nhung03__d61587f5-eb8b-442b-9c1d-58a5cfc13ddc

adapter: lora
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - cb467f516e247820_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/cb467f516e247820_train_data.json
  type:
    field_instruction: instruction
    field_output: positive_sample
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 1
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: nhung03/d61587f5-eb8b-442b-9c1d-58a5cfc13ddc
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 5.0e-05
load_in_4bit: true
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 200
micro_batch_size: 2
mlflow_experiment_name: /tmp/cb467f516e247820_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 1
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 3d4e1f5b-dc71-4b11-a0fa-e63310d045c4
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 3d4e1f5b-dc71-4b11-a0fa-e63310d045c4
warmup_steps: 5
weight_decay: 0.01
xformers_attention: true