metadata

license: mit
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: xlm-roberta-base-wnut2017
    results: []

xlm-roberta-base-wnut2017

This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2943
Precision: 0.5430
Recall: 0.4181
F1: 0.4724
Accuracy: 0.9379

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: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	106	0.3715	0.0667	0.0012	0.0024	0.9119
No log	2.0	212	0.3279	0.3482	0.1783	0.2359	0.9217
No log	3.0	318	0.3008	0.5574	0.3627	0.4394	0.9344
No log	4.0	424	0.2884	0.5226	0.3614	0.4274	0.9363
0.2149	5.0	530	0.2943	0.5430	0.4181	0.4724	0.9379
0.2149	6.0	636	0.3180	0.5338	0.3711	0.4378	0.9377
0.2149	7.0	742	0.3090	0.4993	0.4277	0.4607	0.9365
0.2149	8.0	848	0.3300	0.5300	0.4048	0.4590	0.9380
0.2149	9.0	954	0.3365	0.4938	0.3843	0.4322	0.9367
0.0623	10.0	1060	0.3363	0.5028	0.4313	0.4643	0.9363
0.0623	11.0	1166	0.3567	0.4992	0.3880	0.4366	0.9356
0.0623	12.0	1272	0.3681	0.5164	0.3988	0.4500	0.9375
0.0623	13.0	1378	0.3698	0.5086	0.3928	0.4432	0.9376
0.0623	14.0	1484	0.3690	0.5157	0.4157	0.4603	0.9380
0.0303	15.0	1590	0.3744	0.5045	0.4072	0.4507	0.9375

Framework versions

Transformers 4.26.1
Pytorch 1.13.1+cu116
Datasets 2.9.0
Tokenizers 0.13.2