safafaf22/MyAwesomeModel-step1000

MyAwesomeModel (step_1000)

This repository holds the best checkpoint of MyAwesomeModel, selected from the workspace training run (checkpoints/step_1000). The selection was made by running the workspace's own evaluation/eval.py pipeline across all 10 checkpoints (step_100 … step_1000); step_1000 achieved the highest weighted overall score.

Selected checkpoint

• Checkpoint: step_1000
• Weighted overall score: 0.712 (highest among all checkpoints)

Evaluation results — all 15 benchmarks (step_1000)

Scores are reported to 3 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

Weighted overall score

The overall score is the weighted average of the 15 benchmark scores, using the weights defined in evaluation/eval.py (reasoning tasks receive extra weight):

• math_reasoning ×1.2, logical_reasoning ×1.2
• code_generation ×1.1, question_answering ×1.1, instruction_following ×1.1, safety_evaluation ×1.1
• reading_comprehension ×1.0, common_sense ×1.0, dialogue_generation ×1.0, summarization ×1.0, translation ×1.0, knowledge_retrieval ×1.0
• text_classification ×0.9, sentiment_analysis ×0.9, creative_writing ×0.9

Weighted overall = 0.712.