You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

dense_dan_100m_mult

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

  • Loss: 5.0855

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 11395
  • training_steps: 113957
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
5.9371 0.8775 10000 5.8804
4.9934 1.7550 20000 5.0208
4.6476 2.6325 30000 4.7727
4.3166 3.5100 40000 4.6728
4.0181 4.3875 50000 4.6482
3.7146 5.2650 60000 4.6816
3.3834 6.1425 70000 4.7419
3.0504 7.0200 80000 4.8071
3.208 7.8975 90000 4.8842
2.9186 8.7750 100000 5.0045
2.6484 9.6525 110000 5.0833

Framework versions

  • Transformers 4.51.0
  • Pytorch 2.7.0+cu126
  • Datasets 3.6.0
  • Tokenizers 0.21.1
Downloads last month
-
Safetensors
Model size
0.2B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Evaluation results