06/19/2024 22:00:21 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: False 06/19/2024 22:00:21 - INFO - __main__ - Training/evaluation parameters TrainingArguments( _n_gpu=1, adafactor=False, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, auto_find_batch_size=False, bf16=False, bf16_full_eval=False, data_seed=None, dataloader_drop_last=False, dataloader_num_workers=0, dataloader_pin_memory=True, ddp_bucket_cap_mb=None, ddp_find_unused_parameters=None, ddp_timeout=1800, debug=[], deepspeed=None, disable_tqdm=False, do_eval=False, do_predict=True, do_train=False, eval_accumulation_steps=None, eval_delay=0, eval_steps=None, evaluation_strategy=no, fp16=False, fp16_backend=auto, fp16_full_eval=False, fp16_opt_level=O1, fsdp=[], fsdp_min_num_params=0, fsdp_transformer_layer_cls_to_wrap=None, full_determinism=False, gradient_accumulation_steps=1, gradient_checkpointing=False, greater_is_better=None, group_by_length=False, half_precision_backend=auto, hub_model_id=None, hub_private_repo=False, hub_strategy=every_save, hub_token=, ignore_data_skip=False, include_inputs_for_metrics=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, learning_rate=5e-05, length_column_name=length, load_best_model_at_end=False, local_rank=-1, log_level=passive, log_level_replica=passive, log_on_each_node=True, logging_dir=/projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41/runs/Jun19_22-00-21_ppi-nlp6, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=500, logging_strategy=steps, lr_scheduler_type=linear, max_grad_norm=1.0, max_steps=-1, metric_for_best_model=None, mp_parameters=, no_cuda=False, num_train_epochs=3.0, optim=adamw_hf, optim_args=None, output_dir=/projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41, overwrite_output_dir=False, past_index=-1, per_device_eval_batch_size=4, per_device_train_batch_size=8, prediction_loss_only=False, push_to_hub=False, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=, ray_scope=last, remove_unused_columns=True, report_to=[], resume_from_checkpoint=None, run_name=/projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41, save_on_each_node=False, save_steps=500, save_strategy=steps, save_total_limit=None, seed=42, sharded_ddp=[], skip_memory_metrics=True, tf32=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.0, warmup_steps=0, weight_decay=0.0, xpu_backend=None, ) /home/ext_maiara_frodrigues2000_gmail_/.pyenv/versions/spokennlp/lib/python3.8/site-packages/datasets/load.py:2555: FutureWarning: 'ignore_verifications' was deprecated in favor of 'verification_mode' in version 2.9.1 and will be removed in 3.0.0. You can remove this warning by passing 'verification_mode=no_checks' instead. warnings.warn( /home/ext_maiara_frodrigues2000_gmail_/.pyenv/versions/spokennlp/lib/python3.8/site-packages/datasets/load.py:929: FutureWarning: The repository for wiki_section_city contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at ./src/datasets/wiki_section_city/wiki_section_city.py You can avoid this message in future by passing the argument `trust_remote_code=True`. Passing `trust_remote_code=True` will be mandatory to load this dataset from the next major release of `datasets`. warnings.warn( No config specified, defaulting to the single config: wiki_section_city/WikiSectionCityForDocumentSegmentation 06/19/2024 22:00:21 - INFO - datasets.builder - No config specified, defaulting to the single config: wiki_section_city/WikiSectionCityForDocumentSegmentation Using custom data configuration WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad 06/19/2024 22:00:21 - INFO - datasets.builder - Using custom data configuration WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad Loading Dataset Infos from /home/ext_luti4497_gmail_com/.cache/huggingface/modules/datasets_modules/datasets/wiki_section_city/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4 06/19/2024 22:00:21 - INFO - datasets.info - Loading Dataset Infos from /home/ext_luti4497_gmail_com/.cache/huggingface/modules/datasets_modules/datasets/wiki_section_city/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4 Generating dataset wiki_section_city (/projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4) 06/19/2024 22:00:21 - INFO - datasets.builder - Generating dataset wiki_section_city (/projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4) Downloading and preparing dataset wiki_section_city/WikiSectionCityForDocumentSegmentation to /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4... 