Hugging Face's logo

hamzagorgulu
/
alarm_prediction_tokenizer3

Text Generation
Transformers
TensorFlow
gpt2
generated_from_keras_callback
text-generation-inference
Inference Endpoints
Model card Files Community
hamzagorgulu commited on
Commit
f4a587f
•
1 Parent(s): 5cd7229

Upload model

Browse files
Files changed (2) hide show
  1. README.md +9 -6
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,9 +14,9 @@ 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: 2.8575
18
- - Validation Loss: 2.2917
19
- - Epoch: 2
20
 
21
  ## Model description
22
 
@@ -42,9 +42,12 @@ The following hyperparameters were used during training:
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
- | 5.6081 | 4.2247 | 0 |
46
- | 3.7293 | 3.0492 | 1 |
47
- | 2.8575 | 2.2917 | 2 |
 
 
 
48
 
49
 
50
  ### 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: 0.6252
18
+ - Validation Loss: 0.5814
19
+ - Epoch: 5
20
 
21
  ## Model description
22
 
 
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
+ | 1.9339 | 1.3070 | 0 |
46
+ | 1.1890 | 0.9436 | 1 |
47
+ | 0.9039 | 0.7802 | 2 |
48
+ | 0.7734 | 0.6915 | 3 |
49
+ | 0.6879 | 0.6274 | 4 |
50
+ | 0.6252 | 0.5814 | 5 |
51
 
52
 
53
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43a25d8edf0d53d31f584fd60d9e44ffb5f7d7792f9661e68b3c0b2c20856039
3
  size 344909928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a89f883fe5bc4d7547d5eff3fc0ebf3d4ff6febdbbac904135eaa982858e2669
3
  size 344909928