End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # e1_math_all_phi
 
-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/e1_math_all_phi dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 1.6787206024137277e+18,
-    "train_loss": 0.9509255293409834,
-    "train_runtime": 7299.169,
-    "train_samples_per_second": 21.646,
-    "train_steps_per_second": 0.169
+    "train_loss": 0.0,
+    "train_runtime": 3.5426,
+    "train_samples_per_second": 44600.403,
+    "train_steps_per_second": 348.617
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 1.6787206024137277e+18,
-    "train_loss": 0.9509255293409834,
-    "train_runtime": 7299.169,
-    "train_samples_per_second": 21.646,
-    "train_steps_per_second": 0.169
+    "train_loss": 0.0,
+    "train_runtime": 3.5426,
+    "train_samples_per_second": 44600.403,
+    "train_steps_per_second": 348.617
 }

trainer_state.json

@@ -8657,10 +8657,10 @@
       "epoch": 5.0,
       "step": 1235,
       "total_flos": 1.6787206024137277e+18,
-      "train_loss": 0.9509255293409834,
-      "train_runtime": 7299.169,
-      "train_samples_per_second": 21.646,
-      "train_steps_per_second": 0.169
+      "train_loss": 0.0,
+      "train_runtime": 3.5426,
+      "train_samples_per_second": 44600.403,
+      "train_steps_per_second": 348.617
     }
   ],
   "logging_steps": 1,