Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,19 @@
|
|
1 |
---
|
2 |
license: afl-3.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: afl-3.0
|
3 |
---
|
4 |
+
A MacBERTh model fine-tuned on SQuAD_v2. Hopefully, this will allow the model to perform well on QA tasks on historical texts.
|
5 |
+
Finetune parameters:
|
6 |
+
|
7 |
+
```
|
8 |
+
training_args = TrainingArguments(
|
9 |
+
output_dir="./results",
|
10 |
+
evaluation_strategy="epoch",
|
11 |
+
learning_rate=3e-5,
|
12 |
+
per_device_train_batch_size=64,
|
13 |
+
per_device_eval_batch_size=64,
|
14 |
+
num_train_epochs=2,
|
15 |
+
weight_decay=0.01,
|
16 |
+
lr_scheduler_type=SchedulerType.LINEAR,
|
17 |
+
warmup_ratio=0.2
|
18 |
+
)
|
19 |
+
```
|