distilbert-base-uncased – AI Model by Jaats | AlphaNeural AI

You can deploy this model and start earning money today!

Jaats/
distilbert-base-uncased

like

0

text-classification

generated_from_trainer

text-embeddings-inference

endpoints_compatible

Views

No views yet

distilbert-base-uncased

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.0305
F1: 0.6423

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
gradient_accumulation_steps: 8
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1
5.6264	1.0	236	0.7188	0.6106
4.8328	2.0	472	0.7031	0.6390
4.3461	3.0	708	0.7443	0.6344
4.0118	4.0	944	0.7749	0.6535
2.8793	5.0	1180	0.7818	0.6664
2.7670	6.0	1416	0.8388	0.6593
2.0051	7.0	1652	0.9725	0.6391
1.6775	8.0	1888	1.0305	0.6423

Framework versions

Transformers 5.6.2
Pytorch 2.11.0
Datasets 4.8.5
Tokenizers 0.22.2