97f1b1758d
* feat: add custom kimi linear patch [skip ci] * feat: add configuration file and fix import [skip ci] * fix: hijack tokenizer temporarily [skip ci] * chore: remove accidental commit * fix: attempt patch kimi remote * fix: kwargs passsed * fix: device for tensor * fix: aux loss calculation * feat: cleaned up patches order * fix: remove duplicate tokenizer patch * chore: add debug logs * chore: add debug logs * chore: debug * Revert "chore: add debug logs" This reverts commitda372a5f67. * Revert "chore: add debug logs" This reverts commit97d1de1d7c. * fix: KeyError: 'tokenization_kimi' * fix: support remote_model_id in cce patch * feat: add config preload patch * fix: use standard aux loss calc and updated modeling * fix: import * feat: add kimi-linear docs and example * chore: add note about moe kernels * feat: update cce to include kimi-linear * chore: lint * chore: update main readme * fix: patch mechanism to address comments * chore: lint * fix: tests * chore: cleanup comment
82 lines
1.3 KiB
YAML
82 lines
1.3 KiB
YAML
base_model: moonshotai/Kimi-Linear-48B-A3B-Instruct
|
|
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
trust_remote_code: true
|
|
|
|
plugins:
|
|
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
|
|
|
load_in_8bit: true
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: fozziethebeat/alpaca_messages_2k_test
|
|
type: chat_template
|
|
split: train
|
|
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.2
|
|
output_dir: ./outputs/lora-out
|
|
|
|
adapter: lora
|
|
lora_model_dir:
|
|
|
|
sequence_len: 2048
|
|
sample_packing: true
|
|
pad_to_sequence_len: true
|
|
|
|
lora_r: 16
|
|
lora_alpha: 32
|
|
lora_dropout: 0.05
|
|
lora_fan_in_fan_out:
|
|
lora_target_modules:
|
|
- gate_proj
|
|
- down_proj
|
|
- up_proj
|
|
- q_proj
|
|
- v_proj
|
|
- k_proj
|
|
- o_proj
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 2
|
|
micro_batch_size: 2
|
|
num_epochs: 1
|
|
optimizer: adamw_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: auto
|
|
fp16:
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
loss_watchdog_threshold: 5.0
|
|
loss_watchdog_patience: 3
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch: 2
|
|
saves_per_epoch: 1
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.0
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|