scottsuk0306
commited on
Commit
•
54a1ce6
1
Parent(s):
240c66f
End of training
Browse files- README.md +18 -4
- all_results.json +6 -0
- eval_results.json +9 -0
README.md
CHANGED
@@ -2,14 +2,28 @@
|
|
2 |
license: gemma
|
3 |
base_model: google/gemma-2-2b-it
|
4 |
tags:
|
|
|
|
|
5 |
- trl
|
6 |
- reward-trainer
|
7 |
- generated_from_trainer
|
|
|
|
|
8 |
metrics:
|
9 |
- accuracy
|
10 |
model-index:
|
11 |
- name: easylm-helpsteer-rm-gemma-2-2b-it
|
12 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -17,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# easylm-helpsteer-rm-gemma-2-2b-it
|
19 |
|
20 |
-
This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on
|
21 |
It achieves the following results on the evaluation set:
|
22 |
-
- Loss: 0.
|
23 |
-
- Accuracy: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
2 |
license: gemma
|
3 |
base_model: google/gemma-2-2b-it
|
4 |
tags:
|
5 |
+
- easylm
|
6 |
+
- alignment-handbook
|
7 |
- trl
|
8 |
- reward-trainer
|
9 |
- generated_from_trainer
|
10 |
+
datasets:
|
11 |
+
- helpsteer-rm
|
12 |
metrics:
|
13 |
- accuracy
|
14 |
model-index:
|
15 |
- name: easylm-helpsteer-rm-gemma-2-2b-it
|
16 |
+
results:
|
17 |
+
- task:
|
18 |
+
name: Text Classification
|
19 |
+
type: text-classification
|
20 |
+
dataset:
|
21 |
+
name: helpsteer-rm
|
22 |
+
type: helpsteer-rm
|
23 |
+
metrics:
|
24 |
+
- name: Accuracy
|
25 |
+
type: accuracy
|
26 |
+
value: 0.653179190751445
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
|
32 |
# easylm-helpsteer-rm-gemma-2-2b-it
|
33 |
|
34 |
+
This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on the helpsteer-rm dataset.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 0.6647
|
37 |
+
- Accuracy: 0.6532
|
38 |
|
39 |
## Model description
|
40 |
|
all_results.json
CHANGED
@@ -1,5 +1,11 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 0.0,
|
4 |
"train_loss": 0.7032692458603408,
|
5 |
"train_runtime": 2584.7937,
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_accuracy": 0.653179190751445,
|
4 |
+
"eval_loss": 0.6647074222564697,
|
5 |
+
"eval_runtime": 12.0829,
|
6 |
+
"eval_samples": 346,
|
7 |
+
"eval_samples_per_second": 28.635,
|
8 |
+
"eval_steps_per_second": 9.6,
|
9 |
"total_flos": 0.0,
|
10 |
"train_loss": 0.7032692458603408,
|
11 |
"train_runtime": 2584.7937,
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_accuracy": 0.653179190751445,
|
4 |
+
"eval_loss": 0.6647074222564697,
|
5 |
+
"eval_runtime": 12.0829,
|
6 |
+
"eval_samples": 346,
|
7 |
+
"eval_samples_per_second": 28.635,
|
8 |
+
"eval_steps_per_second": 9.6
|
9 |
+
}
|