End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # nemo_nano_code_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_3k dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 6.850632911392405,
     "total_flos": 3.752328513370194e+17,
-    "train_loss": 0.3664968802061464,
-    "train_runtime": 17905.752,
-    "train_samples_per_second": 1.235,
-    "train_steps_per_second": 0.013
+    "train_loss": 0.0,
+    "train_runtime": 1.9604,
+    "train_samples_per_second": 11283.566,
+    "train_steps_per_second": 114.264
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 6.850632911392405,
     "total_flos": 3.752328513370194e+17,
-    "train_loss": 0.3664968802061464,
-    "train_runtime": 17905.752,
-    "train_samples_per_second": 1.235,
-    "train_steps_per_second": 0.013
+    "train_loss": 0.0,
+    "train_runtime": 1.9604,
+    "train_samples_per_second": 11283.566,
+    "train_steps_per_second": 114.264
 }

trainer_state.json

@@ -1580,10 +1580,10 @@
       "epoch": 6.850632911392405,
       "step": 224,
       "total_flos": 3.752328513370194e+17,
-      "train_loss": 0.3664968802061464,
-      "train_runtime": 17905.752,
-      "train_samples_per_second": 1.235,
-      "train_steps_per_second": 0.013
+      "train_loss": 0.0,
+      "train_runtime": 1.9604,
+      "train_samples_per_second": 11283.566,
+      "train_steps_per_second": 114.264
     }
   ],
   "logging_steps": 1,