End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: ex27_qwen2.5_1.5b_500k_16kcw_2ep_O2_arm
@@ -15,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ex27_qwen2.5_1.5b_500k_16kcw_2ep_O2_arm
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on the anghabencho2_16k dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0037
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.9999440700243296,
+    "eval_loss": 0.0036745350807905197,
+    "eval_runtime": 4.4482,
+    "eval_samples_per_second": 44.962,
+    "eval_steps_per_second": 22.481,
+    "total_flos": 2.104089093791233e+19,
+    "train_loss": 0.013820042532603908,
+    "train_runtime": 130820.0015,
+    "train_samples_per_second": 8.747,
+    "train_steps_per_second": 0.273
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.9999440700243296,
+    "eval_loss": 0.0036745350807905197,
+    "eval_runtime": 4.4482,
+    "eval_samples_per_second": 44.962,
+    "eval_steps_per_second": 22.481
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9999440700243296,
+    "total_flos": 2.104089093791233e+19,
+    "train_loss": 0.013820042532603908,
+    "train_runtime": 130820.0015,
+    "train_samples_per_second": 8.747,
+    "train_steps_per_second": 0.273
+}