Training complete
Browse files
README.md
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: Dr-BERT/DrBERT-7GB
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- quaero
|
8 |
+
metrics:
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
- f1
|
12 |
+
- accuracy
|
13 |
+
model-index:
|
14 |
+
- name: drbert-7gb-finedtuned-ner
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Token Classification
|
18 |
+
type: token-classification
|
19 |
+
dataset:
|
20 |
+
name: quaero
|
21 |
+
type: quaero
|
22 |
+
config: emea
|
23 |
+
split: validation
|
24 |
+
args: emea
|
25 |
+
metrics:
|
26 |
+
- name: Precision
|
27 |
+
type: precision
|
28 |
+
value: 0.7103274559193955
|
29 |
+
- name: Recall
|
30 |
+
type: recall
|
31 |
+
value: 0.7359081419624217
|
32 |
+
- name: F1
|
33 |
+
type: f1
|
34 |
+
value: 0.7228915662650602
|
35 |
+
- name: Accuracy
|
36 |
+
type: accuracy
|
37 |
+
value: 0.9223586595037094
|
38 |
+
---
|
39 |
+
|
40 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
41 |
+
should probably proofread and complete it, then remove this comment. -->
|
42 |
+
|
43 |
+
# drbert-7gb-finedtuned-ner
|
44 |
+
|
45 |
+
This model is a fine-tuned version of [Dr-BERT/DrBERT-7GB](https://huggingface.co/Dr-BERT/DrBERT-7GB) on the quaero dataset.
|
46 |
+
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 0.3775
|
48 |
+
- Precision: 0.7103
|
49 |
+
- Recall: 0.7359
|
50 |
+
- F1: 0.7229
|
51 |
+
- Accuracy: 0.9224
|
52 |
+
|
53 |
+
## Model description
|
54 |
+
|
55 |
+
More information needed
|
56 |
+
|
57 |
+
## Intended uses & limitations
|
58 |
+
|
59 |
+
More information needed
|
60 |
+
|
61 |
+
## Training and evaluation data
|
62 |
+
|
63 |
+
More information needed
|
64 |
+
|
65 |
+
## Training procedure
|
66 |
+
|
67 |
+
### Training hyperparameters
|
68 |
+
|
69 |
+
The following hyperparameters were used during training:
|
70 |
+
- learning_rate: 2e-05
|
71 |
+
- train_batch_size: 8
|
72 |
+
- eval_batch_size: 8
|
73 |
+
- seed: 42
|
74 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
75 |
+
- lr_scheduler_type: linear
|
76 |
+
- num_epochs: 3
|
77 |
+
|
78 |
+
### Training results
|
79 |
+
|
80 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
81 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
82 |
+
| No log | 1.0 | 61 | 0.3947 | 0.7117 | 0.6905 | 0.7009 | 0.9198 |
|
83 |
+
| No log | 2.0 | 122 | 0.3738 | 0.7210 | 0.7244 | 0.7227 | 0.9224 |
|
84 |
+
| No log | 3.0 | 183 | 0.3775 | 0.7103 | 0.7359 | 0.7229 | 0.9224 |
|
85 |
+
|
86 |
+
|
87 |
+
### Framework versions
|
88 |
+
|
89 |
+
- Transformers 4.38.1
|
90 |
+
- Pytorch 2.1.0+cu121
|
91 |
+
- Datasets 2.17.1
|
92 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 440213956
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f5cbee230868a66398bbba74f73d32e9e14a35e1a14661a9580a5c6757e5f34
|
3 |
size 440213956
|
runs/Mar01_02-38-39_1cc23fee8ba3/events.out.tfevents.1709260729.1cc23fee8ba3.4565.2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b40cc9d089a95d828e7cb3e946eb78b6414496ba51fd9f5ac6ce55c7a8d27f7
|
3 |
+
size 7197
|