open-r1-eval-leaderboard / eval_results /abacaj /phi-2-super /main /hellaswag /results_2024-03-02T15-43-34.133154.json
lewtun's picture
lewtun HF staff
Upload eval_results/abacaj/phi-2-super/main/hellaswag/results_2024-03-02T15-43-34.133154.json with huggingface_hub
165cba6 verified
raw
history blame
2.31 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 1,
"max_samples": null,
"job_id": "",
"start_time": 671925.202655765,
"end_time": 672394.228311995,
"total_evaluation_time_secondes": "469.0256562300492",
"model_name": "abacaj/phi-2-super",
"model_sha": "f1e578c868e6cc20fb1ea8eeee427ddf6e0e2ee4",
"model_dtype": "torch.bfloat16",
"model_size": "5.19 GB",
"config": null
},
"results": {
"lighteval|hellaswag|10": {
"acc": 0.563931487751444,
"acc_stderr": 0.004948824501355488,
"acc_norm": 0.7383987253535153,
"acc_norm_stderr": 0.004386083683839618
}
},
"versions": {
"lighteval|hellaswag|10": 0
},
"config_tasks": {
"lighteval|hellaswag": {
"name": "hellaswag",
"prompt_function": "hellaswag_harness",
"hf_repo": "hellaswag",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm"
],
"hf_avail_splits": [
"train",
"test",
"validation"
],
"evaluation_splits": [
"validation"
],
"few_shots_split": null,
"few_shots_select": "random_sampling_from_train",
"generation_size": -1,
"stop_sequence": [
"\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 10042,
"effective_num_docs": 10042
}
},
"summary_tasks": {
"lighteval|hellaswag|10": {
"hashes": {
"hash_examples": "31985c805c3a737e",
"hash_full_prompts": "7b6e46f1ae3e8bd5",
"hash_input_tokens": "634c81ef9fb975b7",
"hash_cont_tokens": "4acec451e7e448c7"
},
"truncated": 0,
"non_truncated": 10042,
"padded": 40033,
"non_padded": 135,
"effective_few_shots": 10.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "63bc2cf8bae03fbc",
"hash_full_prompts": "ab72c04da86c65d7",
"hash_input_tokens": "77530d3fe093d963",
"hash_cont_tokens": "780c3b619b1929e1"
},
"truncated": 0,
"non_truncated": 10042,
"padded": 40033,
"non_padded": 135,
"num_truncated_few_shots": 0
}
}