Tristan commited on
Commit
37a34f9
1 Parent(s): a343b43

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -25
README.md CHANGED
@@ -65,28 +65,30 @@ The model was trained according to the OLM GPT2 instructions at this [repo](http
65
 
66
  The model achieves the following results without any fine-tuning (zero-shot):
67
 
68
- | Task | Version | Metric | Original GPT2 | OLM GPT2 Dec 2022 (Ours) | Significance of Difference (two-tailed p-value) |
69
- |:------------|:--------|:-----------|--------------------:|-------------------------:|----------------------------------:|
70
- |rte |0 |acc |0.5307 |0.5199 |0.7184 |
71
- |piqa |0 |acc/acc_norm|0.6289/0.6251 |**0.6692**/**0.6665** |**0.0004**/**0.0003** |
72
- |copa |0 |acc |0.6400 |0.6800 |0.4070 |
73
- |record |0 |f1/em |**0.7094**/**0.7026**|0.6884/0.6818 |**0.0000**/**0.0000** |
74
- |boolq |1 |acc |0.4872 |**0.6021** |**0.0000** |
75
- |cb |1 |acc/f1 |0.4107/0.2619 |0.3393/0.1840 |0.2816/NA |
76
- |hellaswag |0 |acc/acc_norm|0.2892/0.3114 |**0.3079**/**0.3482** |**0.0000**/**0.0000** |
77
- |mrpc |0 |acc/f1 |0.5662/0.6911 |**0.6814**/**0.8099** |**0.0000**/**0.0000** |
78
- |multirc |1 |acc |0.0189 |0.0220 |0.4755 |
79
- |lambada |0 |ppl/acc |40.0554/0.3256 |**28.3359**/**0.3699** |**0.0000**/**0.0000** |
80
- |wsc |0 |acc |0.4327 |0.3654 |0.1680 |
81
- |wic |0 |acc |0.4922 |0.5000 |0.6924 |
82
- |mnli |0 |acc |0.3372 |**0.3501** |**0.0071** |
83
- |qnli |0 |acc |0.5017 |0.4946 |0.2913 |
84
- |cola |0 |mcc |0.0126 |0.0000 |0.6880 |
85
- |triviaqa |1 |acc |0.0151 |**0.0181** |**0.0088** |
86
- |winogrande |0 |acc |0.5162 |0.5051 |0.4314 |
87
- |webqs |0 |acc |0.0030 |**0.0079** |**0.0000** |
88
- |arc_easy |0 |acc/acc_norm|0.4381/0.3948 |**0.4693**/**0.4230** |**0.0022**/**0.0049** |
89
- |arc_challenge|0 |acc/acc_norm|0.1903/0.2270 |0.2090/0.2398 |0.1017/0.2957 |
90
-
91
- To get these results, we used the Eleuther AI evaluation harness [here](https://github.com/EleutherAI/lm-evaluation-harness),
92
- which can produce results different than those reported in the GPT2 paper. The p-values come from the stderr from the evaluation harness, plus a normal distribution assumption.
 
 
 
65
 
66
  The model achieves the following results without any fine-tuning (zero-shot):
67
 
68
+ | Task | Metric | Original GPT2 | OLM GPT2 Dec 2022 (Ours) | Significance of Difference (two-tailed p-value) |
69
+ |:------------|:-----------|--------------------:|-------------------------:|----------------------------------:|
70
+ |rte |acc |0.5307 |0.5199 |0.7184 |
71
+ |piqa |acc/acc_norm|0.6289/0.6251 |**0.6692**/**0.6665** |**0.0004**/**0.0003** |
72
+ |copa |acc |0.6400 |0.6800 |0.4070 |
73
+ |record |f1/em |**0.7094**/**0.7026**|0.6884/0.6818 |**0.0000**/**0.0000** |
74
+ |boolq |acc |0.4872 |**0.6021** |**0.0000** |
75
+ |cb |acc/f1 |0.4107/0.2619 |0.3393/0.1840 |0.2816/NA |
76
+ |hellaswag |acc/acc_norm|0.2892/0.3114 |**0.3079**/**0.3482** |**0.0000**/**0.0000** |
77
+ |mrpc |acc/f1 |0.5662/0.6911 |**0.6814**/**0.8099** |**0.0000**/**0.0000** |
78
+ |multirc |acc |0.0189 |0.0220 |0.4755 |
79
+ |lambada |ppl/acc |40.0554/0.3256 |**28.3359**/**0.3699** |**0.0000**/**0.0000** |
80
+ |wsc |acc |0.4327 |0.3654 |0.1680 |
81
+ |wic |acc |0.4922 |0.5000 |0.6924 |
82
+ |mnli |acc |0.3372 |**0.3501** |**0.0071** |
83
+ |qnli |acc |0.5017 |0.4946 |0.2913 |
84
+ |cola |mcc |0.0126 |0.0000 |0.6880 |
85
+ |triviaqa |acc |0.0151 |**0.0181** |**0.0088** |
86
+ |winogrande |acc |0.5162 |0.5051 |0.4314 |
87
+ |webqs |acc |0.0030 |**0.0079** |**0.0000** |
88
+ |arc_easy |acc/acc_norm|0.4381/0.3948 |**0.4693**/**0.4230** |**0.0022**/**0.0049** |
89
+ |arc_challenge|acc/acc_norm|0.1903/0.2270 |0.2090/0.2398 |0.1017/0.2957 |
90
+
91
+ To get these results, we used commit `f079e322b857714fcef1ada9e78ddc606fe51e84` of the Eleuther AI evaluation harness [here](https://github.com/EleutherAI/lm-evaluation-harness),
92
+ which can produce results different than those reported in the GPT2 paper.
93
+ We added a change [here](https://github.com/EleutherAI/lm-evaluation-harness/compare/master...mathemakitten:lm-evaluation-harness:master) to enable evaluation of the OLM GPT2, which has a very slightly different vocab size.
94
+ The p-values come from the stderr from the evaluation harness, plus a normal distribution assumption.