metadata
base_model: cardiffnlp/twitter-xlm-roberta-base-sentiment
tags:
- generated_from_trainer
model-index:
- name: twitter-xlm-roberta-base-sentiment
results: []
twitter-xlm-roberta-base-sentiment
This model is a fine-tuned version of cardiffnlp/twitter-xlm-roberta-base-sentiment on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6295
- Rmse: 0.7173
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rmse |
|---|---|---|---|---|
| 0.7384 | 1.0 | 500 | 0.7162 | 0.7593 |
| 0.6322 | 2.0 | 1000 | 0.6433 | 0.7228 |
| 0.541 | 3.0 | 1500 | 0.6295 | 0.7173 |
| 0.4118 | 4.0 | 2000 | 0.7930 | 0.6804 |
| 0.2949 | 5.0 | 2500 | 0.8727 | 0.6756 |
| 0.2109 | 6.0 | 3000 | 1.2173 | 0.7211 |
| 0.1558 | 7.0 | 3500 | 1.5233 | 0.7249 |
| 0.1077 | 8.0 | 4000 | 1.6957 | 0.7162 |
| 0.0767 | 9.0 | 4500 | 1.8504 | 0.6982 |
| 0.0534 | 10.0 | 5000 | 1.9203 | 0.7068 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1