Add files using upload-large-folder tool

.gitattributes

@@ -473,3 +473,292 @@ overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_orig
 overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-1520/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-1540/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-1560/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3160/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3220/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3260/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3340/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3380/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-340/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3440/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3520/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3540/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3560/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3580/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3620/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3640/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3660/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3680/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3720/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3740/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3780/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-380/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3820/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3840/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3860/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3880/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3920/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3940/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3960/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-3980/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-4020/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-440/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-520/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-540/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-560/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-580/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-620/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-640/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-660/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-680/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-720/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-740/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-780/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-80/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-820/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-840/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-860/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-880/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-920/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-940/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-960/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-980/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1020/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1040/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1060/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1080/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1140/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1160/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1220/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1260/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1340/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1380/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-140/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1440/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1520/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1540/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1560/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1580/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-160/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1620/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1640/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1660/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1680/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1720/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1740/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1780/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1820/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1840/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1860/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1880/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1920/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1940/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1960/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-1980/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-20/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2020/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2040/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2060/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2080/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2140/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2160/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-220/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2220/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2260/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2340/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2380/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2440/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2520/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2540/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2560/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2580/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-260/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2620/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2640/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2660/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2680/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2720/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2740/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2780/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2820/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2840/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2860/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2880/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2920/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2940/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2960/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-2980/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3020/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3040/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3060/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3080/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3140/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3160/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3220/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3260/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3340/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3380/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-340/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3440/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3520/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3540/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3560/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3580/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3620/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3640/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3660/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3680/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3720/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3740/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3780/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-380/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3820/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3840/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3860/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3880/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3920/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3940/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3960/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-3980/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-4020/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-440/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-520/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-540/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-560/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-580/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-620/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-640/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-660/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-680/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-720/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-740/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-780/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-80/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-820/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-840/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-860/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-880/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-920/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-940/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-960/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Swedish/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test1/checkpoint-980/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Estonian/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Estonian/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Estonian/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-1020/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Estonian/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-1040/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Estonian/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-1060/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Estonian/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-1080/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+overgeneralisation_original_Estonian/Qwen3-4B-Base_overgeneralisation_splits_original_features_train_overgeneralisation_splits_original_features_test2/checkpoint-1100/tokenizer.json filter=lfs diff=lfs merge=lfs -text

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: transformers
+model_name: Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1
+
+This model is a fine-tuned version of [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/katriin-kukk/Cross_lingual_morphological_generalization/runs/d2qeywxf) 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.29.0
+- Transformers: 5.5.4
+- Pytorch: 2.10.0
+- Datasets: 4.6.1
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1155/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1155/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.009078376988692594,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1155/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1155/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1155/trainer_state.json

@@ -0,0 +1,297 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1155,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.2479030179977415,
+      "epoch": 0.1299545159194282,
+      "grad_norm": 1.519571304321289,
+      "learning_rate": 3.522207847653314e-05,
+      "loss": 2.093206329345703,
+      "mean_token_accuracy": 0.6068353663384914,
+      "num_tokens": 154518.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.932415626347065,
+      "epoch": 0.2599090318388564,
+      "grad_norm": 1.180830955505371,
+      "learning_rate": 7.11629748811588e-05,
+      "loss": 0.8930854797363281,
+      "mean_token_accuracy": 0.7708445385098457,
+      "num_tokens": 306733.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7730373838543891,
+      "epoch": 0.3898635477582846,
+      "grad_norm": 0.7839977145195007,
+      "learning_rate": 0.00010710387128578447,
+      "loss": 0.7302116394042969,
+      "mean_token_accuracy": 0.8012136635184288,
+      "num_tokens": 446267.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6934178560972214,
+      "epoch": 0.5198180636777128,
+      "grad_norm": 0.666778564453125,
+      "learning_rate": 0.0001430447676904101,
+      "loss": 0.6505754852294922,
+      "mean_token_accuracy": 0.8195212116837501,
+      "num_tokens": 600256.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6900296103954315,
+      "epoch": 0.649772579597141,
+      "grad_norm": 0.6762415766716003,
+      "learning_rate": 0.00017898566409503577,
+      "loss": 0.6378536987304687,
+      "mean_token_accuracy": 0.8223087686300278,
+      "num_tokens": 738649.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.667421719878912,
+      "epoch": 0.7797270955165692,
+      "grad_norm": 0.5047685503959656,
+      "learning_rate": 0.00021492656049966144,
+      "loss": 0.6148524856567383,
+      "mean_token_accuracy": 0.8280292323231697,
+      "num_tokens": 883494.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6388977643847465,
+      "epoch": 0.9096816114359974,
+      "grad_norm": 0.4360353350639343,
+      "learning_rate": 0.0002508674569042871,
+      "loss": 0.5933729553222656,
+      "mean_token_accuracy": 0.8329134130477905,
+      "num_tokens": 1032111.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.6612381511009656,
+      "eval_loss": 0.6559221744537354,
+      "eval_mean_token_accuracy": 0.8195324820967821,
+      "eval_num_tokens": 1132140.0,
+      "eval_runtime": 53.4007,
+      "eval_samples_per_second": 31.03,
+      "eval_steps_per_second": 3.895,
+      "step": 385
+    },
+    {
+      "entropy": 0.6224366770916848,
+      "epoch": 1.0389863547758285,
+      "grad_norm": 0.5294668078422546,
+      "learning_rate": 0.00027673375518355765,
+      "loss": 0.5677951431274414,
+      "mean_token_accuracy": 0.8380465067211708,
+      "num_tokens": 1177556.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.5827466724812984,
+      "epoch": 1.1689408706952567,
+      "grad_norm": 0.5172416567802429,
+      "learning_rate": 0.0002765120122346144,
+      "loss": 0.5423126983642578,
+      "mean_token_accuracy": 0.8467991036176682,
+      "num_tokens": 1325434.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5831517253816128,
+      "epoch": 1.2988953866146848,
+      "grad_norm": 0.41916292905807495,
+      "learning_rate": 0.0002760064270819138,
+      "loss": 0.534448013305664,
+      "mean_token_accuracy": 0.8456632816791534,
+      "num_tokens": 1474116.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5869986982643605,
+      "epoch": 1.428849902534113,
+      "grad_norm": 0.4387759566307068,
+      "learning_rate": 0.00027521803857633113,
+      "loss": 0.5367491912841796,
