Model save

README.md

@@ -1,15 +1,12 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
 library_name: transformers
-model_name: Qwen2.5-1.5B-Open-R1-GRPO
 tags:
 - generated_from_trainer
-- trl
-- grpo
 licence: license
 ---
 
-# Model Card for Qwen2.5-1.5B-Open-R1-GRPO
+# Model Card for None
 
 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).
 It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -27,7 +24,7 @@ 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/ruikangzhao-danmarks-tekniske-universitet-dtu/huggingface/runs/brfye0bx) 
+[<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/ruikangzhao-danmarks-tekniske-universitet-dtu/huggingface/runs/u8581ung) 
 
 
 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).

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.00015604885993525386,
-    "train_runtime": 10592.7921,
-    "train_samples": 100,
-    "train_samples_per_second": 0.009,
-    "train_steps_per_second": 0.001
+    "train_loss": 1.862645149230957e-09,
+    "train_runtime": 387.7333,
+    "train_samples": 3,
+    "train_samples_per_second": 0.008,
+    "train_steps_per_second": 0.003
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaef5d1ced970e06eac33309db3aa15291869bdd1e1cbaa6ef004a53c031e96a
+oid sha256:02688ef1124d12440fd239b434dddc8ee9f818de68b1a651e3999555db4595b3
 size 4996670464

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:473a9c09782385eaa0e3cf068bef93b025c5711a8f3b3e6f12dc40f15224dd56
+oid sha256:a4d0eae97532a467f289e0be214543efb098996f4878c8bf54b251b4d15ac9e6
 size 2111719976

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.00015604885993525386,
-    "train_runtime": 10592.7921,
-    "train_samples": 100,
-    "train_samples_per_second": 0.009,
-    "train_steps_per_second": 0.001
+    "train_loss": 1.862645149230957e-09,
+    "train_runtime": 387.7333,
+    "train_samples": 3,
+    "train_samples_per_second": 0.008,
+    "train_steps_per_second": 0.003
 }

trainer_state.json

@@ -1,31 +1,31 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.96,
+  "epoch": 1.0,
   "eval_steps": 100,
-  "global_step": 6,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 791.9205729166666,
-      "epoch": 0.96,
-      "kl": 0.0039011780130143356,
-      "reward": 0.3671875,
-      "reward_std": 0.20240005695571503,
-      "rewards/accuracy_reward": 0.3671875,
+      "completion_length": 955.5833333333334,
+      "epoch": 1.0,
+      "kl": 0.0,
+      "reward": 0.25,
+      "reward_std": 0.15430335203806558,
+      "rewards/accuracy_reward": 0.25,
       "rewards/format_reward": 0.0,
-      "step": 6,
+      "step": 1,
       "total_flos": 0.0,
-      "train_loss": 0.00015604885993525386,
-      "train_runtime": 10592.7921,
-      "train_samples_per_second": 0.009,
-      "train_steps_per_second": 0.001
+      "train_loss": 1.862645149230957e-09,
+      "train_runtime": 387.7333,
+      "train_samples_per_second": 0.008,
+      "train_steps_per_second": 0.003
     }
   ],
   "logging_steps": 10,
-  "max_steps": 6,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8bd5b42bb729c1abe0b9035a79589d55fe19e38ed393671496f55d11e783fdc
+oid sha256:1f0ba137453abddbfd819c5f1476a21083d44a541e4ecd3b4e7af905fe6f8160
 size 5752