End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # c1_science_0d_1s
 
-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/c1_science_0d_1s dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.982278481012658,
     "total_flos": 2.525762970561757e+18,
-    "train_loss": 0.41162928419142236,
-    "train_runtime": 39803.4607,
-    "train_samples_per_second": 3.968,
-    "train_steps_per_second": 0.031
+    "train_loss": 0.0,
+    "train_runtime": 1.7951,
+    "train_samples_per_second": 88017.078,
+    "train_steps_per_second": 685.196
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.982278481012658,
     "total_flos": 2.525762970561757e+18,
-    "train_loss": 0.41162928419142236,
-    "train_runtime": 39803.4607,
-    "train_samples_per_second": 3.968,
-    "train_steps_per_second": 0.031
+    "train_loss": 0.0,
+    "train_runtime": 1.7951,
+    "train_samples_per_second": 88017.078,
+    "train_steps_per_second": 685.196
 }

trainer_state.json

@@ -8622,10 +8622,10 @@
       "epoch": 4.982278481012658,
       "step": 1230,
       "total_flos": 2.525762970561757e+18,
-      "train_loss": 0.41162928419142236,
-      "train_runtime": 39803.4607,
-      "train_samples_per_second": 3.968,
-      "train_steps_per_second": 0.031
+      "train_loss": 0.0,
+      "train_runtime": 1.7951,
+      "train_samples_per_second": 88017.078,
+      "train_steps_per_second": 685.196
     }
   ],
   "logging_steps": 1,