metadata

license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: boss-toxicity-12000-bert-base-uncased
    results: []

boss-toxicity-12000-bert-base-uncased

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

F1: 0.6566
Acc: 0.8020
Loss: 1.1220

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: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20

Training results

Training Loss	Epoch	Step	F1	Acc	Validation Loss
0.5963	1.0	750	0.7051	0.8547	0.3709
0.2873	2.0	1500	0.7428	0.8860	0.2969
0.206	3.0	2250	0.7121	0.8594	0.4031
0.1319	4.0	3000	0.7368	0.8832	0.4616
0.0751	5.0	3750	0.6566	0.8020	1.1220

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu121
Datasets 2.14.6
Tokenizers 0.14.1