ivangrapher/cfdbf28d-a164-472c-9481-f4894aaa67c1

adapter: lora
base_model: NousResearch/Hermes-2-Pro-Llama-3-8B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 064b590a023d4bc0_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/064b590a023d4bc0_train_data.json
  type:
    field_input: text
    field_instruction: instruction
    field_output: Resume_test
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: null
eval_max_new_tokens: 256
eval_steps: 5
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: ivangrapher/cfdbf28d-a164-472c-9481-f4894aaa67c1
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 3
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 75GiB
max_steps: 30
micro_batch_size: 2
mlflow_experiment_name: /tmp/064b590a023d4bc0_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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: 15
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: cdac4aef-b554-4070-8d02-a2ed3e212859
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: cdac4aef-b554-4070-8d02-a2ed3e212859
warmup_steps: 15
weight_decay: 0.01
xformers_attention: true