aisuko commited on
Commit
647a852
1 Parent(s): b5098d4

End of training

Browse files
Files changed (3) hide show
  1. README.md +20 -8
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -4,12 +4,25 @@ base_model: bert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
- - swag
8
  metrics:
9
  - accuracy
10
  model-index:
11
  - name: ft-bert-with-swag
12
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -19,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the swag dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.5656
23
- - Accuracy: 0.7797
24
 
25
  ## Model description
26
 
@@ -45,15 +58,14 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - num_epochs: 3
 
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
- | 0.7503 | 1.0 | 2299 | 0.5656 | 0.7797 |
55
- | 0.3776 | 2.0 | 4598 | 0.5692 | 0.7986 |
56
- | 0.1457 | 3.0 | 6897 | 0.7690 | 0.8022 |
57
 
58
 
59
  ### Framework versions
 
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
+ - text-classification
8
  metrics:
9
  - accuracy
10
  model-index:
11
  - name: ft-bert-with-swag
12
+ results:
13
+ - task:
14
+ name: Multiple Choice
15
+ type: multiple-choice
16
+ dataset:
17
+ name: swag
18
+ type: text-classification
19
+ config: regular
20
+ split: train[:500]
21
+ args: regular
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.48
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the swag dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.2843
36
+ - Accuracy: 0.48
37
 
38
  ## Model description
39
 
 
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 1
62
+ - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | No log | 1.0 | 13 | 1.2843 | 0.48 |
 
 
69
 
70
 
71
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fe48aaefdde8828f23a49f38757fe143c85d1ed5a591d4789b9933bf0407cb8
3
  size 437955572
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5771565338e1dbf04b2bfe03d564d095dd748f5b8c9ada1c5ea1b3ec17fbd16d
3
  size 437955572
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e375616bba3e8686b29ad6169332ed34c4ce95ee7fcd28bf401933b698532ee
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e0080780cc0e7e0f2288ea900b4a58540d97b41036f3acf646a8c998dbb389e
3
  size 4155