End of training

README.md

@@ -1,17 +1,19 @@
 ---
 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
+model_name: Qwen/Qwen2.5-1.5B-Instruct
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
 ---
 
-# Model Card for Qwen2.5-1.5B-Open-R1-Distill
+# Model Card for 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).
+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

@@ -1,10 +1,10 @@
 {
     "epoch": 0.999259807549963,
-    "eval_loss": 0.7437080144882202,
-    "eval_runtime": 13.7531,
+    "eval_loss": 0.7528421878814697,
+    "eval_runtime": 7.0991,
     "eval_samples": 100,
-    "eval_samples_per_second": 9.307,
-    "eval_steps_per_second": 2.327,
+    "eval_samples_per_second": 18.03,
+    "eval_steps_per_second": 2.254,
     "total_flos": 76888336760832.0,
     "train_loss": 0.7675936229140671,
     "train_runtime": 4627.4844,

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.9994447529150472,
-    "eval_loss": 0.7437080144882202,
-    "eval_runtime": 13.7531,
+    "epoch": 0.999259807549963,
+    "eval_loss": 0.7528421878814697,
+    "eval_runtime": 7.0991,
     "eval_samples": 100,
-    "eval_samples_per_second": 9.307,
-    "eval_steps_per_second": 2.327
+    "eval_samples_per_second": 18.03,
+    "eval_steps_per_second": 2.254
 }