metadata
library_name: transformers
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_IMDB_roberta
results: []
my_awesome_IMDB_roberta
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6932
- Accuracy: 0.5
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: 4e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7042 | 1.0 | 3125 | 0.7165 | 0.5 |
| 0.703 | 2.0 | 6250 | 0.6988 | 0.5 |
| 0.7011 | 3.0 | 9375 | 0.6976 | 0.5 |
| 0.701 | 4.0 | 12500 | 0.6945 | 0.5 |
| 0.6971 | 5.0 | 15625 | 0.6980 | 0.5 |
| 0.6975 | 6.0 | 18750 | 0.6934 | 0.5 |
| 0.697 | 7.0 | 21875 | 0.6949 | 0.5 |
| 0.6962 | 8.0 | 25000 | 0.6935 | 0.5 |
| 0.6952 | 9.0 | 28125 | 0.6933 | 0.5 |
| 0.6957 | 10.0 | 31250 | 0.6932 | 0.5 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3