06/19/2024 22:00:21 - INFO - datasets.builder - Downloading and preparing dataset wiki_section_city/WikiSectionCityForDocumentSegmentation to /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4... Downloading took 0.0 min 06/19/2024 22:00:21 - INFO - datasets.download.download_manager - Downloading took 0.0 min Checksum Computation took 0.0 min 06/19/2024 22:00:21 - INFO - datasets.download.download_manager - Checksum Computation took 0.0 min Generating train split 06/19/2024 22:00:21 - INFO - datasets.builder - Generating train split Generating train split: 0 examples [00:00, ? examples/s] Generating train split: 1 examples [00:00, 1.88 examples/s] Generating train split: 174 examples [00:00, 366.96 examples/s] Generating train split: 332 examples [00:00, 647.83 examples/s] Generating train split: 497 examples [00:00, 889.10 examples/s] Generating train split: 684 examples [00:00, 1141.68 examples/s] Generating train split: 873 examples [00:01, 1341.00 examples/s] Generating train split: 1086 examples [00:01, 1212.55 examples/s] Generating train split: 1257 examples [00:01, 1324.98 examples/s] Generating train split: 1459 examples [00:01, 1496.72 examples/s] Generating train split: 1642 examples [00:01, 1581.27 examples/s] Generating train split: 1815 examples [00:01, 1615.68 examples/s] Generating train split: 2000 examples [00:01, 1338.66 examples/s] Generating train split: 2170 examples [00:01, 1423.52 examples/s] Generating train split: 2420 examples [00:02, 1504.76 examples/s] Generating train split: 2632 examples [00:02, 1471.35 examples/s] Generating train split: 2843 examples [00:02, 1619.36 examples/s] Generating train split: 3074 examples [00:02, 1345.54 examples/s] Generating train split: 3246 examples [00:02, 1419.60 examples/s] Generating train split: 3444 examples [00:02, 1548.34 examples/s] Generating train split: 3631 examples [00:02, 1622.73 examples/s] Generating train split: 3807 examples [00:02, 1647.77 examples/s] Generating train split: 4000 examples [00:03, 1339.79 examples/s] Generating train split: 4221 examples [00:03, 1378.81 examples/s] Generating train split: 4394 examples [00:03, 1450.17 examples/s] Generating train split: 4581 examples [00:03, 1551.81 examples/s] Generating train split: 4746 examples [00:03, 1577.15 examples/s] Generating train split: 4915 examples [00:03, 1601.50 examples/s] Generating train split: 5083 examples [00:03, 1406.14 examples/s] Generating train split: 5256 examples [00:03, 1480.60 examples/s] Generating train split: 5424 examples [00:04, 1525.76 examples/s] Generating train split: 5615 examples [00:04, 1626.54 examples/s] Generating train split: 5847 examples [00:04, 1819.32 examples/s] Generating train split: 6096 examples [00:04, 1628.07 examples/s] Generating train split: 6318 examples [00:04, 1772.44 examples/s] Generating train split: 6511 examples [00:04, 1812.82 examples/s] Generating train split: 6751 examples [00:04, 1732.66 examples/s] Generating train split: 7000 examples [00:05, 1480.66 examples/s] Generating train split: 7170 examples [00:05, 1525.90 examples/s] Generating train split: 7335 examples [00:05, 1552.06 examples/s] Generating train split: 7520 examples [00:05, 1614.80 examples/s] Generating train split: 7698 examples [00:05, 1655.31 examples/s] Generating train split: 7949 examples [00:05, 1657.55 examples/s] Generating train split: 8177 examples [00:05, 1419.31 examples/s] Generating train split: 8352 examples [00:05, 1484.50 examples/s] Generating train split: 8512 examples [00:06, 1501.58 examples/s] Generating train split: 8729 examples [00:06, 1667.42 examples/s] Generating train split: 8910 examples [00:06, 1705.12 examples/s] Generating train split: 9165 examples [00:06, 1438.58 examples/s] Generating train split: 9330 examples [00:06, 1483.22 examples/s] Generating train split: 9501 examples [00:06, 1533.76 examples/s] Generating train split: 9668 examples [00:06, 1565.15 examples/s] Generating train split: 9880 examples [00:06, 1712.02 examples/s] Generating train split: 10074 examples [00:07, 1392.32 examples/s] Generating train split: 10320 examples [00:07, 1464.61 examples/s] Generating train split: 10484 examples [00:07, 1500.61 examples/s] Generating train split: 10706 examples [00:07, 1488.11 examples/s] Generating train split: 10890 examples [00:07, 1561.42 examples/s] Generating train split: 11088 examples [00:07, 1344.40 examples/s] Generating train split: 11272 examples [00:07, 1451.97 examples/s] Generating train split: 11444 examples [00:07, 1510.27 examples/s] Generating train split: 11637 examples [00:08, 1616.70 examples/s] Generating train split: 11810 examples [00:08, 1644.38 examples/s] Generating train split: 11996 examples [00:08, 1703.68 examples/s] Generating train split: 12185 examples [00:08, 1474.44 examples/s] Generating train split: 12353 examples [00:08, 1522.07 examples/s] Generating train split: 12557 examples [00:08, 1656.48 examples/s] Generating train