Hugging Face's logo

eclec
/
patentClassfication2

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Model card Files Community
1
eclec commited on
Commit
d4488f0
·
1 Parent(s): 6294bfb

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -19
README.md CHANGED
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model was trained from scratch on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6212
22
- - Accuracy: 0.6754
23
- - F1: 0.7015
24
- - Precision: 0.6475
25
- - Recall: 0.7653
26
 
27
  ## Model description
28
 
@@ -41,30 +41,31 @@ More information needed
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
- - learning_rate: 1.939963e-05
45
- - train_batch_size: 8
46
  - eval_batch_size: 8
47
- - seed: 40
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: cosine
50
  - lr_scheduler_warmup_ratio: 0.1
 
51
  - num_epochs: 11
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
56
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
57
- | 0.6217 | 1.0 | 4438 | 0.6251 | 0.6405 | 0.5425 | 0.7414 | 0.4278 |
58
- | 0.5918 | 2.0 | 8876 | 0.6212 | 0.6754 | 0.7015 | 0.6475 | 0.7653 |
59
- | 0.5097 | 3.0 | 13314 | 0.8241 | 0.6748 | 0.6827 | 0.6645 | 0.7020 |
60
- | 0.4099 | 4.0 | 17752 | 1.0772 | 0.6685 | 0.6810 | 0.6542 | 0.7102 |
61
- | 0.3342 | 5.0 | 22190 | 1.7059 | 0.6550 | 0.6645 | 0.6446 | 0.6857 |
62
- | 0.216 | 6.0 | 26628 | 2.1970 | 0.6503 | 0.6529 | 0.6459 | 0.6600 |
63
- | 0.1214 | 7.0 | 31066 | 2.7215 | 0.6498 | 0.6642 | 0.6360 | 0.6950 |
64
- | 0.0548 | 8.0 | 35504 | 2.9805 | 0.6515 | 0.6557 | 0.6458 | 0.6658 |
65
- | 0.0356 | 9.0 | 39942 | 3.2608 | 0.6541 | 0.6560 | 0.6503 | 0.6618 |
66
- | 0.0284 | 10.0 | 44380 | 3.3810 | 0.6513 | 0.6548 | 0.6461 | 0.6638 |
67
- | 0.0186 | 11.0 | 48818 | 3.3967 | 0.6514 | 0.6576 | 0.6440 | 0.6717 |
68
 
69
 
70
  ### Framework versions
 
18
 
19
  This model was trained from scratch on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5108
22
+ - Accuracy: 0.7492
23
+ - F1: 0.7710
24
+ - Precision: 0.7025
25
+ - Recall: 0.8543
26
 
27
  ## Model description
28
 
 
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
+ - learning_rate: 2.329139e-05
45
+ - train_batch_size: 32
46
  - eval_batch_size: 8
47
+ - seed: 18
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: cosine
50
  - lr_scheduler_warmup_ratio: 0.1
51
+ - lr_scheduler_warmup_steps: 478
52
  - num_epochs: 11
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
57
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
58
+ | 0.5264 | 1.0 | 1110 | 0.5108 | 0.7492 | 0.7710 | 0.7025 | 0.8543 |
59
+ | 0.4405 | 2.0 | 2220 | 0.5624 | 0.7463 | 0.7295 | 0.7710 | 0.6923 |
60
+ | 0.2972 | 3.0 | 3330 | 0.7480 | 0.7394 | 0.7224 | 0.7629 | 0.6859 |
61
+ | 0.1733 | 4.0 | 4440 | 0.7975 | 0.7328 | 0.7316 | 0.7266 | 0.7367 |
62
+ | 0.1242 | 5.0 | 5550 | 1.3035 | 0.7314 | 0.7396 | 0.7101 | 0.7716 |
63
+ | 0.0866 | 6.0 | 6660 | 1.6628 | 0.7272 | 0.7110 | 0.7464 | 0.6788 |
64
+ | 0.0493 | 7.0 | 7770 | 1.7728 | 0.7321 | 0.7285 | 0.7297 | 0.7274 |
65
+ | 0.0313 | 8.0 | 8880 | 2.0279 | 0.7383 | 0.7325 | 0.7402 | 0.7249 |
66
+ | 0.0187 | 9.0 | 9990 | 2.1956 | 0.7375 | 0.7445 | 0.7173 | 0.7739 |
67
+ | 0.0148 | 10.0 | 11100 | 2.2491 | 0.7355 | 0.7366 | 0.7256 | 0.7479 |
68
+ | 0.0129 | 11.0 | 12210 | 2.2694 | 0.7350 | 0.7378 | 0.7220 | 0.7543 |
69
 
70
 
71
  ### Framework versions