Hugging Face's logo

satyanshu404
/
gpt2-finetuned-justification-v5

Text2Text Generation
Transformers
Safetensors
encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Community
satyanshu404 commited on
Commit
bbbea08
·
verified ·
1 Parent(s): 874663a

End of training

Browse files
Files changed (3) hide show
  1. README.md +160 -0
  2. generation_config.json +7 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - rouge
6
+ model-index:
7
+ - name: gpt2-finetuned-justification-v5
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # gpt2-finetuned-justification-v5
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.3593
19
+ - Rouge1: 30.3314
20
+ - Rouge2: 13.6649
21
+ - Rougel: 22.1151
22
+ - Rougelsum: 27.5740
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
+ - train_batch_size: 1
43
+ - eval_batch_size: 1
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 100
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
53
+ | 0.2489 | 1.0 | 676 | 0.1998 | 31.2785 | 13.9405 | 23.6754 | 29.4276 |
54
+ | 0.1946 | 2.0 | 1352 | 0.1975 | 28.9246 | 13.8110 | 21.8172 | 26.7381 |
55
+ | 0.1665 | 3.0 | 2028 | 0.1992 | 30.6132 | 13.5815 | 22.8313 | 28.3888 |
56
+ | 0.1502 | 4.0 | 2704 | 0.2014 | 28.8523 | 13.8110 | 21.7893 | 26.6709 |
57
+ | 0.1468 | 5.0 | 3380 | 0.2056 | 30.6551 | 13.6239 | 22.4474 | 28.1216 |
58
+ | 0.1252 | 6.0 | 4056 | 0.2108 | 27.3409 | 12.8890 | 22.0237 | 25.8205 |
59
+ | 0.1165 | 7.0 | 4732 | 0.2156 | 30.6132 | 13.5815 | 22.8313 | 28.3888 |
60
+ | 0.1066 | 8.0 | 5408 | 0.2256 | 27.4403 | 13.0727 | 22.0916 | 25.8186 |
61
+ | 0.0934 | 9.0 | 6084 | 0.2280 | 26.2488 | 13.3334 | 21.6255 | 25.0369 |
62
+ | 0.0852 | 10.0 | 6760 | 0.2389 | 29.5864 | 13.4737 | 21.9157 | 27.1120 |
63
+ | 0.0761 | 11.0 | 7436 | 0.2431 | 26.4819 | 13.0004 | 20.5264 | 24.8436 |
64
+ | 0.0684 | 12.0 | 8112 | 0.2452 | 30.6579 | 13.6910 | 22.8683 | 28.4284 |
65
+ | 0.0611 | 13.0 | 8788 | 0.2583 | 28.2628 | 13.8124 | 21.5380 | 25.9928 |
66
+ | 0.0602 | 14.0 | 9464 | 0.2605 | 27.2437 | 13.5522 | 20.9343 | 25.1400 |
67
+ | 0.0498 | 15.0 | 10140 | 0.2677 | 30.5254 | 13.0067 | 22.0006 | 27.6813 |
68
+ | 0.0459 | 16.0 | 10816 | 0.2727 | 28.2628 | 13.8124 | 21.5380 | 25.9928 |
69
+ | 0.0463 | 17.0 | 11492 | 0.2769 | 30.4338 | 13.4529 | 22.2644 | 27.8807 |
70
+ | 0.0379 | 18.0 | 12168 | 0.2807 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
71
+ | 0.0363 | 19.0 | 12844 | 0.2850 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
72
+ | 0.0329 | 20.0 | 13520 | 0.2889 | 30.5473 | 13.5205 | 22.8369 | 28.3332 |
73
+ | 0.0292 | 21.0 | 14196 | 0.2906 | 27.2109 | 13.8527 | 21.2733 | 25.1714 |
74
+ | 0.0293 | 22.0 | 14872 | 0.2926 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
75
+ | 0.026 | 23.0 | 15548 | 0.2953 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
76
+ | 0.0245 | 24.0 | 16224 | 0.3007 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
77
+ | 0.0234 | 25.0 | 16900 | 0.3026 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
78
+ | 0.0216 | 26.0 | 17576 | 0.3051 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
79
+ | 0.021 | 27.0 | 18252 | 0.3065 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
80
+ | 0.0198 | 28.0 | 18928 | 0.3104 | 26.4846 | 12.9852 | 20.4826 | 24.8131 |
81
+ | 0.0187 | 29.0 | 19604 | 0.3089 | 27.6064 | 13.3010 | 20.9219 | 25.4612 |
82
+ | 0.0184 | 30.0 | 20280 | 0.3130 | 26.4846 | 12.9852 | 20.4826 | 24.8131 |
