sft_5000_p

This model is a fine-tuned version of mistralai/Mistral-Nemo-Instruct-2407 on the heat_transfer_5000_p dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0024

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: 12
  • eval_batch_size: 12
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • total_train_batch_size: 24
  • total_eval_batch_size: 24
  • 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: cosine
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.0073 0.1064 20 0.0036
0.0029 0.2128 40 0.0030
0.0028 0.3191 60 0.0028
0.0028 0.4255 80 0.0027
0.0027 0.5319 100 0.0026
0.0027 0.6383 120 0.0026
0.0026 0.7447 140 0.0026
0.0025 0.8511 160 0.0025
0.0025 0.9574 180 0.0025

Framework versions

  • PEFT 0.12.0
  • Transformers 4.46.0
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.20.1
Downloads last month
5
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for Howard881010/heat_transfer_sft_5000_p