Upload eval_results/HuggingFaceTB/SmolLM2-1.7B-Instruct/main/gsm8k/results_2025-02-12T15-02-58.450524.json with huggingface_hub

eval_results/HuggingFaceTB/SmolLM2-1.7B-Instruct/main/gsm8k/results_2025-02-12T15-02-58.450524.json

@@ -0,0 +1,113 @@
+{
+  "config_general": {
+    "lighteval_sha": "?",
+    "num_fewshot_seeds": 1,
+    "override_batch_size": -1,
+    "max_samples": null,
+    "job_id": 0,
+    "start_time": 343146.31067292,
+    "end_time": 343349.693702219,
+    "total_evaluation_time_secondes": "203.38302929897327",
+    "model_name": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
+    "model_sha": "",
+    "model_dtype": null,
+    "model_size": null
+  },
+  "results": {
+    "lighteval|gsm8k|0": {
+      "maj@8": 0.000758150113722517,
+      "maj@8_stderr": 0.0007581501137225375,
+      "qem": 0.000758150113722517,
+      "qem_stderr": 0.0007581501137225247
+    },
+    "all": {
+      "maj@8": 0.000758150113722517,
+      "maj@8_stderr": 0.0007581501137225375,
+      "qem": 0.000758150113722517,
+      "qem_stderr": 0.0007581501137225247
+    }
+  },
+  "versions": {
+    "lighteval|gsm8k|0": 0
+  },
+  "config_tasks": {
+    "lighteval|gsm8k": {
+      "name": "gsm8k",
+      "prompt_function": "gsm8k",
+      "hf_repo": "gsm8k",
+      "hf_subset": "main",
+      "metric": [
+        {
+          "metric_name": "qem",
+          "higher_is_better": true,
+          "category": "3",
+          "use_case": "5",
+          "sample_level_fn": "compute",
+          "corpus_level_fn": "mean"
+        },
+        {
+          "metric_name": "maj@8",
+          "higher_is_better": true,
+          "category": "5",
+          "use_case": "5",
+          "sample_level_fn": "compute",
+          "corpus_level_fn": "mean"
+        }
+      ],
+      "hf_revision": null,
+      "hf_filter": null,
+      "hf_avail_splits": [
+        "train",
+        "test"
+      ],
+      "trust_dataset": true,
+      "evaluation_splits": [
+        "test"
+      ],
+      "few_shots_split": null,
+      "few_shots_select": "random_sampling_from_train",
+      "generation_size": 256,
+      "generation_grammar": null,
+      "stop_sequence": [
+        "Question="
+      ],
+      "num_samples": null,
+      "suite": [
+        "lighteval"
+      ],
+      "original_num_docs": 1319,
+      "effective_num_docs": 1319,
+      "must_remove_duplicate_docs": false,
+      "version": 0
+    }
+  },
+  "summary_tasks": {
+    "lighteval|gsm8k|0": {
+      "hashes": {
+        "hash_examples": "7957ba36acab8574",
+        "hash_full_prompts": "10c92cb4d0869dd2",
+        "hash_input_tokens": "bb685ca93dc87ad9",
+        "hash_cont_tokens": "dd1c8df7717b0659"
+      },
+      "truncated": 0,
+      "non_truncated": 2638,
+      "padded": 0,
+      "non_padded": 2638,
+      "effective_few_shots": 0.0,
+      "num_truncated_few_shots": 0
+    }
+  },
+  "summary_general": {
+    "hashes": {
+      "hash_examples": "e99e29b2d4ab55c1",
+      "hash_full_prompts": "087dc6ae8b324c9a",
+      "hash_input_tokens": "0f08978b7c932878",
+      "hash_cont_tokens": "968d36161d6c64cd"
+    },
+    "truncated": 0,
+    "non_truncated": 2638,
+    "padded": 0,
+    "non_padded": 2638,
+    "num_truncated_few_shots": 0
+  }
+}