../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_onlyRefAns_webinstructsub_chunk1_v1_50_150k_64gbs_gradAcc4_1epochs_1e6/math-500 2025-04-02 15:51:22 Final Accuracy: 53.2
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_onlyRefAns_webinstructsub_chunk1_v1_50_150k_64gbs_gradAcc4_1epochs_1e6/minerva_math 2025-04-02 15:57:03 Final Accuracy: 29.0
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_onlyRefAns_webinstructsub_chunk1_v1_50_150k_64gbs_gradAcc4_1epochs_1e6/gsm8k 2025-04-02 16:03:14 Final Accuracy: 82.1
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_onlyRefAns_webinstructsub_chunk1_v1_50_150k_64gbs_gradAcc4_1epochs_1e6/olympiadbench 2025-04-02 16:27:44 Final Accuracy: 15.9
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_onlyRefAns_webinstructsub_chunk1_v1_50_150k_64gbs_gradAcc4_1epochs_1e6/amc23 2025-04-02 16:32:31 Final Accuracy: 17.5
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_onlyRefAns_webinstructsub_chunk1_v1_50_150k_64gbs_gradAcc4_1epochs_1e6/aime24 2025-04-02 16:37:12 Final Accuracy: 6.7
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_onlyRefAns_webinstructsub_chunk1_v1_50_150k_64gbs_gradAcc4_1epochs_1e6/theoremqa 2025-04-02 16:57:10 Final Accuracy: 27.3
64gbs_gradAcc4_1epochs_1e6 gpqa  n_shot=5 2025-04-02 16:59:02 Final Accuracy: 0.3181818181818182
../eval_output_gpu96_noapplychat_lma_answer_16k_csd_packing_llama3p1_8B_Inst_onlyRefAns_webinstructsub_chunk1_v1_50_150k_64gbs_gradAcc4_1epochs_1e6/mmlu-pro 2025-04-02 17:36:16 Final Accuracy: 0.22265624998149466
