Hugging Face's logo

MayBashendy
/
Arabic_FineTuningAraBERT_AugV0_k1_task1_organization_fold1

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
MayBashendy commited on
Commit
8717ed4
•
1 Parent(s): 4148e83

Training in progress, step 160

Browse files
Files changed (4) hide show
  1. README.md +144 -0
  2. config.json +32 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: aubmindlab/bert-base-arabertv02
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: Arabic_FineTuningAraBERT_AugV0_k1_task1_organization_fold0
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # Arabic_FineTuningAraBERT_AugV0_k1_task1_organization_fold0
15
+
16
+ This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.6600
19
+ - Qwk: 0.7927
20
+ - Mse: 0.6600
21
+ - Rmse: 0.8124
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 10
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse | Rmse |
51
+ |:-------------:|:------:|:----:|:---------------:|:-------:|:------:|:------:|
52
+ | No log | 0.1176 | 2 | 5.1890 | -0.0064 | 5.1890 | 2.2779 |
53
+ | No log | 0.2353 | 4 | 3.8578 | -0.1290 | 3.8578 | 1.9641 |
54
+ | No log | 0.3529 | 6 | 2.3353 | -0.0151 | 2.3353 | 1.5282 |
55
+ | No log | 0.4706 | 8 | 1.2919 | 0.2434 | 1.2919 | 1.1366 |
56
+ | No log | 0.5882 | 10 | 1.1164 | 0.3552 | 1.1164 | 1.0566 |
57
+ | No log | 0.7059 | 12 | 1.0476 | 0.4059 | 1.0476 | 1.0235 |
58
+ | No log | 0.8235 | 14 | 1.1871 | 0.3527 | 1.1871 | 1.0895 |
59
+ | No log | 0.9412 | 16 | 1.0400 | 0.3026 | 1.0400 | 1.0198 |
60
+ | No log | 1.0588 | 18 | 1.0199 | 0.2667 | 1.0199 | 1.0099 |
61
+ | No log | 1.1765 | 20 | 0.9724 | 0.3326 | 0.9724 | 0.9861 |
62
+ | No log | 1.2941 | 22 | 1.0450 | 0.3845 | 1.0450 | 1.0223 |
63
+ | No log | 1.4118 | 24 | 1.2606 | 0.5542 | 1.2606 | 1.1228 |
64
+ | No log | 1.5294 | 26 | 0.9732 | 0.6092 | 0.9732 | 0.9865 |
65
+ | No log | 1.6471 | 28 | 0.8156 | 0.5438 | 0.8156 | 0.9031 |
66
+ | No log | 1.7647 | 30 | 0.8650 | 0.5446 | 0.8650 | 0.9300 |
67
+ | No log | 1.8824 | 32 | 0.7208 | 0.6144 | 0.7208 | 0.8490 |
68
+ | No log | 2.0 | 34 | 0.8030 | 0.5625 | 0.8030 | 0.8961 |
69
+ | No log | 2.1176 | 36 | 0.8379 | 0.5645 | 0.8379 | 0.9154 |
70
+ | No log | 2.2353 | 38 | 1.0002 | 0.5064 | 1.0002 | 1.0001 |
71
+ | No log | 2.3529 | 40 | 0.9721 | 0.4832 | 0.9721 | 0.9859 |
72
+ | No log | 2.4706 | 42 | 0.7294 | 0.5818 | 0.7294 | 0.8540 |
73
+ | No log | 2.5882 | 44 | 0.6524 | 0.5462 | 0.6524 | 0.8077 |
74
+ | No log | 2.7059 | 46 | 0.7395 | 0.5579 | 0.7395 | 0.8599 |
75
+ | No log | 2.8235 | 48 | 0.7186 | 0.5579 | 0.7186 | 0.8477 |
76
+ | No log | 2.9412 | 50 | 0.6298 | 0.5640 | 0.6298 | 0.7936 |
77
+ | No log | 3.0588 | 52 | 0.8391 | 0.6533 | 0.8391 | 0.9160 |
78
+ | No log | 3.1765 | 54 | 1.0310 | 0.5276 | 1.0310 | 1.0154 |
79
+ | No log | 3.2941 | 56 | 0.9175 | 0.6648 | 0.9175 | 0.9579 |
80
+ | No log | 3.4118 | 58 | 0.7070 | 0.6316 | 0.7070 | 0.8409 |
81
+ | No log | 3.5294 | 60 | 0.6652 | 0.5640 | 0.6652 | 0.8156 |
82
+ | No log | 3.6471 | 62 | 0.6834 | 0.6316 | 0.6834 | 0.8267 |
83
+ | No log | 3.7647 | 64 | 0.6860 | 0.6607 | 0.6860 | 0.8283 |
84
+ | No log | 3.8824 | 66 | 0.6585 | 0.6607 | 0.6585 | 0.8115 |
85
+ | No log | 4.0 | 68 | 0.7025 | 0.6655 | 0.7025 | 0.8382 |
86
+ | No log | 4.1176 | 70 | 0.7958 | 0.7003 | 0.7958 | 0.8921 |
87
+ | No log | 4.2353 | 72 | 0.7204 | 0.7529 | 0.7204 | 0.8488 |
88
+ | No log | 4.3529 | 74 | 0.5990 | 0.7458 | 0.5990 | 0.7739 |
89
+ | No log | 4.4706 | 76 | 0.5825 | 0.7213 | 0.5825 | 0.7632 |
90
+ | No log | 4.5882 | 78 | 0.6001 | 0.7689 | 0.6001 | 0.7747 |
91
+ | No log | 4.7059 | 80 | 0.6855 | 0.7529 | 0.6855 | 0.8279 |
92
+ | No log | 4.8235 | 82 | 0.8947 | 0.7162 | 0.8947 | 0.9459 |
93
+ | No log | 4.9412 | 84 | 0.8521 | 0.7606 | 0.8521 | 0.9231 |
94
+ | No log | 5.0588 | 86 | 0.6751 | 0.7293 | 0.6751 | 0.8216 |
95
+ | No log | 5.1765 | 88 | 0.5689 | 0.7689 | 0.5689 | 0.7543 |
96
+ | No log | 5.2941 | 90 | 0.5797 | 0.7458 | 0.5797 | 0.7614 |
97
+ | No log | 5.4118 | 92 | 0.5998 | 0.7689 | 0.5998 | 0.7745 |
98
+ | No log | 5.5294 | 94 | 0.7300 | 0.7004 | 0.7300 | 0.8544 |
99
+ | No log | 5.6471 | 96 | 0.8426 | 0.7448 | 0.8426 | 0.9179 |
100
+ | No log | 5.7647 | 98 | 0.8054 | 0.73 | 0.8054 | 0.8974 |
101
+ | No log | 5.8824 | 100 | 0.7236 | 0.6912 | 0.7236 | 0.8506 |
102
+ | No log | 6.0 | 102 | 0.6455 | 0.7455 | 0.6455 | 0.8034 |
103
+ | No log | 6.1176 | 104 | 0.6161 | 0.7455 | 0.6161 | 0.7849 |
104
+ | No log | 6.2353 | 106 | 0.6421 | 0.7455 | 0.6421 | 0.8013 |
105
+ | No log | 6.3529 | 108 | 0.7005 | 0.6912 | 0.7005 | 0.8369 |
106
+ | No log | 6.4706 | 110 | 0.7615 | 0.7064 | 0.7615 | 0.8726 |
107
+ | No log | 6.5882 | 112 | 0.7749 | 0.7064 | 0.7749 | 0.8803 |
108
+ | No log | 6.7059 | 114 | 0.7041 | 0.7064 | 0.7041 | 0.8391 |
109
+ | No log | 6.8235 | 116 | 0.6778 | 0.7451 | 0.6778 | 0.8233 |
110
+ | No log | 6.9412 | 118 | 0.7136 | 0.7064 | 0.7136 | 0.8448 |
111
+ | No log | 7.0588 | 120 | 0.7518 | 0.7064 | 0.7518 | 0.8671 |
112
