Clearing cached results

eval-results-bk/demo-leaderboard/gpt2-demo/results_2023-11-21T18-10-08.json

@@ -0,0 +1,19 @@
+{
+    "config": {
+        "model_dtype": "torch.float16", 
+        "model_name": "demo-leaderboard/gpt2-demo",
+        "model_sha": "ac3299b02780836378b9e1e68c6eead546e89f90"
+    },
+    "results": {
+    "realtoxicityprompts": {
+            "perspective_api_toxicity_score": 0
+        },
+        "toxigen": { "acc_norm": 0},
+        "anli_r1": {
+            "acc": 0
+        },
+        "logiqa": {
+            "acc_norm": 0.90
+        }
+    }
+}

eval-results-bk/demo-leaderboard/gpt2-demo/results_2023-11-22 15:46:20.425378.json

@@ -0,0 +1,37 @@
+{
+  "results": {
+    "realtoxicityprompts": {
+            "perspective_api_toxicity_score": 0
+        },
+    "toxigen": { "acc_norm": 0},
+    "anli_r1": {
+      "acc": 0.4,
+      "acc_stderr": 0.11239029738980327
+    },
+    "logiqa": {
+      "acc": 0.35,
+      "acc_stderr": 0.10942433098048308,
+      "acc_norm": 0.3,
+      "acc_norm_stderr": 0.10513149660756933
+    }
+  },
+  "versions": {
+    "anli_r1": 0,
+    "logiqa": 0
+  },
+  "config": {
+    "model": "hf-causal-experimental",
+    "model_args": "pretrained=demo-leaderboard/gpt2-demo,revision=main,dtype=bfloat16",
+    "num_fewshot": 0,
+    "batch_size": 1,
+    "batch_sizes": [],
+    "device": "cpu",
+    "no_cache": true,
+    "limit": 20,
+    "bootstrap_iters": 100000,
+    "description_dict": null,
+    "model_dtype": "bfloat16",
+    "model_name": "demo-leaderboard/gpt2-demo",
+    "model_sha": "main"
+  }
+}