2022-07-01 15:34:05,571 - __main__ - INFO - Label List:['O', 'B-PERSON', 'I-PERSON', 'B-NORP', 'I-NORP', 'B-FAC', 'I-FAC', 'B-ORG', 'I-ORG', 'B-GPE', 'I-GPE', 'B-LOC', 'I-LOC', 'B-PRODUCT', 'I-PRODUCT', 'B-DATE', 'I-DATE', 'B-TIME', 'I-TIME', 'B-PERCENT', 'I-PERCENT', 'B-MONEY', 'I-MONEY', 'B-QUANTITY', 'I-QUANTITY', 'B-ORDINAL', 'I-ORDINAL', 'B-CARDINAL', 'I-CARDINAL', 'B-EVENT', 'I-EVENT', 'B-WORK_OF_ART', 'I-WORK_OF_ART', 'B-LAW', 'I-LAW', 'B-LANGUAGE', 'I-LANGUAGE'] 2022-07-01 15:34:14,083 - __main__ - INFO - Dataset({ features: ['id', 'words', 'ner_tags'], num_rows: 75187 }) 2022-07-01 15:34:14,812 - __main__ - INFO - Dataset({ features: ['id', 'words', 'ner_tags'], num_rows: 9479 }) 2022-07-01 15:34:14,815 - transformers.tokenization_utils_base - INFO - Didn't find file models/roberta-base_1656662418.0944197/checkpoint-14100/added_tokens.json. We won't load it. 2022-07-01 15:34:14,816 - transformers.tokenization_utils_base - INFO - loading file models/roberta-base_1656662418.0944197/checkpoint-14100/vocab.json 2022-07-01 15:34:14,816 - transformers.tokenization_utils_base - INFO - loading file models/roberta-base_1656662418.0944197/checkpoint-14100/merges.txt 2022-07-01 15:34:14,816 - transformers.tokenization_utils_base - INFO - loading file models/roberta-base_1656662418.0944197/checkpoint-14100/tokenizer.json 2022-07-01 15:34:14,816 - transformers.tokenization_utils_base - INFO - loading file None 2022-07-01 15:34:14,816 - transformers.tokenization_utils_base - INFO - loading file models/roberta-base_1656662418.0944197/checkpoint-14100/special_tokens_map.json 2022-07-01 15:34:14,816 - transformers.tokenization_utils_base - INFO - loading file models/roberta-base_1656662418.0944197/checkpoint-14100/tokenizer_config.json 2022-07-01 15:34:14,880 - __main__ - INFO - {'input_ids': [[0, 653, 761, 9, 3783, 17487, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [0, 166, 32928, 9603, 47, 7, 1183, 10, 780, 5403, 9, 15581, 436, 479, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [0, 15584, 3082, 3192, 23959, 15, 5, 2860, 3875, 9, 436, 4832, 41876, 38628, 9, 15643, 24610, 4743, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [0, 15125, 6764, 15, 15643, 24610, 4743, 16, 5, 23001, 7, 5, 41184, 6304, 25132, 23909, 479, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [0, 85, 16, 14092, 9, 10, 2270, 11235, 459, 2156, 5929, 1690, 523, 293, 2156, 10, 1307, 1062, 18185, 8, 30943, 9368, 2156, 8, 5, 2860, 2298, 2156, 566, 97, 383, 479, 2]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]} 2022-07-01 15:34:14,880 - __main__ - INFO - ['', 'ĠWhat', 'Ġkind', 'Ġof', 'Ġmemory', 'Ġ?', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', ''] 2022-07-01 15:34:14,880 - __main__ - INFO - ['', 'ĠWe', 'Ġrespectfully', 'Ġinvite', 'Ġyou', 'Ġto', 'Ġwatch', 'Ġa', 'Ġspecial', 'Ġedition', 'Ġof', 'ĠAcross', 'ĠChina', 'Ġ.', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', ''] 2022-07-01 15:34:14,881 - __main__ - INFO - ['', 'ĠWW', 'ĠII', 'ĠLand', 'marks', 'Ġon', 'Ġthe', 'ĠGreat', 'ĠEarth', 'Ġof', 'ĠChina', 'Ġ:', 'ĠEternal', 'ĠMemories', 'Ġof', 'ĠTai', 'hang', 'ĠMountain', '', '', '', '', '', '', '', '', '', '', '', '', '', '', ''] 2022-07-01 15:34:14,881 - __main__ - INFO - ['', 'ĠStanding', 'Ġtall', 'Ġon', 'ĠTai', 'hang', 'ĠMountain', 'Ġis', 'Ġthe', 'ĠMonument', 'Ġto', 'Ġthe', 'ĠHundred', 'ĠReg', 'iments', 'ĠOffensive', 'Ġ.', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', ''] 2022-07-01 15:34:14,881 - __main__ - INFO - ['', 'ĠIt', 'Ġis', 'Ġcomposed', 'Ġof', 'Ġa', 'Ġprimary', 'Ġste', 'le', 'Ġ,', 'Ġsecondary', 'Ġst', 'el', 'es', 'Ġ,', 'Ġa', 'Ġhuge', 'Ġround', 'Ġsculpture', 'Ġand', 'Ġbeacon', 'Ġtower', 'Ġ,', 'Ġand', 'Ġthe', 'ĠGreat', 'ĠWall', 'Ġ,', 'Ġamong', 'Ġother', 'Ġthings', 'Ġ.', ''] 2022-07-01 15:34:14,881 - __main__ - INFO - ------------- 2022-07-01 15:34:14,881 - __main__ - INFO - ['', 'ĠWe', 'Ġrespectfully', 'Ġinvite', 'Ġyou', 'Ġto', 'Ġwatch', 'Ġa', 'Ġspecial', 'Ġedition', 'Ġof', 'ĠAcross', 'ĠChina', 'Ġ.', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', ''] 2022-07-01 15:34:14,882 - __main__ - INFO - [None, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None] 2022-07-01 15:34:14,885 - datasets.fingerprint - WARNING - Parameter 'function'= of the transform datasets.arrow_dataset.Dataset._map_single couldn't be hashed properly, a random hash was used instead. Make sure your transforms and parameters are serializable with pickle or dill for the dataset fingerprinting and caching to work. If you reuse this transform, the caching mechanism will consider it to be different from the previous calls and recompute everything. This warning is only showed once. Subsequent hashing failures won't be showed. 