Upload EleutherAI/pythia-410m/step_128 with huggingface_hub

EleutherAI/pythia-410m/step_128

@@ -0,0 +1,119 @@
+{
+  "results": {
+    "piqa": {
+      "alias": "piqa",
+      "acc,none": 0.5310119695321001,
+      "acc_stderr,none": 0.011643363511107454,
+      "acc_norm,none": 0.515233949945593,
+      "acc_norm_stderr,none": 0.011660408257153632
+    }
+  },
+  "group_subtasks": {
+    "piqa": []
+  },
+  "configs": {
+    "piqa": {
+      "task": "piqa",
+      "dataset_path": "piqa",
+      "dataset_kwargs": {
+        "trust_remote_code": true
+      },
+      "training_split": "train",
+      "validation_split": "validation",
+      "doc_to_text": "Question: {{goal}}\nAnswer:",
+      "doc_to_target": "label",
+      "doc_to_choice": "{{[sol1, sol2]}}",
+      "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": true,
+      "doc_to_decontamination_query": "goal",
+      "metadata": {
+        "version": 1.0
+      }
+    }
+  },
+  "versions": {
+    "piqa": 1.0
+  },
+  "n-shot": {
+    "piqa": 0
+  },
+  "higher_is_better": {
+    "piqa": {
+      "acc": true,
+      "acc_norm": true
+    }
+  },
+  "n-samples": {
+    "piqa": {
+      "original": 1838,
+      "effective": 1838
+    }
+  },
+  "config": {
+    "model": "hf",
+    "model_args": "pretrained=EleutherAI/pythia-410m,revision=step128,dtype=float,trust_remote_code=True",
+    "model_num_parameters": 405334016,
+    "model_dtype": "torch.float32",
+    "model_revision": "step128",
+    "model_sha": "37581aa339cb9dd52c6db1029242c47223099ca1",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "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": "2fea05a",
+  "date": 1731708289.1385095,
+  "pretty_env_info": "PyTorch version: 2.5.1+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: NVIDIA A100-SXM4-40GB\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):                               12\nOn-line CPU(s) list:                  0-11\nVendor ID:                            GenuineIntel\nModel name:                           Intel(R) Xeon(R) CPU @ 2.20GHz\nCPU family:                           6\nModel:                                85\nThread(s) per core:                   2\nCore(s) per socket:                   6\nSocket(s):                            1\nStepping:                             7\nBogoMIPS:                             4400.38\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 ibrs_enhanced 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 avx512_vnni md_clear arch_capabilities\nHypervisor vendor:                    KVM\nVirtualization type:                  full\nL1d cache:                            192 KiB (6 instances)\nL1i cache:                            192 KiB (6 instances)\nL2 cache:                             6 MiB (6 instances)\nL3 cache:                             38.5 MiB (1 instance)\nNUMA node(s):                         1\nNUMA node0 CPU(s):                    0-11\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:        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: Vulnerable; 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==0.13.1\n[pip3] torch==2.5.1+cu121\n[pip3] torchaudio==2.5.1+cu121\n[pip3] torchsummary==1.5.1\n[pip3] torchvision==0.20.1+cu121\n[conda] Could not collect",
+  "transformers_version": "4.46.2",
+  "upper_git_hash": null,
+  "tokenizer_pad_token": [
+    "<|endoftext|>",
+    "0"
+  ],
+  "tokenizer_eos_token": [
+    "<|endoftext|>",
+    "0"
+  ],
+  "tokenizer_bos_token": [
+    "<|endoftext|>",
+    "0"
+  ],
+  "eot_token_id": 0,
+  "max_length": 2048,
+  "task_hashes": {},
+  "model_source": "hf",
+  "model_name": "EleutherAI/pythia-410m",
+  "model_name_sanitized": "EleutherAI__pythia-410m",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "fewshot_as_multiturn": false,
+  "chat_template": null,
+  "chat_template_sha": null,
+  "start_time": 2179.441520334,
+  "end_time": 2231.008473813,
+  "total_evaluation_time_seconds": "51.56695347899995"
+}