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: ex29_qwen2.5_1.5b_141k_16kcw_2ep_cuda_amd_all
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ex29_qwen2.5_1.5b_141k_16kcw_2ep_cuda_amd_all
 
-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 cuda_amd_141k dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9999440856607678,
+    "total_flos": 1.0843712808281965e+19,
+    "train_loss": 0.03612275462217664,
+    "train_runtime": 160033.9881,
+    "train_samples_per_second": 1.788,
+    "train_steps_per_second": 0.112
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9999440856607678,
+    "total_flos": 1.0843712808281965e+19,
+    "train_loss": 0.03612275462217664,
+    "train_runtime": 160033.9881,
+    "train_samples_per_second": 1.788,
+    "train_steps_per_second": 0.112
+}