Commit
•
0e5a4dd
1
Parent(s):
985efa0
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
- f1
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
model-index:
|
11 |
+
- name: SloBertAA_Top100_WithoutOOC_082023_MultilingualBertBase
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# SloBertAA_Top100_WithoutOOC_082023_MultilingualBertBase
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an unknown dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 1.8490
|
23 |
+
- Accuracy: 0.6964
|
24 |
+
- F1: 0.6972
|
25 |
+
- Precision: 0.7001
|
26 |
+
- Recall: 0.6964
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 2e-05
|
46 |
+
- train_batch_size: 12
|
47 |
+
- eval_batch_size: 12
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 10
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
56 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|:---------:|:------:|
|
57 |
+
| 1.6988 | 1.0 | 44675 | 1.6287 | 0.5883 | 0.5902 | 0.6087 | 0.5883 |
|
58 |
+
| 1.3829 | 2.0 | 89350 | 1.4305 | 0.6351 | 0.6379 | 0.6563 | 0.6351 |
|
59 |
+
| 1.1122 | 3.0 | 134025 | 1.3339 | 0.6635 | 0.6651 | 0.6774 | 0.6635 |
|
60 |
+
| 0.881 | 4.0 | 178700 | 1.3128 | 0.6799 | 0.6805 | 0.6876 | 0.6799 |
|
61 |
+
| 0.7032 | 5.0 | 223375 | 1.3628 | 0.6831 | 0.6840 | 0.6932 | 0.6831 |
|
62 |
+
| 0.5454 | 6.0 | 268050 | 1.4343 | 0.6877 | 0.6890 | 0.6956 | 0.6877 |
|
63 |
+
| 0.408 | 7.0 | 312725 | 1.5546 | 0.6877 | 0.6888 | 0.6958 | 0.6877 |
|
64 |
+
| 0.2752 | 8.0 | 357400 | 1.6623 | 0.6932 | 0.6948 | 0.6992 | 0.6932 |
|
65 |
+
| 0.1844 | 9.0 | 402075 | 1.7825 | 0.6947 | 0.6959 | 0.6995 | 0.6947 |
|
66 |
+
| 0.1506 | 10.0 | 446750 | 1.8490 | 0.6964 | 0.6972 | 0.7001 | 0.6964 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.26.1
|
72 |
+
- Pytorch 1.8.0
|
73 |
+
- Datasets 2.10.1
|
74 |
+
- Tokenizers 0.13.2
|