vit-resnet-mistral-SYDNEY-with-4-captioning

swadhindas324/vit-resnet-mistral-SYDNEY-with-4-captioning

vit-resnet-mistral-SYDNEY-with-4-captioning is a machine learning model from swadhindas324. 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 transformers.

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

Downloads · 30 days

2% of all-time downloads

All-time downloads

Public

Parameters

298M

4.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.2 GB · 100%

At a glance

Library: transformers
Model type: vision-encoder-decoder
Access: Public
Created: Jun 30, 2026
Updated: Jun 30, 2026
SHA: 9a51ad69

Model card

From the Hugging Face model README

vit-resnet-mistral-SYDNEY-with-4-captioning

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

Loss: 0.4667
Accuracy: 68.11
Bleu-1: 0.8259
Bleu-2: 0.7610
Bleu-3: 0.6988
Bleu-4: 0.6417
Meteor: 0.7792
Rouge-l: 0.7580
Cider: 2.7366

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: 64
eval_batch_size: 64
seed: 50
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 0.1
num_epochs: 128
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Bleu-1	Bleu-2	Bleu-3	Bleu-4	Meteor	Rouge-l	Cider
No log	1.0	44	0.9243	65.25	0.5333	0.4166	0.3342	0.2634	0.4432	0.4633	0.8705
No log	2.0	88	0.5274	61.65	0.5480	0.4380	0.3590	0.2933	0.4270	0.4606	0.7265
No log	3.0	132	0.4464	66.42	0.6572	0.5579	0.4760	0.4077	0.5689	0.5868	1.5454
No log	4.0	176	0.4236	66.82	0.8113	0.7230	0.6359	0.5462	0.7164	0.6845	2.4479
No log	5.0	220	0.4062	66.65	0.7911	0.7052	0.6201	0.5329	0.7081	0.6696	2.1740
No log	6.0	264	0.4101	68.42	0.8158	0.7251	0.6369	0.5508	0.7314	0.7233	2.3911
No log	7.0	308	0.4019	68.62	0.7936	0.7284	0.6614	0.5991	0.7572	0.7309	2.7046
No log	8.0	352	0.3925	66.91	0.8182	0.7618	0.7138	0.6699	0.7963	0.7617	2.9399
No log	9.0	396	0.4188	68.41	0.8079	0.7323	0.6642	0.6023	0.7511	0.7258	2.4982
No log	10.0	440	0.4323	66.84	0.7919	0.7131	0.6405	0.5703	0.7476	0.6983	2.5100
No log	11.0	484	0.4290	68.26	0.7851	0.7087	0.6426	0.5811	0.7534	0.7213	2.4317
No log	12.0	528	0.4305	69.23	0.7928	0.7197	0.6595	0.6071	0.7628	0.7342	2.6617
No log	13.0	572	0.4290	67.79	0.7755	0.7046	0.6374	0.5798	0.7066	0.6895	2.5779
No log	14.0	616	0.4456	67.5	0.8025	0.7287	0.6585	0.5928	0.7578	0.7274	2.6972
No log	15.0	660	0.4505	67.86	0.8162	0.7401	0.6770	0.6180	0.7648	0.7047	2.7424
No log	16.0	704	0.4554	68.03	0.8055	0.7346	0.6812	0.6330	0.7619	0.7189	2.5708
No log	17.0	748	0.4501	67.63	0.8165	0.7502	0.6944	0.6432	0.7743	0.7385	2.8210
No log	18.0	792	0.4667	68.11	0.8259	0.7610	0.6988	0.6417	0.7792	0.7580	2.7366

Framework versions

Transformers 5.12.1
Pytorch 2.12.1+cu130
Datasets 5.0.0
Tokenizers 0.22.2

Library: transformers
Type: vision-encoder-decoder
Created: Jun 30, 2026
Updated: Jun 30, 2026