distilgpt2-alpaca-instruction-fine-tuning-qlora

santis2/distilgpt2-alpaca-instruction-fine-tuning-qlora

distilgpt2-alpaca-instruction-fine-tuning-qlora is a machine learning model from santis2. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

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

Downloads · 30 days

Access

Public

Updated Oct 3, 2023

Repo size

1.7 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.json2.9 MB · 77%

At a glance

License: apache-2.0
Access: Public
Created: Oct 1, 2023
Updated: Oct 3, 2023
SHA: 55e50b37

Base models

Model card

From the Hugging Face model README

distilgpt2-alpaca-instruction-fine-tuning-qlora

This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.2461

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
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 1000
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
2.9811	0.11	1000	2.4141
2.5312	0.22	2000	2.3164
2.4908	0.33	3000	2.2871
2.4785	0.44	4000	2.2754
2.4518	0.55	5000	2.2832
2.4277	0.66	6000	2.2578
2.4352	0.77	7000	2.25
2.4171	0.88	8000	2.2480
2.4138	0.99	9000	2.2461

Framework versions

Transformers 4.33.3
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3

License: apache-2.0
Created: Oct 1, 2023
Updated: Oct 3, 2023