Training in progress, step 500

config.json

@@ -1,45 +1,37 @@
 {
-  "_name_or_path": "hanifnoerr/Fine-tuned-Indonesian-Sentiment-Classifier",
-  "_num_labels": 5,
+  "_name_or_path": "lxyuan/distilbert-base-multilingual-cased-sentiments-student",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "directionality": "bidi",
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "negative",
     "1": "netral",
     "2": "positive"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "negative": 0,
     "netral": 1,
     "positive": 2
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "max_split_size_mb": 100,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "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": "4.37.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 50000
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e28a903c11a002ea3e79ad40713937266ce341a03940344baa02db0776c8e866
-size 497798148
+oid sha256:c3a7ee76cb83474d5a82243fca04cc6560ae7e50d28df6c6b06a9d390dc1c79f
+size 541320452

runs/Feb22_05-56-09_c8d13364ede2/events.out.tfevents.1708581370.c8d13364ede2.1075.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629451d95e089d7c1976a95448d13c1939441ce9f56ba8aa7b86562785bcee1d
+size 4653

tokenizer_config.json

@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "1": {
+    "100": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "2": {
+    "101": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "3": {
+    "102": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "4": {
+    "103": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -44,15 +44,21 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
   "max_length": 512,
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "never_split": null,
+  "pad_to_multiple_of": null,
   "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",
+  "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f13d40545425ad0dcbdeec10e83a7c0ddca63fbf4c94e88e68694fd7b9c435d1
+oid sha256:11bf066db97bce61d10cca02c8a5961d0917904ef5b22283d3f686b48d3816f6
 size 4664