base_model: furiosa-ai/mlperf-gpt-j-6b
batch_size: 32
bf16: true
chat_template: tokenizer_default_fallback_alpaca
datasets:
- format: custom
  path: https://gradients.s3.eu-north-1.amazonaws.com/3fdaac89f074f524_train_data.json?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAVVZOOA7SA4UOFLPI%2F20250208%2Feu-north-1%2Fs3%2Faws4_request&X-Amz-Date=20250208T161036Z&X-Amz-Expires=604800&X-Amz-SignedHeaders=host&X-Amz-Signature=a1efdc5f15ab5cff5586d44a19c13ab5b6176760b2aaeac5fa898939acd74ff7
  type:
    field_instruction: anchor
    field_output: positive
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
device_map: auto
eval_sample_packing: false
eval_steps: 40
flash_attention: true
gradient_checkpointing: true
group_by_length: true
hub_model_id: SystemAdmin123/01900ae1-e7d5-4ce2-bbd7-2b4e8624c1c5
hub_strategy: checkpoint
learning_rate: 0.0002
logging_steps: 10
lr_scheduler: cosine
max_steps: 10000
micro_batch_size: 3
model_type: AutoModelForCausalLM
num_epochs: 100
optimizer: adamw_bnb_8bit
output_dir: /root/.sn56/axolotl/tmp/01900ae1-e7d5-4ce2-bbd7-2b4e8624c1c5
pad_to_sequence_len: true
resize_token_embeddings_to_32x: false
sample_packing: true
save_steps: 40
save_total_limit: 2
sequence_len: 2048
tokenizer_type: GPT2TokenizerFast
torch_dtype: bf16
training_args_kwargs:
  hub_private_repo: true
trust_remote_code: true
val_set_size: 0.1
wandb_entity: ''
wandb_mode: online
wandb_name: furiosa-ai/mlperf-gpt-j-6b-https://gradients.s3.eu-north-1.amazonaws.com/3fdaac89f074f524_train_data.json?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAVVZOOA7SA4UOFLPI%2F20250208%2Feu-north-1%2Fs3%2Faws4_request&X-Amz-Date=20250208T161036Z&X-Amz-Expires=604800&X-Amz-SignedHeaders=host&X-Amz-Signature=a1efdc5f15ab5cff5586d44a19c13ab5b6176760b2aaeac5fa898939acd74ff7
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: default
warmup_ratio: 0.05