83
+ | 0.0169 | 31.0 | 20956 | 0.3173 | 28.2628 | 13.8124 | 21.5380 | 25.9928 |
84
+ | 0.0165 | 32.0 | 21632 | 0.3175 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
85
+ | 0.0158 | 33.0 | 22308 | 0.3193 | 27.1320 | 12.8840 | 21.1562 | 25.2442 |
86
+ | 0.0155 | 34.0 | 22984 | 0.3202 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
87
+ | 0.0142 | 35.0 | 23660 | 0.3249 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
88
+ | 0.0146 | 36.0 | 24336 | 0.3239 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
89
+ | 0.0142 | 37.0 | 25012 | 0.3258 | 30.5254 | 13.0067 | 22.0006 | 27.6813 |
90
+ | 0.0133 | 38.0 | 25688 | 0.3256 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
91
+ | 0.0131 | 39.0 | 26364 | 0.3289 | 30.5254 | 13.0067 | 22.0006 | 27.6813 |
92
+ | 0.013 | 40.0 | 27040 | 0.3302 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
93
+ | 0.0124 | 41.0 | 27716 | 0.3316 | 29.4371 | 13.3012 | 21.8783 | 27.0869 |
94
+ | 0.0122 | 42.0 | 28392 | 0.3333 | 28.9119 | 13.0811 | 21.4711 | 26.5360 |
95
+ | 0.0121 | 43.0 | 29068 | 0.3351 | 27.4513 | 12.6124 | 20.8266 | 25.4587 |
96
+ | 0.0119 | 44.0 | 29744 | 0.3328 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
97
+ | 0.0117 | 45.0 | 30420 | 0.3337 | 26.4846 | 12.9852 | 20.4826 | 24.8131 |
98
+ | 0.0113 | 46.0 | 31096 | 0.3381 | 28.2105 | 13.3220 | 20.6021 | 25.4881 |
99
+ | 0.011 | 47.0 | 31772 | 0.3390 | 27.2109 | 13.8527 | 21.2733 | 25.1714 |
100
+ | 0.0111 | 48.0 | 32448 | 0.3367 | 26.4846 | 12.9852 | 20.4826 | 24.8131 |
101
+ | 0.0108 | 49.0 | 33124 | 0.3373 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
102
+ | 0.0107 | 50.0 | 33800 | 0.3423 | 27.1320 | 12.8840 | 21.1562 | 25.2442 |
103
+ | 0.0107 | 51.0 | 34476 | 0.3413 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
104
+ | 0.0101 | 52.0 | 35152 | 0.3423 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
105
+ | 0.0102 | 53.0 | 35828 | 0.3419 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
106
+ | 0.0102 | 54.0 | 36504 | 0.3443 | 27.2109 | 13.8527 | 21.2733 | 25.1714 |
107
+ | 0.01 | 55.0 | 37180 | 0.3447 | 22.6096 | 11.8510 | 18.9963 | 21.1395 |
108
+ | 0.0098 | 56.0 | 37856 | 0.3447 | 27.2109 | 13.8527 | 21.2733 | 25.1714 |
109
+ | 0.0097 | 57.0 | 38532 | 0.3435 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
110
+ | 0.0096 | 58.0 | 39208 | 0.3487 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
111
+ | 0.0096 | 59.0 | 39884 | 0.3467 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
112
+ | 0.0096 | 60.0 | 40560 | 0.3465 | 28.5241 | 13.2937 | 21.7465 | 26.4838 |
113
+ | 0.0094 | 61.0 | 41236 | 0.3477 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
114
+ | 0.0093 | 62.0 | 41912 | 0.3514 | 28.5832 | 12.9429 | 21.4631 | 26.4030 |
115
+ | 0.0091 | 63.0 | 42588 | 0.3520 | 26.4137 | 12.8727 | 19.8282 | 23.8750 |
116
+ | 0.0092 | 64.0 | 43264 | 0.3499 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
117
+ | 0.009 | 65.0 | 43940 | 0.3515 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
118
+ | 0.0091 | 66.0 | 44616 | 0.3517 | 27.0378 | 13.1450 | 20.9935 | 24.8358 |
119
+ | 0.0089 | 67.0 | 45292 | 0.3518 | 28.9119 | 13.0811 | 21.4711 | 26.5360 |
120
+ | 0.0089 | 68.0 | 45968 | 0.3523 | 26.4137 | 12.8727 | 19.8282 | 23.8750 |
121
+ | 0.0088 | 69.0 | 46644 | 0.3521 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
122
