SiddharthaM
commited on
Commit
•
ae8de28
1
Parent(s):
5f4ef49
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 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
model-index:
|
11 |
+
- name: hasoc19-bert-base-multilingual-cased-profane-new
|
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 |
+
# hasoc19-bert-base-multilingual-cased-profane-new
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.5065
|
23 |
+
- Accuracy: 0.9030
|
24 |
+
- Precision: 0.8465
|
25 |
+
- Recall: 0.8330
|
26 |
+
- F1: 0.8395
|
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: 1e-05
|
46 |
+
- train_batch_size: 32
|
47 |
+
- eval_batch_size: 32
|
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 | Precision | Recall | F1 |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
57 |
+
| No log | 1.0 | 296 | 0.2873 | 0.8954 | 0.8513 | 0.7881 | 0.8140 |
|
58 |
+
| 0.2999 | 2.0 | 592 | 0.2556 | 0.9078 | 0.8703 | 0.8149 | 0.8385 |
|
59 |
+
| 0.2999 | 3.0 | 888 | 0.2595 | 0.9106 | 0.8613 | 0.8415 | 0.8509 |
|
60 |
+
| 0.1945 | 4.0 | 1184 | 0.2682 | 0.9078 | 0.8601 | 0.8302 | 0.8439 |
|
61 |
+
| 0.1945 | 5.0 | 1480 | 0.3286 | 0.9087 | 0.8590 | 0.8365 | 0.8471 |
|
62 |
+
| 0.142 | 6.0 | 1776 | 0.3911 | 0.9002 | 0.8390 | 0.8351 | 0.8370 |
|
63 |
+
| 0.0944 | 7.0 | 2072 | 0.4184 | 0.9068 | 0.8558 | 0.8334 | 0.8439 |
|
64 |
+
| 0.0944 | 8.0 | 2368 | 0.4763 | 0.9011 | 0.8450 | 0.8261 | 0.8350 |
|
65 |
+
| 0.0631 | 9.0 | 2664 | 0.4952 | 0.9002 | 0.8412 | 0.8293 | 0.8351 |
|
66 |
+
| 0.0631 | 10.0 | 2960 | 0.5065 | 0.9030 | 0.8465 | 0.8330 | 0.8395 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.24.0.dev0
|
72 |
+
- Pytorch 1.11.0+cu102
|
73 |
+
- Datasets 2.6.1
|
74 |
+
- Tokenizers 0.13.1
|