End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+datasets: zwt963/FinReasoner
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-GRPO
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - grpo
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-Open-R1-GRPO
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B).
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on the [zwt963/FinReasoner](https://huggingface.co/datasets/zwt963/FinReasoner) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 0.012486881576478481,
+    "eval_runtime": 79.6968,
+    "eval_samples": 223,
+    "eval_samples_per_second": 2.798,
+    "eval_steps_per_second": 0.1,
     "total_flos": 0.0,
     "train_loss": 0.0029402809985185742,
     "train_runtime": 7951.9567,

config.json

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

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "eval_loss": 0.00024833829957060516,
-    "eval_runtime": 83.9269,
+    "eval_loss": 0.012486881576478481,
+    "eval_runtime": 79.6968,
     "eval_samples": 223,
-    "eval_samples_per_second": 2.657,
-    "eval_steps_per_second": 0.095
+    "eval_samples_per_second": 2.798,
+    "eval_steps_per_second": 0.1
 }