Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
-datasets: jdy_analysis
 library_name: transformers
 model_name: Qwen2.5-32B-Open-R1-Distill-jdy-ft
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-32B-Open-R1-Distill-jdy-ft
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) on the [jdy_analysis](https://huggingface.co/datasets/jdy_analysis) dataset.
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B).
 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/songhao9021-9uest/huggingface/runs/b9jksdu6) 
+[<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/songhao9021-9uest/huggingface/runs/mvb67nds) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 978754951168.0,
-    "train_loss": 1.4972400459749946,
-    "train_runtime": 1197.8134,
+    "total_flos": 955996483584.0,
+    "train_loss": 1.542164264054134,
+    "train_runtime": 1339.7897,
     "train_samples": 114,
-    "train_samples_per_second": 0.095,
-    "train_steps_per_second": 0.024
+    "train_samples_per_second": 0.085,
+    "train_steps_per_second": 0.022
 }

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 152064
 }

model-00001-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c98ad299bfb0ad21d3f4f30c9b46bd079c5abffddb796045f20d9a6235745778
+oid sha256:723e9cc765fe6d7e1298eb0b8a8a36aafb71c64b3afc05efb71b329ca7e3ca03
 size 4891730992

model-00002-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c239207fe1daed298851ed1e20c6cfe0b8ac4e8370db4ef2735ed8f492ecb06
+oid sha256:9d9f0f73d44a40e5d87ca8db4efefeb94d54215c5e098537b2cff4b175b98e76
 size 4876059352

model-00003-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8913b0145e91f057b5d9a5590ac42336272ac82a3d03662704bb49db5e056e7c
+oid sha256:a2d339ee1815d9b130f674be93c8e5e1a1e9f3b316cd87176a2474b2baf8ec18
 size 4876059384

model-00004-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57d337ac26eb0a1f348b5b7b609c150bcf86ea24e68edcc5cf9cbffe80236bf6
+oid sha256:cdf440c8fdcfc19be30d1512774c9a57208c7b15fe1a39bb2e185a22f9677cfa
 size 4876059416

model-00005-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5e7da71a26e0279b0a8114371a973654ee48b29ef5f75a4f3b908522d991740
+oid sha256:752f257f75f379c6e9701a6fe26d150be02099356f874dcf509b891c8846ff63
 size 4876059416

model-00006-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3caf9484d748eabf2cb6ef903ab2ed3613bfbe5b0f0980cb6a3618b5bca5d590
+oid sha256:2e013b32e86bb103c9e995121a2295bd64190b7fdd49e2deda46c66006558049
 size 4876059416

model-00007-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c1caa1accd0b3f811e76c114728d1a9b689c0073654880521902697ae800463
+oid sha256:c7d868db5bb5231bafa3eff67d81fc8cec1a0789c4a874f850b2bb02282b185d
 size 4876059416

model-00008-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46eae515c6642f537372a2d531b8a8bec79fc9a97eec73fde60c176bf4bc7eef
+oid sha256:9dcac482f774c4ed4528af65f31b2c4a70882c0446b9bcfbbfbd5e38dd213823
 size 4876059416

model-00009-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef6c7494e61f9cb5d591e64303874956a5b5825bc3195fc315d0e6aec4e0ffab
+oid sha256:1459f8167fa1376bc6245f54a8db86f17fcf360cfc533b9890b6da451984a15d
 size 4876059416

model-00010-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a1f5fada1ea8b081533df536b6a7f226105c1df01d8296381671c1dea312218
+oid sha256:0bbce57bb600be813a27649838b5f1397e7de9d003328c8a2b6162e75624d8f9
 size 4876059416

model-00011-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea50b5b5edce1b55fb34d465e1d701b8d2a3242319b1e275cdd6140c78b1b358
+oid sha256:a7c2a839fcd50146834b27e6356b8df535409f0fe5df5fd9761a1d6e813ce325
 size 4876059416

model-00012-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecfcdd48c9481edbd8826c679280745e6b87074bf97e85b1a596e2e548b02477
+oid sha256:278cbfc415104daa0bdd51d7dca602ce8987200636a19b03f4a191a72f8d87fb
 size 4876059416

model-00013-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cbc5dfea8eb28ba59749282884883bc6f1805b63366cf92bfbe54160bc52309
+oid sha256:1f30cb4f146ffc55d56f89c3ee3b8db64c3c42b2b74710d47dbde71a90b89071
 size 4876059416

model-00014-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f447e36f64421c710826847bff3ae27e7e28cc5768f0db0b58700d3a7fd62ed1
+oid sha256:8db71c7aa728cd9ffff7032ee0b7afa1a17db979e4ceec6be6734fd1f1a4f791
 size 2123397800

