Update README.md
Browse files
README.md
CHANGED
|
@@ -19,16 +19,38 @@ Pythia-1.4b supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch.
|
|
| 19 |
See [Pythia-1.4b](https://huggingface.co/EleutherAI/pythia-1.4b) for model details [(paper)](https://arxiv.org/abs/2101.00027).
|
| 20 |
|
| 21 |
|
| 22 |
-
# Benchmark results:
|
| 23 |
-
|
| 24 |
-
## Zero shot
|
| 25 |
|
| 26 |
Results for the base model are taken from the [Pythia paper](https://arxiv.org/abs/2101.00027).
|
| 27 |
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
## Five shot
|
| 31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
|
| 33 |
|
| 34 |
|
|
|
|
| 19 |
See [Pythia-1.4b](https://huggingface.co/EleutherAI/pythia-1.4b) for model details [(paper)](https://arxiv.org/abs/2101.00027).
|
| 20 |
|
| 21 |
|
| 22 |
+
# Benchmark raw results:
|
|
|
|
|
|
|
| 23 |
|
| 24 |
Results for the base model are taken from the [Pythia paper](https://arxiv.org/abs/2101.00027).
|
| 25 |
|
| 26 |
|
| 27 |
+
## Zero shot
|
| 28 |
+
|
| 29 |
+
| Task | 1.4B_base | 1.4B_sft |
|
| 30 |
+
|------------------|--------------:|--------------:|
|
| 31 |
+
| Lambada (OpenAI) | 0.616 ± 0.007 | 0.5977 ± 0.0068 |
|
| 32 |
+
| PIQA | 0.711 ± 0.011 | 0.7133 ± 0.0106 |
|
| 33 |
+
| WinoGrande | 0.573 ± 0.014 | 0.5793 ± 0.0139 |
|
| 34 |
+
| WSC | 0.365 ± 0.047 | 0.3654 ± 0.0474 |
|
| 35 |
+
| ARC - Easy | 0.606 ± 0.010 | 0.6098 ± 0.0100 |
|
| 36 |
+
| ARC - Challenge | 0.260 ± 0.013 | 0.2696 ± 0.0130 |
|
| 37 |
+
| SciQ | 0.865 ± 0.011 | 0.8540 ± 0.0112 |
|
| 38 |
+
| LogiQA | 0.210 ± 0.016 | NA |
|
| 39 |
+
|
| 40 |
|
| 41 |
## Five shot
|
| 42 |
|
| 43 |
+
| Task | 1.4B_base | 1.4B_sft |
|
| 44 |
+
|------------------|----------------:|----------------:|
|
| 45 |
+
| Lambada (OpenAI) | 0.578 ± 0.007 | 0.5201 ± 0.007 |
|
| 46 |
+
| PIQA | 0.705 ± 0.011 | 0.7176 ± 0.0105|
|
| 47 |
+
| WinoGrande | 0.580 ± 0.014 | 0.5793 ± 0.0139|
|
| 48 |
+
| WSC | 0.365 ± 0.047 | 0.5288 ± 0.0492|
|
| 49 |
+
| ARC - Easy | 0.643 ± 0.010 | 0.6376 ± 0.0099|
|
| 50 |
+
| ARC - Challenge | 0.290 ± 0.013 | 0.2935 ± 0.0133|
|
| 51 |
+
| SciQ | 0.92 ± 0.009 | 0.9180 ± 0.0087|
|
| 52 |
+
| LogiQA | 0.240 ± 0.017 | N/A |
|
| 53 |
+
|
| 54 |
|
| 55 |
|
| 56 |
|