Hugging Face's logo

mHossain
/
bengali_pos_v1_500000

Token Classification
Transformers
TensorBoard
Safetensors
electra
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mHossain commited on
Commit
8791cf1
•
1 Parent(s): 5182773

Training complete

Browse files
Files changed (1) hide show
  1. README.md +14 -14
README.md CHANGED
@@ -24,16 +24,16 @@ model-index:
24
  metrics:
25
  - name: Precision
26
  type: precision
27
- value: 0.7579696797959762
28
  - name: Recall
29
  type: recall
30
- value: 0.7590989712664066
31
  - name: F1
32
  type: f1
33
- value: 0.7585339052142781
34
  - name: Accuracy
35
  type: accuracy
36
- value: 0.8206361113872795
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,11 +43,11 @@ should probably proofread and complete it, then remove this comment. -->
43
 
44
  This model is a fine-tuned version of [mHossain/bengali_pos_v1_400000](https://huggingface.co/mHossain/bengali_pos_v1_400000) on the pos_tag_100k dataset.
45
  It achieves the following results on the evaluation set:
46
- - Loss: 0.6169
47
- - Precision: 0.7580
48
- - Recall: 0.7591
49
- - F1: 0.7585
50
- - Accuracy: 0.8206
51
 
52
  ## Model description
53
 
@@ -76,11 +76,11 @@ The following hyperparameters were used during training:
76
 
77
  ### Training results
78
 
79
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
- |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
- | 0.6277 | 1.0 | 22500 | 0.6102 | 0.7441 | 0.7474 | 0.7458 | 0.8109 |
82
- | 0.5143 | 2.0 | 45000 | 0.5998 | 0.7549 | 0.7561 | 0.7555 | 0.8183 |
83
- | 0.4392 | 3.0 | 67500 | 0.6169 | 0.7580 | 0.7591 | 0.7585 | 0.8206 |
84
 
85
 
86
  ### Framework versions
 
24
  metrics:
25
  - name: Precision
26
  type: precision
27
+ value: 0.7517491791092168
28
  - name: Recall
29
  type: recall
30
+ value: 0.7532968740056972
31
  - name: F1
32
  type: f1
33
+ value: 0.752522230781312
34
  - name: Accuracy
35
  type: accuracy
36
+ value: 0.8148741068930406
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
43
 
44
  This model is a fine-tuned version of [mHossain/bengali_pos_v1_400000](https://huggingface.co/mHossain/bengali_pos_v1_400000) on the pos_tag_100k dataset.
45
  It achieves the following results on the evaluation set:
46
+ - Loss: 0.6185
47
+ - Precision: 0.7517
48
+ - Recall: 0.7533
49
+ - F1: 0.7525
50
+ - Accuracy: 0.8149
51
 
52
  ## Model description
53
 
 
76
 
77
  ### Training results
78
 
79
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
+ |:-------------:|:-----:|:------:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | 0.6508 | 1.0 | 67500 | 0.6325 | 0.7386 | 0.7396 | 0.7391 | 0.8041 |
82
+ | 0.5713 | 2.0 | 135000 | 0.6093 | 0.7487 | 0.7500 | 0.7493 | 0.8123 |
83
+ | 0.4789 | 3.0 | 202500 | 0.6185 | 0.7517 | 0.7533 | 0.7525 | 0.8149 |
84
 
85
 
86
  ### Framework versions