WillHeld commited on
Commit
4959bfa
1 Parent(s): dc97d8e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -22
README.md CHANGED
@@ -1,11 +1,7 @@
1
  ---
2
- language:
3
- - en
4
  license: apache-2.0
5
  tags:
6
  - generated_from_trainer
7
- datasets:
8
- - mtop
9
  model-index:
10
  - name: t5-small-pointer-mtop
11
  results: []
@@ -16,10 +12,10 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # t5-small-pointer-mtop
18
 
19
- This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the mtop dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.1064
22
- - Exact Match: 0.7570
23
 
24
  ## Model description
25
 
@@ -52,21 +48,21 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Exact Match |
54
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|
55
- | 2.0944 | 6.65 | 200 | 0.6548 | 0.0027 |
56
- | 0.5307 | 13.33 | 400 | 0.2456 | 0.2779 |
57
- | 0.2388 | 19.98 | 600 | 0.1486 | 0.4559 |
58
- | 0.1459 | 26.65 | 800 | 0.1190 | 0.5043 |
59
- | 0.1011 | 33.33 | 1000 | 0.1117 | 0.5230 |
60
- | 0.0774 | 39.98 | 1200 | 0.1084 | 0.5374 |
61
- | 0.0598 | 46.65 | 1400 | 0.1064 | 0.5405 |
62
- | 0.0478 | 53.33 | 1600 | 0.1147 | 0.5454 |
63
- | 0.0397 | 59.98 | 1800 | 0.1139 | 0.5472 |
64
- | 0.0337 | 66.65 | 2000 | 0.1179 | 0.5481 |
65
- | 0.0286 | 73.33 | 2200 | 0.1243 | 0.5499 |
66
- | 0.0251 | 79.98 | 2400 | 0.1259 | 0.5481 |
67
- | 0.0218 | 86.65 | 2600 | 0.1276 | 0.5503 |
68
- | 0.0197 | 93.33 | 2800 | 0.1309 | 0.5503 |
69
- | 0.0184 | 99.98 | 3000 | 0.1317 | 0.5503 |
70
 
71
 
72
  ### Framework versions
 
1
  ---
 
 
2
  license: apache-2.0
3
  tags:
4
  - generated_from_trainer
 
 
5
  model-index:
6
  - name: t5-small-pointer-mtop
7
  results: []
 
12
 
13
  # t5-small-pointer-mtop
14
 
15
+ This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.1505
18
+ - Exact Match: 0.5512
19
 
20
  ## Model description
21
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Exact Match |
50
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|
51
+ | 2.1451 | 6.65 | 200 | 0.5966 | 0.0134 |
52
+ | 0.4695 | 13.33 | 400 | 0.2264 | 0.2998 |
53
+ | 0.2229 | 19.98 | 600 | 0.1446 | 0.4649 |
54
+ | 0.1389 | 26.65 | 800 | 0.1227 | 0.5154 |
55
+ | 0.097 | 33.33 | 1000 | 0.1213 | 0.5221 |
56
+ | 0.0724 | 39.98 | 1200 | 0.1202 | 0.5365 |
57
+ | 0.0562 | 46.65 | 1400 | 0.1207 | 0.5436 |
58
+ | 0.0457 | 53.33 | 1600 | 0.1240 | 0.5441 |
59
+ | 0.0399 | 59.98 | 1800 | 0.1349 | 0.5441 |
60
+ | 0.0317 | 66.65 | 2000 | 0.1369 | 0.5477 |
61
+ | 0.0271 | 73.33 | 2200 | 0.1409 | 0.5490 |
62
+ | 0.0237 | 79.98 | 2400 | 0.1462 | 0.5539 |
63
+ | 0.0207 | 86.65 | 2600 | 0.1470 | 0.5517 |
64
+ | 0.0188 | 93.33 | 2800 | 0.1505 | 0.5508 |
65
+ | 0.0174 | 99.98 | 3000 | 0.1505 | 0.5512 |
66
 
67
 
68
  ### Framework versions