Update README.md
Browse files
README.md
CHANGED
|
@@ -20,4 +20,50 @@ Fully reproducible finetuning code is available on [GitHub](https://github.com/l
|
|
| 20 |
|
| 21 |
See [Pythia-70m](https://huggingface.co/EleutherAI/pythia-410m) for model details [(paper)](https://arxiv.org/abs/2101.00027).
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
|
|
|
| 20 |
|
| 21 |
See [Pythia-70m](https://huggingface.co/EleutherAI/pythia-410m) for model details [(paper)](https://arxiv.org/abs/2101.00027).
|
| 22 |
|
| 23 |
+
hf (pretrained=lomahony/pythia-70m-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 | 0.1715|± | 0.0110|
|
| 27 |
+
| | |none | 0|acc_norm | 0.2082|± | 0.0119|
|
| 28 |
+
|arc_easy | 1|none | 0|acc | 0.3384|± | 0.0097|
|
| 29 |
+
| | |none | 0|acc_norm | 0.3262|± | 0.0096|
|
| 30 |
+
|boolq | 2|none | 0|acc | 0.4239|± | 0.0086|
|
| 31 |
+
|hellaswag | 1|none | 0|acc | 0.2629|± | 0.0044|
|
| 32 |
+
| | |none | 0|acc_norm | 0.2691|± | 0.0044|
|
| 33 |
+
|lambada_openai| 1|none | 0|perplexity |5937.7964|± |424.7555|
|
| 34 |
+
| | |none | 0|acc | 0.0328|± | 0.0025|
|
| 35 |
+
|openbookqa | 1|none | 0|acc | 0.1580|± | 0.0163|
|
| 36 |
+
| | |none | 0|acc_norm | 0.2520|± | 0.0194|
|
| 37 |
+
|piqa | 1|none | 0|acc | 0.5593|± | 0.0116|
|
| 38 |
+
| | |none | 0|acc_norm | 0.5392|± | 0.0116|
|
| 39 |
+
|sciq | 1|none | 0|acc | 0.3710|± | 0.0153|
|
| 40 |
+
| | |none | 0|acc_norm | 0.4990|± | 0.0158|
|
| 41 |
+
|wikitext | 2|none | 0|word_perplexity| 550.5954|± |N/A |
|
| 42 |
+
| | |none | 0|byte_perplexity| 3.2550|± |N/A |
|
| 43 |
+
| | |none | 0|bits_per_byte | 1.7027|± |N/A |
|
| 44 |
+
|winogrande | 1|none | 0|acc | 0.4878|± | 0.0140|
|
| 45 |
+
|
| 46 |
+
hf (pretrained=lomahony/pythia-70m-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 | 0.1869|± | 0.0114|
|
| 50 |
+
| | |none | 5|acc_norm | 0.2210|± | 0.0121|
|
| 51 |
+
|arc_easy | 1|none | 5|acc | 0.3207|± | 0.0096|
|
| 52 |
+
| | |none | 5|acc_norm | 0.3245|± | 0.0096|
|
| 53 |
+
|boolq | 2|none | 5|acc | 0.4159|± | 0.0086|
|
| 54 |
+
|hellaswag | 1|none | 5|acc | 0.2633|± | 0.0044|
|
| 55 |
+
| | |none | 5|acc_norm | 0.2596|± | 0.0044|
|
| 56 |
+
|lambada_openai| 1|none | 5|perplexity |19968.0749|± |1423.3001|
|
| 57 |
+
| | |none | 5|acc | 0.0202|± | 0.0020|
|
| 58 |
+
|openbookqa | 1|none | 5|acc | 0.1440|± | 0.0157|
|
| 59 |
+
| | |none | 5|acc_norm | 0.2420|± | 0.0192|
|
| 60 |
+
|piqa | 1|none | 5|acc | 0.5359|± | 0.0116|
|
| 61 |
+
| | |none | 5|acc_norm | 0.5229|± | 0.0117|
|
| 62 |
+
|sciq | 1|none | 5|acc | 0.3240|± | 0.0148|
|
| 63 |
+
| | |none | 5|acc_norm | 0.4310|± | 0.0157|
|
| 64 |
+
|wikitext | 2|none | 5|word_perplexity| 550.5954|± |N/A |
|
| 65 |
+
| | |none | 5|byte_perplexity| 3.2550|± |N/A |
|
| 66 |
+
| | |none | 5|bits_per_byte | 1.7027|± |N/A |
|
| 67 |
+
|winogrande | 1|none | 5|acc | 0.5154|± | 0.0140|
|
| 68 |
+
|
| 69 |
|