Multilingual-Perspectivist-NLU/irony_pt_Brazil
Browse files- README.md +77 -0
- config.json +28 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: roberta-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: irony_pt_Brazil
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# irony_pt_Brazil
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0033
|
24 |
+
- Accuracy: 0.6463
|
25 |
+
- Precision: 0.44
|
26 |
+
- Recall: 0.5739
|
27 |
+
- F1: 0.4981
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-06
|
47 |
+
- train_batch_size: 16
|
48 |
+
- eval_batch_size: 64
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 20
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
58 |
+
| 0.0043 | 1.0 | 71 | 0.0042 | 0.5745 | 0.3448 | 0.4348 | 0.3846 |
|
59 |
+
| 0.0043 | 2.0 | 142 | 0.0041 | 0.5266 | 0.3562 | 0.6783 | 0.4671 |
|
60 |
+
| 0.0039 | 3.0 | 213 | 0.0039 | 0.5266 | 0.3562 | 0.6783 | 0.4671 |
|
61 |
+
| 0.004 | 4.0 | 284 | 0.0038 | 0.6170 | 0.4110 | 0.5826 | 0.4820 |
|
62 |
+
| 0.0036 | 5.0 | 355 | 0.0035 | 0.6516 | 0.4452 | 0.5652 | 0.4981 |
|
63 |
+
| 0.0035 | 6.0 | 426 | 0.0036 | 0.4973 | 0.3630 | 0.8522 | 0.5091 |
|
64 |
+
| 0.0031 | 7.0 | 497 | 0.0033 | 0.5904 | 0.4156 | 0.8348 | 0.5549 |
|
65 |
+
| 0.0027 | 8.0 | 568 | 0.0033 | 0.6543 | 0.4460 | 0.5391 | 0.4882 |
|
66 |
+
| 0.0027 | 9.0 | 639 | 0.0031 | 0.6144 | 0.4257 | 0.7478 | 0.5426 |
|
67 |
+
| 0.0023 | 10.0 | 710 | 0.0029 | 0.6303 | 0.4388 | 0.7478 | 0.5531 |
|
68 |
+
| 0.0021 | 11.0 | 781 | 0.0031 | 0.6383 | 0.4348 | 0.6087 | 0.5072 |
|
69 |
+
| 0.0018 | 12.0 | 852 | 0.0033 | 0.6463 | 0.44 | 0.5739 | 0.4981 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.34.1
|
75 |
+
- Pytorch 2.0.1+cu117
|
76 |
+
- Datasets 2.14.5
|
77 |
+
- Tokenizers 0.14.1
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.34.1",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 50265
|
28 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac07e913bb8f1999e2c724c1820a180ad262c205929238b5827d0aa44191881e
|
3 |
+
size 498657649
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1111cde0490d8c4e3f0f3a2771ec9fa829b0b37740011641dcf766ae6d4a96d
|
3 |
+
size 4091
|