Update README.md
Browse files
README.md
CHANGED
|
@@ -32,6 +32,9 @@ print(output["generated_text"])
|
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
| 34 |
|
|
|
|
|
|
|
|
|
|
| 35 |
|
| 36 |
## Model `/workspace/checkpoints_new/SmolLM2-360M-sft`:
|
| 37 |
### Question:
|
|
|
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
| 34 |
|
| 35 |
+
- SFT loss "eval_loss": 1.4015671014785767,
|
| 36 |
+
- base model loss "eval_loss": 1.6745600700378418,
|
| 37 |
+
|
| 38 |
|
| 39 |
## Model `/workspace/checkpoints_new/SmolLM2-360M-sft`:
|
| 40 |
### Question:
|