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: qwen2.5_1.5b_500k_O3_16kcw_2ep_risc
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen2.5_1.5b_500k_O3_16kcw_2ep_risc
 
-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 anghabench_o3 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0186
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.01856272667646408,
+    "eval_runtime": 4.0104,
+    "eval_samples_per_second": 49.87,
+    "eval_steps_per_second": 24.935,
+    "total_flos": 1.1570533976082743e+19,
+    "train_loss": 0.03249076200670694,
+    "train_runtime": 108704.5915,
+    "train_samples_per_second": 9.095,
+    "train_steps_per_second": 2.274
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.01856272667646408,
+    "eval_runtime": 4.0104,
+    "eval_samples_per_second": 49.87,
+    "eval_steps_per_second": 24.935
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.1570533976082743e+19,
+    "train_loss": 0.03249076200670694,
+    "train_runtime": 108704.5915,
+    "train_samples_per_second": 9.095,
+    "train_steps_per_second": 2.274
+}