metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: roberta-base-sentiment
results: []
roberta-base-sentiment
This model is a fine-tuned version of roberta-base on a manually labelled sentiment dataset of earnings call transcript sentences. It achieves the following results on the evaluation set:
- Loss: 0.8190
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: 5e-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_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.09 | 1.0 | 39 | 1.0853 |
| 1.0329 | 2.0 | 78 | 1.0255 |
| 0.7433 | 3.0 | 117 | 0.8066 |
| 0.7679 | 4.0 | 156 | 0.7961 |
| 0.4994 | 5.0 | 195 | 0.8190 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1