Upload pawsx_0.4.8_results_2025-03-18T13-56-32.464817.json

lm_eval/Qwen__Qwen2.5-7B/0.4.8/pawsx_0.4.8_results_2025-03-18T13-56-32.464817.json

@@ -0,0 +1,394 @@
+{
+  "results": {
+    "pawsx": {
+      "acc,none": 0.5892857142857143,
+      "acc_stderr,none": 0.004124430121757617,
+      "alias": "pawsx"
+    },
+    "paws_de": {
+      "alias": " - paws_de",
+      "acc,none": 0.648,
+      "acc_stderr,none": 0.010681996654477083
+    },
+    "paws_en": {
+      "alias": " - paws_en",
+      "acc,none": 0.6495,
+      "acc_stderr,none": 0.01067154233969731
+    },
+    "paws_es": {
+      "alias": " - paws_es",
+      "acc,none": 0.6445,
+      "acc_stderr,none": 0.010705941508891127
+    },
+    "paws_fr": {
+      "alias": " - paws_fr",
+      "acc,none": 0.615,
+      "acc_stderr,none": 0.010883323176386978
+    },
+    "paws_ja": {
+      "alias": " - paws_ja",
+      "acc,none": 0.473,
+      "acc_stderr,none": 0.01116681910502999
+    },
+    "paws_ko": {
+      "alias": " - paws_ko",
+      "acc,none": 0.5385,
+      "acc_stderr,none": 0.01114993432795706
+    },
+    "paws_zh": {
+      "alias": " - paws_zh",
+      "acc,none": 0.5565,
+      "acc_stderr,none": 0.011111507899646485
+    }
+  },
+  "groups": {
+    "pawsx": {
+      "acc,none": 0.5892857142857143,
+      "acc_stderr,none": 0.004124430121757617,
+      "alias": "pawsx"
+    }
+  },
+  "group_subtasks": {
+    "pawsx": [
+      "paws_en",
+      "paws_de",
+      "paws_es",
+      "paws_fr",
+      "paws_ja",
+      "paws_ko",
+      "paws_zh"
+    ]
+  },
+  "configs": {
+    "paws_de": {
+      "task": "paws_de",
+      "dataset_path": "paws-x",
+      "dataset_name": "de",
+      "training_split": "train",
+      "validation_split": "validation",
+      "test_split": "test",
+      "doc_to_text": "",
+      "doc_to_target": "label",
+      "unsafe_code": false,
+      "doc_to_choice": "{{[sentence1+\", richtig? Nein, \"+sentence2, sentence1+\", richtig? Ja, \"+sentence2]}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "paws_en": {
+      "task": "paws_en",
+      "dataset_path": "paws-x",
+      "dataset_name": "en",
+      "training_split": "train",
+      "validation_split": "validation",
+      "test_split": "test",
+      "doc_to_text": "",
+      "doc_to_target": "label",
+      "unsafe_code": false,
+      "doc_to_choice": "{{[sentence1+\", right? No, \"+sentence2, sentence1+\", right? Yes, \"+sentence2]}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "paws_es": {
+      "task": "paws_es",
+      "dataset_path": "paws-x",
+      "dataset_name": "es",
+      "training_split": "train",
+      "validation_split": "validation",
+      "test_split": "test",
+      "doc_to_text": "",
+      "doc_to_target": "label",
+      "unsafe_code": false,
+      "doc_to_choice": "{{[sentence1+\", verdad? No, \"+sentence2, sentence1+\", verdad? Sí, \"+sentence2]}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "paws_fr": {
+      "task": "paws_fr",
+      "dataset_path": "paws-x",
+      "dataset_name": "fr",
+      "training_split": "train",
+      "validation_split": "validation",
+      "test_split": "test",
+      "doc_to_text": "",
+      "doc_to_target": "label",
+      "unsafe_code": false,
+      "doc_to_choice": "{{[sentence1+\", n'est-ce pas? Non, \"+sentence2, sentence1+\", n'est-ce pas? Oui, \"+sentence2]}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "paws_ja": {
+      "task": "paws_ja",
+      "dataset_path": "paws-x",
+      "dataset_name": "ja",
+      "training_split": "train",
+      "validation_split": "validation",
+      "test_split": "test",
+      "doc_to_text": "",
+      "doc_to_target": "label",
+      "unsafe_code": false,
+      "doc_to_choice": "{{[sentence1+\", ですね? いいえ, \"+sentence2, sentence1+\", ですね? はい, \"+sentence2]}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "paws_ko": {
+      "task": "paws_ko",
+      "dataset_path": "paws-x",
+      "dataset_name": "ko",
+      "training_split": "train",
+      "validation_split": "validation",
+      "test_split": "test",
+      "doc_to_text": "",
+      "doc_to_target": "label",
+      "unsafe_code": false,
+      "doc_to_choice": "{{[sentence1+\", 맞죠? 아니요, \"+sentence2, sentence1+\", 맞죠? 예, \"+sentence2]}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "paws_zh": {
+      "task": "paws_zh",
+      "dataset_path": "paws-x",
+      "dataset_name": "zh",
+      "training_split": "train",
+      "validation_split": "validation",
+      "test_split": "test",
+      "doc_to_text": "",
+      "doc_to_target": "label",
+      "unsafe_code": false,
+      "doc_to_choice": "{{[sentence1+\", 对吧? 不是, \"+sentence2, sentence1+\", 对吧? 是, \"+sentence2]}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    }
+  },
+  "versions": {
+    "paws_de": 1.0,
+    "paws_en": 1.0,
+    "paws_es": 1.0,
+    "paws_fr": 1.0,
+    "paws_ja": 1.0,
+    "paws_ko": 1.0,
+    "paws_zh": 1.0,
+    "pawsx": 0.0
+  },
+  "n-shot": {
+    "paws_de": 0,
+    "paws_en": 0,
+    "paws_es": 0,
+    "paws_fr": 0,
+    "paws_ja": 0,
+    "paws_ko": 0,
