Model save

README.md

@@ -1,10 +1,8 @@
 ---
-datasets: AI-MO/NuminaMath-TIR
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-GRPO
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -12,7 +10,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-Open-R1-GRPO
 
-This model is a fine-tuned version of [None](https://huggingface.co/None) on the [AI-MO/NuminaMath-TIR](https://huggingface.co/datasets/AI-MO/NuminaMath-TIR) dataset.
+This model is a fine-tuned version of [None](https://huggingface.co/None).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -28,7 +26,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/757885345/huggingface/runs/iqi1iy6m) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/757885345/huggingface/runs/dm87vc7f) 
 
 
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "o_proj",
-    "q_proj",
+    "gate_proj",
     "k_proj",
+    "down_proj",
+    "up_proj",
     "v_proj",
-    "gate_proj",
-    "up_proj"
+    "q_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c26155a7d3d9e66f9febfff6832261b50e423f00faefb97363998dd10d7d8b
-size 5097560
+oid sha256:35682366b4e92b1eb5bbaae7c298cf18275540690c3d914ad436d11fb254a8cf
+size 10143544

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 7.264316082000732e-08,
-    "train_runtime": 133.0262,
+    "train_loss": 1.862645149230957e-09,
+    "train_runtime": 136.0453,
     "train_samples": 6,
-    "train_samples_per_second": 0.045,
-    "train_steps_per_second": 0.008
+    "train_samples_per_second": 0.044,
+    "train_steps_per_second": 0.007
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 7.264316082000732e-08,
-    "train_runtime": 133.0262,
+    "train_loss": 1.862645149230957e-09,
+    "train_runtime": 136.0453,
     "train_samples": 6,
-    "train_samples_per_second": 0.045,
-    "train_steps_per_second": 0.008
+    "train_samples_per_second": 0.044,
+    "train_steps_per_second": 0.007
 }

trainer_state.json

@@ -9,21 +9,21 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 440.25,
+      "completion_length": 489.4166666666667,
       "epoch": 1.0,
       "kl": 0.0,
-      "reward": 0.7877263873815536,
-      "reward_std": 1.0702333394438028,
+      "reward": 0.8493689298629761,
+      "reward_std": 0.9399438500404358,
       "rewards/accuracy_reward": 0.4166666666666667,
-      "rewards/cosine_scaled_reward": 0.12105972071488698,
+      "rewards/cosine_scaled_reward": 0.12714668611685434,
       "rewards/format_reward": 0.0,
-      "rewards/reasoning_steps_reward": 0.2500000024835269,
+      "rewards/reasoning_steps_reward": 0.3055555671453476,
       "step": 1,
       "total_flos": 0.0,
-      "train_loss": 7.264316082000732e-08,
-      "train_runtime": 133.0262,
-      "train_samples_per_second": 0.045,
-      "train_steps_per_second": 0.008
+      "train_loss": 1.862645149230957e-09,
+      "train_runtime": 136.0453,
+      "train_samples_per_second": 0.044,
+      "train_steps_per_second": 0.007
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b613bdc9b900e9284f4a80538d88932d940044418895e3183ddba6e32bd84db
-size 7224
+oid sha256:68594e258603339d2a26bbd17f95c3e591db19a99d2bda4a98b5e2f330fc13e7
+size 5880