End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: allenai/OLMoE-1B-7B-0125-Instruct
+datasets: chenggong1995/NuminaMath-TIR-8000
 library_name: transformers
 model_name: OLMoE-1B-7B-0125-Instruct-grpo-E6-D8000-L4096
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - grpo
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for OLMoE-1B-7B-0125-Instruct-grpo-E6-D8000-L4096
 
-This model is a fine-tuned version of [allenai/OLMoE-1B-7B-0125-Instruct](https://huggingface.co/allenai/OLMoE-1B-7B-0125-Instruct).
+This model is a fine-tuned version of [allenai/OLMoE-1B-7B-0125-Instruct](https://huggingface.co/allenai/OLMoE-1B-7B-0125-Instruct) on the [chenggong1995/NuminaMath-TIR-8000](https://huggingface.co/datasets/chenggong1995/NuminaMath-TIR-8000) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 0.06355151534080505,
+    "eval_runtime": 162.8364,
+    "eval_samples": 99,
+    "eval_samples_per_second": 0.608,
+    "eval_steps_per_second": 0.018,
     "total_flos": 0.0,
     "train_loss": 0.03362821891328426,
     "train_runtime": 77437.8148,

config.json

@@ -28,6 +28,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 50304
 }

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 0.06355151534080505,
+    "eval_runtime": 162.8364,
+    "eval_samples": 99,
+    "eval_samples_per_second": 0.608,
+    "eval_steps_per_second": 0.018
+}