{
    "checkpoint_path": "/data_2to/devel_data/nn_pruning/output/squadv2_test_2/hp_mnop-bert-large-uncased-whole-word-masking_dn-squad_v2_v2wn1_od-__data_2to__devel_data__nn_pruning__output__squadv2_test_2___es-steps_pdtbs8_pdebs128_nte20_ls250_stl50_est5000_rn---58ebffa395d47d66/checkpoint-325000", 
    "config": {
        "_name_or_path": "/tmp/tmpitf3rdr5", 
        "architectures": ["BertForQuestionAnswering"], 
        "attention_probs_dropout_prob": 0.1, 
        "gradient_checkpointing": false, 
        "hidden_act": "gelu", 
        "hidden_dropout_prob": 0.1, 
        "hidden_size": 1024, 
        "initializer_range": 0.02, 
        "intermediate_size": 4096, 
        "layer_norm_eps": 1e-12, 
        "max_position_embeddings": 512, 
        "model_type": "bert", 
        "num_attention_heads": 16, 
        "num_hidden_layers": 24, 
        "pad_token_id": 0, 
        "position_embedding_type": "absolute", 
        "pruned_heads": {
            "0": [0, 1, 3, 4, 5, 8, 9, 13, 15], 
            "1": [0, 1, 3, 5, 7, 9, 10, 13, 14], 
            "10": [1, 2, 4, 5, 6, 8, 11, 13], 
            "11": [0, 2, 5, 6, 7, 8, 10, 12, 15], 
            "12": [0, 2, 6, 8, 9, 11, 13], 
            "13": [2, 6, 10, 12, 15], 
            "14": [1, 5, 6, 10, 11, 15], 
            "15": [0, 9], 
            "16": [5, 7], 
            "17": [1, 4, 8, 12, 14], 
            "18": [3, 4, 11], 
            "19": [0, 5, 12], 
            "2": [0, 1, 4, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], 
            "20": [0, 4, 10, 12], 
            "21": [0, 2, 3, 4, 8, 11, 12, 15], 
            "22": [0, 1, 3, 4, 7, 9, 10, 11, 13, 15], 
            "23": [2, 4, 8, 9, 10, 13, 14, 15], 
            "3": [0, 3, 5, 6, 7, 8, 9, 11, 13, 14, 15], 
            "4": [0, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 14], 
            "5": [1, 3, 4, 5, 6, 7, 8, 9, 12, 13, 14, 15], 
            "6": [0, 1, 2, 3, 4, 7, 8, 9, 10, 11, 12, 15], 
            "7": [0, 3, 4, 5, 8, 9, 10, 11, 12, 13, 14], 
            "8": [3, 4, 5, 7, 8, 9, 10, 11, 12], 
            "9": [0, 1, 2, 3, 5, 6, 7, 9, 10, 13, 14, 15]
        }, 
        "transformers_version": "4.5.1", 
        "type_vocab_size": 2, 
        "use_cache": true, 
        "vocab_size": 30522
    }, 
    "eval_metrics": {
        "HasAns_exact": 74.8144399460189, 
        "HasAns_f1": 80.555306012496, 
        "HasAns_total": 5928, 
        "NoAns_exact": 84.57527333894029, 
        "NoAns_f1": 84.57527333894029, 
        "NoAns_total": 5945, 
        "best_exact": 79.70184452118251, 
        "best_exact_thresh": 0.0, 
        "best_f1": 82.56816761071966, 
        "best_f1_thresh": 0.0, 
        "exact": 79.70184452118251, 
        "f1": 82.56816761071981, 
        "main_metric": 82.56816761071981, 
        "total": 11873
    }, 
    "model_args": {
        "cache_dir": null, 
        "config_name": null, 
        "model_name_or_path": "bert-large-uncased-whole-word-masking", 
        "tokenizer_name": null, 
        "use_fast_tokenizer": true
    }, 
    "sparse_args": {
        "ampere_pruning_method": "disabled", 
        "attention_block_cols": 32, 
        "attention_block_rows": 32, 
        "attention_lambda": 1.0, 
        "attention_output_with_dense": 0, 
        "attention_pruning_method": "sigmoied_threshold", 
        "bias_mask": true, 
        "dense_block_cols": 1, 
        "dense_block_rows": 1, 
        "dense_lambda": 1.0, 
        "dense_pruning_method": "sigmoied_threshold:1d_alt", 
        "distil_alpha_ce": 0.1, 
        "distil_alpha_teacher": 0.9, 
        "distil_teacher_name_or_path": "madlag/bert-large-uncased-whole-word-masking-finetuned-squadv2", 
        "distil_temperature": 2.0, 
        "eval_with_current_patch_params": false, 
        "final_ampere_temperature": 20.0, 
        "final_finetune": false, 
        "final_threshold": 0.1, 
        "final_warmup": 10, 
        "gelu_patch": 0, 
        "gelu_patch_steps": 50000, 
        "initial_ampere_temperature": 0.0, 
        "initial_threshold": 0, 
        "initial_warmup": 1, 
        "layer_norm_patch": 0, 
        "layer_norm_patch_start_delta": 0.99, 
        "layer_norm_patch_steps": 50000, 
        "linear_min_parameters": 0.005, 
        "mask_init": "constant", 
        "mask_scale": 0.0, 
        "mask_scores_learning_rate": 0.01, 
        "qat": false, 
        "qconfig": "default", 
        "regularization": "l1", 
        "regularization_final_lambda": 5, 
        "rewind_model_name_or_path": null
    }, 
    "speed": {
        "cuda_eval_elapsed_time": 52.126098907470706, 
        "eval_elapsed_time": 56.62768604200005
    }, 
    "speedup": 0.8466287123910415, 
    "stats": {
        "layers": {
            "0": {
                "linear_attention_nnz": 998400, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 587776, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 1586176, 
                "linear_total": 12582912, 
                "nnz": 1593727, 
                "total": 12594496
            }, 
            "1": {
                "linear_attention_nnz": 1025024, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 624640, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 1649664, 
                "linear_total": 12582912, 
                "nnz": 1657297, 
                "total": 12594496
            }, 
            "10": {
