End of training
Browse files
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: pdelobelle/robbert-v2-dutch-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- recall
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: robbert0410_lrate10b16
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# robbert0410_lrate10b16
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [pdelobelle/robbert-v2-dutch-base](https://huggingface.co/pdelobelle/robbert-v2-dutch-base) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.4783
|
22 |
+
- Precisions: 0.8324
|
23 |
+
- Recall: 0.8123
|
24 |
+
- F-measure: 0.8208
|
25 |
+
- Accuracy: 0.9164
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 0.0001
|
45 |
+
- train_batch_size: 16
|
46 |
+
- eval_batch_size: 16
|
47 |
+
- seed: 42
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 8
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:---------:|:--------:|
|
56 |
+
| 0.6379 | 1.0 | 236 | 0.4156 | 0.8657 | 0.6790 | 0.6955 | 0.8798 |
|
57 |
+
| 0.3257 | 2.0 | 472 | 0.3378 | 0.7529 | 0.7397 | 0.7336 | 0.8932 |
|
58 |
+
| 0.1977 | 3.0 | 708 | 0.3737 | 0.7960 | 0.7383 | 0.7451 | 0.9003 |
|
59 |
+
| 0.1197 | 4.0 | 944 | 0.4060 | 0.8446 | 0.7503 | 0.7696 | 0.9025 |
|
60 |
+
| 0.0659 | 5.0 | 1180 | 0.4428 | 0.7851 | 0.7731 | 0.7779 | 0.9063 |
|
61 |
+
| 0.0447 | 6.0 | 1416 | 0.4972 | 0.8285 | 0.7991 | 0.8124 | 0.9127 |
|
62 |
+
| 0.0256 | 7.0 | 1652 | 0.4783 | 0.8324 | 0.8123 | 0.8208 | 0.9164 |
|
63 |
+
| 0.0173 | 8.0 | 1888 | 0.4918 | 0.8251 | 0.8082 | 0.8159 | 0.9169 |
|
64 |
+
|
65 |
+
|
66 |
+
### Framework versions
|
67 |
+
|
68 |
+
- Transformers 4.34.0
|
69 |
+
- Pytorch 2.0.1+cu118
|
70 |
+
- Datasets 2.14.5
|
71 |
+
- Tokenizers 0.14.0
|