Hugging Face's logo

RajuEEE
/
RewardModel

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
1
RajuEEE commited on
Commit
76f3db8
·
1 Parent(s): bc36b35

RajuEEE/RewardModel

Browse files
Files changed (3) hide show
  1. README.md +10 -8
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.5976
22
- - F1: 0.1404
23
- - Roc Auc: 0.525
24
- - Accuracy: 0.08
25
 
26
  ## Model description
27
 
@@ -46,15 +46,17 @@ The following hyperparameters were used during training:
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - num_epochs: 3
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
55
- | No log | 1.0 | 258 | 0.6350 | 0.0 | 0.5 | 0.0 |
56
- | 0.6342 | 2.0 | 516 | 0.6221 | 0.1391 | 0.5225 | 0.08 |
57
- | 0.6342 | 3.0 | 774 | 0.5976 | 0.1404 | 0.525 | 0.08 |
 
 
58
 
59
 
60
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.4309
22
+ - F1: 0.4988
23
+ - Roc Auc: 0.6238
24
+ - Accuracy: 0.495
25
 
26
  ## Model description
27
 
 
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 10
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
55
+ | 0.6271 | 1.94 | 500 | 0.6232 | 0.0099 | 0.5012 | 0.005 |
56
+ | 0.4933 | 3.88 | 1000 | 0.6828 | 0.4608 | 0.5975 | 0.445 |
57
+ | 0.2696 | 5.81 | 1500 | 1.0285 | 0.4612 | 0.5962 | 0.46 |
58
+ | 0.1273 | 7.75 | 2000 | 1.3377 | 0.48 | 0.61 | 0.48 |
59
+ | 0.0725 | 9.69 | 2500 | 1.4309 | 0.4988 | 0.6238 | 0.495 |
60
 
61
 
62
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c04090641a917ef04239cba54f51a3ee2a571744e28e90d00a95de87b2facd43
3
  size 438006577
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b76ddd53d559a03196ad3bfbc40d7cd5bd8aeb1ca67a6b0727ac422dfb99baf5
3
  size 438006577
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8407432b27f41c4a269c942b3a35ca262ac89070870d4d89dae7bf7d26aa87d1
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e35e505e567adf690a5feaa6c160b534c912783ff480d8432aff267cf37e64b8
3
  size 4027