+    "paws_zh": 0
+  },
+  "higher_is_better": {
+    "paws_de": {
+      "acc": true
+    },
+    "paws_en": {
+      "acc": true
+    },
+    "paws_es": {
+      "acc": true
+    },
+    "paws_fr": {
+      "acc": true
+    },
+    "paws_ja": {
+      "acc": true
+    },
+    "paws_ko": {
+      "acc": true
+    },
+    "paws_zh": {
+      "acc": true
+    },
+    "pawsx": {
+      "acc": true
+    }
+  },
+  "n-samples": {
+    "paws_en": {
+      "original": 2000,
+      "effective": 2000
+    },
+    "paws_de": {
+      "original": 2000,
+      "effective": 2000
+    },
+    "paws_es": {
+      "original": 2000,
+      "effective": 2000
+    },
+    "paws_fr": {
+      "original": 2000,
+      "effective": 2000
+    },
+    "paws_ja": {
+      "original": 2000,
+      "effective": 2000
+    },
+    "paws_ko": {
+      "original": 2000,
+      "effective": 2000
+    },
+    "paws_zh": {
+      "original": 2000,
+      "effective": 2000
+    }
+  },
+  "config": {
+    "model": "hf",
+    "model_args": "pretrained=Qwen/Qwen2.5-7B,dtype=float32,trust_remote_code=True",
+    "model_num_parameters": 7615616512,
+    "model_dtype": "torch.float32",
+    "model_revision": "main",
+    "model_sha": "d149729398750b98c0af14eb82c78cfe92750796",
+    "batch_size": "auto",
+    "batch_sizes": [
+      32
+    ],
+    "device": "cuda",
+    "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": null,
+  "date": 1742304929.7642052,
+  "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 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 3.16.3\nLibc version: glibc-2.31\n\nPython version: 3.10.10 (main, Mar 21 2023, 18:45:11) [GCC 11.2.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1077-aws-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: GPU 0: NVIDIA L40S\nNvidia driver version: 535.230.02\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.0\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.0\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.0\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.0\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.0\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.0\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.0\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):                               16\nOn-line CPU(s) list:                  0-15\nThread(s) per core:                   2\nCore(s) per socket:                   8\nSocket(s):                            1\nNUMA node(s):                         1\nVendor ID:                            AuthenticAMD\nCPU family:                           25\nModel:                                1\nModel name:                           AMD EPYC 7R13 Processor\nStepping:                             1\nCPU MHz:                              2649.998\nBogoMIPS:                             5299.99\nHypervisor vendor:                    KVM\nVirtualization type:                  full\nL1d cache:                            256 KiB\nL1i cache:                            256 KiB\nL2 cache:                             4 MiB\nL3 cache:                             32 MiB\nNUMA node0 CPU(s):                    0-15\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:   Mitigation; safe RET, no microcode\nVulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl and seccomp\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\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 tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch topoext invpcid_single ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru wbnoinvd arat npt nrip_save vaes vpclmulqdq rdpid\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] pytorch-lightning==2.5.0.post0\n[pip3] torch==2.5.1+cu121\n[pip3] torchaudio==2.5.1+cu121\n[pip3] torchmetrics==1.3.1\n[pip3] torchvision==0.20.1+cu121\n[pip3] triton==3.1.0\n[conda] numpy                     1.26.4                   pypi_0    pypi\n[conda] pytorch-lightning         2.5.0.post0              pypi_0    pypi\n[conda] torch                     2.5.1+cu121              pypi_0    pypi\n[conda] torchaudio                2.5.1+cu121              pypi_0    pypi\n[conda] torchmetrics              1.3.1                    pypi_0    pypi\n[conda] torchvision               0.20.1+cu121             pypi_0    pypi\n[conda] triton                    3.1.0                    pypi_0    pypi",
+  "transformers_version": "4.49.0",
+  "upper_git_hash": null,
+  "tokenizer_pad_token": [
+    "<|endoftext|>",
+    "151643"
+  ],
+  "tokenizer_eos_token": [
+    "<|endoftext|>",
+    "151643"
+  ],
+  "tokenizer_bos_token": [
+    null,
+    "None"
+  ],
+  "eot_token_id": 151643,
+  "max_length": 131072,
+  "task_hashes": {},
+  "model_source": "hf",
+  "model_name": "Qwen/Qwen2.5-7B",
+  "model_name_sanitized": "Qwen__Qwen2.5-7B",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "fewshot_as_multiturn": false,
+  "chat_template": null,
+  "chat_template_sha": null,
+  "start_time": 106.775862057,
+  "end_time": 1381.904321725,
+  "total_evaluation_time_seconds": "1275.128459668"
+}