Spaces:
Running
Running
{ | |
"config_general": { | |
"model_name": "aisquared/dlite-v2-124m", | |
"model_sha": "bc719f990748ea72be4b6c270df34fc3d37291dc", | |
"model_size": "238.85 MB", | |
"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": 0.0050335570469798654, | |
"em_stderr": 0.0007247385547751906, | |
"f1": 0.05289324664429539, | |
"f1_stderr": 0.001460860471625635 | |
}, | |
"harness|gsm8k|5": { | |
"acc": 0.0, | |
"acc_stderr": 0.0 | |
}, | |
"harness|winogrande|5": { | |
"acc": 0.5043409629044988, | |
"acc_stderr": 0.014051956064076892 | |
}, | |
"all": { | |
"em": 0.0050335570469798654, | |
"em_stderr": 0.0007247385547751906, | |
"f1": 0.05289324664429539, | |
"f1_stderr": 0.001460860471625635, | |
"acc": 0.2521704814522494, | |
"acc_stderr": 0.007025978032038446 | |
} | |
}, | |
"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": "fa7a2e45b0104bc4", | |
"hash_cont_tokens": "bf61a7c21d9ed7af" | |
}, | |
"truncated": 9290, | |
"non-truncated": 246, | |
"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": "52733972d41ebb11", | |
"hash_cont_tokens": "683fee6b08788061" | |
}, | |
"truncated": 917, | |
"non-truncated": 402, | |
"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": "84cacac1590bb0a5", | |
"hash_cont_tokens": "64ca3ed9b5dacc6e" | |
}, | |
"truncated": 0, | |
"non-truncated": 2534, | |
"padded": 2426, | |
"non-padded": 108, | |
"effective_few_shots": 5.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "9b4d8993161e637d", | |
"hash_full_prompts": "08215e527b7e60a5", | |
"hash_input_tokens": "6b3de69e2f87348c", | |
"hash_cont_tokens": "8882ca9d833687d6" | |
}, | |
"total_evaluation_time_secondes": "4724.538892507553", | |
"truncated": 10207, | |
"non-truncated": 3182, | |
"padded": 2426, | |
"non-padded": 10963, | |
"num_truncated_few_shots": 0 | |
} | |
} |