metadata

library_name: transformers
base_model: Qwen/Qwen3-0.6B-Base
tags:
  - generated_from_trainer
model-index:
  - name: MNLP_M2_rag_model
    results: []

MNLP_M2_rag_model

This model is a fine-tuned version of Qwen/Qwen3-0.6B-Base

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_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
lr_scheduler_warmup_steps: 500
num_epochs: 3