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
d23681f
·
1 Parent(s): aca5e41

binary-5

Browse files
Files changed (4) hide show
  1. README.md +20 -21
  2. config.toml +2 -2
  3. pytorch_model.bin +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -23,13 +23,13 @@ model-index:
23
  metrics:
24
  - name: F1
25
  type: f1
26
- value: 0.5652559928973069
27
  - name: Precision
28
  type: precision
29
- value: 0.7137518684603886
30
  - name: Recall
31
  type: recall
32
- value: 0.4679078882900539
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: 0.5595
43
- - F1: 0.5653
44
- - Precision: 0.7138
45
- - Recall: 0.4679
46
  - Support: None
47
 
48
  ## Model description
@@ -78,20 +78,19 @@ The following hyperparameters were used during training:
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Support |
80
  |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|:-------:|
81
- | 0.8838 | 0.64 | 500 | 0.6201 | 0.4182 | 0.6907 | 0.2999 | None |
82
- | 0.6748 | 1.28 | 1000 | 0.5750 | 0.4756 | 0.7174 | 0.3557 | None |
83
- | 0.6404 | 1.91 | 1500 | 0.5329 | 0.5705 | 0.6788 | 0.4919 | None |
84
- | 0.5836 | 2.55 | 2000 | 0.5316 | 0.5649 | 0.7069 | 0.4704 | None |
85
- | 0.5793 | 3.19 | 2500 | 0.5267 | 0.6255 | 0.6614 | 0.5933 | None |
86
- | 0.557 | 3.83 | 3000 | 0.5211 | 0.6145 | 0.6669 | 0.5698 | None |
87
- | 0.5279 | 4.46 | 3500 | 0.5301 | 0.6516 | 0.6481 | 0.6551 | None |
88
- | 0.5121 | 5.1 | 4000 | 0.5220 | 0.6356 | 0.6818 | 0.5953 | None |
89
- | 0.5067 | 5.74 | 4500 | 0.5270 | 0.6609 | 0.6481 | 0.6742 | None |
90
- | 0.4806 | 6.38 | 5000 | 0.5259 | 0.6309 | 0.6899 | 0.5811 | None |
91
- | 0.4858 | 7.02 | 5500 | 0.5303 | 0.6145 | 0.6890 | 0.5546 | None |
92
- | 0.4608 | 7.65 | 6000 | 0.5429 | 0.6558 | 0.6402 | 0.6722 | None |
93
- | 0.441 | 8.29 | 6500 | 0.5575 | 0.6279 | 0.6776 | 0.5850 | None |
94
- | 0.4367 | 8.93 | 7000 | 0.5595 | 0.5653 | 0.7138 | 0.4679 | None |
95
 
96
 
97
  ### Framework versions
 
23
  metrics:
24
  - name: F1
25
  type: f1
26
+ value: 0.665627088438405
27
  - name: Precision
28
  type: precision
29
+ value: 0.6102941176470589
30
  - name: Recall
31
  type: recall
32
+ value: 0.7319941205291524
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: 0.6040
43
+ - F1: 0.6656
44
+ - Precision: 0.6103
45
+ - Recall: 0.7320
46
  - Support: None
47
 
48
  ## Model description
 
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Support |
80
  |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|:-------:|
81
+ | 0.9793 | 0.64 | 500 | 0.6349 | 0.6207 | 0.5750 | 0.6742 | None |
82
+ | 0.7395 | 1.28 | 1000 | 0.6231 | 0.6212 | 0.6139 | 0.6286 | None |
83
+ | 0.7008 | 1.91 | 1500 | 0.5850 | 0.6487 | 0.5941 | 0.7144 | None |
84
+ | 0.637 | 2.55 | 2000 | 0.5758 | 0.6521 | 0.5919 | 0.7261 | None |
85
+ | 0.6338 | 3.19 | 2500 | 0.5791 | 0.6497 | 0.5350 | 0.8270 | None |
86
+ | 0.6066 | 3.83 | 3000 | 0.5688 | 0.6557 | 0.5596 | 0.7918 | None |
87
+ | 0.5755 | 4.46 | 3500 | 0.5775 | 0.6507 | 0.5337 | 0.8334 | None |
88
+ | 0.5581 | 5.1 | 4000 | 0.5680 | 0.6661 | 0.5807 | 0.7810 | None |
89
+ | 0.555 | 5.74 | 4500 | 0.5712 | 0.6644 | 0.5604 | 0.8158 | None |
90
+ | 0.525 | 6.38 | 5000 | 0.5730 | 0.6638 | 0.5667 | 0.8011 | None |
91
+ | 0.5294 | 7.02 | 5500 | 0.5752 | 0.6692 | 0.6085 | 0.7433 | None |
92
+ | 0.5053 | 7.65 | 6000 | 0.5854 | 0.6610 | 0.5645 | 0.7972 | None |
93
+ | 0.4835 | 8.29 | 6500 | 0.6040 | 0.6656 | 0.6103 | 0.7320 | None |
 
94
 
95
 
96
  ### Framework versions
config.toml CHANGED
@@ -1,5 +1,5 @@
1
  [experiment]
2
- name = "binary-4"
3
  type = "binary"
4
 
5
 
@@ -32,6 +32,6 @@ per_device_eval_batch_size = 32
32
  gradient_accumulation_steps = 2
33
  weight_decay = 0.01
34
  label_smoothing_factor = 0.1
35
- weighted_loss = false
36
  early_stopping_patience = 5
37
  early_stopping_threshold = 0.005
 
1
  [experiment]
2
+ name = "binary-5"
3
  type = "binary"
4
 
5
 
 
32
  gradient_accumulation_steps = 2
33
  weight_decay = 0.01
34
  label_smoothing_factor = 0.1
35
+ weighted_loss = true
36
  early_stopping_patience = 5
37
  early_stopping_threshold = 0.005
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40de39f946a025883e44c47ae5e11ea1f08dc35b0befe9f2443dbc785a4045bd
3
  size 313992076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db70f3b2c4f2256831e61ee73a8b38812f9d97efa8f5d0a9988315e673c286c
3
  size 313992076
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37aa39e079233d13bb57c12ffb2e9ddc52bb1ab690045ff67bde840cebbe2c7b
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca4863cd3f201e2a14530833eccce4f8cf44d225e6c55891d01d4ccb4961a7e
3
  size 4091