+      "mean_token_accuracy": 0.8462416216731071,
+      "num_tokens": 1621193.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.5771756853163242,
+      "epoch": 1.5588044184535412,
+      "grad_norm": 0.49079665541648865,
+      "learning_rate": 0.00027414846665880935,
+      "loss": 0.5238623809814453,
+      "mean_token_accuracy": 0.84760089635849,
+      "num_tokens": 1767789.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5549105909466744,
+      "epoch": 1.6887589343729694,
+      "grad_norm": 0.4000363051891327,
+      "learning_rate": 0.0002727999090317863,
+      "loss": 0.510434226989746,
+      "mean_token_accuracy": 0.8517858856916427,
+      "num_tokens": 1918138.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.583413660377264,
+      "epoch": 1.8187134502923976,
+      "grad_norm": 0.33592426776885986,
+      "learning_rate": 0.00027117513664346674,
+      "loss": 0.5297993850708008,
+      "mean_token_accuracy": 0.846615691781044,
+      "num_tokens": 2057575.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5732646904885769,
+      "epoch": 1.9486679662118258,
+      "grad_norm": 0.5528839230537415,
+      "learning_rate": 0.00026927748799421714,
+      "loss": 0.5219194793701172,
+      "mean_token_accuracy": 0.8489033079147339,
+      "num_tokens": 2208320.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6027900550801021,
+      "eval_loss": 0.5946928858757019,
+      "eval_mean_token_accuracy": 0.8318195798649237,
+      "eval_num_tokens": 2264280.0,
+      "eval_runtime": 53.3837,
+      "eval_samples_per_second": 31.039,
+      "eval_steps_per_second": 3.896,
+      "step": 770
+    },
+    {
+      "entropy": 0.5329899657611272,
+      "epoch": 2.077972709551657,
+      "grad_norm": 0.45793575048446655,
+      "learning_rate": 0.0002671108622767842,
+      "loss": 0.48420516967773436,
+      "mean_token_accuracy": 0.8578200301333289,
+      "num_tokens": 2348248.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5142687204480171,
+      "epoch": 2.207927225471085,
+      "grad_norm": 0.4690960645675659,
+      "learning_rate": 0.0002646797113644295,
+      "loss": 0.4593114471435547,
+      "mean_token_accuracy": 0.8622670090198516,
+      "num_tokens": 2501427.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.5135884112119675,
+      "epoch": 2.3378817413905133,
+      "grad_norm": 0.3752821683883667,
+      "learning_rate": 0.00026198903066344565,
+      "loss": 0.4626216125488281,
+      "mean_token_accuracy": 0.8612511262297631,
+      "num_tokens": 2650794.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5137367483973503,
+      "epoch": 2.4678362573099415,
+      "grad_norm": 0.3726271390914917,
+      "learning_rate": 0.0002590443488488465,
+      "loss": 0.4601683807373047,
+      "mean_token_accuracy": 0.8620512077212333,
+      "num_tokens": 2798180.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5105714881420136,
+      "epoch": 2.5977907732293697,
+      "grad_norm": 0.41296717524528503,
+      "learning_rate": 0.00025585171650432525,
+      "loss": 0.46279102325439453,
+      "mean_token_accuracy": 0.8611763519048691,
+      "num_tokens": 2950301.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5169161760807037,
+      "epoch": 2.727745289148798,
+      "grad_norm": 0.4614253044128418,
+      "learning_rate": 0.0002524176936898197,
+      "loss": 0.45492774963378907,
+      "mean_token_accuracy": 0.8627680170536042,
+      "num_tokens": 3091810.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.4989277676492929,
+      "epoch": 2.857699805068226,
+      "grad_norm": 0.37512704730033875,
+      "learning_rate": 0.00024874933646223225,
+      "loss": 0.4531984329223633,
+      "mean_token_accuracy": 0.8637665447592735,
+      "num_tokens": 3242184.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5177617704868317,
+      "epoch": 2.9876543209876543,
+      "grad_norm": 0.3700532019138336,
+      "learning_rate": 0.00024485418237699976,
+      "loss": 0.45844474792480466,
+      "mean_token_accuracy": 0.8626988258957863,
+      "num_tokens": 3382605.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5253989950108987,
+      "eval_loss": 0.5857328176498413,
+      "eval_mean_token_accuracy": 0.8360884573597175,
+      "eval_num_tokens": 3396420.0,
+      "eval_runtime": 53.341,
+      "eval_samples_per_second": 31.064,
+      "eval_steps_per_second": 3.899,
+      "step": 1155
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4826229545264538e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1540/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1540/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.009078376988692594,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1540/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1540/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1540/trainer_state.json

@@ -0,0 +1,378 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1540,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.2479030179977415,
+      "epoch": 0.1299545159194282,
+      "grad_norm": 1.519571304321289,
+      "learning_rate": 3.522207847653314e-05,
+      "loss": 2.093206329345703,
+      "mean_token_accuracy": 0.6068353663384914,
+      "num_tokens": 154518.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.932415626347065,
+      "epoch": 0.2599090318388564,
+      "grad_norm": 1.180830955505371,
+      "learning_rate": 7.11629748811588e-05,
+      "loss": 0.8930854797363281,
+      "mean_token_accuracy": 0.7708445385098457,
+      "num_tokens": 306733.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7730373838543891,
+      "epoch": 0.3898635477582846,
+      "grad_norm": 0.7839977145195007,
+      "learning_rate": 0.00010710387128578447,
+      "loss": 0.7302116394042969,
+      "mean_token_accuracy": 0.8012136635184288,
+      "num_tokens": 446267.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6934178560972214,
+      "epoch": 0.5198180636777128,
+      "grad_norm": 0.666778564453125,
+      "learning_rate": 0.0001430447676904101,
+      "loss": 0.6505754852294922,
+      "mean_token_accuracy": 0.8195212116837501,
+      "num_tokens": 600256.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6900296103954315,
+      "epoch": 0.649772579597141,
+      "grad_norm": 0.6762415766716003,
+      "learning_rate": 0.00017898566409503577,
+      "loss": 0.6378536987304687,
+      "mean_token_accuracy": 0.8223087686300278,
+      "num_tokens": 738649.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.667421719878912,
+      "epoch": 0.7797270955165692,
+      "grad_norm": 0.5047685503959656,
+      "learning_rate": 0.00021492656049966144,
+      "loss": 0.6148524856567383,
+      "mean_token_accuracy": 0.8280292323231697,
+      "num_tokens": 883494.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6388977643847465,
+      "epoch": 0.9096816114359974,
+      "grad_norm": 0.4360353350639343,
+      "learning_rate": 0.0002508674569042871,
+      "loss": 0.5933729553222656,
+      "mean_token_accuracy": 0.8329134130477905,
+      "num_tokens": 1032111.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.6612381511009656,
+      "eval_loss": 0.6559221744537354,
+      "eval_mean_token_accuracy": 0.8195324820967821,
+      "eval_num_tokens": 1132140.0,
+      "eval_runtime": 53.4007,
+      "eval_samples_per_second": 31.03,
+      "eval_steps_per_second": 3.895,
+      "step": 385
+    },
+    {
+      "entropy": 0.6224366770916848,
+      "epoch": 1.0389863547758285,
+      "grad_norm": 0.5294668078422546,
+      "learning_rate": 0.00027673375518355765,
+      "loss": 0.5677951431274414,
+      "mean_token_accuracy": 0.8380465067211708,
+      "num_tokens": 1177556.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.5827466724812984,
+      "epoch": 1.1689408706952567,
+      "grad_norm": 0.5172416567802429,
+      "learning_rate": 0.0002765120122346144,
+      "loss": 0.5423126983642578,
+      "mean_token_accuracy": 0.8467991036176682,
+      "num_tokens": 1325434.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5831517253816128,
+      "epoch": 1.2988953866146848,
+      "grad_norm": 0.41916292905807495,
+      "learning_rate": 0.0002760064270819138,
+      "loss": 0.534448013305664,
+      "mean_token_accuracy": 0.8456632816791534,
+      "num_tokens": 1474116.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5869986982643605,
+      "epoch": 1.428849902534113,
+      "grad_norm": 0.4387759566307068,
+      "learning_rate": 0.00027521803857633113,
+      "loss": 0.5367491912841796,
+      "mean_token_accuracy": 0.8462416216731071,
+      "num_tokens": 1621193.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.5771756853163242,
+      "epoch": 1.5588044184535412,
+      "grad_norm": 0.49079665541648865,
+      "learning_rate": 0.00027414846665880935,
+      "loss": 0.5238623809814453,
+      "mean_token_accuracy": 0.84760089635849,
+      "num_tokens": 1767789.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5549105909466744,
+      "epoch": 1.6887589343729694,
+      "grad_norm": 0.4000363051891327,
+      "learning_rate": 0.0002727999090317863,
+      "loss": 0.510434226989746,
+      "mean_token_accuracy": 0.8517858856916427,
+      "num_tokens": 1918138.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.583413660377264,
+      "epoch": 1.8187134502923976,
+      "grad_norm": 0.33592426776885986,
+      "learning_rate": 0.00027117513664346674,
+      "loss": 0.5297993850708008,
+      "mean_token_accuracy": 0.846615691781044,
+      "num_tokens": 2057575.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5732646904885769,
+      "epoch": 1.9486679662118258,
+      "grad_norm": 0.5528839230537415,
+      "learning_rate": 0.00026927748799421714,
+      "loss": 0.5219194793701172,
+      "mean_token_accuracy": 0.8489033079147339,
+      "num_tokens": 2208320.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6027900550801021,
+      "eval_loss": 0.5946928858757019,
+      "eval_mean_token_accuracy": 0.8318195798649237,
+      "eval_num_tokens": 2264280.0,
+      "eval_runtime": 53.3837,
+      "eval_samples_per_second": 31.039,
+      "eval_steps_per_second": 3.896,
+      "step": 770
+    },
+    {
+      "entropy": 0.5329899657611272,
+      "epoch": 2.077972709551657,
+      "grad_norm": 0.45793575048446655,
+      "learning_rate": 0.0002671108622767842,
+      "loss": 0.48420516967773436,
+      "mean_token_accuracy": 0.8578200301333289,
+      "num_tokens": 2348248.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5142687204480171,
+      "epoch": 2.207927225471085,
+      "grad_norm": 0.4690960645675659,
+      "learning_rate": 0.0002646797113644295,
+      "loss": 0.4593114471435547,
+      "mean_token_accuracy": 0.8622670090198516,
+      "num_tokens": 2501427.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.5135884112119675,
+      "epoch": 2.3378817413905133,
+      "grad_norm": 0.3752821683883667,
+      "learning_rate": 0.00026198903066344565,
+      "loss": 0.4626216125488281,
+      "mean_token_accuracy": 0.8612511262297631,
+      "num_tokens": 2650794.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5137367483973503,
+      "epoch": 2.4678362573099415,
+      "grad_norm": 0.3726271390914917,
+      "learning_rate": 0.0002590443488488465,
+      "loss": 0.4601683807373047,
+      "mean_token_accuracy": 0.8620512077212333,
+      "num_tokens": 2798180.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5105714881420136,
+      "epoch": 2.5977907732293697,
+      "grad_norm": 0.41296717524528503,
+      "learning_rate": 0.00025585171650432525,
+      "loss": 0.46279102325439453,
+      "mean_token_accuracy": 0.8611763519048691,
+      "num_tokens": 2950301.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5169161760807037,
+      "epoch": 2.727745289148798,
+      "grad_norm": 0.4614253044128418,
+      "learning_rate": 0.0002524176936898197,
+      "loss": 0.45492774963378907,
+      "mean_token_accuracy": 0.8627680170536042,
+      "num_tokens": 3091810.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.4989277676492929,
+      "epoch": 2.857699805068226,
+      "grad_norm": 0.37512704730033875,
+      "learning_rate": 0.00024874933646223225,
+      "loss": 0.4531984329223633,
+      "mean_token_accuracy": 0.8637665447592735,
+      "num_tokens": 3242184.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5177617704868317,
+      "epoch": 2.9876543209876543,
+      "grad_norm": 0.3700532019138336,
+      "learning_rate": 0.00024485418237699976,
+      "loss": 0.45844474792480466,
+      "mean_token_accuracy": 0.8626988258957863,
+      "num_tokens": 3382605.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5253989950108987,
+      "eval_loss": 0.5857328176498413,
+      "eval_mean_token_accuracy": 0.8360884573597175,
+      "eval_num_tokens": 3396420.0,
+      "eval_runtime": 53.341,
+      "eval_samples_per_second": 31.064,
+      "eval_steps_per_second": 3.899,
+      "step": 1155
+    },
+    {
+      "entropy": 0.4535361140517134,
+      "epoch": 3.116959064327485,
+      "grad_norm": 0.3412795662879944,
+      "learning_rate": 0.00024074023500030492,
+      "loss": 0.3942829132080078,
+      "mean_token_accuracy": 0.8781378038564519,
+      "num_tokens": 3522582.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.44747897461056707,
+      "epoch": 3.246913580246914,
+      "grad_norm": 0.46647050976753235,
+      "learning_rate": 0.0002364159474637521,
+      "loss": 0.38986759185791015,
+      "mean_token_accuracy": 0.8777281475067139,
+      "num_tokens": 3670864.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.4480265176296234,
+      "epoch": 3.3768680961663415,
+      "grad_norm": 0.4068582355976105,
+      "learning_rate": 0.00023189020509529866,
+      "loss": 0.39444759368896487,
+      "mean_token_accuracy": 0.8774515727162361,
+      "num_tokens": 3822021.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.45180007234215736,
+      "epoch": 3.50682261208577,
+      "grad_norm": 0.4249928593635559,
+      "learning_rate": 0.00022717230716213122,
+      "loss": 0.3977077102661133,
+      "mean_token_accuracy": 0.8762744688987731,
+      "num_tokens": 3968736.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.4614932192862034,
+      "epoch": 3.636777128005198,
+      "grad_norm": 0.561008095741272,
+      "learning_rate": 0.00022227194776300045,
+      "loss": 0.4022808456420898,
+      "mean_token_accuracy": 0.8760285252332687,
+      "num_tokens": 4113509.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.4414680179953575,
+      "epoch": 3.7667316439246266,
+      "grad_norm": 0.38943538069725037,
+      "learning_rate": 0.00021719919590927584,
+      "loss": 0.38586376190185545,
+      "mean_token_accuracy": 0.8783121705055237,
+      "num_tokens": 4267958.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.45685607343912127,
+      "epoch": 3.8966861598440543,
+      "grad_norm": 0.5362406969070435,
+      "learning_rate": 0.00021196447483564875,
+      "loss": 0.3983576583862305,
+      "mean_token_accuracy": 0.8764419692754746,
+      "num_tokens": 4415398.0,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.49981127894268584,
+      "eval_loss": 0.5997208952903748,
+      "eval_mean_token_accuracy": 0.8368159819107789,
+      "eval_num_tokens": 4528560.0,
+      "eval_runtime": 53.4304,
+      "eval_samples_per_second": 31.012,
+      "eval_steps_per_second": 3.893,
