End of training
Browse files- README.md +3 -1
- all_results.json +5 -0
- config.json +1 -1
- eval_results.json +7 -0
README.md
CHANGED
@@ -1,9 +1,11 @@
|
|
1 |
---
|
2 |
base_model: suayptalha/DeepSeek-R1-Distill-Llama-3B
|
|
|
3 |
library_name: transformers
|
4 |
model_name: Llama-3B-Open-R1-GRPO
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
7 |
- trl
|
8 |
- grpo
|
9 |
licence: license
|
@@ -11,7 +13,7 @@ licence: license
|
|
11 |
|
12 |
# Model Card for Llama-3B-Open-R1-GRPO
|
13 |
|
14 |
-
This model is a fine-tuned version of [suayptalha/DeepSeek-R1-Distill-Llama-3B](https://huggingface.co/suayptalha/DeepSeek-R1-Distill-Llama-3B).
|
15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
16 |
|
17 |
## Quick start
|
|
|
1 |
---
|
2 |
base_model: suayptalha/DeepSeek-R1-Distill-Llama-3B
|
3 |
+
datasets: basicv8vc/SimpleQA
|
4 |
library_name: transformers
|
5 |
model_name: Llama-3B-Open-R1-GRPO
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
+
- open-r1
|
9 |
- trl
|
10 |
- grpo
|
11 |
licence: license
|
|
|
13 |
|
14 |
# Model Card for Llama-3B-Open-R1-GRPO
|
15 |
|
16 |
+
This model is a fine-tuned version of [suayptalha/DeepSeek-R1-Distill-Llama-3B](https://huggingface.co/suayptalha/DeepSeek-R1-Distill-Llama-3B) on the [basicv8vc/SimpleQA](https://huggingface.co/datasets/basicv8vc/SimpleQA) dataset.
|
17 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
18 |
|
19 |
## Quick start
|
all_results.json
CHANGED
@@ -1,4 +1,9 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
2 |
"total_flos": 0.0,
|
3 |
"train_loss": 0.13259683549404144,
|
4 |
"train_runtime": 313.1662,
|
|
|
1 |
{
|
2 |
+
"eval_loss": 0.09372581541538239,
|
3 |
+
"eval_runtime": 337.1395,
|
4 |
+
"eval_samples": 174,
|
5 |
+
"eval_samples_per_second": 0.516,
|
6 |
+
"eval_steps_per_second": 0.012,
|
7 |
"total_flos": 0.0,
|
8 |
"train_loss": 0.13259683549404144,
|
9 |
"train_runtime": 313.1662,
|
config.json
CHANGED
@@ -32,6 +32,6 @@
|
|
32 |
"torch_dtype": "bfloat16",
|
33 |
"transformers_version": "4.50.0.dev0",
|
34 |
"unsloth_fixed": true,
|
35 |
-
"use_cache":
|
36 |
"vocab_size": 128256
|
37 |
}
|
|
|
32 |
"torch_dtype": "bfloat16",
|
33 |
"transformers_version": "4.50.0.dev0",
|
34 |
"unsloth_fixed": true,
|
35 |
+
"use_cache": true,
|
36 |
"vocab_size": 128256
|
37 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_loss": 0.09372581541538239,
|
3 |
+
"eval_runtime": 337.1395,
|
4 |
+
"eval_samples": 174,
|
5 |
+
"eval_samples_per_second": 0.516,
|
6 |
+
"eval_steps_per_second": 0.012
|
7 |
+
}
|