Hkang/summarize_sft-test_lm-PPO_BON_with_KL_newrm_12K_seed-42_numex-250
Viewer • Updated • 250 • 3
Hangoo Kang
Hkang
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
TRACE: Capability-Targeted Agentic Training upvoted a paper 7 days ago
SEVerA: Verified Synthesis of Self-Evolving Agents upvoted a paper 4 months ago
BEAVER: An Efficient Deterministic LLM VerifierOrganizations
Hkang/summarize_sft-test_lm-pythia1b-oai-summary-PPO-0KL-newrm_12K_seed-42_numex-250
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-pythia1b-oai-summary-PPO-wKL-secondrm_2_seed-42_numex-250
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_12K_newrm-BON_64
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-pythia1b-oai-summary-PPO-0KL-n163K_seed-42_numex-250
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_3K_re-BON_16
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_3K-BON_32
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_4K-BON_32
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_6K_newrm_re-BON_64
Viewer • Updated • 250 • 2
Hkang/summarize_sft-test_lm-pythia1b-oai-summary-PPO-0KL-80K-bestrm_seed-42_numex-250
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-pythia1b-oai-summary-PPO-0KL-1ep-bestrm_seed-42_numex-250
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-pythia1b-oai-summary-PPO-wKL-1ep-secondrm_seed-42_numex-250
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-pythia1b-oai-summary-PPO-0KL-1ep-secondrm_seed-20_numex-250
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-pythia1b-oai-summary-PPO-0KL-1ep-final_seed-42_numex-1000
Viewer • Updated • 1k • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_6K-BON_128
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_9K-BON_32
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_8K-BON_32
Viewer • Updated • 250 • 1
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_6K-BON_32
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_1K-BON_32
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_9K_BON_only-BON_64
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_8K_BON_only-BON_64
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_6K_BON_only-BON_64
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_64K-BON_16
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_48K-BON_16
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8_32K-BON_16
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_lr3e8-BON_16
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_chosen_ref-BON_64
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-pythia1b-oai-summary-PPO-wKL-1ep-baseline_seed-42_numex-1000
Viewer • Updated • 1k • 2
Hkang/summarize_sft-test_lm-pythia1b-oai-summary-PPO-wKL-1ep-baseline_seed-42_numex-250
Viewer • Updated • 250 • 3
Hkang/summarize_sft-test_lm-pythia1b-oai-summary-PPO-0KL-1ep-baseline_seed-42_numex-250
Viewer • Updated • 250 • 3