+      "step": 1540
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.97414227488298e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1925/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1925/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.009078376988692594,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1925/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1925/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-1925/trainer_state.json

@@ -0,0 +1,469 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1925,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.2479030179977415,
+      "epoch": 0.1299545159194282,
+      "grad_norm": 1.519571304321289,
+      "learning_rate": 3.522207847653314e-05,
+      "loss": 2.093206329345703,
+      "mean_token_accuracy": 0.6068353663384914,
+      "num_tokens": 154518.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.932415626347065,
+      "epoch": 0.2599090318388564,
+      "grad_norm": 1.180830955505371,
+      "learning_rate": 7.11629748811588e-05,
+      "loss": 0.8930854797363281,
+      "mean_token_accuracy": 0.7708445385098457,
+      "num_tokens": 306733.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7730373838543891,
+      "epoch": 0.3898635477582846,
+      "grad_norm": 0.7839977145195007,
+      "learning_rate": 0.00010710387128578447,
+      "loss": 0.7302116394042969,
+      "mean_token_accuracy": 0.8012136635184288,
+      "num_tokens": 446267.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6934178560972214,
+      "epoch": 0.5198180636777128,
+      "grad_norm": 0.666778564453125,
+      "learning_rate": 0.0001430447676904101,
+      "loss": 0.6505754852294922,
+      "mean_token_accuracy": 0.8195212116837501,
+      "num_tokens": 600256.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6900296103954315,
+      "epoch": 0.649772579597141,
+      "grad_norm": 0.6762415766716003,
+      "learning_rate": 0.00017898566409503577,
+      "loss": 0.6378536987304687,
+      "mean_token_accuracy": 0.8223087686300278,
+      "num_tokens": 738649.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.667421719878912,
+      "epoch": 0.7797270955165692,
+      "grad_norm": 0.5047685503959656,
+      "learning_rate": 0.00021492656049966144,
+      "loss": 0.6148524856567383,
+      "mean_token_accuracy": 0.8280292323231697,
+      "num_tokens": 883494.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6388977643847465,
+      "epoch": 0.9096816114359974,
+      "grad_norm": 0.4360353350639343,
+      "learning_rate": 0.0002508674569042871,
+      "loss": 0.5933729553222656,
+      "mean_token_accuracy": 0.8329134130477905,
+      "num_tokens": 1032111.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.6612381511009656,
+      "eval_loss": 0.6559221744537354,
+      "eval_mean_token_accuracy": 0.8195324820967821,
+      "eval_num_tokens": 1132140.0,
+      "eval_runtime": 53.4007,
+      "eval_samples_per_second": 31.03,
+      "eval_steps_per_second": 3.895,
+      "step": 385
+    },
+    {
+      "entropy": 0.6224366770916848,
+      "epoch": 1.0389863547758285,
+      "grad_norm": 0.5294668078422546,
+      "learning_rate": 0.00027673375518355765,
+      "loss": 0.5677951431274414,
+      "mean_token_accuracy": 0.8380465067211708,
+      "num_tokens": 1177556.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.5827466724812984,
+      "epoch": 1.1689408706952567,
+      "grad_norm": 0.5172416567802429,
+      "learning_rate": 0.0002765120122346144,
+      "loss": 0.5423126983642578,
+      "mean_token_accuracy": 0.8467991036176682,
+      "num_tokens": 1325434.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5831517253816128,
+      "epoch": 1.2988953866146848,
+      "grad_norm": 0.41916292905807495,
+      "learning_rate": 0.0002760064270819138,
+      "loss": 0.534448013305664,
+      "mean_token_accuracy": 0.8456632816791534,
+      "num_tokens": 1474116.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5869986982643605,
+      "epoch": 1.428849902534113,
+      "grad_norm": 0.4387759566307068,
+      "learning_rate": 0.00027521803857633113,
+      "loss": 0.5367491912841796,
+      "mean_token_accuracy": 0.8462416216731071,
+      "num_tokens": 1621193.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.5771756853163242,
+      "epoch": 1.5588044184535412,
+      "grad_norm": 0.49079665541648865,
+      "learning_rate": 0.00027414846665880935,
+      "loss": 0.5238623809814453,
+      "mean_token_accuracy": 0.84760089635849,
+      "num_tokens": 1767789.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5549105909466744,
+      "epoch": 1.6887589343729694,
+      "grad_norm": 0.4000363051891327,
+      "learning_rate": 0.0002727999090317863,
+      "loss": 0.510434226989746,
+      "mean_token_accuracy": 0.8517858856916427,
+      "num_tokens": 1918138.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.583413660377264,
+      "epoch": 1.8187134502923976,
+      "grad_norm": 0.33592426776885986,
+      "learning_rate": 0.00027117513664346674,
+      "loss": 0.5297993850708008,
+      "mean_token_accuracy": 0.846615691781044,
+      "num_tokens": 2057575.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5732646904885769,
+      "epoch": 1.9486679662118258,
+      "grad_norm": 0.5528839230537415,
+      "learning_rate": 0.00026927748799421714,
+      "loss": 0.5219194793701172,
+      "mean_token_accuracy": 0.8489033079147339,
+      "num_tokens": 2208320.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6027900550801021,
+      "eval_loss": 0.5946928858757019,
+      "eval_mean_token_accuracy": 0.8318195798649237,
+      "eval_num_tokens": 2264280.0,
+      "eval_runtime": 53.3837,
+      "eval_samples_per_second": 31.039,
+      "eval_steps_per_second": 3.896,
+      "step": 770
+    },
+    {
+      "entropy": 0.5329899657611272,
+      "epoch": 2.077972709551657,
+      "grad_norm": 0.45793575048446655,
+      "learning_rate": 0.0002671108622767842,
+      "loss": 0.48420516967773436,
+      "mean_token_accuracy": 0.8578200301333289,
+      "num_tokens": 2348248.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5142687204480171,
+      "epoch": 2.207927225471085,
+      "grad_norm": 0.4690960645675659,
+      "learning_rate": 0.0002646797113644295,
+      "loss": 0.4593114471435547,
+      "mean_token_accuracy": 0.8622670090198516,
+      "num_tokens": 2501427.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.5135884112119675,
+      "epoch": 2.3378817413905133,
+      "grad_norm": 0.3752821683883667,
+      "learning_rate": 0.00026198903066344565,
+      "loss": 0.4626216125488281,
+      "mean_token_accuracy": 0.8612511262297631,
+      "num_tokens": 2650794.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5137367483973503,
+      "epoch": 2.4678362573099415,
+      "grad_norm": 0.3726271390914917,
+      "learning_rate": 0.0002590443488488465,
+      "loss": 0.4601683807373047,
+      "mean_token_accuracy": 0.8620512077212333,
+      "num_tokens": 2798180.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5105714881420136,
+      "epoch": 2.5977907732293697,
+      "grad_norm": 0.41296717524528503,
+      "learning_rate": 0.00025585171650432525,
+      "loss": 0.46279102325439453,
+      "mean_token_accuracy": 0.8611763519048691,
+      "num_tokens": 2950301.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5169161760807037,
+      "epoch": 2.727745289148798,
+      "grad_norm": 0.4614253044128418,
+      "learning_rate": 0.0002524176936898197,
+      "loss": 0.45492774963378907,
+      "mean_token_accuracy": 0.8627680170536042,
+      "num_tokens": 3091810.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.4989277676492929,
+      "epoch": 2.857699805068226,
+      "grad_norm": 0.37512704730033875,
+      "learning_rate": 0.00024874933646223225,
+      "loss": 0.4531984329223633,
+      "mean_token_accuracy": 0.8637665447592735,
+      "num_tokens": 3242184.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5177617704868317,
+      "epoch": 2.9876543209876543,
+      "grad_norm": 0.3700532019138336,
+      "learning_rate": 0.00024485418237699976,
+      "loss": 0.45844474792480466,
+      "mean_token_accuracy": 0.8626988258957863,
+      "num_tokens": 3382605.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5253989950108987,
+      "eval_loss": 0.5857328176498413,
+      "eval_mean_token_accuracy": 0.8360884573597175,
+      "eval_num_tokens": 3396420.0,
+      "eval_runtime": 53.341,
+      "eval_samples_per_second": 31.064,
+      "eval_steps_per_second": 3.899,
+      "step": 1155
+    },
+    {
+      "entropy": 0.4535361140517134,
+      "epoch": 3.116959064327485,
+      "grad_norm": 0.3412795662879944,
+      "learning_rate": 0.00024074023500030492,
+      "loss": 0.3942829132080078,
+      "mean_token_accuracy": 0.8781378038564519,
+      "num_tokens": 3522582.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.44747897461056707,
+      "epoch": 3.246913580246914,
+      "grad_norm": 0.46647050976753235,
+      "learning_rate": 0.0002364159474637521,
+      "loss": 0.38986759185791015,
+      "mean_token_accuracy": 0.8777281475067139,
+      "num_tokens": 3670864.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.4480265176296234,
+      "epoch": 3.3768680961663415,
+      "grad_norm": 0.4068582355976105,
+      "learning_rate": 0.00023189020509529866,
+      "loss": 0.39444759368896487,
+      "mean_token_accuracy": 0.8774515727162361,
+      "num_tokens": 3822021.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.45180007234215736,
+      "epoch": 3.50682261208577,
+      "grad_norm": 0.4249928593635559,
+      "learning_rate": 0.00022717230716213122,
+      "loss": 0.3977077102661133,
+      "mean_token_accuracy": 0.8762744688987731,
+      "num_tokens": 3968736.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.4614932192862034,
+      "epoch": 3.636777128005198,
+      "grad_norm": 0.561008095741272,
+      "learning_rate": 0.00022227194776300045,
+      "loss": 0.4022808456420898,
+      "mean_token_accuracy": 0.8760285252332687,
+      "num_tokens": 4113509.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.4414680179953575,
+      "epoch": 3.7667316439246266,
+      "grad_norm": 0.38943538069725037,
+      "learning_rate": 0.00021719919590927584,
+      "loss": 0.38586376190185545,
+      "mean_token_accuracy": 0.8783121705055237,
+      "num_tokens": 4267958.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.45685607343912127,
+      "epoch": 3.8966861598440543,
+      "grad_norm": 0.5362406969070435,
+      "learning_rate": 0.00021196447483564875,
+      "loss": 0.3983576583862305,
+      "mean_token_accuracy": 0.8764419692754746,
+      "num_tokens": 4415398.0,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.49981127894268584,
+      "eval_loss": 0.5997208952903748,
+      "eval_mean_token_accuracy": 0.8368159819107789,
+      "eval_num_tokens": 4528560.0,
+      "eval_runtime": 53.4304,
+      "eval_samples_per_second": 31.012,
+      "eval_steps_per_second": 3.893,
+      "step": 1540
+    },
+    {
+      "entropy": 0.4439909208060509,
+      "epoch": 4.025990903183885,
+      "grad_norm": 0.5490113496780396,
+      "learning_rate": 0.00020657854058299564,
+      "loss": 0.38307292938232423,
+      "mean_token_accuracy": 0.8795150506436525,
+      "num_tokens": 4559534.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.3837250977009535,
+      "epoch": 4.155945419103314,
+      "grad_norm": 0.5567234754562378,
+      "learning_rate": 0.0002010524598974076,
+      "loss": 0.3182963752746582,
+      "mean_token_accuracy": 0.8964017608761787,
+      "num_tokens": 4707075.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.377872094810009,
+      "epoch": 4.2858999350227425,
+      "grad_norm": 0.4315710961818695,
+      "learning_rate": 0.00019539758749079845,
+      "loss": 0.318333683013916,
+      "mean_token_accuracy": 0.8963816618919372,
+      "num_tokens": 4851683.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.38739304527640345,
+      "epoch": 4.41585445094217,
+      "grad_norm": 0.49140632152557373,
+      "learning_rate": 0.00018962554270981555,
+      "loss": 0.32688804626464846,
+      "mean_token_accuracy": 0.8937860554456711,
+      "num_tokens": 4994086.0,
+      "step": 1700
+    },
+    {
+      "entropy": 0.39157475270330905,
+      "epoch": 4.545808966861598,
+      "grad_norm": 0.40667369961738586,
+      "learning_rate": 0.00018374818566099208,
+      "loss": 0.3305763626098633,
+      "mean_token_accuracy": 0.8916732975840569,
+      "num_tokens": 5137171.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3838599680364132,
+      "epoch": 4.675763482781027,
+      "grad_norm": 0.4632417857646942,
+      "learning_rate": 0.0001777775928411983,
+      "loss": 0.3267818450927734,
+      "mean_token_accuracy": 0.8946500706672669,
+      "num_tokens": 5287076.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.38270787581801413,
+      "epoch": 4.805717998700455,
+      "grad_norm": 0.5529720187187195,
+      "learning_rate": 0.0001717260323234649,
+      "loss": 0.3264235305786133,
+      "mean_token_accuracy": 0.8948800846934318,
+      "num_tokens": 5436923.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.38736109718680384,
+      "epoch": 4.935672514619883,
+      "grad_norm": 0.5604785680770874,
+      "learning_rate": 0.00016560593854916497,
+      "loss": 0.3280513381958008,
+      "mean_token_accuracy": 0.8931388029456139,
+      "num_tokens": 5589195.0,
+      "step": 1900
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.4370518812479881,
+      "eval_loss": 0.6210553050041199,
+      "eval_mean_token_accuracy": 0.8379779781859654,
+      "eval_num_tokens": 5660700.0,
+      "eval_runtime": 53.4039,
+      "eval_samples_per_second": 31.028,
+      "eval_steps_per_second": 3.895,
+      "step": 1925
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.466249383274455e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-2310/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-2310/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.009078376988692594,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-2310/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-2310/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-2310/trainer_state.json

@@ -0,0 +1,560 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 2310,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.2479030179977415,
+      "epoch": 0.1299545159194282,
+      "grad_norm": 1.519571304321289,
+      "learning_rate": 3.522207847653314e-05,
+      "loss": 2.093206329345703,
+      "mean_token_accuracy": 0.6068353663384914,
+      "num_tokens": 154518.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.932415626347065,
+      "epoch": 0.2599090318388564,
+      "grad_norm": 1.180830955505371,
+      "learning_rate": 7.11629748811588e-05,
+      "loss": 0.8930854797363281,
+      "mean_token_accuracy": 0.7708445385098457,
+      "num_tokens": 306733.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7730373838543891,
+      "epoch": 0.3898635477582846,
+      "grad_norm": 0.7839977145195007,
+      "learning_rate": 0.00010710387128578447,
+      "loss": 0.7302116394042969,
+      "mean_token_accuracy": 0.8012136635184288,
+      "num_tokens": 446267.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6934178560972214,
+      "epoch": 0.5198180636777128,
+      "grad_norm": 0.666778564453125,
