vit-Mistral-SYDNEY-without-captioning

swadhindas324/vit-Mistral-SYDNEY-without-captioning

vit-Mistral-SYDNEY-without-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

1% of all-time downloads

All-time downloads

453

Public

Parameters

210M

4.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors839 MB · 100%

At a glance

Library: transformers
Model type: vision-encoder-decoder
Access: Public
Created: Jul 15, 2026
Updated: Jul 15, 2026
SHA: 211ae469

Model card

From the Hugging Face model README

vit-Mistral-SYDNEY-without-captioning

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

Loss: 0.8729
Accuracy: 67.55
Bleu-1: 0.7915
Bleu-2: 0.7175
Bleu-3: 0.6500
Bleu-4: 0.5860
Meteor: 0.7424
Rouge-l: 0.6988
Cider: 2.4552

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	1.2436	65.66	0.5411	0.4282	0.3470	0.2770	0.4560	0.4782	0.9812
No log	2.0	88	0.6975	66.27	0.6151	0.5148	0.4371	0.3711	0.5162	0.5474	1.3648
No log	3.0	132	0.6618	66.05	0.7409	0.6444	0.5553	0.4760	0.6457	0.6292	1.9662
No log	4.0	176	0.6667	67.42	0.8186	0.7346	0.6492	0.5703	0.7347	0.7342	2.4139
No log	5.0	220	0.6546	65.42	0.8	0.7228	0.6453	0.5648	0.7184	0.6730	2.2561
No log	6.0	264	0.6613	68.48	0.7940	0.7107	0.6257	0.5485	0.7275	0.7177	2.3071
No log	7.0	308	0.6814	68.83	0.8358	0.7714	0.7063	0.6465	0.7714	0.7465	2.7852
No log	8.0	352	0.6983	68.56	0.8024	0.7282	0.6613	0.6006	0.7547	0.7220	2.4693
No log	9.0	396	0.7446	68.02	0.8210	0.7478	0.6822	0.6238	0.7501	0.7133	2.7541
No log	10.0	440	0.7425	67.82	0.8207	0.7581	0.6967	0.6334	0.7681	0.7114	2.6941
No log	11.0	484	0.7773	67.74	0.7689	0.6920	0.6291	0.5693	0.7200	0.6818	2.4618
No log	12.0	528	0.8024	69.7	0.7858	0.7041	0.6277	0.5609	0.7264	0.7019	2.3112
No log	13.0	572	0.7955	67.89	0.8045	0.7226	0.6370	0.5559	0.7408	0.7130	2.3740
No log	14.0	616	0.8455	67.58	0.7949	0.7242	0.6505	0.5828	0.7783	0.7422	2.6241
No log	15.0	660	0.8653	68.11	0.8199	0.7558	0.6892	0.6235	0.7606	0.7317	2.4645
No log	16.0	704	0.8509	68.53	0.7956	0.7346	0.6800	0.6263	0.7615	0.7151	2.8530
No log	17.0	748	0.8729	67.55	0.7915	0.7175	0.6500	0.5860	0.7424	0.6988	2.4552

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: Jul 15, 2026
Updated: Jul 15, 2026