candor_np_30

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

  • Loss: 4.4603

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: 30
  • 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
5.7598 1.0 422 4.7842
4.6302 2.0 844 4.5992
4.509 3.0 1266 4.5203
4.4379 4.0 1688 4.4752
4.3845 5.0 2110 4.4397
4.339 6.0 2532 4.4169
4.2979 7.0 2954 4.3993
4.2587 8.0 3376 4.3859
4.2205 9.0 3798 4.3783
4.1822 10.0 4220 4.3769
4.144 11.0 4642 4.3795
4.1055 12.0 5064 4.3841
4.067 13.0 5486 4.3927
4.0291 14.0 5908 4.4016
3.993 15.0 6330 4.4118
3.9588 16.0 6752 4.4246
3.9273 17.0 7174 4.4361
3.8995 18.0 7596 4.4472
3.8776 19.0 8018 4.4547
3.861 20.0 8440 4.4603

Framework versions

  • Transformers 4.56.1
  • Pytorch 2.8.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.0
Downloads last month
64
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