Experimental pre-training on instruction datasets. https://wandb.ai/open-assistant/supervised-finetuning/runs/ys9rt5ue
Checkpoint: 3500 steps
Used oasst dataset config:
pretrain:
use_custom_sampler: true
sort_by_length: false
datasets:
- joke
- webgpt:
val_split: 0.1
- gpt4all:
val_split: 0.01
- alpaca:
val_split: 0.025
- code_alpaca:
val_split: 0.05
- minimath
- humaneval_mbpp_codegen_qa
- humaneval_mbpp_testgen_qa
- grade_school_math_instructions
- recipes
- cmu_wiki_qa
#- youtube_subs_howto100m # uses incompatible column names
#- ubuntu_dialogue_qa # fails to load
- oa_wiki_qa_bart_10000row
- prosocial_dialogue:
fraction: 0.1
- explain_prosocial:
fraction: 0.05
pythia parameters:
pythia-12b:
dtype: fp16
log_dir: "pythia_log_12b"
learning_rate: 6e-6
model_name: EleutherAI/pythia-12b-deduped
output_dir: pythia_model_12b
weight_decay: 0.0
max_length: 2048
use_flash_attention: true
#deepspeed_config: configs/zero3_config.json
warmup_steps: 50
gradient_checkpointing: true
gradient_accumulation_steps: 8
per_device_train_batch_size: 2
per_device_eval_batch_size: 5
eval_steps: 200
save_steps: 500
num_train_epochs: 2
save_total_limit: 2
- Downloads last month
- 2