--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: Finetune_Pegasus_2 results: [] --- # Finetune_Pegasus_2 This model is a fine-tuned version of [Gayathri142214002/Finetune_Pegasus_1](https://huggingface.co/Gayathri142214002/Finetune_Pegasus_1) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2891 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 7 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 0.5877 | 0.09 | 10 | 0.4730 | | 0.4521 | 0.19 | 20 | 0.4180 | | 0.5412 | 0.28 | 30 | 0.3851 | | 0.3669 | 0.37 | 40 | 0.3635 | | 0.3732 | 0.47 | 50 | 0.3396 | | 0.3724 | 0.56 | 60 | 0.3555 | | 0.3693 | 0.65 | 70 | 0.3412 | | 0.3476 | 0.75 | 80 | 0.3060 | | 0.3288 | 0.84 | 90 | 0.3009 | | 0.3439 | 0.93 | 100 | 0.3344 | | 0.2644 | 1.03 | 110 | 0.3283 | | 0.2926 | 1.12 | 120 | 0.3101 | | 0.2615 | 1.21 | 130 | 0.3189 | | 0.3004 | 1.31 | 140 | 0.3085 | | 0.3202 | 1.4 | 150 | 0.3148 | | 0.2989 | 1.49 | 160 | 0.3062 | | 0.3326 | 1.59 | 170 | 0.3055 | | 0.3101 | 1.68 | 180 | 0.2886 | | 0.3011 | 1.77 | 190 | 0.2896 | | 0.2795 | 1.86 | 200 | 0.2901 | | 0.2759 | 1.96 | 210 | 0.3092 | | 0.2883 | 2.05 | 220 | 0.2948 | | 0.2566 | 2.14 | 230 | 0.2760 | | 0.222 | 2.24 | 240 | 0.2802 | | 0.2667 | 2.33 | 250 | 0.2733 | | 0.262 | 2.42 | 260 | 0.2928 | | 0.2784 | 2.52 | 270 | 0.3061 | | 0.2832 | 2.61 | 280 | 0.3079 | | 0.2885 | 2.7 | 290 | 0.3160 | | 0.275 | 2.8 | 300 | 0.3111 | | 0.3059 | 2.89 | 310 | 0.2992 | | 0.2604 | 2.98 | 320 | 0.2923 | | 0.2425 | 3.08 | 330 | 0.2991 | | 0.2225 | 3.17 | 340 | 0.2988 | | 0.2548 | 3.26 | 350 | 0.3124 | | 0.2393 | 3.36 | 360 | 0.3009 | | 0.2383 | 3.45 | 370 | 0.2846 | | 0.2251 | 3.54 | 380 | 0.2871 | | 0.253 | 3.64 | 390 | 0.2875 | | 0.2615 | 3.73 | 400 | 0.2829 | | 0.238 | 3.82 | 410 | 0.2815 | | 0.2685 | 3.92 | 420 | 0.2892 | | 0.2532 | 4.01 | 430 | 0.2906 | | 0.2105 | 4.1 | 440 | 0.2851 | | 0.2382 | 4.2 | 450 | 0.2823 | | 0.2316 | 4.29 | 460 | 0.2777 | | 0.2565 | 4.38 | 470 | 0.2816 | | 0.2216 | 4.48 | 480 | 0.2869 | | 0.2477 | 4.57 | 490 | 0.2968 | | 0.2223 | 4.66 | 500 | 0.3006 | | 0.2445 | 4.76 | 510 | 0.3035 | | 0.2383 | 4.85 | 520 | 0.2985 | | 0.2482 | 4.94 | 530 | 0.2929 | | 0.2151 | 5.03 | 540 | 0.2881 | | 0.2266 | 5.13 | 550 | 0.2891 | | 0.2222 | 5.22 | 560 | 0.2908 | | 0.2305 | 5.31 | 570 | 0.2921 | | 0.2383 | 5.41 | 580 | 0.2927 | | 0.2055 | 5.5 | 590 | 0.2908 | | 0.2229 | 5.59 | 600 | 0.2916 | | 0.2365 | 5.69 | 610 | 0.2898 | | 0.2357 | 5.78 | 620 | 0.2897 | | 0.2116 | 5.87 | 630 | 0.2902 | | 0.2342 | 5.97 | 640 | 0.2915 | | 0.2011 | 6.06 | 650 | 0.2906 | | 0.1961 | 6.15 | 660 | 0.2885 | | 0.2089 | 6.25 | 670 | 0.2881 | | 0.1908 | 6.34 | 680 | 0.2886 | | 0.2093 | 6.43 | 690 | 0.2884 | | 0.1976 | 6.53 | 700 | 0.2882 | | 0.1843 | 6.62 | 710 | 0.2887 | | 0.2039 | 6.71 | 720 | 0.2893 | | 0.204 | 6.81 | 730 | 0.2894 | | 0.2124 | 6.9 | 740 | 0.2891 | ### Framework versions - Transformers 4.29.2 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3