Hugging Face's logo

shafin
/
distilbert-base-uncased-finetuned-cust

Fill-Mask
Transformers
PyTorch
TensorBoard
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
shafin commited on
Commit
849e6b0
•
1 Parent(s): 6383203

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -3
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 2.5376
18
 
19
  ## Model description
20
 
@@ -39,14 +39,18 @@ The following hyperparameters were used during training:
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
- - num_epochs: 1
43
  - mixed_precision_training: Native AMP
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 2.7034 | 1.0 | 157 | 2.5023 |
 
 
 
 
50
 
51
 
52
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 2.0735
18
 
19
  ## Model description
20
 
 
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
+ - num_epochs: 5
43
  - mixed_precision_training: Native AMP
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 2.4249 | 1.0 | 625 | 2.2071 |
50
+ | 2.2697 | 2.0 | 1250 | 2.1411 |
51
+ | 2.2092 | 3.0 | 1875 | 2.1255 |
52
+ | 2.1674 | 4.0 | 2500 | 2.0682 |
53
+ | 2.1499 | 5.0 | 3125 | 2.0667 |
54
 
55
 
56
  ### Framework versions