CodeLlama-7B-Instruct-AWQ-FaVe-rank8-10epochs

Ferdi/CodeLlama-7B-Instruct-AWQ-FaVe-rank8-10epochs

CodeLlama-7B-Instruct-AWQ-FaVe-rank8-10epochs is a machine learning model from Ferdi. 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 llama2.

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

Downloads · 30 days

29% of all-time downloads

All-time downloads

Public

Repo size

16.8 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors16.8 MB · 90%

At a glance

Library: peft
License: llama2
Access: Public
Created: Jun 25, 2024
Updated: Jun 25, 2024
SHA: 51ed7e63

Base models

TheBloke/CodeLlama-7B-Instruct-AWQ

Model card

From the Hugging Face model README

CodeLlama-7B-Instruct-AWQ-FaVe-rank8-10epochs

This model is a fine-tuned version of TheBloke/CodeLlama-7B-Instruct-AWQ on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4895

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: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 10
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.2685	10	2.3646
2.4179	0.5369	20	2.1518
2.4179	0.8054	30	1.7627
1.8436	1.0738	40	1.4048
1.8436	1.3423	50	1.0944
1.1066	1.6107	60	0.9634
1.1066	1.8792	70	0.8695
0.7716	2.1477	80	0.7980
0.7716	2.4161	90	0.7575
0.6585	2.6846	100	0.7293
0.6585	2.9530	110	0.6901
0.6067	3.2215	120	0.6729
0.6067	3.4899	130	0.6452
0.5672	3.7584	140	0.6255
0.5672	4.0268	150	0.6129
0.5196	4.2953	160	0.5954
0.5196	4.5638	170	0.5747
0.4492	4.8322	180	0.5668
0.4492	5.1007	190	0.5590
0.4539	5.3691	200	0.5435
0.4539	5.6376	210	0.5397
0.3938	5.9060	220	0.5359
0.3938	6.1745	230	0.5188
0.3748	6.4430	240	0.5247
0.3748	6.7114	250	0.5190
0.3759	6.9799	260	0.5069
0.3759	7.2483	270	0.4995
0.3308	7.5168	280	0.5114
0.3308	7.7852	290	0.5004
0.3259	8.0537	300	0.4937
0.3259	8.3221	310	0.4990
0.3023	8.5906	320	0.4964
0.3023	8.8591	330	0.4904
0.3036	9.1275	340	0.4898
0.3036	9.3960	350	0.4914
0.3118	9.6644	360	0.4897
0.3118	9.9329	370	0.4895

Framework versions

PEFT 0.10.0
Transformers 4.40.2
Pytorch 2.2.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Library: peft
License: llama2
Created: Jun 25, 2024
Updated: Jun 25, 2024