base_model: mistralai/Magistral-Small-2506

# Enable to use mistral-common tokenizer
tokenizer_use_mistral_common: true

# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

plugins:
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

load_in_8bit: false
load_in_4bit: true

datasets:
  - path: fozziethebeat/alpaca_messages_2k_test
    type: chat_template

dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./outputs/lora-out

adapter: qlora
lora_model_dir:

sequence_len: 2048
sample_packing: true
eval_sample_packing: false

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 0.0002

bf16: auto
tf32: false

gradient_checkpointing:
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_ratio: 0.1
evals_per_epoch: 1
saves_per_epoch: 1

fsdp:
  - full_shard
  - auto_wrap
fsdp_config:
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_transformer_layer_cls_to_wrap: MistralDecoderLayer
  fsdp_activation_checkpointing: true

# save_first_step: true  # uncomment this to validate checkpoint saving works with your config