xlm-roberta-base-finetuned-marc-en
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6572
- Accuracy: 0.7805
- Recall: 0.6445
- Precision: 0.5522
- F1: 0.5948
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: 32
- eval_batch_size: 32
- 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: 15
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1 |
---|---|---|---|---|---|---|---|
0.5098 | 1.0 | 309 | 0.4999 | 0.7498 | 0.0 | 0.0 | 0.0 |
0.4698 | 2.0 | 618 | 0.4456 | 0.7959 | 0.3456 | 0.6816 | 0.4586 |
0.3921 | 3.0 | 927 | 0.4620 | 0.8094 | 0.4561 | 0.6765 | 0.5448 |
0.3771 | 4.0 | 1236 | 0.4446 | 0.8172 | 0.5156 | 0.6766 | 0.5852 |
0.3454 | 5.0 | 1545 | 0.4567 | 0.8249 | 0.5609 | 0.6828 | 0.6159 |
0.2713 | 6.0 | 1854 | 0.4726 | 0.8136 | 0.6176 | 0.6301 | 0.6237 |
0.272 | 7.0 | 2163 | 0.5024 | 0.8108 | 0.6317 | 0.6194 | 0.6255 |
0.2478 | 8.0 | 2472 | 0.5689 | 0.8051 | 0.6516 | 0.6021 | 0.6259 |
0.1869 | 9.0 | 2781 | 0.6018 | 0.8044 | 0.7082 | 0.5910 | 0.6443 |
0.1575 | 10.0 | 3090 | 0.6700 | 0.8108 | 0.4986 | 0.6617 | 0.5687 |
0.1411 | 11.0 | 3399 | 0.7287 | 0.8157 | 0.5581 | 0.6545 | 0.6024 |
0.1014 | 12.0 | 3708 | 0.8177 | 0.8086 | 0.5269 | 0.6436 | 0.5794 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.