metadata

license: apache-2.0
base_model: TIGER-Lab/Mantis-8B-Idefics2
tags:
  - generated_from_trainer
model-index:
  - name: mantis-8b-idefics2_italian_8192
    results: []

mantis-8b-idefics2_italian_8192

This model is a fine-tuned version of TIGER-Lab/Mantis-8B-Idefics2 on an unknown dataset.

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-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 32
total_train_batch_size: 128
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 30.0

Training results

Framework versions

Transformers 4.40.1
Pytorch 2.2.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1