Delete lm_eval/Qwen__Qwen2.5-7B/0.4.8/pawsx_results_2025-03-18T10-30-34.862496.json

lm_eval/Qwen__Qwen2.5-7B/0.4.8/pawsx_results_2025-03-18T10-30-34.862496.json

@@ -1,394 +0,0 @@
-{
-  "results": {
-    "pawsx": {
-      "acc,none": 0.5646428571428571,
-      "acc_stderr,none": 0.004161968268437977,
-      "alias": "pawsx"
-    },
-    "paws_de": {
-      "alias": " - paws_de",
-      "acc,none": 0.6045,
-      "acc_stderr,none": 0.010936163625212344
-    },
-    "paws_en": {
-      "alias": " - paws_en",
-      "acc,none": 0.653,
-      "acc_stderr,none": 0.01064669789596951
-    },
-    "paws_es": {
-      "alias": " - paws_es",
-      "acc,none": 0.611,
-      "acc_stderr,none": 0.010904079487730011
-    },
-    "paws_fr": {
-      "alias": " - paws_fr",
-      "acc,none": 0.5665,
-      "acc_stderr,none": 0.011083785461207571
-    },
-    "paws_ja": {
-      "alias": " - paws_ja",
-      "acc,none": 0.471,
-      "acc_stderr,none": 0.011164310140373722
-    },
-    "paws_ko": {
-      "alias": " - paws_ko",
-      "acc,none": 0.511,
-      "acc_stderr,none": 0.011180429374603775
-    },
-    "paws_zh": {
-      "alias": " - paws_zh",
-      "acc,none": 0.5355,
-      "acc_stderr,none": 0.011154913314119561
-    }
-  },
-  "groups": {
-    "pawsx": {
-      "acc,none": 0.5646428571428571,
-      "acc_stderr,none": 0.004161968268437977,
-      "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=HuggingFaceTB/SmolLM2-1.7B,dtype=float32,trust_remote_code=True",
-    "model_num_parameters": 1711376384,
-    "model_dtype": "torch.float32",
-    "model_revision": "main",
-    "model_sha": "effd688a12921b4cc83e3312b6feb579f70f9c71",
-    "batch_size": "auto",
-    "batch_sizes": [
-      16
-    ],
-    "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": 1742291512.9980397,
-  "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 3.31.2\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-6.6.56+-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: \nGPU 0: Tesla T4\nGPU 1: Tesla T4\n\nNvidia driver version: 560.35.03\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):                               4\nOn-line CPU(s) list:                  0-3\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:                   2\nSocket(s):                            1\nStepping:                             3\nBogoMIPS:                             4000.30\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 pti 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:                            64 KiB (2 instances)\nL1i cache:                            64 KiB (2 instances)\nL2 cache:                             2 MiB (2 instances)\nL3 cache:                             38.5 MiB (1 instance)\nNUMA node(s):                         1\nNUMA node0 CPU(s):                    0-3\nVulnerability Gather data sampling:   Not affected\nVulnerability Itlb multihit:          Not affected\nVulnerability L1tf:                   Mitigation; PTE Inversion\nVulnerability Mds:                    Mitigation; Clear CPU buffers; SMT Host state unknown\nVulnerability Meltdown:               Mitigation; PTI\nVulnerability Mmio stale data:        Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown\nVulnerability Reg file data sampling: Not affected\nVulnerability Retbleed:               Mitigation; IBRS\nVulnerability Spec rstack overflow:   Not affected\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; IBRS; IBPB conditional; STIBP conditional; RSB filling; PBRSB-eIBRS Not affected; BHI SW loop, KVM SW loop\nVulnerability Srbds:                  Not affected\nVulnerability Tsx async abort:        Mitigation; Clear CPU buffers; SMT Host state unknown\n\nVersions of relevant libraries:\n[pip3] mypy-extensions==1.0.0\n[pip3] numpy==1.26.4\n[pip3] onnx==1.17.0\n[pip3] optree==0.13.1\n[pip3] pytorch-ignite==0.5.1\n[pip3] pytorch-lightning==2.5.0.post0\n[pip3] torch==2.5.1+cu121\n[pip3] torchaudio==2.5.1+cu121\n[pip3] torchinfo==1.8.0\n[pip3] torchmetrics==1.6.1\n[pip3] torchsummary==1.5.1\n[pip3] torchtune==0.5.0\n[pip3] torchvision==0.20.1+cu121\n[conda] Could not collect",
-  "transformers_version": "4.47.0",
-  "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": 8192,
-  "task_hashes": {},
-  "model_source": "hf",
-  "model_name": "HuggingFaceTB/SmolLM2-1.7B",
-  "model_name_sanitized": "HuggingFaceTB__SmolLM2-1.7B",
-  "system_instruction": null,
-  "system_instruction_sha": null,
-  "fewshot_as_multiturn": false,
-  "chat_template": null,
-  "chat_template_sha": null,
-  "start_time": 7864.038658229,
-  "end_time": 10202.237625076,
-  "total_evaluation_time_seconds": "2338.1989668470005"
-}