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_eng_100m_mult_het

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

  • Loss: 4.9199

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: 8849
  • training_steps: 88495
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
5.3437 1.1301 10000 5.3484
4.6671 2.2601 20000 4.8006
4.3398 3.3902 30000 4.6134
4.0825 4.5202 40000 4.5581
3.861 5.6503 50000 4.5743
3.6091 6.7804 60000 4.6403
3.3689 7.9104 70000 4.7419
2.8561 9.0406 80000 4.8836

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
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Evaluation results