Upload eval_results/HuggingFaceH4/starchat-beta/main/ifeval/results_2024-03-12T16-23-57.905356.json with huggingface_hub

eval_results/HuggingFaceH4/starchat-beta/main/ifeval/results_2024-03-12T16-23-57.905356.json

@@ -0,0 +1,90 @@
+{
+  "config_general": {
+    "lighteval_sha": "?",
+    "num_fewshot_seeds": 1,
+    "override_batch_size": 4,
+    "max_samples": null,
+    "job_id": "",
+    "start_time": 7262383.022051326,
+    "end_time": 7263080.52226492,
+    "total_evaluation_time_secondes": "697.5002135941759",
+    "model_name": "HuggingFaceH4/starchat-beta",
+    "model_sha": "b1bcda690655777373f57ea6614eb095ec2c886f",
+    "model_dtype": "torch.bfloat16",
+    "model_size": "28.91 GB",
+    "config": null
+  },
+  "results": {
+    "custom|ifeval|0": {
+      "prompt_level_strict_acc": 0.07948243992606285,
+      "prompt_level_strict_acc_stderr": 0.011640047542656424,
+      "inst_level_strict_acc": 0.16786570743405277,
+      "inst_level_strict_acc_stderr": 0.0003899948844238547,
+      "prompt_level_loose_acc": 0.08133086876155268,
+      "prompt_level_loose_acc_stderr": 0.011762791189613622,
+      "inst_level_loose_acc": 0.16906474820143885,
+      "inst_level_loose_acc_stderr": 0.0003933603551046757
+    }
+  },
+  "versions": {
+    "custom|ifeval|0": 0
+  },
+  "config_tasks": {
+    "custom|ifeval": {
+      "name": "ifeval",
+      "prompt_function": "ifeval_prompt",
+      "hf_repo": "wis-k/instruction-following-eval",
+      "hf_subset": "default",
+      "metric": [
+        "ifeval_metric"
+      ],
+      "hf_avail_splits": [
+        "train"
+      ],
+      "evaluation_splits": [
+        "train"
+      ],
+      "few_shots_split": "train",
+      "few_shots_select": "random_sampling",
+      "generation_size": 1280,
+      "stop_sequence": [],
+      "output_regex": null,
+      "frozen": false,
+      "suite": [
+        "custom"
+      ],
+      "original_num_docs": 541,
+      "effective_num_docs": 541,
+      "trust_dataset": null
+    }
+  },
+  "summary_tasks": {
+    "custom|ifeval|0": {
+      "hashes": {
+        "hash_examples": "e99cbf567588d7c6",
+        "hash_full_prompts": "a9ce44ad3034bed3",
+        "hash_input_tokens": "939580bdd7fbc0b7",
+        "hash_cont_tokens": "6b81cf6e20401fac"
+      },
+      "truncated": 0,
+      "non_truncated": 541,
+      "padded": 0,
+      "non_padded": 541,
+      "effective_few_shots": 0.0,
+      "num_truncated_few_shots": 0
+    }
+  },
+  "summary_general": {
+    "hashes": {
+      "hash_examples": "ea046ab2c6fc5928",
+      "hash_full_prompts": "1592c8fb4ad1c0dc",
+      "hash_input_tokens": "4bbb3427f6d0d85e",
+      "hash_cont_tokens": "e0a90629ad2f13e5"
+    },
+    "truncated": 0,
+    "non_truncated": 541,
+    "padded": 0,
+    "non_padded": 541,
+    "num_truncated_few_shots": 0
+  }
+}