peft-deepseek-code-lora-7b

liyingjian/peft-deepseek-code-lora-7b

peft-deepseek-code-lora-7b is a machine learning model from liyingjian. 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 other.

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

Downloads · 30 days

11% of all-time downloads

All-time downloads

187

Public

Repo size

3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors80 MB · 100%

At a glance

Library: peft
License: other
Access: Public
Created: Jun 3, 2024
Updated: Jun 4, 2024
SHA: 69691cd4

Base models

deepseek-ai/deepseek-coder-6.7b-base

Model card

From the Hugging Face model README

peft-deepseek-code-lora-7b

This model is a fine-tuned version of deepseek-ai/deepseek-coder-6.7b-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.7491

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 45
training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss
0.801	0.025	100	0.7577
0.7385	0.05	200	0.7172
0.7535	0.075	300	0.6915
0.6987	0.1	400	0.6718
0.6345	0.125	500	0.6596
0.623	0.15	600	0.6515
0.6228	0.175	700	0.6413
0.5966	0.2	800	0.6362
0.5503	0.225	900	0.6403
0.504	0.25	1000	0.6274
0.4782	0.275	1100	0.6270
0.5021	0.3	1200	0.6272
0.4737	0.325	1300	0.6190
0.4343	0.35	1400	0.6233
0.458	0.375	1500	0.6247
0.4316	0.4	1600	0.6302
0.4161	0.425	1700	0.6337
0.3798	0.45	1800	0.6307
0.3731	0.475	1900	0.6382
0.3339	0.5	2000	0.6468
0.3279	0.525	2100	0.6529
0.3042	0.55	2200	0.6484
0.2738	0.575	2300	0.6612
0.3121	0.6	2400	0.6684
0.2735	0.625	2500	0.6795
0.2595	0.65	2600	0.6802
0.2291	0.675	2700	0.6856
0.2239	0.7	2800	0.6964
0.2242	0.725	2900	0.7081
0.2357	0.75	3000	0.7200
0.2058	0.775	3100	0.7166
0.1881	0.8	3200	0.7303
0.1859	0.825	3300	0.7299
0.193	0.85	3400	0.7375
0.2061	0.875	3500	0.7392
0.1719	0.9	3600	0.7461
0.1908	0.925	3700	0.7464
0.1756	0.95	3800	0.7480
0.1863	0.975	3900	0.7489
0.1619	1.0	4000	0.7491

Framework versions

PEFT 0.11.1
Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.14.6
Tokenizers 0.19.1

Library: peft
License: other
Created: Jun 3, 2024
Updated: Jun 4, 2024