Qwen2-VL-Redundancy

sxj1215/Qwen2-VL-Redundancy

Qwen2-VL-Redundancy is a machine learning model from sxj1215. 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

12% of all-time downloads

All-time downloads

Public

Repo size

92.2 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors80.8 MB · 82%

At a glance

Library: peft
License: other
Access: Public
Created: May 25, 2025
Updated: May 25, 2025
SHA: ab34df3e

Base models

Qwen/Qwen2-VL-7B-Instruct

Model card

From the Hugging Face model README

sft_redundancy_new

This model is a fine-tuned version of Qwen/Qwen2-VL-7B-Instruct on the resisc45, the ucmerced, the fer2013, the scienceqa, the mmimdb and the screen2words datasets. It achieves the following results on the evaluation set:

Loss: 0.5808

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: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.8948	0.0481	500	0.6562
0.6832	0.0961	1000	0.6148
0.5927	0.1442	1500	0.5914
0.6813	0.1923	2000	0.5738
0.4088	0.2403	2500	0.5824
0.6205	0.2884	3000	0.5768
0.7229	0.3364	3500	0.5607
0.6292	0.3845	4000	0.5635
0.6033	0.4326	4500	0.5492
0.4986	0.4806	5000	0.5470
0.623	0.5287	5500	0.5453
0.6596	0.5768	6000	0.5430
0.6779	0.6248	6500	0.5386
0.6796	0.6729	7000	0.5345
0.5758	0.7209	7500	0.5397
0.5142	0.7690	8000	0.5340
0.5752	0.8171	8500	0.5318
0.4997	0.8651	9000	0.5289
0.6262	0.9132	9500	0.5303
0.6193	0.9613	10000	0.5334
0.7338	1.0093	10500	0.5258
0.6178	1.0574	11000	0.5341
0.5629	1.1055	11500	0.5253
0.6407	1.1535	12000	0.5292
0.5549	1.2016	12500	0.5284
0.4914	1.2496	13000	0.5231
0.4535	1.2977	13500	0.5242
0.5162	1.3458	14000	0.5224
0.4466	1.3938	14500	0.5275
0.5427	1.4419	15000	0.5243
0.4722	1.4900	15500	0.5145
0.6199	1.5380	16000	0.5200
0.4566	1.5861	16500	0.5288
0.5564	1.6341	17000	0.5169
0.5187	1.6822	17500	0.5143
0.5339	1.7303	18000	0.5104
0.5703	1.7783	18500	0.5110
0.5368	1.8264	19000	0.5142
0.6051	1.8745	19500	0.5110
0.4187	1.9225	20000	0.5140
0.5876	1.9706	20500	0.5118
0.2579	2.0186	21000	0.5429
0.3344	2.0667	21500	0.5561
0.2026	2.1148	22000	0.5703
0.3255	2.1628	22500	0.5742
0.3463	2.2109	23000	0.5739
0.3232	2.2590	23500	0.5824
0.2879	2.3070	24000	0.5799
0.3236	2.3551	24500	0.5742
0.3262	2.4032	25000	0.5799
0.3792	2.4512	25500	0.5767
0.3268	2.4993	26000	0.5762
0.2743	2.5473	26500	0.5775
0.3534	2.5954	27000	0.5800
0.2689	2.6435	27500	0.5803
0.3619	2.6915	28000	0.5801
0.3634	2.7396	28500	0.5803
0.3301	2.7877	29000	0.5804
0.3127	2.8357	29500	0.5821
0.3687	2.8838	30000	0.5810
0.2652	2.9318	30500	0.5806
0.4041	2.9799	31000	0.5809

Framework versions

PEFT 0.12.0
Transformers 4.45.2
Pytorch 2.1.2+cu121
Datasets 3.1.0
Tokenizers 0.20.3

Library: peft
License: other
Created: May 25, 2025
Updated: May 25, 2025