metadata
library_name: transformers
license: other
base_model: Qwen/Qwen2-VL-2B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: qwen2-VL-2B-Instruct-atm-pretrain-random-level
results: []
qwen2-VL-2B-Instruct-atm-pretrain-random-level
This model is a fine-tuned version of /dev/shm/Qwen2-VL-2B-Instruct on the atm_pretrain 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: 1e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- total_eval_batch_size: 32
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cu121
- Datasets 3.6.0
- Tokenizers 0.21.1