{
    "checkpoint_path": "/data_2to/devel_data/nn_pruning/output/squad_test4/hp_od-__data_2to__devel_data__nn_pruning__output__squad4___es-steps_nte20_ls250_stl50_est5000_rn-__data_2to__devel_data__nn_pruning__output__squad4___dpm-sigmoied_threshold:1d_alt_ap--17cd29ad8a563746/checkpoint-110000", 
    "config": {
        "_name_or_path": "/tmp/tmpspdgp5f3", 
        "architectures": ["BertForQuestionAnswering"], 
        "attention_probs_dropout_prob": 0.1, 
        "gradient_checkpointing": false, 
        "hidden_act": "gelu", 
        "hidden_dropout_prob": 0.1, 
        "hidden_size": 768, 
        "initializer_range": 0.02, 
        "intermediate_size": 3072, 
        "layer_norm_eps": 1e-12, 
        "max_position_embeddings": 512, 
        "model_type": "bert", 
        "num_attention_heads": 12, 
        "num_hidden_layers": 12, 
        "pad_token_id": 0, 
        "position_embedding_type": "absolute", 
        "pruned_heads": {
            "0": [0, 2, 4, 5, 6, 7, 11], 
            "1": [0, 2, 3, 5, 6, 7, 8], 
            "10": [1, 2, 4, 5, 6, 7, 8], 
            "11": [0, 2, 5, 7, 8, 10, 11], 
            "2": [4, 7, 8], 
            "3": [2, 4, 6, 7], 
            "4": [1, 2, 11], 
            "5": [1, 2, 5, 6, 7, 11], 
            "6": [2, 3, 7, 10], 
            "7": [1, 3, 6, 7, 11], 
            "8": [0, 3, 4, 8], 
            "9": [1, 4, 5, 7, 9, 10]
        }, 
        "transformers_version": "4.4.2", 
        "type_vocab_size": 2, 
        "use_cache": true, 
        "vocab_size": 30522
    }, 
    "eval_metrics": {
        "exact_match": 78.77010406811732, 
        "f1": 86.63938864881486, 
        "main_metric": 86.63938864881486
    }, 
    "model_args": {
        "cache_dir": null, 
        "config_name": null, 
        "model_name_or_path": "bert-base-uncased", 
        "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": "bert-large-uncased-whole-word-masking-finetuned-squad", 
        "distil_temperature": 2.0, 
        "final_ampere_temperature": 20.0, 
        "final_finetune": false, 
        "final_threshold": 0.1, 
        "final_warmup": 10, 
        "initial_ampere_temperature": 0.0, 
        "initial_threshold": 0, 
        "initial_warmup": 1, 
        "mask_init": "constant", 
        "mask_scale": 0.0, 
        "mask_scores_learning_rate": 0.01, 
        "regularization": "l1", 
        "regularization_final_lambda": 20
    }, 
    "speed": {
        "cuda_eval_elapsed_time": 16.665313415527343, 
        "eval_elapsed_time": 23.629751751199365
    }, 
    "speedup": 2.3158516160525413, 
    "stats": {
        "layers": {
            "0": {
                "linear_attention_nnz": 677888, 
                "linear_attention_total": 2359296, 
                "linear_dense_nnz": 310272, 
                "linear_dense_total": 4718592, 
                "linear_nnz": 988160, 
                "linear_total": 7077888, 
                "nnz": 993834, 
                "total": 7087872
            }, 
            "1": {
                "linear_attention_nnz": 689152, 
                "linear_attention_total": 2359296, 
                "linear_dense_nnz": 436224, 
                "linear_dense_total": 4718592, 
                "linear_nnz": 1125376, 
                "linear_total": 7077888, 
                "nnz": 1131132, 
                "total": 7087872
            }, 
            "10": {
                "linear_attention_nnz": 434176, 
                "linear_attention_total": 2359296, 
                "linear_dense_nnz": 121344, 
                "linear_dense_total": 4718592, 
                "linear_nnz": 555520, 
                "linear_total": 7077888, 
                "nnz": 560943, 
                "total": 7087872
            }, 
            "11": {
                "linear_attention_nnz": 334848, 
                "linear_attention_total": 2359296, 
                "linear_dense_nnz": 156672, 
                "linear_dense_total": 4718592, 
                "linear_nnz": 491520, 
                "linear_total": 7077888, 
                "nnz": 496838, 
                "total": 7087872
            }, 
            "2": {
                "linear_attention_nnz": 1087488, 
                "linear_attention_total": 2359296, 
