File size: 8,756 Bytes
3980395
 
ebf6261
 
 
 
 
 
 
3980395
 
 
 
 
 
 
 
 
ebf6261
3980395
 
 
ebf6261
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3980395
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ebf6261
3980395
 
 
ebf6261
3980395
 
 
ebf6261
 
 
 
3980395
 
 
 
 
 
 
 
 
ebf6261
 
 
 
3980395
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ebf6261
3980395
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ebf6261
 
 
3980395
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
{
  "results": {
    "hellaswag": {
      "alias": "hellaswag",
      "acc,none": 0.25492929695279826,
      "acc_stderr,none": 0.004349307702735166,
      "acc_norm,none": 0.26010754829715194,
      "acc_norm_stderr,none": 0.004377965074211624
    },
    "sciq": {
      "alias": "sciq",
      "acc,none": 0.195,
      "acc_stderr,none": 0.012535235623319334,
      "acc_norm,none": 0.216,
      "acc_norm_stderr,none": 0.013019735539307803
    }
  },
  "group_subtasks": {
    "hellaswag": [],
    "sciq": []
  },
  "configs": {
    "hellaswag": {
      "task": "hellaswag",
      "tag": [
        "multiple_choice"
      ],
      "dataset_path": "hellaswag",
      "dataset_kwargs": {
        "trust_remote_code": true
      },
      "training_split": "train",
      "validation_split": "validation",
      "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",
      "doc_to_text": "{{query}}",
      "doc_to_target": "{{label}}",
      "doc_to_choice": "choices",
      "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": false,
      "metadata": {
        "version": 1.0
      }
    },
    "sciq": {
      "task": "sciq",
      "dataset_path": "sciq",
      "training_split": "train",
      "validation_split": "validation",
      "test_split": "test",
      "doc_to_text": "{{support.lstrip()}}\nQuestion: {{question}}\nAnswer:",
      "doc_to_target": 3,
      "doc_to_choice": "{{[distractor1, distractor2, distractor3, correct_answer]}}",
      "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": "{{support}} {{question}}",
      "metadata": {
        "version": 1.0
      }
    }
  },
  "versions": {
    "hellaswag": 1.0,
    "sciq": 1.0
  },
  "n-shot": {
    "hellaswag": 0,
    "sciq": 0
  },
  "higher_is_better": {
    "hellaswag": {
      "acc": true,
      "acc_norm": true
    },
    "sciq": {
      "acc": true,
      "acc_norm": true
    }
  },
  "n-samples": {
    "sciq": {
      "original": 1000,
      "effective": 1000
    },
    "hellaswag": {
      "original": 10042,
      "effective": 10042
    }
  },
  "config": {
    "model": "hf",
    "model_args": "pretrained=EleutherAI/pythia-70m,revision=step0,dtype=float,trust_remote_code=True",
    "model_num_parameters": 70426624,
    "model_dtype": "torch.float32",
    "model_revision": "step0",
    "model_sha": "61c46343f90c4d113efdfe09eb195382dd242200",
    "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": "a5b7c41",
  "date": 1729863770.9386845,
  "pretty_env_info": "PyTorch version: 2.5.0+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: Tesla T4\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):                               2\nOn-line CPU(s) list:                  0,1\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:                   1\nSocket(s):                            1\nStepping:                             3\nBogoMIPS:                             4000.42\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 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:                            32 KiB (1 instance)\nL1i cache:                            32 KiB (1 instance)\nL2 cache:                             1 MiB (1 instance)\nL3 cache:                             38.5 MiB (1 instance)\nNUMA node(s):                         1\nNUMA node0 CPU(s):                    0,1\nVulnerability Gather data sampling:   Not affected\nVulnerability Itlb multihit:          Not affected\nVulnerability L1tf:                   Mitigation; PTE Inversion\nVulnerability Mds:                    Vulnerable; SMT Host state unknown\nVulnerability Meltdown:               Vulnerable\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: Not affected; 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==0.13.0\n[pip3] torch==2.5.0+cu121\n[pip3] torchaudio==2.5.0+cu121\n[pip3] torchsummary==1.5.1\n[pip3] torchvision==0.20.0+cu121\n[conda] Could not collect",
  "transformers_version": "4.44.2",
  "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-70m",
  "model_name_sanitized": "EleutherAI__pythia-70m",
  "system_instruction": null,
  "system_instruction_sha": null,
  "fewshot_as_multiturn": false,
  "chat_template": null,
  "chat_template_sha": null,
  "start_time": 4692.118664113,
  "end_time": 4888.466629147,
  "total_evaluation_time_seconds": "196.34796503400048"
}