brikdavies
/

qwen1.7B-MMLU-hint-following-RL

Generated from Trainer

Model card Files Files and versions

qwen1.7B-MMLU-hint-following-RL

Commit History

Upload eval_mmlu/eval_base/per_problem.jsonl with huggingface_hub

b1e6253
verified

brikdavies commited on Feb 23

Upload checkpoint-50/adapter_config.json with huggingface_hub

6d59178
verified

brikdavies commited on Feb 23

Upload logs/step_stats.jsonl with huggingface_hub

5aad6d6
verified

brikdavies commited on Feb 23

Upload logs/prompt_stats.jsonl with huggingface_hub

7170853
verified

brikdavies commited on Feb 23

Upload logs/rollouts.jsonl with huggingface_hub

0f0c205
verified

brikdavies commited on Feb 23

Upload README.md with huggingface_hub

5609716
verified

brikdavies commited on Feb 23

Upload config.json with huggingface_hub

86f9d7e
verified

brikdavies commited on Feb 23

Upload training_settings.md with huggingface_hub

242d6fe
verified

brikdavies commited on Feb 23

Upload length_reduction_analysis.md with huggingface_hub

93e6dd2
verified

brikdavies commited on Feb 23

Upload eval_results.md with huggingface_hub

abb7100
verified

brikdavies commited on Feb 23

initial commit

56d6127
verified

brikdavies commited on Feb 23