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
645af52
·
1 Parent(s): cad48fc

binary-16

Browse files
Files changed (4) hide show
  1. README.md +13 -13
  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: 0.5838509316770187
27
  - name: Precision
28
  type: precision
29
- value: 0.4380672062791268
30
  - name: Recall
31
  type: recall
32
- value: 0.875061244487996
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: 1.0523
43
- - F1: 0.5839
44
- - Precision: 0.4381
45
- - Recall: 0.8751
46
  - Support: None
47
 
48
  ## Model description
@@ -62,7 +62,7 @@ More information needed
62
  ### Training hyperparameters
63
 
64
  The following hyperparameters were used during training:
65
- - learning_rate: 1e-05
66
  - train_batch_size: 32
67
  - eval_batch_size: 32
68
  - seed: 42
@@ -78,11 +78,11 @@ The following hyperparameters were used during training:
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Support |
80
  |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|:-------:|
81
- | 3.5522 | 0.98 | 500 | 1.1946 | 0.5430 | 0.4215 | 0.7629 | None |
82
- | 2.195 | 1.96 | 1000 | 0.7704 | 0.5473 | 0.4695 | 0.6561 | None |
83
- | 1.8703 | 2.94 | 1500 | 1.0588 | 0.5587 | 0.4080 | 0.8858 | None |
84
- | 1.5932 | 3.92 | 2000 | 1.2887 | 0.5529 | 0.3942 | 0.9255 | None |
85
- | 1.4506 | 4.9 | 2500 | 1.0523 | 0.5839 | 0.4381 | 0.8751 | None |
86
 
87
 
88
  ### Framework versions
 
23
  metrics:
24
  - name: F1
25
  type: f1
26
+ value: 0.6309942603221625
27
  - name: Precision
28
  type: precision
29
+ value: 0.5071428571428571
30
  - name: Recall
31
  type: recall
32
+ value: 0.8348848603625674
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: 1.0499
43
+ - F1: 0.6310
44
+ - Precision: 0.5071
45
+ - Recall: 0.8349
46
  - Support: None
47
 
48
  ## Model description
 
62
  ### Training hyperparameters
63
 
64
  The following hyperparameters were used during training:
65
+ - learning_rate: 3e-05
66
  - train_batch_size: 32
67
  - eval_batch_size: 32
68
  - seed: 42
 
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Support |
80
  |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|:-------:|
81
+ | 2.4225 | 0.98 | 500 | 0.7505 | 0.5739 | 0.4681 | 0.7413 | None |
82
+ | 1.5207 | 1.96 | 1000 | 0.8548 | 0.5951 | 0.4935 | 0.7491 | None |
83
+ | 1.2637 | 2.94 | 1500 | 1.3438 | 0.5942 | 0.4475 | 0.8839 | None |
84
+ | 1.0813 | 3.92 | 2000 | 1.1361 | 0.6163 | 0.4792 | 0.8633 | None |
85
+ | 0.9742 | 4.9 | 2500 | 1.0499 | 0.6310 | 0.5071 | 0.8349 | None |
86
 
87
 
88
  ### Framework versions
config.toml CHANGED
@@ -1,5 +1,5 @@
1
  [experiment]
2
- name = "binary-15"
3
  type = "binary"
4
 
5
 
@@ -26,7 +26,7 @@ classifier_dropout = 0.5
26
  num_train_epochs = 5
27
  warmup_steps = 1e3
28
  lr_scheduler_type = "constant"
29
- learning_rate = 1e-5
30
  per_device_train_batch_size = 32
31
  per_device_eval_batch_size = 32
32
  gradient_accumulation_steps = 2
 
1
  [experiment]
2
+ name = "binary-16"
3
  type = "binary"
4
 
5
 
 
26
  num_train_epochs = 5
27
  warmup_steps = 1e3
28
  lr_scheduler_type = "constant"
29
+ learning_rate = 3e-5
30
  per_device_train_batch_size = 32
31
  per_device_eval_batch_size = 32
32
  gradient_accumulation_steps = 2
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:651839ef37b16508bafde4abfebb6a8a2a56acd6d0d3fc0b007b6620e3ca5c3c
3
  size 427419953
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1912b3c6adb29b66a3968271a99b2e678dcfb3fb06bd0f14233304ddb560a271
3
  size 427419953
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e97bb5b9624197daf4fcc5f26fde4ab6240de63d1d19a619e858b885dcfe171
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc0bc99e89a204c136cec58d3fc624718e14ab6bce3ca160a06de601cc2f37c8
3
  size 4091