Hugging Face's logo

JanSt
/
gbert-base-finetuned-twitter

Fill-Mask
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
JanSt commited on
Commit
0f3faa3
•
1 Parent(s): 804fa1c

End of training

Browse files
Files changed (2) hide show
  1. README.md +16 -26
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [deepset/gbert-base](https://huggingface.co/deepset/gbert-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 2.4845
19
 
20
  ## Model description
21
 
@@ -35,37 +35,27 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 2e-05
38
- - train_batch_size: 64
39
- - eval_batch_size: 64
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 20
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss |
48
- |:-------------:|:-----:|:----:|:---------------:|
49
- | 3.4514 | 1.0 | 17 | 2.7126 |
50
- | 2.8858 | 2.0 | 34 | 2.2124 |
51
- | 2.6941 | 3.0 | 51 | 2.7717 |
52
- | 2.704 | 4.0 | 68 | 2.8004 |
53
- | 2.5674 | 5.0 | 85 | 2.9648 |
54
- | 2.4679 | 6.0 | 102 | 2.3775 |
55
- | 2.4074 | 7.0 | 119 | 2.2347 |
56
- | 2.4651 | 8.0 | 136 | 2.6914 |
57
- | 2.3944 | 9.0 | 153 | 2.1919 |
58
- | 2.4347 | 10.0 | 170 | 2.5820 |
59
- | 2.4214 | 11.0 | 187 | 2.6333 |
60
- | 2.3458 | 12.0 | 204 | 2.4690 |
61
- | 2.3471 | 13.0 | 221 | 2.1549 |
62
- | 2.3521 | 14.0 | 238 | 2.8202 |
63
- | 2.4039 | 15.0 | 255 | 3.3286 |
64
- | 2.3449 | 16.0 | 272 | 2.4369 |
65
- | 2.329 | 17.0 | 289 | 2.1589 |
66
- | 2.3293 | 18.0 | 306 | 1.9620 |
67
- | 2.2919 | 19.0 | 323 | 2.3828 |
68
- | 2.3209 | 20.0 | 340 | 2.2413 |
69
 
70
 
71
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [deepset/gbert-base](https://huggingface.co/deepset/gbert-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.7380
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 2e-05
38
+ - train_batch_size: 192
39
+ - eval_batch_size: 192
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 10
44
 
45
  ### Training results
46
 
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 2.194 | 1.0 | 4180 | 1.9622 |
50
+ | 2.0075 | 2.0 | 8360 | 1.8813 |
51
+ | 1.9429 | 3.0 | 12540 | 1.8339 |
52
+ | 1.8985 | 4.0 | 16720 | 1.8057 |
53
+ | 1.8676 | 5.0 | 20900 | 1.7801 |
54
+ | 1.8446 | 6.0 | 25080 | 1.7793 |
55
+ | 1.829 | 7.0 | 29260 | 1.7580 |
56
+ | 1.815 | 8.0 | 33440 | 1.7445 |
57
+ | 1.8048 | 9.0 | 37620 | 1.7319 |
58
+ | 1.7997 | 10.0 | 41800 | 1.7331 |
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf9f5edb727e1890549a8a4d5f0275931e99ed83b2cdfb3b7f28354d5de0adc3
3
  size 439910197
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0604bd380fbb188c63bdb9399fc10d4b64eb1cfb21490556cf896ba1f2a74af
3
  size 439910197