Model save
Browse files
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/yknxxh-seoul-national-university/huggingface/runs/
|
31 |
|
32 |
This model was trained with SFT.
|
33 |
|
|
|
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/yknxxh-seoul-national-university/huggingface/runs/wjpxhixe)
|
31 |
|
32 |
This model was trained with SFT.
|
33 |
|
all_results.json
CHANGED
@@ -2,8 +2,8 @@
|
|
2 |
"epoch": 0.96,
|
3 |
"total_flos": 96668442181632.0,
|
4 |
"train_loss": 3.916761557261149,
|
5 |
-
"train_runtime": 4.
|
6 |
"train_samples": 100,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second": 1.
|
9 |
}
|
|
|
2 |
"epoch": 0.96,
|
3 |
"total_flos": 96668442181632.0,
|
4 |
"train_loss": 3.916761557261149,
|
5 |
+
"train_runtime": 4.2749,
|
6 |
"train_samples": 100,
|
7 |
+
"train_samples_per_second": 23.392,
|
8 |
+
"train_steps_per_second": 1.404
|
9 |
}
|
runs/Feb09_15-41-09_yekyung-nah-0/events.out.tfevents.1739083280.yekyung-nah-0.118709.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d17a1a41137b51918828528f871e4b8ec726ca585e6afb22679b135472456cd9
|
3 |
+
size 6951
|
train_results.json
CHANGED
@@ -2,8 +2,8 @@
|
|
2 |
"epoch": 0.96,
|
3 |
"total_flos": 96668442181632.0,
|
4 |
"train_loss": 3.916761557261149,
|
5 |
-
"train_runtime": 4.
|
6 |
"train_samples": 100,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second": 1.
|
9 |
}
|
|
|
2 |
"epoch": 0.96,
|
3 |
"total_flos": 96668442181632.0,
|
4 |
"train_loss": 3.916761557261149,
|
5 |
+
"train_runtime": 4.2749,
|
6 |
"train_samples": 100,
|
7 |
+
"train_samples_per_second": 23.392,
|
8 |
+
"train_steps_per_second": 1.404
|
9 |
}
|
trainer_state.json
CHANGED
@@ -25,9 +25,9 @@
|
|
25 |
{
|
26 |
"epoch": 0.96,
|
27 |
"eval_loss": 2.263831377029419,
|
28 |
-
"eval_runtime": 0.
|
29 |
-
"eval_samples_per_second":
|
30 |
-
"eval_steps_per_second":
|
31 |
"step": 6
|
32 |
},
|
33 |
{
|
@@ -35,9 +35,9 @@
|
|
35 |
"step": 6,
|
36 |
"total_flos": 96668442181632.0,
|
37 |
"train_loss": 3.916761557261149,
|
38 |
-
"train_runtime": 4.
|
39 |
-
"train_samples_per_second":
|
40 |
-
"train_steps_per_second": 1.
|
41 |
}
|
42 |
],
|
43 |
"logging_steps": 5,
|
|
|
25 |
{
|
26 |
"epoch": 0.96,
|
27 |
"eval_loss": 2.263831377029419,
|
28 |
+
"eval_runtime": 0.1012,
|
29 |
+
"eval_samples_per_second": 98.826,
|
30 |
+
"eval_steps_per_second": 29.648,
|
31 |
"step": 6
|
32 |
},
|
33 |
{
|
|
|
35 |
"step": 6,
|
36 |
"total_flos": 96668442181632.0,
|
37 |
"train_loss": 3.916761557261149,
|
38 |
+
"train_runtime": 4.2749,
|
39 |
+
"train_samples_per_second": 23.392,
|
40 |
+
"train_steps_per_second": 1.404
|
41 |
}
|
42 |
],
|
43 |
"logging_steps": 5,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5816
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f16737eef625c46b4954dd8bebeedbb75c359563af0b55303c3e086d9bf229d0
|
3 |
size 5816
|