base_model: JackFram/llama-68m
batch_size: 64
bf16: true
chat_template: tokenizer_default_fallback_alpaca
datasets:
- format: custom
  path: argilla/databricks-dolly-15k-curated-en
  type:
    field_input: original-instruction
    field_instruction: original-instruction
    field_output: original-response
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
device_map: auto
eval_sample_packing: false
eval_steps: 50
flash_attention: true
gradient_checkpointing: true
group_by_length: true
hub_model_id: SystemAdmin123/llama-68m
hub_strategy: checkpoint
learning_rate: 0.0002
logging_steps: 10
lr_scheduler: cosine
max_steps: 5000
micro_batch_size: 32
model_type: AutoModelForCausalLM
num_epochs: 100
optimizer: adamw_bnb_8bit
output_dir: /root/.sn56/axolotl/tmp/llama-68m
pad_to_sequence_len: true
resize_token_embeddings_to_32x: false
sample_packing: true
save_steps: 50
save_total_limit: 2
sequence_len: 2048
special_tokens:
  pad_token: </s>
tokenizer_type: LlamaTokenizerFast
torch_dtype: bf16
trust_remote_code: true
val_set_size: 0.1
wandb_entity: ''
wandb_mode: online
wandb_name: JackFram/llama-68m-argilla/databricks-dolly-15k-curated-en
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: default
warmup_ratio: 0.05