Upload eval_results/HuggingFaceH4/mistral-7b-ift/v48.103/winogrande/results_2024-03-12T22-22-47.130509.json with huggingface_hub
Browse files
    	
        eval_results/HuggingFaceH4/mistral-7b-ift/v48.103/winogrande/results_2024-03-12T22-22-47.130509.json
    ADDED
    
    | @@ -0,0 +1,87 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "config_general": {
         | 
| 3 | 
            +
                "lighteval_sha": "?",
         | 
| 4 | 
            +
                "num_fewshot_seeds": 1,
         | 
| 5 | 
            +
                "override_batch_size": 1,
         | 
| 6 | 
            +
                "max_samples": null,
         | 
| 7 | 
            +
                "job_id": "",
         | 
| 8 | 
            +
                "start_time": 325482.619392621,
         | 
| 9 | 
            +
                "end_time": 325548.083938218,
         | 
| 10 | 
            +
                "total_evaluation_time_secondes": "65.46454559703125",
         | 
| 11 | 
            +
                "model_name": "HuggingFaceH4/mistral-7b-ift",
         | 
| 12 | 
            +
                "model_sha": "8a42a58fb1e5285fa3b0ff54300cc41882b6f0a9",
         | 
| 13 | 
            +
                "model_dtype": "torch.bfloat16",
         | 
| 14 | 
            +
                "model_size": "13.99 GB",
         | 
| 15 | 
            +
                "config": null
         | 
| 16 | 
            +
              },
         | 
| 17 | 
            +
              "results": {
         | 
| 18 | 
            +
                "lighteval|winogrande|5": {
         | 
| 19 | 
            +
                  "acc": 0.7300710339384373,
         | 
| 20 | 
            +
                  "acc_stderr": 0.012476433372002603
         | 
| 21 | 
            +
                }
         | 
| 22 | 
            +
              },
         | 
| 23 | 
            +
              "versions": {
         | 
| 24 | 
            +
                "lighteval|winogrande|5": 0
         | 
| 25 | 
            +
              },
         | 
| 26 | 
            +
              "config_tasks": {
         | 
| 27 | 
            +
                "lighteval|winogrande": {
         | 
| 28 | 
            +
                  "name": "winogrande",
         | 
| 29 | 
            +
                  "prompt_function": "winogrande",
         | 
| 30 | 
            +
                  "hf_repo": "winogrande",
         | 
| 31 | 
            +
                  "hf_subset": "winogrande_xl",
         | 
| 32 | 
            +
                  "metric": [
         | 
| 33 | 
            +
                    "loglikelihood_acc"
         | 
| 34 | 
            +
                  ],
         | 
| 35 | 
            +
                  "hf_avail_splits": [
         | 
| 36 | 
            +
                    "train",
         | 
| 37 | 
            +
                    "test",
         | 
| 38 | 
            +
                    "validation"
         | 
| 39 | 
            +
                  ],
         | 
| 40 | 
            +
                  "evaluation_splits": [
         | 
| 41 | 
            +
                    "validation"
         | 
| 42 | 
            +
                  ],
         | 
| 43 | 
            +
                  "few_shots_split": null,
         | 
| 44 | 
            +
                  "few_shots_select": "random_sampling",
         | 
| 45 | 
            +
                  "generation_size": -1,
         | 
| 46 | 
            +
                  "stop_sequence": [
         | 
| 47 | 
            +
                    "\n"
         | 
| 48 | 
            +
                  ],
         | 
| 49 | 
            +
                  "output_regex": null,
         | 
| 50 | 
            +
                  "frozen": false,
         | 
| 51 | 
            +
                  "suite": [
         | 
| 52 | 
            +
                    "lighteval"
         | 
| 53 | 
            +
                  ],
         | 
| 54 | 
            +
                  "original_num_docs": 1267,
         | 
| 55 | 
            +
                  "effective_num_docs": 1267
         | 
| 56 | 
            +
                }
         | 
| 57 | 
            +
              },
         | 
| 58 | 
            +
              "summary_tasks": {
         | 
| 59 | 
            +
                "lighteval|winogrande|5": {
         | 
| 60 | 
            +
                  "hashes": {
         | 
| 61 | 
            +
                    "hash_examples": "087d5d1a1afd4c7b",
         | 
| 62 | 
            +
                    "hash_full_prompts": "68a2321c6687b7fb",
         | 
| 63 | 
            +
                    "hash_input_tokens": "4ee3b4a10c000d4e",
         | 
| 64 | 
            +
                    "hash_cont_tokens": "b62ff56a2b8ad70e"
         | 
| 65 | 
            +
                  },
         | 
| 66 | 
            +
                  "truncated": 0,
         | 
| 67 | 
            +
                  "non_truncated": 1267,
         | 
| 68 | 
            +
                  "padded": 2403,
         | 
| 69 | 
            +
                  "non_padded": 131,
         | 
| 70 | 
            +
                  "effective_few_shots": 5.0,
         | 
| 71 | 
            +
                  "num_truncated_few_shots": 0
         | 
| 72 | 
            +
                }
         | 
| 73 | 
            +
              },
         | 
| 74 | 
            +
              "summary_general": {
         | 
| 75 | 
            +
                "hashes": {
         | 
| 76 | 
            +
                  "hash_examples": "b9a49975cc41fab7",
         | 
| 77 | 
            +
                  "hash_full_prompts": "61d22a7151c380da",
         | 
| 78 | 
            +
                  "hash_input_tokens": "be615631b41f228f",
         | 
| 79 | 
            +
                  "hash_cont_tokens": "02fbe23ec37d1582"
         | 
| 80 | 
            +
                },
         | 
| 81 | 
            +
                "truncated": 0,
         | 
| 82 | 
            +
                "non_truncated": 1267,
         | 
| 83 | 
            +
                "padded": 2403,
         | 
| 84 | 
            +
                "non_padded": 131,
         | 
| 85 | 
            +
                "num_truncated_few_shots": 0
         | 
| 86 | 
            +
              }
         | 
| 87 | 
            +
            }
         | 
 
			
