Hugging Face's logo

GuysTrans
/
bart-base-finetuned-xsum

Text2Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
3
GuysTrans commited on
Commit
5858f77
•
1 Parent(s): 03f1680

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +112 -4
README.md CHANGED
@@ -3,6 +3,8 @@ license: apache-2.0
3
  base_model: facebook/bart-base
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: bart-base-finetuned-xsum
8
  results: []
@@ -14,6 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
14
  # bart-base-finetuned-xsum
15
 
16
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
 
 
 
 
 
 
 
17
 
18
  ## Model description
19
 
@@ -38,13 +47,112 @@ The following hyperparameters were used during training:
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
- - num_epochs: 1
42
 
43
  ### Training results
44
 
45
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
46
- |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
47
- | No log | 1.0 | 22 | 3.6905 | 8.6869 | 1.0568 | 6.621 | 7.9606 | 19.5556 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
 
49
 
50
  ### Framework versions
 
3
  base_model: facebook/bart-base
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - rouge
8
  model-index:
9
  - name: bart-base-finetuned-xsum
10
  results: []
 
16
  # bart-base-finetuned-xsum
17
 
18
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0536
21
+ - Rouge1: 30.3379
22
+ - Rouge2: 28.823
23
+ - Rougel: 30.2838
24
+ - Rougelsum: 30.2947
25
+ - Gen Len: 19.9298
26
 
