End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-Coder-0.5B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: qwen2.5-0.5b-anghabench-32kcw
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen2.5-0.5b-anghabench-32kcw
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct) on the anghabench dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0016
+- Loss: 0.0015
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.001458541490137577,
+    "eval_runtime": 7.5809,
+    "eval_samples_per_second": 26.382,
+    "eval_steps_per_second": 6.596,
+    "total_flos": 389042235549696.0,
+    "train_loss": 0.008355458706034012,
+    "train_runtime": 62709.2593,
+    "train_samples_per_second": 7.797,
+    "train_steps_per_second": 0.975
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.001458541490137577,
+    "eval_runtime": 7.5809,
+    "eval_samples_per_second": 26.382,
+    "eval_steps_per_second": 6.596
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 389042235549696.0,
+    "train_loss": 0.008355458706034012,
+    "train_runtime": 62709.2593,
+    "train_samples_per_second": 7.797,
+    "train_steps_per_second": 0.975
+}