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: ex26_qwen2.5_1.5b_500k_16kcw_2ep_O2_risc
@@ -15,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ex26_qwen2.5_1.5b_500k_16kcw_2ep_O2_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 anghabencho2_16k dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0150
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.9999460825610784,
+    "eval_loss": 0.015018176287412643,
+    "eval_runtime": 3.7274,
+    "eval_samples_per_second": 53.656,
+    "eval_steps_per_second": 26.828,
+    "total_flos": 1.8998956805654053e+19,
+    "train_loss": 0.04169469768040635,
+    "train_runtime": 114542.7696,
+    "train_samples_per_second": 10.363,
+    "train_steps_per_second": 0.324
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.9999460825610784,
+    "eval_loss": 0.015018176287412643,
+    "eval_runtime": 3.7274,
+    "eval_samples_per_second": 53.656,
+    "eval_steps_per_second": 26.828
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9999460825610784,
+    "total_flos": 1.8998956805654053e+19,
+    "train_loss": 0.04169469768040635,
+    "train_runtime": 114542.7696,
+    "train_samples_per_second": 10.363,
+    "train_steps_per_second": 0.324
+}