Files changed (1) hide show
  1. README.md +118 -2
README.md CHANGED
@@ -1,14 +1,117 @@
1
  ---
2
  language:
3
  - en
 
4
  tags:
5
  - pytorch
6
  - causal-lm
7
  - pythia
8
  - pythia_v0
9
- license: apache-2.0
10
  datasets:
11
  - the_pile
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
 
14
  The *Pythia Scaling Suite* is a collection of models developed to facilitate
@@ -240,4 +343,17 @@ current naming convention (70M, 160M, etc.) is based on total parameter count.
240
  | 2.8B | 2.7B | 2,775,208,960 | 2,517,652,480 |
241
  | 6.9B | 6.7B | 6,857,302,016 | 6,444,163,072 |
242
  | 12B | 13B | 11,846,072,320 | 11,327,027,200 |
243
- </figure>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  language:
3
  - en
4
+ license: apache-2.0
5
  tags:
6
  - pytorch
7
  - causal-lm
8
  - pythia
9
  - pythia_v0
 
10
  datasets:
11
  - the_pile
12
+ model-index:
13
+ - name: pythia-1.3b
14
+ results:
15
+ - task:
16
+ type: text-generation
17
+ name: Text Generation
18
+ dataset:
19
+ name: AI2 Reasoning Challenge (25-Shot)
20
+ type: ai2_arc
21
+ config: ARC-Challenge
22
+ split: test
23
+ args:
24
+ num_few_shot: 25
25
+ metrics:
26
+ - type: acc_norm
27
+ value: 31.14
28
+ name: normalized accuracy
29
+ source:
30
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EleutherAI/pythia-1.3b
31
+ name: Open LLM Leaderboard
32
+ - task:
33
+ type: text-generation
34
+ name: Text Generation
35
+ dataset:
36
+ name: HellaSwag (10-Shot)
37
+ type: hellaswag
38
+ split: validation
39
+ args:
40
+ num_few_shot: 10
41
+ metrics:
42
+ - type: acc_norm
43
+ value: 51.43
44
+ name: normalized accuracy
45
+ source:
46
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EleutherAI/pythia-1.3b
47
+ name: Open LLM Leaderboard
48
+ - task:
49
+ type: text-generation
50
+ name: Text Generation
51
+ dataset:
52
+ name: MMLU (5-Shot)
53
+ type: cais/mmlu
54
+ config: all
55
+ split: test
56
+ args:
57
+ num_few_shot: 5
58
+ metrics:
59
+ - type: acc
60
+ value: 26.55
61
+ name: accuracy
62
+ source:
63
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EleutherAI/pythia-1.3b
64
+ name: Open LLM Leaderboard
65
+ - task:
66
+ type: text-generation
67
+ name: Text Generation
68
+ dataset:
69
+ name: TruthfulQA (0-shot)
70
+ type: truthful_qa
71
+ config: multiple_choice
72
+ split: validation
73
+ args:
74
+ num_few_shot: 0
75
+ metrics:
76
+ - type: mc2
77
+ value: 39.24
78
+ source:
79
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EleutherAI/pythia-1.3b
80
+ name: Open LLM Leaderboard
81
+ - task:
82
+ type: text-generation
83
+ name: Text Generation
84
+ dataset:
85
+ name: Winogrande (5-shot)
86
+ type: winogrande
87
+ config: winogrande_xl
88
+ split: validation
89
+ args:
90
+ num_few_shot: 5
91
+ metrics:
92
+ - type: acc
93
+ value: 57.38
94
+ name: accuracy
95
+ source:
96
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EleutherAI/pythia-1.3b
97
+ name: Open LLM Leaderboard
98
+ - task:
99
+ type: text-generation
100
+ name: Text Generation
101
+ dataset:
102
+ name: GSM8k (5-shot)
103
+ type: gsm8k
104
+ config: main
105
+ split: test
106
+ args:
107
+ num_few_shot: 5
108
+ metrics:
109
+ - type: acc
110
+ value: 0.99
111
+ name: accuracy
112
+ source:
113
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=EleutherAI/pythia-1.3b
114
+ name: Open LLM Leaderboard
115
  ---
116
 
117
  The *Pythia Scaling Suite* is a collection of models developed to facilitate
 
343
  | 2.8B | 2.7B | 2,775,208,960 | 2,517,652,480 |
344
  | 6.9B | 6.7B | 6,857,302,016 | 6,444,163,072 |
345
  | 12B | 13B | 11,846,072,320 | 11,327,027,200 |
346
+ </figure>
347
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
348
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_EleutherAI__pythia-1.3b)
349
+
350
+ | Metric |Value|
351
+ |---------------------------------|----:|
352
+ |Avg. |34.46|
353
+ |AI2 Reasoning Challenge (25-Shot)|31.14|
354
+ |HellaSwag (10-Shot) |51.43|
355
+ |MMLU (5-Shot) |26.55|
356
+ |TruthfulQA (0-shot) |39.24|
357
+ |Winogrande (5-shot) |57.38|
358
+ |GSM8k (5-shot) | 0.99|
359
+