End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen_openthoughts_science_claude
 
-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/open-thoughts-science-claude dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.9908374174302153,
-    "total_flos": 5.823250357953757e+18,
-    "train_loss": 0.4340486013453845,
-    "train_runtime": 43453.4374,
-    "train_samples_per_second": 5.184,
-    "train_steps_per_second": 0.01
+    "epoch": 2.987419245154709,
+    "total_flos": 7.259120111838036e+18,
+    "train_loss": 0.5428441533675561,
+    "train_runtime": 82839.4057,
+    "train_samples_per_second": 1.704,
+    "train_steps_per_second": 0.003
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.9908374174302153,
-    "total_flos": 5.823250357953757e+18,
-    "train_loss": 0.4340486013453845,
-    "train_runtime": 43453.4374,
-    "train_samples_per_second": 5.184,
-    "train_steps_per_second": 0.01
+    "epoch": 2.987419245154709,
+    "total_flos": 7.259120111838036e+18,
+    "train_loss": 0.5428441533675561,
+    "train_runtime": 82839.4057,
+    "train_samples_per_second": 1.704,
+    "train_steps_per_second": 0.003
 }