Update README.md
Browse files
README.md
CHANGED
@@ -19,3 +19,27 @@ Fully reproducible finetuning code is available on [GitHub](https://github.com/l
|
|
19 |
[wandb log](https://wandb.ai/lauraomahony999/pythia-dpo/runs/blurtl4v)
|
20 |
|
21 |
See [Pythia-2.8b](https://huggingface.co/EleutherAI/pythia-2.8b) for model details [(paper)](https://arxiv.org/abs/2101.00027).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
[wandb log](https://wandb.ai/lauraomahony999/pythia-dpo/runs/blurtl4v)
|
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-dpo), 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 | 0.3157|± |0.0136|
|
27 |
+
| | |none | 0|acc_norm | 0.3447|± |0.0139|
|
28 |
+
|arc_easy | 1|none | 0|acc | 0.6591|± |0.0097|
|
29 |
+
| | |none | 0|acc_norm | 0.6002|± |0.0101|
|
30 |
+
|boolq | 2|none | 0|acc | 0.6239|± |0.0085|
|
31 |
+
|hellaswag | 1|none | 0|acc | 0.4671|± |0.0050|
|
32 |
+
| | |none | 0|acc_norm | 0.6107|± |0.0049|
|
33 |
+
|lambada_openai| 1|none | 0|perplexity | 4.8811|± |0.1354|
|
34 |
+
| | |none | 0|acc | 0.6264|± |0.0067|
|
35 |
+
|openbookqa | 1|none | 0|acc | 0.2820|± |0.0201|
|
36 |
+
| | |none | 0|acc_norm | 0.4040|± |0.0220|
|
37 |
+
|piqa | 1|none | 0|acc | 0.7568|± |0.0100|
|
38 |
+
| | |none | 0|acc_norm | 0.7557|± |0.0100|
|
39 |
+
|sciq | 1|none | 0|acc | 0.8900|± |0.0099|
|
40 |
+
| | |none | 0|acc_norm | 0.8340|± |0.0118|
|
41 |
+
|wikitext | 2|none | 0|word_perplexity|13.9186|± |N/A |
|
42 |
+
| | |none | 0|byte_perplexity| 1.6363|± |N/A |
|
43 |
+
| | |none | 0|bits_per_byte | 0.7104|± |N/A |
|
44 |
+
|winogrande | 1|none | 0|acc | 0.6046|± |0.0137|
|
45 |
+
|