| { | |
| "checkpoint_path": "/data_2to/devel_data/nn_pruning/output/squad_test_9_fullpatch6/hp_od-__data_2to__devel_data__nn_pruning__output__squad_test_9_fullpatch6___es-steps_nte20_ls250_stl50_est5000_rn-__data_2to__devel_data__nn_pruning__output__squad_test_9_fullpatch6_--5f772c87c5edbc85/checkpoint-100000", | |
| "config": { | |
| "_name_or_path": "/tmp/tmpcklouvey", | |
| "architectures": ["BertForQuestionAnswering"], | |
| "attention_probs_dropout_prob": 0.1, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "relu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "layer_norm_type": "no_norm", | |
| "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], | |
| "1": [0, 2, 3, 5, 6, 7, 8], | |
| "10": [1, 2, 4, 5, 6, 7, 8], | |
| "11": [0, 5, 7, 8, 10, 11], | |
| "2": [4, 7, 8], | |
| "3": [2, 4, 6], | |
| "4": [1, 2], | |
| "5": [1, 2, 6, 7, 11], | |
| "6": [2, 3, 10], | |
| "7": [1, 3, 6, 7, 11], | |
| "8": [0, 3, 4], | |
| "9": [1, 4, 5, 7, 9, 10] | |
| }, | |
| "type_vocab_size": 2, | |
| "vocab_size": 30522 | |
| }, | |
| "eval_metrics": { | |
| "exact_match": 82.21381267738883, | |
| "f1": 89.18874369381042, | |
| "main_metric": 89.18874369381042 | |
| }, | |
| "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, | |
| "gelu_patch": 1, | |
| "gelu_patch_steps": 50000, | |
| "initial_ampere_temperature": 0.0, | |
| "initial_threshold": 0, | |
| "initial_warmup": 1, | |
| "layer_norm_patch": 1, | |
| "layer_norm_patch_start_delta": 0.99, | |
| "layer_norm_patch_steps": 50000, | |
| "linear_min_parameters": 0, | |
| "mask_init": "constant", | |
| "mask_scale": 0.0, | |
| "mask_scores_learning_rate": 0.01, | |
| "regularization": "l1", | |
| "regularization_final_lambda": 10, | |
| "rewind_model_name_or_path": "madlag/bert-base-uncased-squadv1-x1.96-f88.3-d27-hybrid-filled-opt-v1" | |
| }, | |
| "speed": { | |
| "cuda_eval_elapsed_time": 19.22297591018677, | |
| "eval_elapsed_time": 26.312922549434006 | |
| }, | |
| "speedup": 2.00772207100977, | |
| "stats": { | |
| "layers": { | |
| "0": { | |
| "linear_attention_nnz": 1376256, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 734208, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 2110464, | |
| "linear_total": 7077888, | |
| "nnz": 2116894, | |
| "total": 7086912 | |
| }, | |
| "1": { | |
| "linear_attention_nnz": 983040, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 814080, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 1797120, | |
| "linear_total": 7077888, | |
| "nnz": 1803218, | |
| "total": 7086528 | |
| }, | |
| "10": { | |
| "linear_attention_nnz": 983040, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 505344, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 1488384, | |
| "linear_total": 7077888, | |
| "nnz": 1494281, | |
| "total": 7086528 | |
| }, | |
| "11": { | |
| "linear_attention_nnz": 1179648, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 728064, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 1907712, | |
| "linear_total": 7077888, | |
| "nnz": 1913946, | |
| "total": 7086720 | |
| }, | |
| "2": { | |
| "linear_attention_nnz": 1769472, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 1021440, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 2790912, | |
| "linear_total": 7077888, | |
| "nnz": 2797913, | |
| "total": 7087296 | |
| }, | |
| "3": { | |
| "linear_attention_nnz": 1769472, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 964608, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 2734080, | |
| "linear_total": 7077888, | |
| "nnz": 2741044, | |
| "total": 7087296 | |
| }, | |
| "4": { | |
| "linear_attention_nnz": 1966080, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 835584, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 2801664, | |
| "linear_total": 7077888, | |
| "nnz": 2808736, | |
| "total": 7087488 | |
| }, | |
| "5": { | |
| "linear_attention_nnz": 1376256, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 857088, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 2233344, | |
| "linear_total": 7077888, | |
| "nnz": 2239854, | |
| "total": 7086912 | |
| }, | |
| "6": { | |
| "linear_attention_nnz": 1769472, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 740352, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 2509824, | |
| "linear_total": 7077888, | |
| "nnz": 2516642, | |
| "total": 7087296 | |
| }, | |
| "7": { | |
| "linear_attention_nnz": 1376256, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 563712, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 1939968, | |
| "linear_total": 7077888, | |
| "nnz": 1946287, | |
| "total": 7086912 | |
| }, | |
| "8": { | |
| "linear_attention_nnz": 1769472, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 282624, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 2052096, | |
| "linear_total": 7077888, | |
| "nnz": 2058616, | |
| "total": 7087296 | |
| }, | |
| "9": { | |
| "linear_attention_nnz": 1179648, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 201216, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 1380864, | |
| "linear_total": 7077888, | |
| "nnz": 1386755, | |
| "total": 7086720 | |
| } | |
| }, | |
| "linear_nnz": 25746432, | |
| "linear_sparsity": 69.68677662037037, | |
| "linear_total": 84934656, | |
| "nnz": 49662908, | |
| "pruned_heads": { | |
| "0": [0, 2, 4, 5, 6], | |
| "1": [0, 2, 3, 5, 6, 7, 8], | |
| "10": [1, 2, 4, 5, 6, 7, 8], | |
| "11": [0, 5, 7, 8, 10, 11], | |
| "2": [8, 4, 7], | |
| "3": [2, 4, 6], | |
| "4": [1, 2], | |
| "5": [1, 2, 6, 7, 11], | |
| "6": [3, 10, 2], | |
| "7": [1, 3, 6, 7, 11], | |
| "8": [0, 3, 4], | |
| "9": [1, 4, 5, 7, 9, 10] | |
| }, | |
| "total": 108882626, | |
| "total_sparsity": 54.38858353765275 | |
| }, | |
| "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_9_fullpatch6/", | |
| "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_9_fullpatch6/", | |
| "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_9_fullpatch6/", | |
| "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 | |
| } | |
| } |