Training in progress, epoch 1

config.json

@@ -1,43 +1,38 @@
 {
-  "_name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
+  "attention_dropout": 0.1,
   "attention_probs_dropout_prob": 0.2,
   "classifier_dropout": 0.2,
-  "directionality": "bidi",
-  "hidden_act": "gelu",
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "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": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "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",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 29794
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b5a830901bb1a0eee04930d30ab97306799246f883e70b23208127368c0323
-size 435725300
+oid sha256:1e40c283058a5b5891e2fc3f60eb0ae5af1044225d9238cc41a6feb068563f6c
+size 267835644

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d5624dc30a928d5f2ab2bdabaa6596436d4c3713eae2d6c385de24c3a401d81
+size 5595

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -43,22 +43,13 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
-  "max_length": 512,
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
-  "pad_to_multiple_of": null,
+  "model_max_length": 512,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "[SEP]",
-  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:163d07ad7620fb4d8f2b4690e3064a28dbc04778a0f87963e4e64c09d17e296b
+oid sha256:549dcb3d826cb2249f77438cda48ca934f4ff717ef093ebb7fe613ce06bc1b63
 size 5176