End of training

README.md

@@ -1,7 +1,10 @@
 ---
 library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen3-8B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: gpt-oss-120B-stack-overflow-32ep-131k-summtrc
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gpt-oss-120B-stack-overflow-32ep-131k-summtrc
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the DCAgent2/gpt-oss-120B-stack-overflow-32ep-131k-summtrc dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 0.6998917596550104,
+    "achieved_tflops_per_gpu_theoretical": 189.7226555180974,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.25550705194473267,
+    "mfu_percent": 0.22432428194070844,
+    "mfu_percent_theoretical": 60.80854343528763,
+    "total_flos": 4.3179169980769894e+17,
+    "train_loss": 0.5313117267349349,
+    "train_runtime": 77117.5853,
+    "train_samples_per_second": 0.9,
+    "train_steps_per_second": 0.056,
+    "valid_targets_mean": 1777.2,
+    "valid_targets_min": 540
+}

train_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 0.6998917596550104,
+    "achieved_tflops_per_gpu_theoretical": 189.7226555180974,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.25550705194473267,
+    "mfu_percent": 0.22432428194070844,
+    "mfu_percent_theoretical": 60.80854343528763,
+    "total_flos": 4.3179169980769894e+17,
+    "train_loss": 0.5313117267349349,
+    "train_runtime": 77117.5853,
+    "train_samples_per_second": 0.9,
+    "train_steps_per_second": 0.056,
+    "valid_targets_mean": 1777.2,
+    "valid_targets_min": 540
+}