metadata
license: apache-2.0
base_model: bert-large-uncased-whole-word-masking-finetuned-squad
tags:
- generated_from_trainer
model-index:
- name: my_awesome_qa_model
results: []
my_awesome_qa_model
This model is a fine-tuned version of bert-large-uncased-whole-word-masking-finetuned-squad on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6490
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6212 | 1.0 | 10950 | 1.0075 |
| 0.3918 | 2.0 | 21900 | 1.0852 |
| 0.1993 | 3.0 | 32850 | 1.6490 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1