mistral_instruct_generation2

This model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1836

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: 2e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 6

Training results

Training Loss Epoch Step Validation Loss
0.1924 1.0 373 0.2022
0.182 2.0 746 0.1896
0.1792 3.0 1119 0.1864
0.177 4.0 1492 0.1850
0.174 5.0 1865 0.1842
0.1723 6.0 2238 0.1836

Framework versions

  • PEFT 0.11.1
  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
0
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Model tree for bif02/mistral_instruct_generation2

Adapter
(119)
this model