c67910fa6f
* bump hf deps * upgrade liger-kernel too * install cce from fork for transformers fix * fix reference to vocab size in gemma3 patch * use padding_idx instead of pad_token_id * remove fixed gemma3 patch * use updated cce fork * fix local mllama cce patches w docstring * add test for multipack with trainer setup and fix trainer for trainer refactor upstream * bump modal version * guard for iterable datasetS * mllama model arch layout changed in latest transformers * fix batch sampler with drop_last * fix: address upstream vlm changes for lora * fix: update references to old lora target path * fix: remove mllama fa2 patch due to upstream fix * fix: lora kernel patch path for multimodal models * fix: removed mllama from quarto * run test for came optim on 2.6.0+ * fix fsdp2 patch and remove deprecated patch * make sure to set sequence_parallel_degree for grpo * Add SP test for GRPO * add sp to grpo config for trainer * use reward_funcs as kwarg to grpo trainer * fix the comprehension for reward funcs * reward funcs already passed in as args * init sp_group right before training * fix check for adding models to SP context * make sure to pass args to super * upgrade deepspeed * use updated trl and add reasoning flags for vllm * patch the worker --------- Co-authored-by: NanoCode012 <nano@axolotl.ai>
59 lines
1.2 KiB
YAML
59 lines
1.2 KiB
YAML
base_model: mistralai/Mistral-Small-3.1-24B-Instruct-2503
|
|
processor_type: AutoProcessor
|
|
|
|
load_in_8bit: true
|
|
|
|
# these 3 lines are needed for now to handle vision chat templates w images
|
|
skip_prepare_dataset: true
|
|
remove_unused_columns: false
|
|
sample_packing: false
|
|
|
|
chat_template: mistral_v7_tekken
|
|
datasets:
|
|
- path: HuggingFaceH4/llava-instruct-mix-vsft
|
|
type: chat_template
|
|
split: train[:1%]
|
|
field_messages: messages
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.01
|
|
output_dir: ./outputs/out
|
|
|
|
adapter: lora
|
|
lora_model_dir:
|
|
|
|
sequence_len: 2048
|
|
pad_to_sequence_len: false
|
|
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_modules: 'model.language_model.layers.[\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 1
|
|
micro_batch_size: 1
|
|
num_epochs: 1
|
|
optimizer: adamw_bnb_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
bf16: true
|
|
fp16:
|
|
tf32: true
|
|
|
|
gradient_checkpointing: true
|
|
logging_steps: 1
|
|
flash_attention: false # PixtralVisionModel does not support Flash Attention 2.0 yet.
|
|
eager_attention:
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch: 1
|
|
saves_per_epoch: 1
|
|
weight_decay: 0.0
|
|
special_tokens:
|