split: 12739 examples [00:08, 1699.51 examples/s] Generating train split: 12918 examples [00:08, 1721.07 examples/s] Generating train split: 13182 examples [00:09, 1494.64 examples/s] Generating train split: 13355 examples [00:09, 1549.45 examples/s] Generating train split: 13579 examples [00:09, 1719.46 examples/s] Generating train split: 13672 examples [00:09, 1464.90 examples/s] Generating validation split topic_segmentation 06/19/2024 22:00:31 - INFO - datasets.builder - Generating validation split Generating validation split: 0 examples [00:00, ? examples/s] Generating validation split: 69 examples [00:00, 579.82 examples/s] Generating validation split: 218 examples [00:00, 1069.82 examples/s] Generating validation split: 373 examples [00:00, 1276.30 examples/s] Generating validation split: 520 examples [00:00, 1341.50 examples/s] Generating validation split: 703 examples [00:00, 1510.53 examples/s] Generating validation split: 881 examples [00:00, 1597.28 examples/s] Generating validation split: 1071 examples [00:00, 1270.73 examples/s] Generating validation split: 1274 examples [00:00, 1464.39 examples/s] Generating validation split: 1467 examples [00:01, 1587.66 examples/s] Generating validation split: 1713 examples [00:01, 1601.55 examples/s] Generating validation split: 1906 examples [00:01, 1677.42 examples/s] Generating validation split: 1950 examples [00:01, 1426.26 examples/s] Generating test split topic_segmentation 06/19/2024 22:00:32 - INFO - datasets.builder - Generating test split Generating test split: 0 examples [00:00, ? examples/s] Generating test split: 1 examples [00:00, 7.47 examples/s] Generating test split: 159 examples [00:00, 810.44 examples/s] Generating test split: 302 examples [00:00, 1066.26 examples/s] Generating test split: 477 examples [00:00, 1316.18 examples/s] Generating test split: 663 examples [00:00, 1501.87 examples/s] Generating test split: 826 examples [00:00, 1538.20 examples/s] Generating test split: 1000 examples [00:00, 1257.60 examples/s] Generating test split: 1151 examples [00:00, 1322.06 examples/s] Generating test split: 1322 examples [00:01, 1425.72 examples/s] Generating test split: 1495 examples [00:01, 1508.46 examples/s] Generating test split: 1683 examples [00:01, 1610.97 examples/s] Generating test split: 1891 examples [00:01, 1745.28 examples/s] Generating test split: 2077 examples [00:01, 1408.22 examples/s] Generating test split: 2256 examples [00:01, 1500.50 examples/s] Generating test split: 2427 examples [00:01, 1543.24 examples/s] Generating test split: 2619 examples [00:01, 1644.22 examples/s] Generating test split: 2837 examples [00:01, 1571.16 examples/s] Generating test split: 3071 examples [00:02, 1378.60 examples/s] Generating test split: 3265 examples [00:02, 1501.05 examples/s] Generating test split: 3458 examples [00:02, 1601.68 examples/s] Generating test split: 3718 examples [00:02, 1630.09 examples/s] Generating test split: 3897 examples [00:02, 1666.47 examples/s] Generating test split: 3904 examples [00:02, 1445.18 examples/s] Dataset wiki_section_city downloaded and prepared to /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4. Subsequent calls will reuse this data. topic_segmentation 06/19/2024 22:00:35 - INFO - datasets.builder - Dataset wiki_section_city downloaded and prepared to /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4. Subsequent calls will reuse this data. [INFO|configuration_utils.py:658] 2024-06-19 22:00:36,128 >> loading configuration file /projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41/config.json [INFO|configuration_utils.py:712] 2024-06-19 22:00:36,132 >> Model config BertConfig { "_name_or_path": "/projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41", "architectures": [ "BertWithDAForSentenceLabelingTopicSegmentation" ], "attention_probs_dropout_prob": 0.1, "cache_dir": null, "cl_anchor_level": "eop_list", "cl_loss_weight": 0.5, "cl_negative_k": 3, "cl_positive_k": 1, "cl_temp": 0.1, "classifier_dropout": null, "config_name": null, "directionality": "bidi", "do_cssl": true, "do_da_ts": true, "do_tssp": true, "finetuning_task": "topic_segment", "focal_loss_gamma": 0.0, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 1024, "id2label": { "0": "B-EOP", "1": "O" }, "ignore_mismatched_sizes": false, "initializer_range": 0.02, "intermediate_size": 4096, "label2id": { "B-EOP": 0, "O": 1 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_name_or_path": "neuralmind/bert-large-portuguese-cased", "model_revision": "main", "model_type": "bert", "num_attention_heads": 16, "num_gpu": 1, "num_hidden_layers": 24, "num_topic_labels": 0, "num_tssp_labels": 3, "output_past": true, "pad_token_id": 0, "pooler_fc_size": 