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 978754951168.0,
-    "train_loss": 1.4972400459749946,
-    "train_runtime": 1197.8134,
+    "total_flos": 955996483584.0,
+    "train_loss": 1.542164264054134,
+    "train_runtime": 1339.7897,
     "train_samples": 114,
-    "train_samples_per_second": 0.095,
-    "train_steps_per_second": 0.024
+    "train_samples_per_second": 0.085,
+    "train_steps_per_second": 0.022
 }

trainer_state.json

@@ -10,244 +10,244 @@
   "log_history": [
     {
       "epoch": 0.034482758620689655,
-      "grad_norm": 3.9996883869171143,
+      "grad_norm": 4.296210765838623,
       "learning_rate": 3.333333333333333e-07,
-      "loss": 1.4892,
-      "mean_token_accuracy": 0.6603646278381348,
+      "loss": 1.5533,
+      "mean_token_accuracy": 0.6920064091682434,
       "step": 1
     },
     {
       "epoch": 0.06896551724137931,
-      "grad_norm": 4.237244606018066,
+      "grad_norm": 5.163259029388428,
       "learning_rate": 6.666666666666666e-07,
-      "loss": 1.4666,
-      "mean_token_accuracy": 0.7045964002609253,
+      "loss": 1.7853,
+      "mean_token_accuracy": 0.6263327598571777,
       "step": 2
     },
     {
       "epoch": 0.10344827586206896,
-      "grad_norm": 4.874926567077637,
+      "grad_norm": 4.452831745147705,
       "learning_rate": 1e-06,
-      "loss": 1.7228,
-      "mean_token_accuracy": 0.6302095651626587,
+      "loss": 1.5075,
+      "mean_token_accuracy": 0.7126692533493042,
       "step": 3
     },
     {
       "epoch": 0.13793103448275862,
-      "grad_norm": 4.235203266143799,
+      "grad_norm": 6.790956497192383,
       "learning_rate": 9.963544370490268e-07,
-      "loss": 1.4493,
-      "mean_token_accuracy": 0.6814345717430115,
+      "loss": 1.9253,
+      "mean_token_accuracy": 0.6712393760681152,
       "step": 4
     },
     {
       "epoch": 0.1724137931034483,
-      "grad_norm": 7.380453109741211,
+      "grad_norm": 3.9182674884796143,
       "learning_rate": 9.85470908713026e-07,
-      "loss": 2.0416,
-      "mean_token_accuracy": 0.6577650904655457,
+      "loss": 1.6858,
+      "mean_token_accuracy": 0.559170126914978,
       "step": 5
     },
     {
       "epoch": 0.20689655172413793,
-      "grad_norm": 3.541438341140747,
+      "grad_norm": 3.839620351791382,
       "learning_rate": 9.675081213427074e-07,
-      "loss": 1.2546,
-      "mean_token_accuracy": 0.7483809590339661,
+      "loss": 1.5418,
+      "mean_token_accuracy": 0.6354226469993591,
       "step": 6
     },
     {
       "epoch": 0.2413793103448276,
-      "grad_norm": 3.448702812194824,
+      "grad_norm": 4.464385986328125,
       "learning_rate": 9.427280128266049e-07,
-      "loss": 1.3896,
-      "mean_token_accuracy": 0.6593328714370728,
+      "loss": 1.5432,
+      "mean_token_accuracy": 0.6771755814552307,
       "step": 7
     },
     {
       "epoch": 0.27586206896551724,
-      "grad_norm": 3.706294298171997,
+      "grad_norm": 3.300748348236084,
       "learning_rate": 9.114919329468282e-07,
-      "loss": 1.4015,
-      "mean_token_accuracy": 0.6922000646591187,
+      "loss": 1.3202,
+      "mean_token_accuracy": 0.6744688153266907,
       "step": 8
     },
     {
       "epoch": 0.3103448275862069,
-      "grad_norm": 4.539882659912109,
+      "grad_norm": 4.529242515563965,
       "learning_rate": 8.742553740855505e-07,
-      "loss": 1.7425,
-      "mean_token_accuracy": 0.5878053307533264,
+      "loss": 1.5632,
+      "mean_token_accuracy": 0.7091418504714966,
       "step": 9
     },
     {
       "epoch": 0.3448275862068966,
-      "grad_norm": 3.8082709312438965,
+      "grad_norm": 4.9364800453186035,
       "learning_rate": 8.315613291203976e-07,
