base_model: meta-llama/Meta-Llama-3.1-8B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

datasets:
  - path: /workspace/datasets/openhermes_200k_unfiltered/Open_Hermes_200k_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/magpie_function_calling/magpie_function_calling.jsonl
    type: sharegpt
    conversation: chatml

unfrozen_parameters:
- ^lm_head.weight$
- ^model.embed_tokens.weight$
# input_layernorm layers
- model.layers.0.input_layernorm
- model.layers.1.input_layernorm
- model.layers.2.input_layernorm
- model.layers.3.input_layernorm
- model.layers.4.input_layernorm
- model.layers.5.input_layernorm
- model.layers.6.input_layernorm
- model.layers.7.input_layernorm
- model.layers.8.input_layernorm
- model.layers.9.input_layernorm
- model.layers.10.input_layernorm
- model.layers.11.input_layernorm
- model.layers.12.input_layernorm
- model.layers.13.input_layernorm
- model.layers.14.input_layernorm
- model.layers.15.input_layernorm
# lm_head layers
# mlp.down_proj layers
- model.layers.1.mlp.down_proj
- model.layers.0.mlp.down_proj
- model.layers.30.mlp.down_proj
- model.layers.2.mlp.down_proj
- model.layers.21.mlp.down_proj
- model.layers.22.mlp.down_proj
- model.layers.29.mlp.down_proj
- model.layers.5.mlp.down_proj
- model.layers.4.mlp.down_proj
- model.layers.20.mlp.down_proj
- model.layers.23.mlp.down_proj
- model.layers.19.mlp.down_proj
- model.layers.3.mlp.down_proj
- model.layers.17.mlp.down_proj
- model.layers.6.mlp.down_proj
- model.layers.31.mlp.down_proj
# mlp.gate_proj layers
- model.layers.1.mlp.gate_proj
- model.layers.2.mlp.gate_proj
- model.layers.3.mlp.gate_proj
- model.layers.4.mlp.gate_proj
- model.layers.0.mlp.gate_proj
- model.layers.25.mlp.gate_proj
- model.layers.26.mlp.gate_proj
- model.layers.5.mlp.gate_proj
- model.layers.24.mlp.gate_proj
- model.layers.28.mlp.gate_proj
- model.layers.23.mlp.gate_proj
- model.layers.27.mlp.gate_proj
- model.layers.21.mlp.gate_proj
- model.layers.22.mlp.gate_proj
- model.layers.29.mlp.gate_proj
- model.layers.20.mlp.gate_proj
# mlp.up_proj layers
- model.layers.4.mlp.up_proj
- model.layers.3.mlp.up_proj
- model.layers.0.mlp.up_proj
- model.layers.5.mlp.up_proj
- model.layers.7.mlp.up_proj
- model.layers.6.mlp.up_proj
- model.layers.2.mlp.up_proj
- model.layers.1.mlp.up_proj
- model.layers.8.mlp.up_proj
- model.layers.12.mlp.up_proj
- model.layers.14.mlp.up_proj
- model.layers.9.mlp.up_proj
- model.layers.15.mlp.up_proj
- model.layers.17.mlp.up_proj
- model.layers.13.mlp.up_proj
- model.layers.19.mlp.up_proj
# model.embed_tokens layers
# model.norm layers
# post_attention_layernorm layers
- model.layers.0.post_attention_layernorm
- model.layers.1.post_attention_layernorm
- model.layers.2.post_attention_layernorm
- model.layers.3.post_attention_layernorm
- model.layers.4.post_attention_layernorm
- model.layers.5.post_attention_layernorm
- model.layers.6.post_attention_layernorm
- model.layers.7.post_attention_layernorm
- model.layers.8.post_attention_layernorm
- model.layers.9.post_attention_layernorm
- model.layers.10.post_attention_layernorm
- model.layers.11.post_attention_layernorm
- model.layers.12.post_attention_layernorm
- model.layers.13.post_attention_layernorm
- model.layers.14.post_attention_layernorm
- model.layers.15.post_attention_layernorm
# self_attn.k_proj layers
- model.layers.29.self_attn.k_proj
- model.layers.25.self_attn.k_proj
- model.layers.23.self_attn.k_proj
- model.layers.28.self_attn.k_proj
- model.layers.21.self_attn.k_proj
- model.layers.19.self_attn.k_proj
- model.layers.22.self_attn.k_proj
- model.layers.20.self_attn.k_proj
- model.layers.24.self_attn.k_proj
- model.layers.31.self_attn.k_proj
- model.layers.27.self_attn.k_proj
- model.layers.26.self_attn.k_proj
- model.layers.17.self_attn.k_proj
- model.layers.11.self_attn.k_proj
- model.layers.18.self_attn.k_proj
- model.layers.14.self_attn.k_proj
# self_attn.o_proj layers
- model.layers.14.self_attn.o_proj
- model.layers.7.self_attn.o_proj
- model.layers.5.self_attn.o_proj
- model.layers.11.self_attn.o_proj
- model.layers.6.self_attn.o_proj
- model.layers.24.self_attn.o_proj
- model.layers.9.self_attn.o_proj
- model.layers.13.self_attn.o_proj
- model.layers.10.self_attn.o_proj
- model.layers.12.self_attn.o_proj
- model.layers.8.self_attn.o_proj
- model.layers.25.self_attn.o_proj
- model.layers.21.self_attn.o_proj
- model.layers.23.self_attn.o_proj
- model.layers.15.self_attn.o_proj
- model.layers.16.self_attn.o_proj
# self_attn.q_proj layers
- model.layers.8.self_attn.q_proj
- model.layers.13.self_attn.q_proj
- model.layers.9.self_attn.q_proj
- model.layers.14.self_attn.q_proj
- model.layers.10.self_attn.q_proj
- model.layers.11.self_attn.q_proj
- model.layers.0.self_attn.q_proj
- model.layers.15.self_attn.q_proj
- model.layers.1.self_attn.q_proj
- model.layers.6.self_attn.q_proj
- model.layers.5.self_attn.q_proj
- model.layers.7.self_attn.q_proj
- model.layers.12.self_attn.q_proj
- model.layers.16.self_attn.q_proj
- model.layers.17.self_attn.q_proj
- model.layers.26.self_attn.q_proj
# self_attn.v_proj layers
- model.layers.26.self_attn.v_proj
- model.layers.17.self_attn.v_proj
- model.layers.3.self_attn.v_proj
- model.layers.28.self_attn.v_proj
- model.layers.29.self_attn.v_proj
- model.layers.21.self_attn.v_proj
- model.layers.15.self_attn.v_proj
- model.layers.16.self_attn.v_proj
- model.layers.20.self_attn.v_proj
- model.layers.25.self_attn.v_proj
- model.layers.6.self_attn.v_proj
- model.layers.23.self_attn.v_proj
- model.layers.4.self_attn.v_proj
- model.layers.1.self_attn.v_proj
- model.layers.22.self_attn.v_proj
- model.layers.14.self_attn.v_proj


chat_template: chatml
val_set_size: 0.01
output_dir: llama_3.1_8b_function_calling
data_seed: 49
seed: 49

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

wandb_project: function-calling-spectrum
wandb_entity: therealagi-reviewramp
wandb_watch: gradients
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: linear #linear is theoreticall optimal... https://arxiv.org/abs/2310.07831
learning_rate: 5e-6

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
auto_resume_from_checkpoints: true

warmup_steps: 10
evals_per_epoch: 2
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 2
save_total_limit: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|endoftext|>"
  eos_token: "<|im_end|>"