+      "learning_rate": 0.0001430447676904101,
+      "loss": 0.6505754852294922,
+      "mean_token_accuracy": 0.8195212116837501,
+      "num_tokens": 600256.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6900296103954315,
+      "epoch": 0.649772579597141,
+      "grad_norm": 0.6762415766716003,
+      "learning_rate": 0.00017898566409503577,
+      "loss": 0.6378536987304687,
+      "mean_token_accuracy": 0.8223087686300278,
+      "num_tokens": 738649.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.667421719878912,
+      "epoch": 0.7797270955165692,
+      "grad_norm": 0.5047685503959656,
+      "learning_rate": 0.00021492656049966144,
+      "loss": 0.6148524856567383,
+      "mean_token_accuracy": 0.8280292323231697,
+      "num_tokens": 883494.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6388977643847465,
+      "epoch": 0.9096816114359974,
+      "grad_norm": 0.4360353350639343,
+      "learning_rate": 0.0002508674569042871,
+      "loss": 0.5933729553222656,
+      "mean_token_accuracy": 0.8329134130477905,
+      "num_tokens": 1032111.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.6612381511009656,
+      "eval_loss": 0.6559221744537354,
+      "eval_mean_token_accuracy": 0.8195324820967821,
+      "eval_num_tokens": 1132140.0,
+      "eval_runtime": 53.4007,
+      "eval_samples_per_second": 31.03,
+      "eval_steps_per_second": 3.895,
+      "step": 385
+    },
+    {
+      "entropy": 0.6224366770916848,
+      "epoch": 1.0389863547758285,
+      "grad_norm": 0.5294668078422546,
+      "learning_rate": 0.00027673375518355765,
+      "loss": 0.5677951431274414,
+      "mean_token_accuracy": 0.8380465067211708,
+      "num_tokens": 1177556.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.5827466724812984,
+      "epoch": 1.1689408706952567,
+      "grad_norm": 0.5172416567802429,
+      "learning_rate": 0.0002765120122346144,
+      "loss": 0.5423126983642578,
+      "mean_token_accuracy": 0.8467991036176682,
+      "num_tokens": 1325434.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5831517253816128,
+      "epoch": 1.2988953866146848,
+      "grad_norm": 0.41916292905807495,
+      "learning_rate": 0.0002760064270819138,
+      "loss": 0.534448013305664,
+      "mean_token_accuracy": 0.8456632816791534,
+      "num_tokens": 1474116.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5869986982643605,
+      "epoch": 1.428849902534113,
+      "grad_norm": 0.4387759566307068,
+      "learning_rate": 0.00027521803857633113,
+      "loss": 0.5367491912841796,
+      "mean_token_accuracy": 0.8462416216731071,
+      "num_tokens": 1621193.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.5771756853163242,
+      "epoch": 1.5588044184535412,
+      "grad_norm": 0.49079665541648865,
+      "learning_rate": 0.00027414846665880935,
+      "loss": 0.5238623809814453,
+      "mean_token_accuracy": 0.84760089635849,
+      "num_tokens": 1767789.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5549105909466744,
+      "epoch": 1.6887589343729694,
+      "grad_norm": 0.4000363051891327,
+      "learning_rate": 0.0002727999090317863,
+      "loss": 0.510434226989746,
+      "mean_token_accuracy": 0.8517858856916427,
+      "num_tokens": 1918138.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.583413660377264,
+      "epoch": 1.8187134502923976,
+      "grad_norm": 0.33592426776885986,
+      "learning_rate": 0.00027117513664346674,
+      "loss": 0.5297993850708008,
+      "mean_token_accuracy": 0.846615691781044,
+      "num_tokens": 2057575.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5732646904885769,
+      "epoch": 1.9486679662118258,
+      "grad_norm": 0.5528839230537415,
+      "learning_rate": 0.00026927748799421714,
+      "loss": 0.5219194793701172,
+      "mean_token_accuracy": 0.8489033079147339,
+      "num_tokens": 2208320.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6027900550801021,
+      "eval_loss": 0.5946928858757019,
+      "eval_mean_token_accuracy": 0.8318195798649237,
+      "eval_num_tokens": 2264280.0,
+      "eval_runtime": 53.3837,
+      "eval_samples_per_second": 31.039,
+      "eval_steps_per_second": 3.896,
+      "step": 770
+    },
+    {
+      "entropy": 0.5329899657611272,
+      "epoch": 2.077972709551657,
+      "grad_norm": 0.45793575048446655,
+      "learning_rate": 0.0002671108622767842,
+      "loss": 0.48420516967773436,
+      "mean_token_accuracy": 0.8578200301333289,
+      "num_tokens": 2348248.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5142687204480171,
+      "epoch": 2.207927225471085,
+      "grad_norm": 0.4690960645675659,
+      "learning_rate": 0.0002646797113644295,
+      "loss": 0.4593114471435547,
+      "mean_token_accuracy": 0.8622670090198516,
+      "num_tokens": 2501427.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.5135884112119675,
+      "epoch": 2.3378817413905133,
+      "grad_norm": 0.3752821683883667,
+      "learning_rate": 0.00026198903066344565,
+      "loss": 0.4626216125488281,
+      "mean_token_accuracy": 0.8612511262297631,
+      "num_tokens": 2650794.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5137367483973503,
+      "epoch": 2.4678362573099415,
+      "grad_norm": 0.3726271390914917,
+      "learning_rate": 0.0002590443488488465,
+      "loss": 0.4601683807373047,
+      "mean_token_accuracy": 0.8620512077212333,
+      "num_tokens": 2798180.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5105714881420136,
+      "epoch": 2.5977907732293697,
+      "grad_norm": 0.41296717524528503,
+      "learning_rate": 0.00025585171650432525,
+      "loss": 0.46279102325439453,
+      "mean_token_accuracy": 0.8611763519048691,
+      "num_tokens": 2950301.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5169161760807037,
+      "epoch": 2.727745289148798,
+      "grad_norm": 0.4614253044128418,
+      "learning_rate": 0.0002524176936898197,
+      "loss": 0.45492774963378907,
+      "mean_token_accuracy": 0.8627680170536042,
+      "num_tokens": 3091810.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.4989277676492929,
+      "epoch": 2.857699805068226,
+      "grad_norm": 0.37512704730033875,
+      "learning_rate": 0.00024874933646223225,
+      "loss": 0.4531984329223633,
+      "mean_token_accuracy": 0.8637665447592735,
+      "num_tokens": 3242184.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5177617704868317,
+      "epoch": 2.9876543209876543,
+      "grad_norm": 0.3700532019138336,
+      "learning_rate": 0.00024485418237699976,
+      "loss": 0.45844474792480466,
+      "mean_token_accuracy": 0.8626988258957863,
+      "num_tokens": 3382605.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5253989950108987,
+      "eval_loss": 0.5857328176498413,
+      "eval_mean_token_accuracy": 0.8360884573597175,
+      "eval_num_tokens": 3396420.0,
+      "eval_runtime": 53.341,
+      "eval_samples_per_second": 31.064,
+      "eval_steps_per_second": 3.899,
+      "step": 1155
+    },
+    {
+      "entropy": 0.4535361140517134,
+      "epoch": 3.116959064327485,
+      "grad_norm": 0.3412795662879944,
+      "learning_rate": 0.00024074023500030492,
+      "loss": 0.3942829132080078,
+      "mean_token_accuracy": 0.8781378038564519,
+      "num_tokens": 3522582.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.44747897461056707,
+      "epoch": 3.246913580246914,
+      "grad_norm": 0.46647050976753235,
+      "learning_rate": 0.0002364159474637521,
+      "loss": 0.38986759185791015,
+      "mean_token_accuracy": 0.8777281475067139,
+      "num_tokens": 3670864.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.4480265176296234,
+      "epoch": 3.3768680961663415,
+      "grad_norm": 0.4068582355976105,
+      "learning_rate": 0.00023189020509529866,
+      "loss": 0.39444759368896487,
+      "mean_token_accuracy": 0.8774515727162361,
+      "num_tokens": 3822021.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.45180007234215736,
+      "epoch": 3.50682261208577,
+      "grad_norm": 0.4249928593635559,
+      "learning_rate": 0.00022717230716213122,
+      "loss": 0.3977077102661133,
+      "mean_token_accuracy": 0.8762744688987731,
+      "num_tokens": 3968736.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.4614932192862034,
+      "epoch": 3.636777128005198,
+      "grad_norm": 0.561008095741272,
+      "learning_rate": 0.00022227194776300045,
+      "loss": 0.4022808456420898,
+      "mean_token_accuracy": 0.8760285252332687,
+      "num_tokens": 4113509.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.4414680179953575,
+      "epoch": 3.7667316439246266,
+      "grad_norm": 0.38943538069725037,
+      "learning_rate": 0.00021719919590927584,
+      "loss": 0.38586376190185545,
+      "mean_token_accuracy": 0.8783121705055237,
+      "num_tokens": 4267958.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.45685607343912127,
+      "epoch": 3.8966861598440543,
+      "grad_norm": 0.5362406969070435,
+      "learning_rate": 0.00021196447483564875,
+      "loss": 0.3983576583862305,
+      "mean_token_accuracy": 0.8764419692754746,
+      "num_tokens": 4415398.0,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.49981127894268584,
+      "eval_loss": 0.5997208952903748,
+      "eval_mean_token_accuracy": 0.8368159819107789,
+      "eval_num_tokens": 4528560.0,
+      "eval_runtime": 53.4304,
+      "eval_samples_per_second": 31.012,
+      "eval_steps_per_second": 3.893,
+      "step": 1540
+    },
+    {
+      "entropy": 0.4439909208060509,
+      "epoch": 4.025990903183885,
+      "grad_norm": 0.5490113496780396,
+      "learning_rate": 0.00020657854058299564,
+      "loss": 0.38307292938232423,
+      "mean_token_accuracy": 0.8795150506436525,
+      "num_tokens": 4559534.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.3837250977009535,
+      "epoch": 4.155945419103314,
+      "grad_norm": 0.5567234754562378,
+      "learning_rate": 0.0002010524598974076,
+      "loss": 0.3182963752746582,
+      "mean_token_accuracy": 0.8964017608761787,
+      "num_tokens": 4707075.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.377872094810009,
+      "epoch": 4.2858999350227425,
+      "grad_norm": 0.4315710961818695,
+      "learning_rate": 0.00019539758749079845,
+      "loss": 0.318333683013916,
+      "mean_token_accuracy": 0.8963816618919372,
+      "num_tokens": 4851683.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.38739304527640345,
+      "epoch": 4.41585445094217,
+      "grad_norm": 0.49140632152557373,
+      "learning_rate": 0.00018962554270981555,
+      "loss": 0.32688804626464846,
+      "mean_token_accuracy": 0.8937860554456711,
+      "num_tokens": 4994086.0,
+      "step": 1700
+    },
+    {
+      "entropy": 0.39157475270330905,
+      "epoch": 4.545808966861598,
+      "grad_norm": 0.40667369961738586,
+      "learning_rate": 0.00018374818566099208,
+      "loss": 0.3305763626098633,
+      "mean_token_accuracy": 0.8916732975840569,
+      "num_tokens": 5137171.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3838599680364132,
+      "epoch": 4.675763482781027,
+      "grad_norm": 0.4632417857646942,
+      "learning_rate": 0.0001777775928411983,
+      "loss": 0.3267818450927734,
+      "mean_token_accuracy": 0.8946500706672669,
+      "num_tokens": 5287076.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.38270787581801413,
+      "epoch": 4.805717998700455,
+      "grad_norm": 0.5529720187187195,
+      "learning_rate": 0.0001717260323234649,
+      "loss": 0.3264235305786133,
+      "mean_token_accuracy": 0.8948800846934318,
+      "num_tokens": 5436923.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.38736109718680384,
+      "epoch": 4.935672514619883,
+      "grad_norm": 0.5604785680770874,
+      "learning_rate": 0.00016560593854916497,
+      "loss": 0.3280513381958008,
+      "mean_token_accuracy": 0.8931388029456139,
+      "num_tokens": 5589195.0,
+      "step": 1900
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.4370518812479881,
+      "eval_loss": 0.6210553050041199,
+      "eval_mean_token_accuracy": 0.8379779781859654,
+      "eval_num_tokens": 5660700.0,
+      "eval_runtime": 53.4039,
+      "eval_samples_per_second": 31.028,
+      "eval_steps_per_second": 3.895,
+      "step": 1925
+    },
+    {
+      "entropy": 0.3330705868988181,
+      "epoch": 5.064977257959714,
+      "grad_norm": 0.5386723875999451,
+      "learning_rate": 0.0001594298867783512,
+      "loss": 0.2754818344116211,
+      "mean_token_accuracy": 0.9101201346771202,
+      "num_tokens": 5739445.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.2980620255321264,
+      "epoch": 5.1949317738791425,
+      "grad_norm": 0.5633581876754761,
+      "learning_rate": 0.00015321056725074549,
+      "loss": 0.23754241943359375,
+      "mean_token_accuracy": 0.9203532826900482,
+      "num_tokens": 5888043.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.3111592583358288,
+      "epoch": 5.32488628979857,
+      "grad_norm": 0.5031015872955322,
+      "learning_rate": 0.0001469607591104745,
+      "loss": 0.24428102493286133,
+      "mean_token_accuracy": 0.917181601524353,
+      "num_tokens": 6031284.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.31522042460739613,
+      "epoch": 5.454840805717999,
+      "grad_norm": 0.6432453393936157,
+      "learning_rate": 0.0001406933041481286,
+      "loss": 0.25112478256225584,
+      "mean_token_accuracy": 0.9152472382783889,
+      "num_tokens": 6179927.0,
+      "step": 2100
+    },
+    {
+      "entropy": 0.3046229027956724,
+      "epoch": 5.584795321637427,
+      "grad_norm": 0.5104537606239319,
+      "learning_rate": 0.00013442108041409814,
+      "loss": 0.2431495475769043,
+      "mean_token_accuracy": 0.917829519212246,
+      "num_tokens": 6322630.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.30440517760813235,
+      "epoch": 5.714749837556855,
+      "grad_norm": 0.5307765603065491,
+      "learning_rate": 0.0001281569757574053,
+      "loss": 0.24610313415527343,
+      "mean_token_accuracy": 0.9166415151953697,
+      "num_tokens": 6469843.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.304359400421381,
+      "epoch": 5.844704353476283,
+      "grad_norm": 0.5014523267745972,
+      "learning_rate": 0.00012191386134440133,
+      "loss": 0.24548973083496095,
+      "mean_token_accuracy": 0.9165477308630944,
+      "num_tokens": 6617768.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.3141418205201626,
+      "epoch": 5.974658869395712,
+      "grad_norm": 0.567398726940155,
+      "learning_rate": 0.00011570456521174339,
+      "loss": 0.24975168228149414,
+      "mean_token_accuracy": 0.9139353120326996,
+      "num_tokens": 6761187.0,
+      "step": 2300
+    },
+    {
+      "epoch": 6.0,
+      "eval_entropy": 0.3758909202252443,
+      "eval_loss": 0.6843022108078003,
+      "eval_mean_token_accuracy": 0.8348075449466705,
+      "eval_num_tokens": 6792840.0,
+      "eval_runtime": 53.3825,
+      "eval_samples_per_second": 31.04,
+      "eval_steps_per_second": 3.896,
+      "step": 2310
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.9583147604912435e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-2695/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-2695/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.009078376988692594,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-2695/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-2695/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-2695/trainer_state.json

