distilgpt2-HC3/README.md

language, license, library_name, tags, datasets, metrics, widget, inference, pipeline_tag, model-index

language	license	library_name	tags	datasets	metrics	widget	inference	pipeline_tag	model-index
en	apache-2.0	transformers	generated_from_trainer chatgpt HC3	pszemraj/HC3-textgen-qa	accuracy	text example_title Review: Best cast iron skillet you will ever buy. Is this review positive or negative? <answer> Sentiment analysis text example_title Barack Obama nominated Hilary Clinton as his secretary of state on Monday. He chose her because <answer> Coreference resolution text example_title On a shelf, there are five books: a gray book, a red book, a purple book, a blue book, and a black book. Here's the puzzle, <answer> Logic puzzles text example_title The two men running to become New York City's next mayor will face off in their first debate Wednesday night <answer> Reading comprehension text example_title Is it true that if I have five 5-hour energy drinks in a single 24-hour period, I get 25 hours of energy and spontaneously explode? <answer> 5 hour energy text example_title what happens if you train a smaller model on a dataset of reinforcement-learning optimized model responses? <answer> deep learning advice	parameters temperature max_length no_repeat_ngram_size repetition_penalty eta_cutoff renormalize_logits 0.6 96 4 1.5 0.0008 true	text-generation	name results distilgpt2-HC3

distilgpt2-HC3

what happens if you train a smaller model on a dataset of chatGPT responses?

This happens.

Model description

This model is a fine-tuned version of distilgpt2 on the "chatgpt answers" column of the Hello-SimpleAI/HC3 dataset.

It achieves the following results on the evaluation set:

• Loss: 1.9983
• Accuracy: 0.5441

Intended uses & limitations

Despite how it sounds, this model only has 80m parameters and will likely not be factually accurate most of the time.

Training and evaluation data

Modifications made w.r.t. original dataset:

• drop all rows that did not have a chatGPT answer
• if a row (i.e. ELI5 question, etc) had more than one response (from chatGPT), randomly choose one of the responses as the answer to the question
• the "question" and chatGPT answer were combined into a single string for that row as follows: QUESTION_TEXT <answer> CHATGPT_ANSWER_TEXT <end_answer>
  • <answer> and <end_answer> serve as added tokens to help the model learn "turns" in the conversation

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.001
• train_batch_size: 8
• eval_batch_size: 4
• seed: 3208
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 6.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.2485	0.98	41	2.1457	0.5158
2.0757	1.98	82	2.0584	0.5304
1.966	2.98	123	2.0210	0.5376
1.8602	3.98	164	2.0012	0.5422
1.8089	4.98	205	1.9977	0.5436
1.7698	5.98	246	1.9983	0.5441

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.11.0+cu113
• Datasets 2.6.1
• Tokenizers 0.12.1

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	28.18
AI2 Reasoning Challenge (25-Shot)	24.66
HellaSwag (10-Shot)	27.99
MMLU (5-Shot)	23.95
TruthfulQA (0-shot)	42.10
Winogrande (5-shot)	50.36
GSM8k (5-shot)	0.00