Commit
·
1568692
1
Parent(s):
3bec713
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,31 @@
|
|
| 1 |
-
|
| 2 |
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# TinyLlama-1.1B
|
| 2 |
|
| 3 |
+
|
| 4 |
+
---
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
datasets:
|
| 7 |
+
- Generated using GPT 3.5 and 4
|
| 8 |
+
|
| 9 |
+
language:
|
| 10 |
+
- en
|
| 11 |
+
---
|
| 12 |
+
<div align="center">
|
| 13 |
+
|
| 14 |
+
# TinyLlama-1.1B
|
| 15 |
+
</div>
|
| 16 |
+
|
| 17 |
+
https://github.com/jzhang38/TinyLlama
|
| 18 |
+
|
| 19 |
+
Finetuning TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T model on Clinical Dataset.
|
| 20 |
+
|
| 21 |
+
#### Eval
|
| 22 |
+
|
| 23 |
+
| Model | Pretrain Tokens | HellaSwag | Obqa | WinoGrande | ARC_c | ARC_e | boolq | piqa | avg |
|
| 24 |
+
|-------------------------------------------|-----------------|-----------|------|------------|-------|-------|-------|------|-----|
|
| 25 |
+
| Pythia-1.0B | 300B | 47.16 | 31.40| 53.43 | 27.05 | 48.99 | 60.83 | 69.21 | 48.30 |
|
| 26 |
+
| TinyLlama-1.1B-intermediate-step-50K-104b | 103B | 43.50 | 29.80| 53.28 | 24.32 | 44.91 | 59.66 | 67.30 | 46.11|
|
| 27 |
+
| TinyLlama-1.1B-intermediate-step-240k-503b| 503B | 49.56 |31.40 |55.80 |26.54 |48.32 |56.91 |69.42 | 48.28 |
|
| 28 |
+
| TinyLlama-1.1B-intermediate-step-480k-1007B | 1007B | 52.54 | 33.40 | 55.96 | 27.82 | 52.36 | 59.54 | 69.91 | 50.22 |
|
| 29 |
+
| TinyLlama-1.1B-intermediate-step-715k-1.5T | 1.5T | 53.68 | 35.20 | 58.33 | 29.18 | 51.89 | 59.08 | 71.65 | 51.29 |
|
| 30 |
+
| TinyLlama-1.1B-intermediate-step-955k-2T | 2T | 54.63 | 33.40 | 56.83 | 28.07 | 54.67 | 63.21 | 70.67 | 51.64 |
|
| 31 |
+
| **TinyLlama-1.1B-intermediate-step-1195k-token-2.5T** | **2.5T** | **58.96** | **34.40** | **58.72** | **31.91** | **56.78** | **63.21** | **73.07** | **53.86**|
|