Hugging Face's logo

bradmin
/
reward-gpt

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
gpt_neox
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
bradmin commited on
Commit
9b69c4d
·
1 Parent(s): 53f6455

Model save

Browse files
Files changed (2) hide show
  1. README.md +11 -13
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -1,5 +1,6 @@
1
  ---
2
- base_model: klue/roberta-large
 
3
  tags:
4
  - generated_from_trainer
5
  metrics:
@@ -14,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # reward-gpt
16
 
17
- This model is a fine-tuned version of [klue/roberta-large](https://huggingface.co/klue/roberta-large) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
  - Loss: 0.0000
20
- - Accuracy: 0.0
21
 
22
  ## Model description
23
 
@@ -37,11 +38,11 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 9e-06
40
- - train_batch_size: 6
41
- - eval_batch_size: 6
42
  - seed: 2023
43
- - gradient_accumulation_steps: 10
44
- - total_train_batch_size: 60
45
  - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
46
  - lr_scheduler_type: cosine
47
  - num_epochs: 1
@@ -50,12 +51,9 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 0.0808 | 0.15 | 100 | 0.0000 | 0.0 |
54
- | 0.0682 | 0.3 | 200 | 0.0000 | 0.0 |
55
- | 0.0718 | 0.46 | 300 | 0.0000 | 0.0 |
56
- | 0.0579 | 0.61 | 400 | 0.0000 | 0.0 |
57
- | 0.0557 | 0.76 | 500 | 0.0000 | 0.0 |
58
- | 0.0458 | 0.91 | 600 | 0.0000 | 0.0 |
59
 
60
 
61
  ### Framework versions
 
1
  ---
2
+ license: apache-2.0
3
+ base_model: EleutherAI/polyglot-ko-1.3b
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
15
 
16
  # reward-gpt
17
 
18
+ This model is a fine-tuned version of [EleutherAI/polyglot-ko-1.3b](https://huggingface.co/EleutherAI/polyglot-ko-1.3b) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.0000
21
+ - Accuracy: 0.5
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 9e-06
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
  - seed: 2023
44
+ - gradient_accumulation_steps: 8
45
+ - total_train_batch_size: 64
46
  - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
47
  - lr_scheduler_type: cosine
48
  - num_epochs: 1
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 0.1029 | 0.25 | 100 | 0.0000 | 0.5 |
55
+ | 0.0836 | 0.5 | 200 | 0.0000 | 0.5 |
56
+ | 0.0772 | 0.75 | 300 | 0.0000 | 0.5 |
 
 
 
57
 
58
 
59
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5a038be930d7e4b9c06380cca5c12b961950b685498eb1df7b7188f4af6c5ba
3
  size 5080945162
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aac08b0078cb2fdd9289144e195da94484338161874b90d5245b7839daa3213
3
  size 5080945162