base_model: google/gemma-3-1b-it

model_type: Gemma3ForCausalLM
cls_model_config: Gemma3TextConfig

# gemma3 doesn't seem to play nice with ddp
ddp_find_unused_parameters: true

chat_template: gemma3
eot_tokens:
  - <end_of_turn>
datasets:
  - path: cgato/SlimOrcaDedupCleaned
    type: chat_template
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

val_set_size: 0.05
output_dir: ./outputs/gemma-3-1b-fft-dft

sequence_len: 2048
sample_packing: true

# Enable Dynamic Fine-Tuning loss
use_dynamic_finetuning: true

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: 5e-5

bf16: auto
tf32: true

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

warmup_ratio: 0.1
evals_per_epoch: 2
saves_per_epoch: 1
weight_decay: 0.0