Hugging Face's logo

thejosango
/
nuha-binary

Text Classification
Transformers
PyTorch
Arabic
bert
hate-speech
gender-based-violence
arabic
binary-classification
pilot
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
yazansh commited on
Commit
4a30404
·
verified ·
1 Parent(s): 152141c

binary-55

Browse files
Files changed (5) hide show
  1. README.md +16 -14
  2. config.json +1 -1
  3. config.toml +2 -2
  4. pytorch_model.bin +2 -2
  5. training_args.bin +1 -1
README.md CHANGED
@@ -24,13 +24,13 @@ model-index:
24
  metrics:
25
  - name: F1
26
  type: f1
27
- value: 0.705621049034683
28
  - name: Precision
29
  type: precision
30
- value: 0.6562847608453838
31
  - name: Recall
32
  type: recall
33
- value: 0.7629780158876778
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,10 +40,10 @@ should probably proofread and complete it, then remove this comment. -->
40
 
41
  This model is a fine-tuned version of [thejosango/nuha-mlm](https://huggingface.co/thejosango/nuha-mlm) on the nuha-dataset dataset.
42
  It achieves the following results on the evaluation set:
43
- - Loss: 0.5407
44
- - F1: 0.7056
45
- - Precision: 0.6563
46
- - Recall: 0.7630
47
  - Support: None
48
 
49
  ## Model description
@@ -76,13 +76,15 @@ The following hyperparameters were used during training:
76
 
77
  | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Support |
78
  |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|:-------:|
79
- | 0.5708 | 0.25 | 500 | 0.5477 | 0.6832 | 0.6017 | 0.7903 | None |
80
- | 0.5573 | 0.5 | 1000 | 0.5365 | 0.6951 | 0.5983 | 0.8293 | None |
81
- | 0.5389 | 0.75 | 1500 | 0.5343 | 0.6994 | 0.6342 | 0.7794 | None |
82
- | 0.5344 | 1.0 | 2000 | 0.5297 | 0.7038 | 0.6316 | 0.7946 | None |
83
- | 0.4947 | 1.26 | 2500 | 0.5371 | 0.7058 | 0.6485 | 0.7742 | None |
84
- | 0.4823 | 1.51 | 3000 | 0.5399 | 0.7040 | 0.6329 | 0.7933 | None |
85
- | 0.4814 | 1.76 | 3500 | 0.5407 | 0.7056 | 0.6563 | 0.7630 | None |
 
 
86
 
87
 
88
  ### Framework versions
 
24
  metrics:
25
  - name: F1
26
  type: f1
27
+ value: 0.6868284228769497
28
  - name: Precision
29
  type: precision
30
+ value: 0.6468092051574996
31
  - name: Recall
32
  type: recall
33
+ value: 0.7321263624607427
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
40
 
41
  This model is a fine-tuned version of [thejosango/nuha-mlm](https://huggingface.co/thejosango/nuha-mlm) on the nuha-dataset dataset.
42
  It achieves the following results on the evaluation set:
43
+ - Loss: 0.5763
44
+ - F1: 0.6868
45
+ - Precision: 0.6468
46
+ - Recall: 0.7321
47
  - Support: None
48
 
49
  ## Model description
 
76
 
77
  | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Support |
78
  |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|:-------:|
79
+ | 0.572 | 0.25 | 500 | 0.5492 | 0.6774 | 0.5836 | 0.8069 | None |
80
+ | 0.5571 | 0.5 | 1000 | 0.5384 | 0.6937 | 0.6053 | 0.8123 | None |
81
+ | 0.541 | 0.75 | 1500 | 0.5344 | 0.6967 | 0.6324 | 0.7755 | None |
82
+ | 0.5359 | 1.0 | 2000 | 0.5300 | 0.7032 | 0.6300 | 0.7957 | None |
83
+ | 0.4984 | 1.26 | 2500 | 0.5406 | 0.7023 | 0.6597 | 0.7508 | None |
84
+ | 0.4878 | 1.51 | 3000 | 0.5415 | 0.7012 | 0.6425 | 0.7718 | None |
85
+ | 0.4847 | 1.76 | 3500 | 0.5435 | 0.6980 | 0.6422 | 0.7645 | None |
86
+ | 0.4779 | 2.01 | 4000 | 0.5526 | 0.7034 | 0.6377 | 0.7842 | None |
87
+ | 0.4265 | 2.26 | 4500 | 0.5763 | 0.6868 | 0.6468 | 0.7321 | None |
88
 
89
 
90
  ### Framework versions
config.json CHANGED
@@ -23,7 +23,7 @@
23
  "max_position_embeddings": 512,
24
  "model_type": "bert",
25
  "num_attention_heads": 12,
26
- "num_hidden_layers": 6,
27
  "pad_token_id": 0,
28
  "position_embedding_type": "absolute",
29
  "problem_type": "single_label_classification",
 
23
  "max_position_embeddings": 512,
24
  "model_type": "bert",
25
  "num_attention_heads": 12,
26
+ "num_hidden_layers": 4,
27
  "pad_token_id": 0,
28
  "position_embedding_type": "absolute",
29
  "problem_type": "single_label_classification",
config.toml CHANGED
@@ -1,5 +1,5 @@
1
  [experiment]
2
- name = "binary-54"
3
  type = "binary"
4
 
5
 
@@ -13,7 +13,7 @@ undersampling_strategy = false
13
  [model]
14
  pretrained_model_name_or_path = "thejosango/nuha-mlm"
15
  revision = "ce20f497544665775129f9ff5b3cd2a3e350dce8"
16
- num_hidden_layers = 6
17
  classifier_dropout = 0.25
18
 
19
  [training]
 
1
  [experiment]
2
+ name = "binary-55"
3
  type = "binary"
4
 
5
 
 
13
  [model]
14
  pretrained_model_name_or_path = "thejosango/nuha-mlm"
15
  revision = "ce20f497544665775129f9ff5b3cd2a3e350dce8"
16
+ num_hidden_layers = 4
17
  classifier_dropout = 0.25
18
 
19
  [training]
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:816e722701ebc7fc3c3530a8409079f18ef0fbfaa58648041372b53124b50de6
3
- size 370706033
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28c3aa09ebd3a0c1b7b418bed98c4e2a3db1ba33304f8af556ae95907e3c2cae
3
+ size 313992076
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4a66855564174c1c15c6e706dd7d0928b1c8aa8bc548337355e66e9c1644b98
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a03f95e740df4d0f787430d74d3e1a322dbd96f1199c899477c0651189f7b9e
3
  size 4091