stringtron/mdel-aurora-test-Mike

base_model: aurora-m/aurora-m-v0.1 # this can be swapped for mdel model when the model is released
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
is_llama_derived_model: false

load_in_8bit: false # when this is true inference quality is terrible
load_in_4bit: false
strict: false

datasets:
  - path: /workspace/axolotl-mdel/mtg.txt # change this to where your dataset is
    type: completion # change this to 'alpaca' if you are using alpaca formatting

lora_modules_to_save:
  - embed_tokens
  - lm_head

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./lora-out

sequence_len: 4096 # this can be tweaked for efficiency
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: mtg-aurora-test-Mike # give this a name
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2 # this can be tweaked for efficiency
micro_batch_size: 1 # this can be tweaked for efficiency
num_epochs: 1 # this can be experimented with
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: true
group_by_length: false
bf16: true
fp16: false
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: false # when this is true, inference quality is terrible
s2_attention:

warmup_steps: 10 # this can be tweaked for efficiency
evals_per_epoch: 10 # this can be tweaked for efficiency
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 1 
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|endoftext|>"
  eos_token: "<|endoftext|>"