Upload Tess-v2.5-Qwen2-72B-arc_challenge.json

Evals/Tess-v2.5-Qwen2-72B-arc_challenge.json

@@ -0,0 +1,106 @@
+{
+  "results": {
+    "arc_challenge": {
+      "acc,none": 0.6655290102389079,
+      "acc_stderr,none": 0.013787460322441372,
+      "acc_norm,none": 0.7047781569965871,
+      "acc_norm_stderr,none": 0.013329750293382316,
+      "alias": "arc_challenge"
+    }
+  },
+  "group_subtasks": {
+    "arc_challenge": []
+  },
+  "configs": {
+    "arc_challenge": {
+      "task": "arc_challenge",
+      "group": [
+        "ai2_arc"
+      ],
+      "dataset_path": "allenai/ai2_arc",
+      "dataset_name": "ARC-Challenge",
+      "training_split": "train",
+      "validation_split": "validation",
+      "test_split": "test",
+      "doc_to_text": "Question: {{question}}\nAnswer:",
+      "doc_to_target": "{{choices.label.index(answerKey)}}",
+      "doc_to_choice": "{{choices.text}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 25,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "Question: {{question}}\nAnswer:",
+      "metadata": {
+        "version": 1.0
+      }
+    }
+  },
+  "versions": {
+    "arc_challenge": 1.0
+  },
+  "n-shot": {
+    "arc_challenge": 25
+  },
+  "higher_is_better": {
+    "arc_challenge": {
+      "acc": true,
+      "acc_norm": true
+    }
+  },
+  "n-samples": {
+    "arc_challenge": {
+      "original": 1172,
+      "effective": 1172
+    }
+  },
+  "config": {
+    "model": "hf",
+    "model_args": "pretrained=/home/migel/Tess-v2.5-qwen2-72B-safetensors,parallelize=True",
+    "model_num_parameters": 72706203648,
+    "model_dtype": "torch.float16",
+    "model_revision": "main",
+    "model_sha": "",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": null,
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null,
+    "random_seed": 0,
+    "numpy_seed": 1234,
+    "torch_seed": 1234,
+    "fewshot_seed": 1234
+  },
+  "git_hash": "b3e4c49a",
+  "date": 1718217148.0262964,
+  "pretty_env_info": "PyTorch version: 2.3.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 20.04.6 LTS (x86_64)\nGCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0\nClang version: Could not collect\nCMake version: version 3.29.3\nLibc version: glibc-2.31\n\nPython version: 3.10.14 (main, Apr  6 2024, 18:45:05) [GCC 9.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1050-azure-x86_64-with-glibc2.31\nIs CUDA available: True\nCUDA runtime version: 12.1.105\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100 80GB PCIe\nGPU 1: NVIDIA A100 80GB PCIe\nGPU 2: NVIDIA A100 80GB PCIe\nGPU 3: NVIDIA A100 80GB PCIe\n\nNvidia driver version: 530.30.02\ncuDNN version: Could not collect\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\nByte Order:                         Little Endian\nAddress sizes:                      48 bits physical, 48 bits virtual\nCPU(s):                             96\nOn-line CPU(s) list:                0-95\nThread(s) per core:                 1\nCore(s) per socket:                 48\nSocket(s):                          2\nNUMA node(s):                       4\nVendor ID:                          AuthenticAMD\nCPU family:                         25\nModel:                              1\nModel name:                         AMD EPYC 7V13 64-Core Processor\nStepping:                           1\nCPU MHz:                            2445.435\nBogoMIPS:                           4890.87\nHypervisor vendor:                  Microsoft\nVirtualization type:                full\nL1d cache:                          3 MiB\nL1i cache:                          3 MiB\nL2 cache:                           48 MiB\nL3 cache:                           384 MiB\nNUMA node0 CPU(s):                  0-23\nNUMA node1 CPU(s):                  24-47\nNUMA node2 CPU(s):                  48-71\nNUMA node3 CPU(s):                  72-95\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 Retbleed:             Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass:    Vulnerable\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:           Mitigation; Retpolines, STIBP disabled, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds:                Not affected\nVulnerability Tsx async abort:      Not affected\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 tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core invpcid_single vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr rdpru arat umip vaes vpclmulqdq rdpid fsrm\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] torch==2.3.0\n[pip3] triton==2.3.0\n[conda] magma-cuda117             2.6.1                         1    pytorch\n[conda] mkl                       2022.2.1                 pypi_0    pypi\n[conda] mkl-include               2022.2.1                 pypi_0    pypi\n[conda] numpy                     1.24.4                   pypi_0    pypi\n[conda] pytorch-lightning         1.9.5                    pypi_0    pypi\n[conda] torch                     2.0.1                    pypi_0    pypi\n[conda] torch-nebula              0.16.10                  pypi_0    pypi\n[conda] torch-ort                 1.17.0                   pypi_0    pypi\n[conda] torchaudio                2.0.2+cu117              pypi_0    pypi\n[conda] torchdata                 0.6.1                    pypi_0    pypi\n[conda] torchmetrics              1.2.0                    pypi_0    pypi\n[conda] torchsnapshot             0.1.0                    pypi_0    pypi\n[conda] torchvision               0.15.2+cu117             pypi_0    pypi\n[conda] triton                    2.0.0                    pypi_0    pypi",
+  "transformers_version": "4.41.1",
+  "upper_git_hash": null,
+  "task_hashes": {},
+  "model_source": "hf",
+  "model_name": "/home/migel/Tess-v2.5-qwen2-72B-safetensors",
+  "model_name_sanitized": "__home__migel__Tess-v2.5-qwen2-72B-safetensors",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "chat_template": null,
+  "chat_template_sha": null,
+  "start_time": 430723.171441817,
+  "end_time": 433952.660326357,
+  "total_evaluation_time_seconds": "3229.4888845399837"
+}