Na_L3_100steps_1e6rate_SFT

tsavage68/Na_L3_100steps_1e6rate_SFT

Na_L3_100steps_1e6rate_SFT is a text generation model from tsavage68. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.

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

Downloads · 30 days

3% of all-time downloads

All-time downloads

208

Public

Parameters

16.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors32.1 GB · 100%

At a glance

Task: Text Generation
Library: transformers
License: llama3
Model type: llama
Access: Public
Created: Sep 3, 2024
Updated: Sep 3, 2024
SHA: a43d88f7

Try a prompt

Base models

meta-llama/Meta-Llama-3-8B-Instruct

Model card

From the Hugging Face model README

Na_L3_100steps_1e6rate_SFT

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2960

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: 1e-06
train_batch_size: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
0.8942	0.2667	50	0.6239
0.3097	0.5333	100	0.2960

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Task: Text Generation
Library: transformers
Type: llama
License: llama3
Created: Sep 3, 2024
Updated: Sep 3, 2024