|
--- |
|
license: apache-2.0 |
|
--- |
|
- base model: [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) |
|
- wandb (internal): https://wandb.ai/open-assistant/supervised-finetuning/runs/tlevhltw |
|
- checkpoint: 2000 steps (~2.9 epochs) |
|
|
|
Model: |
|
``` |
|
falcon-7b: |
|
dtype: bf16 |
|
log_dir: "falcon_log_7b" |
|
learning_rate: 1e-5 |
|
model_name: "tiiuae/falcon-7b" |
|
deepspeed_config: configs/zero_config.json |
|
output_dir: falcon |
|
weight_decay: 0.0 |
|
max_length: 2048 |
|
warmup_steps: 20 |
|
gradient_checkpointing: true |
|
gradient_accumulation_steps: 4 |
|
per_device_train_batch_size: 4 |
|
per_device_eval_batch_size: 8 |
|
eval_steps: 100 |
|
save_steps: 500 |
|
save_strategy: steps |
|
num_train_epochs: 8 |
|
save_total_limit: 4 |
|
residual_dropout: 0.2 |
|
residual_dropout_lima: true |
|
``` |
|
|
|
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) |
|
|
|
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 |
|
``` |