@@ -0,0 +1,641 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 2695,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.2479030179977415,
+      "epoch": 0.1299545159194282,
+      "grad_norm": 1.519571304321289,
+      "learning_rate": 3.522207847653314e-05,
+      "loss": 2.093206329345703,
+      "mean_token_accuracy": 0.6068353663384914,
+      "num_tokens": 154518.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.932415626347065,
+      "epoch": 0.2599090318388564,
+      "grad_norm": 1.180830955505371,
+      "learning_rate": 7.11629748811588e-05,
+      "loss": 0.8930854797363281,
+      "mean_token_accuracy": 0.7708445385098457,
+      "num_tokens": 306733.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7730373838543891,
+      "epoch": 0.3898635477582846,
+      "grad_norm": 0.7839977145195007,
+      "learning_rate": 0.00010710387128578447,
+      "loss": 0.7302116394042969,
+      "mean_token_accuracy": 0.8012136635184288,
+      "num_tokens": 446267.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6934178560972214,
+      "epoch": 0.5198180636777128,
+      "grad_norm": 0.666778564453125,
+      "learning_rate": 0.0001430447676904101,
+      "loss": 0.6505754852294922,
+      "mean_token_accuracy": 0.8195212116837501,
+      "num_tokens": 600256.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6900296103954315,
+      "epoch": 0.649772579597141,
+      "grad_norm": 0.6762415766716003,
+      "learning_rate": 0.00017898566409503577,
+      "loss": 0.6378536987304687,
+      "mean_token_accuracy": 0.8223087686300278,
+      "num_tokens": 738649.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.667421719878912,
+      "epoch": 0.7797270955165692,
+      "grad_norm": 0.5047685503959656,
+      "learning_rate": 0.00021492656049966144,
+      "loss": 0.6148524856567383,
+      "mean_token_accuracy": 0.8280292323231697,
+      "num_tokens": 883494.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6388977643847465,
+      "epoch": 0.9096816114359974,
+      "grad_norm": 0.4360353350639343,
+      "learning_rate": 0.0002508674569042871,
+      "loss": 0.5933729553222656,
+      "mean_token_accuracy": 0.8329134130477905,
+      "num_tokens": 1032111.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.6612381511009656,
+      "eval_loss": 0.6559221744537354,
+      "eval_mean_token_accuracy": 0.8195324820967821,
+      "eval_num_tokens": 1132140.0,
+      "eval_runtime": 53.4007,
+      "eval_samples_per_second": 31.03,
+      "eval_steps_per_second": 3.895,
+      "step": 385
+    },
+    {
+      "entropy": 0.6224366770916848,
+      "epoch": 1.0389863547758285,
+      "grad_norm": 0.5294668078422546,
+      "learning_rate": 0.00027673375518355765,
+      "loss": 0.5677951431274414,
+      "mean_token_accuracy": 0.8380465067211708,
+      "num_tokens": 1177556.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.5827466724812984,
+      "epoch": 1.1689408706952567,
+      "grad_norm": 0.5172416567802429,
+      "learning_rate": 0.0002765120122346144,
+      "loss": 0.5423126983642578,
+      "mean_token_accuracy": 0.8467991036176682,
+      "num_tokens": 1325434.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5831517253816128,
+      "epoch": 1.2988953866146848,
+      "grad_norm": 0.41916292905807495,
+      "learning_rate": 0.0002760064270819138,
+      "loss": 0.534448013305664,
+      "mean_token_accuracy": 0.8456632816791534,
+      "num_tokens": 1474116.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5869986982643605,
+      "epoch": 1.428849902534113,
+      "grad_norm": 0.4387759566307068,
+      "learning_rate": 0.00027521803857633113,
+      "loss": 0.5367491912841796,
+      "mean_token_accuracy": 0.8462416216731071,
+      "num_tokens": 1621193.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.5771756853163242,
+      "epoch": 1.5588044184535412,
+      "grad_norm": 0.49079665541648865,
+      "learning_rate": 0.00027414846665880935,
+      "loss": 0.5238623809814453,
+      "mean_token_accuracy": 0.84760089635849,
+      "num_tokens": 1767789.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5549105909466744,
+      "epoch": 1.6887589343729694,
+      "grad_norm": 0.4000363051891327,
+      "learning_rate": 0.0002727999090317863,
+      "loss": 0.510434226989746,
+      "mean_token_accuracy": 0.8517858856916427,
+      "num_tokens": 1918138.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.583413660377264,
+      "epoch": 1.8187134502923976,
+      "grad_norm": 0.33592426776885986,
+      "learning_rate": 0.00027117513664346674,
+      "loss": 0.5297993850708008,
+      "mean_token_accuracy": 0.846615691781044,
+      "num_tokens": 2057575.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5732646904885769,
+      "epoch": 1.9486679662118258,
+      "grad_norm": 0.5528839230537415,
+      "learning_rate": 0.00026927748799421714,
+      "loss": 0.5219194793701172,
+      "mean_token_accuracy": 0.8489033079147339,
+      "num_tokens": 2208320.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6027900550801021,
+      "eval_loss": 0.5946928858757019,
+      "eval_mean_token_accuracy": 0.8318195798649237,
+      "eval_num_tokens": 2264280.0,
+      "eval_runtime": 53.3837,
+      "eval_samples_per_second": 31.039,
+      "eval_steps_per_second": 3.896,
+      "step": 770
+    },
+    {
+      "entropy": 0.5329899657611272,
+      "epoch": 2.077972709551657,
+      "grad_norm": 0.45793575048446655,
+      "learning_rate": 0.0002671108622767842,
+      "loss": 0.48420516967773436,
+      "mean_token_accuracy": 0.8578200301333289,
+      "num_tokens": 2348248.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5142687204480171,
+      "epoch": 2.207927225471085,
+      "grad_norm": 0.4690960645675659,
+      "learning_rate": 0.0002646797113644295,
+      "loss": 0.4593114471435547,
+      "mean_token_accuracy": 0.8622670090198516,
+      "num_tokens": 2501427.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.5135884112119675,
+      "epoch": 2.3378817413905133,
+      "grad_norm": 0.3752821683883667,
+      "learning_rate": 0.00026198903066344565,
+      "loss": 0.4626216125488281,
+      "mean_token_accuracy": 0.8612511262297631,
+      "num_tokens": 2650794.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5137367483973503,
+      "epoch": 2.4678362573099415,
+      "grad_norm": 0.3726271390914917,
+      "learning_rate": 0.0002590443488488465,
+      "loss": 0.4601683807373047,
+      "mean_token_accuracy": 0.8620512077212333,
+      "num_tokens": 2798180.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5105714881420136,
+      "epoch": 2.5977907732293697,
+      "grad_norm": 0.41296717524528503,
+      "learning_rate": 0.00025585171650432525,
+      "loss": 0.46279102325439453,
+      "mean_token_accuracy": 0.8611763519048691,
+      "num_tokens": 2950301.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5169161760807037,
+      "epoch": 2.727745289148798,
+      "grad_norm": 0.4614253044128418,
+      "learning_rate": 0.0002524176936898197,
+      "loss": 0.45492774963378907,
+      "mean_token_accuracy": 0.8627680170536042,
+      "num_tokens": 3091810.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.4989277676492929,
+      "epoch": 2.857699805068226,
+      "grad_norm": 0.37512704730033875,
+      "learning_rate": 0.00024874933646223225,
+      "loss": 0.4531984329223633,
+      "mean_token_accuracy": 0.8637665447592735,
+      "num_tokens": 3242184.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5177617704868317,
+      "epoch": 2.9876543209876543,
+      "grad_norm": 0.3700532019138336,
+      "learning_rate": 0.00024485418237699976,
+      "loss": 0.45844474792480466,
+      "mean_token_accuracy": 0.8626988258957863,
+      "num_tokens": 3382605.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5253989950108987,
+      "eval_loss": 0.5857328176498413,
+      "eval_mean_token_accuracy": 0.8360884573597175,
+      "eval_num_tokens": 3396420.0,
+      "eval_runtime": 53.341,
+      "eval_samples_per_second": 31.064,
+      "eval_steps_per_second": 3.899,
+      "step": 1155
+    },
+    {
+      "entropy": 0.4535361140517134,
+      "epoch": 3.116959064327485,
+      "grad_norm": 0.3412795662879944,
+      "learning_rate": 0.00024074023500030492,
+      "loss": 0.3942829132080078,
+      "mean_token_accuracy": 0.8781378038564519,
+      "num_tokens": 3522582.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.44747897461056707,
+      "epoch": 3.246913580246914,
+      "grad_norm": 0.46647050976753235,
+      "learning_rate": 0.0002364159474637521,
+      "loss": 0.38986759185791015,
+      "mean_token_accuracy": 0.8777281475067139,
+      "num_tokens": 3670864.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.4480265176296234,
+      "epoch": 3.3768680961663415,
+      "grad_norm": 0.4068582355976105,
+      "learning_rate": 0.00023189020509529866,
+      "loss": 0.39444759368896487,
+      "mean_token_accuracy": 0.8774515727162361,
+      "num_tokens": 3822021.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.45180007234215736,
+      "epoch": 3.50682261208577,
+      "grad_norm": 0.4249928593635559,
+      "learning_rate": 0.00022717230716213122,
+      "loss": 0.3977077102661133,
+      "mean_token_accuracy": 0.8762744688987731,
+      "num_tokens": 3968736.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.4614932192862034,
+      "epoch": 3.636777128005198,
+      "grad_norm": 0.561008095741272,
+      "learning_rate": 0.00022227194776300045,
+      "loss": 0.4022808456420898,
+      "mean_token_accuracy": 0.8760285252332687,
+      "num_tokens": 4113509.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.4414680179953575,
+      "epoch": 3.7667316439246266,
+      "grad_norm": 0.38943538069725037,
+      "learning_rate": 0.00021719919590927584,
+      "loss": 0.38586376190185545,
+      "mean_token_accuracy": 0.8783121705055237,
+      "num_tokens": 4267958.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.45685607343912127,
+      "epoch": 3.8966861598440543,
+      "grad_norm": 0.5362406969070435,
+      "learning_rate": 0.00021196447483564875,
+      "loss": 0.3983576583862305,
+      "mean_token_accuracy": 0.8764419692754746,
+      "num_tokens": 4415398.0,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.49981127894268584,
+      "eval_loss": 0.5997208952903748,
+      "eval_mean_token_accuracy": 0.8368159819107789,
+      "eval_num_tokens": 4528560.0,
+      "eval_runtime": 53.4304,
+      "eval_samples_per_second": 31.012,
+      "eval_steps_per_second": 3.893,
+      "step": 1540
+    },
+    {
+      "entropy": 0.4439909208060509,
+      "epoch": 4.025990903183885,
+      "grad_norm": 0.5490113496780396,
+      "learning_rate": 0.00020657854058299564,
+      "loss": 0.38307292938232423,
+      "mean_token_accuracy": 0.8795150506436525,
+      "num_tokens": 4559534.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.3837250977009535,
+      "epoch": 4.155945419103314,
+      "grad_norm": 0.5567234754562378,
+      "learning_rate": 0.0002010524598974076,
+      "loss": 0.3182963752746582,
+      "mean_token_accuracy": 0.8964017608761787,
+      "num_tokens": 4707075.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.377872094810009,
+      "epoch": 4.2858999350227425,
+      "grad_norm": 0.4315710961818695,
+      "learning_rate": 0.00019539758749079845,
+      "loss": 0.318333683013916,
+      "mean_token_accuracy": 0.8963816618919372,
+      "num_tokens": 4851683.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.38739304527640345,
+      "epoch": 4.41585445094217,
+      "grad_norm": 0.49140632152557373,
+      "learning_rate": 0.00018962554270981555,
+      "loss": 0.32688804626464846,
+      "mean_token_accuracy": 0.8937860554456711,
+      "num_tokens": 4994086.0,
+      "step": 1700
+    },
+    {
+      "entropy": 0.39157475270330905,
+      "epoch": 4.545808966861598,
+      "grad_norm": 0.40667369961738586,
+      "learning_rate": 0.00018374818566099208,
+      "loss": 0.3305763626098633,
+      "mean_token_accuracy": 0.8916732975840569,
+      "num_tokens": 5137171.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3838599680364132,
+      "epoch": 4.675763482781027,
+      "grad_norm": 0.4632417857646942,
+      "learning_rate": 0.0001777775928411983,
+      "loss": 0.3267818450927734,
+      "mean_token_accuracy": 0.8946500706672669,
+      "num_tokens": 5287076.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.38270787581801413,
+      "epoch": 4.805717998700455,
+      "grad_norm": 0.5529720187187195,
+      "learning_rate": 0.0001717260323234649,
+      "loss": 0.3264235305786133,
+      "mean_token_accuracy": 0.8948800846934318,
+      "num_tokens": 5436923.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.38736109718680384,
+      "epoch": 4.935672514619883,
+      "grad_norm": 0.5604785680770874,
+      "learning_rate": 0.00016560593854916497,
+      "loss": 0.3280513381958008,
+      "mean_token_accuracy": 0.8931388029456139,
+      "num_tokens": 5589195.0,
+      "step": 1900
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.4370518812479881,
+      "eval_loss": 0.6210553050041199,
+      "eval_mean_token_accuracy": 0.8379779781859654,
+      "eval_num_tokens": 5660700.0,
+      "eval_runtime": 53.4039,
+      "eval_samples_per_second": 31.028,
+      "eval_steps_per_second": 3.895,
+      "step": 1925
+    },
+    {
+      "entropy": 0.3330705868988181,
+      "epoch": 5.064977257959714,
+      "grad_norm": 0.5386723875999451,
+      "learning_rate": 0.0001594298867783512,
+      "loss": 0.2754818344116211,
+      "mean_token_accuracy": 0.9101201346771202,
+      "num_tokens": 5739445.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.2980620255321264,
+      "epoch": 5.1949317738791425,
+      "grad_norm": 0.5633581876754761,
+      "learning_rate": 0.00015321056725074549,
+      "loss": 0.23754241943359375,
+      "mean_token_accuracy": 0.9203532826900482,
+      "num_tokens": 5888043.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.3111592583358288,
+      "epoch": 5.32488628979857,
+      "grad_norm": 0.5031015872955322,
+      "learning_rate": 0.0001469607591104745,
+      "loss": 0.24428102493286133,
+      "mean_token_accuracy": 0.917181601524353,
+      "num_tokens": 6031284.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.31522042460739613,
+      "epoch": 5.454840805717999,
+      "grad_norm": 0.6432453393936157,
+      "learning_rate": 0.0001406933041481286,
+      "loss": 0.25112478256225584,
+      "mean_token_accuracy": 0.9152472382783889,
+      "num_tokens": 6179927.0,
+      "step": 2100
+    },
+    {
+      "entropy": 0.3046229027956724,
+      "epoch": 5.584795321637427,
+      "grad_norm": 0.5104537606239319,
+      "learning_rate": 0.00013442108041409814,
+      "loss": 0.2431495475769043,
+      "mean_token_accuracy": 0.917829519212246,
+      "num_tokens": 6322630.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.30440517760813235,
+      "epoch": 5.714749837556855,
+      "grad_norm": 0.5307765603065491,
+      "learning_rate": 0.0001281569757574053,
+      "loss": 0.24610313415527343,
+      "mean_token_accuracy": 0.9166415151953697,
+      "num_tokens": 6469843.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.304359400421381,
+      "epoch": 5.844704353476283,
+      "grad_norm": 0.5014523267745972,
