Upload EleutherAI/pythia-410m/step_256 with huggingface_hub
Browse files- EleutherAI/pythia-410m/step_256 +33 -26
EleutherAI/pythia-410m/step_256
CHANGED
|
@@ -1,27 +1,28 @@
|
|
| 1 |
{
|
| 2 |
"results": {
|
| 3 |
-
"
|
| 4 |
-
"alias": "
|
| 5 |
-
"acc,none": 0.
|
| 6 |
-
"acc_stderr,none": 0.
|
|
|
|
|
|
|
| 7 |
}
|
| 8 |
},
|
| 9 |
"group_subtasks": {
|
| 10 |
-
"
|
| 11 |
},
|
| 12 |
"configs": {
|
| 13 |
-
"
|
| 14 |
-
"task": "
|
| 15 |
-
"dataset_path": "
|
| 16 |
-
"dataset_name": "winogrande_xl",
|
| 17 |
"dataset_kwargs": {
|
| 18 |
"trust_remote_code": true
|
| 19 |
},
|
| 20 |
"training_split": "train",
|
| 21 |
"validation_split": "validation",
|
| 22 |
-
"doc_to_text": "
|
| 23 |
-
"doc_to_target": "
|
| 24 |
-
"doc_to_choice": "
|
| 25 |
"description": "",
|
| 26 |
"target_delimiter": " ",
|
| 27 |
"fewshot_delimiter": "\n\n",
|
|
@@ -31,32 +32,38 @@
|
|
| 31 |
"metric": "acc",
|
| 32 |
"aggregation": "mean",
|
| 33 |
"higher_is_better": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
}
|
| 35 |
],
|
| 36 |
"output_type": "multiple_choice",
|
| 37 |
"repeats": 1,
|
| 38 |
"should_decontaminate": true,
|
| 39 |
-
"doc_to_decontamination_query": "
|
| 40 |
"metadata": {
|
| 41 |
"version": 1.0
|
| 42 |
}
|
| 43 |
}
|
| 44 |
},
|
| 45 |
"versions": {
|
| 46 |
-
"
|
| 47 |
},
|
| 48 |
"n-shot": {
|
| 49 |
-
"
|
| 50 |
},
|
| 51 |
"higher_is_better": {
|
| 52 |
-
"
|
| 53 |
-
"acc": true
|
|
|
|
| 54 |
}
|
| 55 |
},
|
| 56 |
"n-samples": {
|
| 57 |
-
"
|
| 58 |
-
"original":
|
| 59 |
-
"effective":
|
| 60 |
}
|
| 61 |
},
|
| 62 |
"config": {
|
|
@@ -79,9 +86,9 @@
|
|
| 79 |
"fewshot_seed": 1234
|
| 80 |
},
|
| 81 |
"git_hash": "2fea05a",
|
| 82 |
-
"date":
|
| 83 |
-
"pretty_env_info": "PyTorch version: 2.5.
|
| 84 |
-
"transformers_version": "4.
|
| 85 |
"upper_git_hash": null,
|
| 86 |
"tokenizer_pad_token": [
|
| 87 |
"<|endoftext|>",
|
|
@@ -106,7 +113,7 @@
|
|
| 106 |
"fewshot_as_multiturn": false,
|
| 107 |
"chat_template": null,
|
| 108 |
"chat_template_sha": null,
|
| 109 |
-
"start_time":
|
| 110 |
-
"end_time":
|
| 111 |
-
"total_evaluation_time_seconds": "
|
| 112 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"results": {
|
| 3 |
+
"piqa": {
|
| 4 |
+
"alias": "piqa",
|
| 5 |
+
"acc,none": 0.5315560391730142,
|
| 6 |
+
"acc_stderr,none": 0.01164256771087894,
|
| 7 |
+
"acc_norm,none": 0.5163220892274211,
|
| 8 |
+
"acc_norm_stderr,none": 0.011659606710151782
|
| 9 |
}
|
| 10 |
},
|
| 11 |
"group_subtasks": {
|
| 12 |
+
"piqa": []
|
| 13 |
},
|
| 14 |
"configs": {
|
| 15 |
+
"piqa": {
|
| 16 |
+
"task": "piqa",
|
| 17 |
+
"dataset_path": "piqa",
|
|
|
|
| 18 |
"dataset_kwargs": {
|
| 19 |
"trust_remote_code": true
|
| 20 |
},
|
| 21 |
"training_split": "train",
|
| 22 |
"validation_split": "validation",
|
| 23 |
+
"doc_to_text": "Question: {{goal}}\nAnswer:",
|
| 24 |
+
"doc_to_target": "label",
|
| 25 |
+
"doc_to_choice": "{{[sol1, sol2]}}",
|
| 26 |
"description": "",
|
| 27 |
"target_delimiter": " ",
|
| 28 |
"fewshot_delimiter": "\n\n",
|
|
|
|
| 32 |
"metric": "acc",
|
| 33 |
"aggregation": "mean",
|
| 34 |
"higher_is_better": true
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"metric": "acc_norm",
|
| 38 |
+
"aggregation": "mean",
|
| 39 |
+
"higher_is_better": true
|
| 40 |
}
|
| 41 |
],
|
| 42 |
"output_type": "multiple_choice",
|
| 43 |
"repeats": 1,
|
| 44 |
"should_decontaminate": true,
|
| 45 |
+
"doc_to_decontamination_query": "goal",
|
| 46 |
"metadata": {
|
| 47 |
"version": 1.0
|
| 48 |
}
|
| 49 |
}
|
| 50 |
},
|
| 51 |
"versions": {
|
| 52 |
+
"piqa": 1.0
|
| 53 |
},
|
| 54 |
"n-shot": {
|
| 55 |
+
"piqa": 0
|
| 56 |
},
|
| 57 |
"higher_is_better": {
|
| 58 |
+
"piqa": {
|
| 59 |
+
"acc": true,
|
| 60 |
+
"acc_norm": true
|
| 61 |
}
|
| 62 |
},
|
| 63 |
"n-samples": {
|
| 64 |
+
"piqa": {
|
| 65 |
+
"original": 1838,
|
| 66 |
+
"effective": 1838
|
| 67 |
}
|
| 68 |
},
|
| 69 |
"config": {
|
|
|
|
| 86 |
"fewshot_seed": 1234
|
| 87 |
},
|
| 88 |
"git_hash": "2fea05a",
|
| 89 |
+
"date": 1731708350.2994263,
|
| 90 |
+
"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",
|
| 91 |
+
"transformers_version": "4.46.2",
|
| 92 |
"upper_git_hash": null,
|
| 93 |
"tokenizer_pad_token": [
|
| 94 |
"<|endoftext|>",
|
|
|
|
| 113 |
"fewshot_as_multiturn": false,
|
| 114 |
"chat_template": null,
|
| 115 |
"chat_template_sha": null,
|
| 116 |
+
"start_time": 2240.47196228,
|
| 117 |
+
"end_time": 2298.434063645,
|
| 118 |
+
"total_evaluation_time_seconds": "57.96210136500031"
|
| 119 |
}
|