-      "loss": 1.4157,
-      "mean_token_accuracy": 0.6789916157722473,
+      "loss": 1.3939,
+      "mean_token_accuracy": 0.676058828830719,
       "step": 10
     },
     {
       "epoch": 0.3793103448275862,
-      "grad_norm": 5.028677940368652,
+      "grad_norm": 4.520140171051025,
       "learning_rate": 7.840323733655778e-07,
-      "loss": 1.755,
-      "mean_token_accuracy": 0.6366782188415527,
+      "loss": 1.6434,
+      "mean_token_accuracy": 0.6085848808288574,
       "step": 11
     },
     {
       "epoch": 0.41379310344827586,
-      "grad_norm": 5.152957439422607,
+      "grad_norm": 3.786013126373291,
       "learning_rate": 7.323615860218842e-07,
-      "loss": 1.7695,
-      "mean_token_accuracy": 0.6314002275466919,
+      "loss": 1.4203,
+      "mean_token_accuracy": 0.6495858430862427,
       "step": 12
     },
     {
       "epoch": 0.4482758620689655,
-      "grad_norm": 3.268697738647461,
+      "grad_norm": 4.0102105140686035,
       "learning_rate": 6.773024435212677e-07,
-      "loss": 1.4895,
-      "mean_token_accuracy": 0.6149526834487915,
+      "loss": 1.4744,
+      "mean_token_accuracy": 0.715476393699646,
       "step": 13
     },
     {
       "epoch": 0.4827586206896552,
-      "grad_norm": 3.3466408252716064,
+      "grad_norm": 6.1422576904296875,
       "learning_rate": 6.196578321437789e-07,
-      "loss": 1.1299,
-      "mean_token_accuracy": 0.7559174299240112,
+      "loss": 1.7096,
+      "mean_token_accuracy": 0.6734651327133179,
       "step": 14
     },
     {
       "epoch": 0.5172413793103449,
-      "grad_norm": 4.494246482849121,
+      "grad_norm": 4.225828647613525,
       "learning_rate": 5.602683401276614e-07,
-      "loss": 1.5723,
-      "mean_token_accuracy": 0.6703522801399231,
+      "loss": 1.6184,
+      "mean_token_accuracy": 0.6401326656341553,
       "step": 15
     },
     {
       "epoch": 0.5517241379310345,
-      "grad_norm": 2.2075376510620117,
+      "grad_norm": 2.499864101409912,
       "learning_rate": 5e-07,
-      "loss": 1.0356,
-      "mean_token_accuracy": 0.7093867063522339,
+      "loss": 1.0916,
+      "mean_token_accuracy": 0.712737500667572,
       "step": 16
     },
     {
       "epoch": 0.5862068965517241,
-      "grad_norm": 2.7901251316070557,
+      "grad_norm": 3.797278881072998,
       "learning_rate": 4.397316598723385e-07,
-      "loss": 1.1132,
-      "mean_token_accuracy": 0.7466140985488892,
+      "loss": 1.5532,
+      "mean_token_accuracy": 0.6137330532073975,
       "step": 17
     },
     {
       "epoch": 0.6206896551724138,
-      "grad_norm": 3.604022979736328,
+      "grad_norm": 3.9196736812591553,
       "learning_rate": 3.8034216785622125e-07,
-      "loss": 1.3046,
-      "mean_token_accuracy": 0.7072184681892395,
+      "loss": 1.5172,
+      "mean_token_accuracy": 0.6513392925262451,
       "step": 18
     },
     {
       "epoch": 0.6551724137931034,
-      "grad_norm": 3.637402057647705,
+      "grad_norm": 3.312458038330078,
       "learning_rate": 3.2269755647873214e-07,
-      "loss": 1.5471,
-      "mean_token_accuracy": 0.6090646386146545,
+      "loss": 1.4259,
+      "mean_token_accuracy": 0.6606206893920898,
       "step": 19
     },
     {
       "epoch": 0.6896551724137931,
-      "grad_norm": 3.484041452407837,
+      "grad_norm": 4.863149642944336,
       "learning_rate": 2.676384139781157e-07,
-      "loss": 1.4808,
-      "mean_token_accuracy": 0.6458947658538818,
+      "loss": 1.801,
+      "mean_token_accuracy": 0.6028177738189697,
       "step": 20
     },
     {
       "epoch": 0.7241379310344828,
-      "grad_norm": 4.93519926071167,
+      "grad_norm": 6.340369701385498,
