Spaces:
Running
Running
MLLM_leaderboard
/
eval-results
/Delcos
/Mistral-Pygmalion-7b
/results_2023-10-28T13-05-25.339926.json
{ | |
"config_general": { | |
"model_name": "Delcos/Mistral-Pygmalion-7b", | |
"model_sha": "1abd9c77daf9db4744823dc0f8fa31e94c71a101", | |
"model_size": "12.61 GB", | |
"model_dtype": "torch.float16", | |
"lighteval_sha": "0f318ecf002208468154899217b3ba7c6ae09374", | |
"num_few_shot_default": 0, | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 1, | |
"max_samples": null, | |
"job_id": "" | |
}, | |
"results": { | |
"harness|drop|3": { | |
"em": 0.001363255033557047, | |
"em_stderr": 0.0003778609196460774, | |
"f1": 0.05936241610738259, | |
"f1_stderr": 0.0013656193493625718 | |
}, | |
"harness|gsm8k|5": { | |
"acc": 0.06823351023502654, | |
"acc_stderr": 0.006945358944067431 | |
}, | |
"harness|winogrande|5": { | |
"acc": 0.7529597474348856, | |
"acc_stderr": 0.012121402942855575 | |
}, | |
"all": { | |
"em": 0.001363255033557047, | |
"em_stderr": 0.0003778609196460774, | |
"f1": 0.05936241610738259, | |
"f1_stderr": 0.0013656193493625718, | |
"acc": 0.41059662883495607, | |
"acc_stderr": 0.009533380943461503 | |
} | |
}, | |
"versions": { | |
"harness|drop|3": 1, | |
"harness|gsm8k|5": 0, | |
"harness|winogrande|5": 0, | |
"all": 0 | |
}, | |
"config_tasks": { | |
"harness|drop": "LM Harness task", | |
"harness|gsm8k": "LM Harness task", | |
"harness|winogrande": "LM Harness task" | |
}, | |
"summary_tasks": { | |
"harness|drop|3": { | |
"hashes": { | |
"hash_examples": "1d27416e8324e9a3", | |
"hash_full_prompts": "a5513ff9a741b385", | |
"hash_input_tokens": "42076f0efbb50aa6", | |
"hash_cont_tokens": "1492761f44bd3a5d" | |
}, | |
"truncated": 3, | |
"non-truncated": 9533, | |
"padded": 0, | |
"non-padded": 9536, | |
"effective_few_shots": 3.0, | |
"num_truncated_few_shots": 0 | |
}, | |
"harness|gsm8k|5": { | |
"hashes": { | |
"hash_examples": "4c0843a5d99bcfdc", | |
"hash_full_prompts": "41d55e83abc0e02d", | |
"hash_input_tokens": "bda342e47b5099b2", | |
"hash_cont_tokens": "e1f25b89acd14fbc" | |
}, | |
"truncated": 0, | |
"non-truncated": 1319, | |
"padded": 0, | |
"non-padded": 1319, | |
"effective_few_shots": 5.0, | |
"num_truncated_few_shots": 0 | |
}, | |
"harness|winogrande|5": { | |
"hashes": { | |
"hash_examples": "aada0a176fd81218", | |
"hash_full_prompts": "c8655cbd12de8409", | |
"hash_input_tokens": "c0bedf98cb040854", | |
"hash_cont_tokens": "f08975ad6f2d5864" | |
}, | |
"truncated": 0, | |
"non-truncated": 2534, | |
"padded": 2432, | |
"non-padded": 102, | |
"effective_few_shots": 5.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "9b4d8993161e637d", | |
"hash_full_prompts": "08215e527b7e60a5", | |
"hash_input_tokens": "a12f3e3c934bd78b", | |
"hash_cont_tokens": "4d4ebc45083d397b" | |
}, | |
"total_evaluation_time_secondes": "9800.566268920898", | |
"truncated": 3, | |
"non-truncated": 13386, | |
"padded": 2432, | |
"non-padded": 10957, | |
"num_truncated_few_shots": 0 | |
} | |
} |