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: b1_code_top_4
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # b1_code_top_4
 
-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/b1_code_top_4 dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "total_flos": 3.0981921380100997e+18,
-    "train_loss": 0.0,
-    "train_runtime": 1.72,
-    "train_samples_per_second": 91859.139,
-    "train_steps_per_second": 718.013
+    "total_flos": 3.233802660553425e+18,
+    "train_loss": 0.4578841227992826,
+    "train_runtime": 28049.3395,
+    "train_samples_per_second": 5.633,
+    "train_steps_per_second": 0.044
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "total_flos": 3.0981921380100997e+18,
-    "train_loss": 0.0,
-    "train_runtime": 1.72,
-    "train_samples_per_second": 91859.139,
-    "train_steps_per_second": 718.013
+    "total_flos": 3.233802660553425e+18,
+    "train_loss": 0.4578841227992826,
+    "train_runtime": 28049.3395,
+    "train_samples_per_second": 5.633,
+    "train_steps_per_second": 0.044
 }