MLLM_leaderboard / eval-results /TinyPixel /elm-test /results_2023-10-28T16-54-03.304592.json
Wwwduojin's picture
Upload 1529 files
a312f2f
{
"config_general": {
"model_name": "TinyPixel/elm-test",
"model_sha": "aa8f81624d897aa493474bcd96dc3feae9f7a535",
"model_size": "12.58 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": 0.0012583892617449664,
"em_stderr": 0.0003630560893119392,
"f1": 0.05654886744966456,
"f1_stderr": 0.0013251750673152706
},
"harness|gsm8k|5": {
"acc": 0.07505686125852919,
"acc_stderr": 0.007257633145486643
},
"harness|winogrande|5": {
"acc": 0.7434885556432518,
"acc_stderr": 0.012273648008759996
},
"all": {
"em": 0.0012583892617449664,
"em_stderr": 0.0003630560893119392,
"f1": 0.05654886744966456,
"f1_stderr": 0.0013251750673152706,
"acc": 0.4092727084508905,
"acc_stderr": 0.00976564057712332
}
},
"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": "61b608e0b5ceed76",
"hash_cont_tokens": "91ebc292723b7ace"
},
"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": "bda342e47b5099b2",
"hash_cont_tokens": "41853c6e7d29c69a"
},
"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": "80afe720f936f8d2",
"hash_cont_tokens": "9686fe7f055183b6"
},
"total_evaluation_time_secondes": "10362.112861156464",
"truncated": 1263,
"non-truncated": 12126,
"padded": 2432,
"non-padded": 10957,
"num_truncated_few_shots": 0
}
}