xlm-roberta-large_baseline_syllables

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: 0.0838
• Patient Id: 0.9883
• Name: 0.9409
• Gender: 0.9712
• Age: 0.9767
• Job: 0.8506
• Location: 0.9670
• Organization: 0.9134
• Date: 0.9860
• Symptom And Disease: 0.8820
• Transportation: 0.9773
• F1 Macro: 0.9453
• F1 Micro: 0.9587

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
0.1707	1.0	629	0.1042	0.9528	0.9227	0.8406	0.9523	0.5899	0.9308	0.8045	0.9874	0.8248	0.96	0.8766	0.9140
0.0475	2.0	1258	0.0811	0.9841	0.9372	0.9591	0.9876	0.6849	0.9350	0.8817	0.9847	0.8584	0.9831	0.9196	0.9390
0.0312	3.0	1887	0.0744	0.9856	0.9297	0.9691	0.9875	0.7554	0.9578	0.8826	0.9869	0.8648	0.9659	0.9285	0.9498
0.0196	4.0	2516	0.0808	0.9883	0.9465	0.9644	0.9835	0.8346	0.9635	0.9136	0.9856	0.8730	0.9886	0.9442	0.9565
0.0119	5.0	3145	0.0838	0.9883	0.9409	0.9712	0.9767	0.8506	0.9670	0.9134	0.9860	0.8820	0.9773	0.9453	0.9587

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1