Hugging Face's logo

daze-unlv
/
distilbert_distilbert-base-uncased-15-epoch

Multiple Choice
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
daze-unlv commited on
Commit
6e0d049
•
1 Parent(s): 8b371c4

End of training

Browse files
Files changed (2) hide show
  1. README.md +19 -19
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 4.3248
21
- - Accuracy: 0.4133
22
 
23
  ## Model description
24
 
@@ -38,8 +38,8 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
- - train_batch_size: 64
42
- - eval_batch_size: 64
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
@@ -49,21 +49,21 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
- | 1.3078 | 1.0 | 2857 | 1.3426 | 0.3356 |
53
- | 1.1327 | 2.0 | 5714 | 1.4079 | 0.3560 |
54
- | 0.911 | 3.0 | 8571 | 1.5413 | 0.3789 |
55
- | 0.7139 | 4.0 | 11428 | 1.7088 | 0.3942 |
56
- | 0.548 | 5.0 | 14285 | 1.9117 | 0.3902 |
57
- | 0.4389 | 6.0 | 17142 | 2.1179 | 0.3971 |
58
- | 0.3422 | 7.0 | 19999 | 2.5687 | 0.4002 |
59
- | 0.2707 | 8.0 | 22856 | 2.6006 | 0.4019 |
60
- | 0.2258 | 9.0 | 25713 | 2.8582 | 0.4069 |
61
- | 0.1817 | 10.0 | 28570 | 3.2135 | 0.4031 |
62
- | 0.1506 | 11.0 | 31427 | 3.2640 | 0.4074 |
63
- | 0.1285 | 12.0 | 34284 | 3.6061 | 0.4086 |
64
- | 0.1067 | 13.0 | 37141 | 3.7931 | 0.4141 |
65
- | 0.088 | 14.0 | 39998 | 4.1130 | 0.4129 |
66
- | 0.0772 | 15.0 | 42855 | 4.3248 | 0.4133 |
67
 
68
 
69
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 6.5739
21
+ - Accuracy: 0.4129
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
+ | 1.2998 | 1.0 | 5714 | 1.3409 | 0.3419 |
53
+ | 1.1366 | 2.0 | 11428 | 1.3753 | 0.3634 |
54
+ | 0.9035 | 3.0 | 17142 | 1.4999 | 0.3794 |
55
+ | 0.6883 | 4.0 | 22856 | 1.7468 | 0.3906 |
56
+ | 0.5177 | 5.0 | 28570 | 2.1011 | 0.3997 |
57
+ | 0.3968 | 6.0 | 34284 | 2.2910 | 0.4009 |
58
+ | 0.2936 | 7.0 | 39998 | 2.8000 | 0.4121 |
59
+ | 0.2403 | 8.0 | 45712 | 2.7002 | 0.4086 |
60
+ | 0.1843 | 9.0 | 51426 | 3.4014 | 0.4160 |
61
+ | 0.1478 | 10.0 | 57140 | 3.5690 | 0.4057 |
62
+ | 0.1231 | 11.0 | 62854 | 4.3858 | 0.4102 |
63
+ | 0.1027 | 12.0 | 68568 | 4.6814 | 0.4124 |
64
+ | 0.0897 | 13.0 | 74282 | 4.9962 | 0.4186 |
65
+ | 0.0823 | 14.0 | 79996 | 6.0199 | 0.4160 |
66
+ | 0.0631 | 15.0 | 85710 | 6.5739 | 0.4129 |
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c92f168fcd8c7aaf11652fbc0dfdc82d2bc089bb00bb69fcac912782225f341
3
  size 267829484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d306629c74561d10507648df7158a6a73ff9904a21e1c9126acc12cc7262332
3
  size 267829484