Hugging Face's logo

sento800
/
distilbert-base-cased-squad

Question Answering
Transformers
PyTorch
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
2
sento800 commited on
Commit
e1fcf4c
•
1 Parent(s): 73a5631

End of training

Browse files
Files changed (3) hide show
  1. README.md +11 -11
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the squad dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.3039
21
 
22
  ## Model description
23
 
@@ -37,8 +37,8 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 2e-05
40
- - train_batch_size: 10
41
- - eval_batch_size: 10
42
  - seed: 0
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
@@ -46,14 +46,14 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:-----:|:----:|:---------------:|
51
- | 2.3688 | 1.0 | 1350 | 1.4871 |
52
- | 1.2342 | 2.0 | 2700 | 1.3039 |
53
- | 0.8185 | 3.0 | 4050 | 1.3300 |
54
- | 0.5646 | 4.0 | 5400 | 1.5053 |
55
- | 0.4032 | 5.0 | 6750 | 1.6240 |
56
- | 0.314 | 6.0 | 8100 | 1.7492 |
57
 
58
 
59
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the squad dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.4144
21
 
22
  ## Model description
23
 
 
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 2e-05
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
  - seed: 0
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 0.8764 | 1.0 | 1688 | 1.4144 |
52
+ | 0.5653 | 2.0 | 3376 | 1.4274 |
53
+ | 0.3689 | 3.0 | 5064 | 1.7517 |
54
+ | 0.2427 | 4.0 | 6752 | 2.0817 |
55
+ | 0.1613 | 5.0 | 8440 | 2.3114 |
56
+ | 0.1159 | 6.0 | 10128 | 2.5096 |
57
 
58
 
59
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30216fcef907cc24138f696c613094ccc5372bc7cdfd3bab8044c8f5c38d8f2a
3
  size 260804645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:544761ce051ec8b0f0547d0acd8920ca14f70a88dd64c88e0d40107f415e98c9
3
  size 260804645
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af7b40f158b6d030a2d700d330bd149279208cf495c432ef44de4b5a809ea808
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a32534d20529529e0e92904bd91412ef23591255c36bfc1e82d328f7d246ab
3
  size 4027