Hugging Face's logo

tarekxpc
/
mamba_text_classification

Transformers
PyTorch
Generated from Trainer
Inference Endpoints
Model card Files Community
tarekxpc commited on
Commit
363d37f
•
1 Parent(s): fc31ec7

Training complete

Browse files
Files changed (2) hide show
  1. README.md +17 -18
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model was trained from scratch on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.4457
19
- - Accuracy: 0.9211
20
 
21
  ## Model description
22
 
@@ -36,8 +36,8 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 5e-05
39
- - train_batch_size: 4
40
- - eval_batch_size: 16
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
@@ -46,23 +46,22 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
51
- | 0.6645 | 0.1 | 3000 | 0.4229 | 0.9211 |
52
- | 0.0007 | 0.2 | 6000 | 0.2685 | 0.9342 |
53
- | 0.0 | 0.3 | 9000 | 0.4486 | 0.9211 |
54
- | 1.9934 | 0.4 | 12000 | 0.4740 | 0.9342 |
55
- | 0.4133 | 0.5 | 15000 | 0.4811 | 0.9211 |
56
- | 0.0229 | 0.6 | 18000 | 0.4541 | 0.9211 |
57
- | 0.0004 | 0.7 | 21000 | 0.4255 | 0.9079 |
58
- | 0.0009 | 0.8 | 24000 | 0.4633 | 0.9211 |
59
- | 0.3324 | 0.9 | 27000 | 0.4495 | 0.9211 |
60
- | 1.4221 | 1.0 | 30000 | 0.4457 | 0.9211 |
61
 
62
 
63
  ### Framework versions
64
 
65
- - Transformers 4.38.1
66
- - Pytorch 2.1.0+cu121
67
  - Datasets 2.18.0
68
  - Tokenizers 0.15.2
 
15
 
16
  This model was trained from scratch on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.8755
19
+ - Accuracy: 0.7778
20
 
21
  ## Model description
22
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 5e-05
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 4
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | 2.0279 | 0.1 | 371 | 2.5090 | 0.1111 |
52
+ | 1.3557 | 0.2 | 742 | 1.0745 | 0.6667 |
53
+ | 1.5255 | 0.3 | 1113 | 1.1685 | 0.6667 |
54
+ | 0.7389 | 0.4 | 1484 | 1.3240 | 0.5556 |
55
+ | 0.9114 | 0.5 | 1855 | 1.2930 | 0.6667 |
56
+ | 0.0422 | 0.6 | 2226 | 1.1987 | 0.6667 |
57
+ | 1.5648 | 0.7 | 2597 | 0.5782 | 0.7778 |
58
+ | 1.7356 | 0.8 | 2968 | 0.7707 | 0.6667 |
59
+ | 0.0145 | 0.9 | 3339 | 0.8755 | 0.7778 |
 
60
 
61
 
62
  ### Framework versions
63
 
64
+ - Transformers 4.38.2
65
+ - Pytorch 2.2.1+cu121
66
  - Datasets 2.18.0
67
  - Tokenizers 0.15.2
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac4f50cb73e38edfe96fefc415d488df1fe77dd52c80b096d484fae7c938326a
3
  size 516667930
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d343268c0913283c89b0264258b95dd361ba8308e55e4d5f9a453dd5c1511e96
3
  size 516667930