a098df527b
* feat: add mistral small 4 * fix: update mistral common * fix: deepcopy when passing in tokenizer * feat: add doc on reasoning and thinking section * fix: don't use custom tokenizer and quantize experts * chore: update docs and configs * chore: update doc to follow official name * feat: update cce to include mistral4 * chore: move * fix: naming * fix: test mock breaking get_text_config check * fix: enable CCE and add expert block targetting to configs * chore: docs * fix: use act checkpointing * chore: doc * chore: docs * chore: docs
59 lines
1.1 KiB
YAML
59 lines
1.1 KiB
YAML
base_model: mistralai/Mistral-Small-4-119B-2603
|
|
|
|
plugins:
|
|
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
|
|
|
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: 0.01
|
|
output_dir: ./outputs/out
|
|
|
|
adapter: qlora
|
|
|
|
sequence_len: 2048
|
|
sample_packing: true
|
|
|
|
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'
|
|
|
|
# uncomment to train on expert layers
|
|
# 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: 1
|
|
micro_batch_size: 1
|
|
num_epochs: 1
|
|
optimizer: adamw_bnb_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
bf16: true
|
|
tf32: true
|
|
|
|
gradient_checkpointing: true
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch: 1
|
|
saves_per_epoch: 1
|
|
weight_decay: 0.0
|