You can deploy this model and start earning money today!

marcgrec/
distilbert-llm-aug-ag-news

Name: distilbert-llm-aug-ag-news
Availability: InStock

generated_from_trainer

distilbert/distilbert-base-multilingual-cased

finetune

apache-2.0

text-embeddings-inference

endpoints_compatible

Views

No views yet

distilbert-llm-aug-ag-news

This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on the marcgrec/ag_news-llm-aug dataset. It achieves the following results on the evaluation set:

Loss: 0.8388
F1: 0.8674

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: 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
No log	1.0	125	0.4951	0.8394
No log	2.0	250	0.6906	0.8426
No log	3.0	375	0.6696	0.8668
0.183	4.0	500	0.7556	0.8632
0.183	5.0	625	0.7720	0.8665
0.183	6.0	750	0.8164	0.8652
0.183	7.0	875	0.8351	0.8655
0.0013	8.0	1000	0.8220	0.8670
0.0013	9.0	1125	0.8334	0.8673
0.0013	10.0	1250	0.8388	0.8674

Framework versions

Transformers 4.57.1
Pytorch 2.9.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

marcgrec/distilbert-llm-aug-ag-news

distilbert-llm-aug-ag-news

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

marcgrec/
distilbert-llm-aug-ag-news