End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
+datasets: HuggingFaceH4/Bespoke-Stratos-17k
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-Distill-bi
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-Open-R1-Distill-bi
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,13 @@
 {
+    "eval_reasoning_loss": 0.9136209487915039,
+    "eval_reasoning_runtime": 29.1446,
+    "eval_reasoning_samples_per_second": 4.426,
+    "eval_reasoning_steps_per_second": 1.132,
+    "eval_samples": 100,
+    "eval_utility_loss": 1.1523499488830566,
+    "eval_utility_runtime": 11.0014,
+    "eval_utility_samples_per_second": 4.454,
+    "eval_utility_steps_per_second": 1.182,
     "total_flos": 0.0,
     "train_loss": 2.0463369701511103,
     "train_runtime": 33791.3424,

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

eval_results.json

@@ -1,11 +1,11 @@
 {
-    "eval_reasoning_loss": 0.8857828378677368,
-    "eval_reasoning_runtime": 28.8571,
-    "eval_reasoning_samples_per_second": 4.47,
-    "eval_reasoning_steps_per_second": 1.144,
+    "eval_reasoning_loss": 0.9136209487915039,
+    "eval_reasoning_runtime": 29.1446,
+    "eval_reasoning_samples_per_second": 4.426,
+    "eval_reasoning_steps_per_second": 1.132,
     "eval_samples": 100,
-    "eval_utility_loss": 1.152946949005127,
-    "eval_utility_runtime": 10.899,
-    "eval_utility_samples_per_second": 4.496,
-    "eval_utility_steps_per_second": 1.193
+    "eval_utility_loss": 1.1523499488830566,
+    "eval_utility_runtime": 11.0014,
+    "eval_utility_samples_per_second": 4.454,
+    "eval_utility_steps_per_second": 1.182
 }