768, "pooler_num_attention_heads": 12, "pooler_num_fc_layers": 3, "pooler_size_per_head": 128, "pooler_type": "first_token_transform", "position_embedding_type": "absolute", "sentence_pooler_type": null, "tokenizer_name": null, "torch_dtype": "float32", "transformers_version": "4.26.0", "ts_loss_weight": 1.0, "ts_score_predictor": "lt", "ts_score_predictor_cos_temp": 1, "tssp_ablation": "none", "tssp_loss_weight": 1.0, "type_vocab_size": 2, "use_auth_token": false, "use_cache": true, "vocab_size": 29795, "weight_label_zero": 0.5 } [INFO|tokenization_utils_base.py:1800] 2024-06-19 22:00:36,145 >> loading file vocab.txt [INFO|tokenization_utils_base.py:1800] 2024-06-19 22:00:36,145 >> loading file tokenizer.json [INFO|tokenization_utils_base.py:1800] 2024-06-19 22:00:36,145 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:1800] 2024-06-19 22:00:36,145 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:1800] 2024-06-19 22:00:36,145 >> loading file tokenizer_config.json [INFO|modeling_utils.py:2272] 2024-06-19 22:00:36,225 >> loading weights file /projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41/pytorch_model.bin [INFO|modeling_utils.py:2857] 2024-06-19 22:01:00,370 >> All model checkpoint weights were used when initializing BertWithDAForSentenceLabelingTopicSegmentation. [INFO|modeling_utils.py:2865] 2024-06-19 22:01:00,370 >> All the weights of BertWithDAForSentenceLabelingTopicSegmentation were initialized from the model checkpoint at /projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41. If your task is similar to the task the model of the checkpoint was trained on, you can already use BertWithDAForSentenceLabelingTopicSegmentation for predictions without further training. Process #0 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00000_of_00005.arrow labels_are_int: False label_to_id: {'B-EOP': 0, 'O': 1} config: BertConfig { "_name_or_path": "/projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41", "architectures": [ "BertWithDAForSentenceLabelingTopicSegmentation" ], "attention_probs_dropout_prob": 0.1, "cache_dir": null, "cl_anchor_level": "eop_matrix", "cl_loss_weight": 0.0, "cl_negative_k": 1, "cl_positive_k": 1, "cl_temp": 1, "classifier_dropout": null, "config_name": null, "directionality": "bidi", "do_cssl": false, "do_da_ts": false, "do_tssp": false, "finetuning_task": "topic_segment", "focal_loss_gamma": 0.0, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 1024, "id2label": { "0": "B-EOP", "1": "O" }, "ignore_mismatched_sizes": false, "initializer_range": 0.02, "intermediate_size": 4096, "label2id": { "B-EOP": 0, "O": 1 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_name_or_path": "/projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41", "model_revision": "main", "model_type": "bert", "num_attention_heads": 16, "num_gpu": 1, "num_hidden_layers": 24, "num_topic_labels": 0, "num_tssp_labels": 3, "output_past": true, "pad_token_id": 0, "pooler_fc_size": 768, "pooler_num_attention_heads": 12, "pooler_num_fc_layers": 3, "pooler_size_per_head": 128, "pooler_type": "first_token_transform", "position_embedding_type": "absolute", "sentence_pooler_type": null, "tokenizer_name": null, "torch_dtype": "float32", "transformers_version": "4.26.0", "ts_loss_weight": 1.0, "ts_score_predictor": "lt", "ts_score_predictor_cos_temp": 1, "tssp_ablation": "none", "tssp_loss_weight": 0.0, "type_vocab_size": 2, "use_auth_token": false, "use_cache": true, "vocab_size": 29795, "weight_label_zero": 0.5 } model_type: bert final max_seq_length: 512 label_list: ['B-EOP', 'O'] 06/19/2024 22:01:00 - INFO - datasets.arrow_dataset - Process #0 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00000_of_00005.arrow Process #1 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00001_of_00005.arrow 06/19/2024 22:01:00 - INFO - datasets.arrow_dataset - Process #1 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00001_of_00005.arrow Process #2 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00002_of_00005.arrow 06/19/2024 22:01:00 - INFO - datasets.arrow_dataset - Process #2 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00002_of_00005.arrow Process #3 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00003_of_00005.arrow 06/19/2024 22:01:00 - INFO - datasets.arrow_dataset - Process #3 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00003_of_00005.arrow Process #4 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00004_of_00005.arrow 06/19/2024 22:01:00 - INFO - datasets.arrow_dataset - Process #4 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00004_of_00005.arrow Spawning 5 processes 06/19/2024 22:01:00 - INFO - datasets.arrow_dataset - Spawning 5 processes Running tokenizer on prediction dataset (num_proc=5): 