Training in progress, epoch 1

config.json

@@ -1,38 +1,26 @@
 {
-  "_name_or_path": "PORTULAN/albertina-ptbr",
+  "_name_or_path": "distilbert-base-multilingual-cased",
+  "activation": "gelu",
   "architectures": [
-    "DebertaV2ForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_head_size": 64,
-  "attention_probs_dropout_prob": 0.1,
-  "conv_act": "gelu",
-  "conv_kernel_size": 3,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1536,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 6144,
-  "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
-  "max_relative_positions": -1,
-  "model_type": "deberta-v2",
-  "norm_rel_ebd": "layer_norm",
-  "num_attention_heads": 24,
-  "num_hidden_layers": 24,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
   "pad_token_id": 0,
-  "pooler_dropout": 0,
-  "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 1536,
-  "pos_att_type": [
-    "p2c",
-    "c2p"
-  ],
-  "position_biased_input": false,
-  "position_buckets": 256,
-  "relative_attention": true,
-  "share_att_key": true,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
-  "type_vocab_size": 0,
-  "vocab_size": 128100
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:587df1e2cda8465cb1fbc4cc15fd629f97e121afaa66b5705b7aade86d20c65b
-size 3547878120
+oid sha256:1f8585a2da9aa0c024650a92fe05b4b100f4ba2f27529c983fe7dc225985a9cd
+size 541317368

runs/Dec16_12-33-31_c868fac455d2/events.out.tfevents.1702730012.c868fac455d2.3256.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e15276d4640ff68f38faa6fa047ea0a3deae07b7d013c4d05e81f0b0d2412d7d
+size 4612

special_tokens_map.json

@@ -1,7 +1,5 @@
 {
-  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

tokenizer_config.json

@@ -8,31 +8,31 @@
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "[CLS]",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "[SEP]",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "[UNK]",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128000": {
+    "103": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -41,18 +41,15 @@
       "special": true
     }
   },
-  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": false,
-  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "split_by_punct": false,
-  "tokenizer_class": "DebertaV2Tokenizer",
-  "unk_token": "[UNK]",
-  "vocab_type": "spm"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ebc1decb241980620cee37d69fda5f983f063466b7c3ae117e195b005d30d2f
+oid sha256:bd22dba14a11c6f37685ed817e9e80660635ca295613fc670d62e2283fc9fabe
 size 4600