Hugging Face's logo

zates
/
distilbert-base-uncased-finetuned-squad-seed-9001

Question Answering
Transformers
PyTorch
TensorBoard
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
zates commited on
Commit
5b64768
路
1 Parent(s): 37f27c6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -5
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 squad_v2 dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.9532
20
 
21
  ## Model description
22
 
@@ -41,19 +41,20 @@ The following hyperparameters were used during training:
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
- - num_epochs: 2
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:-----:|:---------------:|
50
- | 2.4505 | 1.0 | 8248 | 2.0949 |
51
- | 2.1358 | 2.0 | 16496 | 1.9532 |
 
52
 
53
 
54
  ### Framework versions
55
 
56
  - Transformers 4.25.1
57
- - Pytorch 1.12.1+cu113
58
  - Datasets 2.7.1
59
  - Tokenizers 0.13.2
 
16
 
17
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad_v2 dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.4060
20
 
21
  ## Model description
22
 
 
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 3
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 1.2411 | 1.0 | 8235 | 1.2265 |
51
+ | 0.9797 | 2.0 | 16470 | 1.2576 |
52
+ | 0.791 | 3.0 | 24705 | 1.4060 |
53
 
54
 
55
  ### Framework versions
56
 
57
  - Transformers 4.25.1
58
+ - Pytorch 1.13.0+cu116
59
  - Datasets 2.7.1
60
  - Tokenizers 0.13.2