Hugging Face's logo

wterrrr
/
mamba_text_classification

Transformers
PyTorch
Generated from Trainer
Model card Files
xet
 Community
wterrrr commited on
Commit
92d57fc
·
verified ·
1 Parent(s): 133220e

Training complete

Browse files
Files changed (2) hide show
  1. README.md +16 -17
  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 the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 3.3681
19
- - Accuracy: 0.7632
20
 
21
  ## Model description
22
 
@@ -42,27 +42,26 @@ The following hyperparameters were used during training:
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_ratio: 0.01
45
- - num_epochs: 10
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
51
- | 0.2013 | 1.0 | 5303 | 0.8670 | 0.7840 |
52
- | 0.6424 | 2.0 | 10606 | 0.8146 | 0.7925 |
53
- | 1.4065 | 3.0 | 15909 | 1.0937 | 0.7566 |
54
- | 0.0052 | 4.0 | 21212 | 1.4049 | 0.7774 |
55
- | 0.001 | 5.0 | 26515 | 1.7016 | 0.7792 |
56
- | 0.6043 | 6.0 | 31818 | 2.0485 | 0.7755 |
57
- | 0.0 | 7.0 | 37121 | 2.5028 | 0.7679 |
58
- | 0.0001 | 8.0 | 42424 | 3.0957 | 0.7651 |
59
- | 0.0001 | 9.0 | 47727 | 3.2818 | 0.7660 |
60
- | 0.0 | 10.0 | 53030 | 3.3681 | 0.7632 |
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 the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.5866
19
+ - Accuracy: 0.7953
20
 
21
  ## Model description
22
 
 
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_ratio: 0.01
45
+ - num_epochs: 2
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | 0.1412 | 0.2 | 1061 | 0.6656 | 0.7236 |
52
+ | 0.8056 | 0.4 | 2122 | 0.6228 | 0.7547 |
53
+ | 0.361 | 0.6 | 3183 | 0.6003 | 0.7670 |
54
+ | 0.2609 | 0.8 | 4244 | 0.6263 | 0.7708 |
55
+ | 0.5028 | 1.0 | 5305 | 0.5934 | 0.7821 |
56
+ | 0.0057 | 1.2 | 6366 | 0.5991 | 0.7887 |
57
+ | 0.3451 | 1.4 | 7427 | 0.5670 | 0.7925 |
58
+ | 0.1607 | 1.6 | 8488 | 0.5861 | 0.7934 |
59
+ | 0.0893 | 1.8 | 9549 | 0.5866 | 0.7953 |
 
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:cff3b982a8af1e7997e5c626c1ad2ea966f9d41a6d748f07b5fcfe80c1e0a47e
3
  size 516643354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12fb6c4a5a28055fcc2a04ec21a3e8697ded74be8d39b5155c60709c6883973
3
  size 516643354