Upload eval_results/edbeeching/mixtral-8x7b-instruct-v0.1_merged/v0.2/ifeval/results_2024-04-14T15-56-38.588846.json with huggingface_hub
Browse files
    	
        eval_results/edbeeching/mixtral-8x7b-instruct-v0.1_merged/v0.2/ifeval/results_2024-04-14T15-56-38.588846.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": 4382731.190675399,
         
     | 
| 9 | 
         
            +
                "end_time": 4395567.219723309,
         
     | 
| 10 | 
         
            +
                "total_evaluation_time_secondes": "12836.029047910124",
         
     | 
| 11 | 
         
            +
                "model_name": "edbeeching/mixtral-8x7b-instruct-v0.1_merged",
         
     | 
| 12 | 
         
            +
                "model_sha": "02e5e37da870d6382b35fd16e9545bbab51dd218",
         
     | 
| 13 | 
         
            +
                "model_dtype": "torch.bfloat16",
         
     | 
| 14 | 
         
            +
                "model_size": "87.49 GB",
         
     | 
| 15 | 
         
            +
                "config": null
         
     | 
| 16 | 
         
            +
              },
         
     | 
| 17 | 
         
            +
              "results": {
         
     | 
| 18 | 
         
            +
                "extended|ifeval|0": {
         
     | 
| 19 | 
         
            +
                  "prompt_level_strict_acc": 0.31608133086876156,
         
     | 
| 20 | 
         
            +
                  "prompt_level_strict_acc_stderr": 0.020008050377238983,
         
     | 
| 21 | 
         
            +
                  "inst_level_strict_acc": 0.45443645083932854,
         
     | 
| 22 | 
         
            +
                  "inst_level_strict_acc_stderr": 0.0005347421322596333,
         
     | 
| 23 | 
         
            +
                  "prompt_level_loose_acc": 0.37153419593345655,
         
     | 
| 24 | 
         
            +
                  "prompt_level_loose_acc_stderr": 0.020794253888707544,
         
     | 
| 25 | 
         
            +
                  "inst_level_loose_acc": 0.5107913669064749,
         
     | 
| 26 | 
         
            +
                  "inst_level_loose_acc_stderr": 0.0005442216295824228
         
     | 
| 27 | 
         
            +
                },
         
     | 
| 28 | 
         
            +
                "all": {
         
     | 
| 29 | 
         
            +
                  "prompt_level_strict_acc": 0.31608133086876156,
         
     | 
| 30 | 
         
            +
                  "prompt_level_strict_acc_stderr": 0.020008050377238983,
         
     | 
| 31 | 
         
            +
                  "inst_level_strict_acc": 0.45443645083932854,
         
     | 
| 32 | 
         
            +
                  "inst_level_strict_acc_stderr": 0.0005347421322596333,
         
     | 
| 33 | 
         
            +
                  "prompt_level_loose_acc": 0.37153419593345655,
         
     | 
| 34 | 
         
            +
                  "prompt_level_loose_acc_stderr": 0.020794253888707544,
         
     | 
| 35 | 
         
            +
                  "inst_level_loose_acc": 0.5107913669064749,
         
     | 
| 36 | 
         
            +
                  "inst_level_loose_acc_stderr": 0.0005442216295824228
         
     | 
| 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": "50f8a8f5a08077cd",
         
     | 
| 77 | 
         
            +
                    "hash_input_tokens": "fb1ed90207cf652b",
         
     | 
| 78 | 
         
            +
                    "hash_cont_tokens": "8f7507ccd1e2c242"
         
     | 
| 79 | 
         
            +
                  },
         
     | 
| 80 | 
         
            +
                  "truncated": 541,
         
     | 
| 81 | 
         
            +
                  "non_truncated": 0,
         
     | 
| 82 | 
         
            +
                  "padded": 116,
         
     | 
| 83 | 
         
            +
                  "non_padded": 425,
         
     | 
| 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": "9c04db679f2c9132",
         
     | 
| 92 | 
         
            +
                  "hash_input_tokens": "af9a63ef7d2de8ba",
         
     | 
| 93 | 
         
            +
                  "hash_cont_tokens": "488c1f93c7b3e9d4"
         
     | 
| 94 | 
         
            +
                },
         
     | 
| 95 | 
         
            +
                "truncated": 541,
         
     | 
| 96 | 
         
            +
                "non_truncated": 0,
         
     | 
| 97 | 
         
            +
                "padded": 116,
         
     | 
| 98 | 
         
            +
                "non_padded": 425,
         
     | 
| 99 | 
         
            +
                "num_truncated_few_shots": 0
         
     | 
| 100 | 
         
            +
              }
         
     | 
| 101 | 
         
            +
            }
         
     |