add evaluations

evals/hellaswag/hellaswag_nl_gpt2-large-dutch.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "hellaswag_nl": {
+      "acc": 0.2506206152185645,
+      "acc_stderr": 0.004502565024646468,
+      "acc_norm": 0.24533189422558013,
+      "acc_norm_stderr": 0.004470496207931054
+    }
+  },
+  "versions": {
+    "hellaswag_nl": 1
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=yhavinga/gpt2-large-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_gpt2-medium-dutch.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "hellaswag_nl": {
+      "acc": 0.25526173772261196,
+      "acc_stderr": 0.004529970992768382,
+      "acc_norm": 0.250728548300054,
+      "acc_norm_stderr": 0.004503210131241702
+    }
+  },
+  "versions": {
+    "hellaswag_nl": 1
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=yhavinga/gpt2-medium-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": {}
+  }
+}