End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # nemo_nano_code_0.3k
 
-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_0.3k dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 12.30379746835443,
     "total_flos": 5.43823155429376e+16,
-    "train_loss": 0.3318551993395528,
-    "train_runtime": 3757.0997,
-    "train_samples_per_second": 1.093,
-    "train_steps_per_second": 0.031
+    "train_loss": 0.0,
+    "train_runtime": 2.2596,
+    "train_samples_per_second": 1817.981,
+    "train_steps_per_second": 51.778
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 12.30379746835443,
     "total_flos": 5.43823155429376e+16,
-    "train_loss": 0.3318551993395528,
-    "train_runtime": 3757.0997,
-    "train_samples_per_second": 1.093,
-    "train_steps_per_second": 0.031
+    "train_loss": 0.0,
+    "train_runtime": 2.2596,
+    "train_samples_per_second": 1817.981,
+    "train_steps_per_second": 51.778
 }

trainer_state.json

@@ -831,10 +831,10 @@
       "epoch": 12.30379746835443,
       "step": 117,
       "total_flos": 5.43823155429376e+16,
-      "train_loss": 0.3318551993395528,
-      "train_runtime": 3757.0997,
-      "train_samples_per_second": 1.093,
-      "train_steps_per_second": 0.031
+      "train_loss": 0.0,
+      "train_runtime": 2.2596,
+      "train_samples_per_second": 1817.981,
+      "train_steps_per_second": 51.778
     }
   ],
   "logging_steps": 1,