Hugging Face's logo

Ghunghru
/
twhin-bert-base

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
Ghunghru commited on
Commit
557cb17
•
1 Parent(s): 398880e

End of training

Browse files
Files changed (3) hide show
  1. README.md +54 -24
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [Twitter/twhin-bert-base](https://huggingface.co/Twitter/twhin-bert-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.5691
21
- - F1: 0.3019
22
 
23
  ## Model description
24
 
@@ -37,38 +37,68 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 0.0002
41
  - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 20
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | F1 |
51
  |:-------------:|:-----:|:----:|:---------------:|:------:|
52
- | 0.6827 | 1.0 | 189 | 0.6385 | 0.0 |
53
- | 0.6734 | 2.0 | 378 | 0.6212 | 0.0 |
54
- | 0.6462 | 3.0 | 567 | 0.6068 | 0.0 |
55
- | 0.6299 | 4.0 | 756 | 0.6033 | 0.0 |
56
- | 0.6433 | 5.0 | 945 | 0.6148 | 0.2903 |
57
- | 0.6516 | 6.0 | 1134 | 0.5877 | 0.0 |
58
- | 0.6256 | 7.0 | 1323 | 0.5976 | 0.2881 |
59
- | 0.6344 | 8.0 | 1512 | 0.5870 | 0.3366 |
60
- | 0.6373 | 9.0 | 1701 | 0.5833 | 0.3137 |
61
- | 0.6375 | 10.0 | 1890 | 0.5780 | 0.3368 |
62
- | 0.6439 | 11.0 | 2079 | 0.5771 | 0.3168 |
63
- | 0.6235 | 12.0 | 2268 | 0.5703 | 0.3182 |
64
- | 0.604 | 13.0 | 2457 | 0.5854 | 0.304 |
65
- | 0.6432 | 14.0 | 2646 | 0.5697 | 0.3061 |
66
- | 0.6009 | 15.0 | 2835 | 0.5701 | 0.3048 |
67
- | 0.6118 | 16.0 | 3024 | 0.5736 | 0.2957 |
68
- | 0.6207 | 17.0 | 3213 | 0.5733 | 0.2957 |
69
- | 0.6357 | 18.0 | 3402 | 0.5701 | 0.2991 |
70
- | 0.621 | 19.0 | 3591 | 0.5689 | 0.3019 |
71
- | 0.6235 | 20.0 | 3780 | 0.5691 | 0.3019 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [Twitter/twhin-bert-base](https://huggingface.co/Twitter/twhin-bert-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.6341
21
+ - F1: 0.3077
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 2e-07
41
  - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 50
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | F1 |
51
  |:-------------:|:-----:|:----:|:---------------:|:------:|
52
+ | 0.6867 | 1.0 | 189 | 0.6817 | 0.1026 |
53
+ | 0.684 | 2.0 | 378 | 0.6746 | 0.0571 |
54
+ | 0.675 | 3.0 | 567 | 0.6649 | 0.0 |
55
+ | 0.6642 | 4.0 | 756 | 0.6577 | 0.0 |
56
+ | 0.6653 | 5.0 | 945 | 0.6542 | 0.0 |
57
+ | 0.6649 | 6.0 | 1134 | 0.6479 | 0.0 |
58
+ | 0.6648 | 7.0 | 1323 | 0.6460 | 0.0 |
59
+ | 0.6511 | 8.0 | 1512 | 0.6387 | 0.0 |
60
+ | 0.6535 | 9.0 | 1701 | 0.6332 | 0.0 |
