add evaluations

evals/arc/arc_nl_gpt-neo-1.3B-dutch.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "arc_nl": {
+      "acc": 0.22583404619332764,
+      "acc_stderr": 0.012234615366330673,
+      "acc_norm": 0.2557741659538067,
+      "acc_norm_stderr": 0.012766130743681095
+    }
+  },
+  "versions": {
+    "arc_nl": 0
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=yhavinga/gpt-neo-1.3B-dutch,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
+    "batch_size": "auto",
+    "device": "cuda",
+    "no_cache": false,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

evals/arc/arc_nl_gpt-neo-125M-dutch.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "arc_nl": {
+      "acc": 0.20786997433704021,
+      "acc_stderr": 0.011873334349879954,
+      "acc_norm": 0.2386655260906758,
+      "acc_norm_stderr": 0.012472719983622024
+    }
+  },
+  "versions": {
+    "arc_nl": 0
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=yhavinga/gpt-neo-125M-dutch,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
+    "batch_size": "auto",
+    "device": "cuda",
+    "no_cache": false,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

evals/hellaswag/hellaswag_nl_gpt-neo-1.3B-dutch.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "hellaswag_nl": {
+      "acc": 0.250512682137075,
+      "acc_stderr": 0.004501919546283265,
+      "acc_norm": 0.245979492714517,
+      "acc_norm_stderr": 0.0044744716050104955
+    }
+  },
+  "versions": {
+    "hellaswag_nl": 1
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=yhavinga/gpt-neo-1.3B-dutch,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
+    "batch_size": "auto",
+    "device": "cuda",
+    "no_cache": false,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

evals/hellaswag/hellaswag_nl_gpt-neo-125M-dutch.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "hellaswag_nl": {
+      "acc": 0.2523475445223961,
+      "acc_stderr": 0.0045128422261964275,
+      "acc_norm": 0.24284943335132217,
+      "acc_norm_stderr": 0.004455130191708228
+    }
+  },
+  "versions": {
+    "hellaswag_nl": 1
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=yhavinga/gpt-neo-125M-dutch,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
+    "batch_size": "auto",
+    "device": "cuda",
+    "no_cache": false,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

evals/mmlu/mmlu_nl_gpt-neo-1.3B-dutch.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "mmlu_nl": {
+      "acc": 0.22622751764438037,
+      "acc_stderr": 0.003644916321363529,
+      "acc_norm": 0.25028458677999543,
+      "acc_norm_stderr": 0.0037737530701406354
+    }
+  },
+  "versions": {
+    "mmlu_nl": 0
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=yhavinga/gpt-neo-1.3B-dutch,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
+    "batch_size": "auto",
+    "device": "cuda",
+    "no_cache": false,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

evals/mmlu/mmlu_nl_gpt-neo-125M-dutch.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "mmlu_nl": {
+      "acc": 0.23222281247628443,
+      "acc_stderr": 0.0036785634314757355,
+      "acc_norm": 0.24694543522804888,
+      "acc_norm_stderr": 0.0037568333535560896
+    }
+  },
+  "versions": {
+    "mmlu_nl": 0
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=yhavinga/gpt-neo-125M-dutch,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
+    "batch_size": "auto",
+    "device": "cuda",
+    "no_cache": false,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

evals/truthfulqa/truthfulqa_nl_gpt-neo-1.3B-dutch.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "truthfulqa_nl": {
+      "mc1": 0.26496815286624203,
+      "mc1_stderr": 0.015761294574831355,
+      "mc2": 0.42842315532854475,
+      "mc2_stderr": 0.015376698164939607
+    }
+  },
+  "versions": {
+    "truthfulqa_nl": 1
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=yhavinga/gpt-neo-1.3B-dutch,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
+    "batch_size": "auto",
+    "device": "cuda",
+    "no_cache": false,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

evals/truthfulqa/truthfulqa_nl_gpt-neo-125M-dutch.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "truthfulqa_nl": {
+      "mc1": 0.25605095541401274,
+      "mc1_stderr": 0.015587510684642944,
+      "mc2": 0.4305171468716022,
+      "mc2_stderr": 0.015454035132644787
+    }
+  },
+  "versions": {
+    "truthfulqa_nl": 1
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=yhavinga/gpt-neo-125M-dutch,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
+    "batch_size": "auto",
+    "device": "cuda",
+    "no_cache": false,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}