| { | |
| "checkpoint_path": "/data_2to/devel_data/nn_pruning/output/squadv2_test_3/hp_mnop-bert-large-uncased-whole-word-masking_dn-squad_v2_v2wn1_od-__data_2to__devel_data__nn_pruning__output__squadv2_test_3___es-steps_pdtbs8_pdebs128_nte20.06_ls250_stl50_est5000_--128cd5d9b5683065/checkpoint-330000", | |
| "config": { | |
| "_name_or_path": "/tmp/tmpxe9vb3vd", | |
| "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, 3, 4, 5, 9, 13, 15], | |
| "1": [0, 1, 7, 9, 10, 13, 14], | |
| "10": [1, 2, 4, 5, 6, 8, 11, 13], | |
| "11": [2, 5, 6, 8, 12, 15], | |
| "12": [0, 2, 6, 9, 13], | |
| "13": [2, 3, 6, 10, 12, 15], | |
| "14": [10, 5], | |
| "15": [0, 9], | |
| "16": [], | |
| "17": [1, 4, 12], | |
| "18": [11, 4], | |
| "19": [5], | |
| "2": [0, 1, 4, 6, 7, 8, 9, 11, 12, 13, 14, 15], | |
| "20": [0, 1, 12], | |
| "21": [0, 2, 3, 4, 8, 10, 11, 12, 15], | |
| "22": [0, 1, 3, 7, 9, 10, 11, 13], | |
| "23": [2, 4, 7, 8, 9, 10, 13], | |
| "3": [0, 3, 5, 6, 7, 8, 9, 13, 14, 15], | |
| "4": [0, 2, 3, 5, 6, 7, 9, 10, 11, 12, 14], | |
| "5": [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": [3, 5, 8, 9, 10, 11, 12, 13], | |
| "8": [3, 5, 7, 8, 9, 11, 12], | |
| "9": [0, 1, 2, 5, 6, 7, 13, 14] | |
| }, | |
| "transformers_version": "4.7.0.dev0", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 30522 | |
| }, | |
| "eval_metrics": { | |
| "HasAns_exact": 76.48448043184885, | |
| "HasAns_f1": 82.55514100819374, | |
| "HasAns_total": 5928, | |
| "NoAns_exact": 83.8856181665265, | |
| "NoAns_f1": 83.8856181665265, | |
| "NoAns_total": 5945, | |
| "best_exact": 80.19034784805862, | |
| "best_exact_thresh": 0.0, | |
| "best_f1": 83.22133208932635, | |
| "best_f1_thresh": 0.0, | |
| "exact": 80.19034784805862, | |
| "f1": 83.22133208932645, | |
| "main_metric": 83.22133208932645, | |
| "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, | |
| "decoder_attention_lambda": null, | |
| "decoder_dense_lambda": null, | |
| "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": 2, | |
| "rewind_model_name_or_path": null | |
| }, | |
| "speed": { | |
| "cuda_eval_elapsed_time": 63.65266278076172, | |
| "eval_elapsed_time": 68.118653698 | |
| }, | |
| "speedup": 0.6933166669240776, | |
| "stats": { | |
| "layers": { | |
| "0": { | |
| "linear_attention_nnz": 1329152, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 1294336, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 2623488, | |
| "linear_total": 12582912, | |
| "nnz": 2631960, | |
| "total": 12594880 | |
| }, | |
| "1": { | |
| "linear_attention_nnz": 1539072, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 1429504, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 2968576, | |
| "linear_total": 12582912, | |
| "nnz": 2977018, | |
| "total": 12594880 | |
| }, | |
| "10": { | |
| "linear_attention_nnz": 1718272, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 1990656, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 3708928, | |
| "linear_total": 12582912, | |
| "nnz": 3717580, | |
| "total": 12594688 | |
| }, | |
| "11": { | |
| "linear_attention_nnz": 2091008, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 2207744, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 4298752, | |
| "linear_total": 12582912, | |
| "nnz": 4307894, | |
| "total": 12595072 | |
| }, | |
| "12": { | |
| "linear_attention_nnz": 2011136, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 1988608, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 3999744, | |
| "linear_total": 12582912, | |
| "nnz": 4008939, | |
| "total": 12595264 | |
| }, | |
| "13": { | |
| "linear_attention_nnz": 2132992, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 2392064, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 4525056, | |
| "linear_total": 12582912, | |
| "nnz": 4534288, | |
| "total": 12595072 | |
| }, | |
| "14": { | |
| "linear_attention_nnz": 2490368, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 1941504, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 4431872, | |
| "linear_total": 12582912, | |
| "nnz": 4441620, | |
| "total": 12595840 | |
| }, | |
| "15": { | |
| "linear_attention_nnz": 2515968, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 1873920, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 4389888, | |
| "linear_total": 12582912, | |
| "nnz": 4399635, | |
| "total": 12595840 | |
| }, | |
| "16": { | |
| "linear_attention_nnz": 2995200, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 1984512, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 4979712, | |
| "linear_total": 12582912, | |
| "nnz": 4989801, | |
| "total": 12596224 | |
| }, | |
| "17": { | |
| "linear_attention_nnz": 2373632, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 1820672, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 4194304, | |
| "linear_total": 12582912, | |
| "nnz": 4203737, | |
| "total": 12595648 | |
| }, | |
| "18": { | |
| "linear_attention_nnz": 2628608, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 1259520, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 3888128, | |
