Zum Inhalt springen
ModelÜberprüftExtern
Herunterladen

Vit Resnet Mistral UCM With 7 Captioning

This model is a fine-tuned version of []( on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.4441 Accuracy: 75.27 Bleu-1: 0.8363 Bleu-2: 0.7755 Bleu-3: 0.7257 Bleu-4: 0.6775...

Quellehuggingface.co/swadhindas324/vit-resnet-mistral-UCM-with-7-captioning/tree/b0e774adc71afdf1754b648a6e88c00447df3590
ArtCLIP visionVersionmodelVerleger@swadhindas324CBewertung

Modellquelle

Art
CLIP vision
Dateigröße
1,11 GB
Version
vmodel
Aktualisiert
21. Okt. 2026
Verleger
@swadhindas324
Downloads
2
Quelle
Hugging Face

Quellenbeschreibung

vit-resnet-mistral-UCM-with-7-captioning

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

  • Loss: 0.4441
  • Accuracy: 75.27
  • Bleu-1: 0.8363
  • Bleu-2: 0.7755
  • Bleu-3: 0.7257
  • Bleu-4: 0.6775
  • Meteor: 0.8123
  • Rouge-l: 0.8096
  • Cider: 3.4695

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 log1.01480.653672.420.41050.27850.20200.14940.31130.34590.3319
No log2.02960.469772.060.29550.20540.13550.08990.22160.24460.3533
No log3.04440.413870.640.63600.55420.49870.45880.59690.60602.0977
No log4.05920.357073.610.81940.74960.69340.64340.77810.76753.1170
No log5.07400.348073.930.83190.77830.73340.69360.80760.80543.3582
No log6.08880.349873.560.83170.77860.73110.68700.81910.81003.2555
0.45097.010360.342074.670.85850.80240.75250.70510.84200.82063.4377
0.45098.011840.347774.310.84430.78790.73950.69510.81250.80373.3959
0.45099.013320.356474.630.85610.80570.76140.72110.82490.81913.5346
0.450910.014800.358174.490.85470.80230.75570.71410.82760.81973.4898
0.450911.016280.362773.540.82900.75930.69980.64280.83230.80193.2609
0.450912.017760.363273.980.83990.77720.72250.67210.81280.80433.2854
0.450913.019240.391573.710.82730.76550.71380.66830.79490.78563.3208
0.164814.020720.385575.050.85630.80390.75560.70940.83550.81793.3844
0.164815.022200.376174.950.86250.80910.76330.71950.83170.82153.6767
0.164816.023680.389375.30.85450.79730.74980.70530.82270.81343.4774
0.164817.025160.393274.590.85890.80520.75960.71670.84540.83003.5445
0.164818.026640.398274.150.84550.78900.74380.70210.82430.81193.4521
0.164819.028120.396874.610.85700.79980.75370.71080.83730.82043.5498
0.164820.029600.420774.590.83240.77160.72280.68070.81060.79823.3747
0.139521.031080.424073.630.84820.79430.74850.70550.83190.81983.4832
0.139522.032560.429474.560.83440.77540.72700.68250.81620.79663.4112
0.139523.034040.433074.230.85530.79970.75260.70770.82970.81363.4253
0.139524.035520.425674.430.83230.77810.73300.69030.81420.80453.3820
0.139525.037000.432374.190.84380.78900.73970.69310.83390.80933.3894
0.139526.038480.442074.660.86260.80580.75640.71250.83670.82433.5029
0.139527.039960.444175.270.83630.77550.72570.67750.81230.80963.4695

Framework versions

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

Quellen

1 Quelle
Hugging FacePrimärVersion b0e774adc71afdf1754b648a6e88c00447df3590
huggingface.co/swadhindas324/vit-resnet-mistral-UCM-with-7-captioning/tree/b0e774adc71afdf1754b648a6e88c00447df3590

Verifiziert 21. Okt.

Modellartefakte

1 Artefakt

model.safetensors

safetensors · 1,11 GB · SHA-256 841f2d35415b…8e0a · Hugging Face

Herunterladen

Quellenauszüge

3 Auszüge
Readme11. Julihuggingface.co/swadhindas324/vit-resnet-mistral-UCM-with-7-captioning

--- library_name: transformers tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-resnet-mistral-UCM-with-7-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-UCM-with-7-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: 0.4441 - Accuracy: 75.27 - Bleu-1: 0.8363 - Bleu-2: 0.7755 - Bleu-3: 0.7257 - Bleu-4: 0.6775 - Meteor: 0.8123 - Rouge-l: 0.8096 - Cider: 3.4695 ## 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 | 148 | 0.6536 | 72.42 | 0.4105 | 0.2785 | 0.2020 | 0.1494 | 0.3113 | 0.3459 | 0.3319 | | No log | 2.0 | 296 | 0.4697 | 72.06 | 0.2955 | 0.2054 | 0.1355 | 0.0899 | 0.2216 | 0.2446 | 0.3533 | | No log | 3.0 | 444 | 0.4138 | 70.64 | 0.6360 | 0.5542 | 0.4987 | 0.4588 | 0.5969 | 0.6060 | 2.0977 | | No log | 4.0 | 592 | 0.3570 | 73.61 | 0.8194 | 0.7496 | 0.6934 | 0.6434 | 0.7781 | 0.7675 | 3.1170 | | No log | 5.0 | 740 | 0.3480 | 73.93 | 0.8319 | 0.7783 | 0.7334 | 0.6936 | 0.8076 | 0.8054 | 3.3582 | | No log | 6.0 | 888 | 0.3498 | 73.56 | 0.8317 | 0.7786 | 0.7311 | 0.6870 | 0.8191 | 0.8100 | 3.2555 | | 0.4509 | 7.0 | 1036 | 0.3420 | 74.67 | 0.8585 | 0.8024 | 0.7525 | 0.7051 | 0.8420 | 0.8206 | 3.4377 | | 0.4509 | 8.0 | 1184 | 0.3477 | 74.31 | 0.8443 | 0.7879 | 0.7395 | 0.6951 | 0.8125 | 0.8037 |...

Note21. Okt.huggingface.co/swadhindas324/vit-resnet-mistral-UCM-with-7-captioning

Source context: 2 downloads · 0 likes · Library transformers · Repo swadhindas324/vit-resnet-mistral-UCM-with-7-captioning

Note5. Aug.huggingface.co/swadhindas324/vit-resnet-mistral-UCM-with-7-captioning

Source context: 10 downloads · 0 likes · Library transformers · Repo swadhindas324/vit-resnet-mistral-UCM-with-7-captioning