BEE-spoke-data

smol_llama-101M-midjourney-messages

README

License: apache-2.0

Model description

This model is a fine-tuned version of BEE-spoke-data/smol_llama-101M-GQA on the pszemraj/midjourney-messages-cleaned dataset. It achieves the following results on the evaluation set:

Loss: 2.8431
Accuracy: 0.4682

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.00025
train_batch_size: 4
eval_batch_size: 4
seed: 17056
gradient_accumulation_steps: 16
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
lr_scheduler_type: inverse_sqrt
lr_scheduler_warmup_ratio: 0.05
num_epochs: 1.0

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

BEE-spoke-data

Model Tree

Base

BEE-spoke-data/smol_llama-101M-GQA

Fine-tuned

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer