Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-Coder-0.5B-Instruct
-datasets: open-r1/codeforces
 library_name: transformers
 model_name: Qwen2.5-Coder-0.5B-Instruct-Codeforces-GRPO
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-Coder-0.5B-Instruct-Codeforces-GRPO
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct) on the [open-r1/codeforces](https://huggingface.co/datasets/open-r1/codeforces) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0025,
+    "train_runtime": 0.0036,
     "train_samples": 16676,
-    "train_samples_per_second": 27052490.236,
-    "train_steps_per_second": 21089.132
+    "train_samples_per_second": 18596002.261,
+    "train_steps_per_second": 28993.527
 }

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.3",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0025,
+    "train_runtime": 0.0036,
     "train_samples": 16676,
-    "train_samples_per_second": 27052490.236,
-    "train_steps_per_second": 21089.132
+    "train_samples_per_second": 18596002.261,
+    "train_steps_per_second": 28993.527
 }

trainer_state.json

@@ -2664,13 +2664,13 @@
       "step": 106,
       "total_flos": 0.0,
       "train_loss": 0.0,
-      "train_runtime": 0.0025,
-      "train_samples_per_second": 27052490.236,
-      "train_steps_per_second": 21089.132
+      "train_runtime": 0.0036,
+      "train_samples_per_second": 18596002.261,
+      "train_steps_per_second": 28993.527
     }
   ],
   "logging_steps": 1,
-  "max_steps": 52,
+  "max_steps": 104,
   "num_input_tokens_seen": 77012768,
   "num_train_epochs": 4,
   "save_steps": 53,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a30d36e583f30dbcb563932cc5cd3c417f91c493f8b1ab819de93cdcbec5b5d6
+oid sha256:77d7702e7810c3d06d2ce787b38b213e201bf9e5586cebeb49fe051e9d1581eb
 size 8977