metadata

library_name: transformers
base_model: FacebookAI/xlm-roberta-large-finetuned-conll03-english
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: xlm-roberta-large-clinical-ner-breast-cancer-sp2
    results: []

xlm-roberta-large-clinical-ner-breast-cancer-sp2

This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll03-english on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2681
Precision: 0.8884
Recall: 0.8873
F1: 0.8879
Accuracy: 0.9450

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_restarts
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.5532	1.0	213	0.5737	0.7666	0.7645	0.7655	0.8879
0.227	2.0	426	0.3389	0.8449	0.8506	0.8477	0.9239
0.1485	3.0	639	0.2949	0.8674	0.8686	0.868	0.9359
0.1168	4.0	852	0.2867	0.8737	0.8679	0.8708	0.9379
0.1178	5.0	1065	0.2790	0.8615	0.8632	0.8624	0.9386
0.0723	6.0	1278	0.2699	0.8798	0.8786	0.8792	0.9434
0.0518	7.0	1491	0.2636	0.8824	0.8859	0.8842	0.9434
0.0549	8.0	1704	0.2635	0.8867	0.8879	0.8873	0.9457
0.0509	9.0	1917	0.2681	0.8884	0.8873	0.8879	0.9450
0.0515	9.9559	2120	0.2690	0.8872	0.8866	0.8869	0.9453

Framework versions

Transformers 4.48.2
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0