End of training

README.md

@@ -4,6 +4,7 @@ library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-Distill
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.999259807549963,
+    "eval_loss": 0.7527158260345459,
+    "eval_runtime": 7.029,
+    "eval_samples": 100,
+    "eval_samples_per_second": 18.21,
+    "eval_steps_per_second": 2.276,
     "total_flos": 76888336760832.0,
     "train_loss": 0.7676166036393908,
     "train_runtime": 4800.2526,

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

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.999259807549963,
+    "eval_loss": 0.7527158260345459,
+    "eval_runtime": 7.029,
+    "eval_samples": 100,
+    "eval_samples_per_second": 18.21,
+    "eval_steps_per_second": 2.276
+}