End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # etihad_demo
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the etihad_conversations_16k dataset.
 
 ## Model description
 

all_results.json

@@ -2,7 +2,7 @@
     "epoch": 3.0,
     "total_flos": 2267642331136.0,
     "train_loss": 2.263103802998861,
-    "train_runtime": 7.6591,
-    "train_samples_per_second": 0.392,
-    "train_steps_per_second": 0.392
+    "train_runtime": 6.9576,
+    "train_samples_per_second": 0.431,
+    "train_steps_per_second": 0.431
 }

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 3.0,
     "total_flos": 2267642331136.0,
     "train_loss": 2.263103802998861,
-    "train_runtime": 7.6591,
-    "train_samples_per_second": 0.392,
-    "train_steps_per_second": 0.392
+    "train_runtime": 6.9576,
+    "train_samples_per_second": 0.431,
+    "train_steps_per_second": 0.431
 }

trainer_state.json

@@ -14,9 +14,9 @@
       "step": 3,
       "total_flos": 2267642331136.0,
       "train_loss": 2.263103802998861,
-      "train_runtime": 7.6591,
-      "train_samples_per_second": 0.392,
-      "train_steps_per_second": 0.392
+      "train_runtime": 6.9576,
+      "train_samples_per_second": 0.431,
+      "train_steps_per_second": 0.431
     }
   ],
   "logging_steps": 10,