Upload EleutherAI/pythia-70m/step_1000 with huggingface_hub

EleutherAI/pythia-70m/step_1000

@@ -1,5 +1,12 @@
 {
   "results": {
+    "hellaswag": {
+      "alias": "hellaswag",
+      "acc,none": 0.25791674965146383,
+      "acc_stderr,none": 0.004365938407209563,
+      "acc_norm,none": 0.25891256721768574,
+      "acc_norm_stderr,none": 0.004371422731216448
+    },
     "sciq": {
       "alias": "sciq",
       "acc,none": 0.453,
@@ -9,9 +16,48 @@
     }
   },
   "group_subtasks": {
+    "hellaswag": [],
     "sciq": []
   },
   "configs": {
+    "hellaswag": {
+      "task": "hellaswag",
+      "tag": [
+        "multiple_choice"
+      ],
+      "dataset_path": "hellaswag",
+      "dataset_kwargs": {
+        "trust_remote_code": true
+      },
+      "training_split": "train",
+      "validation_split": "validation",
+      "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n    def _process_doc(doc):\n        ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n        out_doc = {\n            \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n            \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n            \"gold\": int(doc[\"label\"]),\n        }\n        return out_doc\n\n    return dataset.map(_process_doc)\n",
+      "doc_to_text": "{{query}}",
+      "doc_to_target": "{{label}}",
+      "doc_to_choice": "choices",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "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": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
     "sciq": {
       "task": "sciq",
       "dataset_path": "sciq",
@@ -47,12 +93,18 @@
     }
   },
   "versions": {
+    "hellaswag": 1.0,
     "sciq": 1.0
   },
   "n-shot": {
+    "hellaswag": 0,
     "sciq": 0
   },
   "higher_is_better": {
+    "hellaswag": {
+      "acc": true,
+      "acc_norm": true
+    },
     "sciq": {
       "acc": true,
       "acc_norm": true
@@ -62,6 +114,10 @@
     "sciq": {
       "original": 1000,
       "effective": 1000
+    },
+    "hellaswag": {
+      "original": 10042,
+      "effective": 10042
     }
   },
   "config": {
@@ -84,7 +140,7 @@
     "fewshot_seed": 1234
   },
   "git_hash": "a5b7c41",
-  "date": 1729860041.9080117,
+  "date": 1729863976.1801896,
   "pretty_env_info": "PyTorch version: 2.5.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: 14.0.0-1ubuntu1.1\nCMake version: version 3.30.5\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-6.1.85+-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.140\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: GPU 0: Tesla T4\nNvidia driver version: 535.104.05\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.6\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:                        46 bits physical, 48 bits virtual\nByte Order:                           Little Endian\nCPU(s):                               2\nOn-line CPU(s) list:                  0,1\nVendor ID:                            GenuineIntel\nModel name:                           Intel(R) Xeon(R) CPU @ 2.00GHz\nCPU family:                           6\nModel:                                85\nThread(s) per core:                   2\nCore(s) per socket:                   1\nSocket(s):                            1\nStepping:                             3\nBogoMIPS:                             4000.42\nFlags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves arat md_clear arch_capabilities\nHypervisor vendor:                    KVM\nVirtualization type:                  full\nL1d cache:                            32 KiB (1 instance)\nL1i cache:                            32 KiB (1 instance)\nL2 cache:                             1 MiB (1 instance)\nL3 cache:                             38.5 MiB (1 instance)\nNUMA node(s):                         1\nNUMA node0 CPU(s):                    0,1\nVulnerability Gather data sampling:   Not affected\nVulnerability Itlb multihit:          Not affected\nVulnerability L1tf:                   Mitigation; PTE Inversion\nVulnerability Mds:                    Vulnerable; SMT Host state unknown\nVulnerability Meltdown:               Vulnerable\nVulnerability Mmio stale data:        Vulnerable\nVulnerability Reg file data sampling: Not affected\nVulnerability Retbleed:               Vulnerable\nVulnerability Spec rstack overflow:   Not affected\nVulnerability Spec store bypass:      Vulnerable\nVulnerability Spectre v1:             Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers\nVulnerability Spectre v2:             Vulnerable; IBPB: disabled; STIBP: disabled; PBRSB-eIBRS: Not affected; BHI: Vulnerable (Syscall hardening enabled)\nVulnerability Srbds:                  Not affected\nVulnerability Tsx async abort:        Vulnerable\n\nVersions of relevant libraries:\n[pip3] mypy==1.13.0\n[pip3] mypy-extensions==1.0.0\n[pip3] numpy==1.26.4\n[pip3] optree==0.13.0\n[pip3] torch==2.5.0+cu121\n[pip3] torchaudio==2.5.0+cu121\n[pip3] torchsummary==1.5.1\n[pip3] torchvision==0.20.0+cu121\n[conda] Could not collect",
   "transformers_version": "4.44.2",
   "upper_git_hash": null,
@@ -111,7 +167,7 @@
   "fewshot_as_multiturn": false,
   "chat_template": null,
   "chat_template_sha": null,
-  "start_time": 963.243977508,
-  "end_time": 1001.396068859,
-  "total_evaluation_time_seconds": "38.15209135100008"
+  "start_time": 4897.618315607,
+  "end_time": 5076.044570935,
+  "total_evaluation_time_seconds": "178.42625532799957"
 }