metadata
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
datasets:
- cnec
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: CNEC2_0_Supertypes_xlm-roberta-large
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: cnec
type: cnec
config: default
split: validation
args: default
metrics:
- name: Precision
type: precision
value: 0.8447596532702916
- name: Recall
type: recall
value: 0.8855844692275919
- name: F1
type: f1
value: 0.8646904617866505
- name: Accuracy
type: accuracy
value: 0.9681587715486021
CNEC2_0_Supertypes_xlm-roberta-large
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the cnec dataset. It achieves the following results on the evaluation set:
- Loss: 0.1762
- Precision: 0.8448
- Recall: 0.8856
- F1: 0.8647
- Accuracy: 0.9682
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2106 | 1.0 | 7193 | 0.2086 | 0.7859 | 0.8203 | 0.8027 | 0.9563 |
| 0.1136 | 2.0 | 14386 | 0.1710 | 0.8391 | 0.8678 | 0.8532 | 0.9658 |
| 0.0973 | 3.0 | 21579 | 0.1762 | 0.8448 | 0.8856 | 0.8647 | 0.9682 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0