llama-lora-adapter-eniad

ahmed-ouka/llama-lora-adapter-eniad

llama-lora-adapter-eniad is a machine learning model from ahmed-ouka. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as llama3.1.

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

Downloads · 30 days

12% of all-time downloads

All-time downloads

Public

Repo size

2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt218 MB · 46%

At a glance

Library: peft
License: llama3.1
Access: Public
Created: May 10, 2025
Updated: May 10, 2025
SHA: b4df7e5a

Base models

Model card

From the Hugging Face model README

model-llama

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the eniad-Assistant_finetune_train dataset. It achieves the following results on the evaluation set:

Loss: 0.2621

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: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.5884	0.1	100	0.6809
0.5385	0.2	200	0.5491
0.4435	0.3	300	0.4859
0.3749	0.4	400	0.4397
0.3712	0.5	500	0.3946
0.3056	0.6	600	0.3912
0.3171	0.7	700	0.3637
0.2992	0.8	800	0.3464
0.305	0.9	900	0.3401
0.2774	1.0	1000	0.3249
0.2301	1.1	1100	0.3280
0.2455	1.2	1200	0.3051
0.2183	1.3	1300	0.3002
0.2253	1.4	1400	0.2956
0.2268	1.5	1500	0.2908
0.2338	1.6	1600	0.2866
0.2097	1.7	1700	0.2859
0.1968	1.8	1800	0.2769
0.1881	1.9	1900	0.2813
0.1913	2.0	2000	0.2706
0.1545	2.1	2100	0.2710
0.1476	2.2	2200	0.2715
0.1453	2.3	2300	0.2677
0.1555	2.4	2400	0.2641
0.1389	2.5	2500	0.2657
0.1381	2.6	2600	0.2627
0.1424	2.7	2700	0.2628
0.1545	2.8	2800	0.2615
0.1314	2.9	2900	0.2622
0.1595	3.0	3000	0.2621

Framework versions

PEFT 0.15.1
Transformers 4.48.3
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.21.1

Library: peft
License: llama3.1
Created: May 10, 2025
Updated: May 10, 2025