Upload evaluation_results.json with huggingface_hub

evaluation_results.json

@@ -2,10 +2,10 @@
   "results": {
     "gsm8k": {
       "alias": "gsm8k",
-      "exact_match,strict-match": 0.33434420015163,
-      "exact_match_stderr,strict-match": 0.012994634003332766,
-      "exact_match,flexible-extract": 0.3366186504927976,
-      "exact_match_stderr,flexible-extract": 0.01301646367998336
+      "exact_match,strict-match": 0.34950720242608035,
+      "exact_match_stderr,strict-match": 0.013133836511705991,
+      "exact_match,flexible-extract": 0.3555724033358605,
+      "exact_match_stderr,flexible-extract": 0.013185402252713849
     }
   },
   "group_subtasks": {
@@ -125,7 +125,7 @@
     "fewshot_seed": 1234
   },
   "git_hash": "3c710e0",
-  "date": 1762166557.6260943,
+  "date": 1762181122.5749974,
   "pretty_env_info": "PyTorch version: 2.8.0+cu128\nIs debug build: False\nCUDA used to build PyTorch: 12.8\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.5 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04.2) 11.4.0\nClang version: Could not collect\nCMake version: version 3.22.1\nLibc version: glibc-2.35\n\nPython version: 3.10.19 | packaged by conda-forge | (main, Oct 22 2025, 22:29:10) [GCC 14.3.0] (64-bit runtime)\nPython platform: Linux-6.8.0-79-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 11.5.119\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: GPU 0: NVIDIA RTX 6000 Ada Generation\nNvidia driver version: 580.82.07\ncuDNN version: Probably one of the following:\n/usr/local/cuda-12.1/targets/x86_64-linux/lib/libcudnn.so.8.9.7\n/usr/local/cuda-12.1/targets/x86_64-linux/lib/libcudnn_adv_infer.so.8.9.7\n/usr/local/cuda-12.1/targets/x86_64-linux/lib/libcudnn_adv_train.so.8.9.7\n/usr/local/cuda-12.1/targets/x86_64-linux/lib/libcudnn_cnn_infer.so.8.9.7\n/usr/local/cuda-12.1/targets/x86_64-linux/lib/libcudnn_cnn_train.so.8.9.7\n/usr/local/cuda-12.1/targets/x86_64-linux/lib/libcudnn_ops_infer.so.8.9.7\n/usr/local/cuda-12.1/targets/x86_64-linux/lib/libcudnn_ops_train.so.8.9.7\n/usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudnn.so.8.9.7\n/usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudnn_adv_infer.so.8.9.7\n/usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudnn_adv_train.so.8.9.7\n/usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudnn_cnn_infer.so.8.9.7\n/usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudnn_cnn_train.so.8.9.7\n/usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudnn_ops_infer.so.8.9.7\n/usr/local/cuda-12.2/targets/x86_64-linux/lib/libcudnn_ops_train.so.8.9.7\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture:                         x86_64\nCPU op-mode(s):                       32-bit, 64-bit\nAddress sizes:                        48 bits physical, 48 bits virtual\nByte Order:                           Little Endian\nCPU(s):                               32\nOn-line CPU(s) list:                  0-31\nVendor ID:                            AuthenticAMD\nModel name:                           AMD Ryzen Threadripper PRO 5955WX 16-Cores\nCPU family:                           25\nModel:                                8\nThread(s) per core:                   2\nCore(s) per socket:                   16\nSocket(s):                            1\nStepping:                             2\nFrequency boost:                      enabled\nCPU max MHz:                          4000.0000\nCPU min MHz:                          1800.0000\nBogoMIPS:                             7985.05\nFlags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin brs arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm debug_swap\nVirtualization:                       AMD-V\nL1d cache:                            512 KiB (16 instances)\nL1i