metadata

license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: spa-eng-pos-tagging-v1.3
    results: []

spa-eng-pos-tagging-v1.3

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

Loss: 0.1650
Accuracy: 0.9471
Precision: 0.9372
Recall: 0.8815
F1: 0.8779
Hamming Loss: 0.0529

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: 5e-05
train_batch_size: 16
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Hamming Loss
0.3809	1.0	1744	0.2945	0.8919	0.8798	0.8290	0.8221	0.1081
0.2625	2.0	3488	0.2725	0.8975	0.9004	0.8279	0.8319	0.1025
0.1918	3.0	5232	0.1901	0.9317	0.9224	0.8645	0.8618	0.0683
0.1674	4.0	6976	0.1780	0.9369	0.9319	0.8695	0.8694	0.0631
0.1478	5.0	8720	0.1816	0.9385	0.9303	0.8735	0.8697	0.0615
0.1201	6.0	10464	0.1650	0.9471	0.9372	0.8815	0.8779	0.0529
0.096	7.0	12208	0.1663	0.9493	0.9390	0.8851	0.8806	0.0507
0.0844	8.0	13952	0.1715	0.9500	0.9421	0.8838	0.8815	0.0500
0.0687	9.0	15696	0.1877	0.9502	0.9433	0.8816	0.8811	0.0498
0.0573	10.0	17440	0.1949	0.9483	0.9444	0.8781	0.8799	0.0517
0.0533	11.0	19184	0.1960	0.9544	0.9450	0.8872	0.8847	0.0456
0.0399	12.0	20928	0.2012	0.9565	0.9494	0.8884	0.8876	0.0435
0.031	13.0	22672	0.2119	0.9571	0.9496	0.8889	0.8879	0.0429
0.0292	14.0	24416	0.2213	0.9587	0.9512	0.8906	0.8896	0.0413
0.024	15.0	26160	0.2274	0.9587	0.9517	0.8899	0.8895	0.0413
0.0198	16.0	27904	0.2314	0.9591	0.8894	0.8905	0.8899	0.0409

Framework versions

Transformers 4.32.0
Pytorch 2.0.1+cu118
Tokenizers 0.13.3