Hugging Face's logo

TungCan
/
tuning-sentiment-5cdviso

Text Classification
Transformers
Safetensors
xlm-roberta
Generated from Trainer
Model card Files
xet
Community
TungCan commited on
Commit
ef6cc28
·
verified ·
1 Parent(s): 8b1a153

TungCan/Sentiment-Finetune

Browse files
Files changed (3) hide show
  1. README.md +20 -24
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [5CD-AI/Vietnamese-Sentiment-visobert](https://huggingface.co/5CD-AI/Vietnamese-Sentiment-visobert) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0617
24
- - Accuracy: 0.984
25
- - F1: 0.9840
26
- - Precision: 0.9837
27
- - Recall: 0.9844
28
 
29
  ## Model description
30
 
@@ -44,34 +44,30 @@ More information needed
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 2e-05
47
- - train_batch_size: 32
48
- - eval_batch_size: 32
49
  - seed: 42
50
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
52
- - num_epochs: 4
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
58
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
59
- | 0.6027 | 0.2451 | 50 | 0.3793 | 0.856 | 0.8561 | 0.8604 | 0.8621 |
60
- | 0.4082 | 0.4902 | 100 | 0.3015 | 0.8806 | 0.8804 | 0.8815 | 0.8854 |
61
- | 0.3498 | 0.7353 | 150 | 0.2385 | 0.9138 | 0.9140 | 0.9132 | 0.9156 |
62
- | 0.3354 | 0.9804 | 200 | 0.1968 | 0.92 | 0.9203 | 0.9199 | 0.9210 |
63
- | 0.2146 | 1.2255 | 250 | 0.2305 | 0.9132 | 0.9140 | 0.9178 | 0.9182 |
64
- | 0.2103 | 1.4706 | 300 | 0.1952 | 0.9255 | 0.9256 | 0.9276 | 0.9301 |
65
- | 0.2094 | 1.7157 | 350 | 0.1357 | 0.9563 | 0.9563 | 0.9563 | 0.9563 |
66
- | 0.2165 | 1.9608 | 400 | 0.1214 | 0.9612 | 0.9611 | 0.9621 | 0.9603 |
67
- | 0.1226 | 2.2059 | 450 | 0.1238 | 0.9618 | 0.9618 | 0.9612 | 0.9629 |
68
- | 0.1409 | 2.4510 | 500 | 0.1241 | 0.9538 | 0.9539 | 0.9540 | 0.9569 |
69
- | 0.138 | 2.6961 | 550 | 0.0839 | 0.9735 | 0.9735 | 0.9730 | 0.9740 |
70
- | 0.1246 | 2.9412 | 600 | 0.0717 | 0.9809 | 0.9809 | 0.9807 | 0.9812 |
71
- | 0.0724 | 3.1863 | 650 | 0.0761 | 0.9791 | 0.9791 | 0.9785 | 0.9799 |
72
- | 0.0851 | 3.4314 | 700 | 0.0686 | 0.9822 | 0.9821 | 0.9821 | 0.9822 |
73
- | 0.0917 | 3.6765 | 750 | 0.0636 | 0.9828 | 0.9828 | 0.9829 | 0.9827 |
74
- | 0.071 | 3.9216 | 800 | 0.0621 | 0.984 | 0.9840 | 0.9837 | 0.9844 |
75
 
76
 
77
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [5CD-AI/Vietnamese-Sentiment-visobert](https://huggingface.co/5CD-AI/Vietnamese-Sentiment-visobert) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.1095
24
+ - Accuracy: 0.9778
25
+ - F1: 0.9780
26
+ - Precision: 0.9780
27
+ - Recall: 0.9781
28
 
29
  ## Model description
30
 
 
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 2e-05
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 16
49
  - seed: 42
50
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 3
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
58
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
59
+ | 0.5372 | 0.2457 | 100 | 0.3840 | 0.8572 | 0.8542 | 0.8716 | 0.8510 |
60
+ | 0.3776 | 0.4914 | 200 | 0.2550 | 0.9058 | 0.9069 | 0.9066 | 0.9075 |
61
+ | 0.3333 | 0.7371 | 300 | 0.2245 | 0.9169 | 0.9181 | 0.9184 | 0.9196 |
62
+ | 0.3303 | 0.9828 | 400 | 0.1704 | 0.9471 | 0.9475 | 0.9483 | 0.9468 |
63
+ | 0.2117 | 1.2285 | 500 | 0.1635 | 0.9458 | 0.9464 | 0.9459 | 0.9471 |
64
+ | 0.2127 | 1.4742 | 600 | 0.1304 | 0.9538 | 0.9539 | 0.9550 | 0.9531 |
65
+ | 0.2021 | 1.7199 | 700 | 0.1385 | 0.9631 | 0.9634 | 0.9627 | 0.9647 |
66
+ | 0.2121 | 1.9656 | 800 | 0.1095 | 0.9655 | 0.9659 | 0.9651 | 0.9673 |
67
+ | 0.1499 | 2.2113 | 900 | 0.1195 | 0.9705 | 0.9708 | 0.9699 | 0.9723 |
68
+ | 0.1323 | 2.4570 | 1000 | 0.1101 | 0.976 | 0.9762 | 0.9757 | 0.9768 |
69
+ | 0.1566 | 2.7027 | 1100 | 0.1125 | 0.9772 | 0.9774 | 0.9776 | 0.9772 |
70
+ | 0.144 | 2.9484 | 1200 | 0.1097 | 0.9778 | 0.9780 | 0.9781 | 0.9780 |
 
 
 
 
71
 
72
 
73
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8fedf0db3ac800b3931b3656561e291f1f426e1e9ea1c81968a10bdd7995b46
3
  size 390297116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d66bd15511f2a52362d9ebadcdaac617d7bcf3422e438d7e144bec03941a0361
3
  size 390297116
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb26ce40ab8e40402c122a1325cb48d59b18cc434fabe01992dd2091b88f8952
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a17cc69f0009c075fdb3206653317fe03e482fb6fcbcb39e59832329b75a1507
3
  size 5240