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: r2egym-nl2bash-stackseq
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # r2egym-nl2bash-stackseq
 
-This model was trained from scratch 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-r2egym-32ep-32k, the penfever/GLM-4.6-nl2bash-verified-32eps-32k and the penfever/GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k datasets.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 10.344710879289135,
+    "achieved_tflops_per_gpu_theoretical": 918.1221365250786,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.11453244835138321,
+    "mfu_percent": 3.31561246131062,
+    "mfu_percent_theoretical": 294.2699155529098,
+    "total_flos": 2.7891230302346936e+18,
+    "train_loss": 0.027739192068844568,
+    "train_runtime": 33702.2835,
+    "train_samples_per_second": 4.331,
+    "train_steps_per_second": 0.271,
+    "valid_targets_mean": 7108.5,
+    "valid_targets_min": 2092
+}

train_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 10.344710879289135,
+    "achieved_tflops_per_gpu_theoretical": 918.1221365250786,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.11453244835138321,
+    "mfu_percent": 3.31561246131062,
+    "mfu_percent_theoretical": 294.2699155529098,
+    "total_flos": 2.7891230302346936e+18,
+    "train_loss": 0.027739192068844568,
+    "train_runtime": 33702.2835,
+    "train_samples_per_second": 4.331,
+    "train_steps_per_second": 0.271,
+    "valid_targets_mean": 7108.5,
+    "valid_targets_min": 2092
+}