add evaluations

evals/hellaswag/hellaswag_nl_Orca-2-7b.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "hellaswag_nl": {
+      "acc": 0.39071775499190503,
+      "acc_stderr": 0.00506922492446768,
+      "acc_norm": 0.4887209929843497,
+      "acc_norm_stderr": 0.005193500820957502
+    }
+  },
+  "versions": {
+    "hellaswag_nl": 1
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=microsoft/Orca-2-7b,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_neural-chat-7b-v3-1.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "hellaswag_nl": {
+      "acc": 0.45169994603345925,
+      "acc_stderr": 0.005170527954184388,
+      "acc_norm": 0.575067458175931,
+      "acc_norm_stderr": 0.005135942094754352
+    }
+  },
+  "versions": {
+    "hellaswag_nl": 1
+  },
+  "config": {
+    "model": "hf-auto",
+    "model_args": "pretrained=Intel/neural-chat-7b-v3-1,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": {}
+  }
+}