Delete Tess-v2.5-Qwen2-72B-hellaswag.json
Browse files
Tess-v2.5-Qwen2-72B-hellaswag.json
DELETED
|
@@ -1,104 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"results": {
|
| 3 |
-
"hellaswag": {
|
| 4 |
-
"acc,none": 0.6811392152957578,
|
| 5 |
-
"acc_stderr,none": 0.004650825168905212,
|
| 6 |
-
"acc_norm,none": 0.8729336785500896,
|
| 7 |
-
"acc_norm_stderr,none": 0.0033236659644120307,
|
| 8 |
-
"alias": "hellaswag"
|
| 9 |
-
}
|
| 10 |
-
},
|
| 11 |
-
"group_subtasks": {
|
| 12 |
-
"hellaswag": []
|
| 13 |
-
},
|
| 14 |
-
"configs": {
|
| 15 |
-
"hellaswag": {
|
| 16 |
-
"task": "hellaswag",
|
| 17 |
-
"group": [
|
| 18 |
-
"multiple_choice"
|
| 19 |
-
],
|
| 20 |
-
"dataset_path": "hellaswag",
|
| 21 |
-
"training_split": "train",
|
| 22 |
-
"validation_split": "validation",
|
| 23 |
-
"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",
|
| 24 |
-
"doc_to_text": "{{query}}",
|
| 25 |
-
"doc_to_target": "{{label}}",
|
| 26 |
-
"doc_to_choice": "choices",
|
| 27 |
-
"description": "",
|
| 28 |
-
"target_delimiter": " ",
|
| 29 |
-
"fewshot_delimiter": "\n\n",
|
| 30 |
-
"num_fewshot": 10,
|
| 31 |
-
"metric_list": [
|
| 32 |
-
{
|
| 33 |
-
"metric": "acc",
|
| 34 |
-
"aggregation": "mean",
|
| 35 |
-
"higher_is_better": true
|
| 36 |
-
},
|
| 37 |
-
{
|
| 38 |
-
"metric": "acc_norm",
|
| 39 |
-
"aggregation": "mean",
|
| 40 |
-
"higher_is_better": true
|
| 41 |
-
}
|
| 42 |
-
],
|
| 43 |
-
"output_type": "multiple_choice",
|
| 44 |
-
"repeats": 1,
|
| 45 |
-
"should_decontaminate": false,
|
| 46 |
-
"metadata": {
|
| 47 |
-
"version": 1.0
|
| 48 |
-
}
|
| 49 |
-
}
|
| 50 |
-
},
|
| 51 |
-
"versions": {
|
| 52 |
-
"hellaswag": 1.0
|
| 53 |
-
},
|
| 54 |
-
"n-shot": {
|
| 55 |
-
"hellaswag": 10
|
| 56 |
-
},
|
| 57 |
-
"higher_is_better": {
|
| 58 |
-
"hellaswag": {
|
| 59 |
-
"acc": true,
|
| 60 |
-
"acc_norm": true
|
| 61 |
-
}
|
| 62 |
-
},
|
| 63 |
-
"n-samples": {
|
| 64 |
-
"hellaswag": {
|
| 65 |
-
"original": 10042,
|
| 66 |
-
"effective": 10042
|
| 67 |
-
}
|
| 68 |
-
},
|
| 69 |
-
"config": {
|
| 70 |
-
"model": "hf",
|
| 71 |
-
"model_args": "pretrained=/home/migel/Tess-v2.5-qwen2-72B-safetensors,parallelize=True",
|
| 72 |
-
"model_num_parameters": 72706203648,
|
| 73 |
-
"model_dtype": "torch.float16",
|
| 74 |
-
"model_revision": "main",
|
| 75 |
-
"model_sha": "",
|
| 76 |
-
"batch_size": "8",
|
| 77 |
-
"batch_sizes": [],
|
| 78 |
-
"device": null,
|
| 79 |
-
"use_cache": null,
|
| 80 |
-
"limit": null,
|
| 81 |
-
"bootstrap_iters": 100000,
|
| 82 |
-
"gen_kwargs": null,
|
| 83 |
-
"random_seed": 0,
|
| 84 |
-
"numpy_seed": 1234,
|
| 85 |
-
"torch_seed": 1234,
|
| 86 |
-
"fewshot_seed": 1234
|
| 87 |
-
},
|
| 88 |
-
"git_hash": "b3e4c49a",
|
| 89 |
-
"date": 1718190545.705119,
|
| 90 |
-
"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",
|
| 91 |
-
"transformers_version": "4.41.1",
|
| 92 |
-
"upper_git_hash": null,
|
| 93 |
-
"task_hashes": {},
|
| 94 |
-
"model_source": "hf",
|
| 95 |
-
"model_name": "/home/migel/Tess-v2.5-qwen2-72B-safetensors",
|
| 96 |
-
"model_name_sanitized": "__home__migel__Tess-v2.5-qwen2-72B-safetensors",
|
| 97 |
-
"system_instruction": null,
|
| 98 |
-
"system_instruction_sha": null,
|
| 99 |
-
"chat_template": null,
|
| 100 |
-
"chat_template_sha": null,
|
| 101 |
-
"start_time": 404120.678699121,
|
| 102 |
-
"end_time": 430406.206534399,
|
| 103 |
-
"total_evaluation_time_seconds": "26285.527835278015"
|
| 104 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|