VuongQuoc commited on
Commit
b94cbb4
1 Parent(s): cd5c589

Model save

Browse files
Files changed (3) hide show
  1. README.md +9 -40
  2. pytorch_model.bin +2 -2
  3. training_args.bin +2 -2
README.md CHANGED
@@ -1,4 +1,6 @@
1
  ---
 
 
2
  tags:
3
  - generated_from_trainer
4
  model-index:
@@ -11,9 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
11
 
12
  # Debertalarg_model_multichoice_Version2
13
 
14
- This model is a fine-tuned version of [VuongQuoc/Debertalarg_model_multichoice_Version2](https://huggingface.co/VuongQuoc/Debertalarg_model_multichoice_Version2) on an unknown dataset.
15
- It achieves the following results on the evaluation set:
16
- - Loss: 0.8611
17
 
18
  ## Model description
19
 
@@ -32,49 +32,18 @@ More information needed
32
  ### Training hyperparameters
33
 
34
  The following hyperparameters were used during training:
35
- - learning_rate: 7e-07
36
- - train_batch_size: 2
37
- - eval_batch_size: 4
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
- - lr_scheduler_warmup_ratio: 0.1
42
- - num_epochs: 1
43
-
44
- ### Training results
45
-
46
- | Training Loss | Epoch | Step | Validation Loss |
47
- |:-------------:|:-----:|:----:|:---------------:|
48
- | 1.0591 | 0.04 | 300 | 0.8278 |
49
- | 1.1284 | 0.08 | 600 | 0.8545 |
50
- | 1.0894 | 0.12 | 900 | 0.8821 |
51
- | 0.9937 | 0.16 | 1200 | 0.9260 |
52
- | 0.8916 | 0.2 | 1500 | 0.9562 |
53
- | 0.7818 | 0.24 | 1800 | 1.0041 |
54
- | 0.7193 | 0.28 | 2100 | 1.0704 |
55
- | 0.712 | 0.32 | 2400 | 1.0295 |
56
- | 0.6913 | 0.36 | 2700 | 1.0537 |
57
- | 0.4193 | 0.4 | 3000 | 1.1205 |
58
- | 0.4197 | 0.44 | 3300 | 1.1187 |
59
- | 0.3394 | 0.48 | 3600 | 1.1435 |
60
- | 0.2916 | 0.52 | 3900 | 1.2060 |
61
- | 0.1957 | 0.56 | 4200 | 1.2312 |
62
- | 0.2363 | 0.6 | 4500 | 1.1874 |
63
- | 0.1818 | 0.64 | 4800 | 1.2510 |
64
- | 0.1853 | 0.68 | 5100 | 1.2274 |
65
- | 0.1488 | 0.72 | 5400 | 1.2450 |
66
- | 0.1007 | 0.76 | 5700 | 1.2106 |
67
- | 0.1387 | 0.8 | 6000 | 1.2997 |
68
- | 2.1064 | 0.84 | 6300 | 0.9987 |
69
- | 1.5963 | 0.88 | 6600 | 0.9290 |
70
- | 1.5086 | 0.92 | 6900 | 0.8935 |
71
- | 1.56 | 0.96 | 7200 | 0.8637 |
72
- | 1.3432 | 1.0 | 7500 | 0.8611 |
73
-
74
 
75
  ### Framework versions
76
 
77
- - Transformers 4.30.2
78
  - Pytorch 2.0.0
79
  - Datasets 2.1.0
80
  - Tokenizers 0.13.3
 
1
  ---
2
+ license: mit
3
+ base_model: microsoft/deberta-v3-large
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
13
 
14
  # Debertalarg_model_multichoice_Version2
15
 
16
+ This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
 
 
17
 
18
  ## Model description
19
 
 
32
  ### Training hyperparameters
33
 
34
  The following hyperparameters were used during training:
35
+ - learning_rate: 5e-06
36
+ - train_batch_size: 32
37
+ - eval_batch_size: 32
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
+ - lr_scheduler_warmup_ratio: 0.8
42
+ - num_epochs: 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
 
44
  ### Framework versions
45
 
46
+ - Transformers 4.33.0
47
  - Pytorch 2.0.0
48
  - Datasets 2.1.0
49
  - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7566a7d62e7dcca707476745ab785f015d9e267591277cc44b3388f665c28cf6
3
- size 1740392185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:910cede3dd2ebe0d786d41b6934950525c450bb8f022c054a54728ecf40a81e2
3
+ size 1753439621
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14fa027f7ec97d4f48a713323700f6a2407c38e195a2c9460fb1f57c437455e9
3
- size 3963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:202cc2df10534b5be0771f7d469d908504985d10430b9bcc3440fce84753e78f
3
+ size 4091