base_model: NousResearch/Meta-Llama-3-70B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: /workspace/datasets/dolphin-2.9/dolphin201-sharegpt2.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/Ultrachat200kunfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/dolphin-coder-translate-sharegpt2.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/dolphin-coder-codegen-sharegpt2.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/m-a-p_Code-Feedback-sharegpt-unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt-unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/not_samantha_norefusals.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/Orca-Math-resort-unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/agent_instruct_react_unfiltered.jsonl
    type: sharegpt  
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/toolbench_instruct_j1s1_3k_unfiltered.jsonl
    type: sharegpt  
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/toolbench_negative_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/toolbench_react_10p_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/toolbench_tflan_cot_30p_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/openhermes200k_unfiltered.jsonl
    type: sharegpt 
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/SystemConversations.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml
adapter: qlora
lora_r: 32
lora_alpha: 16
lora_modules_to_save: [embed_tokens, lm_head]
lora_dropout: 0.05
lora_target_linear: true
# lora_target_modules:
# - model.layers.75.self_attn.v_proj
# - model.layers.18.self_attn.v_proj
# - model.layers.78.self_attn.v_proj
# - model.layers.68.self_attn.v_proj
# - model.layers.47.self_attn.v_proj
# - model.layers.38.self_attn.v_proj
# - model.layers.71.self_attn.v_proj
# - model.layers.19.self_attn.v_proj
# - model.layers.36.self_attn.v_proj
# - model.layers.39.self_attn.v_proj
# - model.layers.20.self_attn.v_proj
# - model.layers.22.self_attn.v_proj
# - model.layers.70.self_attn.v_proj
# - model.layers.16.self_attn.v_proj
# - model.layers.32.self_attn.v_proj
# - model.layers.21.self_attn.v_proj
# - model.layers.13.self_attn.v_proj
# - model.layers.10.self_attn.v_proj
# - model.layers.26.self_attn.v_proj
# - model.layers.23.self_attn.v_proj
# - model.layers.12.self_attn.v_proj
# - model.layers.33.self_attn.v_proj
# - model.layers.72.self_attn.v_proj
# - model.layers.24.self_attn.v_proj
# - model.layers.30.self_attn.v_proj
# - model.layers.14.self_attn.v_proj
# - model.layers.77.self_attn.v_proj
# - model.layers.8.self_attn.v_proj
# - model.layers.27.self_attn.v_proj
# - model.layers.79.self_attn.v_proj
# - model.layers.31.self_attn.v_proj
# - model.layers.35.self_attn.v_proj
# - model.layers.25.self_attn.v_proj
# - model.layers.6.self_attn.v_proj
# - model.layers.56.self_attn.v_proj
# - model.layers.34.self_attn.v_proj
# - model.layers.15.self_attn.v_proj
# - model.layers.52.self_attn.v_proj
# - model.layers.9.self_attn.v_proj
# - model.layers.29.self_attn.v_proj
# - model.layers.74.self_attn.v_proj
# - model.layers.76.self_attn.v_proj
# - model.layers.70.mlp.up_proj
# - model.layers.67.mlp.up_proj
# - model.layers.66.mlp.up_proj
# - model.layers.69.mlp.up_proj
# - model.layers.62.mlp.up_proj
# - model.layers.65.mlp.up_proj
# - model.layers.63.mlp.up_proj
# - model.layers.68.mlp.up_proj
# - model.layers.71.mlp.up_proj
# - model.layers.64.mlp.up_proj
# - model.layers.61.mlp.up_proj
# - model.layers.58.mlp.up_proj
# - model.layers.59.mlp.up_proj
# - model.layers.7.self_attn.v_proj
# - model.layers.57.mlp.up_proj
# - model.layers.55.mlp.up_proj
# - model.layers.72.mlp.up_proj
