README.md

---
language:
  - multilingual

datasets:
  - squad

---

# Multilingual BERT fine-tuned on SQuADv1.1

## Training Arguments

```python
max_seq_length              = 512
doc_stride                  = 256
max_answer_length           = 64
bacth_size                  = 16
gradient_accumulation_steps = 2
learning_rate               = 5e-5
weight_decay                = 3e-7
num_train_epochs            = 3
warmup_ratio                = 0.1
fp16                        = True
fp16_opt_level              = "O1"
seed                        = 0
```

## Results

| EM | F1 |
| :---: | :---: |
| 81.731 | 89.009 |