Hugging Face's logo

andreaschandra
/
unifiedqa-v2-t5-base-1363200-finetuned-causalqa-squad

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
1
andreaschandra commited on
Commit
4ccc9e0
•
1 Parent(s): 9367ba1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +102 -6
README.md CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [allenai/unifiedqa-v2-t5-base-1363200](https://huggingface.co/allenai/unifiedqa-v2-t5-base-1363200) on the None dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 4.7560
17
 
18
  ## Model description
19
 
@@ -44,11 +44,107 @@ The following hyperparameters were used during training:
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
- | 0.1892 | 1.0 | 1479 | 3.7610 |
48
- | 0.1514 | 2.0 | 2958 | 4.1694 |
49
- | 0.0807 | 3.0 | 4437 | 4.5543 |
50
- | 0.0381 | 4.0 | 5916 | 4.6654 |
51
- | 0.0377 | 5.0 | 7395 | 4.7560 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
 
53
 
54
  ### Framework versions
 
13
 
14
  This model is a fine-tuned version of [allenai/unifiedqa-v2-t5-base-1363200](https://huggingface.co/allenai/unifiedqa-v2-t5-base-1363200) on the None dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 1.2574
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 0.7378 | 0.05 | 73 | 1.1837 |
48
+ | 0.6984 | 0.1 | 146 | 0.8918 |
49
+ | 0.4511 | 0.15 | 219 | 0.8342 |
50
+ | 0.4696 | 0.2 | 292 | 0.7642 |
51
+ | 0.295 | 0.25 | 365 | 0.7996 |
52
+ | 0.266 | 0.3 | 438 | 0.7773 |
53
+ | 0.2372 | 0.35 | 511 | 0.8592 |
54
+ | 0.2881 | 0.39 | 584 | 0.8440 |
55
+ | 0.2578 | 0.44 | 657 | 0.8306 |
56
+ | 0.2733 | 0.49 | 730 | 0.8228 |
57
+ | 0.2073 | 0.54 | 803 | 0.8419 |
58
+ | 0.2683 | 0.59 | 876 | 0.8241 |
59
+ | 0.2693 | 0.64 | 949 | 0.8573 |
60
+ | 0.355 | 0.69 | 1022 | 0.8204 |
61
+ | 0.2246 | 0.74 | 1095 | 0.8530 |
62
+ | 0.2468 | 0.79 | 1168 | 0.8410 |
63
+ | 0.3102 | 0.84 | 1241 | 0.8035 |
64
+ | 0.2115 | 0.89 | 1314 | 0.8262 |
65
+ | 0.1855 | 0.94 | 1387 | 0.8560 |
66
+ | 0.1772 | 0.99 | 1460 | 0.8747 |
67
+ | 0.1509 | 1.04 | 1533 | 0.9132 |
68
+ | 0.1871 | 1.09 | 1606 | 0.8920 |
69
+ | 0.1624 | 1.14 | 1679 | 0.9085 |
70
+ | 0.1404 | 1.18 | 1752 | 0.9460 |
71
+ | 0.1639 | 1.23 | 1825 | 0.9812 |
72
+ | 0.0983 | 1.28 | 1898 | 0.9790 |
73
+ | 0.1395 | 1.33 | 1971 | 0.9843 |
74
+ | 0.1439 | 1.38 | 2044 | 0.9877 |
75
+ | 0.1397 | 1.43 | 2117 | 1.0338 |
76
+ | 0.1095 | 1.48 | 2190 | 1.0589 |
77
+ | 0.1228 | 1.53 | 2263 | 1.0498 |
78
+ | 0.1246 | 1.58 | 2336 | 1.0923 |
79
+ | 0.1438 | 1.63 | 2409 | 1.0995 |
80
+ | 0.1305 | 1.68 | 2482 | 1.0867 |
81
+ | 0.1077 | 1.73 | 2555 | 1.1013 |
82
+ | 0.2104 | 1.78 | 2628 | 1.0765 |
