Uzair54 commited on
Commit
a98f543
1 Parent(s): 9259c1b

Model save

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [Uzair54/test](https://huggingface.co/Uzair54/test) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.0250
20
  - Gen Len: 19.0
21
  - P: 0.6886
22
  - R: 0.0017
@@ -52,28 +52,28 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Gen Len | P | R | F1 | Bleu-score | Bleu-precisions | Bleu-bp |
56
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:------:|:----------:|:----------------------------------------------------------------------------:|:-------:|
57
- | No log | 1.0 | 25 | 0.2037 | 19.0 | 0.6294 | -0.0269 | 0.2813 | 6.3902 | [90.98591549295774, 86.94893059799215, 85.21697663328564, 83.39464004203889] | 0.0738 |
58
- | No log | 2.0 | 50 | 0.1119 | 19.0 | 0.6534 | -0.0182 | 0.2969 | 6.6633 | [91.48340663734506, 88.55656697009103, 87.26928537624231, 85.72173006774362] | 0.0755 |
59
- | No log | 3.0 | 75 | 0.0774 | 19.0 | 0.6567 | -0.0197 | 0.2975 | 6.5982 | [91.85066238458451, 88.94209838920331, 87.68426058012363, 86.17077003666842] | 0.0744 |
60
- | No log | 4.0 | 100 | 0.0602 | 19.0 | 0.6594 | -0.0072 | 0.3059 | 6.4170 | [92.53246753246754, 90.04405286343612, 88.82466281310212, 87.35387885228481] | 0.0716 |
61
- | No log | 5.0 | 125 | 0.0512 | 19.0 | 0.6837 | -0.0031 | 0.3189 | 6.6446 | [94.31818181818181, 93.43612334801762, 92.4373795761079, 91.23273113708821] | 0.0716 |
62
- | No log | 6.0 | 150 | 0.0453 | 19.0 | 0.6788 | -0.0049 | 0.3157 | 6.6734 | [93.73484236054972, 92.54385964912281, 91.37104506232023, 89.95771670190275] | 0.0726 |
63
- | No log | 7.0 | 175 | 0.0403 | 19.0 | 0.6834 | -0.0015 | 0.3196 | 6.5922 | [94.62102689486552, 93.93805309734513, 93.17521781219749, 92.2542735042735] | 0.0705 |
64
- | No log | 8.0 | 200 | 0.0378 | 19.0 | 0.6831 | -0.0024 | 0.3190 | 6.5836 | [94.5802770986145, 93.84955752212389, 93.03000968054211, 92.0405982905983] | 0.0705 |
65
- | No log | 9.0 | 225 | 0.0350 | 19.0 | 0.6823 | 0.0016 | 0.3209 | 6.6472 | [94.54841334418226, 94.03710247349824, 93.47826086956522, 92.80383795309169] | 0.0709 |
66
- | No log | 10.0 | 250 | 0.0328 | 19.0 | 0.6845 | 0.0007 | 0.3214 | 6.6067 | [94.77977161500816, 94.28697962798937, 93.75, 93.10160427807487] | 0.0703 |
67
- | No log | 11.0 | 275 | 0.0320 | 19.0 | 0.6836 | 0.0011 | 0.3212 | 6.6270 | [94.66395112016293, 94.16187527642636, 93.61393323657475, 92.95248264815804] | 0.0706 |
68
- | No log | 12.0 | 300 | 0.0296 | 19.0 | 0.6848 | 0.0006 | 0.3214 | 6.5999 | [94.81844145246838, 94.32875498449269, 93.79544352884149, 93.151417870519] | 0.0702 |
69
- | No log | 13.0 | 325 | 0.0283 | 19.0 | 0.6846 | 0.0007 | 0.3214 | 6.6067 | [94.77977161500816, 94.28697962798937, 93.75, 93.10160427807487] | 0.0703 |
70
- | No log | 14.0 | 350 | 0.0274 | 19.0 | 0.6845 | 0.0007 | 0.3214 | 6.6067 | [94.77977161500816, 94.28697962798937, 93.75, 93.10160427807487] | 0.0703 |
71
- | No log | 15.0 | 375 | 0.0266 | 19.0 | 0.6846 | 0.0007 | 0.3214 | 6.6067 | [94.77977161500816, 94.28697962798937, 93.75, 93.10160427807487] | 0.0703 |
72
- | No log | 16.0 | 400 | 0.0260 | 19.0 | 0.6846 | 0.0007 | 0.3214 | 6.6067 | [94.77977161500816, 94.28697962798937, 93.75, 93.10160427807487] | 0.0703 |
73
- | No log | 17.0 | 425 | 0.0256 | 19.0 | 0.6846 | 0.0007 | 0.3214 | 6.6067 | [94.77977161500816, 94.28697962798937, 93.75, 93.10160427807487] | 0.0703 |
74
- | No log | 18.0 | 450 | 0.0255 | 19.0 | 0.6885 | 0.0018 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
75
- | No log | 19.0 | 475 | 0.0251 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
76
- | 0.1131 | 20.0 | 500 | 0.0250 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
77
 
78
 
79
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [Uzair54/test](https://huggingface.co/Uzair54/test) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0057
20
  - Gen Len: 19.0
21
  - P: 0.6886
22
  - R: 0.0017
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Gen Len | P | R | F1 | Bleu-score | Bleu-precisions | Bleu-bp |
56
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:------:|:----------:|:----------------------------------------------------------------------------:|:-------:|
57
+ | No log | 1.0 | 25 | 0.0251 | 19.0 | 0.6885 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
58
+ | No log | 2.0 | 50 | 0.0466 | 19.0 | 0.6885 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
59
+ | No log | 3.0 | 75 | 0.0277 | 19.0 | 0.6889 | 0.0016 | 0.3238 | 6.6660 | [94.99185667752442, 94.56233421750663, 94.05222437137331, 93.43649946638207] | 0.0707 |
60
+ | No log | 4.0 | 100 | 0.0188 | 19.0 | 0.6885 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
61
+ | No log | 5.0 | 125 | 0.0164 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
62
+ | No log | 6.0 | 150 | 0.0150 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
63
+ | No log | 7.0 | 175 | 0.0140 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
64
+ | No log | 8.0 | 200 | 0.0128 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
65
+ | No log | 9.0 | 225 | 0.0110 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
66
+ | No log | 10.0 | 250 | 0.0111 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
67
+ | No log | 11.0 | 275 | 0.0095 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
68
+ | No log | 12.0 | 300 | 0.0086 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
69
+ | No log | 13.0 | 325 | 0.0081 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
70
+ | No log | 14.0 | 350 | 0.0074 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
71
+ | No log | 15.0 | 375 | 0.0070 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
72
+ | No log | 16.0 | 400 | 0.0066 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
73
+ | No log | 17.0 | 425 | 0.0062 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
74
+ | No log | 18.0 | 450 | 0.0059 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
75
+ | No log | 19.0 | 475 | 0.0058 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
76
+ | 0.0237 | 20.0 | 500 | 0.0057 | 19.0 | 0.6886 | 0.0017 | 0.3237 | 6.6728 | [94.95319495319495, 94.52054794520548, 94.00676655389077, 93.38666666666667] | 0.0708 |
77
 
78
 
79
  ### Framework versions
runs/May11_18-20-45_fc664455b536/events.out.tfevents.1715451655.fc664455b536.24.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21a563fe1a34c4d1e8894897f8afba481809371ebe6176b8534fe6e5b17bc643
3
- size 16474
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3705cef590af803da306157418ff38de809b3b7d0131a162bb863f628e6d80ae
3
+ size 17391