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_1M_stack_16kcw_2ep
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen2.5_0.5b_1M_stack_16kcw_2ep
 
-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 None 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_1M_1, the anghabench_1M_2 and the stack datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.0020
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.9999935863106213,
+    "eval_loss": 0.0019563338719308376,
+    "eval_runtime": 3.3586,
+    "eval_samples_per_second": 59.549,
+    "eval_steps_per_second": 14.887,
+    "total_flos": 1.0432719577686213e+19,
+    "train_loss": 0.004895635656955134,
+    "train_runtime": 187864.5289,
+    "train_samples_per_second": 13.279,
+    "train_steps_per_second": 1.66
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.9999935863106213,
+    "eval_loss": 0.0019563338719308376,
+    "eval_runtime": 3.3586,
+    "eval_samples_per_second": 59.549,
+    "eval_steps_per_second": 14.887
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9999935863106213,
+    "total_flos": 1.0432719577686213e+19,
+    "train_loss": 0.004895635656955134,
+    "train_runtime": 187864.5289,
+    "train_samples_per_second": 13.279,
+    "train_steps_per_second": 1.66
+}