Training in progress, epoch 1

config.json

@@ -0,0 +1,158 @@
+{
+  "_name_or_path": "neuralmind/bert-large-portuguese-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "B-A0",
+    "1": "B-A1",
+    "2": "B-A2",
+    "3": "B-A3",
+    "4": "B-A4",
+    "5": "B-AM-ADV",
+    "6": "B-AM-CAU",
+    "7": "B-AM-DIR",
+    "8": "B-AM-DIS",
+    "9": "B-AM-EXT",
+    "10": "B-AM-LOC",
+    "11": "B-AM-MNR",
+    "12": "B-AM-NEG",
+    "13": "B-AM-PNC",
+    "14": "B-AM-PRD",
+    "15": "B-AM-REC",
+    "16": "B-AM-TMP",
+    "17": "B-C-A0",
+    "18": "B-C-A1",
+    "19": "B-C-A2",
+    "20": "B-C-A3",
+    "21": "B-C-AM-ADV",
+    "22": "B-C-AM-CAU",
+    "23": "B-C-AM-DIS",
+    "24": "B-C-AM-EXT",
+    "25": "B-C-AM-LOC",
+    "26": "B-C-AM-MNR",
+    "27": "B-C-AM-NEG",
+    "28": "B-C-AM-PRD",
+    "29": "B-C-AM-TMP",
+    "30": "B-C-V",
+    "31": "B-V",
+    "32": "I-A0",
+    "33": "I-A1",
+    "34": "I-A2",
+    "35": "I-A3",
+    "36": "I-A4",
+    "37": "I-AM-ADV",
+    "38": "I-AM-CAU",
+    "39": "I-AM-DIR",
+    "40": "I-AM-DIS",
+    "41": "I-AM-EXT",
+    "42": "I-AM-LOC",
+    "43": "I-AM-MNR",
+    "44": "I-AM-NEG",
+    "45": "I-AM-PNC",
+    "46": "I-AM-PRD",
+    "47": "I-AM-REC",
+    "48": "I-AM-TMP",
+    "49": "I-C-A0",
+    "50": "I-C-A1",
+    "51": "I-C-A2",
+    "52": "I-C-A3",
+    "53": "I-C-AM-ADV",
+    "54": "I-C-AM-CAU",
+    "55": "I-C-AM-LOC",
+    "56": "I-C-AM-MNR",
+    "57": "I-C-AM-PRD",
+    "58": "I-C-AM-TMP",
+    "59": "I-C-V",
+    "60": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-A0": 0,
+    "B-A1": 1,
+    "B-A2": 2,
+    "B-A3": 3,
+    "B-A4": 4,
+    "B-AM-ADV": 5,
+    "B-AM-CAU": 6,
+    "B-AM-DIR": 7,
+    "B-AM-DIS": 8,
+    "B-AM-EXT": 9,
+    "B-AM-LOC": 10,
+    "B-AM-MNR": 11,
+    "B-AM-NEG": 12,
+    "B-AM-PNC": 13,
+    "B-AM-PRD": 14,
+    "B-AM-REC": 15,
+    "B-AM-TMP": 16,
+    "B-C-A0": 17,
+    "B-C-A1": 18,
+    "B-C-A2": 19,
+    "B-C-A3": 20,
+    "B-C-AM-ADV": 21,
+    "B-C-AM-CAU": 22,
+    "B-C-AM-DIS": 23,
+    "B-C-AM-EXT": 24,
+    "B-C-AM-LOC": 25,
+    "B-C-AM-MNR": 26,
+    "B-C-AM-NEG": 27,
+    "B-C-AM-PRD": 28,
+    "B-C-AM-TMP": 29,
+    "B-C-V": 30,
+    "B-V": 31,
+    "I-A0": 32,
+    "I-A1": 33,
+    "I-A2": 34,
+    "I-A3": 35,
+    "I-A4": 36,
+    "I-AM-ADV": 37,
+    "I-AM-CAU": 38,
+    "I-AM-DIR": 39,
+    "I-AM-DIS": 40,
+    "I-AM-EXT": 41,
+    "I-AM-LOC": 42,
+    "I-AM-MNR": 43,
+    "I-AM-NEG": 44,
+    "I-AM-PNC": 45,
+    "I-AM-PRD": 46,
+    "I-AM-REC": 47,
+    "I-AM-TMP": 48,
+    "I-C-A0": 49,
+    "I-C-A1": 50,
+    "I-C-A2": 51,
+    "I-C-A3": 52,
+    "I-C-AM-ADV": 53,
+    "I-C-AM-CAU": 54,
+    "I-C-AM-LOC": 55,
+    "I-C-AM-MNR": 56,
+    "I-C-AM-PRD": 57,
+    "I-C-AM-TMP": 58,
+    "I-C-V": 59,
+    "O": 60
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca314be227e295b79f6367085e42ff4f7e58782cfa812a151491463c62134b5
+size 1333684180

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ac2b3370d6d082b41b67fee878d3cb7adaec9225808f03e1eacc7f1c97aa71
+size 5048