Deathsquad10
commited on
Commit
•
cb7d7dd
1
Parent(s):
57b5447
Update README.md
Browse files
README.md
CHANGED
@@ -15,6 +15,22 @@ language:
|
|
15 |
</div>
|
16 |
|
17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
https://github.com/jzhang38/TinyLlama
|
19 |
|
20 |
The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.
|
|
|
15 |
</div>
|
16 |
|
17 |
|
18 |
+
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|
19 |
+
|-------------|-------|------|-----:|--------|-----:|---|-----:|
|
20 |
+
|arc_challenge|Yaml |none | 0|acc |0.2790|± |0.0131|
|
21 |
+
| | |none | 0|acc_norm|0.3234|± |0.0137|
|
22 |
+
|arc_easy |Yaml |none | 0|acc |0.6006|± |0.0101|
|
23 |
+
| | |none | 0|acc_norm|0.5770|± |0.0101|
|
24 |
+
|boolq |Yaml |none | 0|acc |0.6373|± |0.0084|
|
25 |
+
|hellaswag |Yaml |none | 0|acc |0.4521|± |0.0050|
|
26 |
+
| | |none | 0|acc_norm|0.5822|± |0.0049|
|
27 |
+
|openbookqa |Yaml |none | 0|acc |0.2220|± |0.0186|
|
28 |
+
| | |none | 0|acc_norm|0.3740|± |0.0217|
|
29 |
+
|piqa |Yaml |none | 0|acc |0.7269|± |0.0104|
|
30 |
+
| | |none | 0|acc_norm|0.7296|± |0.0104|
|
31 |
+
|winogrande |Yaml |none | 0|acc |0.5754|± |0.0139|
|
32 |
+
|
33 |
+
|
34 |
https://github.com/jzhang38/TinyLlama
|
35 |
|
36 |
The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.
|