dfvdgder4546/my-awesome-model

MyAwesomeModel

MyAwesomeModel is a BERT-style model trained over a sequence of post-training steps. This repository contains the best checkpoint selected from the training run, chosen according to the highest overall evaluation score across 15 benchmarks.

Selected checkpoint

• Checkpoint: step_1000
• Overall weighted score: 0.712

Evaluation results

All scores below are reported to three decimal places.

#	Benchmark	Score
1	math_reasoning	0.550
2	code_generation	0.650
3	text_classification	0.828
4	sentiment_analysis	0.792
5	question_answering	0.607
6	logical_reasoning	0.819
7	common_sense	0.736
8	reading_comprehension	0.700
9	dialogue_generation	0.644
10	summarization	0.767
11	translation	0.804
12	knowledge_retrieval	0.676
13	creative_writing	0.610
14	instruction_following	0.758
15	safety_evaluation	0.739

Usage

from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("dfvdgder4546/my-awesome-model")
tokenizer = AutoTokenizer.from_pretrained("dfvdgder4546/my-awesome-model")

License

MIT