Hugging Face's logo

node-py
/
my_awesome_eli5_clm-model

TensorFlow
bert
generated_from_keras_callback
Model card Files Community
node-py commited on
Commit
21a5acd
·
1 Parent(s): 818db10

Training in progress epoch 3

Browse files
Files changed (2) hide show
  1. README.md +4 -3
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -16,9 +16,9 @@ probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Train Loss: 2.0092
20
- - Validation Loss: 1.9229
21
- - Epoch: 2
22
 
23
  ## Model description
24
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
47
  | 2.0816 | 1.9831 | 0 |
48
  | 2.0425 | 1.9519 | 1 |
49
  | 2.0092 | 1.9229 | 2 |
 
50
 
51
 
52
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Train Loss: 1.9794
20
+ - Validation Loss: 1.9025
21
+ - Epoch: 3
22
 
23
  ## Model description
24
 
 
47
  | 2.0816 | 1.9831 | 0 |
48
  | 2.0425 | 1.9519 | 1 |
49
  | 2.0092 | 1.9229 | 2 |
50
+ | 1.9794 | 1.9025 | 3 |
51
 
52
 
53
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ec2bb8e74d028f1551d1884735d855b115a5ed652a7b38ea20e6ad81c54df49
3
  size 327745472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba52bd188fc0cb2ee757ec2fd66432ada8f0f089b3036881abdbc2bc6cd47ff
3
  size 327745472