Hugging Face's logo

sergiomvazq
/
DeBERTaV3_model_V3

Text Classification
Transformers
TensorBoard
Safetensors
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
sergiomvazq commited on
Commit
8c69239
·
verified ·
1 Parent(s): 823d7ce

End of training

Browse files
Files changed (5) hide show
  1. README.md +19 -17
  2. model.safetensors +1 -1
  3. runs/Jun07_09-54-20_0417-111206-hkgnini8-10-45-16-12/events.out.tfevents.1717754065.0417-111206-hkgnini8-10-45-16-12.1976.2 +3 -0
  4. runs/Jun07_09-54-20_0417-111206-hkgnini8-10-45-16-12/events.out.tfevents.1717755614.0417-111206-hkgnini8-10-45-16-12.1976.3 +3 -0
  5. training_args.bin +1 -1
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 [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0963
24
- - Accuracy: 0.9724
25
- - F1: 0.8874
26
- - Precision: 0.9054
27
- - Recall: 0.8701
28
 
29
  ## Model description
30
 
@@ -43,28 +43,30 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 5e-05
47
  - train_batch_size: 5
48
  - eval_batch_size: 5
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - num_epochs: 10
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
58
- | No log | 1.0 | 84 | 0.2797 | 0.9058 | 0.4630 | 0.8065 | 0.3247 |
59
- | No log | 2.0 | 168 | 0.2004 | 0.9269 | 0.6281 | 0.8636 | 0.4935 |
60
- | No log | 3.0 | 252 | 0.1818 | 0.9253 | 0.6761 | 0.7385 | 0.6234 |
61
- | No log | 4.0 | 336 | 0.1692 | 0.9399 | 0.7176 | 0.8704 | 0.6104 |
62
- | No log | 5.0 | 420 | 0.1503 | 0.9513 | 0.7945 | 0.8406 | 0.7532 |
63
- | 0.2044 | 6.0 | 504 | 0.1269 | 0.9562 | 0.8212 | 0.8378 | 0.8052 |
64
- | 0.2044 | 7.0 | 588 | 0.0963 | 0.9724 | 0.8874 | 0.9054 | 0.8701 |
65
- | 0.2044 | 8.0 | 672 | 0.1243 | 0.9594 | 0.8344 | 0.8514 | 0.8182 |
66
- | 0.2044 | 9.0 | 756 | 0.1107 | 0.9659 | 0.8609 | 0.8784 | 0.8442 |
67
- | 0.2044 | 10.0 | 840 | 0.1088 | 0.9675 | 0.8667 | 0.8904 | 0.8442 |
 
 
68
 
69
 
70
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.1015
24
+ - Accuracy: 0.9693
25
+ - F1: 0.8766
26
+ - Precision: 0.8803
27
+ - Recall: 0.8729
28
 
29
  ## Model description
30
 
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
+ - learning_rate: 3e-05
47
  - train_batch_size: 5
48
  - eval_batch_size: 5
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 12
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
58
+ | No log | 1.0 | 100 | 0.3499 | 0.875 | 0.0 | 0.0 | 0.0 |
59
+ | No log | 2.0 | 200 | 0.2517 | 0.9068 | 0.4211 | 0.9412 | 0.2712 |
60
+ | No log | 3.0 | 300 | 0.1835 | 0.9396 | 0.7077 | 0.8961 | 0.5847 |
61
+ | No log | 4.0 | 400 | 0.1338 | 0.9587 | 0.8219 | 0.8911 | 0.7627 |
62
+ | 0.2507 | 5.0 | 500 | 0.1043 | 0.9640 | 0.8522 | 0.875 | 0.8305 |
63
+ | 0.2507 | 6.0 | 600 | 0.1076 | 0.9629 | 0.8472 | 0.8739 | 0.8220 |
64
+ | 0.2507 | 7.0 | 700 | 0.1061 | 0.9619 | 0.8475 | 0.8475 | 0.8475 |
65
+ | 0.2507 | 8.0 | 800 | 0.1015 | 0.9693 | 0.8766 | 0.8803 | 0.8729 |
66
+ | 0.2507 | 9.0 | 900 | 0.1099 | 0.9650 | 0.8596 | 0.8632 | 0.8559 |
67
+ | 0.0434 | 10.0 | 1000 | 0.1101 | 0.9661 | 0.8632 | 0.8707 | 0.8559 |
68
+ | 0.0434 | 11.0 | 1100 | 0.1054 | 0.9693 | 0.8766 | 0.8803 | 0.8729 |
69
+ | 0.0434 | 12.0 | 1200 | 0.1066 | 0.9682 | 0.8729 | 0.8729 | 0.8729 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff0234cfa62f4dfe8e4b4cfd5c5705004798051ec214e6d03ec215b9f3a27447
3
  size 567617008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2aac81c9df133f37908a1d33c3059c34a4b56cd9b202b5737df92fa5acb3dce
3
  size 567617008
runs/Jun07_09-54-20_0417-111206-hkgnini8-10-45-16-12/events.out.tfevents.1717754065.0417-111206-hkgnini8-10-45-16-12.1976.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f0d16c5479065dafae8e34721a20e622c0efe493dbf648ff77a222320bdbdf
3
+ size 11760
runs/Jun07_09-54-20_0417-111206-hkgnini8-10-45-16-12/events.out.tfevents.1717755614.0417-111206-hkgnini8-10-45-16-12.1976.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a16a7b79ed150b3b1aceafdd04837219a5fca0d457deb6fec0c1bdffbbf476b9
3
+ size 512
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba53f2fbdb0e165eb193322e1b78fe5673fe6767d45ea47e6c2eb7a6b11f4dd4
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be92743a7c70c72c05bdbed351b751517b7154183e5deae2147d82dba51cac7
3
  size 5112