# - model.layers.54.mlp.up_proj
# - model.layers.4.self_attn.v_proj
# - model.layers.56.mlp.up_proj
# - model.layers.28.self_attn.v_proj
# - model.layers.60.mlp.up_proj
# - model.layers.40.mlp.down_proj
# - model.layers.73.mlp.up_proj
# - model.layers.46.mlp.down_proj
# - model.layers.44.mlp.down_proj
# - model.layers.45.mlp.down_proj
# - model.layers.43.mlp.down_proj
# - model.layers.51.mlp.up_proj
# - model.layers.50.mlp.up_proj
# - model.layers.52.mlp.down_proj
# - model.layers.47.mlp.down_proj
# - model.layers.53.mlp.up_proj
# - model.layers.48.mlp.down_proj
# - model.layers.39.mlp.down_proj
# - model.layers.49.mlp.down_proj
# - model.layers.52.mlp.up_proj
# - model.layers.74.mlp.up_proj
# - model.layers.38.mlp.down_proj
# - model.layers.49.mlp.up_proj
# - model.layers.53.mlp.down_proj
# - model.layers.41.mlp.down_proj
# - model.layers.35.mlp.down_proj
# - model.layers.51.mlp.down_proj
# - model.layers.30.mlp.up_proj
# - model.layers.42.mlp.down_proj
# - model.layers.34.mlp.up_proj
# - model.layers.47.mlp.up_proj
# - model.layers.46.mlp.up_proj
# - model.layers.50.mlp.down_proj
# - model.layers.37.mlp.down_proj
# - model.layers.48.mlp.up_proj
# - model.layers.60.mlp.down_proj
# - model.layers.76.mlp.down_proj
# - model.layers.54.mlp.down_proj
# - model.layers.36.mlp.down_proj
# - model.layers.57.mlp.down_proj
# - model.layers.56.mlp.down_proj
# - model.layers.55.mlp.down_proj
# - model.layers.59.mlp.down_proj
# - model.layers.77.mlp.down_proj
# - model.layers.38.mlp.up_proj
# - model.layers.45.mlp.up_proj
# - model.layers.61.mlp.down_proj
# - model.layers.43.mlp.up_proj
# - model.layers.29.mlp.up_proj
# - model.layers.42.mlp.up_proj
# - model.layers.75.mlp.up_proj
# - model.layers.58.mlp.down_proj
# - model.layers.35.mlp.up_proj
# - model.layers.44.mlp.up_proj
# - model.layers.65.mlp.down_proj
# - model.layers.31.mlp.up_proj
# - model.layers.73.self_attn.v_proj
# - model.layers.75.mlp.down_proj
# - model.layers.64.mlp.down_proj
# - model.layers.62.mlp.down_proj
# - model.layers.68.mlp.down_proj
# - model.layers.19.mlp.down_proj
# - model.layers.41.mlp.up_proj
# - model.layers.73.mlp.down_proj
# - model.layers.32.mlp.up_proj
# - model.layers.66.mlp.down_proj
# - model.layers.67.mlp.down_proj
# - model.layers.39.mlp.up_proj
# - model.layers.63.mlp.down_proj
# - model.layers.28.mlp.up_proj
# - model.layers.37.mlp.up_proj
# - model.layers.74.mlp.down_proj
# - model.layers.78.mlp.down_proj
# - model.layers.69.mlp.down_proj
# - model.layers.40.mlp.up_proj
# - model.layers.72.mlp.down_proj
# - model.layers.34.mlp.down_proj
# - model.layers.71.mlp.down_proj
# - model.layers.70.mlp.down_proj
# - model.layers.20.mlp.down_proj
# - model.layers.36.mlp.up_proj
# - model.layers.27.mlp.up_proj
# - model.layers.26.mlp.up_proj
# - model.layers.77.mlp.up_proj
# - model.layers.18.mlp.up_proj
# - model.layers.19.mlp.up_proj
# - model.layers.21.mlp.down_proj
# - model.layers.70.mlp.gate_proj
# - model.layers.21.mlp.up_proj
# - model.layers.71.mlp.gate_proj
# - model.layers.20.mlp.up_proj
# - model.layers.25.mlp.up_proj
# - model.layers.33.mlp.down_proj
# - model.layers.76.mlp.up_proj
# - model.layers.31.mlp.down_proj
# - model.layers.67.mlp.gate_proj
# - model.layers.32.mlp.down_proj
# - model.layers.58.mlp.gate_proj
# - model.layers.55.mlp.gate_proj
# - model.layers.57.mlp.gate_proj
# - model.layers.66.mlp.gate_proj
# - model.layers.56.mlp.gate_proj
# - model.layers.72.mlp.gate_proj
# - model.layers.18.mlp.down_proj
# - model.layers.22.mlp.down_proj
# - model.layers.69.mlp.gate_proj
# - model.layers.52.mlp.gate_proj
# - model.layers.54.mlp.gate_proj
# - model.layers.62.mlp.gate_proj
# - model.layers.59.mlp.gate_proj
