Saltar al contenido
ModelVerificadoExterno
Descargar

Vit Convnext 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: 0.8367 Accuracy: 67.63 Bleu-1: 0.7928 Bleu-2: 0.7220 Bleu-3: 0.6579 Bleu-4: 0.6002...

Fuentehuggingface.co/swadhindas324/vit-convnext-Mistral-SYDNEY-without-captioning/tree/a843c30a9c57bd7fe85e8ef5aff1d5d9bad6a1a1
TipoCLIP visionVersiónmodelPublicador@swadhindas324Ccalidad

Fuente del modelo

Tipo
CLIP vision
Tamaño del archivo
1,62 GB
Versión
vmodel
Actualizado
4 oct 2026
Publicador
@swadhindas324
Descargas
10
Tareas
Descripción
Fuente
Hugging Face

Descripción de la fuente

vit-convnext-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: 0.8367
  • Accuracy: 67.63
  • Bleu-1: 0.7928
  • Bleu-2: 0.7220
  • Bleu-3: 0.6579
  • Bleu-4: 0.6002
  • Meteor: 0.7417
  • Rouge-l: 0.7053
  • Cider: 2.3978

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 log1.0441.237665.660.54310.42840.34650.27600.45750.47860.9774
No log2.0880.697466.270.61510.51480.43710.37110.51620.54741.3648
No log3.01320.661466.30.74380.65030.55950.47730.65120.63271.9478
No log4.01760.672167.750.81240.72120.63430.55520.72690.72232.3770
No log5.02200.652166.130.79900.72350.64580.56900.72830.69242.2489
No log6.02640.663968.090.78660.70200.61970.54390.71800.71142.2763
No log7.03080.689368.150.82730.76580.70410.64540.77460.75262.9048
No log8.03520.689468.740.82860.75750.69000.62430.78340.74002.6251
No log9.03960.734367.580.82530.74070.65640.58290.74930.72582.5931
No log10.04400.788367.220.79130.70410.62840.56250.72760.70122.5651
No log11.04840.755466.740.76930.69050.61870.55210.72310.67362.4674
No log12.05280.786268.920.79010.71070.64250.58140.72740.71462.5855
No log13.05720.800268.020.80160.72560.65490.59220.74560.72832.5073
No log14.06160.796268.650.81160.74310.67540.61530.75470.73852.8192
No log15.06600.863467.960.78660.70260.62580.55490.73200.69362.5139
No log16.07040.835768.350.79450.72240.66310.61190.77870.74212.7519
No log17.07480.836767.630.79280.72200.65790.60020.74170.70532.3978

Framework versions

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

Fuentes

1 fuente
Hugging FacePrincipalVersión a843c30a9c57bd7fe85e8ef5aff1d5d9bad6a1a1
huggingface.co/swadhindas324/vit-convnext-Mistral-SYDNEY-without-captioning/tree/a843c30a9c57bd7fe85e8ef5aff1d5d9bad6a1a1

Verificado 4 oct

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 1,62 GB · SHA-256 9a0b30480cad…2b3c · Hugging Face

Descargar

Extractos de fuentes

3 extractos
Readme11 julhuggingface.co/swadhindas324/vit-convnext-Mistral-SYDNEY-without-captioning

--- library_name: transformers tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-convnext-Mistral-SYDNEY-without-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-convnext-Mistral-SYDNEY-without-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: 0.8367 - Accuracy: 67.63 - Bleu-1: 0.7928 - Bleu-2: 0.7220 - Bleu-3: 0.6579 - Bleu-4: 0.6002 - Meteor: 0.7417 - Rouge-l: 0.7053 - Cider: 2.3978 ## 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 | 1.2376 | 65.66 | 0.5431 | 0.4284 | 0.3465 | 0.2760 | 0.4575 | 0.4786 | 0.9774 | | No log | 2.0 | 88 | 0.6974 | 66.27 | 0.6151 | 0.5148 | 0.4371 | 0.3711 | 0.5162 | 0.5474 | 1.3648 | | No log | 3.0 | 132 | 0.6614 | 66.3 | 0.7438 | 0.6503 | 0.5595 | 0.4773 | 0.6512 | 0.6327 | 1.9478 | | No log | 4.0 | 176 | 0.6721 | 67.75 | 0.8124 | 0.7212 | 0.6343 | 0.5552 | 0.7269 | 0.7223 | 2.3770 | | No log | 5.0 | 220 | 0.6521 | 66.13 | 0.7990 | 0.7235 | 0.6458 | 0.5690 | 0.7283 | 0.6924 | 2.2489 | | No log | 6.0 | 264 | 0.6639 | 68.09 | 0.7866 | 0.7020 | 0.6197 | 0.5439 | 0.7180 | 0.7114 | 2.2763 | | No log | 7.0 | 308 | 0.6893 | 68.15 | 0.8273 | 0.7658 | 0.7041 | 0.6454 | 0.7746 | 0.7526 | 2.9048 | | No log | 8.0 | 352 | 0.6894 | 68.74 | 0.8286 | 0.7575 | 0.6900 | 0.6243 | 0.7834 | 0...

Note4 octhuggingface.co/swadhindas324/vit-convnext-Mistral-SYDNEY-without-captioning

Source context: 10 downloads · 0 likes · Library transformers · Repo swadhindas324/vit-convnext-Mistral-SYDNEY-without-captioning

Note18 julhuggingface.co/swadhindas324/vit-convnext-Mistral-SYDNEY-without-captioning

Source context: 716 downloads · 0 likes · Library transformers · Repo swadhindas324/vit-convnext-Mistral-SYDNEY-without-captioning