Today
-
Save plain SFT/RL code-heavy__8m__partial_gsm8k
-
Save plain SFT/RL code-heavy__8m__python_syntax
-
Save plain SFT/RL chat-heavy__64m__reward_modeling
-
Save plain SFT/RL chat-heavy__16m__regex
-
Save plain SFT/RL math-heavy__8m__reward_modeling
-
Save plain SFT/RL code-heavy__8m__make_sentence
-
Save plain SFT/RL math-heavy__16m__cube
-
Save plain SFT/RL code-heavy__8m__brackets
-
Save plain SFT/RL chat-heavy__16m__chess
-
Save plain SFT/RL code-heavy__8m__arithmetic_simple
-
Save plain SFT/RL chat-heavy__16m__mmlu
-
Save plain SFT/RL chat-heavy__32m__mmlu
-
Save plain SFT/RL math-heavy__8m__latex
-
Save plain SFT/RL chat-heavy__64m__cube
-
Save plain SFT/RL chat-heavy__64m__arithmetic_simple
-
Save plain SFT/RL chat-heavy__64m__mbpp_docstring
-
Save plain SFT/RL chat-heavy__64m__latex
-
Save plain SFT/RL code-heavy__8m__mbpp_docstring
-
Save plain SFT/RL chat-heavy__64m__json
-
Save plain SFT/RL chat-heavy__16m__reward_modeling
-
Save plain SFT/RL chat-heavy__8m__cube
-
Save plain SFT/RL web-heavy__64m__latex
-
Save plain SFT/RL chat-heavy__64m__arithmetic
-
Save plain SFT/RL web-heavy__32m__json
-
Save plain SFT/RL chat-heavy__32m__mbpp_docstring
-
Save plain SFT/RL math-heavy__32m__cube
-
Save plain SFT/RL chat-heavy__64m__mbpp
-
Save plain SFT/RL chat-heavy__32m__reward_modeling
-
Save plain SFT/RL chat-heavy__32m__arithmetic
-
Save plain SFT/RL web-heavy__32m__math
-
Save plain SFT/RL chat-heavy__8m__mmlu
-
Save plain SFT/RL code-heavy__8m__gsm8k
-
Save plain SFT/RL chat-heavy__16m__brackets
-
Save plain SFT/RL web-heavy__64m__reward_modeling
-
Save plain SFT/RL web-heavy__64m__chat
-
Save plain SFT/RL chat-heavy__16m__json
-
Save plain SFT/RL code-heavy__8m__json
-
Save plain SFT/RL chat-heavy__64m__chess
-
Save plain SFT/RL chat-heavy__32m__chess
-
Save plain SFT/RL chat-heavy__32m__gsm8k
-
Save plain SFT/RL chat-heavy__64m__python_syntax
-
Save plain SFT/RL web-heavy__8m__latex
-
Save plain SFT/RL chat-heavy__64m__mbpp
-
Save plain SFT/RL web-heavy__64m__cube
-
Save plain SFT/RL chat-heavy__64m__brackets
-
Save plain SFT/RL code-heavy__8m__mbpp
-
Save plain SFT/RL chat-heavy__16m__mbpp
-
Save plain SFT/RL code-heavy__8m__arithmetic
-
Save plain SFT/RL code-heavy__8m__python_syntax
-
Save plain SFT/RL code-heavy__8m__partial_gsm8k