FourOhFour/Vapor_7B

base_model: Qwen/Qwen2.5-7B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: sharegpt
    conversation: chatml
  - path: NewEden/Kalo-Opus-Instruct-22k-Refusal-Murdered
    type: sharegpt
    conversation: chatml
  - path: Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
    type: sharegpt
    conversation: chatml
  - path: NewEden/Gryphe-Sonnet-3.5-35k-Subset
    type: sharegpt
    conversation: chatml
  - path: Nitral-AI/Reasoning-1shot_ShareGPT
    type: sharegpt
    conversation: chatml
  - path: Nitral-AI/GU_Instruct-ShareGPT
    type: sharegpt
    conversation: chatml
  - path: Nitral-AI/Medical_Instruct-ShareGPT
    type: sharegpt
    conversation: chatml

chat_template: chatml

val_set_size: 0.01
output_dir: ./outputs/out

adapter:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:

sequence_len: 8192
# sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

wandb_project: qwen7B
wandb_entity:
wandb_watch:
wandb_name: qwen7B
wandb_log_model:

gradient_accumulation_steps: 32
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00001
weight_decay: 0.05

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

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

warmup_ratio: 0.1
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 2

debug:
deepspeed:
fsdp:
fsdp_config:

special_tokens:
  pad_token: <pad>