qwen-full-sft-few-shot/README.md

metadata

library_name: transformers
license: other
base_model: /mnt/data/rolnan/models/Qwen2-7b
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: full-sft-few-shot
    results: []

full-sft-few-shot

This model is a fine-tuned version of /mnt/data/rolnan/models/Qwen2-7b on the oneflow_limit_num_few_shot 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: 2
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 3
• gradient_accumulation_steps: 2
• total_train_batch_size: 12
• total_eval_batch_size: 24
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0

Training results

Framework versions

• Transformers 4.44.2
• Pytorch 2.1.0+cu118
• Datasets 2.16.1
• Tokenizers 0.19.1