metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: bert-base-uncased-squad
results: []
bert-base-uncased-squad
This model is a fine-tuned version of bert-base-uncased on an unknown dataset.
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: 9e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: IPU
- gradient_accumulation_steps: 32
- total_train_batch_size: 2048
- total_eval_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.25
- num_epochs: 3
- training precision: Mixed Precision
Training results
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cpu
- Datasets 2.8.0
- Tokenizers 0.12.1