rayraycano's picture
Training in progress, step 20
fcca8c8 verified
base_model: mistral-community/pixtral-12b
processor_type: AutoProcessor
strict: false
# 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: pixtral
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: 0.0
output_dir: ./outputs/out
adapter: lora
lora_model_dir:
sequence_len: 8192
pad_to_sequence_len: false
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules: 'language_model.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: 4
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: true
fp16:
tf32: true
gradient_checkpointing: true
local_rank:
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
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
pad_token: <pad>