Ailonordsletta/Nanbeige4.1-3B-microthink

See axolotl config

axolotl version: 0.13.0.dev0

base_model: Nanbeige/Nanbeige4.1-3B
trust_remote_code: true

# Dataset
datasets:
  - path: Ailonordsletta/med-dict
    type: chat_template
chat_template: tokenizer_default

# LoRA
adapter: lora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj
  - gate_proj
  - down_proj
  - up_proj
load_in_8bit: true

# Training
num_epochs: 3
micro_batch_size: 4
gradient_accumulation_steps: 4
learning_rate: 2e-4
lr_scheduler: cosine
warmup_ratio: 0.05
optimizer: adamw_bnb_8bit
sequence_len: 4096
train_on_inputs: false

# Precision
bf16: auto

# Saving
output_dir: ./outputs/nanbeige-microthink
save_strategy: steps
save_steps: 200
save_total_limit: 3
logging_steps: 10
gradient_checkpointing: true

seed: 42

outputs/nanbeige-microthink

This model is a fine-tuned version of Nanbeige/Nanbeige4.1-3B on the Ailonordsletta/med-dict 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: 0.0002
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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: 46
• training_steps: 929

Training results

Framework versions

• PEFT 0.17.1
• Transformers 4.57.0
• Pytorch 2.7.1+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1