                "linear_dense_nnz": 543744, 
                "linear_dense_total": 4718592, 
                "linear_nnz": 1631232, 
                "linear_total": 7077888, 
                "nnz": 1637570, 
                "total": 7087872
            }, 
            "3": {
                "linear_attention_nnz": 1189888, 
                "linear_attention_total": 2359296, 
                "linear_dense_nnz": 565248, 
                "linear_dense_total": 4718592, 
                "linear_nnz": 1755136, 
                "linear_total": 7077888, 
                "nnz": 1761552, 
                "total": 7087872
            }, 
            "4": {
                "linear_attention_nnz": 1104896, 
                "linear_attention_total": 2359296, 
                "linear_dense_nnz": 589824, 
                "linear_dense_total": 4718592, 
                "linear_nnz": 1694720, 
                "linear_total": 7077888, 
                "nnz": 1701216, 
                "total": 7087872
            }, 
            "5": {
                "linear_attention_nnz": 818176, 
                "linear_attention_total": 2359296, 
                "linear_dense_nnz": 514560, 
                "linear_dense_total": 4718592, 
                "linear_nnz": 1332736, 
                "linear_total": 7077888, 
                "nnz": 1338767, 
                "total": 7087872
            }, 
            "6": {
                "linear_attention_nnz": 882688, 
                "linear_attention_total": 2359296, 
                "linear_dense_nnz": 442368, 
                "linear_dense_total": 4718592, 
                "linear_nnz": 1325056, 
                "linear_total": 7077888, 
                "nnz": 1331200, 
                "total": 7087872
            }, 
            "7": {
                "linear_attention_nnz": 846848, 
                "linear_attention_total": 2359296, 
                "linear_dense_nnz": 322560, 
                "linear_dense_total": 4718592, 
                "linear_nnz": 1169408, 
                "linear_total": 7077888, 
                "nnz": 1175442, 
                "total": 7087872
            }, 
            "8": {
                "linear_attention_nnz": 732160, 
                "linear_attention_total": 2359296, 
                "linear_dense_nnz": 167424, 
                "linear_dense_total": 4718592, 
                "linear_nnz": 899584, 
                "linear_total": 7077888, 
                "nnz": 905581, 
                "total": 7087872
            }, 
            "9": {
                "linear_attention_nnz": 449536, 
                "linear_attention_total": 2359296, 
                "linear_dense_nnz": 84480, 
                "linear_dense_total": 4718592, 
                "linear_nnz": 534016, 
                "linear_total": 7077888, 
                "nnz": 539287, 
                "total": 7087872
            }
        }, 
        "linear_nnz": 13502464, 
        "linear_sparsity": 84.10252700617285, 
        "linear_total": 84934656, 
        "nnz": 37412084, 
        "pruned_heads": {
            "0": [0, 2, 4, 5, 6, 7, 11], 
            "1": [0, 2, 3, 5, 6, 7, 8], 
            "10": [1, 2, 4, 5, 6, 7, 8], 
            "11": [0, 2, 5, 7, 8, 10, 11], 
            "2": [8, 4, 7], 
            "3": [2, 4, 6, 7], 
            "4": [1, 2, 11], 
            "5": [1, 2, 5, 6, 7, 11], 
            "6": [10, 2, 3, 7], 
            "7": [1, 3, 6, 7, 11], 
            "8": [0, 8, 3, 4], 
            "9": [1, 4, 5, 7, 9, 10]
        }, 
        "total": 108893186, 
        "total_sparsity": 65.64331950026698
    }, 
    "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/squad4/", 
        "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/squad4/", 
        "overwrite_output_dir": 1, 
        "past_index": -1, 
        "per_device_eval_batch_size": 8, 
        "per_device_train_batch_size": 16, 
        "per_gpu_eval_batch_size": null, 
        "per_gpu_train_batch_size": null, 
        "prediction_loss_only": false, 
        "remove_unused_columns": true, 
        "report_to": null, 
        "run_name": "/data_2to/devel_data/nn_pruning/output/squad4/", 
        "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
    }
}