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
bf5de58
·
verified ·
1 Parent(s): d9bb1d2

binary-43

Browse files
Files changed (4) hide show
  1. README.md +16 -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: 0.6985993964249787
27
  - name: Precision
28
  type: precision
29
- value: 0.6010652463382157
30
  - name: Recall
31
  type: recall
32
- value: 0.8339183447256604
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: 0.5483
43
- - F1: 0.6986
44
- - Precision: 0.6011
45
- - Recall: 0.8339
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: 64
67
  - eval_batch_size: 64
68
  - seed: 42
@@ -75,19 +75,14 @@ The following hyperparameters were used during training:
75
 
76
  | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Support |
77
  |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|:-------:|
78
- | 0.5924 | 0.25 | 500 | 0.5663 | 0.6635 | 0.5810 | 0.7733 | None |
79
- | 0.5748 | 0.5 | 1000 | 0.5603 | 0.6762 | 0.5750 | 0.8206 | None |
80
- | 0.5584 | 0.75 | 1500 | 0.5477 | 0.6856 | 0.6004 | 0.7990 | None |
81
- | 0.554 | 1.0 | 2000 | 0.5411 | 0.6883 | 0.6023 | 0.8029 | None |
82
- | 0.5439 | 1.26 | 2500 | 0.5421 | 0.6925 | 0.6420 | 0.7517 | None |
83
- | 0.5353 | 1.51 | 3000 | 0.5400 | 0.6953 | 0.6046 | 0.8180 | None |
84
- | 0.5285 | 1.76 | 3500 | 0.5441 | 0.6917 | 0.6242 | 0.7755 | None |
85
- | 0.5244 | 2.01 | 4000 | 0.5412 | 0.7005 | 0.6236 | 0.7990 | None |
86
- | 0.5064 | 2.26 | 4500 | 0.5370 | 0.7037 | 0.6304 | 0.7962 | None |
87
- | 0.5102 | 2.51 | 5000 | 0.5360 | 0.7011 | 0.6310 | 0.7887 | None |
88
- | 0.5071 | 2.76 | 5500 | 0.5377 | 0.7036 | 0.6483 | 0.7693 | None |
89
- | 0.5044 | 3.01 | 6000 | 0.5408 | 0.7063 | 0.6521 | 0.7702 | None |
90
- | 0.47 | 3.26 | 6500 | 0.5483 | 0.6986 | 0.6011 | 0.8339 | None |
91
 
92
 
93
  ### Framework versions
 
23
  metrics:
24
  - name: F1
25
  type: f1
26
+ value: 0.7056408425562299
27
  - name: Precision
28
  type: precision
29
+ value: 0.682610948022794
30
  - name: Recall
31
  type: recall
32
+ value: 0.7302789580639202
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: 0.6289
43
+ - F1: 0.7056
44
+ - Precision: 0.6826
45
+ - Recall: 0.7303
46
  - Support: None
47
 
48
  ## Model description
 
62
  ### Training hyperparameters
63
 
64
  The following hyperparameters were used during training:
65
+ - learning_rate: 5e-05
66
  - train_batch_size: 64
67
  - eval_batch_size: 64
68
  - seed: 42
 
75
 
76
  | Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Support |
77
  |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|:-------:|
78
+ | 0.5823 | 0.25 | 500 | 0.5569 | 0.6753 | 0.5610 | 0.8481 | None |
79
+ | 0.5646 | 0.5 | 1000 | 0.5704 | 0.6747 | 0.5367 | 0.9080 | None |
80
+ | 0.5492 | 0.75 | 1500 | 0.5302 | 0.7044 | 0.6496 | 0.7693 | None |
81
+ | 0.5431 | 1.0 | 2000 | 0.5507 | 0.7046 | 0.6173 | 0.8206 | None |
82
+ | 0.5069 | 1.26 | 2500 | 0.5526 | 0.7010 | 0.6206 | 0.8053 | None |
83
+ | 0.4981 | 1.51 | 3000 | 0.5477 | 0.7049 | 0.6284 | 0.8025 | None |
84
+ | 0.4977 | 1.76 | 3500 | 0.5448 | 0.7049 | 0.6448 | 0.7772 | None |
85
+ | 0.4939 | 2.01 | 4000 | 0.6289 | 0.7056 | 0.6826 | 0.7303 | None |
 
 
 
 
 
86
 
87
 
88
  ### Framework versions
config.toml CHANGED
@@ -1,5 +1,5 @@
1
  [experiment]
2
- name = "binary-42"
3
  type = "binary"
4
 
5
 
@@ -19,7 +19,7 @@ revision = "ce20f497544665775129f9ff5b3cd2a3e350dce8"
19
  num_train_epochs = 5
20
  warmup_steps = 0
21
  lr_scheduler_type = "constant"
22
- learning_rate = 1e-5
23
  per_device_train_batch_size = 64
24
  per_device_eval_batch_size = 64
25
  gradient_accumulation_steps = 1
 
1
  [experiment]
2
+ name = "binary-43"
3
  type = "binary"
4
 
5
 
 
19
  num_train_epochs = 5
20
  warmup_steps = 0
21
  lr_scheduler_type = "constant"
22
+ learning_rate = 5e-5
23
  per_device_train_batch_size = 64
24
  per_device_eval_batch_size = 64
25
  gradient_accumulation_steps = 1
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5aabbfb4ad9b9d81fb57d9875418a41977e2d75ba6f7b18e181e103c3c24d2fe
3
  size 540847921
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85268dcea8ec1fdc1e4b5888975b96272d9d1616fc2d2d6348905cde8d0d7cd
3
  size 540847921
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdebe0b166e4d1330c64786faace279562a78bc6264349157d363772460b835c
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60609b4a5f65d9ba9da6a0df20683c1aae6e3c579acea25d5551c87db75e498d
3
  size 4091