End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-7B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: e1_science_longest_r1
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # e1_science_longest_r1
 
-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_science_longest_r1 dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.9869587897756915,
     "total_flos": 2.8011398523411825e+18,
-    "train_loss": 0.0,
-    "train_runtime": 4.4131,
-    "train_samples_per_second": 34739.752,
-    "train_steps_per_second": 270.785
+    "train_loss": 0.4013182716763668,
+    "train_runtime": 47374.7157,
+    "train_samples_per_second": 3.236,
+    "train_steps_per_second": 0.025
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.9869587897756915,
     "total_flos": 2.8011398523411825e+18,
-    "train_loss": 0.0,
-    "train_runtime": 4.4131,
-    "train_samples_per_second": 34739.752,
-    "train_steps_per_second": 270.785
+    "train_loss": 0.4013182716763668,
+    "train_runtime": 47374.7157,
+    "train_samples_per_second": 3.236,
+    "train_steps_per_second": 0.025
 }