Rarri's picture
Add model card, recipe, security review, and lm-eval benchmarks
2941b49 verified
Raw
History Blame Contribute Delete
7.45 kB
{
"results": {
"gsm8k": {
"name": "gsm8k",
"alias": "gsm8k",
"sample_len": 200,
"exact_match,strict-match": 0.69,
"exact_match_stderr,strict-match": 0.032785276754349606,
"exact_match,flexible-extract": 0.965,
"exact_match_stderr,flexible-extract": 0.013027801736688036
},
"ifeval": {
"name": "ifeval",
"alias": "ifeval",
"sample_len": 200,
"prompt_level_strict_acc,none": 0.735,
"prompt_level_strict_acc_stderr,none": 0.03128528159088722,
"inst_level_strict_acc,none": 0.8144654088050315,
"inst_level_strict_acc_stderr,none": "N/A",
"prompt_level_loose_acc,none": 0.765,
"prompt_level_loose_acc_stderr,none": 0.030056479497755487,
"inst_level_loose_acc,none": 0.839622641509434,
"inst_level_loose_acc_stderr,none": "N/A"
}
},
"group_subtasks": {},
"configs": {
"gsm8k": {
"task": "gsm8k",
"dataset_path": "openai/gsm8k",
"dataset_name": "main",
"training_split": "train",
"test_split": "test",
"fewshot_split": "train",
"doc_to_text": "Question: {{question}}\nAnswer:",
"doc_to_target": "{{answer}}",
"unsafe_code": false,
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "default",
"split": "train",
"process_docs": null,
"fewshot_indices": null,
"samples": null,
"doc_to_text": "Question: {{question}}\nAnswer:",
"doc_to_choice": null,
"doc_to_target": "{{answer}}",
"gen_prefix": null,
"fewshot_delimiter": "\n\n",
"target_delimiter": " "
},
"num_fewshot": 5,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true,
"ignore_case": true,
"ignore_punctuation": false,
"regexes_to_ignore": [
",",
"\\$",
"(?s).*#### ",
"\\.$"
]
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Question:",
"</s>",
"<|im_end|>"
],
"do_sample": false,
"temperature": 0.0
},
"repeats": 1,
"filter_list": [
{
"name": "strict-match",
"filter": [
{
"function": "regex",
"regex_pattern": "#### (\\-?[0-9\\.\\,]+)"
},
{
"function": "take_first"
}
]
},
{
"name": "flexible-extract",
"filter": [
{
"function": "regex",
"group_select": -1,
"regex_pattern": "(-?[$0-9.,]{2,})|(-?[0-9]+)"
},
{
"function": "take_first"
}
]
}
],
"should_decontaminate": false,
"metadata": {
"version": 3.0,
"model": "dsv4-hybrid",
"base_url": "http://localhost:PORT/v1/chat/completions",
"num_concurrent": 16,
"max_retries": 3,
"tokenized_requests": false,
"tokenizer": "<model_path>",
"tokenizer_backend": "huggingface",
"config_source": "<lm_eval>/tasks/gsm8k/gsm8k.yaml"
}
},
"ifeval": {
"task": "ifeval",
"dataset_path": "google/IFEval",
"test_split": "train",
"doc_to_text": "prompt",
"doc_to_target": 0,
"unsafe_code": false,
"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",
"fewshot_config": {
"sampler": "default",
"split": null,
"process_docs": null,
"fewshot_indices": null,
"samples": null,
"doc_to_text": "prompt",
"doc_to_choice": null,
"doc_to_target": 0,
"gen_prefix": null,
"fewshot_delimiter": "\n\n",
"target_delimiter": " "
},
"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,
"model": "dsv4-hybrid",
"base_url": "http://localhost:PORT/v1/chat/completions",
"num_concurrent": 16,
"max_retries": 3,
"tokenized_requests": false,
"tokenizer": "<model_path>",
"tokenizer_backend": "huggingface",
"config_source": "<lm_eval>/tasks/ifeval/ifeval.yaml"
}
}
},
"versions": {
"gsm8k": 3.0,
"ifeval": 4.0
},
"n-shot": {
"gsm8k": 5,
"ifeval": 0
},
"higher_is_better": {
"gsm8k": {
"exact_match": true
},
"ifeval": {
"prompt_level_strict_acc": true,
"inst_level_strict_acc": true,
"prompt_level_loose_acc": true,
"inst_level_loose_acc": true
}
},
"n-samples": {
"gsm8k": {
"original": 1319,
"effective": 200
},
"ifeval": {
"original": 541,
"effective": 200
}
},
"config": {
"model": "local-chat-completions",
"model_args": {
"model": "dsv4-hybrid",
"base_url": "http://localhost:PORT/v1/chat/completions",
"num_concurrent": 16,
"max_retries": 3,
"tokenized_requests": false,
"tokenizer": "<model_path>",
"tokenizer_backend": "huggingface"
},
"batch_size": 1,
"batch_sizes": [],
"device": "cuda:0",
"use_cache": null,
"limit": 200.0,
"bootstrap_iters": 100000,
"gen_kwargs": {},
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": null,
"date": 1786209999.0285816,
"transformers_version": "5.14.1",
"lm_eval_version": "0.4.12",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<|end▁of▁sentence|>",
"1"
],
"tokenizer_eos_token": [
"<|end▁of▁sentence|>",
"1"
],
"tokenizer_bos_token": [
"<|begin▁of▁sentence|>",
"0"
],
"eot_token_id": 1,
"max_length": 2047,
"task_hashes": {},
"model_source": "local-chat-completions",
"model_name": "dsv4-hybrid",
"model_name_sanitized": "dsv4-hybrid",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": true,
"chat_template": null,
"chat_template_sha": null,
"total_evaluation_time_seconds": "261.7299920649966",
"hardware_note": "2x NVIDIA RTX PRO 6000 Blackwell (96GB, SM120), TP=2. Detailed host environment omitted."
}