metadata

language:
  - vi
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
  - generated_from_trainer
model-index:
  - name: xlm-roberta-large_baseline_words
    results: []

xlm-roberta-large_baseline_words

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the covid19_ner dataset. It achieves the following results on the evaluation set:

Loss: 0.0850
Patient Id: 0.9840
Name: 0.7711
Gender: 0.9767
Age: 0.9821
Job: 0.8062
Location: 0.9570
Organization: 0.8784
Date: 0.9869
Symptom And Disease: 0.8688
Transportation: 1.0
F1 Macro: 0.9211
F1 Micro: 0.9459

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Patient Id	Name	Gender	Age	Job	Location	Organization	Date	Symptom And Disease	Transportation	F1 Macro	F1 Micro
0.2002	1.0	629	0.1212	0.9160	0.8349	0.8346	0.8122	0.5385	0.8769	0.7201	0.9553	0.7769	0.8587	0.8124	0.8586
0.0557	2.0	1258	0.1025	0.9594	0.8836	0.9533	0.9731	0.2841	0.9228	0.8301	0.9842	0.8545	0.9444	0.8590	0.9191
0.038	3.0	1887	0.0804	0.9741	0.7154	0.9732	0.9821	0.7615	0.9372	0.8576	0.9869	0.8461	0.9943	0.9028	0.9309
0.0222	4.0	2516	0.0862	0.9871	0.5567	0.9691	0.9862	0.8207	0.9553	0.8707	0.9847	0.8740	1.0	0.9005	0.9398
0.0148	5.0	3145	0.0850	0.9840	0.7711	0.9767	0.9821	0.8062	0.9570	0.8784	0.9869	0.8688	1.0	0.9211	0.9459

Framework versions

Transformers 4.41.2
Pytorch 2.1.2
Datasets 2.19.2
Tokenizers 0.19.1