+      "learning_rate": 0.00012191386134440133,
+      "loss": 0.24548973083496095,
+      "mean_token_accuracy": 0.9165477308630944,
+      "num_tokens": 6617768.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.3141418205201626,
+      "epoch": 5.974658869395712,
+      "grad_norm": 0.567398726940155,
+      "learning_rate": 0.00011570456521174339,
+      "loss": 0.24975168228149414,
+      "mean_token_accuracy": 0.9139353120326996,
+      "num_tokens": 6761187.0,
+      "step": 2300
+    },
+    {
+      "epoch": 6.0,
+      "eval_entropy": 0.3758909202252443,
+      "eval_loss": 0.6843022108078003,
+      "eval_mean_token_accuracy": 0.8348075449466705,
+      "eval_num_tokens": 6792840.0,
+      "eval_runtime": 53.3825,
+      "eval_samples_per_second": 31.04,
+      "eval_steps_per_second": 3.896,
+      "step": 2310
+    },
+    {
+      "entropy": 0.24346149432000203,
+      "epoch": 6.1039636127355426,
+      "grad_norm": 0.7140825986862183,
+      "learning_rate": 0.00010954184590799172,
+      "loss": 0.17231273651123047,
+      "mean_token_accuracy": 0.9407721275660261,
+      "num_tokens": 6909578.0,
+      "step": 2350
+    },
+    {
+      "entropy": 0.2160973483324051,
+      "epoch": 6.23391812865497,
+      "grad_norm": 0.49014952778816223,
+      "learning_rate": 0.00010343836627798716,
+      "loss": 0.15455107688903807,
+      "mean_token_accuracy": 0.9467655989527702,
+      "num_tokens": 7056244.0,
+      "step": 2400
+    },
+    {
+      "entropy": 0.21491924367845058,
+      "epoch": 6.363872644574399,
+      "grad_norm": 0.5529471635818481,
+      "learning_rate": 9.740666744387656e-05,
+      "loss": 0.1584029197692871,
+      "mean_token_accuracy": 0.9460993978381157,
+      "num_tokens": 7206950.0,
+      "step": 2450
+    },
+    {
+      "entropy": 0.22037068914622068,
+      "epoch": 6.493827160493828,
+      "grad_norm": 0.6232843995094299,
+      "learning_rate": 9.145914303624717e-05,
+      "loss": 0.15544342041015624,
+      "mean_token_accuracy": 0.9450622496008872,
+      "num_tokens": 7359429.0,
+      "step": 2500
+    },
+    {
+      "entropy": 0.2320463878661394,
+      "epoch": 6.623781676413255,
+      "grad_norm": 0.7459681630134583,
+      "learning_rate": 8.560801372831975e-05,
+      "loss": 0.16350215911865235,
+      "mean_token_accuracy": 0.9416968420147895,
+      "num_tokens": 7499281.0,
+      "step": 2550
+    },
+    {
+      "entropy": 0.22943626195192338,
+      "epoch": 6.753736192332683,
+      "grad_norm": 0.7482302784919739,
+      "learning_rate": 7.986530212552506e-05,
+      "loss": 0.16422538757324218,
+      "mean_token_accuracy": 0.9434959614276885,
+      "num_tokens": 7640758.0,
+      "step": 2600
+    },
+    {
+      "entropy": 0.21795938543975354,
+      "epoch": 6.883690708252112,
+      "grad_norm": 0.5210486054420471,
+      "learning_rate": 7.424280806206118e-05,
+      "loss": 0.15540474891662598,
+      "mean_token_accuracy": 0.9459306105971337,
+      "num_tokens": 7791986.0,
+      "step": 2650
+    },
+    {
+      "epoch": 7.0,
+      "eval_entropy": 0.3157534837149657,
+      "eval_loss": 0.7744874954223633,
+      "eval_mean_token_accuracy": 0.8346395036922052,
+      "eval_num_tokens": 7924980.0,
+      "eval_runtime": 53.3771,
+      "eval_samples_per_second": 31.043,
+      "eval_steps_per_second": 3.897,
+      "step": 2695
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.4509364053876326e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-3080/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-3080/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.009078376988692594,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-3080/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-3080/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-3080/trainer_state.json

@@ -0,0 +1,732 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 3080,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.2479030179977415,
+      "epoch": 0.1299545159194282,
+      "grad_norm": 1.519571304321289,
+      "learning_rate": 3.522207847653314e-05,
+      "loss": 2.093206329345703,
+      "mean_token_accuracy": 0.6068353663384914,
+      "num_tokens": 154518.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.932415626347065,
+      "epoch": 0.2599090318388564,
+      "grad_norm": 1.180830955505371,
+      "learning_rate": 7.11629748811588e-05,
+      "loss": 0.8930854797363281,
+      "mean_token_accuracy": 0.7708445385098457,
+      "num_tokens": 306733.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7730373838543891,
+      "epoch": 0.3898635477582846,
+      "grad_norm": 0.7839977145195007,
+      "learning_rate": 0.00010710387128578447,
+      "loss": 0.7302116394042969,
+      "mean_token_accuracy": 0.8012136635184288,
+      "num_tokens": 446267.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6934178560972214,
+      "epoch": 0.5198180636777128,
+      "grad_norm": 0.666778564453125,
+      "learning_rate": 0.0001430447676904101,
+      "loss": 0.6505754852294922,
+      "mean_token_accuracy": 0.8195212116837501,
+      "num_tokens": 600256.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6900296103954315,
+      "epoch": 0.649772579597141,
+      "grad_norm": 0.6762415766716003,
+      "learning_rate": 0.00017898566409503577,
+      "loss": 0.6378536987304687,
+      "mean_token_accuracy": 0.8223087686300278,
+      "num_tokens": 738649.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.667421719878912,
+      "epoch": 0.7797270955165692,
+      "grad_norm": 0.5047685503959656,
+      "learning_rate": 0.00021492656049966144,
+      "loss": 0.6148524856567383,
+      "mean_token_accuracy": 0.8280292323231697,
+      "num_tokens": 883494.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6388977643847465,
+      "epoch": 0.9096816114359974,
+      "grad_norm": 0.4360353350639343,
+      "learning_rate": 0.0002508674569042871,
+      "loss": 0.5933729553222656,
+      "mean_token_accuracy": 0.8329134130477905,
+      "num_tokens": 1032111.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.6612381511009656,
+      "eval_loss": 0.6559221744537354,
+      "eval_mean_token_accuracy": 0.8195324820967821,
+      "eval_num_tokens": 1132140.0,
+      "eval_runtime": 53.4007,
+      "eval_samples_per_second": 31.03,
+      "eval_steps_per_second": 3.895,
+      "step": 385
+    },
+    {
+      "entropy": 0.6224366770916848,
+      "epoch": 1.0389863547758285,
+      "grad_norm": 0.5294668078422546,
+      "learning_rate": 0.00027673375518355765,
+      "loss": 0.5677951431274414,
+      "mean_token_accuracy": 0.8380465067211708,
+      "num_tokens": 1177556.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.5827466724812984,
+      "epoch": 1.1689408706952567,
+      "grad_norm": 0.5172416567802429,
+      "learning_rate": 0.0002765120122346144,
+      "loss": 0.5423126983642578,
+      "mean_token_accuracy": 0.8467991036176682,
+      "num_tokens": 1325434.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5831517253816128,
+      "epoch": 1.2988953866146848,
+      "grad_norm": 0.41916292905807495,
+      "learning_rate": 0.0002760064270819138,
+      "loss": 0.534448013305664,
+      "mean_token_accuracy": 0.8456632816791534,
+      "num_tokens": 1474116.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5869986982643605,
+      "epoch": 1.428849902534113,
+      "grad_norm": 0.4387759566307068,
+      "learning_rate": 0.00027521803857633113,
+      "loss": 0.5367491912841796,
+      "mean_token_accuracy": 0.8462416216731071,
+      "num_tokens": 1621193.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.5771756853163242,
+      "epoch": 1.5588044184535412,
+      "grad_norm": 0.49079665541648865,
+      "learning_rate": 0.00027414846665880935,
+      "loss": 0.5238623809814453,
+      "mean_token_accuracy": 0.84760089635849,
+      "num_tokens": 1767789.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.5549105909466744,
+      "epoch": 1.6887589343729694,
+      "grad_norm": 0.4000363051891327,
+      "learning_rate": 0.0002727999090317863,
+      "loss": 0.510434226989746,
+      "mean_token_accuracy": 0.8517858856916427,
+      "num_tokens": 1918138.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.583413660377264,
+      "epoch": 1.8187134502923976,
+      "grad_norm": 0.33592426776885986,
+      "learning_rate": 0.00027117513664346674,
+      "loss": 0.5297993850708008,
+      "mean_token_accuracy": 0.846615691781044,
+      "num_tokens": 2057575.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5732646904885769,
+      "epoch": 1.9486679662118258,
+      "grad_norm": 0.5528839230537415,
+      "learning_rate": 0.00026927748799421714,
+      "loss": 0.5219194793701172,
+      "mean_token_accuracy": 0.8489033079147339,
+      "num_tokens": 2208320.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6027900550801021,
+      "eval_loss": 0.5946928858757019,
+      "eval_mean_token_accuracy": 0.8318195798649237,
+      "eval_num_tokens": 2264280.0,
+      "eval_runtime": 53.3837,
+      "eval_samples_per_second": 31.039,
+      "eval_steps_per_second": 3.896,
+      "step": 770
+    },
+    {
+      "entropy": 0.5329899657611272,
+      "epoch": 2.077972709551657,
+      "grad_norm": 0.45793575048446655,
+      "learning_rate": 0.0002671108622767842,
+      "loss": 0.48420516967773436,
+      "mean_token_accuracy": 0.8578200301333289,
+      "num_tokens": 2348248.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5142687204480171,
+      "epoch": 2.207927225471085,
+      "grad_norm": 0.4690960645675659,
+      "learning_rate": 0.0002646797113644295,
+      "loss": 0.4593114471435547,
+      "mean_token_accuracy": 0.8622670090198516,
+      "num_tokens": 2501427.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.5135884112119675,
+      "epoch": 2.3378817413905133,
+      "grad_norm": 0.3752821683883667,
+      "learning_rate": 0.00026198903066344565,
+      "loss": 0.4626216125488281,
+      "mean_token_accuracy": 0.8612511262297631,
+      "num_tokens": 2650794.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5137367483973503,
+      "epoch": 2.4678362573099415,
+      "grad_norm": 0.3726271390914917,
+      "learning_rate": 0.0002590443488488465,
+      "loss": 0.4601683807373047,
+      "mean_token_accuracy": 0.8620512077212333,
+      "num_tokens": 2798180.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5105714881420136,
+      "epoch": 2.5977907732293697,
+      "grad_norm": 0.41296717524528503,
+      "learning_rate": 0.00025585171650432525,
+      "loss": 0.46279102325439453,
+      "mean_token_accuracy": 0.8611763519048691,
+      "num_tokens": 2950301.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5169161760807037,
+      "epoch": 2.727745289148798,
+      "grad_norm": 0.4614253044128418,
+      "learning_rate": 0.0002524176936898197,
+      "loss": 0.45492774963378907,
+      "mean_token_accuracy": 0.8627680170536042,
+      "num_tokens": 3091810.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.4989277676492929,
+      "epoch": 2.857699805068226,
+      "grad_norm": 0.37512704730033875,
+      "learning_rate": 0.00024874933646223225,
+      "loss": 0.4531984329223633,
+      "mean_token_accuracy": 0.8637665447592735,
+      "num_tokens": 3242184.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5177617704868317,
+      "epoch": 2.9876543209876543,
+      "grad_norm": 0.3700532019138336,
+      "learning_rate": 0.00024485418237699976,
+      "loss": 0.45844474792480466,
+      "mean_token_accuracy": 0.8626988258957863,
+      "num_tokens": 3382605.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5253989950108987,
+      "eval_loss": 0.5857328176498413,
+      "eval_mean_token_accuracy": 0.8360884573597175,
+      "eval_num_tokens": 3396420.0,
+      "eval_runtime": 53.341,
+      "eval_samples_per_second": 31.064,
+      "eval_steps_per_second": 3.899,
+      "step": 1155
+    },
+    {
+      "entropy": 0.4535361140517134,
+      "epoch": 3.116959064327485,
+      "grad_norm": 0.3412795662879944,
+      "learning_rate": 0.00024074023500030492,
+      "loss": 0.3942829132080078,
+      "mean_token_accuracy": 0.8781378038564519,
+      "num_tokens": 3522582.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.44747897461056707,
+      "epoch": 3.246913580246914,
+      "grad_norm": 0.46647050976753235,
+      "learning_rate": 0.0002364159474637521,
+      "loss": 0.38986759185791015,
+      "mean_token_accuracy": 0.8777281475067139,
+      "num_tokens": 3670864.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.4480265176296234,
+      "epoch": 3.3768680961663415,
+      "grad_norm": 0.4068582355976105,
+      "learning_rate": 0.00023189020509529866,
+      "loss": 0.39444759368896487,
+      "mean_token_accuracy": 0.8774515727162361,
+      "num_tokens": 3822021.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.45180007234215736,
+      "epoch": 3.50682261208577,
+      "grad_norm": 0.4249928593635559,
+      "learning_rate": 0.00022717230716213122,
+      "loss": 0.3977077102661133,
+      "mean_token_accuracy": 0.8762744688987731,
+      "num_tokens": 3968736.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.4614932192862034,
+      "epoch": 3.636777128005198,
+      "grad_norm": 0.561008095741272,
+      "learning_rate": 0.00022227194776300045,
+      "loss": 0.4022808456420898,
+      "mean_token_accuracy": 0.8760285252332687,
+      "num_tokens": 4113509.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.4414680179953575,
+      "epoch": 3.7667316439246266,
+      "grad_norm": 0.38943538069725037,
+      "learning_rate": 0.00021719919590927584,
+      "loss": 0.38586376190185545,
+      "mean_token_accuracy": 0.8783121705055237,
+      "num_tokens": 4267958.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.45685607343912127,
+      "epoch": 3.8966861598440543,
+      "grad_norm": 0.5362406969070435,
+      "learning_rate": 0.00021196447483564875,
+      "loss": 0.3983576583862305,
+      "mean_token_accuracy": 0.8764419692754746,
+      "num_tokens": 4415398.0,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.49981127894268584,
+      "eval_loss": 0.5997208952903748,
+      "eval_mean_token_accuracy": 0.8368159819107789,
+      "eval_num_tokens": 4528560.0,
+      "eval_runtime": 53.4304,
+      "eval_samples_per_second": 31.012,
+      "eval_steps_per_second": 3.893,
+      "step": 1540
+    },
+    {
+      "entropy": 0.4439909208060509,
+      "epoch": 4.025990903183885,
+      "grad_norm": 0.5490113496780396,
+      "learning_rate": 0.00020657854058299564,
+      "loss": 0.38307292938232423,
+      "mean_token_accuracy": 0.8795150506436525,
+      "num_tokens": 4559534.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.3837250977009535,
+      "epoch": 4.155945419103314,
+      "grad_norm": 0.5567234754562378,
+      "learning_rate": 0.0002010524598974076,
+      "loss": 0.3182963752746582,
+      "mean_token_accuracy": 0.8964017608761787,
+      "num_tokens": 4707075.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.377872094810009,
+      "epoch": 4.2858999350227425,
+      "grad_norm": 0.4315710961818695,
+      "learning_rate": 0.00019539758749079845,
+      "loss": 0.318333683013916,
+      "mean_token_accuracy": 0.8963816618919372,
+      "num_tokens": 4851683.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.38739304527640345,
+      "epoch": 4.41585445094217,
+      "grad_norm": 0.49140632152557373,
