metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: distilroberta-base-culinary
results: []
distilroberta-base-culinary
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0654
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.4348 | 1.0 | 29539 | 1.3527 |
1.2839 | 2.0 | 59078 | 1.2602 |
1.2093 | 3.0 | 88617 | 1.1843 |
1.1824 | 4.0 | 118156 | 1.1563 |
1.1019 | 5.0 | 147695 | 1.1089 |
1.1 | 6.0 | 177234 | 1.0874 |
1.0624 | 7.0 | 206773 | 1.0701 |
1.0421 | 8.0 | 236312 | 1.0654 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1