83
+ | 0.1633 | 1.83 | 2701 | 1.0796 |
84
+ | 0.1658 | 1.88 | 2774 | 1.0314 |
85
+ | 0.1358 | 1.92 | 2847 | 0.9823 |
86
+ | 0.1571 | 1.97 | 2920 | 0.9826 |
87
+ | 0.1127 | 2.02 | 2993 | 1.0324 |
88
+ | 0.0927 | 2.07 | 3066 | 1.0679 |
89
+ | 0.0549 | 2.12 | 3139 | 1.1069 |
90
+ | 0.0683 | 2.17 | 3212 | 1.1624 |
91
+ | 0.0677 | 2.22 | 3285 | 1.1174 |
92
+ | 0.0615 | 2.27 | 3358 | 1.1431 |
93
+ | 0.0881 | 2.32 | 3431 | 1.1721 |
94
+ | 0.0807 | 2.37 | 3504 | 1.1885 |
95
+ | 0.0955 | 2.42 | 3577 | 1.1991 |
96
+ | 0.0779 | 2.47 | 3650 | 1.1999 |
97
+ | 0.11 | 2.52 | 3723 | 1.1774 |
98
+ | 0.0852 | 2.57 | 3796 | 1.2095 |
99
+ | 0.0616 | 2.62 | 3869 | 1.1824 |
100
+ | 0.072 | 2.67 | 3942 | 1.2397 |
101
+ | 0.1055 | 2.71 | 4015 | 1.2181 |
102
+ | 0.0806 | 2.76 | 4088 | 1.2159 |
103
+ | 0.0684 | 2.81 | 4161 | 1.1864 |
104
+ | 0.0869 | 2.86 | 4234 | 1.1816 |
105
+ | 0.1023 | 2.91 | 4307 | 1.1717 |
106
+ | 0.0583 | 2.96 | 4380 | 1.1477 |
107
+ | 0.0684 | 3.01 | 4453 | 1.1662 |
108
+ | 0.0319 | 3.06 | 4526 | 1.2174 |
109
+ | 0.0609 | 3.11 | 4599 | 1.1947 |
110
+ | 0.0435 | 3.16 | 4672 | 1.1821 |
111
+ | 0.0417 | 3.21 | 4745 | 1.1964 |
112
+ | 0.0502 | 3.26 | 4818 | 1.2140 |
113
+ | 0.0844 | 3.31 | 4891 | 1.2028 |
114
+ | 0.0692 | 3.36 | 4964 | 1.2215 |
115
+ | 0.0366 | 3.41 | 5037 | 1.2136 |
116
+ | 0.0615 | 3.46 | 5110 | 1.2224 |
117
+ | 0.0656 | 3.5 | 5183 | 1.2468 |
118
+ | 0.0469 | 3.55 | 5256 | 1.2554 |
119
+ | 0.0475 | 3.6 | 5329 | 1.2804 |
120
+ | 0.0998 | 3.65 | 5402 | 1.2035 |
121
+ | 0.0505 | 3.7 | 5475 | 1.2095 |
122
+ | 0.0459 | 3.75 | 5548 | 1.2064 |
123
+ | 0.0256 | 3.8 | 5621 | 1.2164 |
124
+ | 0.0831 | 3.85 | 5694 | 1.2154 |
125
+ | 0.0397 | 3.9 | 5767 | 1.2126 |
126
+ | 0.0449 | 3.95 | 5840 | 1.2174 |
127
+ | 0.0322 | 4.0 | 5913 | 1.2288 |
128
+ | 0.059 | 4.05 | 5986 | 1.2274 |
129
+ | 0.0382 | 4.1 | 6059 | 1.2228 |
130
+ | 0.0202 | 4.15 | 6132 | 1.2177 |
131
+ | 0.0328 | 4.2 | 6205 | 1.2305 |
132
+ | 0.0407 | 4.24 | 6278 | 1.2342 |
133
+ | 0.0356 | 4.29 | 6351 | 1.2448 |
134
+ | 0.0414 | 4.34 | 6424 | 1.2537 |
135
+ | 0.0448 | 4.39 | 6497 | 1.2540 |
136
+ | 0.0545 | 4.44 | 6570 | 1.2552 |
137
+ | 0.0492 | 4.49 | 6643 | 1.2570 |
138
+ | 0.0293 | 4.54 | 6716 | 1.2594 |
139
+ | 0.0498 | 4.59 | 6789 | 1.2562 |
140
+ | 0.0349 | 4.64 | 6862 | 1.2567 |
141
+ | 0.0497 | 4.69 | 6935 | 1.2550 |
142
+ | 0.0194 | 4.74 | 7008 | 1.2605 |
143
+ | 0.0255 | 4.79 | 7081 | 1.2590 |
144
+ | 0.0212 | 4.84 | 7154 | 1.2571 |
145
+ | 0.0231 | 4.89 | 7227 | 1.2583 |
146
+ | 0.0399 | 4.94 | 7300 | 1.2580 |
147
+ | 0.0719 | 4.99 | 7373 | 1.2574 |
148
 
149
 
150
  ### Framework versions