Training in progress, epoch 1

config.json

@@ -1,38 +1,43 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "neuralmind/bert-base-portuguese-cased",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
   "attention_probs_dropout_prob": 0.2,
   "classifier_dropout": 0.2,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
   "hidden_dropout_prob": 0.2,
+  "hidden_size": 768,
   "id2label": {
     "0": "NEUTRO",
     "1": "POSITIVO",
     "2": "NEGATIVO"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "NEGATIVO": 2,
     "NEUTRO": 0,
     "POSITIVO": 1
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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",
   "problem_type": "multi_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.44.2",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b22bbbdf38905cd9e217e8a6134aa8f2c6e4d645cf908769d8048784819669d
-size 267835644
+oid sha256:c88832c1e6c4c7f50b399d6011ed9c333460d27d86852aea5949b45b137680d8
+size 435725300

runs/Sep21_18-31-56_9d17344fbe2b/events.out.tfevents.1726943518.9d17344fbe2b.3608.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a17074363aeb2df2f0ded92ef6185c0fbc97154f55c808448790700fb1582bb2
-size 6340
+oid sha256:f4677884697f70626ff984c8d5b8855232f45b9e2e46c4480806b3e3dd9b6358
+size 7439

runs/Sep21_18-47-32_9d17344fbe2b/events.out.tfevents.1726944452.9d17344fbe2b.3608.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f74229e4e1542098ac7be06b48db5d55beb78f2a7e0e039f4f12abfdc0200d27
+size 5796

tokenizer_config.json

@@ -43,13 +43,15 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:549dcb3d826cb2249f77438cda48ca934f4ff717ef093ebb7fe613ce06bc1b63
+oid sha256:1fc482d076ffe5cb2f6e8d766ee0b003a2ee08166a09de36922e58a76d04fa5d
 size 5176