Upload folder using huggingface_hub

evals/ifeval/results_2025-01-19T18-50-56.248079.json

@@ -0,0 +1,138 @@
+{
+  "results": {
+    "ifeval": {
+      "alias": "ifeval",
+      "prompt_level_strict_acc,none": 0.11645101663585952,
+      "prompt_level_strict_acc_stderr,none": 0.013803527284071323,
+      "inst_level_strict_acc,none": 0.25059952038369304,
+      "inst_level_strict_acc_stderr,none": "N/A",
+      "prompt_level_loose_acc,none": 0.13123844731977818,
+      "prompt_level_loose_acc_stderr,none": 0.014530613740502811,
+      "inst_level_loose_acc,none": 0.26139088729016785,
+      "inst_level_loose_acc_stderr,none": "N/A"
+    }
+  },
+  "group_subtasks": {
+    "ifeval": []
+  },
+  "configs": {
+    "ifeval": {
+      "task": "ifeval",
+      "dataset_path": "google/IFEval",
+      "test_split": "train",
+      "doc_to_text": "prompt",
+      "doc_to_target": 0,
+      "process_results": "def process_results(doc, results):\n    inp = InputExample(\n        key=doc[\"key\"],\n        instruction_id_list=doc[\"instruction_id_list\"],\n        prompt=doc[\"prompt\"],\n        kwargs=doc[\"kwargs\"],\n    )\n    response = results[0]\n\n    out_strict = test_instruction_following_strict(inp, response)\n    out_loose = test_instruction_following_loose(inp, response)\n\n    return {\n        \"prompt_level_strict_acc\": out_strict.follow_all_instructions,\n        \"inst_level_strict_acc\": out_strict.follow_instruction_list,\n        \"prompt_level_loose_acc\": out_loose.follow_all_instructions,\n        \"inst_level_loose_acc\": out_loose.follow_instruction_list,\n    }\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "prompt_level_strict_acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "inst_level_strict_acc",
+          "aggregation": "def agg_inst_level_acc(items):\n    flat_items = [item for sublist in items for item in sublist]\n    inst_level_acc = sum(flat_items) / len(flat_items)\n    return inst_level_acc\n",
+          "higher_is_better": true
+        },
+        {
+          "metric": "prompt_level_loose_acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "inst_level_loose_acc",
+          "aggregation": "def agg_inst_level_acc(items):\n    flat_items = [item for sublist in items for item in sublist]\n    inst_level_acc = sum(flat_items) / len(flat_items)\n    return inst_level_acc\n",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [],
+        "do_sample": false,
+        "temperature": 0.0,
+        "max_gen_toks": 1280
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 4.0
+      }
+    }
+  },
+  "versions": {
+    "ifeval": 4.0
+  },
+  "n-shot": {
+    "ifeval": 0
+  },
+  "higher_is_better": {
+    "ifeval": {
+      "prompt_level_strict_acc": true,
+      "inst_level_strict_acc": true,
+      "prompt_level_loose_acc": true,
+      "inst_level_loose_acc": true
+    }
+  },
+  "n-samples": {
+    "ifeval": {
+      "original": 541,
+      "effective": 541
+    }
+  },
+  "config": {
+    "model": "hf",
+    "model_args": "pretrained=/scratch/ssd004/scratch/nkandpa2/experiments/Llama_3.2_1B__alpaca_finetune/final-model",
+    "model_num_parameters": 1235818496,
+    "model_dtype": "torch.bfloat16",
+    "model_revision": "main",
+    "model_sha": "",
+    "batch_size": "8",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null,
+    "random_seed": 0,
+    "numpy_seed": 1234,
+    "torch_seed": 1234,
+    "fewshot_seed": 1234
+  },
+  "git_hash": null,
+  "date": 1737328517.023156,
+  "pretty_env_info": "'NoneType' object has no attribute 'splitlines'",
+  "transformers_version": "4.46.3",
+  "upper_git_hash": null,
+  "tokenizer_pad_token": [
+    "<|end_of_text|>",
+    "128001"
+  ],
+  "tokenizer_eos_token": [
+    "<|end_of_text|>",
+    "128001"
+  ],
+  "tokenizer_bos_token": [
+    "<|begin_of_text|>",
+    "128000"
+  ],
+  "eot_token_id": 128001,
+  "max_length": 131072,
+  "task_hashes": {
+    "ifeval": "a9cc24d7d92904c9f59225bb28b88b892d9ab82be222808ea7fa345ffd4500ae"
+  },
+  "model_source": "hf",
+  "model_name": "/scratch/ssd004/scratch/nkandpa2/experiments/Llama_3.2_1B__alpaca_finetune/final-model",
+  "model_name_sanitized": "__scratch__ssd004__scratch__nkandpa2__experiments__Llama_3.2_1B__alpaca_finetune__final-model",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "fewshot_as_multiturn": false,
+  "chat_template": null,
+  "chat_template_sha": null,
+  "start_time": 894679.611532814,
+  "end_time": 896839.537282385,
+  "total_evaluation_time_seconds": "2159.9257495710626"
+}