base_model: Qwen/Qwen2.5-Math-7B-Instruct
batch_size: 32
bf16: true
chat_template: tokenizer_default_fallback_alpaca
datasets:
- data_files:
  - f58008447a01a2e1_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/f58008447a01a2e1_train_data.json
  type:
    field_instruction: question
    field_output: answer
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
eval_steps: 20
flash_attention: true
gpu_memory_limit: 80GiB
gradient_checkpointing: true
group_by_length: true
hub_model_id: SystemAdmin123/0b0d8bdd-1df1-4e38-93cb-eb2f50e3e64a
hub_strategy: checkpoint
learning_rate: 0.0002
logging_steps: 10
lr_scheduler: cosine
micro_batch_size: 2
model_type: AutoModelForCausalLM
num_epochs: 10
optimizer: adamw_bnb_8bit
output_dir: /workspace/axolotl/configs
pad_to_sequence_len: true
resize_token_embeddings_to_32x: false
sample_packing: false
save_steps: 40
save_total_limit: 1
sequence_len: 2048
tokenizer_type: Qwen2TokenizerFast
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.1
wandb_entity: ''
wandb_mode: online
wandb_name: Qwen/Qwen2.5-Math-7B-Instruct-/tmp/f58008447a01a2e1_train_data.json
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: default
warmup_ratio: 0.05
xformers_attention: true