metadata
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: xlm-roberta-base-finetuned-ner-geocorpus
results: []
xlm-roberta-base-finetuned-ner-geocorpus
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1068
- Precision: 0.8357
- Recall: 0.8023
- F1: 0.8187
- Accuracy: 0.9722
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: 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: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 276 | 0.2197 | 0.6414 | 0.5605 | 0.5982 | 0.9495 |
| 0.3027 | 2.0 | 552 | 0.1316 | 0.7289 | 0.7718 | 0.7497 | 0.9657 |
| 0.3027 | 3.0 | 828 | 0.1068 | 0.8357 | 0.8023 | 0.8187 | 0.9722 |
| 0.1022 | 4.0 | 1104 | 0.1235 | 0.6867 | 0.8780 | 0.7707 | 0.9642 |
| 0.1022 | 5.0 | 1380 | 0.1079 | 0.7840 | 0.8854 | 0.8316 | 0.9716 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1