Hugging Face's logo

thombrysmith
/
judge_JuDe

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
thombrysmith commited on
Commit
1920b58
•
1 Parent(s): fe59c77

thombrysmith/judge_JuDe

Browse files
Files changed (3) hide show
  1. README.md +22 -9
  2. pytorch_model.bin +2 -2
  3. training_args.bin +2 -2
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 [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 2.4527
19
 
20
  ## Model description
21
 
@@ -35,25 +35,38 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 2e-05
38
- - train_batch_size: 8
39
- - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 3.0
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:-----:|:---------------:|
49
- | 2.6296 | 1.0 | 16501 | 2.5378 |
50
- | 2.5295 | 2.0 | 33002 | 2.4721 |
51
- | 2.4953 | 3.0 | 49503 | 2.4527 |
 
 
 
 
 
 
 
 
 
 
 
 
 
52
 
53
 
54
  ### Framework versions
55
 
56
  - Transformers 4.34.1
57
- - Pytorch 2.0.1+cu118
58
- - Datasets 2.14.6
59
  - Tokenizers 0.14.1
 
15
 
16
  This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 2.4628
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 2e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 4
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 2.9881 | 0.25 | 2057 | 2.7543 |
50
+ | 2.803 | 0.5 | 4114 | 2.6652 |
51
+ | 2.7298 | 0.75 | 6171 | 2.6124 |
52
+ | 2.687 | 1.0 | 8228 | 2.5772 |
53
+ | 2.6374 | 1.25 | 10285 | 2.5535 |
54
+ | 2.6161 | 1.5 | 12342 | 2.5332 |
55
+ | 2.598 | 1.75 | 14399 | 2.5171 |
56
+ | 2.5773 | 2.0 | 16456 | 2.5050 |
57
+ | 2.5578 | 2.25 | 18513 | 2.4943 |
58
+ | 2.5468 | 2.5 | 20570 | 2.4868 |
59
+ | 2.5385 | 2.75 | 22627 | 2.4783 |
60
+ | 2.5322 | 3.0 | 24684 | 2.4712 |
61
+ | 2.5182 | 3.25 | 26741 | 2.4697 |
62
+ | 2.5188 | 3.5 | 28798 | 2.4657 |
63
+ | 2.513 | 3.75 | 30855 | 2.4630 |
64
+ | 2.5123 | 4.0 | 32912 | 2.4628 |
65
 
66
 
67
  ### Framework versions
68
 
69
  - Transformers 4.34.1
70
+ - Pytorch 1.12.1+cu113
71
+ - Datasets 2.8.0
72
  - Tokenizers 0.14.1
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7f7eaa0f1cb9e0b49af8e98305932eaa8ec64a3f6fb352f19630c69cc59dc48
3
- size 327674773
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:957be5179bae17161922d368beb149dc5e8ce6185b3e8e8f01ba72740420e4ed
3
+ size 327673729
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffa3efa4a3ea05d37a385efcc21b4223741370e32e37732d42a827b83384135d
3
- size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ce6e17bf669e999658e1f754699bdf891652eed22ed70d9c9811a3561f7546
3
+ size 4015