Commit
•
2d9eaa6
1
Parent(s):
24ac46e
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: Finetune_Pegasus_2
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# Finetune_Pegasus_2
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [Gayathri142214002/Finetune_Pegasus_1](https://huggingface.co/Gayathri142214002/Finetune_Pegasus_1) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.2891
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.0001
|
| 37 |
+
- train_batch_size: 1
|
| 38 |
+
- eval_batch_size: 1
|
| 39 |
+
- seed: 42
|
| 40 |
+
- gradient_accumulation_steps: 4
|
| 41 |
+
- total_train_batch_size: 4
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 7
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| 0.5877 | 0.09 | 10 | 0.4730 |
|
| 51 |
+
| 0.4521 | 0.19 | 20 | 0.4180 |
|
| 52 |
+
| 0.5412 | 0.28 | 30 | 0.3851 |
|
| 53 |
+
| 0.3669 | 0.37 | 40 | 0.3635 |
|
| 54 |
+
| 0.3732 | 0.47 | 50 | 0.3396 |
|
| 55 |
+
| 0.3724 | 0.56 | 60 | 0.3555 |
|
| 56 |
+
| 0.3693 | 0.65 | 70 | 0.3412 |
|
| 57 |
+
| 0.3476 | 0.75 | 80 | 0.3060 |
|
| 58 |
+
| 0.3288 | 0.84 | 90 | 0.3009 |
|
| 59 |
+
| 0.3439 | 0.93 | 100 | 0.3344 |
|
| 60 |
+
| 0.2644 | 1.03 | 110 | 0.3283 |
|
| 61 |
+
| 0.2926 | 1.12 | 120 | 0.3101 |
|
| 62 |
+
| 0.2615 | 1.21 | 130 | 0.3189 |
|
| 63 |
+
| 0.3004 | 1.31 | 140 | 0.3085 |
|
| 64 |
+
| 0.3202 | 1.4 | 150 | 0.3148 |
|
| 65 |
+
| 0.2989 | 1.49 | 160 | 0.3062 |
|
| 66 |
+
| 0.3326 | 1.59 | 170 | 0.3055 |
|
| 67 |
+
| 0.3101 | 1.68 | 180 | 0.2886 |
|
| 68 |
+
| 0.3011 | 1.77 | 190 | 0.2896 |
|
| 69 |
+
| 0.2795 | 1.86 | 200 | 0.2901 |
|
| 70 |
+
| 0.2759 | 1.96 | 210 | 0.3092 |
|
| 71 |
+
| 0.2883 | 2.05 | 220 | 0.2948 |
|
| 72 |
+
| 0.2566 | 2.14 | 230 | 0.2760 |
|
| 73 |
+
| 0.222 | 2.24 | 240 | 0.2802 |
|
| 74 |
+
| 0.2667 | 2.33 | 250 | 0.2733 |
|
| 75 |
+
| 0.262 | 2.42 | 260 | 0.2928 |
|
| 76 |
+
| 0.2784 | 2.52 | 270 | 0.3061 |
|
| 77 |
+
| 0.2832 | 2.61 | 280 | 0.3079 |
|
| 78 |
+
| 0.2885 | 2.7 | 290 | 0.3160 |
|
| 79 |
+
| 0.275 | 2.8 | 300 | 0.3111 |
|
| 80 |
+
| 0.3059 | 2.89 | 310 | 0.2992 |
|
| 81 |
+
| 0.2604 | 2.98 | 320 | 0.2923 |
|
| 82 |
+
| 0.2425 | 3.08 | 330 | 0.2991 |
|
| 83 |
+
| 0.2225 | 3.17 | 340 | 0.2988 |
|
| 84 |
+
| 0.2548 | 3.26 | 350 | 0.3124 |
|
| 85 |
+
| 0.2393 | 3.36 | 360 | 0.3009 |
|
| 86 |
+
| 0.2383 | 3.45 | 370 | 0.2846 |
|
| 87 |
+
| 0.2251 | 3.54 | 380 | 0.2871 |
|
| 88 |
+
| 0.253 | 3.64 | 390 | 0.2875 |
|
| 89 |
+
| 0.2615 | 3.73 | 400 | 0.2829 |
|
| 90 |
+
| 0.238 | 3.82 | 410 | 0.2815 |
|
| 91 |
+
| 0.2685 | 3.92 | 420 | 0.2892 |
|
| 92 |
+
| 0.2532 | 4.01 | 430 | 0.2906 |
|
| 93 |
+
| 0.2105 | 4.1 | 440 | 0.2851 |
|
| 94 |
+
| 0.2382 | 4.2 | 450 | 0.2823 |
|
| 95 |
+
| 0.2316 | 4.29 | 460 | 0.2777 |
|
| 96 |
+
| 0.2565 | 4.38 | 470 | 0.2816 |
|
| 97 |
+
| 0.2216 | 4.48 | 480 | 0.2869 |
|
| 98 |
+
| 0.2477 | 4.57 | 490 | 0.2968 |
|
| 99 |
+
| 0.2223 | 4.66 | 500 | 0.3006 |
|
| 100 |
+
| 0.2445 | 4.76 | 510 | 0.3035 |
|
| 101 |
+
| 0.2383 | 4.85 | 520 | 0.2985 |
|
| 102 |
+
| 0.2482 | 4.94 | 530 | 0.2929 |
|
| 103 |
+
| 0.2151 | 5.03 | 540 | 0.2881 |
|
| 104 |
+
| 0.2266 | 5.13 | 550 | 0.2891 |
|
| 105 |
+
| 0.2222 | 5.22 | 560 | 0.2908 |
|
| 106 |
+
| 0.2305 | 5.31 | 570 | 0.2921 |
|
| 107 |
+
| 0.2383 | 5.41 | 580 | 0.2927 |
|
| 108 |
+
| 0.2055 | 5.5 | 590 | 0.2908 |
|
| 109 |
+
| 0.2229 | 5.59 | 600 | 0.2916 |
|
| 110 |
+
| 0.2365 | 5.69 | 610 | 0.2898 |
|
| 111 |
+
| 0.2357 | 5.78 | 620 | 0.2897 |
|
| 112 |
+
| 0.2116 | 5.87 | 630 | 0.2902 |
|
| 113 |
+
| 0.2342 | 5.97 | 640 | 0.2915 |
|
| 114 |
+
| 0.2011 | 6.06 | 650 | 0.2906 |
|
| 115 |
+
| 0.1961 | 6.15 | 660 | 0.2885 |
|
| 116 |
+
| 0.2089 | 6.25 | 670 | 0.2881 |
|
| 117 |
+
| 0.1908 | 6.34 | 680 | 0.2886 |
|
| 118 |
+
| 0.2093 | 6.43 | 690 | 0.2884 |
|
| 119 |
+
| 0.1976 | 6.53 | 700 | 0.2882 |
|
| 120 |
+
| 0.1843 | 6.62 | 710 | 0.2887 |
|
| 121 |
+
| 0.2039 | 6.71 | 720 | 0.2893 |
|
| 122 |
+
| 0.204 | 6.81 | 730 | 0.2894 |
|
| 123 |
+
| 0.2124 | 6.9 | 740 | 0.2891 |
|
| 124 |
+
|
| 125 |
+
|
| 126 |
+
### Framework versions
|
| 127 |
+
|
| 128 |
+
- Transformers 4.29.2
|
| 129 |
+
- Pytorch 2.0.1+cu117
|
| 130 |
+
- Datasets 2.12.0
|
| 131 |
+
- Tokenizers 0.13.3
|