, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 36.55, | |
| "learning_rate": 4.312865497076023e-06, | |
| "loss": 0.0085, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 2.4853801169590643e-06, | |
| "loss": 0.0083, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 39.47, | |
| "learning_rate": 6.578947368421053e-07, | |
| "loss": 0.0072, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "step": 13680, | |
| "total_flos": 2.691983050788864e+16, | |
| "train_loss": 0.3509185360711918, | |
| "train_runtime": 12794.4297, | |
| "train_samples_per_second": 10.683, | |
| "train_steps_per_second": 1.069 | |
| } | |
| ], | |
| "max_steps": 13680, | |
| "num_train_epochs": 40, | |
| "total_flos": 2.691983050788864e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |