metadata

license: apache-2.0
tags:
  - generated_from_trainer
base_model: NourFakih/Vit-GPT2-COCO2017Flickr-80k-08
model-index:
  - name: Vit-GPT2-COCO2017Flickr-85k-09
    results: []

Vit-GPT2-COCO2017Flickr-85k-09

This model is a fine-tuned version of NourFakih/Vit-GPT2-COCO2017Flickr-80k-08 on an unknown dataset. It achieves the following results on the evaluation set:

eval_loss: 0.5351
eval_rouge1: 39.4446
eval_rouge2: 14.1599
eval_rougeL: 35.6123
eval_rougeLsum: 35.5846
eval_gen_len: 11.738
eval_runtime: 463.8252
eval_samples_per_second: 8.624
eval_steps_per_second: 2.156
epoch: 0.0933
step: 500

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: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3.0

Framework versions

Transformers 4.41.2
Pytorch 2.1.2
Datasets 2.19.2
Tokenizers 0.19.1