Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-7B-Instruct
-datasets: open-r1/OpenR1-Math-220k
 library_name: transformers
 model_name: Qwen2.5-7B-Open-R1-GRPO
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-7B-Open-R1-GRPO
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the [open-r1/OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -29,7 +27,7 @@ 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/chenyukang2020-nvidia/huggingface/runs/1ev28g0h) 
+[<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/chenyukang2020-nvidia/huggingface/runs/5jg0las6) 
 
 
 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": 2.302693507703102e-05,
-    "train_runtime": 483.3009,
+    "train_loss": 2.3079139061880094e-05,
+    "train_runtime": 485.9244,
     "train_samples": 93733,
-    "train_samples_per_second": 193.943,
-    "train_steps_per_second": 12.123
+    "train_samples_per_second": 192.896,
+    "train_steps_per_second": 12.057
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:959738c12da49a51f7a460cbae335d3edfda5c0ce6d04f634404eb1f8986424c
+oid sha256:23f5aa810626a63b560cf7cd27d2bf02323878315cb3e2308653432591c922ef
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a3a04625954332916483f50026c077127ed95c997fd01337e3cf532492713f
+oid sha256:83c0f9e741d69b86f126910ab16bb1f55610bf9be6a884357b3dc0e5b16a8bd5
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c33c1e57350eca13054c0f8382f178bc3ad2e9d8ac33d0e14033ab693f05149
+oid sha256:f979882f7b714428dfdebb4df29c5a2129581b59494fb54b78ac204d17163fd1
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1472ee2f3d1890b6d608e3943eba50bc2be7dfa444d5ea09a035c4362517abb9
+oid sha256:9c98ea4d90ca9138f3515081c703162a207a613d8bf29a531c5ea05e46c5b3ce
 size 1089994880

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 2.302693507703102e-05,
-    "train_runtime": 483.3009,
+    "train_loss": 2.3079139061880094e-05,
+    "train_runtime": 485.9244,
     "train_samples": 93733,
-    "train_samples_per_second": 193.943,
-    "train_steps_per_second": 12.123
+    "train_samples_per_second": 192.896,
+    "train_steps_per_second": 12.057
 }

trainer_state.json

@@ -175524,7 +175524,7 @@
       "completions/min_terminated_length": 0.0,
       "epoch": 0.9987198088247845,
       "frac_reward_zero_std": 1.0,
-      "grad_norm": 0.08476304346639023,
+      "grad_norm": 0.08476367046645225,
       "kl": 0.42578125,
       "learning_rate": 1.4376004014216017e-10,
       "loss": 0.017,
@@ -175554,8 +175554,8 @@
       "completions/min_terminated_length": 0.0,
       "epoch": 0.9988905009814799,
       "frac_reward_zero_std": 1.0,
-      "grad_norm": 0.05497211542384655,
-      "kl": 0.42333984375,
+      "grad_norm": 0.055872854179061585,
+      "kl": 0.4228515625,
       "learning_rate": 1.1358823698404131e-10,
       "loss": 0.0169,
       "num_tokens": 3061130200.0,
@@ -175584,10 +175584,10 @@
       "completions/min_terminated_length": 0.0,
       "epoch": 0.9990611931381753,
       "frac_reward_zero_std": 1.0,
-      "grad_norm": 0.09253000509661986,
-      "kl": 0.4189453125,
+      "grad_norm": 0.14358791242151217,
+      "kl": 0.408203125,
       "learning_rate": 8.696603252866808e-11,
-      "loss": 0.0168,
+      "loss": 0.0163,
       "num_tokens": 3061696328.0,
       "reward": 0.0,
       "reward_std": 0.0,
@@ -175614,10 +175614,10 @@
       "completions/min_terminated_length": 0.0,
       "epoch": 0.9992318852948707,
       "frac_reward_zero_std": 1.0,
-      "grad_norm": 0.051989839520072835,
-      "kl": 0.44775390625,
+      "grad_norm": 0.07870414983242291,
+      "kl": 0.4404296875,
       "learning_rate": 6.389343622403844e-11,
-      "loss": 0.0179,
+      "loss": 0.0176,
       "num_tokens": 3062258328.0,
       "reward": 0.0,
       "reward_std": 0.0,
@@ -175644,10 +175644,10 @@
       "completions/min_terminated_length": 0.0,
       "epoch": 0.9994025774515661,
       "frac_reward_zero_std": 1.0,
-      "grad_norm": 0.12960677022550027,
-      "kl": 0.4130859375,
+      "grad_norm": 0.16919090255532782,
+      "kl": 0.41943359375,
       "learning_rate": 4.437045625915737e-11,
-      "loss": 0.0165,
+      "loss": 0.0168,
       "num_tokens": 3062819496.0,
       "reward": 0.0,
       "reward_std": 0.0,
@@ -175674,10 +175674,10 @@
       "completions/min_terminated_length": 0.0,
       "epoch": 0.9995732696082615,
       "frac_reward_zero_std": 1.0,
-      "grad_norm": 0.09159924740428128,
-      "kl": 0.41845703125,
+      "grad_norm": 0.260652148611717,
+      "kl": 0.4287109375,
       "learning_rate": 2.839709956625747e-11,
-      "loss": 0.0167,
+      "loss": 0.0172,
       "num_tokens": 3063382760.0,
       "reward": 0.0,
       "reward_std": 0.0,
@@ -175704,10 +175704,10 @@
       "completions/min_terminated_length": 0.0,
       "epoch": 0.999743961764957,
       "frac_reward_zero_std": 1.0,
-      "grad_norm": 0.12075724493713264,
-      "kl": 0.40185546875,
+      "grad_norm": 0.046304060159445125,
+      "kl": 0.3916015625,
       "learning_rate": 1.5973371813027273e-11,
-      "loss": 0.0161,
+      "loss": 0.0156,
       "num_tokens": 3063952840.0,
       "reward": 0.0,
       "reward_std": 0.0,
@@ -175734,10 +175734,10 @@
       "completions/min_terminated_length": 0.0,
       "epoch": 0.9999146539216524,
       "frac_reward_zero_std": 1.0,
-      "grad_norm": 0.29393920311022953,
-      "kl": 0.4228515625,
+      "grad_norm": 0.3306328504937249,
+      "kl": 0.44287109375,
       "learning_rate": 7.099277411493077e-12,
-      "loss": 0.0169,
+      "loss": 0.0177,
       "num_tokens": 3064519096.0,
       "reward": 0.0,
       "reward_std": 0.0,
@@ -175753,10 +175753,10 @@
       "epoch": 0.9999146539216524,
       "step": 5858,
       "total_flos": 0.0,
-      "train_loss": 2.302693507703102e-05,
-      "train_runtime": 483.3009,
-      "train_samples_per_second": 193.943,
-      "train_steps_per_second": 12.123
+      "train_loss": 2.3079139061880094e-05,
+      "train_runtime": 485.9244,
+      "train_samples_per_second": 192.896,
+      "train_steps_per_second": 12.057
     }
   ],
   "logging_steps": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5afb542630ee6b0422d7310f11680454d6f498ab075bef12a859c2be322da28b
+oid sha256:8b01049e2e10045d3bc2aab78145e486cb1e2eb9a88196800173dcb1c1fe37e2
 size 8440