Edit model card

mistral_instruct_generation

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3407

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: 0.0002
  • 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: 0.03
  • training_steps: 100

Training results

Training Loss Epoch Step Validation Loss
1.561 0.16 20 1.4006
1.4313 0.33 40 1.3646
1.446 0.49 60 1.3534
1.438 0.65 80 1.3453
1.4122 0.81 100 1.3407

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.2+cu121
  • Datasets 2.14.7
  • Tokenizers 0.14.1
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .

Model tree for yuansiwe/mistral_instruct_generation

Finetuned
(139)
this model