eskayML commited on
Commit
a1acfb6
·
verified ·
1 Parent(s): 1b03ffb

eskayML/bert_interview_new

Browse files
Files changed (3) hide show
  1. README.md +7 -8
  2. model.safetensors +1 -1
  3. training_args.bin +0 -0
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.3989
22
- - Accuracy: 0.6207
23
 
24
  ## Model description
25
 
@@ -44,17 +44,16 @@ The following hyperparameters were used during training:
44
  - seed: 42
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
- - num_epochs: 5
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 2.6042 | 1.0 | 579 | 2.4472 | 0.2371 |
54
- | 2.387 | 2.0 | 1158 | 2.0325 | 0.4526 |
55
- | 2.0347 | 3.0 | 1737 | 1.6837 | 0.5517 |
56
- | 1.6932 | 4.0 | 2316 | 1.4596 | 0.6034 |
57
- | 1.6036 | 5.0 | 2895 | 1.3989 | 0.6207 |
58
 
59
 
60
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 2.0245
22
+ - Accuracy: 0.3966
23
 
24
  ## Model description
25
 
 
44
  - seed: 42
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 4
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | No log | 1.0 | 463 | 2.1972 | 0.3491 |
54
+ | 2.2231 | 2.0 | 926 | 2.0334 | 0.4052 |
55
+ | 1.8254 | 3.0 | 1389 | 2.0277 | 0.3922 |
56
+ | 1.6125 | 4.0 | 1852 | 2.0245 | 0.3966 |
 
57
 
58
 
59
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff19e44b97927bfda470969512cfd122e692bc4989f4bb488940e4c62045fec0
3
  size 267887936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:295b18c815e75de78e8bf08bdea54ec83f679cff620307b8c5ddaba3dc2dbfba
3
  size 267887936
training_args.bin CHANGED
Binary files a/training_args.bin and b/training_args.bin differ