Spaces:
Running
Running
{ | |
"config_general": { | |
"model_name": "JosephusCheung/LL7M", | |
"model_sha": "9b31bbf38a43d41eaf166fb3573f706b23cb1c13", | |
"model_size": "12.7 GB", | |
"model_dtype": "torch.bfloat16", | |
"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": 0.019819630872483222, | |
"em_stderr": 0.0014273827117586067, | |
"f1": 0.07556312919463118, | |
"f1_stderr": 0.0018868261588306972 | |
}, | |
"harness|gsm8k|5": { | |
"acc": 0.006065200909780136, | |
"acc_stderr": 0.00213867030146044 | |
}, | |
"harness|winogrande|5": { | |
"acc": 0.6408839779005525, | |
"acc_stderr": 0.013483115202120236 | |
}, | |
"all": { | |
"em": 0.019819630872483222, | |
"em_stderr": 0.0014273827117586067, | |
"f1": 0.07556312919463118, | |
"f1_stderr": 0.0018868261588306972, | |
"acc": 0.3234745894051663, | |
"acc_stderr": 0.007810892751790338 | |
} | |
}, | |
"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": "4f38515ddd508802", | |
"hash_cont_tokens": "3be4a8a13d73b09f" | |
}, | |
"truncated": 1263, | |
"non-truncated": 8273, | |
"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": "5c1882801e34a45b", | |
"hash_cont_tokens": "5953d5df12e66c55" | |
}, | |
"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": "b7d2ede05bc9cad7", | |
"hash_cont_tokens": "624fc8f48375913b" | |
}, | |
"total_evaluation_time_secondes": "28160.855958223343", | |
"truncated": 1263, | |
"non-truncated": 12126, | |
"padded": 2432, | |
"non-padded": 10957, | |
"num_truncated_few_shots": 0 | |
} | |
} |