Model save
Browse files- README.md +1 -1
- all_results.json +3 -3
- train_results.json +3 -3
README.md
CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
|
|
27 |
|
28 |
## Training procedure
|
29 |
|
30 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/nlee28/reasoning/runs/
|
31 |
|
32 |
|
33 |
This model was trained with SFT.
|
|
|
27 |
|
28 |
## Training procedure
|
29 |
|
30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/nlee28/reasoning/runs/tst1b1ut)
|
31 |
|
32 |
|
33 |
This model was trained with SFT.
|
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"total_flos": 1.182462262019883e+18,
|
3 |
-
"train_loss": 2.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 817,
|
6 |
-
"train_samples_per_second": 0.
|
7 |
"train_steps_per_second": 0.012
|
8 |
}
|
|
|
1 |
{
|
2 |
"total_flos": 1.182462262019883e+18,
|
3 |
+
"train_loss": 2.9063207228978474,
|
4 |
+
"train_runtime": 4935.0728,
|
5 |
"train_samples": 817,
|
6 |
+
"train_samples_per_second": 0.828,
|
7 |
"train_steps_per_second": 0.012
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"total_flos": 1.182462262019883e+18,
|
3 |
-
"train_loss": 2.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 817,
|
6 |
-
"train_samples_per_second": 0.
|
7 |
"train_steps_per_second": 0.012
|
8 |
}
|
|
|
1 |
{
|
2 |
"total_flos": 1.182462262019883e+18,
|
3 |
+
"train_loss": 2.9063207228978474,
|
4 |
+
"train_runtime": 4935.0728,
|
5 |
"train_samples": 817,
|
6 |
+
"train_samples_per_second": 0.828,
|
7 |
"train_steps_per_second": 0.012
|
8 |
}
|