VOOZH about

URL: https://huggingface.co/Kendamarron/Qwen2.5-1.75B-A1.1B-Instruct-ja

⇱ Kendamarron/Qwen2.5-1.75B-A1.1B-Instruct-ja · Hugging Face


Qwen2.5-1.75B-A1.1B-Instruct-ja

Qwen2.5-0.5B系のモデルを組み合わせて作ったMoEです。

Details

https://zenn.dev/kendama/articles/68ae234e9371ac

👁 Built with Axolotl


Qwen2.5-4x0.5B-sft-v1

This model is a fine-tuned version of Kendamarron/Qwen2.5-4x0.5B-cpt on the Kendamarron/jimba-instruction-all, the Kendamarron/OpenMathInstruct-2-ja-CoT-only_thought, the Aratako/Synthetic-JP-EN-Coding-Dataset-801k and the llm-jp/magpie-sft-v1.0 datasets. It achieves the following results on the evaluation set:

  • Loss: 1.0085

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: 2e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • total_eval_batch_size: 4
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 60
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss
1.3068 0.0033 1 1.3071
1.1087 0.3309 100 1.0806
1.1393 0.6617 200 1.0488
1.0569 0.9926 300 1.0286
0.9902 1.3209 400 1.0215
0.9933 1.6518 500 1.0133
0.9706 1.9826 600 1.0085

Framework versions

  • Transformers 4.47.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.21.0
Downloads last month
6
Safetensors
Model size
2B params
Tensor type
BF16
·

Model tree for Kendamarron/Qwen2.5-1.75B-A1.1B-Instruct-ja

Finetuned
(1)
this model

Datasets used to train Kendamarron/Qwen2.5-1.75B-A1.1B-Instruct-ja