       "learning_rate": 2.1596762663442213e-07,
-      "loss": 1.853,
-      "mean_token_accuracy": 0.6095913648605347,
+      "loss": 1.8937,
+      "mean_token_accuracy": 0.6635770797729492,
       "step": 21
     },
     {
       "epoch": 0.7586206896551724,
-      "grad_norm": 6.128385543823242,
+      "grad_norm": 2.400047540664673,
       "learning_rate": 1.6843867087960251e-07,
-      "loss": 1.552,
-      "mean_token_accuracy": 0.6161980032920837,
+      "loss": 1.1017,
+      "mean_token_accuracy": 0.7170366048812866,
       "step": 22
     },
     {
       "epoch": 0.7931034482758621,
-      "grad_norm": 5.635701656341553,
+      "grad_norm": 6.618093490600586,
       "learning_rate": 1.257446259144494e-07,
-      "loss": 1.5498,
-      "mean_token_accuracy": 0.7546396851539612,
+      "loss": 1.8901,
+      "mean_token_accuracy": 0.6319121718406677,
       "step": 23
     },
     {
       "epoch": 0.8275862068965517,
-      "grad_norm": 3.2936410903930664,
+      "grad_norm": 3.391517400741577,
       "learning_rate": 8.850806705317182e-08,
-      "loss": 1.542,
-      "mean_token_accuracy": 0.5884397029876709,
+      "loss": 1.3663,
+      "mean_token_accuracy": 0.6898515224456787,
       "step": 24
     },
     {
       "epoch": 0.8620689655172413,
-      "grad_norm": 3.3056509494781494,
+      "grad_norm": 4.413179874420166,
       "learning_rate": 5.72719871733951e-08,
-      "loss": 1.4571,
-      "mean_token_accuracy": 0.677709698677063,
+      "loss": 1.5641,
+      "mean_token_accuracy": 0.6674157381057739,
       "step": 25
     },
     {
       "epoch": 0.896551724137931,
-      "grad_norm": 3.8348419666290283,
+      "grad_norm": 4.75150728225708,
       "learning_rate": 3.2491878657292635e-08,
-      "loss": 1.5325,
-      "mean_token_accuracy": 0.6370223760604858,
+      "loss": 1.6575,
+      "mean_token_accuracy": 0.6414722204208374,
       "step": 26
     },
     {
       "epoch": 0.9310344827586207,
-      "grad_norm": 3.4010775089263916,
+      "grad_norm": 3.682435989379883,
       "learning_rate": 1.4529091286973993e-08,
-      "loss": 1.3759,
-      "mean_token_accuracy": 0.6779050230979919,
+      "loss": 1.3724,
+      "mean_token_accuracy": 0.674655020236969,
       "step": 27
     },
     {
       "epoch": 0.9655172413793104,
-      "grad_norm": 3.990252733230591,
+      "grad_norm": 3.129405975341797,
       "learning_rate": 3.6455629509730135e-09,
-      "loss": 1.4335,
-      "mean_token_accuracy": 0.688022255897522,
+      "loss": 1.5536,
+      "mean_token_accuracy": 0.5809841752052307,
       "step": 28
     },
     {
       "epoch": 1.0,
-      "grad_norm": 4.286991596221924,
+      "grad_norm": 2.9102606773376465,
       "learning_rate": 0.0,
-      "loss": 1.5531,
-      "mean_token_accuracy": 0.6274685859680176,
+      "loss": 1.2491,
+      "mean_token_accuracy": 0.6780526041984558,
       "step": 29
     },
     {
       "epoch": 1.0,
       "step": 29,
-      "total_flos": 978754951168.0,
-      "train_loss": 1.4972400459749946,
-      "train_runtime": 1197.8134,
-      "train_samples_per_second": 0.095,
-      "train_steps_per_second": 0.024
+      "total_flos": 955996483584.0,
+      "train_loss": 1.542164264054134,
+      "train_runtime": 1339.7897,
+      "train_samples_per_second": 0.085,
+      "train_steps_per_second": 0.022
     }
   ],
   "logging_steps": 1,
@@ -267,7 +267,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 978754951168.0,
+  "total_flos": 955996483584.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e8bf88eeb802e31b36a5851e691b0655ff8116d2b7229b7ff93ac1200c5af3
+oid sha256:2d32fdd6e3debf45b5ea78119281481411bda5d400189c4d03a7bc24c2d0bc3d
 size 7864