lomahony commited on
Commit
78816e3
1 Parent(s): f8e2259

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +47 -2
README.md CHANGED
@@ -10,7 +10,7 @@ datasets:
10
  - Anthropic/hh-rlhf
11
  ---
12
 
13
- [Pythia-1b](https://huggingface.co/EleutherAI/pythia-410m) supervised finetuned using TRLx library with the helpful subset of [Anthropic-hh-rlhf dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf) for 1 epoch.
14
 
15
  Checkpoints are also uploaded.
16
 
@@ -18,5 +18,50 @@ Fully reproducible finetuning code is available on [GitHub](https://github.com/l
18
 
19
  [wandb log](https://wandb.ai/lauraomahony999/sft-pythia/runs/azscanfe)
20
 
21
- See [Pythia-1b](https://huggingface.co/EleutherAI/pythia-410m) for model details [(paper)](https://arxiv.org/abs/2101.00027).
22
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  - Anthropic/hh-rlhf
11
  ---
12
 
13
+ [Pythia-1b](https://huggingface.co/EleutherAI/pythia-1b) supervised finetuned using TRLx library with the helpful subset of [Anthropic-hh-rlhf dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf) for 1 epoch.
14
 
15
  Checkpoints are also uploaded.
16
 
 
18
 
19
  [wandb log](https://wandb.ai/lauraomahony999/sft-pythia/runs/azscanfe)
20
 
21
+ See [Pythia-1b](https://huggingface.co/EleutherAI/pythia-1b) for model details [(paper)](https://arxiv.org/abs/2101.00027).
22
 
23
+ hf (pretrained=lomahony/pythia-1b-helpful-sft), gen_kwargs: (None), limit: None, num_fewshot: 0, batch_size: 16
24
+ | Tasks |Version|Filter|n-shot| Metric | Value | |Stderr|
25
+ |--------------|------:|------|-----:|---------------|------:|---|------|
26
+ |arc_challenge | 1|none | 0|acc | 0.2543|± |0.0127|
27
+ | | |none | 0|acc_norm | 0.2739|± |0.0130|
28
+ |arc_easy | 1|none | 0|acc | 0.5724|± |0.0102|
29
+ | | |none | 0|acc_norm | 0.4941|± |0.0103|
30
+ |boolq | 2|none | 0|acc | 0.6199|± |0.0085|
31
+ |hellaswag | 1|none | 0|acc | 0.3819|± |0.0048|
32
+ | | |none | 0|acc_norm | 0.4736|± |0.0050|
33
+ |lambada_openai| 1|none | 0|perplexity | 7.1374|± |0.2014|
34
+ | | |none | 0|acc | 0.5626|± |0.0069|
35
+ |openbookqa | 1|none | 0|acc | 0.2040|± |0.0180|
36
+ | | |none | 0|acc_norm | 0.3140|± |0.0208|
37
+ |piqa | 1|none | 0|acc | 0.7138|± |0.0105|
38
+ | | |none | 0|acc_norm | 0.6997|± |0.0107|
39
+ |sciq | 1|none | 0|acc | 0.8400|± |0.0116|
40
+ | | |none | 0|acc_norm | 0.7620|± |0.0135|
41
+ |wikitext | 2|none | 0|word_perplexity|16.9719|± |N/A |
42
+ | | |none | 0|byte_perplexity| 1.6981|± |N/A |
43
+ | | |none | 0|bits_per_byte | 0.7639|± |N/A |
44
+ |winogrande | 1|none | 0|acc | 0.5343|± |0.0140|
45
+
46
+ hf (pretrained=lomahony/pythia-1b-helpful-sft), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 16
47
+ | Tasks |Version|Filter|n-shot| Metric | Value | |Stderr|
48
+ |--------------|------:|------|-----:|---------------|------:|---|------|
49
+ |arc_challenge | 1|none | 5|acc | 0.2628|± |0.0129|
50
+ | | |none | 5|acc_norm | 0.2918|± |0.0133|
51
+ |arc_easy | 1|none | 5|acc | 0.6040|± |0.0100|
52
+ | | |none | 5|acc_norm | 0.5816|± |0.0101|
53
+ |boolq | 2|none | 5|acc | 0.5963|± |0.0086|
54
+ |hellaswag | 1|none | 5|acc | 0.3780|± |0.0048|
55
+ | | |none | 5|acc_norm | 0.4719|± |0.0050|
56
+ |lambada_openai| 1|none | 5|perplexity |10.2584|± |0.2936|
57
+ | | |none | 5|acc | 0.4832|± |0.0070|
58
+ |openbookqa | 1|none | 5|acc | 0.1980|± |0.0178|
59
+ | | |none | 5|acc_norm | 0.3220|± |0.0209|
60
+ |piqa | 1|none | 5|acc | 0.7057|± |0.0106|
61
+ | | |none | 5|acc_norm | 0.7095|± |0.0106|
62
+ |sciq | 1|none | 5|acc | 0.8980|± |0.0096|
63
+ | | |none | 5|acc_norm | 0.9000|± |0.0095|
64
+ |wikitext | 2|none | 5|word_perplexity|16.9719|± |N/A |
65
+ | | |none | 5|byte_perplexity| 1.6981|± |N/A |
66
+ | | |none | 5|bits_per_byte | 0.7639|± |N/A |
67
+ |winogrande | 1|none | 5|acc | 0.5446|± |0.0140|