                "linear_attention_nnz": 1531904, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1267712, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 2799616, 
                "linear_total": 12582912, 
                "nnz": 2807915, 
                "total": 12594688
            }, 
            "11": {
                "linear_attention_nnz": 1508352, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1351680, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 2860032, 
                "linear_total": 12582912, 
                "nnz": 2868180, 
                "total": 12594496
            }, 
            "12": {
                "linear_attention_nnz": 1525760, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1236992, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 2762752, 
                "linear_total": 12582912, 
                "nnz": 2771132, 
                "total": 12594880
            }, 
            "13": {
                "linear_attention_nnz": 1813504, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1423360, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 3236864, 
                "linear_total": 12582912, 
                "nnz": 3245559, 
                "total": 12595264
            }, 
            "14": {
                "linear_attention_nnz": 1774592, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1153024, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 2927616, 
                "linear_total": 12582912, 
                "nnz": 2936051, 
                "total": 12595072
            }, 
            "15": {
                "linear_attention_nnz": 1909760, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1077248, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 2987008, 
                "linear_total": 12582912, 
                "nnz": 2996110, 
                "total": 12595840
            }, 
            "16": {
                "linear_attention_nnz": 2169856, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1091584, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 3261440, 
                "linear_total": 12582912, 
                "nnz": 3270645, 
                "total": 12595840
            }, 
            "17": {
                "linear_attention_nnz": 1823744, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1071104, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 2894848, 
                "linear_total": 12582912, 
                "nnz": 2903531, 
                "total": 12595264
            }, 
            "18": {
                "linear_attention_nnz": 1886208, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 774144, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 2660352, 
                "linear_total": 12582912, 
                "nnz": 2669146, 
                "total": 12595648
            }, 
            "19": {
                "linear_attention_nnz": 1472512, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 446464, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 1918976, 
                "linear_total": 12582912, 
                "nnz": 1927354, 
                "total": 12595648
            }, 
            "2": {
                "linear_attention_nnz": 595968, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 876544, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 1472512, 
                "linear_total": 12582912, 
                "nnz": 1479660, 
                "total": 12593728
            }, 
            "20": {
                "linear_attention_nnz": 1079296, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 299008, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 1378304, 
                "linear_total": 12582912, 
                "nnz": 1386290, 
                "total": 12595456
            }, 
            "21": {
                "linear_attention_nnz": 512000, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 155648, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 667648, 
                "linear_total": 12582912, 
                "nnz": 674764, 
                "total": 12594688
            }, 
            "22": {
                "linear_attention_nnz": 375808, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 90112, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 465920, 
                "linear_total": 12582912, 
                "nnz": 472716, 
                "total": 12594304
            }, 
            "23": {
                "linear_attention_nnz": 343040, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 221184, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 564224, 
                "linear_total": 12582912, 
                "nnz": 571244, 
                "total": 12594688
            }, 
            "3": {
                "linear_attention_nnz": 916480, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1085440, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 2001920, 
                "linear_total": 12582912, 
                "nnz": 2009554, 
                "total": 12594112
            }, 
            "4": {
                "linear_attention_nnz": 678912, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1146880, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 1825792, 
                "linear_total": 12582912, 
                "nnz": 1833264, 
                "total": 12593920
            }, 
            "5": {
