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_llamafac_130k-stack
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen2.5_0.5b_llamafac_130k-stack
 
-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: 0.0098
+- Loss: 0.0068
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9995807518516795,
+    "eval_loss": 0.006840116810053587,
+    "eval_runtime": 3.8972,
+    "eval_samples_per_second": 51.319,
+    "eval_steps_per_second": 12.83,
+    "total_flos": 1.2695660559534653e+18,
+    "train_loss": 0.020097828387903093,
+    "train_runtime": 24374.3923,
+    "train_samples_per_second": 10.569,
+    "train_steps_per_second": 0.66
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9995807518516795,
+    "eval_loss": 0.006840116810053587,
+    "eval_runtime": 3.8972,
+    "eval_samples_per_second": 51.319,
+    "eval_steps_per_second": 12.83
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9995807518516795,
+    "total_flos": 1.2695660559534653e+18,
+    "train_loss": 0.020097828387903093,
+    "train_runtime": 24374.3923,
+    "train_samples_per_second": 10.569,
+    "train_steps_per_second": 0.66
+}