End of training
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: distilbert-base-
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
@@ -20,21 +20,21 @@ model-index:
|
|
20 |
name: ner
|
21 |
type: ner
|
22 |
config: indian_names
|
23 |
-
split:
|
24 |
args: indian_names
|
25 |
metrics:
|
26 |
- name: Precision
|
27 |
type: precision
|
28 |
-
value: 0.
|
29 |
- name: Recall
|
30 |
type: recall
|
31 |
-
value: 0.
|
32 |
- name: F1
|
33 |
type: f1
|
34 |
-
value: 0.
|
35 |
- name: Accuracy
|
36 |
type: accuracy
|
37 |
-
value: 0.
|
38 |
---
|
39 |
|
40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -42,13 +42,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
42 |
|
43 |
# Bert-NER
|
44 |
|
45 |
-
This model is a fine-tuned version of [distilbert-base-
|
46 |
It achieves the following results on the evaluation set:
|
47 |
-
- Loss: 0.
|
48 |
-
- Precision: 0.
|
49 |
-
- Recall: 0.
|
50 |
-
- F1: 0.
|
51 |
-
- Accuracy: 0.
|
52 |
|
53 |
## Model description
|
54 |
|
@@ -67,7 +67,7 @@ More information needed
|
|
67 |
### Training hyperparameters
|
68 |
|
69 |
The following hyperparameters were used during training:
|
70 |
-
- learning_rate:
|
71 |
- train_batch_size: 32
|
72 |
- eval_batch_size: 32
|
73 |
- seed: 42
|
@@ -79,11 +79,11 @@ The following hyperparameters were used during training:
|
|
79 |
|
80 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
81 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
82 |
-
| No log | 1.0 |
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
|
88 |
|
89 |
### Framework versions
|
@@ -91,4 +91,4 @@ The following hyperparameters were used during training:
|
|
91 |
- Transformers 4.34.0
|
92 |
- Pytorch 2.0.1+cu118
|
93 |
- Datasets 2.14.5
|
94 |
-
- Tokenizers 0.14.
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
|
|
20 |
name: ner
|
21 |
type: ner
|
22 |
config: indian_names
|
23 |
+
split: train
|
24 |
args: indian_names
|
25 |
metrics:
|
26 |
- name: Precision
|
27 |
type: precision
|
28 |
+
value: 0.982625089167431
|
29 |
- name: Recall
|
30 |
type: recall
|
31 |
+
value: 0.9665213251140179
|
32 |
- name: F1
|
33 |
type: f1
|
34 |
+
value: 0.9745066828368578
|
35 |
- name: Accuracy
|
36 |
type: accuracy
|
37 |
+
value: 0.9865003101950782
|
38 |
---
|
39 |
|
40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
42 |
|
43 |
# Bert-NER
|
44 |
|
45 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the ner dataset.
|
46 |
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 0.0404
|
48 |
+
- Precision: 0.9826
|
49 |
+
- Recall: 0.9665
|
50 |
+
- F1: 0.9745
|
51 |
+
- Accuracy: 0.9865
|
52 |
|
53 |
## Model description
|
54 |
|
|
|
67 |
### Training hyperparameters
|
68 |
|
69 |
The following hyperparameters were used during training:
|
70 |
+
- learning_rate: 5e-05
|
71 |
- train_batch_size: 32
|
72 |
- eval_batch_size: 32
|
73 |
- seed: 42
|
|
|
79 |
|
80 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
81 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
82 |
+
| No log | 1.0 | 469 | 0.0541 | 0.9760 | 0.9580 | 0.9669 | 0.9826 |
|
83 |
+
| 0.0887 | 2.0 | 938 | 0.0503 | 0.9767 | 0.9620 | 0.9693 | 0.9839 |
|
84 |
+
| 0.0519 | 3.0 | 1407 | 0.0464 | 0.9799 | 0.9627 | 0.9712 | 0.9849 |
|
85 |
+
| 0.0467 | 4.0 | 1876 | 0.0430 | 0.9806 | 0.9652 | 0.9728 | 0.9856 |
|
86 |
+
| 0.0427 | 5.0 | 2345 | 0.0404 | 0.9826 | 0.9665 | 0.9745 | 0.9865 |
|
87 |
|
88 |
|
89 |
### Framework versions
|
|
|
91 |
- Transformers 4.34.0
|
92 |
- Pytorch 2.0.1+cu118
|
93 |
- Datasets 2.14.5
|
94 |
+
- Tokenizers 0.14.1
|