metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta-base-riddle-finetuned_new_3choice
results: []
roberta-base-riddle-finetuned_new_3choice
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2420
- Accuracy: 0.9000
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: 0.001
- 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 23 | 0.4131 | 0.875 |
No log | 2.0 | 46 | 0.4599 | 0.8250 |
No log | 3.0 | 69 | 0.3552 | 0.8250 |
No log | 4.0 | 92 | 0.3887 | 0.8500 |
No log | 5.0 | 115 | 0.3795 | 0.875 |
No log | 6.0 | 138 | 0.3703 | 0.875 |
No log | 7.0 | 161 | 0.2565 | 0.875 |
No log | 8.0 | 184 | 0.4069 | 0.875 |
No log | 9.0 | 207 | 0.2420 | 0.9000 |
No log | 10.0 | 230 | 0.2521 | 0.9000 |
Framework versions
- Transformers 4.36.2
- Pytorch 1.13.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.0