120 lines
3.2 KiB
Markdown
120 lines
3.2 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
---
|
||
|
|
|
||
|
|
**Note: internal model, not ready for use**
|
||
|
|
|
||
|
|
This is an intermediate model used as base-model for further pythia 12b SFT-8 experiments.
|
||
|
|
It was trained on a wider set of instruction-tuning datasets for >12.5k steps with batch-size 128 and a context size of 2048.
|
||
|
|
The gpt4all dataset had "as a language model" *contamination* (>1.8k entries). We added filtering later, but this model (pre-v8) was trained on the raw unfildered gpt4all dataset.
|
||
|
|
|
||
|
|
|
||
|
|
- wandb: https://wandb.ai/open-assistant/supervised-finetuning/runs/sytsyhrp
|
||
|
|
- [sampling report](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-pretrained%2F2023-05-05_OpenAssistant_pythia-12b-pre-v8-12_5k-steps_sampling_noprefix2.json)
|
||
|
|
|
||
|
|
|
||
|
|
Datasets:
|
||
|
|
|
||
|
|
```
|
||
|
|
pretrain:
|
||
|
|
num_train_epochs: 1
|
||
|
|
weight_decay: 0.0
|
||
|
|
use_custom_sampler: true
|
||
|
|
sort_by_length: false
|
||
|
|
datasets:
|
||
|
|
- gpteacher_roleplay:
|
||
|
|
val_split: 0.05
|
||
|
|
- red_pajama:
|
||
|
|
fraction: 0.25
|
||
|
|
max_val_set: 1000
|
||
|
|
- wizardlm_70k:
|
||
|
|
val_split: 0.05
|
||
|
|
max_val_set: 500
|
||
|
|
- joke:
|
||
|
|
val_split: 0.05
|
||
|
|
- poem_instructions:
|
||
|
|
val_split: 0.025
|
||
|
|
- oa_stackexchange:
|
||
|
|
val_split: 0.05
|
||
|
|
fraction: 0.1
|
||
|
|
max_val_set: 1000
|
||
|
|
- tell_a_joke:
|
||
|
|
val_split: 0.05
|
||
|
|
max_val_set: 250
|
||
|
|
- webgpt:
|
||
|
|
val_split: 0.05
|
||
|
|
max_val_set: 250
|
||
|
|
- gpt4all:
|
||
|
|
val_split: 0.01
|
||
|
|
max_val_set: 1000
|
||
|
|
- alpaca_gpt4:
|
||
|
|
val_split: 0.025
|
||
|
|
max_val_set: 250
|
||
|
|
- code_alpaca:
|
||
|
|
val_split: 0.05
|
||
|
|
max_val_set: 250
|
||
|
|
- vicuna:
|
||
|
|
max_val_set: 250
|
||
|
|
- oig_file:
|
||
|
|
source_url: https://huggingface.co/datasets/laion/OIG/resolve/main/unified_chip2.jsonl
|
||
|
|
max_count: 10000
|
||
|
|
min_length: 250
|
||
|
|
val_split: 0.05
|
||
|
|
max_val_set: 250
|
||
|
|
- minimath:
|
||
|
|
val_split: 0.05
|
||
|
|
- humaneval_mbpp_codegen_qa:
|
||
|
|
val_split: 0.05
|
||
|
|
- humaneval_mbpp_testgen_qa:
|
||
|
|
val_split: 0.05
|
||
|
|
- grade_school_math_instructions:
|
||
|
|
val_split: 0.05
|
||
|
|
- recipes:
|
||
|
|
val_split: 0.05
|
||
|
|
- cmu_wiki_qa:
|
||
|
|
val_split: 0.05
|
||
|
|
- oa_wiki_qa_bart_10000row:
|
||
|
|
val_split: 0.05
|
||
|
|
max_val_set: 250
|
||
|
|
- prosocial_dialogue:
|
||
|
|
fraction: 0.1
|
||
|
|
max_val_set: 250
|
||
|
|
- explain_prosocial:
|
||
|
|
fraction: 0.075
|
||
|
|
max_val_set: 250
|
||
|
|
- soda:
|
||
|
|
fraction: 0.25
|
||
|
|
max_val_set: 1000
|
||
|
|
- oa_leet10k:
|
||
|
|
val_split: 0.05
|
||
|
|
max_val_set: 250
|
||
|
|
- dolly15k:
|
||
|
|
val_split: 0.05
|
||
|
|
max_val_set: 300
|
||
|
|
```
|
||
|
|
|
||
|
|
|
||
|
|
Pythia:
|
||
|
|
```
|
||
|
|
pythia-12b-pretrain:
|
||
|
|
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
|
||
|
|
warmup_steps: 100
|
||
|
|
gradient_checkpointing: true
|
||
|
|
gradient_accumulation_steps: 4
|
||
|
|
per_device_train_batch_size: 4
|
||
|
|
per_device_eval_batch_size: 4
|
||
|
|
eval_steps: 251
|
||
|
|
save_steps: 500
|
||
|
|
num_train_epochs: 1
|
||
|
|
save_total_limit: 2
|
||
|
|
deepspeed_config: configs/zero_config_pretrain.json
|
||
|
|
```
|
||
|
|
|
||
|
|
|
||
|
|
Command used: `deepspeed trainer_sft.py --show_dataset_stats --configs defaults pythia-12b-pretrain pretrain --cache_dir .cache/ --output_dir .saved/pythia-12b-super-pretrain2 --deepspeed`
|