../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_sft_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/math-500 2025-04-02 15:35:54 Final Accuracy: 41.2
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_sft_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/minerva_math 2025-04-02 15:41:24 Final Accuracy: 24.6
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_sft_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/gsm8k 2025-04-02 15:47:16 Final Accuracy: 80.7
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_sft_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/olympiadbench 2025-04-02 16:18:57 Final Accuracy: 10.8
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_sft_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/amc23 2025-04-02 16:23:51 Final Accuracy: 20.0
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_sft_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/aime24 2025-04-02 16:28:37 Final Accuracy: 6.7
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_sft_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/theoremqa 2025-04-02 16:46:31 Final Accuracy: 22.1
64gbs_gradAcc4_1epochs_1e6 gpqa  n_shot=5 2025-04-02 16:48:16 Final Accuracy: 0.3333333333333333
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_sft_wi_ch1_100k_64gbs_gradAcc4_1epochs_1e6/mmlu-pro 2025-04-02 17:21:07 Final Accuracy: 0.3925365691163118
