metadata
base_model: microsoft/git-large-r-coco
datasets:
- imagefolder
library_name: transformers
license: mit
tags:
- generated_from_trainer
model-index:
- name: git-large-r-coco-IDB_ADv1_COCOv6-rv2
results: []
git-large-r-coco-IDB_ADv1_COCOv6-rv2
This model is a fine-tuned version of microsoft/git-large-r-coco on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0934
- Meteor Score: {'meteor': 0.6849337864778346}
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: 3e-05
- train_batch_size: 6
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 96
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 50
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Meteor Score |
|---|---|---|---|---|
| 0.7802 | 5.0 | 5 | 0.1019 | {'meteor': 0.6667354024231188} |
| 0.756 | 10.0 | 10 | 0.1006 | {'meteor': 0.6766394690979587} |
| 0.7057 | 15.0 | 15 | 0.0972 | {'meteor': 0.6774630113691023} |
| 0.6349 | 20.0 | 20 | 0.0934 | {'meteor': 0.6849337864778346} |
Framework versions
- Transformers 4.46.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.20.2