zlucia's picture
End of training
f9e757f verified
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: mistralai/Mixtral-8x7B-v0.1
model-index:
  - name: Mixtral-8x7B-v0.1_case-briefs
    results: []

Mixtral-8x7B-v0.1_case-briefs

This model is a fine-tuned version of mistralai/Mixtral-8x7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0422

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: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 2.0

Training results

Training Loss Epoch Step Validation Loss
0.9925 0.34 50 1.0546
0.9873 0.68 100 1.0322
0.9577 1.02 150 1.0260
0.8504 1.36 200 1.0648
0.9154 1.7 250 1.0422

Framework versions

  • PEFT 0.7.1
  • Transformers 4.37.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1