Hugging Face's logo

tinchung
/
mamba_text_classification

Transformers
PyTorch
Generated from Trainer
Inference Endpoints
Model card Files Community
tinchung commited on
Commit
52554dd
·
verified ·
1 Parent(s): ee8eee8

Training complete

Browse files
Files changed (2) hide show
  1. README.md +17 -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 an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.2469
19
- - Accuracy: 0.928
20
 
21
  ## Model description
22
 
@@ -37,7 +37,7 @@ More information needed
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
@@ -48,21 +48,21 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
- | 0.0078 | 0.1 | 625 | 0.4242 | 0.884 |
52
- | 1.3233 | 0.2 | 1250 | 0.2781 | 0.92 |
53
- | 0.0583 | 0.3 | 1875 | 0.2481 | 0.916 |
54
- | 0.0012 | 0.4 | 2500 | 0.3076 | 0.916 |
55
- | 0.0007 | 0.5 | 3125 | 0.2800 | 0.916 |
56
- | 2.3209 | 0.6 | 3750 | 0.2640 | 0.92 |
57
- | 1.2896 | 0.7 | 4375 | 0.2880 | 0.92 |
58
- | 0.0028 | 0.8 | 5000 | 0.2491 | 0.928 |
59
- | 0.0041 | 0.9 | 5625 | 0.2486 | 0.928 |
60
- | 0.0466 | 1.0 | 6250 | 0.2469 | 0.928 |
61
 
62
 
63
  ### Framework versions
64
 
65
- - Transformers 4.38.2
66
- - Pytorch 2.2.1+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: 0.2347
19
+ - Accuracy: 0.94
20
 
21
  ## Model description
22
 
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 5e-05
39
  - train_batch_size: 4
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
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | 0.0104 | 0.1 | 625 | 0.3562 | 0.908 |
52
+ | 2.6178 | 0.2 | 1250 | 0.2743 | 0.912 |
53
+ | 0.0297 | 0.3 | 1875 | 0.2873 | 0.932 |
54
+ | 0.0193 | 0.4 | 2500 | 0.2809 | 0.928 |
55
+ | 0.0004 | 0.5 | 3125 | 0.3164 | 0.92 |
56
+ | 1.9664 | 0.6 | 3750 | 0.2281 | 0.952 |
57
+ | 0.9588 | 0.7 | 4375 | 0.2699 | 0.944 |
58
+ | 0.0023 | 0.8 | 5000 | 0.2450 | 0.944 |
59
+ | 0.0074 | 0.9 | 5625 | 0.2358 | 0.944 |
60
+ | 0.6961 | 1.0 | 6250 | 0.2347 | 0.94 |
61
 
62
 
63
  ### Framework versions
64
 
65
+ - Transformers 4.41.2
66
+ - Pytorch 2.3.0+cu121
67
+ - Datasets 2.20.0
68
+ - Tokenizers 0.19.1
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c40a783258a57d4cd9e6271a22e78998f070830dc357c6067783ccdf0371cdf6
3
  size 516640282
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:293443fdf4d680db9b7abdb9aca45c80642ee56b827c4b4b1a59d6247e30cbb1
3
  size 516640282