Upload eval_results/deepseek-ai/deepseek-coder-6.7b-instruct/main/ifeval/results_2024-03-04T12-43-54.459792.json with huggingface_hub

eval_results/deepseek-ai/deepseek-coder-6.7b-instruct/main/ifeval/results_2024-03-04T12-43-54.459792.json

@@ -0,0 +1,89 @@
+{
+  "config_general": {
+    "lighteval_sha": "?",
+    "num_fewshot_seeds": 1,
+    "override_batch_size": 4,
+    "max_samples": null,
+    "job_id": "",
+    "start_time": 890665.801959612,
+    "end_time": 891049.868549886,
+    "total_evaluation_time_secondes": "384.06659027398564",
+    "model_name": "deepseek-ai/deepseek-coder-6.7b-instruct",
+    "model_sha": "e5d64addd26a6a1db0f9b863abf6ee3141936807",
+    "model_dtype": "torch.bfloat16",
+    "model_size": "12.84 GB",
+    "config": null
+  },
+  "results": {
+    "custom|ifeval|0": {
+      "prompt_level_strict_acc": 0.14048059149722736,
+      "prompt_level_strict_acc_stderr": 0.01495337165682276,
+      "inst_level_strict_acc": 0.20503597122302158,
+      "inst_level_strict_acc_stderr": 0.00042702578149430285,
+      "prompt_level_loose_acc": 0.1423290203327172,
+      "prompt_level_loose_acc_stderr": 0.015035234562202793,
+      "inst_level_loose_acc": 0.20623501199040767,
+      "inst_level_loose_acc_stderr": 0.0004296583918251027
+    }
+  },
+  "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
+    }
+  },
+  "summary_tasks": {
+    "custom|ifeval|0": {
+      "hashes": {
+        "hash_examples": "e99cbf567588d7c6",
+        "hash_full_prompts": "348c49204921ac4d",
+        "hash_input_tokens": "2c9c8aa1e47040f4",
+        "hash_cont_tokens": "ca290c168c182beb"
+      },
+      "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": "b7829477f65524c7",
+      "hash_input_tokens": "447fac93b45af88b",
+      "hash_cont_tokens": "3d96aa801b969a8b"
+    },
+    "truncated": 0,
+    "non_truncated": 541,
+    "padded": 0,
+    "non_padded": 541,
+    "num_truncated_few_shots": 0
+  }
+}