Hugging Face's logo

bdanko
/
bert-tweeteval-distilbert

Text Classification
Transformers
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
bdanko commited on
Commit
511a223
·
verified ·
1 Parent(s): d9f4485

End of training

Browse files
Files changed (2) hide show
  1. README.md +7 -8
  2. model.safetensors +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.9742
20
 
21
  ## Model description
22
 
@@ -37,8 +37,8 @@ More information needed
37
  The following hyperparameters were used during training:
38
  - learning_rate: 2e-05
39
  - train_batch_size: 16
40
- - eval_batch_size: 16
41
- - seed: 42
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
  - num_epochs: 20
@@ -47,11 +47,10 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 0.7054 | 1.0 | 204 | 0.6345 |
51
- | 0.4743 | 2.0 | 408 | 0.6160 |
52
- | 0.2753 | 3.0 | 612 | 0.6895 |
53
- | 0.2285 | 4.0 | 816 | 0.8231 |
54
- | 0.1075 | 5.0 | 1020 | 0.9742 |
55
 
56
 
57
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.7781
20
 
21
  ## Model description
22
 
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 2e-05
39
  - train_batch_size: 16
40
+ - eval_batch_size: 100
41
+ - seed: 15179996
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
  - num_epochs: 20
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 0.6412 | 1.0 | 204 | 0.6249 |
51
+ | 0.4852 | 2.0 | 408 | 0.6617 |
52
+ | 0.3196 | 3.0 | 612 | 0.6549 |
53
+ | 0.1780 | 4.0 | 816 | 0.7781 |
 
54
 
55
 
56
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82c6352ed6e14d7f1a44100299d8a251360a07b1219714d126e1e22728e12d13
3
  size 267838720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6192ea134d396e4c36ae87b5607aa59391236f941d545de1b46f8be55f8b67b
3
  size 267838720