../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/math-500 2025-03-31 17:24:22 Final Accuracy: 54.2
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/minerva_math 2025-03-31 17:29:36 Final Accuracy: 33.5
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/gsm8k 2025-03-31 17:34:38 Final Accuracy: 85.7
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/olympiadbench 2025-03-31 17:51:46 Final Accuracy: 23.7
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/amc23 2025-03-31 17:56:00 Final Accuracy: 37.5
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/aime24 2025-03-31 18:00:41 Final Accuracy: 6.7
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/theoremqa 2025-03-31 18:08:54 Final Accuracy: 34.0
64gbs_gradAcc4_1epochs_1e6 gpqa  n_shot=5 2025-04-02 15:14:42 Final Accuracy: 0.35858585858585856
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/mmlu-pro 2025-04-02 15:46:13 Final Accuracy: 0.4030917552856473
