rtahmasbi / data_ex2_50_v2

axolotl version: 0.7.0

base_model: meta-llama/Llama-3.1-8B-Instruct
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: rtahmasbi/data_ex2_50
    type: alpaca
dataset_prepared_path:
val_set_size: 0
output_dir: ./outputs/data_ex2_50_v2

adapter: lora
lora_model_dir:

sequence_len: 15000
sample_packing: true
pad_to_sequence_len: true

lora_r: 16
lora_alpha: 32
lora_dropout: 0.0
lora_target_modules:
  - q_proj
  - v_proj
  - o_proj
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 10
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 3e-4

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|end_of_text|>"