Update README.md
Browse files
README.md
CHANGED
|
@@ -20,3 +20,49 @@ Fully reproducible finetuning code is available on [GitHub](https://github.com/l
|
|
| 20 |
|
| 21 |
See [Pythia-410m](https://huggingface.co/EleutherAI/pythia-410m) for model details [(paper)](https://arxiv.org/abs/2101.00027).
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
See [Pythia-410m](https://huggingface.co/EleutherAI/pythia-410m) for model details [(paper)](https://arxiv.org/abs/2101.00027).
|
| 22 |
|
| 23 |
+
hf (pretrained=lomahony/pythia-410m-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 | 0.2355|± |0.0124|
|
| 27 |
+
| | |none | 0|acc_norm | 0.2594|± |0.0128|
|
| 28 |
+
|arc_easy | 1|none | 0|acc | 0.5051|± |0.0103|
|
| 29 |
+
| | |none | 0|acc_norm | 0.4478|± |0.0102|
|
| 30 |
+
|boolq | 2|none | 0|acc | 0.6113|± |0.0085|
|
| 31 |
+
|hellaswag | 1|none | 0|acc | 0.3372|± |0.0047|
|
| 32 |
+
| | |none | 0|acc_norm | 0.4001|± |0.0049|
|
| 33 |
+
|lambada_openai| 1|none | 0|perplexity |21.8172|± |0.7736|
|
| 34 |
+
| | |none | 0|acc | 0.3755|± |0.0067|
|
| 35 |
+
|openbookqa | 1|none | 0|acc | 0.1940|± |0.0177|
|
| 36 |
+
| | |none | 0|acc_norm | 0.2960|± |0.0204|
|
| 37 |
+
|piqa | 1|none | 0|acc | 0.6719|± |0.0110|
|
| 38 |
+
| | |none | 0|acc_norm | 0.6687|± |0.0110|
|
| 39 |
+
|sciq | 1|none | 0|acc | 0.7700|± |0.0133|
|
| 40 |
+
| | |none | 0|acc_norm | 0.6540|± |0.0151|
|
| 41 |
+
|wikitext | 2|none | 0|word_perplexity|23.8136|± |N/A |
|
| 42 |
+
| | |none | 0|byte_perplexity| 1.8091|± |N/A |
|
| 43 |
+
| | |none | 0|bits_per_byte | 0.8553|± |N/A |
|
| 44 |
+
|winogrande | 1|none | 0|acc | 0.5320|± |0.0140|
|
| 45 |
+
|
| 46 |
+
hf (pretrained=lomahony/pythia-410m-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 | 0.2355|± |0.0124|
|
| 50 |
+
| | |none | 5|acc_norm | 0.2790|± |0.0131|
|
| 51 |
+
|arc_easy | 1|none | 5|acc | 0.5274|± |0.0102|
|
| 52 |
+
| | |none | 5|acc_norm | 0.5072|± |0.0103|
|
| 53 |
+
|boolq | 2|none | 5|acc | 0.5226|± |0.0087|
|
| 54 |
+
|hellaswag | 1|none | 5|acc | 0.3367|± |0.0047|
|
| 55 |
+
| | |none | 5|acc_norm | 0.3991|± |0.0049|
|
| 56 |
+
|lambada_openai| 1|none | 5|perplexity |37.4791|± |1.3737|
|
| 57 |
+
| | |none | 5|acc | 0.3049|± |0.0064|
|
| 58 |
+
|openbookqa | 1|none | 5|acc | 0.1620|± |0.0165|
|
| 59 |
+
| | |none | 5|acc_norm | 0.2900|± |0.0203|
|
| 60 |
+
|piqa | 1|none | 5|acc | 0.6708|± |0.0110|
|
| 61 |
+
| | |none | 5|acc_norm | 0.6676|± |0.0110|
|
| 62 |
+
|sciq | 1|none | 5|acc | 0.8630|± |0.0109|
|
| 63 |
+
| | |none | 5|acc_norm | 0.8430|± |0.0115|
|
| 64 |
+
|wikitext | 2|none | 5|word_perplexity|23.8136|± |N/A |
|
| 65 |
+
| | |none | 5|byte_perplexity| 1.8091|± |N/A |
|
| 66 |
+
| | |none | 5|bits_per_byte | 0.8553|± |N/A |
|
| 67 |
+
|winogrande | 1|none | 5|acc | 0.5272|± |0.0140|
|
| 68 |
+
|