End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen2.5-32b-openalex
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) on the openalex dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.9991031390134529,
     "total_flos": 7841700554735616.0,
-    "train_loss": 0.4275342236729456,
-    "train_runtime": 63728.3403,
-    "train_samples_per_second": 2.239,
-    "train_steps_per_second": 0.009
+    "train_loss": 0.0,
+    "train_runtime": 1.3623,
+    "train_samples_per_second": 104762.356,
+    "train_steps_per_second": 408.87
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.9991031390134529,
     "total_flos": 7841700554735616.0,
-    "train_loss": 0.4275342236729456,
-    "train_runtime": 63728.3403,
-    "train_samples_per_second": 2.239,
-    "train_steps_per_second": 0.009
+    "train_loss": 0.0,
+    "train_runtime": 1.3623,
+    "train_samples_per_second": 104762.356,
+    "train_steps_per_second": 408.87
 }

trainer_state.json

@@ -3911,10 +3911,10 @@
       "epoch": 0.9991031390134529,
       "step": 557,
       "total_flos": 7841700554735616.0,
-      "train_loss": 0.4275342236729456,
-      "train_runtime": 63728.3403,
-      "train_samples_per_second": 2.239,
-      "train_steps_per_second": 0.009
+      "train_loss": 0.0,
+      "train_runtime": 1.3623,
+      "train_samples_per_second": 104762.356,
+      "train_steps_per_second": 408.87
     }
   ],
   "logging_steps": 1,