Upload eval_results/orpo-explorers/Qwen1.5-7B-ohp-10k-v0.15/main/ifeval/results_2024-04-01T20-53-47.664880.json with huggingface_hub
Browse files
eval_results/orpo-explorers/Qwen1.5-7B-ohp-10k-v0.15/main/ifeval/results_2024-04-01T20-53-47.664880.json
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config_general": {
|
| 3 |
+
"lighteval_sha": "?",
|
| 4 |
+
"num_fewshot_seeds": 1,
|
| 5 |
+
"override_batch_size": 4,
|
| 6 |
+
"max_samples": null,
|
| 7 |
+
"job_id": "",
|
| 8 |
+
"start_time": 1173784.951908632,
|
| 9 |
+
"end_time": 1174541.045367852,
|
| 10 |
+
"total_evaluation_time_secondes": "756.0934592201374",
|
| 11 |
+
"model_name": "orpo-explorers/Qwen1.5-7B-ohp-10k-v0.15",
|
| 12 |
+
"model_sha": "f3426e6619898998352ae39f78b7fe3dc7891ba8",
|
| 13 |
+
"model_dtype": "torch.bfloat16",
|
| 14 |
+
"model_size": "14.88 GB",
|
| 15 |
+
"config": null
|
| 16 |
+
},
|
| 17 |
+
"results": {
|
| 18 |
+
"extended|ifeval|0": {
|
| 19 |
+
"prompt_level_strict_acc": 0.3234750462107209,
|
| 20 |
+
"prompt_level_strict_acc_stderr": 0.02013100339211897,
|
| 21 |
+
"inst_level_strict_acc": 0.4364508393285372,
|
| 22 |
+
"inst_level_strict_acc_stderr": 0.0005140800925195361,
|
| 23 |
+
"prompt_level_loose_acc": 0.3438077634011091,
|
| 24 |
+
"prompt_level_loose_acc_stderr": 0.020439793487859976,
|
| 25 |
+
"inst_level_loose_acc": 0.4592326139088729,
|
| 26 |
+
"inst_level_loose_acc_stderr": 0.0005058051374564954
|
| 27 |
+
},
|
| 28 |
+
"all": {
|
| 29 |
+
"prompt_level_strict_acc": 0.3234750462107209,
|
| 30 |
+
"prompt_level_strict_acc_stderr": 0.02013100339211897,
|
| 31 |
+
"inst_level_strict_acc": 0.4364508393285372,
|
| 32 |
+
"inst_level_strict_acc_stderr": 0.0005140800925195361,
|
| 33 |
+
"prompt_level_loose_acc": 0.3438077634011091,
|
| 34 |
+
"prompt_level_loose_acc_stderr": 0.020439793487859976,
|
| 35 |
+
"inst_level_loose_acc": 0.4592326139088729,
|
| 36 |
+
"inst_level_loose_acc_stderr": 0.0005058051374564954
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"versions": {
|
| 40 |
+
"extended|ifeval|0": 0
|
| 41 |
+
},
|
| 42 |
+
"config_tasks": {
|
| 43 |
+
"extended|ifeval": {
|
| 44 |
+
"name": "ifeval",
|
| 45 |
+
"prompt_function": "ifeval_prompt",
|
| 46 |
+
"hf_repo": "wis-k/instruction-following-eval",
|
| 47 |
+
"hf_subset": "default",
|
| 48 |
+
"metric": [
|
| 49 |
+
"ifeval_metric"
|
| 50 |
+
],
|
| 51 |
+
"hf_avail_splits": [
|
| 52 |
+
"train"
|
| 53 |
+
],
|
| 54 |
+
"evaluation_splits": [
|
| 55 |
+
"train"
|
| 56 |
+
],
|
| 57 |
+
"few_shots_split": "train",
|
| 58 |
+
"few_shots_select": "random_sampling",
|
| 59 |
+
"generation_size": 1280,
|
| 60 |
+
"stop_sequence": [],
|
| 61 |
+
"output_regex": null,
|
| 62 |
+
"frozen": false,
|
| 63 |
+
"suite": [
|
| 64 |
+
"extended"
|
| 65 |
+
],
|
| 66 |
+
"original_num_docs": 541,
|
| 67 |
+
"effective_num_docs": 541,
|
| 68 |
+
"trust_dataset": null,
|
| 69 |
+
"must_remove_duplicate_docs": null
|
| 70 |
+
}
|
| 71 |
+
},
|
| 72 |
+
"summary_tasks": {
|
| 73 |
+
"extended|ifeval|0": {
|
| 74 |
+
"hashes": {
|
| 75 |
+
"hash_examples": "e99cbf567588d7c6",
|
| 76 |
+
"hash_full_prompts": "7ea7bf2a8edba8f4",
|
| 77 |
+
"hash_input_tokens": "4d9405a95eea122b",
|
| 78 |
+
"hash_cont_tokens": "b6289dd30d460615"
|
| 79 |
+
},
|
| 80 |
+
"truncated": 541,
|
| 81 |
+
"non_truncated": 0,
|
| 82 |
+
"padded": 111,
|
| 83 |
+
"non_padded": 430,
|
| 84 |
+
"effective_few_shots": 0.0,
|
| 85 |
+
"num_truncated_few_shots": 0
|
| 86 |
+
}
|
| 87 |
+
},
|
| 88 |
+
"summary_general": {
|
| 89 |
+
"hashes": {
|
| 90 |
+
"hash_examples": "ea046ab2c6fc5928",
|
| 91 |
+
"hash_full_prompts": "45f8422f6ad2da79",
|
| 92 |
+
"hash_input_tokens": "0f908ce1163008f8",
|
| 93 |
+
"hash_cont_tokens": "bfee9f45ce2e0300"
|
| 94 |
+
},
|
| 95 |
+
"truncated": 541,
|
| 96 |
+
"non_truncated": 0,
|
| 97 |
+
"padded": 111,
|
| 98 |
+
"non_padded": 430,
|
| 99 |
+
"num_truncated_few_shots": 0
|
| 100 |
+
}
|
| 101 |
+
}
|