End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # nemo_nano_code_1k
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/nemo_nano_code_1k dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 6.72,
     "total_flos": 1.1369810464499302e+17,
-    "train_loss": 0.4443133288196155,
-    "train_runtime": 5664.5559,
-    "train_samples_per_second": 1.236,
-    "train_steps_per_second": 0.012
+    "train_loss": 0.0,
+    "train_runtime": 2.5147,
+    "train_samples_per_second": 2783.603,
+    "train_steps_per_second": 27.836
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 6.72,
     "total_flos": 1.1369810464499302e+17,
-    "train_loss": 0.4443133288196155,
-    "train_runtime": 5664.5559,
-    "train_samples_per_second": 1.236,
-    "train_steps_per_second": 0.012
+    "train_loss": 0.0,
+    "train_runtime": 2.5147,
+    "train_samples_per_second": 2783.603,
+    "train_steps_per_second": 27.836
 }

trainer_state.json

@@ -502,10 +502,10 @@
       "epoch": 6.72,
       "step": 70,
       "total_flos": 1.1369810464499302e+17,
-      "train_loss": 0.4443133288196155,
-      "train_runtime": 5664.5559,
-      "train_samples_per_second": 1.236,
-      "train_steps_per_second": 0.012
+      "train_loss": 0.0,
+      "train_runtime": 2.5147,
+      "train_samples_per_second": 2783.603,
+      "train_steps_per_second": 27.836
     }
   ],
   "logging_steps": 1,