| { | |
| "checkpoint_path": "/data_2to/devel_data/nn_pruning/output/squad_test_final_fine_tune/fine_tuned_hp_od-output__squad_test3_es-steps_nte20_ls250_est5000_rn-output__squad_test3_dpm-sigmoied_threshold:1d_alt_apme-sigmoied_threshold_aowd0_bm1_abr32_abc32_it0_fw10_r-l1_rfl20_dl0.25_dtnop-csarron__bert-base-uncased-squad-v1/checkpoint-22132", | |
| "config": { | |
| "_name_or_path": "/tmp/tmp61klxvbz", | |
| "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, 9, 11], | |
| "1": [0, 2, 3, 5, 6, 7, 8, 9], | |
| "10": [1, 4, 5, 6, 7, 8, 9], | |
| "11": [0, 2, 3, 5, 6, 7, 8, 10, 11], | |
| "2": [1, 2, 4, 7, 8, 11], | |
| "3": [2, 4, 6, 7, 10], | |
| "4": [0, 1, 2, 6, 11], | |
| "5": [0, 1, 2, 5, 6, 7, 11], | |
| "6": [0, 2, 3, 4, 7, 10], | |
| "7": [1, 3, 6, 7, 11], | |
| "8": [0, 1, 2, 3, 4, 6, 8], | |
| "9": [1, 3, 4, 5, 7, 9, 10] | |
| }, | |
| "type_vocab_size": 2, | |
| "vocab_size": 30522 | |
| }, | |
| "eval_metrics": { | |
| "exact_match": 80.02838221381268, | |
| "f1": 87.70940223967354, | |
| "main_metric": 87.70940223967354 | |
| }, | |
| "model_args": { | |
| "cache_dir": null, | |
| "config_name": null, | |
| "model_name_or_path": "/home/lagunas/devel/hf/nn_pruning/nn_pruning/analysis/tmp_finetune", | |
| "tokenizer_name": null | |
| }, | |
| "source_checkpoint": "/data_2to/devel_data/nn_pruning/output/squad_test3/hp_od-output__squad_test3_es-steps_nte20_ls250_est5000_rn-output__squad_test3_dpm-sigmoied_threshold:1d_alt_apme-sigmoied_threshold_aowd0_bm1_abr32_abc32_it0_fw10_r-l1_rfl20_dl0.25_dtnop-csarron__bert-base-uncased-squad-v1/checkpoint-90000", | |
| "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": "topK", | |
| "bias_mask": true, | |
| "dense_block_cols": 1, | |
| "dense_block_rows": 1, | |
| "dense_lambda": 1.0, | |
| "dense_pruning_method": "topK", | |
| "distil_alpha_ce": 0.1, | |
| "distil_alpha_teacher": 0.9, | |
| "distil_teacher_name_or_path": "csarron/bert-base-uncased-squad-v1", | |
| "distil_temperature": 2.0, | |
| "final_ampere_temperature": 20.0, | |
| "final_finetune": 1, | |
| "final_threshold": 0.5, | |
| "final_warmup": 0, | |
| "initial_ampere_temperature": 0.0, | |
| "initial_threshold": 1.0, | |
| "initial_warmup": 0, | |
| "mask_init": "constant", | |
| "mask_scale": 0.0, | |
| "mask_scores_learning_rate": 0.01, | |
| "regularization": "", | |
| "regularization_final_lambda": 0 | |
| }, | |
| "speed": { | |
| "cuda_eval_elapsed_time": 15.838374267578125, | |
| "eval_elapsed_time": 22.999519595876336 | |
| }, | |
| "speedup": 2.436764806371294, | |
| "stats": { | |
| "layers": { | |
| "0": { | |
| "linear_attention_nnz": 786432, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 847872, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 1634304, | |
| "linear_total": 7077888, | |
| "nnz": 1640232, | |
| "total": 7086336 | |
| }, | |
| "1": { | |
| "linear_attention_nnz": 786432, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 1101312, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 1887744, | |
| "linear_total": 7077888, | |
| "nnz": 1893837, | |
| "total": 7086336 | |
| }, | |
| "10": { | |
| "linear_attention_nnz": 983040, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 147456, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 1130496, | |
| "linear_total": 7077888, | |
| "nnz": 1136160, | |
| "total": 7086528 | |
| }, | |
| "11": { | |
| "linear_attention_nnz": 589824, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 365568, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 955392, | |
| "linear_total": 7077888, | |
| "nnz": 960814, | |
| "total": 7086144 | |
| }, | |
| "2": { | |
| "linear_attention_nnz": 1179648, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 1221120, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 2400768, | |
| "linear_total": 7077888, | |
