Hugging Face's logo

armahlovis
/
English2AkuapemTwi

Text2Text Generation
Transformers
PyTorch
TensorBoard
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
armahlovis commited on
Commit
aeb1b92
·
1 Parent(s): b39c43a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -24
README.md CHANGED
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [allenai/unifiedqa-t5-small](https://huggingface.co/allenai/unifiedqa-t5-small) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.4994
19
- - Bleu: 6.0293
20
- - Gen Len: 17.7366
21
 
22
  ## Model description
23
 
@@ -42,33 +42,43 @@ The following hyperparameters were used during training:
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 20
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
51
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
52
- | 2.8191 | 1.0 | 2542 | 2.5415 | 0.1546 | 18.9225 |
53
- | 2.5142 | 2.0 | 5084 | 2.2608 | 0.6935 | 18.7 |
54
- | 2.3329 | 3.0 | 7626 | 2.0914 | 1.0787 | 18.4717 |
55
- | 2.2235 | 4.0 | 10168 | 1.9743 | 1.581 | 18.3826 |
56
- | 2.1334 | 5.0 | 12710 | 1.8892 | 2.2749 | 18.1357 |
57
- | 2.0768 | 6.0 | 15252 | 1.8205 | 2.8561 | 17.941 |
58
- | 2.002 | 7.0 | 17794 | 1.7674 | 3.3599 | 17.9369 |
59
- | 1.9435 | 8.0 | 20336 | 1.7185 | 3.6487 | 17.9559 |
60
- | 1.8942 | 9.0 | 22878 | 1.6762 | 4.078 | 17.9443 |
61
- | 1.8609 | 10.0 | 25420 | 1.6416 | 4.4184 | 17.9453 |
62
- | 1.8462 | 11.0 | 27962 | 1.6123 | 4.7925 | 17.8511 |
63
- | 1.8036 | 12.0 | 30504 | 1.5870 | 5.0708 | 17.831 |
64
- | 1.7719 | 13.0 | 33046 | 1.5659 | 5.2373 | 17.7354 |
65
- | 1.7639 | 14.0 | 35588 | 1.5457 | 5.424 | 17.8385 |
66
- | 1.7486 | 15.0 | 38130 | 1.5316 | 5.5994 | 17.8004 |
67
- | 1.7293 | 16.0 | 40672 | 1.5204 | 5.7504 | 17.7288 |
68
- | 1.7257 | 17.0 | 43214 | 1.5109 | 5.8862 | 17.7461 |
69
- | 1.7077 | 18.0 | 45756 | 1.5045 | 5.9447 | 17.7518 |
70
- | 1.6986 | 19.0 | 48298 | 1.5006 | 6.0469 | 17.7217 |
71
- | 1.6967 | 20.0 | 50840 | 1.4994 | 6.0293 | 17.7366 |
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [allenai/unifiedqa-t5-small](https://huggingface.co/allenai/unifiedqa-t5-small) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.3098
19
+ - Bleu: 8.8875
20
+ - Gen Len: 17.5114
21
 
22
  ## Model description
23
 
 
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 30
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
51
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
52
+ | 2.8304 | 1.0 | 2542 | 2.5363 | 0.2404 | 18.9072 |
53
+ | 2.5079 | 2.0 | 5084 | 2.2533 | 0.5763 | 18.6814 |
54
+ | 2.3362 | 3.0 | 7626 | 2.0838 | 0.8836 | 18.4972 |
55
+ | 2.2155 | 4.0 | 10168 | 1.9649 | 1.3748 | 18.2368 |
56
+ | 2.1066 | 5.0 | 12710 | 1.8767 | 2.0954 | 18.0588 |
57
+ | 2.0368 | 6.0 | 15252 | 1.8057 | 2.6294 | 17.9451 |
58
+ | 1.9641 | 7.0 | 17794 | 1.7436 | 3.0267 | 17.8342 |
59
+ | 1.9194 | 8.0 | 20336 | 1.6907 | 3.4947 | 18.0199 |
60
+ | 1.8474 | 9.0 | 22878 | 1.6438 | 4.0431 | 17.7758 |
61
+ | 1.8261 | 10.0 | 25420 | 1.6008 | 4.4608 | 17.7919 |
62
+ | 1.7833 | 11.0 | 27962 | 1.5642 | 4.9271 | 17.7868 |
63
+ | 1.7255 | 12.0 | 30504 | 1.5322 | 5.3659 | 17.7962 |
64
+ | 1.6913 | 13.0 | 33046 | 1.5020 | 5.9051 | 17.7301 |
65
+ | 1.6616 | 14.0 | 35588 | 1.4780 | 6.0824 | 17.7217 |
66
+ | 1.6522 | 15.0 | 38130 | 1.4550 | 6.6326 | 17.6227 |
67
+ | 1.6039 | 16.0 | 40672 | 1.4327 | 6.7955 | 17.6564 |
68
+ | 1.5926 | 17.0 | 43214 | 1.4119 | 7.0477 | 17.6876 |
69
+ | 1.5802 | 18.0 | 45756 | 1.3960 | 7.4328 | 17.6233 |
70
+ | 1.5438 | 19.0 | 48298 | 1.3816 | 7.4937 | 17.6359 |
71
+ | 1.5452 | 20.0 | 50840 | 1.3695 | 7.7696 | 17.5515 |
72
+ | 1.5423 | 21.0 | 53382 | 1.3569 | 7.9677 | 17.5596 |
73
+ | 1.5076 | 22.0 | 55924 | 1.3465 | 8.2829 | 17.5193 |
74
+ | 1.5183 | 23.0 | 58466 | 1.3386 | 8.4304 | 17.5486 |
75
+ | 1.4919 | 24.0 | 61008 | 1.3296 | 8.536 | 17.5714 |
76
+ | 1.4923 | 25.0 | 63550 | 1.3242 | 8.6446 | 17.4343 |
77
+ | 1.488 | 26.0 | 66092 | 1.3177 | 8.7099 | 17.5126 |
78
+ | 1.477 | 27.0 | 68634 | 1.3144 | 8.8431 | 17.5035 |
79
+ | 1.4724 | 28.0 | 71176 | 1.3116 | 8.8588 | 17.5277 |
80
+ | 1.4488 | 29.0 | 73718 | 1.3105 | 8.8989 | 17.5024 |
81
+ | 1.4837 | 30.0 | 76260 | 1.3098 | 8.8875 | 17.5114 |
82
 
83
 
84
  ### Framework versions