TeeA commited on
Commit
02a6d3d
·
1 Parent(s): 34015c9

End of training

Browse files
Files changed (2) hide show
  1. README.md +10 -23
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,10 +1,8 @@
1
  ---
2
  license: mit
3
- base_model: roberta-base
4
  tags:
5
  - generated_from_trainer
6
- metrics:
7
- - accuracy
8
  model-index:
9
  - name: roberta-classifier-pokemon
10
  results: []
@@ -15,10 +13,15 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # roberta-classifier-pokemon
17
 
18
- This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 8.5882
21
- - Accuracy: 0.0597
 
 
 
 
 
22
 
23
  ## Model description
24
 
@@ -43,23 +46,7 @@ The following hyperparameters were used during training:
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 10
47
-
48
- ### Training results
49
-
50
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | 0.3974 | 1.0 | 305 | 7.3832 | 0.0353 |
53
- | 0.3071 | 2.0 | 610 | 7.5483 | 0.0410 |
54
- | 0.2818 | 3.0 | 915 | 7.6781 | 0.0496 |
55
- | 0.2237 | 4.0 | 1220 | 7.8697 | 0.0554 |
56
- | 0.1664 | 5.0 | 1525 | 8.0893 | 0.0518 |
57
- | 0.1302 | 6.0 | 1830 | 8.1503 | 0.0532 |
58
- | 0.0928 | 7.0 | 2135 | 8.2650 | 0.0612 |
59
- | 0.0738 | 8.0 | 2440 | 8.4590 | 0.0597 |
60
- | 0.0555 | 9.0 | 2745 | 8.5490 | 0.0604 |
61
- | 0.0437 | 10.0 | 3050 | 8.5882 | 0.0597 |
62
-
63
 
64
  ### Framework versions
65
 
 
1
  ---
2
  license: mit
3
+ base_model: TeeA/roberta-classifier-pokemon
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: roberta-classifier-pokemon
8
  results: []
 
13
 
14
  # roberta-classifier-pokemon
15
 
16
+ This model is a fine-tuned version of [TeeA/roberta-classifier-pokemon](https://huggingface.co/TeeA/roberta-classifier-pokemon) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - eval_loss: 11.3963
19
+ - eval_accuracy: 0.0619
20
+ - eval_runtime: 6.6209
21
+ - eval_samples_per_second: 209.942
22
+ - eval_steps_per_second: 13.14
23
+ - epoch: 22.0
24
+ - step: 6710
25
 
26
  ## Model description
27
 
 
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
 
51
  ### Framework versions
52
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6120bd6691b562707f84d41491491fcf7c44840f4c2dc0e4ef0d9aeac9801ad
3
  size 499068072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf169f7c7fdba5575c9f940828b8953925cf5032eb6ac26e84fdcf786ff05c8
3
  size 499068072