Training complete
Browse files
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
base_model: mHossain/
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
@@ -24,16 +24,16 @@ model-index:
|
|
24 |
metrics:
|
25 |
- name: Precision
|
26 |
type: precision
|
27 |
-
value: 0.
|
28 |
- name: Recall
|
29 |
type: recall
|
30 |
-
value: 0.
|
31 |
- name: F1
|
32 |
type: f1
|
33 |
-
value: 0.
|
34 |
- name: Accuracy
|
35 |
type: accuracy
|
36 |
-
value: 0.
|
37 |
---
|
38 |
|
39 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -41,13 +41,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
41 |
|
42 |
# bengali_pos_v1_300000
|
43 |
|
44 |
-
This model is a fine-tuned version of [mHossain/
|
45 |
It achieves the following results on the evaluation set:
|
46 |
-
- Loss: 0.
|
47 |
-
- Precision: 0.
|
48 |
-
- Recall: 0.
|
49 |
-
- F1: 0.
|
50 |
-
- Accuracy: 0.
|
51 |
|
52 |
## Model description
|
53 |
|
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
|
|
78 |
|
79 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
80 |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
|
85 |
|
86 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
base_model: mHossain/bengali_pos_v1_400000
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
|
|
24 |
metrics:
|
25 |
- name: Precision
|
26 |
type: precision
|
27 |
+
value: 0.7758382692500753
|
28 |
- name: Recall
|
29 |
type: recall
|
30 |
+
value: 0.7796834604956177
|
31 |
- name: F1
|
32 |
type: f1
|
33 |
+
value: 0.7777561122887353
|
34 |
- name: Accuracy
|
35 |
type: accuracy
|
36 |
+
value: 0.8338714666872897
|
37 |
---
|
38 |
|
39 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
41 |
|
42 |
# bengali_pos_v1_300000
|
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: 0.5865
|
47 |
+
- Precision: 0.7758
|
48 |
+
- Recall: 0.7797
|
49 |
+
- F1: 0.7778
|
50 |
+
- Accuracy: 0.8339
|
51 |
|
52 |
## Model description
|
53 |
|
|
|
78 |
|
79 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
80 |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
81 |
+
| 0.587 | 1.0 | 22500 | 0.5821 | 0.7614 | 0.7643 | 0.7628 | 0.8232 |
|
82 |
+
| 0.4808 | 2.0 | 45000 | 0.5726 | 0.7733 | 0.7762 | 0.7747 | 0.8316 |
|
83 |
+
| 0.3909 | 3.0 | 67500 | 0.5865 | 0.7758 | 0.7797 | 0.7778 | 0.8339 |
|
84 |
|
85 |
|
86 |
### Framework versions
|