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
172e450
·
1 Parent(s): c20b291

Training in progress epoch 19

Browse files
Files changed (2) hide show
  1. README.md +4 -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: 0.5770
19
- - Validation Loss: 3.2517
20
- - Epoch: 18
21
 
22
  ## Model description
23
 
@@ -62,6 +62,7 @@ The following hyperparameters were used during training:
62
  | 0.7716 | 3.2103 | 16 |
63
  | 0.6679 | 3.3297 | 17 |
64
  | 0.5770 | 3.2517 | 18 |
 
65
 
66
 
67
  ### 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: 0.5098
19
+ - Validation Loss: 3.0959
20
+ - Epoch: 19
21
 
22
  ## Model description
23
 
 
62
  | 0.7716 | 3.2103 | 16 |
63
  | 0.6679 | 3.3297 | 17 |
64
  | 0.5770 | 3.2517 | 18 |
65
+ | 0.5098 | 3.0959 | 19 |
66
 
67
 
68
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe66722492bb3658d8e9911968d2a88be2909dd6ef63301029aab4a936dde3f4
3
  size 497935440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bee494929f83b9694f7820999ac6b356c4a09ea7e2a0f8c35b95addcb43a51a5
3
  size 497935440