Views
No views yet

training:
max_seq_length: 2048
num_epochs: 1
learning_rate: 0.0001
batch_size: 1
gradient_accumulation_steps: 8
warmup_steps: 100
max_steps: -1
save_steps: 500
eval_steps: 0
weight_decay: 0.001
random_seed: 3407
packing: false
train_on_completions: true
gradient_checkpointing: unsloth
optim: adamw_8bit
lr_scheduler_type: cosine
lora:
lora_r: 16
lora_alpha: 32
lora_dropout: 0
target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- up_proj
- down_proj
use_rslora: false
use_loftq: false
finetune_vision_layers: true
finetune_language_layers: true
finetune_attention_modules: true
finetune_mlp_modules: true