Hugging Face's logo

DPhO05
/
my-roberta-RQ3

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
DPhO05 commited on
Commit
7f925c9
·
verified ·
1 Parent(s): f14e87e

End of training

Browse files
Files changed (2) hide show
  1. README.md +54 -46
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,66 +1,74 @@
1
  ---
2
- language: vi
3
  license: mit
4
- base_model: facebook/roberta-base
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: my-roberta-RQ3
9
- results:
10
- - task:
11
- type: text-classification
12
- name: Text Classification
13
- dataset:
14
- name: Unknown Dataset
15
- type: unknown
16
- metrics:
17
- - type: accuracy
18
- value: 0.9462
19
- name: Accuracy
20
- - type: f1
21
- value: 0.5894
22
- name: F1 Macro
23
- - type: f1
24
- value: 0.9458
25
- name: F1 Weighted
26
- - type: loss
27
- value: 0.4223
28
- name: Loss
29
  ---
30
 
 
 
 
31
  # my-roberta-RQ3
32
 
33
- This model is a fine-tuned version of [facebook/roberta-base](https://huggingface.co/facebook/roberta-base).
 
 
 
 
 
34
 
35
- ## Test Results
36
- Dựa trên kết quả đánh giá cuối cùng tại Epoch 10:
37
 
38
- - **Eval Loss:** 0.4223
39
- - **Eval Accuracy:** 0.9462
40
- - **Eval F1 Macro:** 0.5894
41
- - **Eval F1 Weighted:** 0.9458
42
- - **Eval Runtime:** 33.1771 seconds
43
- - **Samples Per Second:** 129.8790
44
- - **Steps Per Second:** 2.0500
45
 
46
- ## Training results
47
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Weighted |
48
- |:---:|:---:|:---:|:---:|:---:|:---:|:---:|
49
- | ... | ... | ... | ... | ... | ... | ... |
50
- | 0.4149 | 10.0 | 5390 | 0.4223 | 0.9462 | 0.5894 | 0.9458 |
 
 
 
 
 
 
51
 
52
- ## Training hyperparameters
53
  The following hyperparameters were used during training:
54
  - learning_rate: 1e-05
55
- - train_batch_size: 32
56
- - eval_batch_size: 32
57
  - seed: 42
58
- - optimizer: AdamW
59
  - lr_scheduler_type: linear
 
60
  - num_epochs: 10
61
- - mixed_precision_training: Native AMP (fp16)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
 
63
- ## Framework versions
64
- - Transformers: 4.x.x
65
- - Pytorch: 2.x.x
66
- - Tokenizers: 0.x.x
 
1
  ---
2
+ library_name: transformers
3
  license: mit
4
+ base_model: FacebookAI/roberta-base
5
  tags:
6
  - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
  model-index:
10
  - name: my-roberta-RQ3
11
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
 
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
  # my-roberta-RQ3
18
 
19
+ This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4273
22
+ - Accuracy: 0.9480
23
+ - F1 Macro: 0.6383
24
+ - F1 Weighted: 0.9479
25
 
26
+ ## Model description
 
27
 
28
+ More information needed
 
 
 
 
 
 
29
 
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
 
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 1e-05
44
+ - train_batch_size: 64
45
+ - eval_batch_size: 64
46
  - seed: 42
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 0.1
50
  - num_epochs: 10
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Weighted |
56
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|
57
+ | 0.3765 | 1.0 | 539 | 0.3696 | 0.9394 | 0.3048 | 0.9294 |
58
+ | 0.3333 | 2.0 | 1078 | 0.3297 | 0.9473 | 0.4082 | 0.9423 |
59
+ | 0.2892 | 3.0 | 1617 | 0.3122 | 0.9499 | 0.4966 | 0.9468 |
60
+ | 0.2429 | 4.0 | 2156 | 0.3167 | 0.9534 | 0.6575 | 0.9518 |
61
+ | 0.1842 | 5.0 | 2695 | 0.3338 | 0.9476 | 0.6299 | 0.9480 |
62
+ | 0.1577 | 6.0 | 3234 | 0.3656 | 0.9513 | 0.6632 | 0.9512 |
63
+ | 0.1413 | 7.0 | 3773 | 0.3701 | 0.9494 | 0.6440 | 0.9494 |
64
+ | 0.1064 | 8.0 | 4312 | 0.4169 | 0.9489 | 0.6454 | 0.9492 |
65
+ | 0.1277 | 9.0 | 4851 | 0.4233 | 0.9480 | 0.6350 | 0.9475 |
66
+ | 0.0979 | 10.0 | 5390 | 0.4273 | 0.9480 | 0.6383 | 0.9479 |
67
+
68
+
69
+ ### Framework versions
70
 
71
+ - Transformers 5.0.0
72
+ - Pytorch 2.10.0+cu128
73
+ - Datasets 4.8.3
74
+ - Tokenizers 0.22.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:553e4e3b9b78a1c7db9ff27536ecca2763b169374f00ad598f48be17bf7662d1
3
  size 498625104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19bdbfd96086d0aad996faad9cccc33fa3a36db8cae35773ae63d18c6150412d
3
  size 498625104