Skip to content
ModelVerifiedExternal
Download

Vit Resnet Mistral SYDNEY With All Captioning

This model is a fine-tuned version of []( on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.5411 Accuracy: 69.9 Bleu-1: 0.8300 Bleu-2: 0.7620 Bleu-3: 0.6937 Bleu-4: 0.6263...

Sourcehuggingface.co/swadhindas324/vit-resnet-mistral-SYDNEY-with-all-captioning/tree/4b85f936f2d8f868237a679ce1dc9b526a2050f1
KindCLIP visionVersionmodelPublisher@swadhindas324Cgrade

Model source

Kind
CLIP vision
File size
1.11 GB
Version
vmodel
Updated
Oct 5, 2026
Publisher
@swadhindas324
Downloads
5
Source
Hugging Face

Source description

vit-resnet-mistral-SYDNEY-with-all-captioning

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

  • Loss: 0.5411
  • Accuracy: 69.9
  • Bleu-1: 0.8300
  • Bleu-2: 0.7620
  • Bleu-3: 0.6937
  • Bleu-4: 0.6263
  • Meteor: 0.7810
  • Rouge-l: 0.7509
  • Cider: 2.6447

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 LossEpochStepValidation LossAccuracyBleu-1Bleu-2Bleu-3Bleu-4MeteorRouge-lCider
No log1.0440.921665.160.51770.39730.31720.24910.42430.44480.8130
No log2.0880.532660.670.54800.43800.35900.29330.42700.46060.7265
No log3.01320.454666.450.66710.56780.48120.41000.58530.59871.5583
No log4.01760.433667.280.79620.69810.59620.49380.69240.66472.1904
No log5.02200.418866.940.78780.70100.61490.52790.69610.65742.1957
No log6.02640.414467.860.79660.70730.62560.55510.71150.70462.2405
No log7.03080.415868.520.80880.73860.67370.61190.75770.73772.6949
No log8.03520.407166.370.83440.77310.71730.66360.76520.73302.8783
No log9.03960.422068.170.81190.73360.65830.58910.74800.72172.5704
No log10.04400.431267.910.82650.75820.69490.63420.77040.73772.6809
No log11.04840.422267.840.80880.73160.66300.60210.75040.70232.5702
No log12.05280.449068.890.76660.67430.59510.52490.70540.68012.1787
No log13.05720.456966.220.82260.75000.68370.61510.75360.70502.4849
No log14.06160.477967.710.80360.71700.63500.55550.73380.71702.4574
No log15.06600.468769.290.79400.71290.64500.58390.75810.72032.3877
No log16.07040.475669.240.80290.73650.67450.61240.75680.72582.5659
No log17.07480.483168.540.79530.71380.64470.58340.75120.71872.5023
No log18.07920.479769.40.83620.77130.70990.65460.78290.76942.8833
No log19.08360.508168.10.79380.70880.64420.58800.73900.70022.5298
No log20.08800.506169.230.81010.73850.67360.61460.77330.75452.6758
No log21.09240.499167.620.79250.72050.66060.60270.73770.68562.3866
No log22.09680.508868.650.78680.70320.63690.57570.75500.72962.5237
No log23.010120.555767.610.78050.69710.62550.55870.72810.69932.3368
0.276424.010560.511168.140.81030.74080.67420.61350.78950.76312.6267
0.276425.011000.534568.610.77730.70140.63910.58150.75710.72172.4595
0.276426.011440.548368.490.81280.73090.65750.59210.74930.73412.5915
0.276427.011880.550168.180.75160.64820.56560.48880.72160.67272.2985
0.276428.012320.541169.90.83000.76200.69370.62630.78100.75092.6447

Framework versions

  • Transformers 5.12.1
  • Pytorch 2.12.1+cu130
  • Datasets 5.0.0
  • Tokenizers 0.22.2

Sources

1 source
Hugging FacePrimaryVersion 4b85f936f2d8f868237a679ce1dc9b526a2050f1
huggingface.co/swadhindas324/vit-resnet-mistral-SYDNEY-with-all-captioning/tree/4b85f936f2d8f868237a679ce1dc9b526a2050f1

Verified Aug 30

Model artifacts

1 artifact

model.safetensors

safetensors · 1.11 GB · SHA-256 2aaca372c478…1242 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeJul 11huggingface.co/swadhindas324/vit-resnet-mistral-SYDNEY-with-all-captioning

--- library_name: transformers tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-resnet-mistral-SYDNEY-with-all-captioning results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-resnet-mistral-SYDNEY-with-all-captioning This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.5411 - Accuracy: 69.9 - Bleu-1: 0.8300 - Bleu-2: 0.7620 - Bleu-3: 0.6937 - Bleu-4: 0.6263 - Meteor: 0.7810 - Rouge-l: 0.7509 - Cider: 2.6447 ## 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 | 0.9216 | 65.16 | 0.5177 | 0.3973 | 0.3172 | 0.2491 | 0.4243 | 0.4448 | 0.8130 | | No log | 2.0 | 88 | 0.5326 | 60.67 | 0.5480 | 0.4380 | 0.3590 | 0.2933 | 0.4270 | 0.4606 | 0.7265 | | No log | 3.0 | 132 | 0.4546 | 66.45 | 0.6671 | 0.5678 | 0.4812 | 0.4100 | 0.5853 | 0.5987 | 1.5583 | | No log | 4.0 | 176 | 0.4336 | 67.28 | 0.7962 | 0.6981 | 0.5962 | 0.4938 | 0.6924 | 0.6647 | 2.1904 | | No log | 5.0 | 220 | 0.4188 | 66.94 | 0.7878 | 0.7010 | 0.6149 | 0.5279 | 0.6961 | 0.6574 | 2.1957 | | No log | 6.0 | 264 | 0.4144 | 67.86 | 0.7966 | 0.7073 | 0.6256 | 0.5551 | 0.7115 | 0.7046 | 2.2405 | | No log | 7.0 | 308 | 0.4158 | 68.52 | 0.8088 | 0.7386 | 0.6737 | 0.6119 | 0.7577 | 0.7377 | 2.6949 | | No log | 8.0 | 352 | 0.4071 | 66.37 | 0.8344 | 0.7731 | 0.7173 | 0.6636 | 0.7652 | 0.7...

NoteAug 30huggingface.co/swadhindas324/vit-resnet-mistral-SYDNEY-with-all-captioning

Source context: 5 downloads · 0 likes · Library transformers · Repo swadhindas324/vit-resnet-mistral-SYDNEY-with-all-captioning

NoteJul 11huggingface.co/swadhindas324/vit-resnet-mistral-SYDNEY-with-all-captioning

Source context: 1197 downloads · 0 likes · Library transformers · Repo swadhindas324/vit-resnet-mistral-SYDNEY-with-all-captioning