metadata

license: apache-2.0
base_model: distilbert-base-multilingual-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: spa-eng-pos-tagging-v3
    results: []

spa-eng-pos-tagging-v3

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

Loss: 0.3384
Accuracy: 0.9036
Precision: 0.8993
Recall: 0.8285
F1: 0.8324
Hamming Loss: 0.0964

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: 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: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Hamming Loss
0.7752	1.0	1744	0.7222	0.7342	0.7317	0.6509	0.6524	0.2658
0.6276	2.0	3488	0.5259	0.8059	0.8008	0.7205	0.7264	0.1941
0.4813	3.0	5232	0.4473	0.8353	0.8281	0.7604	0.7616	0.1647
0.4063	4.0	6976	0.4453	0.8393	0.8353	0.7616	0.7662	0.1607
0.3361	5.0	8720	0.3882	0.8658	0.8661	0.7894	0.7959	0.1342
0.2883	6.0	10464	0.3773	0.8747	0.8693	0.8022	0.8043	0.1253
0.2409	7.0	12208	0.3681	0.8803	0.8753	0.8056	0.8081	0.1197
0.2168	8.0	13952	0.3470	0.8899	0.8836	0.8161	0.8181	0.1101
0.1816	9.0	15696	0.3750	0.8838	0.8832	0.8071	0.8133	0.1162
0.1696	10.0	17440	0.3609	0.8914	0.8871	0.8161	0.8200	0.1086
0.1572	11.0	19184	0.3470	0.8977	0.8924	0.8228	0.8261	0.1023
0.1385	12.0	20928	0.3384	0.9036	0.8993	0.8285	0.8324	0.0964

Framework versions

Transformers 4.32.0
Pytorch 2.0.1+cu118
Tokenizers 0.13.3