Training in progress, epoch 0

config.json

@@ -1,33 +1,43 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "nlptown/bert-base-multilingual-uncased-sentiment",
+  "_num_labels": 5,
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "finetuning_task": "sentiment-analysis",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "NEGATIVE",
     "1": "POSITIVE"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "NEGATIVE": 0,
     "POSITIVE": 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": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.46.3",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 105879
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a37757e4f2d37ab0e80fa6101dd324d7e152a59dca1015c61d331e0a7be227e8
-size 267832560
+oid sha256:3bd1ae1e5eb60056fa89d0c00f06350e8cc3077ba59a5758f93371e2d253438d
+size 669455360

tokenizer_config.json

@@ -41,15 +41,18 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
+  "max_len": 512,
   "model_max_length": 512,
+  "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 sha256:08fbc49afde99e06ec2f0c749b0e30cdaabff3b8ce088de5a56809f85ef20ddc
+oid sha256:948b875c5a5601421178490124e51de155552fa558cd502becdb2ffbba975d23
 size 5240