+ | No log | 7.1765 | 122 | 0.7160 | 0.7064 | 0.7160 | 0.8462 |
113
+ | No log | 7.2941 | 124 | 0.6273 | 0.7451 | 0.6273 | 0.7920 |
114
+ | No log | 7.4118 | 126 | 0.6168 | 0.7451 | 0.6168 | 0.7854 |
115
+ | No log | 7.5294 | 128 | 0.6384 | 0.7451 | 0.6384 | 0.7990 |
116
+ | No log | 7.6471 | 130 | 0.6534 | 0.7451 | 0.6534 | 0.8083 |
117
+ | No log | 7.7647 | 132 | 0.6524 | 0.7927 | 0.6524 | 0.8077 |
118
+ | No log | 7.8824 | 134 | 0.5913 | 0.7451 | 0.5913 | 0.7690 |
119
+ | No log | 8.0 | 136 | 0.5310 | 0.7455 | 0.5310 | 0.7287 |
120
+ | No log | 8.1176 | 138 | 0.5292 | 0.7455 | 0.5292 | 0.7275 |
121
+ | No log | 8.2353 | 140 | 0.5436 | 0.7612 | 0.5436 | 0.7373 |
122
+ | No log | 8.3529 | 142 | 0.5483 | 0.7451 | 0.5483 | 0.7405 |
123
+ | No log | 8.4706 | 144 | 0.5702 | 0.7927 | 0.5702 | 0.7551 |
124
+ | No log | 8.5882 | 146 | 0.5945 | 0.7927 | 0.5945 | 0.7710 |
125
+ | No log | 8.7059 | 148 | 0.6080 | 0.7927 | 0.6080 | 0.7797 |
126
+ | No log | 8.8235 | 150 | 0.6155 | 0.7927 | 0.6155 | 0.7845 |
127
+ | No log | 8.9412 | 152 | 0.6185 | 0.7927 | 0.6185 | 0.7865 |
128
+ | No log | 9.0588 | 154 | 0.6077 | 0.7927 | 0.6077 | 0.7796 |
129
+ | No log | 9.1765 | 156 | 0.6023 | 0.7927 | 0.6023 | 0.7761 |
130
+ | No log | 9.2941 | 158 | 0.6058 | 0.7927 | 0.6058 | 0.7784 |
131
+ | No log | 9.4118 | 160 | 0.6277 | 0.7927 | 0.6277 | 0.7923 |
132
+ | No log | 9.5294 | 162 | 0.6464 | 0.7927 | 0.6464 | 0.8040 |
133
+ | No log | 9.6471 | 164 | 0.6601 | 0.7927 | 0.6601 | 0.8125 |
134
+ | No log | 9.7647 | 166 | 0.6625 | 0.7927 | 0.6625 | 0.8139 |
135
+ | No log | 9.8824 | 168 | 0.6622 | 0.7927 | 0.6622 | 0.8138 |
136
+ | No log | 10.0 | 170 | 0.6600 | 0.7927 | 0.6600 | 0.8124 |
137
+
138
+
139
+ ### Framework versions
140
+
141
+ - Transformers 4.44.2
142
+ - Pytorch 2.4.0+cu118
143
+ - Datasets 2.21.0
144
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "aubmindlab/bert-base-arabertv02",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "bert",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 0,
25
+ "position_embedding_type": "absolute",
26
+ "problem_type": "regression",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.44.2",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 64000
32
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1217f69092e588857867cf812a4db397c0d5c73385d5d1bf4e6daff3110a15ac
3
+ size 540799996
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4346cfd32244ffa243d238479f8a198c7b9a6882c900008cf3fead96232a6746
3
+ size 5240