Commit History

add held-out eval results (base/E0/E1)
583a150
verified

Pranav2748 commited on

Add outputs/E1-div-individual/trl_log_history.json
00f44dd
verified

Pranav2748 commited on

Add outputs/E1-div-individual/reward_history.json
5849a4a
verified

Pranav2748 commited on

Add outputs/E1-div-individual/judge_cost.json
5a4f978
verified

Pranav2748 commited on

Add outputs/E1-div-individual/README.md
efa9390
verified

Pranav2748 commited on

Add outputs/E1-div-individual/final
dee4e0a
verified

Pranav2748 commited on

Add outputs/E1-div-individual/checkpoint-300
da87772
verified

Pranav2748 commited on

Add outputs/E1-div-individual/checkpoint-250
aeaf16a
verified

Pranav2748 commited on

Add outputs/E1-div-individual/checkpoint-200
531c70d
verified

Pranav2748 commited on

Add outputs/E1-div-individual/checkpoint-150
6d6b78d
verified

Pranav2748 commited on

Add outputs/ckpt_study
22f9175
verified

Pranav2748 commited on

Add outputs/E1-div-individual/checkpoint-100
19ad5d9
verified

Pranav2748 commited on

Add outputs/E1-div-individual/checkpoint-50
dd78ed2
verified

Pranav2748 commited on

Add outputs/E0-baseline
f23ef2b
verified

Pranav2748 commited on

Add outputs/pool_4b
36dc922
verified

Pranav2748 commited on

Add outputs/pairs_4b
348f33d
verified

Pranav2748 commited on

Add outputs/ckpt_study
cecbbcf
verified

Pranav2748 commited on