fine-tune-radia-v5

joedonino/fine-tune-radia-v5

fine-tune-radia-v5 is a machine learning model from joedonino. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

Access

Public

Updated Nov 16, 2023

Repo size

34.1 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors33.6 MB · 93%

At a glance

Access: Public
Created: Nov 16, 2023
Updated: Nov 16, 2023
SHA: 0c7cf25e

Base models

meta-llama/Llama-2-7b-hf

Model card

From the Hugging Face model README

fine-tune-radia-v5

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.5763

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: 0.0005
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: constant
lr_scheduler_warmup_ratio: 0.03
training_steps: 50

Training results

Training Loss	Epoch	Step	Validation Loss
0.9282	0.09	5	0.8199
0.7119	0.17	10	0.7063
0.673	0.26	15	0.6752
0.6667	0.34	20	0.6584
0.6191	0.43	25	0.6408
0.6094	0.52	30	0.6226
0.5648	0.6	35	0.6080
0.5579	0.69	40	0.5964
0.5439	0.78	45	0.5867
0.5478	0.86	50	0.5763

Framework versions

Transformers 4.36.0.dev0
Pytorch 2.1.0+cu118
Datasets 2.14.7
Tokenizers 0.15.0

Created: Nov 16, 2023
Updated: Nov 16, 2023