End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen3-8B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: bugs-nl2bashseq
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bugs-nl2bashseq
 
-This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the None dataset.
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the penfever/GLM-4.6-inferredbugs-32eps-65k and the penfever/GLM-4.6-nl2bash-verified-32eps-32k datasets.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 0.0036721295667827185,
+    "achieved_tflops_per_gpu_theoretical": 928.2858502135481,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.08077868074178696,
+    "mfu_percent": 0.0002595144570164465,
+    "mfu_percent_theoretical": 65.60324029777725,
+    "total_flos": 1429777853448192.0,
+    "train_loss": 0.1377790669734474,
+    "train_runtime": 24334.9572,
+    "train_samples_per_second": 4.375,
+    "train_steps_per_second": 0.274,
+    "valid_targets_mean": 1517.8,
+    "valid_targets_min": 393
+}

train_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 0.0036721295667827185,
+    "achieved_tflops_per_gpu_theoretical": 928.2858502135481,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.08077868074178696,
+    "mfu_percent": 0.0002595144570164465,
+    "mfu_percent_theoretical": 65.60324029777725,
+    "total_flos": 1429777853448192.0,
+    "train_loss": 0.1377790669734474,
+    "train_runtime": 24334.9572,
+    "train_samples_per_second": 4.375,
+    "train_steps_per_second": 0.274,
+    "valid_targets_mean": 1517.8,
+    "valid_targets_min": 393
+}