27
  ## Model description
28
 
 
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
+ - num_epochs: 100
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
56
+ | No log | 1.0 | 22 | 3.3585 | 9.7586 | 1.5287 | 7.4201 | 8.9593 | 19.4386 |
57
+ | No log | 2.0 | 44 | 3.1307 | 10.5799 | 1.8167 | 8.2614 | 9.6662 | 19.0175 |
58
+ | No log | 3.0 | 66 | 2.9495 | 11.7652 | 2.1847 | 8.7837 | 10.5655 | 19.3216 |
59
+ | No log | 4.0 | 88 | 2.7920 | 11.5464 | 2.4136 | 8.9111 | 10.5071 | 18.9415 |
60
+ | No log | 5.0 | 110 | 2.6630 | 12.2901 | 2.7634 | 9.4529 | 11.2263 | 18.9883 |
61
+ | No log | 6.0 | 132 | 2.5428 | 12.569 | 2.7898 | 9.4695 | 11.1434 | 19.5146 |
62
+ | No log | 7.0 | 154 | 2.4247 | 13.3365 | 2.8074 | 9.8493 | 11.7428 | 19.731 |
63
+ | No log | 8.0 | 176 | 2.3166 | 14.1582 | 3.3604 | 10.6909 | 12.6087 | 19.8538 |
64
+ | No log | 9.0 | 198 | 2.2134 | 14.4264 | 3.8769 | 11.0709 | 13.0822 | 19.7602 |
65
+ | No log | 10.0 | 220 | 2.1139 | 13.7978 | 3.1148 | 10.3251 | 12.2168 | 19.7778 |
66
+ | No log | 11.0 | 242 | 2.0238 | 14.1079 | 3.7373 | 10.9357 | 12.7981 | 19.8713 |
67
+ | No log | 12.0 | 264 | 1.9397 | 14.7055 | 4.3184 | 11.2992 | 13.5954 | 19.8772 |
68
+ | No log | 13.0 | 286 | 1.8451 | 14.6991 | 3.8832 | 11.2441 | 13.1588 | 19.848 |
69
+ | No log | 14.0 | 308 | 1.7630 | 15.0289 | 4.3497 | 11.5492 | 13.7312 | 19.8538 |
70
+ | No log | 15.0 | 330 | 1.6870 | 14.9628 | 4.4868 | 11.6513 | 13.7924 | 19.8538 |
71
+ | No log | 16.0 | 352 | 1.6129 | 15.8419 | 5.5329 | 12.5427 | 14.6066 | 19.8246 |
72
+ | No log | 17.0 | 374 | 1.5418 | 15.261 | 4.5563 | 11.8716 | 13.9079 | 19.8363 |
73
+ | No log | 18.0 | 396 | 1.4653 | 15.7719 | 5.561 | 12.6223 | 14.4619 | 19.8363 |
74
+ | No log | 19.0 | 418 | 1.3881 | 15.4202 | 5.1589 | 12.0679 | 14.3881 | 19.9064 |
75
+ | No log | 20.0 | 440 | 1.3274 | 16.3873 | 6.1422 | 13.2212 | 15.1157 | 19.8363 |
76
+ | No log | 21.0 | 462 | 1.2554 | 16.5245 | 6.1207 | 13.1476 | 15.2785 | 19.8772 |
77
+ | No log | 22.0 | 484 | 1.1957 | 17.1818 | 6.9277 | 13.756 | 16.0687 | 19.8713 |
78
+ | 2.6205 | 23.0 | 506 | 1.1303 | 16.4459 | 6.5034 | 13.2991 | 15.3716 | 19.8363 |
79
+ | 2.6205 | 24.0 | 528 | 1.0749 | 17.501 | 7.8981 | 14.3457 | 16.273 | 19.8947 |
80
+ | 2.6205 | 25.0 | 550 | 1.0179 | 18.0965 | 8.6491 | 15.0401 | 16.9821 | 19.8772 |
81
+ | 2.6205 | 26.0 | 572 | 0.9642 | 18.4629 | 8.2476 | 15.1398 | 17.1954 | 19.8246 |
82
+ | 2.6205 | 27.0 | 594 | 0.9065 | 18.9359 | 9.0813 | 15.7911 | 17.7216 | 19.9123 |
83
+ | 2.6205 | 28.0 | 616 | 0.8658 | 19.4514 | 10.5142 | 16.7065 | 18.4666 | 19.9123 |
84
+ | 2.6205 | 29.0 | 638 | 0.8187 | 19.7181 | 10.546 | 16.8919 | 18.5289 | 19.9123 |
85
+ | 2.6205 | 30.0 | 660 | 0.7741 | 19.8173 | 10.7183 | 17.1135 | 18.9732 | 19.9123 |
86
+ | 2.6205 | 31.0 | 682 | 0.7250 | 20.4778 | 12.0763 | 18.0214 | 19.641 | 19.9123 |
87
+ | 2.6205 | 32.0 | 704 | 0.6870 | 21.1546 | 12.9349 | 18.7801 | 20.2578 | 19.9123 |
88
+ | 2.6205 | 33.0 | 726 | 0.6507 | 22.6574 | 14.9931 | 20.5845 | 21.742 | 19.8713 |
