Hugging Face's logo

ashishbaraiya
/
my-tweets-finetuned

Text Generation
Transformers
TensorFlow
gpt2
generated_from_keras_callback
Inference Endpoints
Model card Files Community
ashishbaraiya commited on
Commit
aa80ef1
·
1 Parent(s): 1615f89

Training in progress epoch 14

Browse files
Files changed (2) hide show
  1. README.md +7 -3
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 1.8213
19
- - Validation Loss: 3.8208
20
- - Epoch: 10
21
 
22
  ## Model description
23
 
@@ -54,6 +54,10 @@ The following hyperparameters were used during training:
54
  | 2.4261 | 4.0802 | 8 |
55
  | 2.0691 | 3.8920 | 9 |
56
  | 1.8213 | 3.8208 | 10 |
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 1.0135
19
+ - Validation Loss: 3.2981
20
+ - Epoch: 14
21
 
22
  ## Model description
23
 
 
54
  | 2.4261 | 4.0802 | 8 |
55
  | 2.0691 | 3.8920 | 9 |
56
  | 1.8213 | 3.8208 | 10 |
57
+ | 1.5922 | 3.6103 | 11 |
58
+ | 1.3694 | 3.5038 | 12 |
59
+ | 1.1764 | 3.3149 | 13 |
60
+ | 1.0135 | 3.2981 | 14 |
61
 
62
 
63
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18a7fa3c2fa2e715142f59181052a41e5fea68710f273eeeb5f6e43b693aa0a4
3
  size 497935440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df5b8735d754090149229b4a8e69a4e35d89618009a59705aa1777992a70b574
3
  size 497935440