Hugging Face's logo

BogdanTurbal
/
model_gpt2_large_d_gender_bias_hate_bias_ep_1_a_sqn_a_b_p_100_3_v_9

Safetensors
gpt2
Generated from Trainer
Model card Files Community
BogdanTurbal commited on
Commit
f5381b3
•
1 Parent(s): eb0d2b9

End of training

Browse files
Files changed (3) hide show
  1. README.md +14 -14
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -17,16 +17,16 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [BogdanTurbal/model_gpt2_large_d_gender_bias_ep_1_sqn_a_p_100_v_9](https://huggingface.co/BogdanTurbal/model_gpt2_large_d_gender_bias_ep_1_sqn_a_p_100_v_9) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.7395
21
- - Balanced Accuracy: 0.8199
22
- - Accuracy: 0.8199
23
- - F1 Micro: 0.8199
24
- - F1 Macro: 0.8199
25
- - Precision Micro: 0.8199
26
- - Precision Macro: 0.8199
27
- - Recall Micro: 0.8199
28
- - Recall Macro: 0.8199
29
- - Auc: 0.9052
30
 
31
  ## Model description
32
 
@@ -57,10 +57,10 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Balanced Accuracy | Accuracy | F1 Micro | F1 Macro | Precision Micro | Precision Macro | Recall Micro | Recall Macro | Auc |
59
  |:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------:|:--------:|:--------:|:---------------:|:---------------:|:------------:|:------------:|:------:|
60
- | 0.7497 | 1.0 | 46 | 0.4263 | 0.8092 | 0.8092 | 0.8092 | 0.8090 | 0.8092 | 0.8104 | 0.8092 | 0.8092 | 0.8927 |
61
- | 0.1717 | 2.0 | 92 | 0.5743 | 0.8174 | 0.8174 | 0.8174 | 0.8174 | 0.8174 | 0.8179 | 0.8174 | 0.8174 | 0.9053 |
62
- | 0.0239 | 3.0 | 138 | 0.7343 | 0.8191 | 0.8191 | 0.8191 | 0.8190 | 0.8191 | 0.8199 | 0.8191 | 0.8191 | 0.9054 |
63
- | 0.0011 | 4.0 | 184 | 0.7395 | 0.8199 | 0.8199 | 0.8199 | 0.8199 | 0.8199 | 0.8199 | 0.8199 | 0.8199 | 0.9052 |
64
 
65
 
66
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [BogdanTurbal/model_gpt2_large_d_gender_bias_ep_1_sqn_a_p_100_v_9](https://huggingface.co/BogdanTurbal/model_gpt2_large_d_gender_bias_ep_1_sqn_a_p_100_v_9) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.7180
21
+ - Balanced Accuracy: 0.8363
22
+ - Accuracy: 0.8363
23
+ - F1 Micro: 0.8363
24
+ - F1 Macro: 0.8363
25
+ - Precision Micro: 0.8363
26
+ - Precision Macro: 0.8366
27
+ - Recall Micro: 0.8363
28
+ - Recall Macro: 0.8363
29
+ - Auc: 0.9169
30
 
31
  ## Model description
32
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Balanced Accuracy | Accuracy | F1 Micro | F1 Macro | Precision Micro | Precision Macro | Recall Micro | Recall Macro | Auc |
59
  |:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------:|:--------:|:--------:|:---------------:|:---------------:|:------------:|:------------:|:------:|
60
+ | 0.5712 | 1.0 | 46 | 0.4163 | 0.8289 | 0.8289 | 0.8289 | 0.8278 | 0.8289 | 0.8377 | 0.8289 | 0.8289 | 0.9142 |
61
+ | 0.1823 | 2.0 | 92 | 0.5700 | 0.8396 | 0.8396 | 0.8396 | 0.8395 | 0.8396 | 0.8406 | 0.8396 | 0.8396 | 0.9170 |
62
+ | 0.0346 | 3.0 | 138 | 0.6745 | 0.8355 | 0.8355 | 0.8355 | 0.8355 | 0.8355 | 0.8358 | 0.8355 | 0.8355 | 0.9179 |
63
+ | 0.0039 | 4.0 | 184 | 0.7180 | 0.8363 | 0.8363 | 0.8363 | 0.8363 | 0.8363 | 0.8366 | 0.8363 | 0.8363 | 0.9169 |
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e1cdd45fc10cb2d209461358b90ff84d03862e0d031dfd8c92b0dc8ecc90ccf
3
  size 3096176248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44d6418033a6af3b893d470e40f88b4945a29977785ad7e83d6d1a13a4fb76b4
3
  size 3096176248
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c00c7e889c07a14fef9dcbc06452dc7466a6d71846832269936d02baec58197e
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcc388e8b31eeb3b955b077e8773d27da26fd7fc3f7a6620b24d5f540fddd34e
3
  size 5240