End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: suayptalha/DeepSeek-R1-Distill-Llama-3B
+datasets: basicv8vc/SimpleQA
 library_name: transformers
 model_name: Llama-3B-Open-R1-GRPO
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - grpo
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for Llama-3B-Open-R1-GRPO
 
-This model is a fine-tuned version of [suayptalha/DeepSeek-R1-Distill-Llama-3B](https://huggingface.co/suayptalha/DeepSeek-R1-Distill-Llama-3B).
+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.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 0.09372581541538239,
+    "eval_runtime": 337.1395,
+    "eval_samples": 174,
+    "eval_samples_per_second": 0.516,
+    "eval_steps_per_second": 0.012,
     "total_flos": 0.0,
     "train_loss": 0.13259683549404144,
     "train_runtime": 313.1662,

config.json

@@ -32,6 +32,6 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0.dev0",
   "unsloth_fixed": true,
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 0.09372581541538239,
+    "eval_runtime": 337.1395,
+    "eval_samples": 174,
+    "eval_samples_per_second": 0.516,
+    "eval_steps_per_second": 0.012
+}