BenasSabalys
commited on
Commit
·
a49f82b
1
Parent(s):
83ae482
Update README.md
Browse files
README.md
CHANGED
@@ -17,16 +17,6 @@ This is a gpt2 model trained on 142 612 different Lithuanian Wikipedia articles
|
|
17 |
|
18 |
This is a model I trained when writing my bachelors. You can use it anywhere you want.
|
19 |
|
20 |
-
## Training procedure
|
21 |
-
Will be updated
|
22 |
-
|
23 |
-
### Training hyperparameters
|
24 |
-
|
25 |
-
The following hyperparameters were used during training:
|
26 |
-
|
27 |
-
- optimizer: None
|
28 |
-
- training_precision: float32
|
29 |
-
|
30 |
### Training results
|
31 |
|
32 |
Model reached 36.83% accuracy with training data and 37.02% with validation data
|
@@ -61,6 +51,6 @@ beam_outputs = model.generate(
|
|
61 |
no_repeat_ngram_size=2,
|
62 |
num_return_sequences=5
|
63 |
)
|
64 |
-
```
|
65 |
|
66 |
-
print(tokenizer.decode(beam_outputs[0]))
|
|
|
|
17 |
|
18 |
This is a model I trained when writing my bachelors. You can use it anywhere you want.
|
19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
### Training results
|
21 |
|
22 |
Model reached 36.83% accuracy with training data and 37.02% with validation data
|
|
|
51 |
no_repeat_ngram_size=2,
|
52 |
num_return_sequences=5
|
53 |
)
|
|
|
54 |
|
55 |
+
print(tokenizer.decode(beam_outputs[0]))
|
56 |
+
```
|