# - model.layers.3.self_attn.v_proj
# - model.layers.60.mlp.gate_proj
# - model.layers.68.mlp.gate_proj
# - model.layers.74.mlp.gate_proj
# - model.layers.22.mlp.up_proj
# - model.layers.61.mlp.gate_proj
# - model.layers.51.mlp.gate_proj
# - model.layers.53.mlp.gate_proj
# - model.layers.73.mlp.gate_proj
# - model.layers.63.mlp.gate_proj
# - model.layers.48.mlp.gate_proj
# - model.layers.30.mlp.down_proj
# - model.layers.49.mlp.gate_proj
# - model.layers.29.mlp.down_proj
# - model.layers.64.mlp.gate_proj
# - model.layers.17.mlp.up_proj
# - model.layers.78.mlp.up_proj
# - model.layers.50.mlp.gate_proj
# - model.layers.65.mlp.gate_proj
# - model.layers.23.mlp.up_proj
# - model.layers.23.mlp.down_proj
# - model.layers.24.mlp.up_proj
# - model.layers.79.mlp.down_proj
# - model.layers.28.mlp.down_proj
# - model.layers.47.mlp.gate_proj
# - model.layers.44.mlp.gate_proj
# - model.layers.5.self_attn.v_proj
# - model.layers.45.mlp.gate_proj
# - model.layers.75.mlp.gate_proj
# - model.layers.27.mlp.down_proj
# - model.layers.46.mlp.gate_proj
# - model.layers.16.mlp.up_proj
# - model.layers.43.mlp.gate_proj
# - model.layers.25.mlp.down_proj
# - model.layers.26.mlp.down_proj
# - model.layers.24.mlp.down_proj
# - model.layers.77.mlp.gate_proj
# - model.layers.41.mlp.gate_proj
# - model.layers.42.mlp.gate_proj
# - model.layers.40.mlp.gate_proj
# - model.layers.17.mlp.down_proj
# - model.layers.32.mlp.gate_proj
# - model.layers.8.mlp.down_proj
# - model.layers.9.mlp.down_proj
# - model.layers.30.mlp.gate_proj
# - model.layers.15.mlp.up_proj
# - model.layers.2.self_attn.v_proj
# - model.layers.12.mlp.up_proj
# - model.layers.10.mlp.down_proj
# - model.layers.31.mlp.gate_proj
# - model.layers.39.mlp.gate_proj
# - model.layers.37.mlp.gate_proj
# - model.layers.36.mlp.gate_proj
# - model.layers.6.mlp.down_proj
# - model.layers.29.mlp.gate_proj
# - model.layers.28.mlp.gate_proj
# - model.layers.5.mlp.down_proj
# - model.layers.38.mlp.gate_proj
# - model.layers.7.mlp.down_proj
# - model.layers.14.mlp.up_proj
# - model.layers.78.mlp.gate_proj
# - model.layers.2.mlp.down_proj
# - model.layers.11.mlp.down_proj
# - model.layers.12.mlp.down_proj
# - model.layers.27.mlp.gate_proj
# - model.layers.16.mlp.down_proj
# - model.layers.35.mlp.gate_proj
# - model.layers.34.mlp.gate_proj
# - model.layers.13.mlp.up_proj
# - model.layers.4.mlp.down_proj
# - model.layers.3.mlp.down_proj
# - model.layers.76.mlp.gate_proj
# - model.layers.13.mlp.down_proj
# - model.layers.17.mlp.gate_proj
# - model.layers.7.mlp.up_proj
# - model.layers.15.mlp.down_proj
# - model.layers.25.mlp.gate_proj
# - model.layers.1.mlp.down_proj
# - model.layers.10.mlp.up_proj
# - model.layers.20.mlp.gate_proj
# - model.layers.12.mlp.gate_proj
# - model.layers.18.mlp.gate_proj
# - model.layers.16.mlp.gate_proj
# - model.layers.79.mlp.up_proj
# - model.layers.21.mlp.gate_proj
# - model.layers.14.mlp.down_proj
# - model.layers.72.self_attn.k_proj
# - model.layers.24.mlp.gate_proj
# - model.layers.75.self_attn.k_proj
# - model.layers.7.mlp.gate_proj
# - model.layers.71.self_attn.k_proj
# - model.layers.19.mlp.gate_proj
# - model.layers.10.mlp.gate_proj
# - model.layers.74.self_attn.k_proj
# - model.layers.14.mlp.gate_proj

dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

wandb_project: dolphin-2.9-llama3-70b
wandb_watch:
wandb_run_id:
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-4

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
evals_per_epoch: 2
eval_table_size:
saves_per_epoch: 4
save_total_limit: 2
save_steps:
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"
tokens:
  - "<|im_start|>"
  - "<|im_end|>"