zamagi/plamo-2-1b-gorilla-chat3

# モデルの設定
base_model: /notebooks/plamo-2-1b-gorilla-chat2              # HuggingFace上のモデル名
model_type: AutoModelForCausalLM         # モデルのロードに使用するクラス
tokenizer_type: AutoTokenizer           # トークナイザのロードに使用するクラス
trust_remote_code: true                 # リモートのカスタムコードを信頼してモデルをロード

hub_model_id: zamagi/fft-1
hub_strategy: "end"
push_dataset_to_hub:
hf_use_auth_token: true

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

# 8bit/4bit設定（8bitモードでメモリ削減）
load_in_8bit: false   #f                      # 8bit量子化されたモデルをロード
load_in_4bit: false                     # 4bit量子化は使用しない
strict: false                           # 重みの厳密な一致を要求しない（追加トークン等がある場合に許容）

chat_template: tokenizer_default

# データセットの設定
datasets:
  - path: Aratako/Magpie-Tanuki-Qwen2.5-72B-Answered
    type: chat_template
    field_messages: messages
    message_field_role: role
    message_field_content: content
    roles_to_train: ["assistant"]       # 学習対象とする役割（アシスタントの発話のみ学習）
    train_on_eos: last
#  - path: Aratako/magpie-qwen2.5-32b-reasoning-100k-formatted
#    type: chat_template
#    field_messages: conversations
#    message_field_role: role
#    message_field_content: content
#  - path: Aratako/magpie-reasoning-llama-nemotron-70b-100k-filtered
#    type: chat_template
#    field_messages: conversations
#    message_field_role: role
#    message_field_content: content
#  - path: Aratako/Open-Platypus-Japanese-masked-formatted
#    type: chat_template
#    field_messages: conversations
#    message_field_role: role
#    message_field_content: content
#  - path: kanhatakeyama/wizardlm8x22b-logical-math-coding-sft_additional-ja
#    type: chat_template
#    field_messages: messages
#    message_field_role: role
#    message_field_content: content
#  - path: kanhatakeyama/ramdom-to-fixed-multiturn-Calm3
#    split: 20240806filtered
#    type: chat_template
#    field_messages: messages
#    message_field_role: role
#    message_field_content: content
#  - path: Aratako/magpie-ultra-v0.1-formatted
#    type: chat_template
#    field_messages: conversations
#    message_field_role: role
#    message_field_content: content
#  - path: Aratako/orca-agentinstruct-1M-v1-selected
#    type: chat_template
#    field_messages: messages
#    message_field_role: role
#    message_field_content: content
#  - path: Aratako/Synthetic-JP-EN-Coding-Dataset-801k-50k
#    type: chat_template
#    field_messages: messages
#    message_field_role: role
#    message_field_content: content

shuffle_merged_datasets: true
dataset_prepared_path: /notebooks/data/fft-data
val_set_size: 0.003
output_dir: /notebooks/data/27b-fft-out-1
dataset_keep_in_memory: false

gpu_memory_limit: 48GiB

sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:


# トレーニングの設定
gradient_accumulation_steps: 4
micro_batch_size: 8
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler:
cosine_min_lr_ratio: 0.1
learning_rate: 0.00001
max_steps: 5000

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

#wandb: false
#wandb_project: 27b-fft
#wandb_entity: aratako-lm
#wandb_watch:
#wandb_name: attempt-01
#wandb_log_model:

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

save_strategy: steps
save_steps: 100
save_total_limit: 2

warmup_steps: 50
eval_steps: 100
eval_batch_size: 1
eval_table_size:
eval_max_new_tokens:

debug:
deepspeed: /notebooks/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:


# 出力の保存設定
output_dir: /notebooks/output/plamo-2-1b-gorilla-chat3    # チェックポイントや最終モデルの出力先ディレクトリ
hub_model_id: zamagi/plamo-2-1b-gorilla-chat3   # (オプション) Hugging Face Hubにアップロードする場合のリポジトリ名