dimasik87__38c537af-903d-4208-9186-707aa28f3a5b

adapter: lora
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 66e1f5c3a87b9009_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/66e1f5c3a87b9009_train_data.json
  type:
    field_instruction: file_content
    field_output: extracted_data
    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: 4
flash_attention: true
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: dimasik87/38c537af-903d-4208-9186-707aa28f3a5b
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 70GiB
max_steps: 50
micro_batch_size: 2
mlflow_experiment_name: /tmp/66e1f5c3a87b9009_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 5
save_strategy: steps
sequence_len: 2028
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: 38c537af-903d-4208-9186-707aa28f3a5b
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 38c537af-903d-4208-9186-707aa28f3a5b
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null