candor_np_51

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

  • Loss: 4.4606

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: 256
  • eval_batch_size: 256
  • seed: 51
  • optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
5.7404 1.0 422 4.7804
4.6303 2.0 844 4.5992
4.5079 3.0 1266 4.5215
4.4362 4.0 1688 4.4742
4.3824 5.0 2110 4.4432
4.3364 6.0 2532 4.4151
4.2947 7.0 2954 4.3961
4.2553 8.0 3376 4.3847
4.2166 9.0 3798 4.3793
4.1779 10.0 4220 4.3769
4.1392 11.0 4642 4.3781
4.1004 12.0 5064 4.3813
4.0613 13.0 5486 4.3906
4.0233 14.0 5908 4.4032
3.9868 15.0 6330 4.4124
3.9523 16.0 6752 4.4254
3.9204 17.0 7174 4.4358
3.8927 18.0 7596 4.4476
3.8706 19.0 8018 4.4548
3.8539 20.0 8440 4.4606

Framework versions

  • Transformers 4.56.1
  • Pytorch 2.8.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.0
Downloads last month
56
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Evaluation results