End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # SFT_Advanced_Risk_Dice_Qwen3_4B_Base
 
-This model is a fine-tuned version of [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) on the Advanced_Risk_Dice_Qwen3_4B_Base dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.9230769230769231,
     "total_flos": 143598747648.0,
-    "train_loss": 0.4763137102127075,
-    "train_runtime": 235.6976,
-    "train_samples_per_second": 1.714,
-    "train_steps_per_second": 0.025
+    "train_loss": 0.4765191872914632,
+    "train_runtime": 229.2539,
+    "train_samples_per_second": 1.762,
+    "train_steps_per_second": 0.026
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.9230769230769231,
     "total_flos": 143598747648.0,
-    "train_loss": 0.4763137102127075,
-    "train_runtime": 235.6976,
-    "train_samples_per_second": 1.714,
-    "train_steps_per_second": 0.025
+    "train_loss": 0.4765191872914632,
+    "train_runtime": 229.2539,
+    "train_samples_per_second": 1.762,
+    "train_steps_per_second": 0.026
 }

trainer_state.json

@@ -13,10 +13,10 @@
       "epoch": 0.9230769230769231,
       "step": 6,
       "total_flos": 143598747648.0,
-      "train_loss": 0.4763137102127075,
-      "train_runtime": 235.6976,
-      "train_samples_per_second": 1.714,
-      "train_steps_per_second": 0.025
+      "train_loss": 0.4765191872914632,
+      "train_runtime": 229.2539,
+      "train_samples_per_second": 1.762,
+      "train_steps_per_second": 0.026
     }
   ],
   "logging_steps": 10,