metadata

library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-multilingual-cased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
model-index:
  - name: fine-tuned-distilbert-autofill
    results: []

fine-tuned-distilbert-autofill

This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0516
Precision: 0.9887
Recall: 0.9876
F1: 0.9878
Confusion Matrix: [[ 93 7 0] [ 15 43 0] [ 11 0 2489]]

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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Confusion Matrix
No log	1.0	367	0.0597	0.9626	0.9733	0.9659	[[ 100 0 0]
[ 58 0 0]
[ 13 0 2487]]
0.1186	2.0	734	0.0664	0.9622	0.9722	0.9650	[[ 100 0 0]
[ 58 0 0]
[ 16 0 2484]]
0.1138	3.0	1101	0.0447	0.9873	0.9853	0.9851	[[ 96 4 0]
[ 25 33 0]
[ 9 1 2490]]
0.1138	4.0	1468	0.0459	0.9870	0.9857	0.9858	[[ 92 8 0]
[ 20 38 0]
[ 10 0 2490]]
0.094	5.0	1835	0.0518	0.9872	0.9865	0.9867	[[ 90 10 0]
[ 16 42 0]
[ 8 2 2490]]
0.0725	6.0	2202	0.0606	0.9836	0.9808	0.9819	[[ 91 9 0]
[ 15 43 0]
[ 11 16 2473]]
0.0811	7.0	2569	0.0572	0.9864	0.9846	0.9849	[[ 93 7 0]
[ 19 39 0]
[ 14 1 2485]]
0.0811	8.0	2936	0.0610	0.9861	0.9846	0.9851	[[ 89 11 0]
[ 15 43 0]
[ 15 0 2485]]
0.0602	9.0	3303	0.0465	0.9885	0.9868	0.9869	[[ 95 5 0]
[ 19 39 0]
[ 11 0 2489]]
0.0457	10.0	3670	0.0516	0.9887	0.9876	0.9878	[[ 93 7 0]
[ 15 43 0]
[ 11 0 2489]]

Framework versions

Transformers 4.44.2
Pytorch 2.1.2
Datasets 2.19.2
Tokenizers 0.19.1