Hugging Face's logo

Mihir1108
/
DeciLM

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
DeciLM / README.md
Mihir1108's picture
Mihir1108
End of training
006c89d verified
preview code
|
raw
history blame contribute delete
1.14 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: Deci/DeciLM-7B-instruct
model-index:
  - name: DeciLM
    results: []

DeciLM

This model is a fine-tuned version of Deci/DeciLM-7B-instruct on the None dataset.

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: 1
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.7.1
  • Transformers 4.37.1
  • Pytorch 2.1.0+cu118
  • Datasets 2.16.1
  • Tokenizers 0.15.1