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: claude-4-5-sonnet-thinking-stackexchange-overflow-32ep-32k-traces
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # claude-4-5-sonnet-thinking-stackexchange-overflow-32ep-32k-traces
 
-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/claude-4-5-sonnet-thinking-stackexchange-overflow-32ep-32k-traces dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 2.7067145335487743,
+    "achieved_tflops_per_gpu_theoretical": 88.08551863340236,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.17071497440338135,
+    "mfu_percent": 0.867536709470761,
+    "mfu_percent_theoretical": 28.232538023526395,
+    "total_flos": 1.3627384946606735e+18,
+    "train_loss": 0.19606392417490914,
+    "train_runtime": 62933.2387,
+    "train_samples_per_second": 0.419,
+    "train_steps_per_second": 0.026,
+    "valid_targets_mean": 16957.1,
+    "valid_targets_min": 7571
+}

train_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 2.7067145335487743,
+    "achieved_tflops_per_gpu_theoretical": 88.08551863340236,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.17071497440338135,
+    "mfu_percent": 0.867536709470761,
+    "mfu_percent_theoretical": 28.232538023526395,
+    "total_flos": 1.3627384946606735e+18,
+    "train_loss": 0.19606392417490914,
+    "train_runtime": 62933.2387,
+    "train_samples_per_second": 0.419,
+    "train_steps_per_second": 0.026,
+    "valid_targets_mean": 16957.1,
+    "valid_targets_min": 7571
+}