Hugging Face's logo

Kudod
/
my_awesome_model_IMDB

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Kudod commited on
Commit
cb52349
•
1 Parent(s): 88b5522

End of training

Browse files
Files changed (2) hide show
  1. README.md +18 -11
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.2245
21
- - Accuracy: 0.9325
22
 
23
  ## Model description
24
 
@@ -38,25 +38,32 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 2e-05
41
- - train_batch_size: 16
42
- - eval_batch_size: 16
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 2
47
- - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 0.2276 | 1.0 | 1563 | 0.2247 | 0.9160 |
54
- | 0.153 | 2.0 | 3126 | 0.2245 | 0.9325 |
 
 
 
 
 
 
 
 
55
 
56
 
57
  ### Framework versions
58
 
59
- - Transformers 4.35.2
60
- - Pytorch 2.1.0+cu121
61
  - Datasets 2.17.0
62
- - Tokenizers 0.15.1
 
17
 
18
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4229
21
+ - Accuracy: 0.9307
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 2e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 10
 
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 0.2892 | 1.0 | 782 | 0.2075 | 0.9192 |
53
+ | 0.151 | 2.0 | 1564 | 0.2034 | 0.9294 |
54
+ | 0.103 | 3.0 | 2346 | 0.2369 | 0.9270 |
55
+ | 0.0567 | 4.0 | 3128 | 0.2920 | 0.9306 |
56
+ | 0.0415 | 5.0 | 3910 | 0.3699 | 0.9275 |
57
+ | 0.025 | 6.0 | 4692 | 0.3560 | 0.9300 |
58
+ | 0.0204 | 7.0 | 5474 | 0.3690 | 0.9308 |
59
+ | 0.0125 | 8.0 | 6256 | 0.4119 | 0.9300 |
60
+ | 0.0117 | 9.0 | 7038 | 0.4176 | 0.9310 |
61
+ | 0.0065 | 10.0 | 7820 | 0.4229 | 0.9307 |
62
 
63
 
64
  ### Framework versions
65
 
66
+ - Transformers 4.34.0
67
+ - Pytorch 2.0.1+cu117
68
  - Datasets 2.17.0
69
+ - Tokenizers 0.14.0
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb886fd43c384ed04d4dbd6238f0173d2bf4baa41ff0525d21f9c5c7797a6901
3
  size 267855533
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8d3ddd6aa52e024c07e26be876108d6c2d6aaa4375dbf725d54aee1d5cd587
3
  size 267855533