Hugging Face's logo

Kuongan
/
CS221-xlnet-large-cased-finetuned-semeval-NT

Text Classification
Transformers
Safetensors
xlnet
Generated from Trainer
Inference Endpoints
Model card Files Community
Kuongan commited on
Commit
1a1e074
·
verified ·
1 Parent(s): 7335931

Training completed!

Browse files
Files changed (2) hide show
  1. README.md +19 -15
  2. model.safetensors +1 -1
README.md CHANGED
@@ -19,10 +19,10 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [xlnet-large-cased](https://huggingface.co/xlnet-large-cased) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.5455
23
- - F1: 0.7320
24
- - Roc Auc: 0.7940
25
- - Accuracy: 0.4783
26
 
27
  ## Model description
28
 
@@ -42,8 +42,8 @@ More information needed
42
 
43
  The following hyperparameters were used during training:
44
  - learning_rate: 2e-05
45
- - train_batch_size: 8
46
- - eval_batch_size: 8
47
  - seed: 42
48
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
  - lr_scheduler_type: cosine
@@ -54,15 +54,19 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
57
- | 0.4898 | 1.0 | 277 | 0.4345 | 0.4886 | 0.6537 | 0.3213 |
58
- | 0.3807 | 2.0 | 554 | 0.3681 | 0.6681 | 0.7551 | 0.4296 |
59
- | 0.265 | 3.0 | 831 | 0.3890 | 0.6765 | 0.7615 | 0.4693 |
60
- | 0.1741 | 4.0 | 1108 | 0.4131 | 0.7120 | 0.7878 | 0.4404 |
61
- | 0.0835 | 5.0 | 1385 | 0.4718 | 0.7303 | 0.7978 | 0.4765 |
62
- | 0.0798 | 6.0 | 1662 | 0.5455 | 0.7320 | 0.7940 | 0.4783 |
63
- | 0.0533 | 7.0 | 1939 | 0.6251 | 0.6976 | 0.7679 | 0.4386 |
64
- | 0.032 | 8.0 | 2216 | 0.6953 | 0.7158 | 0.7885 | 0.4549 |
65
- | 0.0179 | 9.0 | 2493 | 0.7133 | 0.7313 | 0.7984 | 0.4513 |
 
 
 
 
66
 
67
 
68
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [xlnet-large-cased](https://huggingface.co/xlnet-large-cased) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.6052
23
+ - F1: 0.7508
24
+ - Roc Auc: 0.8048
25
+ - Accuracy: 0.4946
26
 
27
  ## Model description
28
 
 
42
 
43
  The following hyperparameters were used during training:
44
  - learning_rate: 2e-05
45
+ - train_batch_size: 16
46
+ - eval_batch_size: 16
47
  - seed: 42
48
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
  - lr_scheduler_type: cosine
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
57
+ | 0.5646 | 1.0 | 139 | 0.5839 | 0.1510 | 0.5 | 0.1516 |
58
+ | 0.423 | 2.0 | 278 | 0.4050 | 0.5543 | 0.6899 | 0.3809 |
59
+ | 0.3337 | 3.0 | 417 | 0.3495 | 0.7121 | 0.7705 | 0.4639 |
60
+ | 0.2423 | 4.0 | 556 | 0.3842 | 0.7301 | 0.8008 | 0.4801 |
61
+ | 0.168 | 5.0 | 695 | 0.4278 | 0.7409 | 0.8005 | 0.4639 |
62
+ | 0.0905 | 6.0 | 834 | 0.4894 | 0.7207 | 0.7868 | 0.4856 |
63
+ | 0.0619 | 7.0 | 973 | 0.5203 | 0.7238 | 0.7784 | 0.4422 |
64
+ | 0.0371 | 8.0 | 1112 | 0.5356 | 0.7507 | 0.8097 | 0.4747 |
65
+ | 0.0253 | 9.0 | 1251 | 0.6092 | 0.7405 | 0.7970 | 0.4783 |
66
+ | 0.0086 | 10.0 | 1390 | 0.6052 | 0.7508 | 0.8048 | 0.4946 |
67
+ | 0.0102 | 11.0 | 1529 | 0.6632 | 0.7381 | 0.7978 | 0.4639 |
68
+ | 0.0048 | 12.0 | 1668 | 0.6512 | 0.7483 | 0.8060 | 0.4874 |
69
+ | 0.0032 | 13.0 | 1807 | 0.6595 | 0.7399 | 0.7965 | 0.4819 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccf9f5c064074f5d7fad7f93a16d3e1c6df87937b4593b5f8146295b1781be8b
3
  size 1445339812
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fd0332587f2895eefdfe26309be2726000dce7e48ee311a0651af859770b1d4
3
  size 1445339812