| "nnz": 2407323, | |
| "total": 7086720 | |
| }, | |
| "3": { | |
| "linear_attention_nnz": 1376256, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 1211904, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 2588160, | |
| "linear_total": 7077888, | |
| "nnz": 2594901, | |
| "total": 7086912 | |
| }, | |
| "4": { | |
| "linear_attention_nnz": 1376256, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 1279488, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 2655744, | |
| "linear_total": 7077888, | |
| "nnz": 2662529, | |
| "total": 7086912 | |
| }, | |
| "5": { | |
| "linear_attention_nnz": 983040, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 1216512, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 2199552, | |
| "linear_total": 7077888, | |
| "nnz": 2205912, | |
| "total": 7086528 | |
| }, | |
| "6": { | |
| "linear_attention_nnz": 1179648, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 952320, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 2131968, | |
| "linear_total": 7077888, | |
| "nnz": 2138348, | |
| "total": 7086720 | |
| }, | |
| "7": { | |
| "linear_attention_nnz": 1376256, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 715776, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 2092032, | |
| "linear_total": 7077888, | |
| "nnz": 2098450, | |
| "total": 7086912 | |
| }, | |
| "8": { | |
| "linear_attention_nnz": 983040, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 434688, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 1417728, | |
| "linear_total": 7077888, | |
| "nnz": 1423579, | |
| "total": 7086528 | |
| }, | |
| "9": { | |
| "linear_attention_nnz": 983040, | |
| "linear_attention_total": 2359296, | |
| "linear_dense_nnz": 172032, | |
| "linear_dense_total": 4718592, | |
| "linear_nnz": 1155072, | |
| "linear_total": 7077888, | |
| "nnz": 1160752, | |
| "total": 7086528 | |
| } | |
| }, | |
| "linear_nnz": 22248960, | |
| "linear_sparsity": 73.80461516203704, | |
| "linear_total": 84934656, | |
| "nnz": 46161559, | |
| "pruned_heads": { | |
| "0": [0, 2, 4, 5, 6, 7, 9, 11], | |
| "1": [0, 2, 3, 5, 6, 7, 8, 9], | |
| "10": [1, 4, 5, 6, 7, 8, 9], | |
| "11": [0, 2, 3, 5, 6, 7, 8, 10, 11], | |
| "2": [1, 2, 4, 7, 8, 11], | |
| "3": [2, 4, 6, 7, 10], | |
| "4": [0, 1, 2, 6, 11], | |
| "5": [0, 1, 2, 5, 6, 7, 11], | |
| "6": [0, 2, 3, 4, 7, 10], | |
| "7": [1, 3, 6, 7, 11], | |
| "8": [0, 1, 2, 3, 4, 6, 8], | |
| "9": [1, 3, 4, 5, 7, 9, 10] | |
| }, | |
| "total": 108877826, | |
| "total_sparsity": 57.602424023418685 | |
| }, | |
| "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": 2500, | |
| "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_final_fine_tune/fine_tuned_hp_od-output__squad_test3_es-steps_nte20_ls250_est5000_rn-output__squad_test3_dpm-sigmoied_threshold:1d_alt_apme-sigmoied_threshold_aowd0_bm1_abr32_abc32_it0_fw10_r-l1_rfl20_dl0.25_dtnop-csarron__bert-base-uncased-squad-v1", | |
| "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": 4, | |
| "optimize_model_before_eval": "disabled", | |
| "output_dir": "/data_2to/devel_data/nn_pruning/output/squad_test_final_fine_tune/fine_tuned_hp_od-output__squad_test3_es-steps_nte20_ls250_est5000_rn-output__squad_test3_dpm-sigmoied_threshold:1d_alt_apme-sigmoied_threshold_aowd0_bm1_abr32_abc32_it0_fw10_r-l1_rfl20_dl0.25_dtnop-csarron__bert-base-uncased-squad-v1", | |
| "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_final_fine_tune/fine_tuned_hp_od-output__squad_test3_es-steps_nte20_ls250_est5000_rn-output__squad_test3_dpm-sigmoied_threshold:1d_alt_apme-sigmoied_threshold_aowd0_bm1_abr32_abc32_it0_fw10_r-l1_rfl20_dl0.25_dtnop-csarron__bert-base-uncased-squad-v1", | |
| "save_steps": 2500, | |
| "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": 10, | |
| "weight_decay": 0.0 | |
| } | |
| } |