metadata

license: apache-2.0
base_model: Deci/DeciLM-7B
datasets:
  - HuggingFaceH4/ultrachat_200k
tags:
  - generated_from_trainer
model-index:
  - name: bbdeci7b-sft-lora
    results: []

bbdeci7b-sft-lora

This model is a fine-tuned version of Deci/DeciLM-7B on HuggingFaceH4/ultrachat_200k It achieves the following results on the evaluation set:

Loss: 1.0110

Model description

more information to come soon

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 128
total_train_batch_size: 1024
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.0062	1.00	136	1.0110

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1