wiki_o_51

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

  • Loss: 4.3671

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
6.9819 1.0 399 5.9839
5.6158 2.0 798 5.3552
5.164 3.0 1197 5.0618
4.902 4.0 1596 4.8701
4.7103 5.0 1995 4.7380
4.5566 6.0 2394 4.6373
4.4277 7.0 2793 4.5609
4.3162 8.0 3192 4.5039
4.2176 9.0 3591 4.4623
4.1306 10.0 3990 4.4268
4.0536 11.0 4389 4.4057
3.9853 12.0 4788 4.3880
3.9239 13.0 5187 4.3786
3.8689 14.0 5586 4.3702
3.8194 15.0 5985 4.3663
3.7756 16.0 6384 4.3651
3.7371 17.0 6783 4.3632
3.7042 18.0 7182 4.3638
3.677 19.0 7581 4.3666
3.6565 20.0 7980 4.3671

Framework versions

  • Transformers 4.56.1
  • Pytorch 2.8.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.0
Downloads last month
75
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