                "linear_attention_nnz": 509952, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1308672, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 1818624, 
                "linear_total": 12582912, 
                "nnz": 1825983, 
                "total": 12593920
            }, 
            "6": {
                "linear_attention_nnz": 717824, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1441792, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 2159616, 
                "linear_total": 12582912, 
                "nnz": 2167168, 
                "total": 12593920
            }, 
            "7": {
                "linear_attention_nnz": 1009664, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1468416, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 2478080, 
                "linear_total": 12582912, 
                "nnz": 2485901, 
                "total": 12594112
            }, 
            "8": {
                "linear_attention_nnz": 1327104, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1468416, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 2795520, 
                "linear_total": 12582912, 
                "nnz": 2803661, 
                "total": 12594496
            }, 
            "9": {
                "linear_attention_nnz": 631808, 
                "linear_attention_total": 4194304, 
                "linear_dense_nnz": 1531904, 
                "linear_dense_total": 8388608, 
                "linear_nnz": 2163712, 
                "linear_total": 12582912, 
                "nnz": 2171276, 
                "total": 12593920
            }
        }, 
        "linear_nnz": 51337216, 
        "linear_sparsity": 83.00035264756944, 
        "linear_total": 301989888, 
        "nnz": 83313090, 
        "pruned_heads": {
            "0": [0, 1, 3, 4, 5, 8, 9, 13, 15], 
            "1": [0, 1, 3, 5, 7, 9, 10, 13, 14], 
            "10": [1, 2, 4, 5, 6, 8, 11, 13], 
            "11": [0, 2, 5, 6, 7, 8, 10, 12, 15], 
            "12": [0, 2, 6, 8, 9, 11, 13], 
            "13": [2, 6, 10, 12, 15], 
            "14": [1, 5, 6, 10, 11, 15], 
            "15": [0, 9], 
            "16": [5, 7], 
            "17": [1, 4, 8, 12, 14], 
            "18": [3, 11, 4], 
            "19": [0, 12, 5], 
            "2": [0, 1, 4, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], 
            "20": [0, 10, 4, 12], 
            "21": [0, 2, 3, 4, 8, 11, 12, 15], 
            "22": [0, 1, 3, 4, 7, 9, 10, 11, 13, 15], 
            "23": [2, 4, 8, 9, 10, 13, 14, 15], 
            "3": [0, 3, 5, 6, 7, 8, 9, 11, 13, 14, 15], 
            "4": [0, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 14], 
            "5": [1, 3, 4, 5, 6, 7, 8, 9, 12, 13, 14, 15], 
            "6": [0, 1, 2, 3, 4, 7, 8, 9, 10, 11, 12, 15], 
            "7": [0, 3, 4, 5, 8, 9, 10, 11, 12, 13, 14], 
            "8": [3, 4, 5, 7, 8, 9, 10, 11, 12], 
            "9": [0, 1, 2, 3, 5, 6, 7, 9, 10, 13, 14, 15]
        }, 
        "total": 334057858, 
        "total_sparsity": 75.06028132408129
    }, 
    "training_args": {
        "_n_gpu": 1, 
        "adafactor": false, 
        "adam_beta1": 0.9, 
        "adam_beta2": 0.999, 
        "adam_epsilon": 1e-08, 
        "dataloader_drop_last": false, 
        "dataloader_num_workers": 0, 
        "dataloader_pin_memory": true, 
        "ddp_find_unused_parameters": null, 
        "debug": false, 
        "deepspeed": null, 
        "disable_tqdm": false, 
        "do_eval": 1, 
        "do_predict": false, 
        "do_train": 1, 
        "eval_accumulation_steps": null, 
        "eval_steps": 5000, 
        "evaluation_strategy": "steps", 
        "fp16": false, 
        "fp16_backend": "auto", 
        "fp16_full_eval": false, 
        "fp16_opt_level": "O1", 
        "gradient_accumulation_steps": 1, 
        "greater_is_better": null, 
        "group_by_length": false, 
        "ignore_data_skip": false, 
        "label_names": null, 
        "label_smoothing_factor": 0.0, 
        "learning_rate": 3e-05, 
        "length_column_name": "length", 
        "load_best_model_at_end": false, 
        "local_rank": -1, 
        "logging_dir": "/data_2to/devel_data/nn_pruning/output/squadv2_test_2/", 
        "logging_first_step": false, 
        "logging_steps": 250, 
        "logging_strategy": "steps", 
        "lr_scheduler_type": "linear", 
        "max_grad_norm": 1.0, 
        "max_steps": -1, 
        "metric_for_best_model": null, 
        "mp_parameters": "", 
        "no_cuda": false, 
        "num_train_epochs": 20, 
        "optimize_model_before_eval": "disabled", 
        "output_dir": "/data_2to/devel_data/nn_pruning/output/squadv2_test_2/", 
        "overwrite_output_dir": 1, 
        "past_index": -1, 
        "per_device_eval_batch_size": 128, 
        "per_device_train_batch_size": 8, 
        "per_gpu_eval_batch_size": null, 
        "per_gpu_train_batch_size": null, 
        "prediction_loss_only": false, 
        "remove_unused_columns": true, 
        "report_to": ["tensorboard", "wandb"], 
        "run_name": "/data_2to/devel_data/nn_pruning/output/squadv2_test_2/", 
        "save_steps": 5000, 
        "save_strategy": "steps", 
        "save_total_limit": 50, 
        "seed": 17, 
        "sharded_ddp": [], 
        "skip_memory_metrics": false, 
        "tpu_metrics_debug": false, 
        "tpu_num_cores": null, 
        "warmup_ratio": 0.0, 
        "warmup_steps": 5400, 
        "weight_decay": 0.0
    }
}