Hugging Face's logo

soumya13
/
GPT2_CleanDesc_MAKE_v3.0

Text Classification
Transformers
TensorFlow
gpt2
generated_from_keras_callback
Model card Files
xet
Community
1
soumya13 commited on
Commit
c4db142
·
1 Parent(s): fe618e9

Training in progress epoch 16

Browse files
Files changed (2) hide show
  1. README.md +6 -3
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.1495
18
- - Validation Loss: 0.6048
19
  - Train Accuracy: 0.8974
20
- - Epoch: 13
21
 
22
  ## Model description
23
 
@@ -57,6 +57,9 @@ The following hyperparameters were used during training:
57
  | 0.1663 | 0.5285 | 0.8718 | 11 |
58
  | 0.1589 | 0.6002 | 0.8718 | 12 |
59
  | 0.1495 | 0.6048 | 0.8974 | 13 |
 
 
 
60
 
61
 
62
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.0582
18
+ - Validation Loss: 0.5317
19
  - Train Accuracy: 0.8974
20
+ - Epoch: 16
21
 
22
  ## Model description
23
 
 
57
  | 0.1663 | 0.5285 | 0.8718 | 11 |
58
  | 0.1589 | 0.6002 | 0.8718 | 12 |
59
  | 0.1495 | 0.6048 | 0.8974 | 13 |
60
+ | 0.1131 | 0.5759 | 0.8462 | 14 |
61
+ | 0.1051 | 0.5339 | 0.8718 | 15 |
62
+ | 0.0582 | 0.5317 | 0.8974 | 16 |
63
 
64
 
65
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e8a92bfba24cd5595d55c338f6d4e006c6187cc900563a1de34adea3458253a
3
  size 497983984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cef42a7b57111ab36908468ce770e6d648e4197abe457a1d9914a1ecf4a89d4
3
  size 497983984