e672d37f33
* fix: qwen3-next to use fla causal-conv1d to support packing * fix: causal import and update doc for v5 * fix: hard fail for packing without fla
78 lines
1.4 KiB
YAML
78 lines
1.4 KiB
YAML
base_model: Qwen/Qwen3-Next-80B-A3B-Instruct
|
|
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
plugins:
|
|
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: true
|
|
|
|
quantize_moe_experts: true
|
|
|
|
datasets:
|
|
- path: fozziethebeat/alpaca_messages_2k_test
|
|
type: chat_template
|
|
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.1
|
|
output_dir: ./outputs/lora-out
|
|
|
|
adapter: qlora
|
|
lora_model_dir:
|
|
|
|
sequence_len: 2048
|
|
sample_packing: true
|
|
|
|
lora_r: 16
|
|
lora_alpha: 8
|
|
lora_dropout: 0
|
|
lora_target_modules:
|
|
- linear_attn.in_proj_ba
|
|
- linear_attn.in_proj_qkvz
|
|
- linear_attn.out_proj
|
|
- shared_expert.up_proj
|
|
- shared_expert.down_proj
|
|
- shared_expert.gate_proj
|
|
- shared_expert_gate
|
|
- q_proj
|
|
- v_proj
|
|
- k_proj
|
|
- o_proj
|
|
|
|
# lora_target_parameters:
|
|
# - mlp.experts.gate_up_proj
|
|
# - mlp.experts.down_proj
|
|
|
|
lora_mlp_kernel: false
|
|
lora_qkv_kernel: false
|
|
lora_o_kernel: false
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 2
|
|
micro_batch_size: 2
|
|
num_epochs: 1
|
|
optimizer: adamw_bnb_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
bf16: auto
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch: 1
|
|
saves_per_epoch: 1
|
|
|
|
# save_first_step: true # uncomment this to validate checkpoint saving works with your config
|