Hugging Face's logo

liuyanchen1015
/
roberta-base-mnli_ChcE

Text Classification
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
liuyanchen1015 commited on
Commit
3c2ac76
•
1 Parent(s): 1973968

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -22
README.md CHANGED
@@ -3,19 +3,19 @@ license: mit
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
- - name: mnli_ChcE
7
  results: []
8
  ---
9
 
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
  should probably proofread and complete it, then remove this comment. -->
12
 
13
- # mnli_ChcE
14
 
15
  This model is a fine-tuned version of [WillHeld/roberta-base-mnli](https://huggingface.co/WillHeld/roberta-base-mnli) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.5320
18
- - Acc: 0.8721
19
 
20
  ## Model description
21
 
@@ -40,29 +40,41 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 3
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss | Acc |
48
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
49
- | 0.3096 | 0.17 | 2000 | 0.4133 | 0.8553 |
50
- | 0.3028 | 0.33 | 4000 | 0.3985 | 0.8665 |
51
- | 0.3005 | 0.5 | 6000 | 0.3883 | 0.8671 |
52
- | 0.2973 | 0.67 | 8000 | 0.3959 | 0.8648 |
53
- | 0.2921 | 0.83 | 10000 | 0.4101 | 0.8662 |
54
- | 0.2934 | 1.0 | 12000 | 0.4040 | 0.8675 |
55
- | 0.2034 | 1.17 | 14000 | 0.4498 | 0.8651 |
56
- | 0.2021 | 1.33 | 16000 | 0.4749 | 0.8646 |
57
- | 0.2027 | 1.5 | 18000 | 0.4369 | 0.8685 |
58
- | 0.2001 | 1.67 | 20000 | 0.4337 | 0.8699 |
59
- | 0.2014 | 1.83 | 22000 | 0.4438 | 0.8672 |
60
- | 0.1945 | 2.0 | 24000 | 0.4623 | 0.8679 |
61
- | 0.1371 | 2.17 | 26000 | 0.5456 | 0.8705 |
62
- | 0.1404 | 2.33 | 28000 | 0.5174 | 0.8687 |
63
- | 0.1384 | 2.5 | 30000 | 0.5245 | 0.8708 |
64
- | 0.1347 | 2.67 | 32000 | 0.5402 | 0.8711 |
65
- | 0.137 | 2.84 | 34000 | 0.5320 | 0.8721 |
 
 
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: roberta-base-mnli_ChcE
7
  results: []
8
  ---
9
 
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
  should probably proofread and complete it, then remove this comment. -->
12
 
13
+ # roberta-base-mnli_ChcE
14
 
15
  This model is a fine-tuned version of [WillHeld/roberta-base-mnli](https://huggingface.co/WillHeld/roberta-base-mnli) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.7094
18
+ - Acc: 0.8698
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 5
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss | Acc |
48
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
49
+ | 0.3102 | 0.17 | 2000 | 0.4135 | 0.8545 |
50
+ | 0.3046 | 0.33 | 4000 | 0.4024 | 0.8645 |
51
+ | 0.3038 | 0.5 | 6000 | 0.3936 | 0.8668 |
52
+ | 0.3012 | 0.67 | 8000 | 0.4007 | 0.8625 |
53
+ | 0.2979 | 0.83 | 10000 | 0.4235 | 0.8620 |
54
+ | 0.2997 | 1.0 | 12000 | 0.4031 | 0.8644 |
55
+ | 0.2099 | 1.17 | 14000 | 0.4393 | 0.8633 |
56
+ | 0.2114 | 1.33 | 16000 | 0.4662 | 0.8628 |
57
+ | 0.2147 | 1.5 | 18000 | 0.4331 | 0.8648 |
58
+ | 0.2122 | 1.67 | 20000 | 0.4166 | 0.8702 |
59
+ | 0.2156 | 1.83 | 22000 | 0.4463 | 0.8633 |
60
+ | 0.2117 | 2.0 | 24000 | 0.4637 | 0.8680 |
61
+ | 0.1469 | 2.17 | 26000 | 0.5211 | 0.8681 |
62
+ | 0.1526 | 2.33 | 28000 | 0.5206 | 0.8620 |
63
+ | 0.1494 | 2.5 | 30000 | 0.5168 | 0.8664 |
64
+ | 0.1519 | 2.67 | 32000 | 0.4830 | 0.8700 |
65
+ | 0.152 | 2.84 | 34000 | 0.5465 | 0.8636 |
66
+ | 0.1498 | 3.0 | 36000 | 0.5550 | 0.8680 |
67
+ | 0.1131 | 3.17 | 38000 | 0.6764 | 0.8602 |
68
+ | 0.1135 | 3.34 | 40000 | 0.6200 | 0.8657 |
69
+ | 0.1175 | 3.5 | 42000 | 0.5889 | 0.8671 |
70
+ | 0.1156 | 3.67 | 44000 | 0.6300 | 0.8663 |
71
+ | 0.1104 | 3.84 | 46000 | 0.6045 | 0.8690 |
72
+ | 0.1111 | 4.0 | 48000 | 0.6413 | 0.8694 |
73
+ | 0.086 | 4.17 | 50000 | 0.7271 | 0.8658 |
74
+ | 0.0895 | 4.34 | 52000 | 0.7274 | 0.8683 |
75
+ | 0.0867 | 4.5 | 54000 | 0.7226 | 0.8658 |
76
+ | 0.0886 | 4.67 | 56000 | 0.7182 | 0.8691 |
77
+ | 0.0849 | 4.84 | 58000 | 0.7094 | 0.8698 |
78
 
79
 
80
  ### Framework versions