metadata
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
model-index:
- name: hupd_mlm_distilroberta
results: []
hupd_mlm_distilroberta
This model is a fine-tuned version of distilroberta-base on the [HUPD][https://huggingface.co/datasets/HUPD/hupd] patent dataset. It achieves the following results on the evaluation set:
- Loss: 1.1515
- Perplexity: 3.16
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.374 | 1.0 | 2019 | 1.2304 |
| 1.2925 | 2.0 | 4039 | 1.1793 |
| 1.2599 | 3.0 | 6057 | 1.1529 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3