Hugging Face's logo

liuyanchen1015
/
roberta-base-mnli_CollSgE

Text Classification
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
liuyanchen1015 commited on
Commit
5810c46
•
1 Parent(s): 532cf33

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_CollSgE
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_CollSgE
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: 0.5544
18
- - Acc: 0.8501
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
- | 0.4124 | 0.17 | 2000 | 0.4689 | 0.8311 |
50
- | 0.4013 | 0.33 | 4000 | 0.4615 | 0.8321 |
51
- | 0.3867 | 0.5 | 6000 | 0.4457 | 0.8369 |
52
- | 0.3807 | 0.67 | 8000 | 0.4278 | 0.8422 |
53
- | 0.3728 | 0.83 | 10000 | 0.4383 | 0.8404 |
54
- | 0.3702 | 1.0 | 12000 | 0.4330 | 0.8437 |
55
- | 0.2664 | 1.17 | 14000 | 0.5176 | 0.8424 |
56
- | 0.2657 | 1.33 | 16000 | 0.5198 | 0.8433 |
57
- | 0.2731 | 1.5 | 18000 | 0.4909 | 0.8403 |
58
- | 0.2689 | 1.67 | 20000 | 0.4771 | 0.8448 |
59
- | 0.2648 | 1.83 | 22000 | 0.4692 | 0.8482 |
60
- | 0.2641 | 2.0 | 24000 | 0.4924 | 0.8503 |
61
- | 0.1858 | 2.17 | 26000 | 0.5522 | 0.8469 |
62
- | 0.1872 | 2.33 | 28000 | 0.5566 | 0.8487 |
63
- | 0.1893 | 2.5 | 30000 | 0.5387 | 0.8475 |
64
- | 0.1874 | 2.67 | 32000 | 0.5605 | 0.8491 |
65
- | 0.1824 | 2.84 | 34000 | 0.5544 | 0.8501 |
 
 
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: roberta-base-mnli_CollSgE
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_CollSgE
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: 0.7610
18
+ - Acc: 0.8445
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
+ | 0.4123 | 0.17 | 2000 | 0.4693 | 0.8332 |
50
+ | 0.4028 | 0.33 | 4000 | 0.4624 | 0.8338 |
51
+ | 0.3888 | 0.5 | 6000 | 0.4500 | 0.8375 |
52
+ | 0.3841 | 0.67 | 8000 | 0.4281 | 0.8416 |
53
+ | 0.3783 | 0.83 | 10000 | 0.4434 | 0.8365 |
54
+ | 0.3759 | 1.0 | 12000 | 0.4400 | 0.8418 |
55
+ | 0.2721 | 1.17 | 14000 | 0.5022 | 0.8427 |
56
+ | 0.2736 | 1.33 | 16000 | 0.5252 | 0.8431 |
57
+ | 0.2821 | 1.5 | 18000 | 0.4887 | 0.8409 |
58
+ | 0.2802 | 1.67 | 20000 | 0.4758 | 0.8458 |
59
+ | 0.2794 | 1.83 | 22000 | 0.4611 | 0.8458 |
60
+ | 0.2797 | 2.0 | 24000 | 0.4936 | 0.8456 |
61
+ | 0.1915 | 2.17 | 26000 | 0.5545 | 0.8462 |
62
+ | 0.1946 | 2.33 | 28000 | 0.5731 | 0.8443 |
63
+ | 0.2007 | 2.5 | 30000 | 0.5507 | 0.8428 |
64
+ | 0.2008 | 2.67 | 32000 | 0.5499 | 0.8454 |
65
+ | 0.1971 | 2.84 | 34000 | 0.5274 | 0.8483 |
66
+ | 0.2054 | 3.0 | 36000 | 0.5454 | 0.8476 |
67
+ | 0.1436 | 3.17 | 38000 | 0.6787 | 0.8442 |
68
+ | 0.1426 | 3.34 | 40000 | 0.6933 | 0.8421 |
69
+ | 0.1463 | 3.5 | 42000 | 0.6547 | 0.8455 |
70
+ | 0.1447 | 3.67 | 44000 | 0.6469 | 0.8438 |
71
+ | 0.1445 | 3.84 | 46000 | 0.6626 | 0.8472 |
72
+ | 0.1457 | 4.0 | 48000 | 0.6494 | 0.8504 |
73
+ | 0.1133 | 4.17 | 50000 | 0.7664 | 0.8459 |
74
+ | 0.1138 | 4.34 | 52000 | 0.7857 | 0.8452 |
75
+ | 0.1154 | 4.5 | 54000 | 0.7623 | 0.8486 |
76
+ | 0.1102 | 4.67 | 56000 | 0.7740 | 0.8460 |
77
+ | 0.1143 | 4.84 | 58000 | 0.7610 | 0.8445 |
78
 
79
 
80
  ### Framework versions