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-bugsseq
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # r2egym-nl2bash-bugsseq
 
-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-inferredbugs-32eps-65k datasets.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 13.109296686310262,
+    "achieved_tflops_per_gpu_theoretical": 1107.844792043176,
+    "epoch": 6.999592999592999,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.04449460655450821,
+    "mfu_percent": 4.201697655868674,
+    "mfu_percent_theoretical": 355.0784589881975,
+    "total_flos": 2.7561038524606054e+18,
+    "train_loss": 0.015238219677667456,
+    "train_runtime": 26280.0507,
+    "train_samples_per_second": 5.235,
+    "train_steps_per_second": 0.327,
+    "valid_targets_mean": 4028.4,
+    "valid_targets_min": 1273
+}

train_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 13.109296686310262,
+    "achieved_tflops_per_gpu_theoretical": 1107.844792043176,
+    "epoch": 6.999592999592999,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.04449460655450821,
+    "mfu_percent": 4.201697655868674,
+    "mfu_percent_theoretical": 355.0784589881975,
+    "total_flos": 2.7561038524606054e+18,
+    "train_loss": 0.015238219677667456,
+    "train_runtime": 26280.0507,
+    "train_samples_per_second": 5.235,
+    "train_steps_per_second": 0.327,
+    "valid_targets_mean": 4028.4,
+    "valid_targets_min": 1273
+}