| { | |
| "checkpoint_path": "/data_2to/devel_data/nn_pruning/output/squad_test_8_mvp_lt/hp_od-__data_2to__devel_data__nn_pruning__output__squad_test_8_mvp_lt___es-steps_nte20_ls250_stl50_est5000_rn-__data_2to__devel_data__nn_pruning__output__squad_test_8_mvp_lt___dpm-si--7fe43555f854fbb6/checkpoint-110000", | |
| "config": { | |
| "_name_or_path": "/tmp/tmpdczbpf2s", | |
| "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": [9], | |
| "1": [], | |
| "10": [1, 2, 4], | |
| "11": [5, 7, 8, 11], | |
| "2": [8], | |
| "3": [2, 4], | |
| "4": [], | |
| "5": [1], | |
| "6": [2, 3], | |
| "7": [1, 7], | |
| "8": [0], | |
| "9": [1, 4, 5, 7, 10] | |
| }, | |
| "transformers_version": "4.4.2", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 30522 | |
| }, | |
| "eval_metrics": { | |
| "exact_match": 80.93661305581836, | |
| "f1": 88.11360890595924, | |
| "main_metric": 88.11360890595924 | |
| }, | |
| "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": 1, | |
| "attention_block_rows": 1, | |
| "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", | |
| "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, | |
| "gelu_patch": 0, | |
| "initial_ampere_temperature": 0.0, | |
| "initial_threshold": 0, | |
| "initial_warmup": 1, | |
| "layer_norm_patch": 0, | |
| "mask_init": "constant", | |
| "mask_scale": 0.0, | |
| "mask_scores_learning_rate": 0.01, | |
| "regularization": "l1", | |
| "regularization_final_lambda": 120 | |
| }, | |
| "speed": { | |
| "cuda_eval_elapsed_time": 33.17768461608887, | |
| "eval_elapsed_time": 40.18306041043252 | |
| }, | |
| "speedup": 1.1632636047982534, | |
| "stats": { | |
| "layers": { | |
| "0": { | |
| "linear_attention_nnz": 108638, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 743508, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 852146, | |
| "linear_total": 7077888, | |
| "nnz": 860873, | |
| "total": 7087872 | |
| }, | |
| "1": { | |
| "linear_attention_nnz": 171340, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 780119, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 951459, | |
| "linear_total": 7077888, | |
| "nnz": 960245, | |
| "total": 7087872 | |
| }, | |
| "10": { | |
| "linear_attention_nnz": 67316, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 69353, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 136669, | |
| "linear_total": 7077888, | |
| "nnz": 143162, | |
| "total": 7087872 | |
| }, | |
| "11": { | |
| "linear_attention_nnz": 41497, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 55855, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 97352, | |
| "linear_total": 7077888, | |
| "nnz": 103286, | |
| "total": 7087872 | |
| }, | |
| "2": { | |
| "linear_attention_nnz": 221074, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 756625, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 977699, | |
| "linear_total": 7077888, | |
| "nnz": 986901, | |
| "total": 7087872 | |
| }, | |
| "3": { | |
| "linear_attention_nnz": 258229, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 705908, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 964137, | |
| "linear_total": 7077888, | |
| "nnz": 973427, | |
| "total": 7087872 | |
| }, | |
| "4": { | |
| "linear_attention_nnz": 255136, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 593338, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 848474, | |
| "linear_total": 7077888, | |
| "nnz": 858037, | |
| "total": 7087872 | |
| }, | |
| "5": { | |
| "linear_attention_nnz": 179994, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 531061, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 711055, | |
| "linear_total": 7077888, | |
| "nnz": 720395, | |
| "total": 7087872 | |
| }, | |
| "6": { | |
| "linear_attention_nnz": 165167, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 406391, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 571558, | |
| "linear_total": 7077888, | |
| "nnz": 580963, | |
| "total": 7087872 | |
| }, | |
| "7": { | |
| "linear_attention_nnz": 139907, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 272514, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 412421, | |
| "linear_total": 7077888, | |
| "nnz": 421032, | |
| "total": 7087872 | |
| }, | |
| "8": { | |
| "linear_attention_nnz": 113253, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 163778, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 277031, | |
| "linear_total": 7077888, | |
| "nnz": 285536, | |
| "total": 7087872 | |
| }, | |
| "9": { | |
| "linear_attention_nnz": 84915, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 71190, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 156105, | |
| "linear_total": 7077888, | |
| "nnz": 162775, | |
| "total": 7087872 | |
| } | |
| }, | |
| "linear_nnz": 6956106, | |
| "linear_sparsity": 91.81004983407479, | |
| "linear_total": 84934656, | |
| "nnz": 30895354, | |
| "pruned_heads": { | |
| "0": [9], | |
| "1": [], | |
| "10": [1, 2, 4], | |
| "11": [8, 11, 5, 7], | |
| "2": [8], | |
| "3": [2, 4], | |
| "4": [], | |
| "5": [1], | |
| "6": [2, 3], | |
| "7": [1, 7], | |
| "8": [0], | |
| "9": [1, 4, 5, 7, 10] | |
| }, | |
| "total": 108893186, | |
| "total_sparsity": 71.62783537254572 | |
| }, | |
| "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/squad_test_8_mvp_lt/", | |
| "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/squad_test_8_mvp_lt/", | |
| "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/squad_test_8_mvp_lt/", | |
| "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 | |
| } | |
| } |