2022-07-01 15:34:20,039 - __main__ - INFO - {'id': [0, 1, 2, 3, 4], 'words': [['What', 'kind', 'of', 'memory', '?'], ['We', 'respectfully', 'invite', 'you', 'to', 'watch', 'a', 'special', 'edition', 'of', 'Across', 'China', '.'], ['WW', 'II', 'Landmarks', 'on', 'the', 'Great', 'Earth', 'of', 'China', ':', 'Eternal', 'Memories', 'of', 'Taihang', 'Mountain'], ['Standing', 'tall', 'on', 'Taihang', 'Mountain', 'is', 'the', 'Monument', 'to', 'the', 'Hundred', 'Regiments', 'Offensive', '.'], ['It', 'is', 'composed', 'of', 'a', 'primary', 'stele', ',', 'secondary', 'steles', ',', 'a', 'huge', 'round', 'sculpture', 'and', 'beacon', 'tower', ',', 'and', 'the', 'Great', 'Wall', ',', 'among', 'other', 'things', '.']], 'ner_tags': [[0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 8, 0], [31, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32], [0, 0, 0, 11, 12, 0, 31, 32, 32, 32, 32, 32, 32, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 31, 32, 32, 0, 0, 0, 0, 0]], 'input_ids': [[0, 653, 761, 9, 3783, 17487, 2], [0, 166, 32928, 9603, 47, 7, 1183, 10, 780, 5403, 9, 15581, 436, 479, 2], [0, 15584, 3082, 3192, 23959, 15, 5, 2860, 3875, 9, 436, 4832, 41876, 38628, 9, 15643, 24610, 4743, 2], [0, 15125, 6764, 15, 15643, 24610, 4743, 16, 5, 23001, 7, 5, 41184, 6304, 25132, 23909, 479, 2], [0, 85, 16, 14092, 9, 10, 2270, 11235, 459, 2156, 5929, 1690, 523, 293, 2156, 10, 1307, 1062, 18185, 8, 30943, 9368, 2156, 8, 5, 2860, 2298, 2156, 566, 97, 383, 479, 2]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]], 'labels': [[-100, 0, 0, 0, 0, 0, -100], [-100, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 8, 0, -100], [-100, 31, 32, 32, -100, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, -100, 32, -100], [-100, 0, 0, 0, 11, -100, 12, 0, 31, 32, 32, 32, 32, 32, -100, 32, 0, -100], [-100, 0, 0, 0, 0, 0, 0, 0, -100, 0, 0, 0, -100, -100, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 31, 32, 32, 0, 0, 0, 0, 0, -100]]} 2022-07-01 15:34:22,155 - transformers.configuration_utils - INFO - loading configuration file models/roberta-base_1656662418.0944197/checkpoint-14100/config.json 2022-07-01 15:34:22,162 - transformers.configuration_utils - INFO - Model config RobertaConfig { "_name_or_path": "models/roberta-base_1656662418.0944197/checkpoint-14100", "architectures": [ "RobertaForTokenClassification" ], "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "classifier_dropout": null, "eos_token_id": 2, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "O", "1": "B-PERSON", "2": "I-PERSON", "3": "B-NORP", "4": "I-NORP", "5": "B-FAC", "6": "I-FAC", "7": "B-ORG", "8": "I-ORG", "9": "B-GPE", "10": "I-GPE", "11": "B-LOC", "12": "I-LOC", "13": "B-PRODUCT", "14": "I-PRODUCT", "15": "B-DATE", "16": "I-DATE", "17": "B-TIME", "18": "I-TIME", "19": "B-PERCENT", "20": "I-PERCENT", "21": "B-MONEY", "22": "I-MONEY", "23": "B-QUANTITY", "24": "I-QUANTITY", "25": "B-ORDINAL", "26": "I-ORDINAL", "27": "B-CARDINAL", "28": "I-CARDINAL", "29": "B-EVENT", "30": "I-EVENT", "31": "B-WORK_OF_ART", "32": "I-WORK_OF_ART", "33": "B-LAW", "34": "I-LAW", "35": "B-LANGUAGE", "36": "I-LANGUAGE" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "B-CARDINAL": 27, "B-DATE": 15, "B-EVENT": 29, "B-FAC": 5, "B-GPE": 9, "B-LANGUAGE": 35, "B-LAW": 33, "B-LOC": 11, "B-MONEY": 21, "B-NORP": 3, "B-ORDINAL": 25, "B-ORG": 7, "B-PERCENT": 19, "B-PERSON": 1, "B-PRODUCT": 13, "B-QUANTITY": 23, "B-TIME": 17, "B-WORK_OF_ART": 31, "I-CARDINAL": 28, "I-DATE": 16, "I-EVENT": 30, "I-FAC": 6, "I-GPE": 10, "I-LANGUAGE": 