metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: xmlRoBert-Balanced-trimmed-10epoch-Trainer
results: []
xmlRoBert-Balanced-trimmed-10epoch-Trainer
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1137
- Accuracy: 0.3125
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: 10
- eval_batch_size: 10
- 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 | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 3 | 1.1523 | 0.25 |
| No log | 2.0 | 6 | 1.1465 | 0.25 |
| No log | 3.0 | 9 | 1.1425 | 0.25 |
| No log | 4.0 | 12 | 1.1316 | 0.25 |
| No log | 5.0 | 15 | 1.1158 | 0.25 |
| No log | 6.0 | 18 | 1.1335 | 0.375 |
| No log | 7.0 | 21 | 1.1214 | 0.25 |
| No log | 8.0 | 24 | 1.1198 | 0.25 |
| No log | 9.0 | 27 | 1.1155 | 0.25 |
| No log | 10.0 | 30 | 1.1137 | 0.3125 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 1.13.1
- Datasets 2.14.5
- Tokenizers 0.14.1