+ | 0.0087 | 70.0 | 47320 | 0.3520 | 26.4846 | 12.9852 | 20.4826 | 24.8131 |
123
+ | 0.0087 | 71.0 | 47996 | 0.3530 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
124
+ | 0.0087 | 72.0 | 48672 | 0.3525 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
125
+ | 0.0085 | 73.0 | 49348 | 0.3568 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
126
+ | 0.0087 | 74.0 | 50024 | 0.3553 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
127
+ | 0.0084 | 75.0 | 50700 | 0.3555 | 28.2105 | 13.3220 | 20.6021 | 25.4881 |
128
+ | 0.0086 | 76.0 | 51376 | 0.3563 | 28.2105 | 13.3220 | 20.6021 | 25.4881 |
129
+ | 0.0083 | 77.0 | 52052 | 0.3555 | 27.2109 | 13.8527 | 21.2733 | 25.1714 |
130
+ | 0.0084 | 78.0 | 52728 | 0.3525 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
131
+ | 0.0083 | 79.0 | 53404 | 0.3552 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
132
+ | 0.0082 | 80.0 | 54080 | 0.3559 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
133
+ | 0.0082 | 81.0 | 54756 | 0.3557 | 26.3616 | 12.4359 | 20.2061 | 24.1975 |
134
+ | 0.0082 | 82.0 | 55432 | 0.3560 | 28.2105 | 13.3220 | 20.6021 | 25.4881 |
135
+ | 0.0082 | 83.0 | 56108 | 0.3563 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
136
+ | 0.0081 | 84.0 | 56784 | 0.3562 | 27.2109 | 13.8527 | 21.2733 | 25.1714 |
137
+ | 0.008 | 85.0 | 57460 | 0.3565 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
138
+ | 0.008 | 86.0 | 58136 | 0.3588 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
139
+ | 0.008 | 87.0 | 58812 | 0.3572 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
140
+ | 0.0081 | 88.0 | 59488 | 0.3583 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
141
+ | 0.008 | 89.0 | 60164 | 0.3569 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
142
+ | 0.0079 | 90.0 | 60840 | 0.3568 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
143
+ | 0.008 | 91.0 | 61516 | 0.3577 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
144
+ | 0.0079 | 92.0 | 62192 | 0.3587 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
145
+ | 0.0078 | 93.0 | 62868 | 0.3592 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
146
+ | 0.0078 | 94.0 | 63544 | 0.3591 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
147
+ | 0.0078 | 95.0 | 64220 | 0.3591 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
148
+ | 0.0077 | 96.0 | 64896 | 0.3590 | 27.2109 | 13.8527 | 21.2733 | 25.1714 |
149
+ | 0.0077 | 97.0 | 65572 | 0.3596 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
150
+ | 0.0077 | 98.0 | 66248 | 0.3594 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
151
+ | 0.0076 | 99.0 | 66924 | 0.3592 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
152
+ | 0.0076 | 100.0 | 67600 | 0.3593 | 30.3314 | 13.6649 | 22.1151 | 27.5740 |
153
+
154
+
155
+ ### Framework versions
156
+
157
+ - Transformers 4.36.2
158
+ - Pytorch 2.2.2+cu121
159
+ - Datasets 2.16.0
160
+ - Tokenizers 0.15.2
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 50256,
3
+ "decoder_start_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "pad_token_id": 50256,
6
+ "transformers_version": "4.36.2"
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d006c79ac0c0319757dce1e08d03aba23842c27be54be0726963ba42906e0cca
3
  size 1205925664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ad9e67e616e32457f0adeb267f4d178e1ca4e296b3f0c300d0de2aafc18aad
3
  size 1205925664