Hugging Face's logo

Karun-7
/
Karun-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
Karun-ft / README.md
Karun-7's picture
Karun-7
Karun-7/DS
5f21c43 verified
preview code
|
raw
history blame contribute delete
1.85 kB
metadata
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
library_name: peft
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: Karun-ft
    results: []

Karun-ft

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

  • Loss: 1.8332

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: 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: linear
  • lr_scheduler_warmup_steps: 2
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.7969 0.8 1 2.2171
2.8361 1.6 2 2.1821
2.727 2.4 3 2.1073
1.3161 4.0 5 1.9785
2.5451 4.8 6 1.9301
2.4933 5.6 7 1.8925
2.4237 6.4 8 1.8635
1.1945 8.0 10 1.8332

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.1
  • Pytorch 2.3.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1