61
+ | 0.6544 | 10.0 | 1890 | 0.6261 | 0.0 |
62
+ | 0.6382 | 11.0 | 2079 | 0.6154 | 0.0 |
63
+ | 0.6315 | 12.0 | 2268 | 0.6051 | 0.0 |
64
+ | 0.6231 | 13.0 | 2457 | 0.5957 | 0.2326 |
65
+ | 0.603 | 14.0 | 2646 | 0.5858 | 0.2326 |
66
+ | 0.6034 | 15.0 | 2835 | 0.5771 | 0.2553 |
67
+ | 0.5938 | 16.0 | 3024 | 0.5694 | 0.2308 |
68
+ | 0.5884 | 17.0 | 3213 | 0.5642 | 0.3103 |
69
+ | 0.5763 | 18.0 | 3402 | 0.5611 | 0.3103 |
70
+ | 0.5675 | 19.0 | 3591 | 0.5641 | 0.2857 |
71
+ | 0.5672 | 20.0 | 3780 | 0.5598 | 0.3000 |
72
+ | 0.5674 | 21.0 | 3969 | 0.5579 | 0.2857 |
73
+ | 0.5479 | 22.0 | 4158 | 0.5642 | 0.3125 |
74
+ | 0.5621 | 23.0 | 4347 | 0.5688 | 0.2903 |
75
+ | 0.5516 | 24.0 | 4536 | 0.5685 | 0.3077 |
76
+ | 0.5597 | 25.0 | 4725 | 0.5713 | 0.3077 |
77
+ | 0.5418 | 26.0 | 4914 | 0.5761 | 0.3077 |
78
+ | 0.5477 | 27.0 | 5103 | 0.5752 | 0.3030 |
79
+ | 0.535 | 28.0 | 5292 | 0.5876 | 0.3077 |
80
+ | 0.5544 | 29.0 | 5481 | 0.5841 | 0.3030 |
81
+ | 0.5238 | 30.0 | 5670 | 0.5855 | 0.3030 |
82
+ | 0.5375 | 31.0 | 5859 | 0.5894 | 0.3030 |
83
+ | 0.5092 | 32.0 | 6048 | 0.5985 | 0.3077 |
84
+ | 0.5262 | 33.0 | 6237 | 0.5988 | 0.3077 |
85
+ | 0.5418 | 34.0 | 6426 | 0.6038 | 0.3077 |
86
+ | 0.531 | 35.0 | 6615 | 0.6087 | 0.3077 |
87
+ | 0.5627 | 36.0 | 6804 | 0.6064 | 0.3077 |
88
+ | 0.545 | 37.0 | 6993 | 0.6110 | 0.3077 |
89
+ | 0.5105 | 38.0 | 7182 | 0.6134 | 0.3077 |
90
+ | 0.5471 | 39.0 | 7371 | 0.6111 | 0.3077 |
91
+ | 0.5114 | 40.0 | 7560 | 0.6212 | 0.3077 |
92
+ | 0.5411 | 41.0 | 7749 | 0.6159 | 0.3077 |
93
+ | 0.5304 | 42.0 | 7938 | 0.6213 | 0.3077 |
94
+ | 0.5146 | 43.0 | 8127 | 0.6276 | 0.3077 |
95
+ | 0.5223 | 44.0 | 8316 | 0.6301 | 0.3077 |
96
+ | 0.5345 | 45.0 | 8505 | 0.6281 | 0.3077 |
97
+ | 0.5368 | 46.0 | 8694 | 0.6284 | 0.3077 |
98
+ | 0.516 | 47.0 | 8883 | 0.6320 | 0.3077 |
99
+ | 0.5241 | 48.0 | 9072 | 0.6339 | 0.3077 |
100
+ | 0.5267 | 49.0 | 9261 | 0.6342 | 0.3077 |
101
+ | 0.5478 | 50.0 | 9450 | 0.6341 | 0.3077 |
102
 
103
 
104
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:723633affb4d2f4f692efcf15e03085813ce0f4d5f79f2c001b1590a362161ba
3
  size 1115393438
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20666631abf3cf59a3c223ef20d8168c68fef3e4d7f3b1f59bc557549865c1e4
3
  size 1115393438
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3de5528471e131f424915bd06548ac5d69114bc8df74648e5d6dbadaf9f41727
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60e156060f4ac3e2c0b13ab7d5fa1833871aa767cd48b2b96634194be815d175
3
  size 4600