Vit Resnet Mistral RSICD With 3 Captioning | Sweet Tea Studio
Resources / Vit Resnet Mistral RSICD With 3 Captioning Vit Resnet Mistral RSICD With 3 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: 0.8332 Accuracy: 81.61 Bleu-1: 0.6172 Bleu-2: 0.4856 Bleu-3: 0.3941 Bleu-4: 0.3277 Meteor: 0.5872 Rouge-l: 0.5473 Cider: 1.7764 Model description
Verified source
Kind Other Version v6081f110ed76f3ae447155216e723d71cf0f83d2 Publisher @swadhindas324 C grade Model source
Kind Other
Version v6081f110ed76f3ae447155216e723d71cf0f83d2
Tasks Captioning
Source Hugging Face --- library_name: transformers tags: - generated_from_trainer metrics: - accuracy model-index: - name: vit-resnet-mistral-RSICD-with-3-captioning results: [] --- # vit-resnet-mistral-RSICD-with-3-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: 0.8332 - Accuracy: 81.61 - Bleu-1: 0.6172 - Bleu-2: 0.4856 - Bleu-3: 0.3941 - Bleu-4: 0.3277 - Meteor: 0.5872 - Rouge-l: 0.5473 - Cider: 1.7764 ## 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 | 768 | 0.6875 | 79.76 | 0.4668 | 0.3027 | 0.2115 | 0.1537 | 0.4085 | 0.3975 | 0.4800 | | 0.9613 | 2.0 | 1536 | 0.6617 | 79.95 | 0.5408 | 0.3865 | 0.2900 | 0.2251 | 0.5063 | 0.4725 | 0.8810 | | 0.4688 | 3.0 | 2304 | 0.6203 | 81.41 | 0.6967 | 0.5742 | 0.4819 | 0.4076 | 0.6830 | 0.6362 | 2.2115 | | 0.3476 | 4.0 | 3072 | 0.6622 | 81.63 | 0.6703 | 0.5444 | 0.4542 | 0.3856 | 0.6507 | 0.6073 | 2.1154 | | 0.3476 | 5.0 | 3840 | 0.7266 | 80.53 | 0.6206 | 0.4886 | 0.3989 | 0.3344 | 0.6006 | 0.5550 | 1.7074 | | 0.2386 | 6.0 | 4608 | 0.7691 | 82.47 | 0.6587 | 0.5282 | 0.4352 | 0.3655 | 0.6262 | 0.5896 | 1.9587 | | 0.1875 | 7.0 | 5376 | 0.8124 | 81.71 | 0.6256 | 0.4936 | 0.4024 | 0.3350 | 0.5991 | 0.5542 | 1.7928 | | 0.1642 | 8.0 | 6144 | 0.8332 | 81.61 | 0.6172 | 0.4856 | 0.3941 | 0.3277 | 0.5872 | 0.5473 | 1.7764 | ### Framework versions - Transformers 5.12.1 - Pytorch 2.12.1+cu130 - Datasets 5.0.0 - Tokenizers 0.22.2
Sources & provenance
1 active source Source evidence
3 excerpts 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: 0.8332 Accuracy: 81.61 Bleu-1: 0.6172 Bleu-2: 0.4856 Bleu-3: 0.3941 Bleu-4: 0.3277 Meteor: 0.5872 Rouge-l:…
libraryname: transformers tags: generatedfromtrainer metrics: accuracy model-index: name: vit-resnet-mistral-RSICD-with-3-captioning results: []
swadhindas324/vit-resnet-mistral-RSICD-with-3-captioning
