andrembcosta
commited on
Commit
•
22e3abb
1
Parent(s):
f095c5a
Training complete on TPU - full dataset
Browse files
README.md
CHANGED
@@ -1,6 +1,13 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
4 |
model-index:
|
5 |
- name: bert-base-cased
|
6 |
results: []
|
@@ -11,7 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
11 |
|
12 |
# bert-base-cased
|
13 |
|
14 |
-
This model
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
|
16 |
## Model description
|
17 |
|
@@ -30,7 +43,7 @@ More information needed
|
|
30 |
### Training hyperparameters
|
31 |
|
32 |
The following hyperparameters were used during training:
|
33 |
-
- learning_rate:
|
34 |
- train_batch_size: 8
|
35 |
- eval_batch_size: 8
|
36 |
- seed: 42
|
@@ -42,7 +55,7 @@ The following hyperparameters were used during training:
|
|
42 |
|
43 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
44 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
45 |
-
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: dslim/distilbert-NER
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
model-index:
|
12 |
- name: bert-base-cased
|
13 |
results: []
|
|
|
18 |
|
19 |
# bert-base-cased
|
20 |
|
21 |
+
This model is a fine-tuned version of [dslim/distilbert-NER](https://huggingface.co/dslim/distilbert-NER) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0367
|
24 |
+
- Precision: 0.9569
|
25 |
+
- Recall: 0.9677
|
26 |
+
- F1: 0.9623
|
27 |
+
- Accuracy: 0.9915
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
43 |
### Training hyperparameters
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 1e-05
|
47 |
- train_batch_size: 8
|
48 |
- eval_batch_size: 8
|
49 |
- seed: 42
|
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.0315 | 1.0 | 1500 | 0.0367 | 0.9569 | 0.9677 | 0.9623 | 0.9915 |
|
59 |
|
60 |
|
61 |
### Framework versions
|