+      "learning_rate": 0.00018962554270981555,
+      "loss": 0.32688804626464846,
+      "mean_token_accuracy": 0.8937860554456711,
+      "num_tokens": 4994086.0,
+      "step": 1700
+    },
+    {
+      "entropy": 0.39157475270330905,
+      "epoch": 4.545808966861598,
+      "grad_norm": 0.40667369961738586,
+      "learning_rate": 0.00018374818566099208,
+      "loss": 0.3305763626098633,
+      "mean_token_accuracy": 0.8916732975840569,
+      "num_tokens": 5137171.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.3838599680364132,
+      "epoch": 4.675763482781027,
+      "grad_norm": 0.4632417857646942,
+      "learning_rate": 0.0001777775928411983,
+      "loss": 0.3267818450927734,
+      "mean_token_accuracy": 0.8946500706672669,
+      "num_tokens": 5287076.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.38270787581801413,
+      "epoch": 4.805717998700455,
+      "grad_norm": 0.5529720187187195,
+      "learning_rate": 0.0001717260323234649,
+      "loss": 0.3264235305786133,
+      "mean_token_accuracy": 0.8948800846934318,
+      "num_tokens": 5436923.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.38736109718680384,
+      "epoch": 4.935672514619883,
+      "grad_norm": 0.5604785680770874,
+      "learning_rate": 0.00016560593854916497,
+      "loss": 0.3280513381958008,
+      "mean_token_accuracy": 0.8931388029456139,
+      "num_tokens": 5589195.0,
+      "step": 1900
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 0.4370518812479881,
+      "eval_loss": 0.6210553050041199,
+      "eval_mean_token_accuracy": 0.8379779781859654,
+      "eval_num_tokens": 5660700.0,
+      "eval_runtime": 53.4039,
+      "eval_samples_per_second": 31.028,
+      "eval_steps_per_second": 3.895,
+      "step": 1925
+    },
+    {
+      "entropy": 0.3330705868988181,
+      "epoch": 5.064977257959714,
+      "grad_norm": 0.5386723875999451,
+      "learning_rate": 0.0001594298867783512,
+      "loss": 0.2754818344116211,
+      "mean_token_accuracy": 0.9101201346771202,
+      "num_tokens": 5739445.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.2980620255321264,
+      "epoch": 5.1949317738791425,
+      "grad_norm": 0.5633581876754761,
+      "learning_rate": 0.00015321056725074549,
+      "loss": 0.23754241943359375,
+      "mean_token_accuracy": 0.9203532826900482,
+      "num_tokens": 5888043.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.3111592583358288,
+      "epoch": 5.32488628979857,
+      "grad_norm": 0.5031015872955322,
+      "learning_rate": 0.0001469607591104745,
+      "loss": 0.24428102493286133,
+      "mean_token_accuracy": 0.917181601524353,
+      "num_tokens": 6031284.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.31522042460739613,
+      "epoch": 5.454840805717999,
+      "grad_norm": 0.6432453393936157,
+      "learning_rate": 0.0001406933041481286,
+      "loss": 0.25112478256225584,
+      "mean_token_accuracy": 0.9152472382783889,
+      "num_tokens": 6179927.0,
+      "step": 2100
+    },
+    {
+      "entropy": 0.3046229027956724,
+      "epoch": 5.584795321637427,
+      "grad_norm": 0.5104537606239319,
+      "learning_rate": 0.00013442108041409814,
+      "loss": 0.2431495475769043,
+      "mean_token_accuracy": 0.917829519212246,
+      "num_tokens": 6322630.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.30440517760813235,
+      "epoch": 5.714749837556855,
+      "grad_norm": 0.5307765603065491,
+      "learning_rate": 0.0001281569757574053,
+      "loss": 0.24610313415527343,
+      "mean_token_accuracy": 0.9166415151953697,
+      "num_tokens": 6469843.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.304359400421381,
+      "epoch": 5.844704353476283,
+      "grad_norm": 0.5014523267745972,
+      "learning_rate": 0.00012191386134440133,
+      "loss": 0.24548973083496095,
+      "mean_token_accuracy": 0.9165477308630944,
+      "num_tokens": 6617768.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.3141418205201626,
+      "epoch": 5.974658869395712,
+      "grad_norm": 0.567398726940155,
+      "learning_rate": 0.00011570456521174339,
+      "loss": 0.24975168228149414,
+      "mean_token_accuracy": 0.9139353120326996,
+      "num_tokens": 6761187.0,
+      "step": 2300
+    },
+    {
+      "epoch": 6.0,
+      "eval_entropy": 0.3758909202252443,
+      "eval_loss": 0.6843022108078003,
+      "eval_mean_token_accuracy": 0.8348075449466705,
+      "eval_num_tokens": 6792840.0,
+      "eval_runtime": 53.3825,
+      "eval_samples_per_second": 31.04,
+      "eval_steps_per_second": 3.896,
+      "step": 2310
+    },
+    {
+      "entropy": 0.24346149432000203,
+      "epoch": 6.1039636127355426,
+      "grad_norm": 0.7140825986862183,
+      "learning_rate": 0.00010954184590799172,
+      "loss": 0.17231273651123047,
+      "mean_token_accuracy": 0.9407721275660261,
+      "num_tokens": 6909578.0,
+      "step": 2350
+    },
+    {
+      "entropy": 0.2160973483324051,
+      "epoch": 6.23391812865497,
+      "grad_norm": 0.49014952778816223,
+      "learning_rate": 0.00010343836627798716,
+      "loss": 0.15455107688903807,
+      "mean_token_accuracy": 0.9467655989527702,
+      "num_tokens": 7056244.0,
+      "step": 2400
+    },
+    {
+      "entropy": 0.21491924367845058,
+      "epoch": 6.363872644574399,
+      "grad_norm": 0.5529471635818481,
+      "learning_rate": 9.740666744387656e-05,
+      "loss": 0.1584029197692871,
+      "mean_token_accuracy": 0.9460993978381157,
+      "num_tokens": 7206950.0,
+      "step": 2450
+    },
+    {
+      "entropy": 0.22037068914622068,
+      "epoch": 6.493827160493828,
+      "grad_norm": 0.6232843995094299,
+      "learning_rate": 9.145914303624717e-05,
+      "loss": 0.15544342041015624,
+      "mean_token_accuracy": 0.9450622496008872,
+      "num_tokens": 7359429.0,
+      "step": 2500
+    },
+    {
+      "entropy": 0.2320463878661394,
+      "epoch": 6.623781676413255,
+      "grad_norm": 0.7459681630134583,
+      "learning_rate": 8.560801372831975e-05,
+      "loss": 0.16350215911865235,
+      "mean_token_accuracy": 0.9416968420147895,
+      "num_tokens": 7499281.0,
+      "step": 2550
+    },
+    {
+      "entropy": 0.22943626195192338,
+      "epoch": 6.753736192332683,
+      "grad_norm": 0.7482302784919739,
+      "learning_rate": 7.986530212552506e-05,
+      "loss": 0.16422538757324218,
+      "mean_token_accuracy": 0.9434959614276885,
+      "num_tokens": 7640758.0,
+      "step": 2600
+    },
+    {
+      "entropy": 0.21795938543975354,
+      "epoch": 6.883690708252112,
+      "grad_norm": 0.5210486054420471,
+      "learning_rate": 7.424280806206118e-05,
+      "loss": 0.15540474891662598,
+      "mean_token_accuracy": 0.9459306105971337,
+      "num_tokens": 7791986.0,
+      "step": 2650
+    },
+    {
+      "epoch": 7.0,
+      "eval_entropy": 0.3157534837149657,
+      "eval_loss": 0.7744874954223633,
+      "eval_mean_token_accuracy": 0.8346395036922052,
+      "eval_num_tokens": 7924980.0,
+      "eval_runtime": 53.3771,
+      "eval_samples_per_second": 31.043,
+      "eval_steps_per_second": 3.897,
+      "step": 2695
+    },
+    {
+      "entropy": 0.2124774060656677,
+      "epoch": 7.012995451591943,
+      "grad_norm": 0.42238789796829224,
+      "learning_rate": 6.875208435518865e-05,
+      "loss": 0.14792531967163086,
+      "mean_token_accuracy": 0.9490461115861059,
+      "num_tokens": 7940521.0,
+      "step": 2700
+    },
+    {
+      "entropy": 0.15692965138703585,
+      "epoch": 7.142949967511371,
+      "grad_norm": 0.4711572229862213,
+      "learning_rate": 6.340441306708468e-05,
+      "loss": 0.09051708221435546,
+      "mean_token_accuracy": 0.9700166273117066,
+      "num_tokens": 8084193.0,
+      "step": 2750
+    },
+    {
+      "entropy": 0.15241683423519134,
+      "epoch": 7.272904483430799,
+      "grad_norm": 0.4312196671962738,
+      "learning_rate": 5.821078232303016e-05,
+      "loss": 0.08812363624572754,
+      "mean_token_accuracy": 0.9699361199140548,
+      "num_tokens": 8230159.0,
+      "step": 2800
+    },
+    {
+      "entropy": 0.1459079357981682,
+      "epoch": 7.402858999350228,
+      "grad_norm": 0.4804084002971649,
+      "learning_rate": 5.3181863733564636e-05,
+      "loss": 0.08675944328308105,
+      "mean_token_accuracy": 0.9703072866797448,
+      "num_tokens": 8380556.0,
+      "step": 2850
+    },
+    {
+      "entropy": 0.15621621005237102,
+      "epoch": 7.532813515269655,
+      "grad_norm": 0.5435478091239929,
+      "learning_rate": 4.83279904669986e-05,
+      "loss": 0.09016354560852051,
+      "mean_token_accuracy": 0.9674961140751839,
+      "num_tokens": 8523248.0,
+      "step": 2900
+    },
+    {
+      "entropy": 0.1545175113901496,
+      "epoch": 7.662768031189084,
+      "grad_norm": 0.524286687374115,
+      "learning_rate": 4.365913601734056e-05,
+      "loss": 0.09049141883850098,
+      "mean_token_accuracy": 0.9679373624920845,
+      "num_tokens": 8672002.0,
+      "step": 2950
+    },
+    {
+      "entropy": 0.1553485019877553,
+      "epoch": 7.792722547108512,
+      "grad_norm": 0.5006484389305115,
+      "learning_rate": 3.9184893711264495e-05,
+      "loss": 0.08913107872009278,
+      "mean_token_accuracy": 0.9684559822082519,
+      "num_tokens": 8816090.0,
+      "step": 3000
+    },
+    {
+      "entropy": 0.15444331549108029,
+      "epoch": 7.92267706302794,
+      "grad_norm": 0.5613893866539001,
+      "learning_rate": 3.491445699622611e-05,
+      "loss": 0.08711207389831543,
+      "mean_token_accuracy": 0.9684525722265244,
+      "num_tokens": 8966004.0,
+      "step": 3050
+    },
+    {
+      "epoch": 8.0,
+      "eval_entropy": 0.26580205430778175,
+      "eval_loss": 0.8996392488479614,
+      "eval_mean_token_accuracy": 0.8319417791297803,
+      "eval_num_tokens": 9057120.0,
+      "eval_runtime": 53.4042,
+      "eval_samples_per_second": 31.028,
+      "eval_steps_per_second": 3.895,
+      "step": 3080
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.9430479532657766e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-3465/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-3465/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.009078376988692594,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test1/checkpoint-3465/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: transformers
+model_name: Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2
+
+This model is a fine-tuned version of [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/katriin-kukk/Cross_lingual_morphological_generalization/runs/5wprubge) 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.29.0
+- Transformers: 5.5.4
+- Pytorch: 2.10.0
+- Datasets: 4.6.1
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/checkpoint-1155/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/checkpoint-1155/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.04123083959940288,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/checkpoint-1155/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/checkpoint-1155/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/checkpoint-1155/trainer_state.json

@@ -0,0 +1,297 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1155,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.856709834933281,
+      "epoch": 0.1299545159194282,
+      "grad_norm": 0.8576324582099915,
+      "learning_rate": 5.622316634653647e-05,
+      "loss": 1.7368515014648438,
+      "mean_token_accuracy": 0.6531239575147629,
+      "num_tokens": 154518.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.7963882395625115,
+      "epoch": 0.2599090318388564,
+      "grad_norm": 0.478260338306427,
+      "learning_rate": 0.00011359374425116552,
+      "loss": 0.7638471984863281,
+      "mean_token_accuracy": 0.794710833132267,
+      "num_tokens": 306733.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.72038290143013,
+      "epoch": 0.3898635477582846,
+      "grad_norm": 0.44744813442230225,
+      "learning_rate": 0.0001709643221557946,
+      "loss": 0.6789447021484375,
+      "mean_token_accuracy": 0.8134408834576606,
+      "num_tokens": 446267.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6589414384961129,
+      "epoch": 0.5198180636777128,
+      "grad_norm": 0.3264491856098175,
+      "learning_rate": 0.0002283349000604236,
+      "loss": 0.6165869903564453,
+      "mean_token_accuracy": 0.8283544909954071,
+      "num_tokens": 600256.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6685489591956139,
+      "epoch": 0.649772579597141,
+      "grad_norm": 0.46411946415901184,
+      "learning_rate": 0.0002857054779650527,
+      "loss": 0.6179034805297852,
+      "mean_token_accuracy": 0.8271848052740097,
+      "num_tokens": 738649.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6590392506122589,
+      "epoch": 0.7797270955165692,
+      "grad_norm": 0.4984032213687897,
+      "learning_rate": 0.00034307605586968176,
+      "loss": 0.6105824661254883,
+      "mean_token_accuracy": 0.8298770362138748,
+      "num_tokens": 883494.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6322308082878589,
+      "epoch": 0.9096816114359974,
+      "grad_norm": 0.35582953691482544,
+      "learning_rate": 0.0004004466337743108,
+      "loss": 0.5987993621826172,
+      "mean_token_accuracy": 0.8332566061615944,
+      "num_tokens": 1032111.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.6668267184152052,
+      "eval_loss": 0.6812539100646973,
+      "eval_mean_token_accuracy": 0.8146296894321075,
+      "eval_num_tokens": 1132140.0,
+      "eval_runtime": 53.08,
+      "eval_samples_per_second": 31.217,
+      "eval_steps_per_second": 3.919,
+      "step": 385
+    },
+    {
+      "entropy": 0.6360254319169414,
+      "epoch": 1.0389863547758285,
+      "grad_norm": 0.537056028842926,
+      "learning_rate": 0.0004417356562802791,
+      "loss": 0.5937010192871094,
+      "mean_token_accuracy": 0.8332705884123567,
+      "num_tokens": 1177556.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.5945304277539253,
+      "epoch": 1.1689408706952567,
+      "grad_norm": 0.4016346335411072,
+      "learning_rate": 0.00044138169957914594,
+      "loss": 0.564481430053711,
+      "mean_token_accuracy": 0.8422813892364502,
+      "num_tokens": 1325434.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5895386649668217,
+      "epoch": 1.2988953866146848,
+      "grad_norm": 0.32074230909347534,
+      "learning_rate": 0.00044057466037611984,
+      "loss": 0.5511369705200195,
+      "mean_token_accuracy": 0.8431353771686554,
+      "num_tokens": 1474116.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5951217761635781,
+      "epoch": 1.428849902534113,
+      "grad_norm": 0.3066493272781372,
+      "learning_rate": 0.00043931619693465644,
+      "loss": 0.5558741760253906,
+      "mean_token_accuracy": 0.84255860298872,
+      "num_tokens": 1621193.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.5773422825336456,
+      "epoch": 1.5588044184535412,
+      "grad_norm": 0.38174429535865784,
+      "learning_rate": 0.00043760889508197114,
+      "loss": 0.5448895263671875,
+      "mean_token_accuracy": 0.8427786123752594,
+      "num_tokens": 1767789.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.568668949753046,
+      "epoch": 1.6887589343729694,
+      "grad_norm": 0.4095861613750458,
+      "learning_rate": 0.0004354562628958121,
+      "loss": 0.5313994598388672,