0%| | 0/3904 [00:00, ignore_data_skip=False, include_inputs_for_metrics=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, learning_rate=5e-05, length_column_name=length, load_best_model_at_end=False, local_rank=-1, log_level=passive, log_level_replica=passive, log_on_each_node=True, logging_dir=/projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41/runs/Jun19_22-01-19_ppi-nlp6, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=500, logging_strategy=steps, lr_scheduler_type=linear, max_grad_norm=1.0, max_steps=-1, metric_for_best_model=None, mp_parameters=, no_cuda=False, num_train_epochs=3.0, optim=adamw_hf, optim_args=None, output_dir=/projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41, overwrite_output_dir=False, past_index=-1, per_device_eval_batch_size=4, per_device_train_batch_size=8, prediction_loss_only=False, push_to_hub=False, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=, ray_scope=last, remove_unused_columns=True, report_to=[], resume_from_checkpoint=None, run_name=/projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41, save_on_each_node=False, save_steps=500, save_strategy=steps, save_total_limit=None, seed=42, sharded_ddp=[], skip_memory_metrics=True, tf32=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.0, warmup_steps=0, weight_decay=0.0, xpu_backend=None, ) /home/ext_maiara_frodrigues2000_gmail_/.pyenv/versions/spokennlp/lib/python3.8/site-packages/datasets/load.py:2555: FutureWarning: 'ignore_verifications' was deprecated in favor of 'verification_mode' in version 2.9.1 and will be removed in 3.0.0. You can remove this warning by passing 'verification_mode=no_checks' instead. warnings.warn( /home/ext_maiara_frodrigues2000_gmail_/.pyenv/versions/spokennlp/lib/python3.8/site-packages/datasets/load.py:929: FutureWarning: The repository for wiki_section_city contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at ./src/datasets/wiki_section_city/wiki_section_city.py You can avoid this message in future by passing the argument `trust_remote_code=True`. Passing `trust_remote_code=True` will be mandatory to load this dataset from the next major release of `datasets`. warnings.warn( No config specified, defaulting to the single config: wiki_section_city/WikiSectionCityForDocumentSegmentation 06/19/2024 22:01:19 - INFO - datasets.builder - No config specified, defaulting to the single config: wiki_section_city/WikiSectionCityForDocumentSegmentation Using custom data configuration WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad 06/19/2024 22:01:19 - INFO - datasets.builder - Using custom data configuration WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad Loading Dataset Infos from /home/ext_luti4497_gmail_com/.cache/huggingface/modules/datasets_modules/datasets/wiki_section_city/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4 06/19/2024 22:01:19 - INFO - datasets.info - Loading Dataset Infos from /home/ext_luti4497_gmail_com/.cache/huggingface/modules/datasets_modules/datasets/wiki_section_city/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4 Generating dataset wiki_section_city (/projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4) 06/19/2024 22:01:19 - INFO - datasets.builder - Generating dataset wiki_section_city (/projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4) Downloading and preparing dataset wiki_section_city/WikiSectionCityForDocumentSegmentation to /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4... 06/19/2024 22:01:19 - INFO - datasets.builder - Downloading and preparing dataset wiki_section_city/WikiSectionCityForDocumentSegmentation to /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4... Downloading took 0.0 min 06/19/2024 22:01:19 - INFO - datasets.download.download_manager - Downloading took 0.0 min Checksum Computation took 0.0 min 06/19/2024 22:01:19 - INFO - datasets.download.download_manager - Checksum Computation took 0.0 min Generating train split 06/19/2024 22:01:19 - INFO - datasets.builder - Generating train split Generating train split: 0 examples [00:00, ? examples/s] Generating train split: 1 examples [00:00, 1.86 examples/s] Generating train split: 164 examples [00:00, 344.11 examples/s] Generating train split: 327 examples [00:00, 640.15 examples/s] Generating train split: 487 examples [00:00, 873.61 examples/s] Generating train split: 676 examples [00:00, 1135.01 examples/s] Generating train split: 865 examples [00:01, 1332.98 examples/s] Generating train split: 1085 examples [00:01, 1203.80 examples/s] Generating train split: 1249 examples [00:01, 1302.58 examples/s] Generating train split: 1444 examples [00:01, 1462.41 examples/s] Generating train split: 1623 examples [00:01, 1548.04 examples/s] Generating train