model_50m_2.3B card
Browse files- model_50m_2.3B/README.md +0 -4
model_50m_2.3B/README.md
CHANGED
|
@@ -12,12 +12,8 @@ The pretraining base and SFT init for this model are
|
|
| 12 |
|
| 13 |
| | |
|
| 14 |
|---|---|
|
| 15 |
-
| run id | `C6p5e18_50m_alpha0.100_beta0.023` |
|
| 16 |
| parameters | 50m |
|
| 17 |
| pretraining tokens | 2,291,084,661 (2.29B) |
|
| 18 |
-
| compute class | 6p5e18 |
|
| 19 |
-
| alpha (pretrain fraction) | 0.1 |
|
| 20 |
-
| beta (SFT fraction) | 0.023 |
|
| 21 |
| checkpoints here | 20 (steps 100–2000) |
|
| 22 |
| checkpoints saved by the run | 40 |
|
| 23 |
|
|
|
|
| 12 |
|
| 13 |
| | |
|
| 14 |
|---|---|
|
|
|
|
| 15 |
| parameters | 50m |
|
| 16 |
| pretraining tokens | 2,291,084,661 (2.29B) |
|
|
|
|
|
|
|
|
|
|
| 17 |
| checkpoints here | 20 (steps 100–2000) |
|
| 18 |
| checkpoints saved by the run | 40 |
|
| 19 |
|