metadata
license: apache-2.0
base_model: asn1814/openbookqa_bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: openbookqa_bert-base-uncased_fact_retrieval_k_10
results: []
openbookqa_bert-base-uncased_fact_retrieval_k_10
This model is a fine-tuned version of asn1814/openbookqa_bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.9155
- Accuracy: 0.59
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3035 | 1.0 | 310 | 1.4148 | 0.57 |
| 0.1243 | 2.0 | 620 | 1.9743 | 0.57 |
| 0.077 | 3.0 | 930 | 2.4690 | 0.584 |
| 0.028 | 4.0 | 1240 | 2.8887 | 0.582 |
| 0.0118 | 5.0 | 1550 | 2.9155 | 0.59 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2