Hugging Face's logo

AnonymousCS
/
populism_classifier_411

Text Classification
Transformers
Safetensors
rembert
Generated from Trainer
Model card Files
xet
Community
AnonymousCS commited on
Commit
aad76e5
·
verified ·
1 Parent(s): d902805

End of training

Browse files
Files changed (4) hide show
  1. README.md +19 -13
  2. config.json +2 -2
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,12 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google/rembert](https://huggingface.co/google/rembert) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6686
22
- - Accuracy: 0.9118
23
  - 1-f1: 0.0
24
  - 1-recall: 0.0
25
  - 1-precision: 0.0
26
- - Balanced Acc: 0.5
27
 
28
  ## Model description
29
 
@@ -48,21 +48,27 @@ The following hyperparameters were used during training:
48
  - seed: 42
49
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: linear
 
51
  - num_epochs: 20
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
57
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|:--------:|:-----------:|:------------:|
58
- | 0.6746 | 1.0 | 91 | 0.6774 | 0.9118 | 0.0 | 0.0 | 0.0 | 0.5 |
59
- | 0.6333 | 2.0 | 182 | 0.6769 | 0.9118 | 0.0 | 0.0 | 0.0 | 0.5 |
60
- | 0.7695 | 3.0 | 273 | 0.6672 | 0.9118 | 0.0 | 0.0 | 0.0 | 0.5 |
61
- | 0.6843 | 4.0 | 364 | 0.6757 | 0.9118 | 0.0 | 0.0 | 0.0 | 0.5 |
62
- | 0.7178 | 5.0 | 455 | 0.6668 | 0.9118 | 0.0 | 0.0 | 0.0 | 0.5 |
63
- | 0.6505 | 6.0 | 546 | 0.6666 | 0.9118 | 0.0 | 0.0 | 0.0 | 0.5 |
64
- | 0.5584 | 7.0 | 637 | 0.6691 | 0.9118 | 0.0 | 0.0 | 0.0 | 0.5 |
65
- | 0.8056 | 8.0 | 728 | 0.6686 | 0.9118 | 0.0 | 0.0 | 0.0 | 0.5 |
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [google/rembert](https://huggingface.co/google/rembert) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.7307
22
+ - Accuracy: 0.9091
23
  - 1-f1: 0.0
24
  - 1-recall: 0.0
25
  - 1-precision: 0.0
26
+ - Balanced Acc: 0.4985
27
 
28
  ## Model description
29
 
 
48
  - seed: 42
49
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_ratio: 0.06
52
  - num_epochs: 20
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
58
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
59
+ | 0.5911 | 1.0 | 91 | 0.7011 | 0.1515 | 0.1720 | 1.0 | 0.0941 | 0.5347 |
60
+ | 0.6288 | 2.0 | 182 | 0.8307 | 0.0882 | 0.1620 | 1.0 | 0.0882 | 0.5 |
61
+ | 0.5907 | 3.0 | 273 | 0.6749 | 0.2011 | 0.1808 | 1.0 | 0.0994 | 0.5619 |
62
+ | 0.675 | 4.0 | 364 | 0.7471 | 0.0909 | 0.1624 | 1.0 | 0.0884 | 0.5015 |
63
+ | 0.8407 | 5.0 | 455 | 0.9201 | 0.0882 | 0.1620 | 1.0 | 0.0882 | 0.5 |
64
+ | 0.625 | 6.0 | 546 | 0.6675 | 0.8375 | 0.1449 | 0.1562 | 0.1351 | 0.5298 |
65
+ | 0.383 | 7.0 | 637 | 0.6634 | 0.6860 | 0.1972 | 0.4375 | 0.1273 | 0.5737 |
66
+ | 1.0487 | 8.0 | 728 | 0.6541 | 0.7879 | 0.2524 | 0.4062 | 0.1831 | 0.6155 |
67
+ | 0.655 | 9.0 | 819 | 0.8689 | 0.8485 | 0.0678 | 0.0625 | 0.0741 | 0.4935 |
68
+ | 0.7175 | 10.0 | 910 | 0.6738 | 0.8981 | 0.0 | 0.0 | 0.0 | 0.4924 |
69
+ | 0.4837 | 11.0 | 1001 | 0.7142 | 0.9091 | 0.0 | 0.0 | 0.0 | 0.4985 |
70
+ | 0.257 | 12.0 | 1092 | 0.8252 | 0.9091 | 0.0 | 0.0 | 0.0 | 0.4985 |
71
+ | 0.7864 | 13.0 | 1183 | 0.7307 | 0.9091 | 0.0 | 0.0 | 0.0 | 0.4985 |
72
 
73
 
74
  ### Framework versions
config.json CHANGED
@@ -3,14 +3,14 @@
3
  "architectures": [
4
  "RemBertForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0,
7
  "bos_token_id": 312,
8
  "classifier_dropout_prob": 0.1,
9
  "embedding_dropout_prob": 0,
10
  "embedding_size": 256,
11
  "eos_token_id": 313,
12
  "hidden_act": "gelu",
13
- "hidden_dropout_prob": 0,
14
  "hidden_size": 1152,
15
  "initializer_range": 0.02,
16
  "input_embedding_size": 256,
 
3
  "architectures": [
4
  "RemBertForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.2,
7
  "bos_token_id": 312,
8
  "classifier_dropout_prob": 0.1,
9
  "embedding_dropout_prob": 0,
10
  "embedding_size": 256,
11
  "eos_token_id": 313,
12
  "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.2,
14
  "hidden_size": 1152,
15
  "initializer_range": 0.02,
16
  "input_embedding_size": 256,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9a8bfbbb13407f337216b24c649e57f59f915a500fbc466dd8fdd1f15df0f4f
3
  size 2303755328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6e522c185178f43c431c920a90f81f75071076d6735988d642d5f2cb41ffa1f
3
  size 2303755328
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:748085ef807b5b927d51b8e301ee0b78acbcba20768ae0ecdb0d1826705e91af
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9480635f57909670210266745a65e0c8ad76845387fc28c8cbf3b7b5e9129484
3
  size 5432