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: code-contests-sandboxes-traces-terminus-2_global-batch-size_16
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # code-contests-sandboxes-traces-terminus-2_global-batch-size_16
 
-This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the mlfoundations-dev/code-contests-sandboxes-traces-terminus-2 dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 2.979440010208909,
+    "achieved_tflops_per_gpu_theoretical": 348.9541699707863,
+    "epoch": 5.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.1909605711698532,
+    "mfu_percent": 0.3012578372304256,
+    "mfu_percent_theoretical": 35.283535891889414,
+    "total_flos": 7.266001898207969e+17,
+    "train_loss": 0.3592725233459473,
+    "train_runtime": 30483.9243,
+    "train_samples_per_second": 1.64,
+    "train_steps_per_second": 0.103,
+    "valid_targets_mean": 3954.1,
+    "valid_targets_min": 1068
+}

train_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 2.979440010208909,
+    "achieved_tflops_per_gpu_theoretical": 348.9541699707863,
+    "epoch": 5.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.1909605711698532,
+    "mfu_percent": 0.3012578372304256,
+    "mfu_percent_theoretical": 35.283535891889414,
+    "total_flos": 7.266001898207969e+17,
+    "train_loss": 0.3592725233459473,
+    "train_runtime": 30483.9243,
+    "train_samples_per_second": 1.64,
+    "train_steps_per_second": 0.103,
+    "valid_targets_mean": 3954.1,
+    "valid_targets_min": 1068
+}