add evaluations

evals/hellaswag/hellaswag_nl_Llama-2-13b-chat-hf.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "hellaswag_nl": {
+      "acc": 0.4266594711279007,
+      "acc_stderr": 0.005138634679279774,
+      "acc_norm": 0.5464651915812196,
+      "acc_norm_stderr": 0.005172342688078235
+    }
+  },
+  "versions": {
+    "hellaswag_nl": 1
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=meta-llama/Llama-2-13b-chat-hf,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
+    "batch_size": 2,
+    "device": "cuda",
+    "no_cache": false,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

evals/hellaswag/hellaswag_nl_Llama-2-13b-hf.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "hellaswag_nl": {
+      "acc": 0.4386400431732326,
+      "acc_stderr": 0.005155556844320744,
+      "acc_norm": 0.572369131138694,
+      "acc_norm_stderr": 0.005140121115694681
+    }
+  },
+  "versions": {
+    "hellaswag_nl": 1
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=meta-llama/Llama-2-13b-hf,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
+    "batch_size": 2,
+    "device": "cuda",
+    "no_cache": false,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}