update nlg results

results/zero-shot/CerebrumTech__cere-llama-3-8b-tr.json

@@ -13,36 +13,42 @@
         {
             "name": "xlsum_tr",
             "task": "summarization",
-            "rouge1": 0.0148042679964553,
-            "rouge2": 0.006337012269480576,
-            "rougeL": 0.011798434065329946
+            "rouge1": 0.2583902819569687,
+            "rouge2": 0.10868375368178293,
+            "rougeL": 0.1952205382650655
         },
         {
             "name": "wmt-tr-en-prompt",
             "task": "machine_translation",
-            "wer": 0.9177312951556903,
-            "bleu": 0.0010336244771491927
+            "wer": 0.7999790984392787,
+            "bleu": 0.11905815617598979
+        },
+        {
+            "name": "wmt-en-tr-prompt",
+            "task": "machine_translation",
+            "wer": 0.933992772871535,
+            "bleu": 0.044204591279262746
         },
         {
             "name": "wiki_lingua_tr",
             "task": "summarization",
-            "rouge1": 0.07039446024412022,
-            "rouge2": 0.02125810875804613,
-            "rougeL": 0.05181069185122056
+            "rouge1": 0.20581622347355663,
+            "rouge2": 0.0641413363983985,
+            "rougeL": 0.14917636822465685
         },
         {
             "name": "tr-wikihow-summ",
             "task": "summarization",
-            "rouge1": 0.17657152314685107,
-            "rouge2": 0.05191014365298107,
-            "rougeL": 0.1243539526593285
+            "rouge1": 0.2246335258862419,
+            "rouge2": 0.06557441812173484,
+            "rougeL": 0.1559504924053904
         },
         {
             "name": "mlsum_tr",
             "task": "summarization",
-            "rouge1": 0.09056852256508315,
-            "rouge2": 0.05971047138214301,
-            "rougeL": 0.07758457056947823
+            "rouge1": 0.38085271760138706,
+            "rouge2": 0.24779093184456852,
+            "rougeL": 0.31787475025364564
         },
         {
             "name": "gecturk_generation",
@@ -192,12 +198,6 @@
             "task": "multiple_choice",
             "acc": 0.5857142857142857,
             "acc_norm": 0.5857142857142857
-        },
-        {
-            "name": "wmt-en-tr-prompt",
-            "task": "machine_translation",
-            "wer": 0.9521851657325472,
-            "bleu": 0.03042164195826046
         }
     ]
 }

results/zero-shot/aya101.json

@@ -18,9 +18,9 @@
         {
             "name": "xlsum_tr",
             "task": "summarization",
-            "rouge1": 0.02416422194769531,
-            "rouge2": 0.00149839274458772,
-            "rougeL": 0.02416422194769531
+            "rouge1": 0.40329166826890306,
+            "rouge2": 0.24618000685069955,
+            "rougeL": 0.3540445580839572
         },
         {
             "name": "xcopa_tr",
@@ -31,15 +31,15 @@
         {
             "name": "wmt-tr-en-prompt",
             "task": "machine_translation",
-            "wer": 0.9853633715998092,
-            "bleu": 0.0
+            "wer": 0.7665278686420781,
+            "bleu": 0.17158412519070387
         },
         {
             "name": "wiki_lingua_tr",
             "task": "summarization",
-            "rouge1": 0.029006633700390562,
-            "rouge2": 0.0004998910319276452,
-            "rougeL": 0.028967197984657227
+            "rouge1": 0.39998774165132267,
+            "rouge2": 0.2218282180595083,
+            "rougeL": 0.35347919895816715
         },
         {
             "name": "turkish_plu",
@@ -86,9 +86,9 @@
         {
             "name": "tr-wikihow-summ",
             "task": "summarization",
-            "rouge1": 0.02053796966151103,
-            "rouge2": 0.00029270301029826366,
-            "rougeL": 0.020495031370814234
+            "rouge1": 0.3465851896339094,
+            "rouge2": 0.16864200623272294,
+            "rougeL": 0.2930576004057389
         },
         {
             "name": "tquad",
@@ -135,9 +135,9 @@
         {
             "name": "mlsum_tr",
             "task": "summarization",
-            "rouge1": 0.021746360547255133,
-            "rouge2": 0.003113110667892852,
-            "rougeL": 0.021727065059735186
+            "rouge1": 0.45270949786483405,
+            "rouge2": 0.3184853277364837,
+            "rougeL": 0.39689938533216157
         },
         {
             "name": "mkqa_tr",
@@ -195,7 +195,7 @@
         {
             "name": "wmt-en-tr-prompt",
             "task": "machine_translation",
-            "wer": 0.7025061825593694,
+            "wer": 0.7025061825593685,
             "bleu": 0.21521710925537071
         }
     ]

