Hugging Face's logo

lct-rug-2022
/
edos-2023-baseline-bert-base-uncased-label_vector

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
2
k4black commited on
Commit
bee0eb4
·
1 Parent(s): 4214389

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -12
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.9256
20
- - F1: 0.4541
21
 
22
  ## Model description
23
 
@@ -38,26 +38,28 @@ More information needed
38
  The following hyperparameters were used during training:
39
  - learning_rate: 1e-05
40
  - train_batch_size: 32
41
- - eval_batch_size: 64
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 5
46
- - num_epochs: 10
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | F1 |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
- | 2.1225 | 1.18 | 100 | 1.8712 | 0.1078 |
54
- | 1.7933 | 2.35 | 200 | 1.6171 | 0.1861 |
55
- | 1.5819 | 3.53 | 300 | 1.4004 | 0.2706 |
56
- | 1.4077 | 4.71 | 400 | 1.2577 | 0.2964 |
57
- | 1.2928 | 5.88 | 500 | 1.1136 | 0.3732 |
58
- | 1.182 | 7.06 | 600 | 1.0234 | 0.4052 |
59
- | 1.1092 | 8.24 | 700 | 0.9653 | 0.4457 |
60
- | 1.052 | 9.41 | 800 | 0.9256 | 0.4541 |
 
 
61
 
62
 
63
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.5258
20
+ - F1: 0.2606
21
 
22
  ## Model description
23
 
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 1e-05
40
  - train_batch_size: 32
41
+ - eval_batch_size: 32
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 5
46
+ - num_epochs: 12
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | F1 |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 2.1324 | 1.18 | 100 | 1.9573 | 0.0997 |
54
+ | 1.8322 | 2.35 | 200 | 1.8104 | 0.1286 |
55
+ | 1.6653 | 3.53 | 300 | 1.7238 | 0.1577 |
56
+ | 1.5292 | 4.71 | 400 | 1.6735 | 0.1655 |
57
+ | 1.423 | 5.88 | 500 | 1.5987 | 0.1916 |
58
+ | 1.2936 | 7.06 | 600 | 1.5628 | 0.2359 |
59
+ | 1.2256 | 8.24 | 700 | 1.5492 | 0.2496 |
60
+ | 1.1385 | 9.41 | 800 | 1.5388 | 0.2618 |
61
+ | 1.1138 | 10.59 | 900 | 1.5233 | 0.2678 |
62
+ | 1.0599 | 11.76 | 1000 | 1.5258 | 0.2606 |
63
 
64
 
65
  ### Framework versions