Update README.md
Browse files
README.md
CHANGED
|
@@ -20,12 +20,35 @@ Pythia-1.4b supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch (sft
|
|
| 20 |
See [Pythia-1.4b](https://huggingface.co/EleutherAI/pythia-1.4b) for model details [(paper)](https://arxiv.org/abs/2101.00027).
|
| 21 |
|
| 22 |
|
| 23 |
-
# Benchmark results:
|
|
|
|
|
|
|
| 24 |
|
| 25 |
## Zero shot
|
| 26 |
|
| 27 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
|
| 30 |
|
| 31 |
## Five shot
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
See [Pythia-1.4b](https://huggingface.co/EleutherAI/pythia-1.4b) for model details [(paper)](https://arxiv.org/abs/2101.00027).
|
| 21 |
|
| 22 |
|
| 23 |
+
# Benchmark raw results:
|
| 24 |
+
|
| 25 |
+
Results for the base model are taken from the [Pythia paper](https://arxiv.org/abs/2101.00027).
|
| 26 |
|
| 27 |
## Zero shot
|
| 28 |
|
| 29 |
+
| Task | 1.4B_base | 1.4B_sft | 1.4B_dpo |
|
| 30 |
+
|------------------|--------------:|--------------:|---------------:|
|
| 31 |
+
| Lambada (OpenAI) | 0.616 ± 0.007 | 0.5977 ± 0.0068 | 0.5948 ± 0.0068 |
|
| 32 |
+
| PIQA | 0.711 ± 0.011 | 0.7133 ± 0.0106 | 0.7165 ± 0.0105 |
|
| 33 |
+
| WinoGrande | 0.573 ± 0.014 | 0.5793 ± 0.0139 | 0.5746 ± 0.0139 |
|
| 34 |
+
| WSC | 0.365 ± 0.047 | 0.3654 ± 0.0474 | 0.3654 ± 0.0474 |
|
| 35 |
+
| ARC - Easy | 0.606 ± 0.010 | 0.6098 ± 0.0100 | 0.6199 ± 0.0100 |
|
| 36 |
+
| ARC - Challenge | 0.260 ± 0.013 | 0.2696 ± 0.0130 | 0.2884 ± 0.0132 |
|
| 37 |
+
| SciQ | 0.865 ± 0.011 | 0.8540 ± 0.0112 | 0.8550 ± 0.0111 |
|
| 38 |
+
| LogiQA | 0.210 ± 0.016 | NA | NA |
|
| 39 |
|
| 40 |
|
| 41 |
|
| 42 |
## Five shot
|
| 43 |
+
|
| 44 |
+
| Task | 1.4B_base | 1.4B_sft | 1.4B_dpo |
|
| 45 |
+
|------------------|----------------|----------------|----------------|
|
| 46 |
+
| Lambada (OpenAI) | 0.578 ± 0.007 | 0.5201 ± 0.007 | 0.5247 ± 0.007 |
|
| 47 |
+
| PIQA | 0.705 ± 0.011 | 0.7176 ± 0.0105| 0.7209 ± 0.0105|
|
| 48 |
+
| WinoGrande | 0.580 ± 0.014 | 0.5793 ± 0.0139| 0.5746 ± 0.0139|
|
| 49 |
+
| WSC | 0.365 ± 0.047 | 0.5288 ± 0.0492| 0.5769 ± 0.0487|
|
| 50 |
+
| ARC - Easy | 0.643 ± 0.010 | 0.6376 ± 0.0099| 0.6561 ± 0.0097|
|
| 51 |
+
| ARC - Challenge | 0.290 ± 0.013 | 0.2935 ± 0.0133| 0.3166 ± 0.0136|
|
| 52 |
+
| SciQ | 0.92 ± 0.009 | 0.9180 ± 0.0087| 0.9150 ± 0.0088|
|
| 53 |
+
| LogiQA | 0.240 ± 0.017 | N/A | N/A |
|
| 54 |
+
|