results/zero-shot/llama-3.2-1b.json

@@ -44,13 +44,6 @@
             "exact_match": 0.007694584196507843,
             "f1": 0.03304091036050505
         },
-        {
-            "name": "mlsum_tr",
-            "task": "summarization",
-            "rouge1": 0.23283491254211872,
-            "rouge2": 0.13426790568610214,
-            "rougeL": 0.18915548037371513
-        },
         {
             "name": "news_cat",
             "task": "text_classification",
@@ -81,43 +74,18 @@
             "exact_match": 0.06278026905829596,
             "f1": 0.21486130318406463
         },
-        {
-            "name": "wiki_lingua_tr",
-            "task": "summarization",
-            "rouge1": 0.10861529436199803,
-            "rouge2": 0.034862923521078545,
-            "rougeL": 0.08692160533533941
-        },
-        {
-            "name": "wmt-tr-en-prompt",
-            "task": "machine_translation",
-            "wer": 3.910683208136067,
-            "bleu": 0.012043288243775466
-        },
         {
             "name": "xcopa_tr",
             "task": "multiple_choice",
             "acc": 0.556,
             "acc_norm": 0.556
         },
-        {
-            "name": "xlsum_tr",
-            "task": "summarization",
-            "rouge1": 0.16924699150407269,
-            "rouge2": 0.07190935921365724,
-            "rougeL": 0.13255123335488528
-        },
         {
             "name": "xquad_tr",
             "task": "extractive_question_answering",
             "exact_match": 0.04873949579831932,
             "f1": 0.11156636293859905
         },
-        {
-            "name": "gecturk_generation",
-            "task": "grammatical_error_correction",
-            "exact_match": 0.0073185998362944775
-        },
         {
             "name": "mlsum_tr",
             "task": "summarization",

results/zero-shot/llama-3.2-3b-instruct.json

@@ -44,13 +44,6 @@
             "exact_match": 0.04675939627108612,
             "f1": 0.08114473798410345
         },
-        {
-            "name": "mlsum_tr",
-            "task": "summarization",
-            "rouge1": 0.2669056212126977,
-            "rouge2": 0.1480446780314802,
-            "rougeL": 0.2106440565987865
-        },
         {
             "name": "news_cat",
             "task": "text_classification",
@@ -81,43 +74,18 @@
             "exact_match": 0.18721973094170405,
             "f1": 0.5109898180473623
         },
-        {
-            "name": "wiki_lingua_tr",
-            "task": "summarization",
-            "rouge1": 0.1342879173103036,
-            "rouge2": 0.041489300068460175,
-            "rougeL": 0.10482785510181569
-        },
-        {
-            "name": "wmt-tr-en-prompt",
-            "task": "machine_translation",
-            "wer": 1.7706536060519733,
-            "bleu": 0.048843165627950165
-        },
         {
             "name": "xcopa_tr",
             "task": "multiple_choice",
             "acc": 0.546,
             "acc_norm": 0.546
         },
-        {
-            "name": "xlsum_tr",
-            "task": "summarization",
-            "rouge1": 0.17224405229987672,
-            "rouge2": 0.06736413357191079,
-            "rougeL": 0.12750762702828333
-        },
         {
             "name": "xquad_tr",
             "task": "extractive_question_answering",
             "exact_match": 0.23025210084033615,
             "f1": 0.4335914561273987
         },
-        {
-            "name": "gecturk_generation",
-            "task": "grammatical_error_correction",
-            "exact_match": 0.009726033992970293
-        },
         {
             "name": "mlsum_tr",
             "task": "summarization",