Hugging Face's logo

Geo
/
gpt2_custom_c_q_and_a

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
1
Geo commited on
Commit
6ffd94c
·
1 Parent(s): c3bd0e1

Model save

Browse files
Files changed (2) hide show
  1. README.md +17 -7
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [lighteternal/gpt2-finetuned-greek](https://huggingface.co/lighteternal/gpt2-finetuned-greek) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0467
19
 
20
  ## Model description
21
 
@@ -41,18 +41,28 @@ The following hyperparameters were used during training:
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 100
44
- - num_epochs: 30
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
  | 2.5542 | 4.76 | 100 | 0.7706 |
51
- | 0.4862 | 9.52 | 200 | 0.1913 |
52
- | 0.1955 | 14.29 | 300 | 0.0978 |
53
- | 0.1228 | 19.05 | 400 | 0.0660 |
54
- | 0.0934 | 23.81 | 500 | 0.0527 |
55
- | 0.0792 | 28.57 | 600 | 0.0467 |
 
 
 
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [lighteternal/gpt2-finetuned-greek](https://huggingface.co/lighteternal/gpt2-finetuned-greek) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0098
19
 
20
  ## Model description
21
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 100
44
+ - num_epochs: 80
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
  | 2.5542 | 4.76 | 100 | 0.7706 |
51
+ | 0.4813 | 9.52 | 200 | 0.1839 |
52
+ | 0.1838 | 14.29 | 300 | 0.0892 |
53
+ | 0.109 | 19.05 | 400 | 0.0532 |
54
+ | 0.0767 | 23.81 | 500 | 0.0385 |
55
+ | 0.0579 | 28.57 | 600 | 0.0290 |
56
+ | 0.0447 | 33.33 | 700 | 0.0213 |
57
+ | 0.0365 | 38.1 | 800 | 0.0178 |
58
+ | 0.0319 | 42.86 | 900 | 0.0157 |
59
+ | 0.0277 | 47.62 | 1000 | 0.0140 |
60
+ | 0.0252 | 52.38 | 1100 | 0.0125 |
61
+ | 0.0229 | 57.14 | 1200 | 0.0113 |
62
+ | 0.0213 | 61.9 | 1300 | 0.0107 |
63
+ | 0.0199 | 66.67 | 1400 | 0.0104 |
64
+ | 0.0181 | 71.43 | 1500 | 0.0099 |
65
+ | 0.0184 | 76.19 | 1600 | 0.0098 |
66
 
67
 
68
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1d98cbf36ba5db5683659e376f263295bb39c1d0708a4e4df80dacc9d5704d2
3
  size 497807197
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:221faa826af4a9500393f544bb1fd9ba047fbcf869fbc62ea81ebf8875e9fd41
3
  size 497807197