cache:                            512 KiB (16 instances)\nL2 cache:                             8 MiB (16 instances)\nL3 cache:                             64 MiB (2 instances)\nNUMA node(s):                         1\nNUMA node0 CPU(s):                    0-31\nVulnerability Gather data sampling:   Not affected\nVulnerability Itlb multihit:          Not affected\nVulnerability L1tf:                   Not affected\nVulnerability Mds:                    Not affected\nVulnerability Meltdown:               Not affected\nVulnerability Mmio stale data:        Not affected\nVulnerability Reg file data sampling: Not affected\nVulnerability Retbleed:               Not affected\nVulnerability Spec rstack overflow:   Vulnerable: Safe RET, no microcode\nVulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl\nVulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:             Mitigation; Retpolines; IBPB conditional; IBRS_FW; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\nVulnerability Srbds:                  Not affected\nVulnerability Tsx async abort:        Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==2.2.6\n[pip3] nvidia-cublas-cu12==12.8.4.1\n[pip3] nvidia-cuda-cupti-cu12==12.8.90\n[pip3] nvidia-cuda-nvrtc-cu12==12.8.93\n[pip3] nvidia-cuda-runtime-cu12==12.8.90\n[pip3] nvidia-cudnn-cu12==9.10.2.21\n[pip3] nvidia-cufft-cu12==11.3.3.83\n[pip3] nvidia-curand-cu12==10.3.9.90\n[pip3] nvidia-cusolver-cu12==11.7.3.90\n[pip3] nvidia-cusparse-cu12==12.5.8.93\n[pip3] nvidia-cusparselt-cu12==0.7.1\n[pip3] nvidia-nccl-cu12==2.27.3\n[pip3] nvidia-nvjitlink-cu12==12.8.93\n[pip3] nvidia-nvtx-cu12==12.8.90\n[pip3] torch==2.8.0\n[pip3] torchaudio==2.8.0\n[pip3] torchvision==0.23.0\n[pip3] triton==3.4.0\n[conda] numpy                                2.2.6            pypi_0              pypi\n[conda] nvidia-cublas-cu12                   12.8.4.1         pypi_0              pypi\n[conda] nvidia-cuda-cupti-cu12               12.8.90          pypi_0              pypi\n[conda] nvidia-cuda-nvrtc-cu12               12.8.93          pypi_0              pypi\n[conda] nvidia-cuda-runtime-cu12             12.8.90          pypi_0              pypi\n[conda] nvidia-cudnn-cu12                    9.10.2.21        pypi_0              pypi\n[conda] nvidia-cufft-cu12                    11.3.3.83        pypi_0              pypi\n[conda] nvidia-curand-cu12                   10.3.9.90        pypi_0              pypi\n[conda] nvidia-cusolver-cu12                 11.7.3.90        pypi_0              pypi\n[conda] nvidia-cusparse-cu12                 12.5.8.93        pypi_0              pypi\n[conda] nvidia-cusparselt-cu12               0.7.1            pypi_0              pypi\n[conda] nvidia-nccl-cu12                     2.27.3           pypi_0              pypi\n[conda] nvidia-nvjitlink-cu12                12.8.93          pypi_0              pypi\n[conda] nvidia-nvtx-cu12                     12.8.90          pypi_0              pypi\n[conda] torch                                2.8.0            pypi_0              pypi\n[conda] torchaudio                           2.8.0            pypi_0              pypi\n[conda] torchvision                          0.23.0           pypi_0              pypi\n[conda] triton                               3.4.0            pypi_0              pypi",
   "transformers_version": "4.57.1",
   "lm_eval_version": "0.4.9.1",
@@ -153,7 +153,7 @@
   "fewshot_as_multiturn": false,
   "chat_template": null,
   "chat_template_sha": null,
-  "start_time": 4828492.248598479,
-  "end_time": 4828605.615266261,
-  "total_evaluation_time_seconds": "113.3666677819565"
+  "start_time": 4843057.177305116,
+  "end_time": 4843164.274402437,
+  "total_evaluation_time_seconds": "107.09709732048213"
 }