Commit
•
9e6bee9
1
Parent(s):
ce89360
update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,73 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- pt
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- toxicity
|
| 7 |
+
- portuguese
|
| 8 |
+
- hate speech
|
| 9 |
+
- offensive language
|
| 10 |
+
- generated_from_trainer
|
| 11 |
+
metrics:
|
| 12 |
+
- accuracy
|
| 13 |
+
- f1
|
| 14 |
+
- precision
|
| 15 |
+
- recall
|
| 16 |
+
model-index:
|
| 17 |
+
- name: dougtrajano/toxicity-target-type-identification
|
| 18 |
+
results: []
|
| 19 |
---
|
| 20 |
+
|
| 21 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 22 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 23 |
+
|
| 24 |
+
# dougtrajano/toxicity-target-type-identification
|
| 25 |
+
|
| 26 |
+
This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on the OLID-BR dataset.
|
| 27 |
+
It achieves the following results on the evaluation set:
|
| 28 |
+
- Loss: 0.7001
|
| 29 |
+
- Accuracy: 0.7505
|
| 30 |
+
- F1: 0.7603
|
| 31 |
+
- Precision: 0.7813
|
| 32 |
+
- Recall: 0.7505
|
| 33 |
+
|
| 34 |
+
## Model description
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Intended uses & limitations
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Training and evaluation data
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training procedure
|
| 47 |
+
|
| 48 |
+
### Training hyperparameters
|
| 49 |
+
|
| 50 |
+
The following hyperparameters were used during training:
|
| 51 |
+
- learning_rate: 3.952388499692274e-05
|
| 52 |
+
- train_batch_size: 8
|
| 53 |
+
- eval_batch_size: 8
|
| 54 |
+
- seed: 1993
|
| 55 |
+
- optimizer: Adam with betas=(0.9944095815441554,0.8750000522553327) and epsilon=1.8526084265228802e-07
|
| 56 |
+
- lr_scheduler_type: linear
|
| 57 |
+
- num_epochs: 30
|
| 58 |
+
|
| 59 |
+
### Training results
|
| 60 |
+
|
| 61 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
| 62 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
| 63 |
+
| No log | 1.0 | 355 | 0.7001 | 0.7505 | 0.7603 | 0.7813 | 0.7505 |
|
| 64 |
+
| 0.7919 | 2.0 | 710 | 1.0953 | 0.7505 | 0.7452 | 0.7590 | 0.7505 |
|
| 65 |
+
| 0.5218 | 3.0 | 1065 | 1.4217 | 0.7484 | 0.7551 | 0.7688 | 0.7484 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.26.0
|
| 71 |
+
- Pytorch 1.10.2+cu113
|
| 72 |
+
- Datasets 2.9.0
|
| 73 |
+
- Tokenizers 0.13.2
|