metadata
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
model-index:
- name: roberta_large_hv_3
results: []
Human Value Detection Roberta Large with Upsampled Data
This model is a fine-tuned version of FacebookAI/roberta-large on the upsampled training data of the ValueML dataset.
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
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 4
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0
- Datasets 2.19.0
- Tokenizers 0.15.1