Commit
•
fdaf454
1
Parent(s):
a38ea88
3007-2
Browse files
README.md
CHANGED
|
@@ -3,6 +3,7 @@ license: openrail
|
|
| 3 |
datasets:
|
| 4 |
- Skylion007/openwebtext
|
| 5 |
- ArtifactAI/arxiv-math-instruct-50k
|
|
|
|
| 6 |
---
|
| 7 |
|
| 8 |
# Bamboo 400M
|
|
@@ -23,8 +24,9 @@ As mentioned, a few updates are planned:
|
|
| 23 |
|
| 24 |
This table tracks the performance of our model on various tasks over time. The metric used is 'acc'.
|
| 25 |
|
| 26 |
-
| Date (YYYY-MM-DD) | arc_easy
|
| 27 |
-
|
|
|
|
| 28 |
| 2024-07-30 | 29.50% ± 0.94% | 25.36% ± 0.43% | 50.54% ± 3.01% | 41.07% ± 1.16% | 36.60% |
|
| 29 |
| 2024-07-29 | 32.24% ± 0.96% | 25.74% ± 0.44% | 47.29% ± 3.01% | 39.91% ± 1.11% | 36.30% |
|
| 30 |
| 2024-07-27 | 27.40% ± 0.92% | 25.52% ± 0.44% | 52.71% ± 3.01% | 39.52% ± 1.11% | 36.29% |
|
|
|
|
| 3 |
datasets:
|
| 4 |
- Skylion007/openwebtext
|
| 5 |
- ArtifactAI/arxiv-math-instruct-50k
|
| 6 |
+
- Saauan/leetcode-performance
|
| 7 |
---
|
| 8 |
|
| 9 |
# Bamboo 400M
|
|
|
|
| 24 |
|
| 25 |
This table tracks the performance of our model on various tasks over time. The metric used is 'acc'.
|
| 26 |
|
| 27 |
+
| Date (YYYY-MM-DD) | arc_easy | hellaswag | sglue_rte | truthfulqa | Avg |
|
| 28 |
+
|-------------------|----------------|----------------|----------------|----------------| ------ |
|
| 29 |
+
| 2024-07-30-2 | 28.91% ± 0.94% | 25.32% ± 0.43% | 50.54% ± 3.01% | 41.31% ± 1.16% | 36.52% |
|
| 30 |
| 2024-07-30 | 29.50% ± 0.94% | 25.36% ± 0.43% | 50.54% ± 3.01% | 41.07% ± 1.16% | 36.60% |
|
| 31 |
| 2024-07-29 | 32.24% ± 0.96% | 25.74% ± 0.44% | 47.29% ± 3.01% | 39.91% ± 1.11% | 36.30% |
|
| 32 |
| 2024-07-27 | 27.40% ± 0.92% | 25.52% ± 0.44% | 52.71% ± 3.01% | 39.52% ± 1.11% | 36.29% |
|