Commit History
-
add PDF report generator
Verified signature471fe4d -
refresh model card: E0+E1 complete, held-out eval results
Verified signature22e699a -
add held-out eval results (base/E0/E1)
Verified signature583a150 -
add report.html
Verified signatureef7dec7 -
add NOTES.md
Verified signaturef956591 -
add REPORT.pdf
Verified signature9e03a3f -
Add outputs/E1-div-individual/trl_log_history.json
Verified signature00f44dd -
Add outputs/E1-div-individual/reward_history.json
Verified signature5849a4a -
Add outputs/E1-div-individual/judge_cost.json
Verified signature5a4f978 -
Add outputs/E1-div-individual/README.md
Verified signatureefa9390 -
Add outputs/E1-div-individual/final
Verified signaturedee4e0a -
Add outputs/E1-div-individual/checkpoint-300
Verified signatureda87772 -
Add outputs/E1-div-individual/checkpoint-250
Verified signatureaeaf16a -
Add outputs/E1-div-individual/checkpoint-200
Verified signature531c70d -
Add outputs/E1-div-individual/checkpoint-150
Verified signature6d6b78d -
Add outputs/ckpt_study
Verified signature22f9175 -
Add logs/figures
Verified signatureb072bfe -
Add logs/experiments
Verified signature97995c5 -
Add outputs/E1-div-individual/checkpoint-100
Verified signature19ad5d9 -
Add outputs/E1-div-individual/checkpoint-50
Verified signaturedd78ed2 -
Add outputs/E0-baseline
Verified signaturef23ef2b -
Add outputs/pool_4b
Verified signature36dc922 -
Add outputs/pairs_4b
Verified signature348f33d -
Add prior_run/train.py (API key redacted)
Verified signaturef6ff951 -
Add prior_run
Verified signature670d882 -
Add outputs/ckpt_study
Verified signaturececbbcf -
Add logs/figures
Verified signaturef531b87 -
Add logs/experiments
Verified signature1f4cc19 -
Add src
Verified signaturecbc33fe -
Add data
Verified signature8605f3a -
Add configs
Verified signature1a9a893 -
Add model card
Verified signature89eb5e8 -
initial commit
Verified signature5acd9d3