+      "mean_token_accuracy": 0.847584228515625,
+      "num_tokens": 1918138.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.5952580836415291,
+      "epoch": 1.8187134502923976,
+      "grad_norm": 0.34596189856529236,
+      "learning_rate": 0.0004328627234962387,
+      "loss": 0.5546007919311523,
+      "mean_token_accuracy": 0.8419265493750572,
+      "num_tokens": 2057575.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5800049532949925,
+      "epoch": 1.9486679662118258,
+      "grad_norm": 0.3752591609954834,
+      "learning_rate": 0.0004298336059572178,
+      "loss": 0.5452734756469727,
+      "mean_token_accuracy": 0.8436958035826683,
+      "num_tokens": 2208320.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6070062083980212,
+      "eval_loss": 0.631233274936676,
+      "eval_mean_token_accuracy": 0.8255004269572405,
+      "eval_num_tokens": 2264280.0,
+      "eval_runtime": 53.1092,
+      "eval_samples_per_second": 31.2,
+      "eval_steps_per_second": 3.916,
+      "step": 770
+    },
+    {
+      "entropy": 0.5432504566770103,
+      "epoch": 2.077972709551657,
+      "grad_norm": 0.4615200459957123,
+      "learning_rate": 0.0004263751343567108,
+      "loss": 0.5117238616943359,
+      "mean_token_accuracy": 0.8515748070113024,
+      "num_tokens": 2348248.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5108437672257423,
+      "epoch": 2.207927225471085,
+      "grad_norm": 0.39224034547805786,
+      "learning_rate": 0.0004224944149877526,
+      "loss": 0.47819324493408205,
+      "mean_token_accuracy": 0.8583902576565743,
+      "num_tokens": 2501427.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.5110109977424144,
+      "epoch": 2.3378817413905133,
+      "grad_norm": 0.36829307675361633,
+      "learning_rate": 0.00041819942175679877,
+      "loss": 0.4832262420654297,
+      "mean_token_accuracy": 0.8568637049198151,
+      "num_tokens": 2650794.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5188203908503055,
+      "epoch": 2.4678362573099415,
+      "grad_norm": 0.47326067090034485,
+      "learning_rate": 0.00041349897979934495,
+      "loss": 0.48348499298095704,
+      "mean_token_accuracy": 0.8567950987815857,
+      "num_tokens": 2798180.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5181271532177925,
+      "epoch": 2.5977907732293697,
+      "grad_norm": 0.2972731292247772,
+      "learning_rate": 0.0004084027473464832,
+      "loss": 0.4918654251098633,
+      "mean_token_accuracy": 0.8539192593097686,
+      "num_tokens": 2950301.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5172442196309567,
+      "epoch": 2.727745289148798,
+      "grad_norm": 0.4516422152519226,
+      "learning_rate": 0.0004029211958796559,
+      "loss": 0.4767612457275391,
+      "mean_token_accuracy": 0.8575084239244462,
+      "num_tokens": 3091810.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.5078031922131777,
+      "epoch": 2.857699805068226,
+      "grad_norm": 0.28876274824142456,
+      "learning_rate": 0.00039706558861438384,
+      "loss": 0.47852867126464843,
+      "mean_token_accuracy": 0.8580548599362373,
+      "num_tokens": 3242184.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5267327691614628,
+      "epoch": 2.9876543209876543,
+      "grad_norm": 0.29029977321624756,
+      "learning_rate": 0.000390847957357179,
+      "loss": 0.48259868621826174,
+      "mean_token_accuracy": 0.8568289718031883,
+      "num_tokens": 3382605.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5411632635559027,
+      "eval_loss": 0.5956819653511047,
+      "eval_mean_token_accuracy": 0.8327134661376476,
+      "eval_num_tokens": 3396420.0,
+      "eval_runtime": 53.1279,
+      "eval_samples_per_second": 31.189,
+      "eval_steps_per_second": 3.915,
+      "step": 1155
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.562044974242181e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/checkpoint-1540/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/checkpoint-1540/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.04123083959940288,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/checkpoint-1540/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/checkpoint-1540/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/checkpoint-1540/trainer_state.json

@@ -0,0 +1,378 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1540,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.856709834933281,
+      "epoch": 0.1299545159194282,
+      "grad_norm": 0.8576324582099915,
+      "learning_rate": 5.622316634653647e-05,
+      "loss": 1.7368515014648438,
+      "mean_token_accuracy": 0.6531239575147629,
+      "num_tokens": 154518.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.7963882395625115,
+      "epoch": 0.2599090318388564,
+      "grad_norm": 0.478260338306427,
+      "learning_rate": 0.00011359374425116552,
+      "loss": 0.7638471984863281,
+      "mean_token_accuracy": 0.794710833132267,
+      "num_tokens": 306733.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.72038290143013,
+      "epoch": 0.3898635477582846,
+      "grad_norm": 0.44744813442230225,
+      "learning_rate": 0.0001709643221557946,
+      "loss": 0.6789447021484375,
+      "mean_token_accuracy": 0.8134408834576606,
+      "num_tokens": 446267.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.6589414384961129,
+      "epoch": 0.5198180636777128,
+      "grad_norm": 0.3264491856098175,
+      "learning_rate": 0.0002283349000604236,
+      "loss": 0.6165869903564453,
+      "mean_token_accuracy": 0.8283544909954071,
+      "num_tokens": 600256.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6685489591956139,
+      "epoch": 0.649772579597141,
+      "grad_norm": 0.46411946415901184,
+      "learning_rate": 0.0002857054779650527,
+      "loss": 0.6179034805297852,
+      "mean_token_accuracy": 0.8271848052740097,
+      "num_tokens": 738649.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6590392506122589,
+      "epoch": 0.7797270955165692,
+      "grad_norm": 0.4984032213687897,
+      "learning_rate": 0.00034307605586968176,
+      "loss": 0.6105824661254883,
+      "mean_token_accuracy": 0.8298770362138748,
+      "num_tokens": 883494.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.6322308082878589,
+      "epoch": 0.9096816114359974,
+      "grad_norm": 0.35582953691482544,
+      "learning_rate": 0.0004004466337743108,
+      "loss": 0.5987993621826172,
+      "mean_token_accuracy": 0.8332566061615944,
+      "num_tokens": 1032111.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.6668267184152052,
+      "eval_loss": 0.6812539100646973,
+      "eval_mean_token_accuracy": 0.8146296894321075,
+      "eval_num_tokens": 1132140.0,
+      "eval_runtime": 53.08,
+      "eval_samples_per_second": 31.217,
+      "eval_steps_per_second": 3.919,
+      "step": 385
+    },
+    {
+      "entropy": 0.6360254319169414,
+      "epoch": 1.0389863547758285,
+      "grad_norm": 0.537056028842926,
+      "learning_rate": 0.0004417356562802791,
+      "loss": 0.5937010192871094,
+      "mean_token_accuracy": 0.8332705884123567,
+      "num_tokens": 1177556.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.5945304277539253,
+      "epoch": 1.1689408706952567,
+      "grad_norm": 0.4016346335411072,
+      "learning_rate": 0.00044138169957914594,
+      "loss": 0.564481430053711,
+      "mean_token_accuracy": 0.8422813892364502,
+      "num_tokens": 1325434.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.5895386649668217,
+      "epoch": 1.2988953866146848,
+      "grad_norm": 0.32074230909347534,
+      "learning_rate": 0.00044057466037611984,
+      "loss": 0.5511369705200195,
+      "mean_token_accuracy": 0.8431353771686554,
+      "num_tokens": 1474116.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.5951217761635781,
+      "epoch": 1.428849902534113,
+      "grad_norm": 0.3066493272781372,
+      "learning_rate": 0.00043931619693465644,
+      "loss": 0.5558741760253906,
+      "mean_token_accuracy": 0.84255860298872,
+      "num_tokens": 1621193.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.5773422825336456,
+      "epoch": 1.5588044184535412,
+      "grad_norm": 0.38174429535865784,
+      "learning_rate": 0.00043760889508197114,
+      "loss": 0.5448895263671875,
+      "mean_token_accuracy": 0.8427786123752594,
+      "num_tokens": 1767789.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.568668949753046,
+      "epoch": 1.6887589343729694,
+      "grad_norm": 0.4095861613750458,
+      "learning_rate": 0.0004354562628958121,
+      "loss": 0.5313994598388672,
+      "mean_token_accuracy": 0.847584228515625,
+      "num_tokens": 1918138.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.5952580836415291,
+      "epoch": 1.8187134502923976,
+      "grad_norm": 0.34596189856529236,
+      "learning_rate": 0.0004328627234962387,
+      "loss": 0.5546007919311523,
+      "mean_token_accuracy": 0.8419265493750572,
+      "num_tokens": 2057575.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.5800049532949925,
+      "epoch": 1.9486679662118258,
+      "grad_norm": 0.3752591609954834,
+      "learning_rate": 0.0004298336059572178,
+      "loss": 0.5452734756469727,
+      "mean_token_accuracy": 0.8436958035826683,
+      "num_tokens": 2208320.0,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.6070062083980212,
+      "eval_loss": 0.631233274936676,
+      "eval_mean_token_accuracy": 0.8255004269572405,
+      "eval_num_tokens": 2264280.0,
+      "eval_runtime": 53.1092,
+      "eval_samples_per_second": 31.2,
+      "eval_steps_per_second": 3.916,
+      "step": 770
+    },
+    {
+      "entropy": 0.5432504566770103,
+      "epoch": 2.077972709551657,
+      "grad_norm": 0.4615200459957123,
+      "learning_rate": 0.0004263751343567108,
+      "loss": 0.5117238616943359,
+      "mean_token_accuracy": 0.8515748070113024,
+      "num_tokens": 2348248.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.5108437672257423,
+      "epoch": 2.207927225471085,
+      "grad_norm": 0.39224034547805786,
+      "learning_rate": 0.0004224944149877526,
+      "loss": 0.47819324493408205,
+      "mean_token_accuracy": 0.8583902576565743,
+      "num_tokens": 2501427.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.5110109977424144,
+      "epoch": 2.3378817413905133,
+      "grad_norm": 0.36829307675361633,
+      "learning_rate": 0.00041819942175679877,
+      "loss": 0.4832262420654297,
+      "mean_token_accuracy": 0.8568637049198151,
+      "num_tokens": 2650794.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.5188203908503055,
+      "epoch": 2.4678362573099415,
+      "grad_norm": 0.47326067090034485,
+      "learning_rate": 0.00041349897979934495,
+      "loss": 0.48348499298095704,
+      "mean_token_accuracy": 0.8567950987815857,
+      "num_tokens": 2798180.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.5181271532177925,
+      "epoch": 2.5977907732293697,
+      "grad_norm": 0.2972731292247772,
+      "learning_rate": 0.0004084027473464832,
+      "loss": 0.4918654251098633,
+      "mean_token_accuracy": 0.8539192593097686,
+      "num_tokens": 2950301.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.5172442196309567,
+      "epoch": 2.727745289148798,
+      "grad_norm": 0.4516422152519226,
+      "learning_rate": 0.0004029211958796559,
+      "loss": 0.4767612457275391,
+      "mean_token_accuracy": 0.8575084239244462,
+      "num_tokens": 3091810.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.5078031922131777,
+      "epoch": 2.857699805068226,
+      "grad_norm": 0.28876274824142456,
+      "learning_rate": 0.00039706558861438384,
+      "loss": 0.47852867126464843,
+      "mean_token_accuracy": 0.8580548599362373,
+      "num_tokens": 3242184.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.5267327691614628,
+      "epoch": 2.9876543209876543,
+      "grad_norm": 0.29029977321624756,
+      "learning_rate": 0.000390847957357179,
+      "loss": 0.48259868621826174,
+      "mean_token_accuracy": 0.8568289718031883,
+      "num_tokens": 3382605.0,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.5411632635559027,
+      "eval_loss": 0.5956819653511047,
+      "eval_mean_token_accuracy": 0.8327134661376476,
+      "eval_num_tokens": 3396420.0,
+      "eval_runtime": 53.1279,
+      "eval_samples_per_second": 31.189,
+      "eval_steps_per_second": 3.915,
+      "step": 1155
+    },
+    {
+      "entropy": 0.44545789564674226,
+      "epoch": 3.116959064327485,
+      "grad_norm": 0.3036324381828308,
+      "learning_rate": 0.00038428107778319486,
+      "loss": 0.4016357421875,
+      "mean_token_accuracy": 0.8744772864346528,
+      "num_tokens": 3522582.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.4417941153049469,
+      "epoch": 3.246913580246914,
+      "grad_norm": 0.3334718942642212,
+      "learning_rate": 0.0003773784431854142,
+      "loss": 0.3976226806640625,
+      "mean_token_accuracy": 0.8750237095355987,
+      "num_tokens": 3670864.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.4398873296380043,
+      "epoch": 3.3768680961663415,
+      "grad_norm": 0.2897355258464813,
+      "learning_rate": 0.0003701542367493103,
+      "loss": 0.40165950775146486,
+      "mean_token_accuracy": 0.874879752099514,
+      "num_tokens": 3822021.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.4448629415035248,
+      "epoch": 3.50682261208577,
+      "grad_norm": 0.2915370464324951,
+      "learning_rate": 0.00036262330240995327,
+      "loss": 0.40887042999267575,
+      "mean_token_accuracy": 0.8728678345680236,
+      "num_tokens": 3968736.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.46088827416300776,
+      "epoch": 3.636777128005198,
+      "grad_norm": 0.3924349546432495,
+      "learning_rate": 0.0003548011143514403,
+      "loss": 0.4195223617553711,
+      "mean_token_accuracy": 0.8715560722351074,
+      "num_tokens": 4113509.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.4382705672085285,
+      "epoch": 3.7667316439246266,
+      "grad_norm": 0.27308768033981323,
+      "learning_rate": 0.0003467037452113232,
+      "loss": 0.39946125030517576,
+      "mean_token_accuracy": 0.8747073370218277,
+      "num_tokens": 4267958.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.45163255512714384,
+      "epoch": 3.8966861598440543,
+      "grad_norm": 0.34591901302337646,
+      "learning_rate": 0.00033834783305536283,
+      "loss": 0.4112929534912109,
+      "mean_token_accuracy": 0.8722118473052979,
+      "num_tokens": 4415398.0,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.49164803326129913,
+      "eval_loss": 0.602810800075531,
+      "eval_mean_token_accuracy": 0.8353393092178382,
+      "eval_num_tokens": 4528560.0,
+      "eval_runtime": 53.117,
+      "eval_samples_per_second": 31.195,
+      "eval_steps_per_second": 3.916,
+      "step": 1540
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.079894291063982e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/checkpoint-1925/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/checkpoint-1925/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.04123083959940288,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/checkpoint-1925/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

DBCA_code_Estonian/Qwen3-4B-Base_code_features_structural_train_code_features_structural_test2/checkpoint-1925/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}