metadata
license: apache-2.0
Supervised fine-tuning of falcon40b with a mix of OASST top-2 threads and synthetic instruction datasets. Exported at end of 2nd epoch.
- base model: tiiuae/falcon-40b
- wandb (internal): https://wandb.ai/open-assistant/supervised-finetuning/runs/feplc450
- checkpoint: 1226 steps
Model:
falcon-40b:
dtype: bf16
log_dir: "falcon_log_40b"
learning_rate: 1e-5
model_name: "tiiuae/falcon-40b"
deepspeed_config: configs/zero3_config_falcon.json
output_dir: falcon
weight_decay: 0.0
max_length: 2048
warmup_steps: 20
gradient_checkpointing: true
gradient_accumulation_steps: 1
per_device_train_batch_size: 18
per_device_eval_batch_size: 10
eval_steps: 120
#save_steps: 80
num_train_epochs: 8
save_total_limit: 4
use_flash_attention: false
residual_dropout: 0.3
residual_dropout_lima: true
sort_by_length: false
save_strategy: steps
Dataset:
sft9-stage2:
# oasst_export: 100.00% (29899)
# vicuna: 50.00% (16963)
# code_alpaca: 50.00% (9510)
# oa_wiki_qa_bart_10000row: 100.00% (9434)
# grade_school_math_instructions: 100.00% (8351)
# dolly15k: 100.00% (14250)
save_strategy: steps # epoch seems not to work, gets stuck with DS 0.9.1
save_steps: 613
use_custom_sampler: true
datasets:
- oasst_export:
lang: "bg,ca,cs,da,de,en,es,fr,hr,hu,it,nl,pl,pt,ro,ru,sl,sr,sv,uk" # sft-8.0
input_file_path: 2023-06-02_oasst_all_labels.jsonl.gz
val_split: 0.05
top_k: 2
- vicuna:
fraction: 0.5
val_split: 0.025
max_val_set: 250
- code_alpaca:
fraction: 0.5
val_split: 0.05
max_val_set: 250
- oa_wiki_qa_bart_10000row:
val_split: 0.05
max_val_set: 250
- grade_school_math_instructions:
val_split: 0.05
- dolly15k:
val_split: 0.05
max_val_set: 300