89
+ | 2.6205 | 34.0 | 748 | 0.6117 | 22.5952 | 15.5575 | 20.4172 | 21.7037 | 19.8772 |
90
+ | 2.6205 | 35.0 | 770 | 0.5780 | 23.1109 | 16.2589 | 21.0752 | 22.3091 | 19.9181 |
91
+ | 2.6205 | 36.0 | 792 | 0.5464 | 23.1603 | 16.305 | 20.9824 | 22.2362 | 19.8713 |
92
+ | 2.6205 | 37.0 | 814 | 0.5142 | 24.162 | 17.7426 | 22.3464 | 23.3824 | 19.9181 |
93
+ | 2.6205 | 38.0 | 836 | 0.4892 | 24.2007 | 17.7402 | 22.3069 | 23.2964 | 19.9123 |
94
+ | 2.6205 | 39.0 | 858 | 0.4554 | 25.0508 | 19.2285 | 23.532 | 24.3425 | 19.8713 |
95
+ | 2.6205 | 40.0 | 880 | 0.4351 | 25.2177 | 19.7802 | 23.87 | 24.5619 | 19.8713 |
96
+ | 2.6205 | 41.0 | 902 | 0.4080 | 25.6072 | 20.2655 | 24.2885 | 25.012 | 19.8713 |
97
+ | 2.6205 | 42.0 | 924 | 0.3853 | 26.2649 | 21.7378 | 25.3695 | 25.8268 | 19.8713 |
98
+ | 2.6205 | 43.0 | 946 | 0.3644 | 26.5133 | 22.0374 | 25.6096 | 26.0746 | 19.8713 |
99
+ | 2.6205 | 44.0 | 968 | 0.3434 | 27.544 | 23.6211 | 26.7186 | 27.1989 | 19.9415 |
100
+ | 2.6205 | 45.0 | 990 | 0.3238 | 28.139 | 24.4929 | 27.4976 | 27.8511 | 19.9006 |
101
+ | 1.2313 | 46.0 | 1012 | 0.3078 | 28.3887 | 25.1736 | 27.9633 | 28.1744 | 19.9415 |
102
+ | 1.2313 | 47.0 | 1034 | 0.2926 | 28.6862 | 25.3258 | 28.1086 | 28.42 | 19.9123 |
103
+ | 1.2313 | 48.0 | 1056 | 0.2725 | 28.5213 | 25.4276 | 28.1376 | 28.3496 | 19.9006 |
104
+ | 1.2313 | 49.0 | 1078 | 0.2584 | 28.765 | 25.8043 | 28.2786 | 28.5328 | 19.9006 |
105
+ | 1.2313 | 50.0 | 1100 | 0.2450 | 28.8002 | 25.8598 | 28.4401 | 28.5732 | 19.9006 |
106
+ | 1.2313 | 51.0 | 1122 | 0.2314 | 29.1758 | 26.5723 | 28.7541 | 28.9057 | 19.9006 |
107
+ | 1.2313 | 52.0 | 1144 | 0.2193 | 29.2566 | 26.7015 | 28.8675 | 29.0212 | 19.9006 |
108
+ | 1.2313 | 53.0 | 1166 | 0.2095 | 29.1182 | 26.6288 | 28.8878 | 28.9966 | 19.9006 |
109
+ | 1.2313 | 54.0 | 1188 | 0.2014 | 29.9429 | 27.8068 | 29.8207 | 29.8447 | 19.9474 |
110
+ | 1.2313 | 55.0 | 1210 | 0.1868 | 29.0828 | 26.719 | 28.8889 | 28.9866 | 19.9006 |
111
+ | 1.2313 | 56.0 | 1232 | 0.1795 | 29.8194 | 27.8057 | 29.7228 | 29.7447 | 19.9006 |
112
+ | 1.2313 | 57.0 | 1254 | 0.1690 | 29.6354 | 27.4725 | 29.4187 | 29.4941 | 19.9006 |
113
+ | 1.2313 | 58.0 | 1276 | 0.1601 | 30.0272 | 27.9412 | 29.7751 | 29.8644 | 19.9298 |
114
+ | 1.2313 | 59.0 | 1298 | 0.1544 | 30.1801 | 28.3209 | 30.004 | 30.067 | 19.9474 |
115
+ | 1.2313 | 60.0 | 1320 | 0.1479 | 30.1894 | 28.3483 | 30.0292 | 30.0775 | 19.9298 |
116
+ | 1.2313 | 61.0 | 1342 | 0.1414 | 30.2365 | 28.4556 | 30.1151 | 30.1872 | 19.9298 |
117
+ | 1.2313 | 62.0 | 1364 | 0.1339 | 30.2558 | 28.4829 | 30.1638 | 30.2142 | 19.9474 |
118
+ | 1.2313 | 63.0 | 1386 | 0.1290 | 30.1935 | 28.3722 | 30.047 | 30.1198 | 19.9298 |
119
+ | 1.2313 | 64.0 | 1408 | 0.1232 | 30.2356 | 28.4823 | 30.1396 | 30.1941 | 19.9474 |
120
+ | 1.2313 | 65.0 | 1430 | 0.1181 | 30.2719 | 28.5342 | 30.176 | 30.245 | 19.9298 |
121
+ | 1.2313 | 66.0 | 1452 | 0.1125 | 30.2062 | 28.4951 | 30.1307 | 30.1736 | 19.9298 |
122
+ | 1.2313 | 67.0 | 1474 | 0.1069 | 30.2193 | 28.498 | 30.1143 | 30.1778 | 19.9298 |
