Hugging Face's logo

mnlp-nsoai
/
mistral7b-sft-on-mmlu-pro

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
mistral7b-sft-on-mmlu-pro / README.md
alexmsrh's picture
alexmsrh
mnlp-nsoai/mistral7b-sft-on-mmlu-pro
fcae8b5 verified
preview code
|
raw
history blame contribute delete
No virus
1.96 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
  - name: sft-mmlu-mistral7B
    results: []

Visualize in Weights & Biases

sft-mmlu-mistral7B

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5664

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: cosine
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 1.0

Training results

Training Loss Epoch Step Validation Loss
0.5914 0.1450 100 0.6232
0.5203 0.2901 200 0.5968
0.6183 0.4351 300 0.5859
0.559 0.5801 400 0.5763
0.567 0.7252 500 0.5690
0.5787 0.8702 600 0.5664

Framework versions

  • PEFT 0.11.1
  • Transformers 4.41.0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1