268543a3be
* current not clean working version move torch trainer to do_cli update code with config changes and clean up edit config cleanup add run name to trainer * address comments * use axolotl train in multigpu tests and add ray tests for multi-gpu * accelerate uses underscores for main_process_port arg * chore: lint * fix order of accelerate args * include ray train in docker images * current not clean working version move torch trainer to do_cli update code with config changes and clean up edit config cleanup add run name to trainer * address comments * use axolotl train in multigpu tests and add ray tests for multi-gpu * accelerate uses underscores for main_process_port arg * chore: lint * fix order of accelerate args * include ray train in docker images * fix bf16 resolution behavior * move dtype logic * x Signed-off-by: SumanthRH <sumanthrh@anyscale.com> * rename Signed-off-by: SumanthRH <sumanthrh@anyscale.com> * add to sidebar Signed-off-by: SumanthRH <sumanthrh@anyscale.com> * Apply suggestions from code review Co-authored-by: Eric Tang <46737979+erictang000@users.noreply.github.com> * Update docs/ray-integration.qmd Co-authored-by: Eric Tang <46737979+erictang000@users.noreply.github.com> * pre-commit fixes Signed-off-by: SumanthRH <sumanthrh@anyscale.com> * use output_dir instead of hardcoded saves path Co-authored-by: NanoCode012 <kevinvong@rocketmail.com> * bugfix storage dir * change type\ for resources_per_worker --------- Signed-off-by: SumanthRH <sumanthrh@anyscale.com> Co-authored-by: Wing Lian <wing@axolotl.ai> Co-authored-by: SumanthRH <sumanthrh@anyscale.com> Co-authored-by: Sumanth R Hegde <39546518+SumanthRH@users.noreply.github.com> Co-authored-by: Wing Lian <wing.lian@gmail.com> Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
80 lines
1.3 KiB
YAML
80 lines
1.3 KiB
YAML
base_model: NousResearch/Llama-3.2-1B
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: teknium/GPT4-LLM-Cleaned
|
|
type: alpaca
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.1
|
|
output_dir: ./outputs/lora-out
|
|
|
|
adapter: lora
|
|
lora_model_dir:
|
|
|
|
sequence_len: 2048
|
|
sample_packing: true
|
|
eval_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
|
|
xformers_attention:
|
|
flash_attention: true
|
|
|
|
loss_watchdog_threshold: 5.0
|
|
loss_watchdog_patience: 3
|
|
|
|
warmup_steps: 10
|
|
evals_per_epoch: 4
|
|
saves_per_epoch: 1
|
|
debug:
|
|
deepspeed: deepspeed_configs/zero3.json
|
|
weight_decay: 0.0
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|
|
pad_token: "<|end_of_text|>"
|
|
|
|
use_ray: true
|
|
ray_num_workers: 4
|