123
+ | 1.2313 | 68.0 | 1496 | 0.1027 | 30.0782 | 28.4741 | 30.0127 | 30.0385 | 19.9006 |
124
+ | 0.6386 | 69.0 | 1518 | 0.1014 | 30.2859 | 28.7111 | 30.2224 | 30.2692 | 19.9298 |
125
+ | 0.6386 | 70.0 | 1540 | 0.0979 | 30.2806 | 28.6988 | 30.2214 | 30.2583 | 19.9298 |
126
+ | 0.6386 | 71.0 | 1562 | 0.0945 | 30.2865 | 28.7031 | 30.2387 | 30.2613 | 19.9298 |
127
+ | 0.6386 | 72.0 | 1584 | 0.0902 | 30.3134 | 28.8224 | 30.2775 | 30.2923 | 19.9474 |
128
+ | 0.6386 | 73.0 | 1606 | 0.0875 | 30.316 | 28.8558 | 30.2741 | 30.2958 | 19.9474 |
129
+ | 0.6386 | 74.0 | 1628 | 0.0848 | 30.2854 | 28.7254 | 30.2396 | 30.273 | 19.9298 |
130
+ | 0.6386 | 75.0 | 1650 | 0.0801 | 30.3158 | 28.8377 | 30.2739 | 30.2988 | 19.9474 |
131
+ | 0.6386 | 76.0 | 1672 | 0.0790 | 30.316 | 28.8628 | 30.2741 | 30.2958 | 19.9474 |
132
+ | 0.6386 | 77.0 | 1694 | 0.0770 | 30.3249 | 28.8701 | 30.2905 | 30.3056 | 19.9474 |
133
+ | 0.6386 | 78.0 | 1716 | 0.0745 | 30.3109 | 28.8801 | 30.2683 | 30.2891 | 19.9474 |
134
+ | 0.6386 | 79.0 | 1738 | 0.0735 | 30.3249 | 28.8732 | 30.2905 | 30.3056 | 19.9474 |
135
+ | 0.6386 | 80.0 | 1760 | 0.0704 | 30.3249 | 28.899 | 30.2905 | 30.3056 | 19.9474 |
136
+ | 0.6386 | 81.0 | 1782 | 0.0698 | 30.3183 | 28.9058 | 30.2817 | 30.2965 | 19.9474 |
137
+ | 0.6386 | 82.0 | 1804 | 0.0674 | 30.287 | 28.785 | 30.2354 | 30.2658 | 19.9298 |
138
+ | 0.6386 | 83.0 | 1826 | 0.0655 | 30.287 | 28.785 | 30.2354 | 30.2658 | 19.9298 |
139
+ | 0.6386 | 84.0 | 1848 | 0.0647 | 30.3006 | 28.8093 | 30.2572 | 30.2715 | 19.9298 |
140
+ | 0.6386 | 85.0 | 1870 | 0.0625 | 30.3006 | 28.8093 | 30.2572 | 30.2715 | 19.924 |
141
+ | 0.6386 | 86.0 | 1892 | 0.0620 | 30.287 | 28.7763 | 30.2354 | 30.2658 | 19.9298 |
142
+ | 0.6386 | 87.0 | 1914 | 0.0603 | 30.3006 | 28.8093 | 30.2572 | 30.2715 | 19.9298 |
143
+ | 0.6386 | 88.0 | 1936 | 0.0595 | 30.3006 | 28.8093 | 30.2572 | 30.2715 | 19.924 |
144
+ | 0.6386 | 89.0 | 1958 | 0.0584 | 30.3006 | 28.8093 | 30.2572 | 30.2715 | 19.924 |
145
+ | 0.6386 | 90.0 | 1980 | 0.0571 | 30.3006 | 28.8093 | 30.2572 | 30.2715 | 19.924 |
146
+ | 0.4186 | 91.0 | 2002 | 0.0566 | 30.3006 | 28.8093 | 30.2572 | 30.2715 | 19.9298 |
147
+ | 0.4186 | 92.0 | 2024 | 0.0560 | 30.3379 | 28.8176 | 30.272 | 30.2843 | 19.924 |
148
+ | 0.4186 | 93.0 | 2046 | 0.0557 | 30.3006 | 28.8093 | 30.2572 | 30.2715 | 19.924 |
149
+ | 0.4186 | 94.0 | 2068 | 0.0550 | 30.3379 | 28.823 | 30.2838 | 30.2947 | 19.924 |
150
+ | 0.4186 | 95.0 | 2090 | 0.0546 | 30.3528 | 28.9302 | 30.321 | 30.3214 | 19.9474 |
151
+ | 0.4186 | 96.0 | 2112 | 0.0542 | 30.3528 | 28.9255 | 30.3159 | 30.3159 | 19.9474 |
152
+ | 0.4186 | 97.0 | 2134 | 0.0540 | 30.3379 | 28.8176 | 30.272 | 30.2843 | 19.9298 |
153
+ | 0.4186 | 98.0 | 2156 | 0.0539 | 30.3379 | 28.8176 | 30.272 | 30.2843 | 19.9298 |
154
+ | 0.4186 | 99.0 | 2178 | 0.0537 | 30.3379 | 28.8176 | 30.272 | 30.2843 | 19.9298 |
155
+ | 0.4186 | 100.0 | 2200 | 0.0536 | 30.3379 | 28.823 | 30.2838 | 30.2947 | 19.9298 |
156
 
157
 
158
  ### Framework versions