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>

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: cgato/SlimOrcaDedupCleaned
    type: chat_template
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

dataset_prepared_path:
val_set_size: 0
output_dir: ./outputs/eaft-gemma-3-1b

use_eaft: true
eaft_alpha: 1.0
eaft_k: 20

sequence_len: 1024
sample_packing: false

adapter:
lora_model_dir:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 1
eval_batch_size: 1
max_steps: 1000
evaluation_strategy: "no"
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 5e-5

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false

early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
attn_implementation: flash_attention_2

warmup_ratio: 0.1
weight_decay: 0.0
debug:
deepspeed:
fsdp:
fsdp_config:
special_tokens: