my_final_llama_model_v2_add_wiki_fix_resume

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 4.0000

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: 8
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 64
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • training_steps: 8000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
4.2118 0.1537 500 4.1942
4.1614 0.3074 1000 4.1656
4.1253 0.4611 1500 4.1383
4.1131 0.6148 2000 4.1153
4.0994 0.7685 2500 4.0954
4.0668 0.9222 3000 4.0779
4.0383 1.0756 3500 4.0644
4.049 1.2293 4000 4.0529
4.0126 1.3830 4500 4.0404
3.9655 1.5367 5000 4.0297
3.9358 1.6904 5500 4.0210
3.9137 1.8441 6000 4.0134
4.0083 1.9978 6500 4.0067
3.8427 2.1512 7000 4.0045
3.8823 2.3049 7500 4.0014
3.9662 2.4586 8000 4.0000

Framework versions

  • Transformers 4.57.1
  • Pytorch 2.8.0+cu126
  • Datasets 4.4.1
  • Tokenizers 0.22.1
Downloads last month
529
Safetensors
Model size
64.4M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for mifeng09/my_final_llama_model_v2_add_wiki_fix_resume

Adapters
2 models

Evaluation results