Hugging Face's logo

thejosango
/
nuha-ajp-binary

Text Classification
Transformers
PyTorch
Safetensors
Arabic
bert
hate-speech
gender-based-violence
arabic
binary-classification
pilot
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
4
yazansh commited on
Commit
86f9052
·
verified ·
1 Parent(s): 92a36c3

binary-48

Browse files
Files changed (5) hide show
  1. README.md +16 -15
  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
@@ -23,13 +23,13 @@ model-index:
23
  metrics:
24
  - name: F1
25
  type: f1
26
- value: 0.6886962211680027
27
  - name: Precision
28
  type: precision
29
- value: 0.6179362982533392
30
  - name: Recall
31
  type: recall
32
- value: 0.7777572510622576
33
  ---
34
 
35
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -39,10 +39,10 @@ should probably proofread and complete it, then remove this comment. -->
39
 
40
  This model is a fine-tuned version of [thejosango/nuha-mlm](https://huggingface.co/thejosango/nuha-mlm) on the nuha-dataset dataset.
41
  It achieves the following results on the evaluation set:
42
- - Loss: 0.5851
43
- - F1: 0.6887
44
- - Precision: 0.6179
45
- - Recall: 0.7778
46
  - Support: None
47
 
48
  ## Model description
@@ -75,14 +75,15 @@ The following hyperparameters were used during training:
75
 
76
  | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Support |
77
  |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|:-------:|
78
- | 0.5549 | 0.37 | 500 | 0.5309 | 0.6858 | 0.6241 | 0.7611 | None |
79
- | 0.5349 | 0.74 | 1000 | 0.5707 | 0.6901 | 0.5765 | 0.8592 | None |
80
- | 0.5139 | 1.11 | 1500 | 0.5371 | 0.7008 | 0.6114 | 0.8208 | None |
81
- | 0.471 | 1.48 | 2000 | 0.5462 | 0.7006 | 0.6150 | 0.8140 | None |
82
- | 0.4704 | 1.85 | 2500 | 0.5332 | 0.7028 | 0.6302 | 0.7944 | None |
83
- | 0.3856 | 2.22 | 3000 | 0.5706 | 0.6944 | 0.6350 | 0.7661 | None |
84
- | 0.3905 | 2.58 | 3500 | 0.5791 | 0.6914 | 0.6259 | 0.7722 | None |
85
- | 0.3957 | 2.95 | 4000 | 0.5851 | 0.6887 | 0.6179 | 0.7778 | None |
 
86
 
87
 
88
  ### Framework versions
 
23
  metrics:
24
  - name: F1
25
  type: f1
26
+ value: 0.6800462504129501
27
  - name: Precision
28
  type: precision
29
+ value: 0.6149365197908887
30
  - name: Recall
31
  type: recall
32
+ value: 0.7605763901718086
33
  ---
34
 
35
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
39
 
40
  This model is a fine-tuned version of [thejosango/nuha-mlm](https://huggingface.co/thejosango/nuha-mlm) on the nuha-dataset dataset.
41
  It achieves the following results on the evaluation set:
42
+ - Loss: 0.6279
43
+ - F1: 0.6800
44
+ - Precision: 0.6149
45
+ - Recall: 0.7606
46
  - Support: None
47
 
48
  ## Model description
 
75
 
76
  | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Support |
77
  |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|:-------:|
78
+ | 0.5551 | 0.37 | 500 | 0.5371 | 0.6814 | 0.6026 | 0.7840 | None |
79
+ | 0.5363 | 0.74 | 1000 | 0.5705 | 0.6878 | 0.5740 | 0.8579 | None |
80
+ | 0.5154 | 1.11 | 1500 | 0.5587 | 0.6896 | 0.5873 | 0.8352 | None |
81
+ | 0.4736 | 1.48 | 2000 | 0.5350 | 0.6992 | 0.6391 | 0.7718 | None |
82
+ | 0.4749 | 1.85 | 2500 | 0.5340 | 0.6994 | 0.6222 | 0.7984 | None |
83
+ | 0.3901 | 2.22 | 3000 | 0.5633 | 0.6859 | 0.6494 | 0.7268 | None |
84
+ | 0.4004 | 2.58 | 3500 | 0.5731 | 0.6837 | 0.6266 | 0.7523 | None |
85
+ | 0.4049 | 2.95 | 4000 | 0.5521 | 0.6875 | 0.6279 | 0.7597 | None |
86
+ | 0.3327 | 3.32 | 4500 | 0.6279 | 0.6800 | 0.6149 | 0.7606 | None |
87
 
88
 
89
  ### 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-46"
3
  type = "binary"
4
 
5
 
@@ -13,7 +13,7 @@ undersampling_strategy = true
13
  [model]
14
  pretrained_model_name_or_path = "thejosango/nuha-mlm"
15
  revision = "ce20f497544665775129f9ff5b3cd2a3e350dce8"
16
- num_hidden_layers = 6
17
 
18
  [training]
19
  num_train_epochs = 5
 
1
  [experiment]
2
+ name = "binary-48"
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
 
18
  [training]
19
  num_train_epochs = 5
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:904255272f36d41452bdda91d40363364638cdb10712492a10eca784ee0dd12f
3
- size 370706033
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58663cde72a8994db819a92a7e7162df854174ce68b16532a92f66d6c5f91bcf
3
+ size 313992076
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ed43b62dcb0304a51b2e0207f14d0168c56fe5a2d2bbcacd6c62934adaecdd1
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4451636d8c623728db5d931aad51bde214c675f6f40552ccb51f795f783383f4
3
  size 4091