Hugging Face's logo

eclec
/
patentClassificationLongFormerTextrank

Text Classification
Transformers
PyTorch
longformer
Generated from Trainer
Model card Files
xet
 Community
eclec commited on
Commit
58e50af
·
1 Parent(s): df4b414

End of training

Browse files
Files changed (2) hide show
  1. README.md +10 -10
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [eclec/patentClassificationLongFormer2](https://huggingface.co/eclec/patentClassificationLongFormer2) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.4605
21
- - Accuracy: 0.7891
22
- - F1: 0.5698
23
 
24
  ## Model description
25
 
@@ -38,25 +38,25 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 4.3241744156881815e-05
42
  - train_batch_size: 8
43
  - eval_batch_size: 8
44
- - seed: 172
45
  - gradient_accumulation_steps: 4
46
  - total_train_batch_size: 32
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: cosine
49
- - lr_scheduler_warmup_ratio: 0.2047474135167534
50
- - lr_scheduler_warmup_steps: 292
51
  - num_epochs: 3
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
57
- | 0.484 | 1.0 | 2059 | 0.4607 | 0.7810 | 0.4952 |
58
- | 0.4358 | 2.0 | 4119 | 0.4476 | 0.7828 | 0.5851 |
59
- | 0.3661 | 3.0 | 6177 | 0.4605 | 0.7891 | 0.5698 |
60
 
61
 
62
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [eclec/patentClassificationLongFormer2](https://huggingface.co/eclec/patentClassificationLongFormer2) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4294
21
+ - Accuracy: 0.7959
22
+ - F1: 0.6187
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 1.330504416591152e-05
42
  - train_batch_size: 8
43
  - eval_batch_size: 8
44
+ - seed: 3
45
  - gradient_accumulation_steps: 4
46
  - total_train_batch_size: 32
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.24934655263987432
50
+ - lr_scheduler_warmup_steps: 90
51
  - num_epochs: 3
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
57
+ | 0.4444 | 1.0 | 2059 | 0.4397 | 0.7947 | 0.6100 |
58
+ | 0.3942 | 2.0 | 4119 | 0.4294 | 0.7959 | 0.6187 |
59
+ | 0.3331 | 3.0 | 6177 | 0.4607 | 0.7999 | 0.6078 |
60
 
61
 
62
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3732aedfcf5b87562efcf2770c365842a74fab24cfc536c976f761c7c9bec0a9
3
  size 1738600369
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e395031e4f950d2cb21220ff7c033171d540727b8f2bce246490f27c74a27f5
3
  size 1738600369