metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: 16class_11k_newtest_xlm_roberta_base_25nov_v2_8epoch
results: []
16class_11k_newtest_xlm_roberta_base_25nov_v2_8epoch
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: 0.1142
- Accuracy: 0.9706
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.7244 | 1.0 | 826 | 0.6693 | 0.8036 |
0.6119 | 2.0 | 1652 | 0.4189 | 0.8734 |
0.5004 | 3.0 | 2478 | 0.3088 | 0.9141 |
0.3626 | 4.0 | 3304 | 0.2287 | 0.9339 |
0.2776 | 5.0 | 4130 | 0.1735 | 0.9513 |
0.2445 | 6.0 | 4956 | 0.1446 | 0.9606 |
0.1944 | 7.0 | 5782 | 0.1192 | 0.9682 |
0.1633 | 8.0 | 6608 | 0.1142 | 0.9706 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0