Hugging Face's logo

eysharaazia
/
cyber_deberta

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
eysharaazia commited on
Commit
f3ca15f
•
1 Parent(s): 8d9552e

cyber_deberta

Browse files
Files changed (3) hide show
  1. README.md +14 -11
  2. model.safetensors +1 -1
  3. training_args.bin +2 -2
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7](https://huggingface.co/MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.4646
24
- - Accuracy: 0.8273
25
- - F1: 0.8125
26
- - Precision: 0.8068
27
- - Recall: 0.8207
28
 
29
  ## Model description
30
 
@@ -47,8 +47,11 @@ The following hyperparameters were used during training:
47
  - train_batch_size: 64
48
  - eval_batch_size: 64
49
  - seed: 42
 
 
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
- - lr_scheduler_type: linear
 
52
  - num_epochs: 5
53
  - mixed_precision_training: Native AMP
54
 
@@ -56,11 +59,11 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
59
- | 0.3747 | 1.0 | 277 | 0.4398 | 0.7981 | 0.7899 | 0.7874 | 0.8177 |
60
- | 0.2971 | 2.0 | 554 | 0.4022 | 0.8226 | 0.8101 | 0.8031 | 0.8241 |
61
- | 0.2659 | 3.0 | 831 | 0.4262 | 0.8258 | 0.8135 | 0.8065 | 0.8280 |
62
- | 0.2387 | 4.0 | 1108 | 0.4502 | 0.8320 | 0.8168 | 0.8118 | 0.8235 |
63
- | 0.268 | 5.0 | 1385 | 0.4646 | 0.8273 | 0.8125 | 0.8068 | 0.8207 |
64
 
65
 
66
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7](https://huggingface.co/MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.3811
24
+ - Accuracy: 0.8357
25
+ - F1: 0.8180
26
+ - Precision: 0.8167
27
+ - Recall: 0.8193
28
 
29
  ## Model description
30
 
 
47
  - train_batch_size: 64
48
  - eval_batch_size: 64
49
  - seed: 42
50
+ - gradient_accumulation_steps: 2
51
+ - total_train_batch_size: 128
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: cosine
54
+ - lr_scheduler_warmup_steps: 500
55
  - num_epochs: 5
56
  - mixed_precision_training: Native AMP
57
 
 
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
61
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
62
+ | 0.6162 | 1.0 | 105 | 0.6158 | 0.6573 | 0.3966 | 0.3292 | 0.4988 |
63
+ | 0.4929 | 2.0 | 210 | 0.4845 | 0.7621 | 0.7338 | 0.7353 | 0.7325 |
64
+ | 0.4092 | 3.0 | 315 | 0.4153 | 0.8044 | 0.7827 | 0.7824 | 0.7830 |
65
+ | 0.3707 | 4.0 | 420 | 0.3846 | 0.8206 | 0.7986 | 0.8015 | 0.7960 |
66
+ | 0.3046 | 5.0 | 525 | 0.3811 | 0.8357 | 0.8180 | 0.8167 | 0.8193 |
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be81b4d62a52e62cdc175eab3bab0db532fecfde7751ca63e5de1810a7e50ba6
3
  size 1115268200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e3d78e6a0ec3ff63c47cc5a99cdb2f29ca5b488f39f45476fa9bdfef115046e
3
  size 1115268200
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b06cfc114d7acf6808c55d2d25cac269166e7d5e899592aa2dab29327b053c0
3
- size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49dcaa7482fed2158c1abd1129fcd16d8f4e37bcefd022a489d704af4cc934b6
3
+ size 5048