End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-7B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: qwen_s1ablation_diversity_sampling_27k
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen_s1ablation_diversity_sampling_27k
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/s1_ablation_diversity_sampling_27k dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.999341672152732,
+    "total_flos": 8.138715082826711e+17,
+    "train_loss": 0.008948151262695454,
+    "train_runtime": 693.8105,
+    "train_samples_per_second": 105.059,
+    "train_steps_per_second": 1.094
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.999341672152732,
+    "total_flos": 8.138715082826711e+17,
+    "train_loss": 0.008948151262695454,
+    "train_runtime": 693.8105,
+    "train_samples_per_second": 105.059,
+    "train_steps_per_second": 1.094
+}