metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: roberta-base-ppasubj-20000-1e-06-8
results: []
roberta-base-ppasubj-20000-1e-06-8
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6790
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: 1e-06
- train_batch_size: 32
- eval_batch_size: 1024
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.6939 | 1.0 | 625 | 0.6925 |
0.6933 | 2.0 | 1250 | 0.6912 |
0.6909 | 3.0 | 1875 | 0.6863 |
0.683 | 4.0 | 2500 | 0.6799 |
0.6813 | 5.0 | 3125 | 0.6772 |
0.6752 | 6.0 | 3750 | 0.6766 |
0.6711 | 7.0 | 4375 | 0.6758 |
0.6694 | 8.0 | 5000 | 0.6778 |
0.6682 | 9.0 | 5625 | 0.6816 |
0.6601 | 10.0 | 6250 | 0.6790 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1