Update README.md
#2
by
samforeman
- opened
README.md
CHANGED
|
@@ -1,6 +1,9 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
# Model Card for Model ID
|
|
@@ -39,5 +42,4 @@ Trained on 32 nodes of Polaris supercomputer using pytorch FSDP with Hybrid-shar
|
|
| 39 |
* LR = 5x10^-5
|
| 40 |
* per-gpu batch size = 1
|
| 41 |
* Gradient accumulation = 6
|
| 42 |
-
* Global batch size = 768
|
| 43 |
-
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
datasets:
|
| 4 |
+
- allenai/dolma
|
| 5 |
+
base_model:
|
| 6 |
+
- argonne-private/AuroraGPT-7B
|
| 7 |
---
|
| 8 |
|
| 9 |
# Model Card for Model ID
|
|
|
|
| 42 |
* LR = 5x10^-5
|
| 43 |
* per-gpu batch size = 1
|
| 44 |
* Gradient accumulation = 6
|
| 45 |
+
* Global batch size = 768
|
|
|