36, "I-LAW": 34, "I-LOC": 12, "I-MONEY": 22, "I-NORP": 4, "I-ORDINAL": 26, "I-ORG": 8, "I-PERCENT": 20, "I-PERSON": 2, "I-PRODUCT": 14, "I-QUANTITY": 24, "I-TIME": 18, "I-WORK_OF_ART": 32, "O": 0 }, "layer_norm_eps": 1e-05, "max_position_embeddings": 514, "model_type": "roberta", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 1, "position_embedding_type": "absolute", "torch_dtype": "float32", "transformers_version": "4.20.0", "type_vocab_size": 1, "use_cache": true, "vocab_size": 50265 } 2022-07-01 15:34:22,259 - transformers.modeling_utils - INFO - loading weights file models/roberta-base_1656662418.0944197/checkpoint-14100/pytorch_model.bin 2022-07-01 15:34:23,639 - transformers.modeling_utils - INFO - All model checkpoint weights were used when initializing RobertaForTokenClassification. 2022-07-01 15:34:23,640 - transformers.modeling_utils - INFO - All the weights of RobertaForTokenClassification were initialized from the model checkpoint at models/roberta-base_1656662418.0944197/checkpoint-14100. If your task is similar to the task the model of the checkpoint was trained on, you can already use RobertaForTokenClassification for predictions without further training. 2022-07-01 15:34:23,646 - __main__ - INFO - RobertaForTokenClassification( (roberta): RobertaModel( (embeddings): RobertaEmbeddings( (word_embeddings): Embedding(50265, 768, padding_idx=1) (position_embeddings): Embedding(514, 768, padding_idx=1) (token_type_embeddings): Embedding(1, 768) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (encoder): RobertaEncoder( (layer): ModuleList( (0): RobertaLayer( (attention): RobertaAttention( (self): RobertaSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): RobertaSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): RobertaIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): RobertaOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (1): RobertaLayer( (attention): RobertaAttention( (self): RobertaSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): RobertaSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): RobertaIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): RobertaOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (2): RobertaLayer( (attention): RobertaAttention( (self): RobertaSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): RobertaSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): RobertaIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): RobertaOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (3): RobertaLayer( (attention): RobertaAttention( (self): RobertaSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): RobertaSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): RobertaIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): RobertaOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (4): RobertaLayer( (attention): RobertaAttention( (self): RobertaSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): RobertaSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): RobertaIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): RobertaOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (5): RobertaLayer( (attention): RobertaAttention( (self): RobertaSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): RobertaSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): RobertaIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): RobertaOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (6): RobertaLayer( (attention): RobertaAttention( (self): RobertaSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): RobertaSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): RobertaIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): RobertaOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (7): RobertaLayer( (attention): RobertaAttention( (self): RobertaSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): RobertaSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): RobertaIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): RobertaOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (8): RobertaLayer( (attention): RobertaAttention( (self): RobertaSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): RobertaSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): RobertaIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): RobertaOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (9): RobertaLayer( (attention): RobertaAttention( (self): RobertaSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): RobertaSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): RobertaIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): RobertaOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (10): RobertaLayer( (attention): RobertaAttention( (self): RobertaSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): RobertaSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): RobertaIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): RobertaOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (11): RobertaLayer( (attention): RobertaAttention( (self): RobertaSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): RobertaSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): RobertaIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): RobertaOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) ) ) (dropout): Dropout(p=0.1, inplace=False) (classifier): Linear(in_features=768, out_features=37, bias=True) ) 2022-07-01 15:34:23,647 - __main__ - INFO - CONFIGS:{ "output_dir": "./models/fine-tunned-roberta-14100_1656669845.567399", "per_device_train_batch_size": 16, "per_device_eval_batch_size": 16, "save_total_limit": 2, "num_train_epochs": 3, "seed": 1, "load_best_model_at_end": true, "evaluation_strategy": "epoch", "save_strategy": "epoch", "learning_rate": 2e-05, "weight_decay": 0.01, "logging_steps": 469.0 } 2022-07-01 15:34:23,647 - transformers.training_args - INFO - PyTorch: setting up devices 2022-07-01 15:34:23,702 - transformers.training_args - INFO - The default value for the training argument `--report_to` will change in v5 (from all installed integrations to none). In v5, you will need to use `--report_to all` to get the same behavior as now. You should start updating your code and make this info disappear :-). 2022-07-01 15:34:27,143 - __main__ - INFO - [[ MODEL EVALUATION ]] 2022-07-01 15:34:27,143 - transformers.trainer - INFO - The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: id, ner_tags, words. If id, ner_tags, words are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. 2022-07-01 15:34:27,146 - transformers.trainer - INFO - ***** Running Evaluation ***** 2022-07-01 15:34:27,146 - transformers.trainer - INFO - Num examples = 9479 2022-07-01 15:34:27,146 - transformers.trainer - INFO - Batch size = 16 2022-07-01 15:35:42,947 - __main__ - INFO - {'eval_loss': 0.06502678245306015, 'eval_precision': 0.888830852267781, 'eval_recall': 0.9069912054721506, 'eval_f1': 0.8978192050650721, 'eval_accuracy': 0.9842020533202814, 'eval_runtime': 75.7916, 'eval_samples_per_second': 125.067, 'eval_steps_per_second': 7.824, 'step': 0} 2022-07-01 15:35:42,947 - transformers.trainer - INFO - The following columns in the test set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: id, ner_tags, words. If id, ner_tags, words are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message. 2022-07-01 15:35:42,949 - transformers.trainer - INFO - ***** Running Prediction ***** 2022-07-01 15:35:42,949 - transformers.trainer - INFO - Num examples = 9479 2022-07-01 15:35:42,950 - transformers.trainer - INFO - Batch size = 16 2022-07-01 15:37:01,513 - __main__ - INFO - precision recall f1-score support CARDINAL 0.84 0.85 0.85 935 DATE 0.85 0.90 0.87 1602 EVENT 0.67 0.76 0.71 63 FAC 0.74 0.72 0.73 135 GPE 0.97 0.96 0.96 2240 LANGUAGE 0.83 0.68 0.75 22 LAW 0.66 0.62 0.64 40 LOC 0.74 0.80 0.77 179 MONEY 0.85 0.89 0.87 314 NORP 0.93 0.96 0.95 841 ORDINAL 0.81 0.89 0.85 195 ORG 0.90 0.91 0.91 1795 PERCENT 0.90 0.92 0.91 349 PERSON 0.95 0.95 0.95 1988 PRODUCT 0.74 0.83 0.78 76 QUANTITY 0.76 0.80 0.78 105 TIME 0.62 0.67 0.65 212 WORK_OF_ART 0.58 0.69 0.63 166 micro avg 0.89 0.91 0.90 11257 macro avg 0.80 0.82 0.81 11257 weighted avg 0.89 0.91 0.90 11257