Update README.md
Browse files
README.md
CHANGED
|
@@ -20,3 +20,48 @@ Fully reproducible finetuning code is available on [GitHub](https://github.com/l
|
|
| 20 |
|
| 21 |
See [Pythia-2.8b](https://huggingface.co/EleutherAI/pythia-2.8b) for model details [(paper)](https://arxiv.org/abs/2101.00027).
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
See [Pythia-2.8b](https://huggingface.co/EleutherAI/pythia-2.8b) for model details [(paper)](https://arxiv.org/abs/2101.00027).
|
| 22 |
|
| 23 |
+
hf (pretrained=lomahony/pythia-2.8b-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 | 0.2901|± |0.0133|
|
| 27 |
+
| | |none | 0|acc_norm | 0.3404|± |0.0138|
|
| 28 |
+
|arc_easy | 1|none | 0|acc | 0.6469|± |0.0098|
|
| 29 |
+
| | |none | 0|acc_norm | 0.5766|± |0.0101|
|
| 30 |
+
|boolq | 2|none | 0|acc | 0.6361|± |0.0084|
|
| 31 |
+
|hellaswag | 1|none | 0|acc | 0.4557|± |0.0050|
|
| 32 |
+
| | |none | 0|acc_norm | 0.5984|± |0.0049|
|
| 33 |
+
|lambada_openai| 1|none | 0|perplexity | 5.2226|± |0.1377|
|
| 34 |
+
| | |none | 0|acc | 0.6210|± |0.0068|
|
| 35 |
+
|openbookqa | 1|none | 0|acc | 0.2640|± |0.0197|
|
| 36 |
+
| | |none | 0|acc_norm | 0.3760|± |0.0217|
|
| 37 |
+
|piqa | 1|none | 0|acc | 0.7481|± |0.0101|
|
| 38 |
+
| | |none | 0|acc_norm | 0.7481|± |0.0101|
|
| 39 |
+
|sciq | 1|none | 0|acc | 0.8800|± |0.0103|
|
| 40 |
+
| | |none | 0|acc_norm | 0.8180|± |0.0122|
|
| 41 |
+
|wikitext | 2|none | 0|word_perplexity|13.4928|± |N/A |
|
| 42 |
+
| | |none | 0|byte_perplexity| 1.6268|± |N/A |
|
| 43 |
+
| | |none | 0|bits_per_byte | 0.7020|± |N/A |
|
| 44 |
+
|winogrande | 1|none | 0|acc | 0.6125|± |0.0137|
|
| 45 |
+
|
| 46 |
+
hf (pretrained=lomahony/pythia-2.8b-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 | 0.3285|± |0.0137|
|
| 50 |
+
| | |none | 5|acc_norm | 0.3677|± |0.0141|
|
| 51 |
+
|arc_easy | 1|none | 5|acc | 0.6873|± |0.0095|
|
| 52 |
+
| | |none | 5|acc_norm | 0.6835|± |0.0095|
|
| 53 |
+
|boolq | 2|none | 5|acc | 0.6670|± |0.0082|
|
| 54 |
+
|hellaswag | 1|none | 5|acc | 0.4542|± |0.0050|
|
| 55 |
+
| | |none | 5|acc_norm | 0.5963|± |0.0049|
|
| 56 |
+
|lambada_openai| 1|none | 5|perplexity | 7.4076|± |0.2095|
|
| 57 |
+
| | |none | 5|acc | 0.5486|± |0.0069|
|
| 58 |
+
|openbookqa | 1|none | 5|acc | 0.2680|± |0.0198|
|
| 59 |
+
| | |none | 5|acc_norm | 0.3620|± |0.0215|
|
| 60 |
+
|piqa | 1|none | 5|acc | 0.7568|± |0.0100|
|
| 61 |
+
| | |none | 5|acc_norm | 0.7486|± |0.0101|
|
| 62 |
+
|sciq | 1|none | 5|acc | 0.9380|± |0.0076|
|
| 63 |
+
| | |none | 5|acc_norm | 0.9330|± |0.0079|
|
| 64 |
+
|wikitext | 2|none | 5|word_perplexity|13.4928|± |N/A |
|
| 65 |
+
| | |none | 5|byte_perplexity| 1.6268|± |N/A |
|
| 66 |
+
| | |none | 5|bits_per_byte | 0.7020|± |N/A |
|
| 67 |
+
|winogrande | 1|none | 5|acc | 0.5935|± |0.0138|
|