split: 1873 examples [00:01, 1581.85 examples/s] Generating train split: 2088 examples [00:01, 1354.26 examples/s] Generating train split: 2312 examples [00:02, 1394.05 examples/s] Generating train split: 2488 examples [00:02, 1474.50 examples/s] Generating train split: 2715 examples [00:02, 1477.61 examples/s] Generating train split: 2901 examples [00:02, 1564.50 examples/s] Generating train split: 3075 examples [00:02, 1305.09 examples/s] Generating train split: 3244 examples [00:02, 1387.65 examples/s] Generating train split: 3439 examples [00:02, 1520.39 examples/s] Generating train split: 3612 examples [00:02, 1573.60 examples/s] Generating train split: 3783 examples [00:03, 1607.63 examples/s] Generating train split: 4000 examples [00:03, 1339.28 examples/s] Generating train split: 4170 examples [00:03, 1418.57 examples/s] Generating train split: 4362 examples [00:03, 1541.76 examples/s] Generating train split: 4561 examples [00:03, 1657.36 examples/s] Generating train split: 4740 examples [00:03, 1670.80 examples/s] Generating train split: 4920 examples [00:03, 1704.66 examples/s] Generating train split: 5191 examples [00:03, 1556.63 examples/s] Generating train split: 5381 examples [00:04, 1638.00 examples/s] Generating train split: 5553 examples [00:04, 1658.23 examples/s] Generating train split: 5781 examples [00:04, 1823.54 examples/s] Generating train split: 5979 examples [00:04, 1854.55 examples/s] Generating train split: 6222 examples [00:04, 1685.10 examples/s] Generating train split: 6410 examples [00:04, 1721.16 examples/s] Generating train split: 6649 examples [00:04, 1673.17 examples/s] Generating train split: 6887 examples [00:04, 1638.36 examples/s] Generating train split: 7083 examples [00:05, 1427.36 examples/s] Generating train split: 7245 examples [00:05, 1469.27 examples/s] Generating train split: 7409 examples [00:05, 1508.98 examples/s] Generating train split: 7593 examples [00:05, 1584.40 examples/s] Generating train split: 7762 examples [00:05, 1609.11 examples/s] Generating train split: 7937 examples [00:05, 1641.42 examples/s] Generating train split: 8168 examples [00:05, 1348.83 examples/s] Generating train split: 8322 examples [00:05, 1391.53 examples/s] Generating train split: 8551 examples [00:06, 1432.31 examples/s] Generating train split: 8771 examples [00:06, 1602.43 examples/s] Generating train split: 8952 examples [00:06, 1646.20 examples/s] Generating train split: 9160 examples [00:06, 1403.59 examples/s] Generating train split: 9318 examples [00:06, 1438.63 examples/s] Generating train split: 9489 examples [00:06, 1503.82 examples/s] Generating train split: 9651 examples [00:06, 1526.44 examples/s] Generating train split: 9857 examples [00:06, 1665.31 examples/s] Generating train split: 10070 examples [00:07, 1373.33 examples/s] Generating train split: 10315 examples [00:07, 1442.57 examples/s] Generating train split: 10479 examples [00:07, 1485.39 examples/s] Generating train split: 10704 examples [00:07, 1483.83 examples/s] Generating train split: 10894 examples [00:07, 1577.27 examples/s] Generating train split: 11092 examples [00:07, 1361.95 examples/s] Generating train split: 11277 examples [00:07, 1468.39 examples/s] Generating train split: 11445 examples [00:08, 1516.88 examples/s] Generating train split: 11632 examples [00:08, 1600.38 examples/s] Generating train split: 11807 examples [00:08, 1633.90 examples/s] Generating train split: 11993 examples [00:08, 1693.04 examples/s] Generating train split: 12178 examples [00:08, 1428.25 examples/s] Generating train split: 12338 examples [00:08, 1445.53 examples/s] Generating train split: 12543 examples [00:08, 1600.38 examples/s] Generating train split: 12734 examples [00:08, 1673.56 examples/s] Generating train split: 12919 examples [00:08, 1718.61 examples/s] Generating train split: 13173 examples [00:09, 1473.04 examples/s] Generating train split: 13349 examples [00:09, 1539.35 examples/s] Generating train split: 13549 examples [00:09, 1642.87 examples/s] Generating train split: 13672 examples [00:09, 1454.41 examples/s] Generating validation split topic_segmentation 06/19/2024 22:01:28 - INFO - datasets.builder - Generating validation split Generating validation split: 0 examples [00:00, ? examples/s] Generating validation split: 69 examples [00:00, 608.54 examples/s] Generating validation split: 217 examples [00:00, 1089.66 examples/s] Generating validation split: 367 examples [00:00, 1264.36 examples/s] Generating validation split: 524 examples [00:00, 1378.19 examples/s] Generating validation split: 703 examples [00:00, 1519.31 examples/s] Generating validation split: 869 examples [00:00, 1565.22 examples/s] Generating validation split: 1068 examples [00:00, 1252.69 examples/s] Generating validation split: 1271 examples [00:00, 1448.10 examples/s] Generating validation split: 1464 examples [00:01, 1575.39 examples/s] Generating validation split: 1713 examples [00:01, 1595.15 examples/s] Generating validation split: 1906 examples [00:01, 1673.40 examples/s] Generating validation split: 1950 examples [00:01, 1431.59 examples/s] Generating test split topic_segmentation 06/19/2024 22:01:30 - INFO - datasets.builder - Generating test split Generating test split: 0 examples [00:00, ? examples/s] Generating test split: 1 examples [00:00, 8.19 examples/s] Generating test split: 155 examples [00:00, 825.12 examples/s] Generating test split: 295 examples [00:00, 1071.91 examples/s] Generating test split: 465 examples [00:00, 1308.99 examples/s] Generating test split: 648 examples [00:00, 1489.93 examples/s] Generating test split: 814 examples [00:00, 1542.01 examples/s] Generating test split: 986 examples [00:00, 1591.45 examples/s] Generating test split: 1152 examples [00:00, 1267.31 examples/s] Generating test split: 1321 examples [00:01, 1376.15 examples/s] Generating test split: 1495 examples [00:01, 1471.51 examples/s] Generating test split: 1682 examples [00:01, 1579.17 examples/s] Generating test split: 1882 examples [00:01, 1693.42 examples/s] Generating test split: 2077 examples [00:01, 1402.70 examples/s] Generating test split: 2257 examples [00:01, 1499.42 examples/s] Generating test split: 2425 examples [00:01, 1540.54 examples/s] Generating test split: 2609 examples [00:01, 1616.79 examples/s] Generating test split: 2835 examples [00:01, 1568.50 examples/s] Generating test split: 3000 examples [00:02, 1364.80 examples/s] Generating test split: 3162 examples [00:02, 1425.57 examples/s] Generating test split: 3367 examples [00:02, 1584.11 examples/s] Generating test split: 3589 examples [00:02, 1523.09 examples/s] Generating test split: 3752 examples [00:02, 1546.15 examples/s] Generating test split: 3904 examples [00:02, 1420.90 examples/s] Dataset wiki_section_city downloaded and prepared to /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4. Subsequent calls will reuse this data. topic_segmentation 06/19/2024 22:01:32 - INFO - datasets.builder - Dataset wiki_section_city downloaded and prepared to /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4. Subsequent calls will reuse this data. [INFO|configuration_utils.py:658] 2024-06-19 22:01:33,637 >> loading configuration file /projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41/config.json [INFO|configuration_utils.py:712] 2024-06-19 22:01:33,641 >> Model config BertConfig { "_name_or_path": "/projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41", "architectures": [ "BertWithDAForSentenceLabelingTopicSegmentation" ], "attention_probs_dropout_prob": 0.1, "cache_dir": null, "cl_anchor_level": "eop_list", "cl_loss_weight": 0.5, "cl_negative_k": 3, "cl_positive_k": 1, "cl_temp": 0.1, "classifier_dropout": null, "config_name": null, "directionality": "bidi", "do_cssl": true, "do_da_ts": true, "do_tssp": true, "finetuning_task": "topic_segment", "focal_loss_gamma": 0.0, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 1024, "id2label": { "0": "B-EOP", "1": "O" }, "ignore_mismatched_sizes": false, "initializer_range": 0.02, "intermediate_size": 4096, "label2id": { "B-EOP": 0, "O": 1 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_name_or_path": "neuralmind/bert-large-portuguese-cased", "model_revision": "main", "model_type": "bert", "num_attention_heads": 16, "num_gpu": 1, "num_hidden_layers": 24, "num_topic_labels": 0, "num_tssp_labels": 3, "output_past": true, "pad_token_id": 0, "pooler_fc_size": 768, "pooler_num_attention_heads": 12, "pooler_num_fc_layers": 3, "pooler_size_per_head": 128, "pooler_type": "first_token_transform", "position_embedding_type": "absolute", "sentence_pooler_type": null, "tokenizer_name": null, "torch_dtype": "float32", "transformers_version": "4.26.0", "ts_loss_weight": 1.0, "ts_score_predictor": "lt", "ts_score_predictor_cos_temp": 1, "tssp_ablation": "none", "tssp_loss_weight": 1.0, "type_vocab_size": 2, "use_auth_token": false, "use_cache": true, "vocab_size": 29795, "weight_label_zero": 0.5 } [INFO|tokenization_utils_base.py:1800] 2024-06-19 22:01:33,643 >> loading file vocab.txt [INFO|tokenization_utils_base.py:1800] 2024-06-19 22:01:33,643 >> loading file tokenizer.json [INFO|tokenization_utils_base.py:1800] 2024-06-19 22:01:33,643 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:1800] 2024-06-19 22:01:33,643 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:1800] 2024-06-19 22:01:33,643 >> loading file tokenizer_config.json [INFO|modeling_utils.py:2272] 2024-06-19 22:01:33,668 >> loading weights file /projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41/pytorch_model.bin [INFO|modeling_utils.py:2857] 2024-06-19 22:01:37,435 >> All model checkpoint weights were used when initializing BertWithDAForSentenceLabelingTopicSegmentation. [INFO|modeling_utils.py:2865] 2024-06-19 22:01:37,436 >> All the weights of BertWithDAForSentenceLabelingTopicSegmentation were initialized from the model checkpoint at /projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41. If your task is similar to the task the model of the checkpoint was trained on, you can already use BertWithDAForSentenceLabelingTopicSegmentation for predictions without further training. Process #0 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00000_of_00005.arrow labels_are_int: False label_to_id: {'B-EOP': 0, 'O': 1} config: BertConfig { "_name_or_path": "/projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41", "architectures": [ "BertWithDAForSentenceLabelingTopicSegmentation" ], "attention_probs_dropout_prob": 0.1, "cache_dir": null, "cl_anchor_level": "eop_matrix", "cl_loss_weight": 0.0, "cl_negative_k": 1, "cl_positive_k": 1, "cl_temp": 1, "classifier_dropout": null, "config_name": null, "directionality": "bidi", "do_cssl": false, "do_da_ts": false, "do_tssp": false, "finetuning_task": "topic_segment", "focal_loss_gamma": 0.0, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 1024, "id2label": { "0": "B-EOP", "1": "O" }, "ignore_mismatched_sizes": false, "initializer_range": 0.02, "intermediate_size": 4096, "label2id": { "B-EOP": 0, "O": 1 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_name_or_path": "/projeto/SpokenNLP/emnlp2023-topic_segmentation/output/neuralmind/bert-large-portuguese-cased-finetune-wiki_section_disease/seed42-seq512-lr5e-05-epoch5-bs4-ts1.0-tssp1.0-cl0.5-2024-05-30_21:01:41", "model_revision": "main", "model_type": "bert", "num_attention_heads": 16, "num_gpu": 1, "num_hidden_layers": 24, "num_topic_labels": 0, "num_tssp_labels": 3, "output_past": true, "pad_token_id": 0, "pooler_fc_size": 768, "pooler_num_attention_heads": 12, "pooler_num_fc_layers": 3, "pooler_size_per_head": 128, "pooler_type": "first_token_transform", "position_embedding_type": "absolute", "sentence_pooler_type": null, "tokenizer_name": null, "torch_dtype": "float32", "transformers_version": "4.26.0", "ts_loss_weight": 1.0, "ts_score_predictor": "lt", "ts_score_predictor_cos_temp": 1, "tssp_ablation": "none", "tssp_loss_weight": 0.0, "type_vocab_size": 2, "use_auth_token": false, "use_cache": true, "vocab_size": 29795, "weight_label_zero": 0.5 } model_type: bert final max_seq_length: 512 label_list: ['B-EOP', 'O'] 06/19/2024 22:01:37 - INFO - datasets.arrow_dataset - Process #0 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00000_of_00005.arrow Process #1 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00001_of_00005.arrow 06/19/2024 22:01:37 - INFO - datasets.arrow_dataset - Process #1 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00001_of_00005.arrow Process #2 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00002_of_00005.arrow 06/19/2024 22:01:37 - INFO - datasets.arrow_dataset - Process #2 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00002_of_00005.arrow Process #3 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00003_of_00005.arrow 06/19/2024 22:01:37 - INFO - datasets.arrow_dataset - Process #3 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00003_of_00005.arrow Process #4 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00004_of_00005.arrow 06/19/2024 22:01:37 - INFO - datasets.arrow_dataset - Process #4 will write at /projeto/SpokenNLP/emnlp2023-topic_segmentation/cached_data/wiki_section_city_neuralmind/bert-large-portuguese-cased_512/wiki_section_city/WikiSectionCityForDocumentSegmentation-15c5ff72c77600ad/1.1.1/cafcd4e7f86f04cfd46e90d782f42526ea3b1d6deab48ae6dcf7f4bab4f252d4/cache-bert_wiki_section_city_512_test_00004_of_00005.arrow Spawning 5 processes 06/19/2024 22:01:37 - INFO - datasets.arrow_dataset - Spawning 5 processes Running tokenizer on prediction dataset (num_proc=5): 0%| | 0/3904 [00:00> The following columns in the test set don't have a corresponding argument in `BertWithDAForSentenceLabelingTopicSegmentation.forward` and have been ignored: sentences, example_id. If sentences, example_id are not expected by `BertWithDAForSentenceLabelingTopicSegmentation.forward`, you can safely ignore this message. [INFO|trainer.py:2964] 2024-06-19 22:02:21,586 >> ***** Running Prediction ***** [INFO|trainer.py:2966] 2024-06-19 22:02:21,586 >> Num examples = 15271 [INFO|trainer.py:2969] 2024-06-19 22:02:21,586 >> Batch size = 4 num predict samples: 15271 num predict examples: 3904 0%| | 0/3818 [00:00