AndresR2909/finetuning_bert_text_classification

Source: 🤗At risk🏴‍☠️ Rescued by: isilicontext-classificationapache-2.067M params269 MBsafetensors✓ 7 checksumsupdated 761d ago

Magnet 0

finetuning-bert-text-classification

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

Loss: 0.2394
Accuracy: 0.9073

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: 16
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
0.2612	1.0	6250	0.2394	0.9073
0.1966	2.0	12500	0.2488	0.9184
0.1737	3.0	18750	0.2759	0.9192
0.1415	4.0	25000	0.3322	0.9165
0.0857	5.0	31250	0.3835	0.9199

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1

Loading…