scottsuk0306
commited on
Commit
•
b52e3d5
1
Parent(s):
0fe2f8c
End of training
Browse files- README.md +21 -4
- all_results.json +5 -5
- config.json +1 -1
- eval_results.json +5 -5
README.md
CHANGED
@@ -2,14 +2,28 @@
|
|
2 |
license: cc-by-nc-4.0
|
3 |
base_model: sfairXC/FsfairX-LLaMA3-RM-v0.1
|
4 |
tags:
|
5 |
-
- trl
|
6 |
-
- reward-trainer
|
7 |
- easylm
|
8 |
- alignment-handbook
|
|
|
|
|
9 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
10 |
model-index:
|
11 |
- name: easylm-helpsteer-rm-FsfairX-LLaMA3-RM-v0.1
|
12 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -17,7 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# easylm-helpsteer-rm-FsfairX-LLaMA3-RM-v0.1
|
19 |
|
20 |
-
This model is a fine-tuned version of [sfairXC/FsfairX-LLaMA3-RM-v0.1](https://huggingface.co/sfairXC/FsfairX-LLaMA3-RM-v0.1) on
|
|
|
|
|
|
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
2 |
license: cc-by-nc-4.0
|
3 |
base_model: sfairXC/FsfairX-LLaMA3-RM-v0.1
|
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-FsfairX-LLaMA3-RM-v0.1
|
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: 0.664756446991404
|
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-FsfairX-LLaMA3-RM-v0.1
|
33 |
|
34 |
+
This model is a fine-tuned version of [sfairXC/FsfairX-LLaMA3-RM-v0.1](https://huggingface.co/sfairXC/FsfairX-LLaMA3-RM-v0.1) on the helpsteer-rm dataset.
|
35 |
+
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 0.6508
|
37 |
+
- Accuracy: 0.6648
|
38 |
|
39 |
## Model description
|
40 |
|
all_results.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 5.
|
6 |
"eval_samples": 349,
|
7 |
-
"eval_samples_per_second": 58.
|
8 |
-
"eval_steps_per_second": 7.
|
9 |
"total_flos": 0.0,
|
10 |
"train_loss": 0.7041080118083268,
|
11 |
"train_runtime": 641.2149,
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_accuracy": 0.664756446991404,
|
4 |
+
"eval_loss": 0.6507900357246399,
|
5 |
+
"eval_runtime": 5.9367,
|
6 |
"eval_samples": 349,
|
7 |
+
"eval_samples_per_second": 58.786,
|
8 |
+
"eval_steps_per_second": 7.411,
|
9 |
"total_flos": 0.0,
|
10 |
"train_loss": 0.7041080118083268,
|
11 |
"train_runtime": 641.2149,
|
config.json
CHANGED
@@ -31,6 +31,6 @@
|
|
31 |
"tie_word_embeddings": false,
|
32 |
"torch_dtype": "bfloat16",
|
33 |
"transformers_version": "4.43.3",
|
34 |
-
"use_cache":
|
35 |
"vocab_size": 128257
|
36 |
}
|
|
|
31 |
"tie_word_embeddings": false,
|
32 |
"torch_dtype": "bfloat16",
|
33 |
"transformers_version": "4.43.3",
|
34 |
+
"use_cache": true,
|
35 |
"vocab_size": 128257
|
36 |
}
|
eval_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 5.
|
6 |
"eval_samples": 349,
|
7 |
-
"eval_samples_per_second": 58.
|
8 |
-
"eval_steps_per_second": 7.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_accuracy": 0.664756446991404,
|
4 |
+
"eval_loss": 0.6507900357246399,
|
5 |
+
"eval_runtime": 5.9367,
|
6 |
"eval_samples": 349,
|
7 |
+
"eval_samples_per_second": 58.786,
|
8 |
+
"eval_steps_per_second": 7.411
|
9 |
}
|