Commit
·
b8506f1
1
Parent(s):
f6059d3
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- pt
|
4 |
+
metrics:
|
5 |
+
- perplexity
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
---
|
8 |
+
# Model Card for Model ID
|
9 |
+
|
10 |
+
A Portuguese language model trained on https://huggingface.co/facebook/opt-125m .
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** Monique Monteiro
|
21 |
+
- **Shared by [optional]:** Monique Monteiro
|
22 |
+
- **Model type:** OPT
|
23 |
+
- **Language(s) (NLP):** Portuguese
|
24 |
+
- **License:** [More Information Needed]
|
25 |
+
- **Finetuned from model [optional]:** facebook/opt-125m
|
26 |
+
|
27 |
+
Use the code below to get started with the model.
|
28 |
+
|
29 |
+
```python
|
30 |
+
generator = pipeline('text-generation', 'monilouise/opt125M_portuguese')
|
31 |
+
output = generator("Era uma vez", max_length=50, do_sample=True)
|
32 |
+
```
|
33 |
+
|
34 |
+
## Training Details
|
35 |
+
|
36 |
+
### Training Data
|
37 |
+
|
38 |
+
The model was trained on gs://unicamp-dl/ia025a_2022s1/aula9/sample-1gb.txt
|
39 |
+
|
40 |
+
### Training Procedure
|
41 |
+
|
42 |
+
The model was trained for 3 epochs, by using learning rate = 5e-5 (linear scheduler).
|
43 |
+
|
44 |
+
#### Preprocessing [optional]
|
45 |
+
|
46 |
+
All text was tokenized and broken into chunks of 1024 tokens.
|
47 |
+
|
48 |
+
|
49 |
+
#### Training Hyperparameters
|
50 |
+
|
51 |
+
- **Training regime:** fp16 mixed precision
|
52 |
+
|
53 |
+
#### Speeds, Sizes, Times [optional]
|
54 |
+
|
55 |
+
Training time: 17 hours
|
56 |
+
|
57 |
+
## Evaluation
|
58 |
+
|
59 |
+
The model was evaluated on a 5% validation split.
|
60 |
+
|
61 |
+
#### Metrics
|
62 |
+
|
63 |
+
Perplexity = 7.94.
|
64 |
+
|
65 |
+
## Model Card Authors [optional]
|
66 |
+
|
67 | |
68 |
+
|
69 |
+
## Model Card Contact
|
70 |
+
|
71 |