wiki_o_67

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

  • Loss: 4.3688

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: 67
  • 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
6.9863 1.0 399 5.9816
5.6184 2.0 798 5.3611
5.168 3.0 1197 5.0639
4.9038 4.0 1596 4.8716
4.7112 5.0 1995 4.7365
4.5567 6.0 2394 4.6368
4.4271 7.0 2793 4.5616
4.3154 8.0 3192 4.5030
4.2166 9.0 3591 4.4596
4.1296 10.0 3990 4.4295
4.0523 11.0 4389 4.4067
3.9838 12.0 4788 4.3896
3.9219 13.0 5187 4.3781
3.8667 14.0 5586 4.3692
3.8168 15.0 5985 4.3677
3.7728 16.0 6384 4.3674
3.7344 17.0 6783 4.3653
3.7016 18.0 7182 4.3660
3.6741 19.0 7581 4.3677
3.6531 20.0 7980 4.3688

Framework versions

  • Transformers 4.56.1
  • Pytorch 2.8.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.0
Downloads last month
3
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