update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: 10_epochs_camembert_jb
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# 10_epochs_camembert_jb
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [Jean-Baptiste/camembert-ner](https://huggingface.co/Jean-Baptiste/camembert-ner) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.1070
|
18 |
+
- Overall Precision: 0.8279
|
19 |
+
- Overall Recall: 0.8660
|
20 |
+
- Overall F1: 0.8465
|
21 |
+
- Overall Accuracy: 0.9803
|
22 |
+
- Er F1: 0.8617
|
23 |
+
- Oc F1: 0.8347
|
24 |
+
- Umanprod F1: 0.7297
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 2e-05
|
44 |
+
- train_batch_size: 16
|
45 |
+
- eval_batch_size: 16
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 10
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | Er F1 | Oc F1 | Umanprod F1 |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|:------:|:------:|:-----------:|
|
55 |
+
| 0.2805 | 1.0 | 613 | 0.0797 | 0.7802 | 0.7990 | 0.7895 | 0.9749 | 0.8187 | 0.7677 | 0.4231 |
|
56 |
+
| 0.072 | 2.0 | 1226 | 0.0790 | 0.8060 | 0.8392 | 0.8223 | 0.9773 | 0.8458 | 0.8050 | 0.5574 |
|
57 |
+
| 0.0511 | 3.0 | 1839 | 0.0807 | 0.8139 | 0.8623 | 0.8374 | 0.9789 | 0.8583 | 0.8200 | 0.6933 |
|
58 |
+
| 0.0354 | 4.0 | 2452 | 0.0808 | 0.8097 | 0.8574 | 0.8329 | 0.9793 | 0.8589 | 0.8115 | 0.6667 |
|
59 |
+
| 0.0198 | 5.0 | 3065 | 0.0940 | 0.7936 | 0.8591 | 0.8250 | 0.9781 | 0.8426 | 0.8124 | 0.6835 |
|
60 |
+
| 0.0165 | 6.0 | 3678 | 0.0988 | 0.8350 | 0.8542 | 0.8445 | 0.9802 | 0.8656 | 0.8297 | 0.6486 |
|
61 |
+
| 0.0126 | 7.0 | 4291 | 0.0990 | 0.8292 | 0.8692 | 0.8488 | 0.9805 | 0.8682 | 0.8340 | 0.6849 |
|
62 |
+
| 0.0103 | 8.0 | 4904 | 0.1042 | 0.8246 | 0.8666 | 0.8450 | 0.9803 | 0.8630 | 0.8331 | 0.6575 |
|
63 |
+
| 0.0076 | 9.0 | 5517 | 0.1066 | 0.8195 | 0.8687 | 0.8434 | 0.9801 | 0.8593 | 0.8305 | 0.7297 |
|
64 |
+
| 0.0066 | 10.0 | 6130 | 0.1070 | 0.8279 | 0.8660 | 0.8465 | 0.9803 | 0.8617 | 0.8347 | 0.7297 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.25.1
|
70 |
+
- Pytorch 1.13.0+cpu
|
71 |
+
- Datasets 2.7.1
|
72 |
+
- Tokenizers 0.13.2
|