| "linear_total": 12582912, | |
| "nnz": 3897575, | |
| "total": 12595840 | |
| }, | |
| "19": { | |
| "linear_attention_nnz": 2135040, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 776192, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 2911232, | |
| "linear_total": 12582912, | |
| "nnz": 2920315, | |
| "total": 12596032 | |
| }, | |
| "2": { | |
| "linear_attention_nnz": 761856, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 1775616, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 2537472, | |
| "linear_total": 12582912, | |
| "nnz": 2545251, | |
| "total": 12593920 | |
| }, | |
| "20": { | |
| "linear_attention_nnz": 1545216, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 507904, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 2053120, | |
| "linear_total": 12582912, | |
| "nnz": 2061560, | |
| "total": 12595648 | |
| }, | |
| "21": { | |
| "linear_attention_nnz": 608256, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 260096, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 868352, | |
| "linear_total": 12582912, | |
| "nnz": 875551, | |
| "total": 12594496 | |
| }, | |
| "22": { | |
| "linear_attention_nnz": 617472, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 149504, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 766976, | |
| "linear_total": 12582912, | |
| "nnz": 774281, | |
| "total": 12594688 | |
| }, | |
| "23": { | |
| "linear_attention_nnz": 527360, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 284672, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 812032, | |
| "linear_total": 12582912, | |
| "nnz": 819435, | |
| "total": 12594880 | |
| }, | |
| "3": { | |
| "linear_attention_nnz": 1164288, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 2027520, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 3191808, | |
| "linear_total": 12582912, | |
| "nnz": 3200094, | |
| "total": 12594304 | |
| }, | |
| "4": { | |
| "linear_attention_nnz": 835584, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 2035712, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 2871296, | |
| "linear_total": 12582912, | |
| "nnz": 2879362, | |
| "total": 12594112 | |
| }, | |
| "5": { | |
| "linear_attention_nnz": 734208, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 2123776, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 2857984, | |
| "linear_total": 12582912, | |
| "nnz": 2866029, | |
| "total": 12594112 | |
| }, | |
| "6": { | |
| "linear_attention_nnz": 816128, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 2312192, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 3128320, | |
| "linear_total": 12582912, | |
| "nnz": 3136361, | |
| "total": 12593920 | |
| }, | |
| "7": { | |
| "linear_attention_nnz": 1503232, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 2338816, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 3842048, | |
| "linear_total": 12582912, | |
| "nnz": 3850774, | |
| "total": 12594688 | |
| }, | |
| "8": { | |
| "linear_attention_nnz": 1784832, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 2328576, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 4113408, | |
| "linear_total": 12582912, | |
| "nnz": 4122385, | |
| "total": 12594880 | |
| }, | |
| "9": { | |
| "linear_attention_nnz": 1396736, | |
| "linear_attention_total": 4194304, | |
| "linear_dense_nnz": 2463744, | |
| "linear_dense_total": 8388608, | |
| "linear_nnz": 3860480, | |
| "linear_total": 12582912, | |
| "nnz": 3869363, | |
| "total": 12594688 | |
| } | |
| }, | |
| "linear_nnz": 77822976, | |
| "linear_sparsity": 74.22993977864583, | |
| "linear_total": 301989888, | |
| "nnz": 109815770, | |
| "pruned_heads": { | |
| "0": [0, 3, 4, 5, 9, 13, 15], | |
| "1": [0, 1, 7, 9, 10, 13, 14], | |
| "10": [1, 2, 4, 5, 6, 8, 11, 13], | |
| "11": [2, 5, 6, 8, 12, 15], | |
| "12": [0, 2, 6, 9, 13], | |
| "13": [2, 3, 6, 10, 12, 15], | |
| "14": [10, 5], | |
| "15": [0, 9], | |
| "16": [], | |
| "17": [1, 4, 12], | |
| "18": [11, 4], | |
| "19": [5], | |
| "2": [0, 1, 4, 6, 7, 8, 9, 11, 12, 13, 14, 15], | |
| "20": [0, 1, 12], | |
| "21": [0, 2, 3, 4, 8, 10, 11, 12, 15], | |
| "22": [0, 1, 3, 7, 9, 10, 11, 13], | |
| "23": [2, 4, 7, 8, 9, 10, 13], | |
| "3": [0, 3, 5, 6, 7, 8, 9, 13, 14, 15], | |
| "4": [0, 2, 3, 5, 6, 7, 9, 10, 11, 12, 14], | |
| "5": [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": [3, 5, 8, 9, 10, 11, 12, 13], | |
| "8": [3, 5, 7, 8, 9, 11, 12], | |
| "9": [0, 1, 2, 5, 6, 7, 13, 14] | |
| }, | |
| "total": 334064578, | |
| "total_sparsity": 67.12738277806874 | |
| }, | |
| "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_3/", | |
| "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": 20.06, | |
| "optimize_model_before_eval": "disabled", | |
| "output_dir": "/data_2to/devel_data/nn_pruning/output/squadv2_test_3/", | |
| "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_3/", | |
| "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 | |
| } | |
| } |