scottsuk0306
commited on
Commit
•
0d3585a
1
Parent(s):
a30ad28
End of training
Browse files- README.md +5 -1
- all_results.json +5 -0
- eval_results.json +5 -5
README.md
CHANGED
@@ -2,6 +2,10 @@
|
|
2 |
license: gemma
|
3 |
base_model: google/gemma-2-2b
|
4 |
tags:
|
|
|
|
|
|
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
@@ -19,7 +23,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
|
20 |
This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on the alpaca_farm dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
-
- Loss: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
2 |
license: gemma
|
3 |
base_model: google/gemma-2-2b
|
4 |
tags:
|
5 |
+
- easylm
|
6 |
+
- trl
|
7 |
+
- sft
|
8 |
+
- generated_from_trainer
|
9 |
- trl
|
10 |
- sft
|
11 |
- generated_from_trainer
|
|
|
23 |
|
24 |
This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on the alpaca_farm dataset.
|
25 |
It achieves the following results on the evaluation set:
|
26 |
+
- Loss: 0.7072
|
27 |
|
28 |
## Model description
|
29 |
|
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 4.566411071245517e+16,
|
4 |
"train_loss": 0.5696872653961181,
|
5 |
"train_runtime": 1519.873,
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
+
"eval_loss": 0.7071993350982666,
|
4 |
+
"eval_runtime": 7.3649,
|
5 |
+
"eval_samples": 2000,
|
6 |
+
"eval_samples_per_second": 271.56,
|
7 |
+
"eval_steps_per_second": 16.972,
|
8 |
"total_flos": 4.566411071245517e+16,
|
9 |
"train_loss": 0.5696872653961181,
|
10 |
"train_runtime": 1519.873,
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss": 0.
|
4 |
-
"eval_runtime": 7.
|
5 |
"eval_samples": 2000,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_loss": 0.7071993350982666,
|
4 |
+
"eval_runtime": 7.3649,
|
5 |
"eval_samples": 2000,
|
6 |
+
"eval_samples_per_second": 271.56,
|
7 |
+
"eval_steps_per_second": 16.972
|
8 |
}
|