wiki_w_30

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

  • Loss: 5.4160

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
7.0487 1.0 400 6.1961
5.9579 2.0 800 5.8509
5.7329 3.0 1200 5.7164
5.6001 4.0 1600 5.6209
5.4926 5.0 2000 5.5505
5.4002 6.0 2400 5.4954
5.3184 7.0 2800 5.4550
5.2446 8.0 3200 5.4271
5.1766 9.0 3600 5.4064
5.1131 10.0 4000 5.3941
5.0524 11.0 4400 5.3854
4.9961 12.0 4800 5.3821
4.9422 13.0 5200 5.3864
4.891 14.0 5600 5.3879
4.8459 15.0 6000 5.3910
4.8059 16.0 6400 5.3987
4.7713 17.0 6800 5.4039
4.7416 18.0 7200 5.4100
4.7178 19.0 7600 5.4134
4.6991 20.0 8000 5.4160

Framework versions

  • Transformers 4.56.1
  • Pytorch 2.8.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.0
Downloads last month
38
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