Update README.md
Browse files
README.md
CHANGED
|
@@ -20,12 +20,34 @@ Pythia-1b supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch (sft-m
|
|
| 20 |
See [Pythia-1b](https://huggingface.co/EleutherAI/pythia-1b) for model details [(paper)](https://arxiv.org/abs/2101.00027).
|
| 21 |
|
| 22 |
|
| 23 |
-
# Benchmark results:
|
| 24 |
-
|
| 25 |
-
## Zero shot
|
| 26 |
|
| 27 |
Results for the base model are taken from the [Pythia paper](https://arxiv.org/abs/2101.00027).
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
|
| 31 |
## Five shot
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
See [Pythia-1b](https://huggingface.co/EleutherAI/pythia-1b) 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 | 1B_base | 1B_sft | 1B_dpo |
|
| 30 |
+
|------------------|----------------|----------------|-----------------|
|
| 31 |
+
| Lambada (OpenAI) | 0.562 ± 0.007 | 0.563 ± 0.007 | 0.5575 ± 0.0069 |
|
| 32 |
+
| PIQA | 0.707 ± 0.011 | 0.711 ± 0.011 | 0.7122 ± 0.0106 |
|
| 33 |
+
| WinoGrande | 0.537 ± 0.014 | 0.534 ± 0.014 | 0.5525 ± 0.0140 |
|
| 34 |
+
| WSC | 0.365 ± 0.047 | 0.365 ± 0.047 | 0.3654 ± 0.0474 |
|
| 35 |
+
| ARC - Easy | 0.569 ± 0.010 | 0.583 ± 0.010 | 0.5901 ± 0.0101 |
|
| 36 |
+
| ARC - Challenge | 0.244 ± 0.013 | 0.248 ± 0.013 | 0.2611 ± 0.0128 |
|
| 37 |
+
| SciQ | 0.840 ± 0.012 | 0.847 ± 0.011 | 0.8530 ± 0.0112 |
|
| 38 |
+
| LogiQA | 0.223 ± 0.016 | N/A | N/A |
|
| 39 |
|
| 40 |
|
| 41 |
## Five shot
|
| 42 |
+
|
| 43 |
+
| Task | 1B_base | 1B_sft | 1B_dpo |
|
| 44 |
+
|------------------|----------------|----------------|-----------------|
|
| 45 |
+
| Lambada (OpenAI) | 0.507 ± 0.007 | 0.4722 ± 0.007 | 0.4669 ± 0.0070 |
|
| 46 |
+
| PIQA | 0.705 ± 0.011 | 0.7165 ± 0.0105| 0.7138 ± 0.0105 |
|
| 47 |
+
| WinoGrande | 0.532 ± 0.014 | 0.5343 ± 0.014 | 0.5525 ± 0.0140 |
|
| 48 |
+
| WSC | 0.365 ± 0.047 | 0.5000 ± 0.0493| 0.5577 ± 0.0489 |
|
| 49 |
+
| ARC - Easy | 0.594 ± 0.010 | 0.6010 ± 0.010 | 0.6170 ± 0.0100 |
|
| 50 |
+
| ARC - Challenge | 0.259 ± 0.013 | 0.2679 ± 0.0129| 0.2833 ± 0.0132 |
|
| 51 |
+
| SciQ | 0.920 ± 0.009 | 0.9100 ± 0.0091| 0.9020 ± 0.0094 |
|
| 52 |
+
| LogiQA | 0.227 ± 0.016 | N/A | N/A |
|
| 53 |
+
|