Hugging Face's logo

Shaer-AI
/
ARBERT-base-submeter-classifier

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
NourFakih commited on
Commit
1c4a1c1
·
verified ·
1 Parent(s): 8185c63

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +91 -9
README.md CHANGED
@@ -1,16 +1,98 @@
1
  ---
2
- language: ar
3
  library_name: transformers
4
- pipeline_tag: text-classification
 
 
 
 
 
 
 
5
  ---
6
- # ARBERT Arabic Poetry Sub-meter Classifier
7
 
8
- Fine-tuned from `UBC-NLP/ARBERT` for 25 Arabic poetry meter–variant classes.
 
9
 
10
- Input: `first_hemistich S second_hemistich`
11
 
12
- Accuracy: 0.970778
13
- Macro F1: 0.599438
14
- Weighted F1: 0.965299
 
 
 
15
 
16
- The checkpoint includes the complete trained 25-class sequence-classification head.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
2
  library_name: transformers
3
+ base_model: UBC-NLP/ARBERT
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: ARBERT-base-submeter-classifier
10
+ results: []
11
  ---
 
12
 
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
 
16
+ # ARBERT-base-submeter-classifier
17
 
18
+ This model is a fine-tuned version of [UBC-NLP/ARBERT](https://huggingface.co/UBC-NLP/ARBERT) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.1113
21
+ - Accuracy: 0.9709
22
+ - Macro F1: 0.6021
23
+ - Weighted F1: 0.9654
24
 
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 128
44
+ - eval_batch_size: 256
45
+ - seed: 42
46
+ - gradient_accumulation_steps: 2
47
+ - total_train_batch_size: 256
48
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: linear
50
+ - num_epochs: 3
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Weighted F1 |
56
+ |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|:-----------:|
57
+ | 1.2986 | 0.0865 | 500 | 0.7567 | 0.7652 | 0.2987 | 0.7566 |
58
+ | 0.5963 | 0.1730 | 1000 | 0.4073 | 0.8766 | 0.4198 | 0.8677 |
59
+ | 0.3789 | 0.2594 | 1500 | 0.2946 | 0.9137 | 0.4782 | 0.9067 |
60
+ | 0.2838 | 0.3459 | 2000 | 0.2346 | 0.9315 | 0.5072 | 0.9263 |
61
+ | 0.2401 | 0.4324 | 2500 | 0.2036 | 0.9422 | 0.5251 | 0.9357 |
62
+ | 0.2168 | 0.5189 | 3000 | 0.1820 | 0.9480 | 0.5299 | 0.9418 |
63
+ | 0.1955 | 0.6054 | 3500 | 0.1703 | 0.9519 | 0.5376 | 0.9455 |
64
+ | 0.1782 | 0.6919 | 4000 | 0.1578 | 0.9557 | 0.5499 | 0.9496 |
65
+ | 0.1699 | 0.7783 | 4500 | 0.1534 | 0.9571 | 0.5466 | 0.9508 |
66
+ | 0.1622 | 0.8648 | 5000 | 0.1496 | 0.9585 | 0.5579 | 0.9523 |
67
+ | 0.1569 | 0.9513 | 5500 | 0.1450 | 0.9602 | 0.5472 | 0.9537 |
68
+ | 0.1422 | 1.0377 | 6000 | 0.1469 | 0.9593 | 0.5690 | 0.9533 |
69
+ | 0.1251 | 1.1242 | 6500 | 0.1369 | 0.9628 | 0.5801 | 0.9568 |
70
+ | 0.123 | 1.2107 | 7000 | 0.1349 | 0.9632 | 0.5686 | 0.9571 |
71
+ | 0.1208 | 1.2972 | 7500 | 0.1337 | 0.9639 | 0.5747 | 0.9577 |
72
+ | 0.1188 | 1.3836 | 8000 | 0.1307 | 0.9645 | 0.5725 | 0.9581 |
73
+ | 0.1201 | 1.4701 | 8500 | 0.1295 | 0.9651 | 0.5705 | 0.9588 |
74
+ | 0.118 | 1.5566 | 9000 | 0.1271 | 0.9657 | 0.5692 | 0.9594 |
75
+ | 0.1167 | 1.6431 | 9500 | 0.1259 | 0.9662 | 0.5795 | 0.9600 |
76
+ | 0.1133 | 1.7296 | 10000 | 0.1220 | 0.9671 | 0.5803 | 0.9609 |
77
+ | 0.1116 | 1.8161 | 10500 | 0.1210 | 0.9674 | 0.5835 | 0.9612 |
78
+ | 0.1103 | 1.9025 | 11000 | 0.1165 | 0.9685 | 0.5836 | 0.9623 |
79
+ | 0.1093 | 1.9890 | 11500 | 0.1172 | 0.9683 | 0.5835 | 0.9623 |
80
+ | 0.0899 | 2.0754 | 12000 | 0.1174 | 0.9689 | 0.5972 | 0.9632 |
81
+ | 0.0851 | 2.1619 | 12500 | 0.1171 | 0.9692 | 0.5858 | 0.9632 |
82
+ | 0.0862 | 2.2484 | 13000 | 0.1172 | 0.9688 | 0.5902 | 0.9635 |
83
+ | 0.0835 | 2.3349 | 13500 | 0.1162 | 0.9696 | 0.5970 | 0.9638 |
84
+ | 0.0854 | 2.4213 | 14000 | 0.1159 | 0.9694 | 0.5925 | 0.9639 |
85
+ | 0.0797 | 2.5078 | 14500 | 0.1157 | 0.9698 | 0.5934 | 0.9640 |
86
+ | 0.0819 | 2.5943 | 15000 | 0.1152 | 0.9698 | 0.6004 | 0.9643 |
87
+ | 0.0813 | 2.6808 | 15500 | 0.1135 | 0.9703 | 0.5964 | 0.9646 |
88
+ | 0.0792 | 2.7673 | 16000 | 0.1120 | 0.9706 | 0.6000 | 0.9649 |
89
+ | 0.0786 | 2.8538 | 16500 | 0.1116 | 0.9707 | 0.6010 | 0.9653 |
90
+ | 0.0789 | 2.9402 | 17000 | 0.1113 | 0.9709 | 0.6021 | 0.9654 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.57.6
96
+ - Pytorch 2.10.0+cu128
97
+ - Datasets 3.6.0
98
+ - Tokenizers 0.22.2