Yousefmd commited on
Commit
ad48f05
·
1 Parent(s): 7885e8e

Model save

Browse files
Files changed (2) hide show
  1. README.md +12 -11
  2. config.json +8 -8
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- base_model: aubmindlab/bert-large-arabertv02
3
  tags:
4
  - generated_from_trainer
5
  metrics:
@@ -14,11 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # arabert-sentiment-classification
16
 
17
- This model is a fine-tuned version of [aubmindlab/bert-large-arabertv02](https://huggingface.co/aubmindlab/bert-large-arabertv02) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.7645
20
- - Macro F1: 0.7216
21
- - Accuracy: 0.7216
22
 
23
  ## Model description
24
 
@@ -39,24 +39,25 @@ More information needed
39
  The following hyperparameters were used during training:
40
  - learning_rate: 2e-05
41
  - train_batch_size: 32
42
- - eval_batch_size: 128
43
- - seed: 42
44
  - gradient_accumulation_steps: 2
45
  - total_train_batch_size: 64
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - num_epochs: 2
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
54
- | No log | 1.0 | 249 | 1.0181 | 0.5867 | 0.5867 |
55
- | No log | 2.0 | 498 | 0.7645 | 0.7216 | 0.7216 |
 
56
 
57
 
58
  ### Framework versions
59
 
60
  - Transformers 4.34.0
61
- - Pytorch 1.12.0
62
  - Tokenizers 0.14.1
 
1
  ---
2
+ base_model: aubmindlab/bert-large-arabertv2
3
  tags:
4
  - generated_from_trainer
5
  metrics:
 
14
 
15
  # arabert-sentiment-classification
16
 
17
+ This model is a fine-tuned version of [aubmindlab/bert-large-arabertv2](https://huggingface.co/aubmindlab/bert-large-arabertv2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.5565
20
+ - Macro F1: 0.6590
21
+ - Accuracy: 0.8
22
 
23
  ## Model description
24
 
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 2e-05
41
  - train_batch_size: 32
42
+ - eval_batch_size: 32
43
+ - seed: 25
44
  - gradient_accumulation_steps: 2
45
  - total_train_batch_size: 64
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - num_epochs: 3
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
54
+ | No log | 1.0 | 249 | 0.5578 | 0.6338 | 0.7925 |
55
+ | No log | 2.0 | 498 | 0.5477 | 0.6342 | 0.7922 |
56
+ | 0.6623 | 3.0 | 747 | 0.5565 | 0.6590 | 0.8 |
57
 
58
 
59
  ### Framework versions
60
 
61
  - Transformers 4.34.0
62
+ - Pytorch 2.0.1+cu118
63
  - Tokenizers 0.14.1
config.json CHANGED
@@ -9,18 +9,18 @@
9
  "hidden_dropout_prob": 0.1,
10
  "hidden_size": 1024,
11
  "id2label": {
12
- "0": "LABEL_0",
13
- "1": "LABEL_1",
14
- "2": "LABEL_2",
15
- "3": "LABEL_3"
16
  },
17
  "initializer_range": 0.02,
18
  "intermediate_size": 4096,
19
  "label2id": {
20
- "LABEL_0": 0,
21
- "LABEL_1": 1,
22
- "LABEL_2": 2,
23
- "LABEL_3": 3
24
  },
25
  "layer_norm_eps": 1e-12,
26
  "max_position_embeddings": 512,
 
9
  "hidden_dropout_prob": 0.1,
10
  "hidden_size": 1024,
11
  "id2label": {
12
+ "0": "Positive",
13
+ "1": "Negative",
14
+ "2": "Neutral",
15
+ "3": "Mixed"
16
  },
17
  "initializer_range": 0.02,
18
  "intermediate_size": 4096,
19
  "label2id": {
20
+ "Mixed": 3,
21
+ "Negative": 1,
22
+ "Neutral": 2,
23
+ "Positive": 0
24
  },
25
  "layer_norm_eps": 1e-12,
26
  "max_position_embeddings": 512,