metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: distilbert-training-1
    results: []

distilbert-training-1

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

Loss: 0.0337
Accuracy: 0.9940
Precision: 1.0
Recall: 0.9875
F1: 0.9937

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: 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	0.25	85	0.0878	0.9819	0.9787	0.9840	0.9813
No log	0.5	170	0.0763	0.9819	1.0	0.9626	0.9809
No log	0.75	255	0.0487	0.9880	0.9841	0.9911	0.9876
0.088	1.0	340	0.0411	0.9931	1.0	0.9857	0.9928
0.088	1.25	425	0.0417	0.9914	0.9964	0.9857	0.9910
0.088	1.5	510	0.0423	0.9923	0.9946	0.9893	0.9920
0.088	1.76	595	0.0404	0.9931	1.0	0.9857	0.9928
0.0325	2.01	680	0.0459	0.9931	1.0	0.9857	0.9928
0.0325	2.26	765	0.0336	0.9940	1.0	0.9875	0.9937
0.0325	2.51	850	0.0358	0.9931	1.0	0.9857	0.9928
0.0325	2.76	935	0.0413	0.9931	1.0	0.9857	0.9928
0.0236	3.01	1020	0.0423	0.9931	1.0	0.9857	0.9928
0.0236	3.26	1105	0.0399	0.9940	1.0	0.9875	0.9937
0.0236	3.51	1190	0.0380	0.9940	1.0	0.9875	0.9937
0.0236	3.76	1275	0.0357	0.9940	1.0	0.9875	0.9937
0.0222	4.01	1360	0.0364	0.9940	1.0	0.9875	0.9937
0.0222	4.26	1445	0.0351	0.9940	1.0	0.9875	0.9937
0.0222	4.51	1530	0.0329	0.9940	1.0	0.9875	0.9937
0.0222	4.76	1615	0.0337	0.9940	1.0	0.9875	0.9937

Framework versions

Transformers 4.33.1
Pytorch 2.2.0.dev20230913+cu121
Tokenizers 0.13.3