yishairasowsky commited on
Commit
29f622e
·
verified ·
1 Parent(s): 93e425c

End of training

Browse files
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
- license: mit
4
- base_model: prajjwal1/bert-medium
5
  tags:
6
  - generated_from_trainer
7
  metrics:
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # my_awesome_swag_model
18
 
19
- This model is a fine-tuned version of [prajjwal1/bert-medium](https://huggingface.co/prajjwal1/bert-medium) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.2680
22
- - Accuracy: 0.46
23
 
24
  ## Model description
25
 
@@ -38,7 +38,7 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 5e-05
42
  - train_batch_size: 8
43
  - eval_batch_size: 8
44
  - seed: 42
@@ -50,12 +50,12 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | No log | 1.0 | 7 | 1.3530 | 0.42 |
54
- | No log | 2.0 | 14 | 1.3340 | 0.42 |
55
- | No log | 3.0 | 21 | 1.3074 | 0.42 |
56
- | No log | 4.0 | 28 | 1.2832 | 0.42 |
57
- | No log | 5.0 | 35 | 1.2727 | 0.46 |
58
- | No log | 6.0 | 42 | 1.2680 | 0.46 |
59
 
60
 
61
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ license: apache-2.0
4
+ base_model: distilbert-base-uncased
5
  tags:
6
  - generated_from_trainer
7
  metrics:
 
16
 
17
  # my_awesome_swag_model
18
 
19
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.2469
22
+ - Accuracy: 0.466
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 1e-05
42
  - train_batch_size: 8
43
  - eval_batch_size: 8
44
  - seed: 42
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | No log | 1.0 | 63 | 1.3792 | 0.342 |
54
+ | No log | 2.0 | 126 | 1.3472 | 0.368 |
55
+ | No log | 3.0 | 189 | 1.2936 | 0.434 |
56
+ | No log | 4.0 | 252 | 1.2597 | 0.454 |
57
+ | No log | 5.0 | 315 | 1.2518 | 0.46 |
58
+ | No log | 6.0 | 378 | 1.2469 | 0.466 |
59
 
60
 
61
  ### Framework versions
runs/Jan08_14-17-01_33098bc040ab/events.out.tfevents.1736345823.33098bc040ab.897.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bed1632b7e41631b4a9d498ca77504fb8f1978df509f407f97d28b78691fa54a
3
- size 6560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ccfd2990f10f53a1c3e92659ba0792c91e188dd4e6b2874d35b879a2bba78c8
3
+ size 7237