Training complete

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: indolem/indobertweet-base-uncased
+license: mit
+base_model: FacebookAI/roberta-base
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # digidaw
 
-This model is a fine-tuned version of [indolem/indobertweet-base-uncased](https://huggingface.co/indolem/indobertweet-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7354
-- Accuracy: 0.8011
-- Precision: 0.6222
-- Recall: 0.5510
-- F1: 0.5686
+- Loss: 1.3618
+- Accuracy: 0.5941
+- Precision: 0.0743
+- Recall: 0.125
+- F1: 0.0932
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.9352        | 1.0   | 110  | 0.7414          | 0.7864   | 0.5489    | 0.4917 | 0.5051 |
-| 0.5174        | 2.0   | 220  | 0.7599          | 0.7850   | 0.5603    | 0.5242 | 0.5374 |
-| 0.3028        | 3.0   | 330  | 0.7354          | 0.8011   | 0.6222    | 0.5510 | 0.5686 |
+| 1.3939        | 1.0   | 110  | 1.3742          | 0.5941   | 0.0743    | 0.125  | 0.0932 |
+| 1.3769        | 2.0   | 220  | 1.3634          | 0.5941   | 0.0743    | 0.125  | 0.0932 |
+| 1.3696        | 3.0   | 330  | 1.3618          | 0.5941   | 0.0743    | 0.125  | 0.0932 |
 
 
 ### Framework versions

config.json

@@ -1,13 +1,12 @@
 {
-  "_name_or_path": "indolem/indobertweet-base-uncased",
+  "_name_or_path": "FacebookAI/roberta-base",
   "architectures": [
-    "BertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_ids": 0,
-  "gradient_checkpointing": false,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -33,18 +32,17 @@
     "Sosial Budaya": 3,
     "Sumber Daya Alam": 5
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 31923
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e7c23dafc1b5ba465df088bbd4d54f5b00ff10094c287fbfd6c8c629c89c2f1
-size 442280976
+oid sha256:2a9896e330afc579e2de627b97a4d37f76b8ed28e7b5f34e8576d2e2b4b7b564
+size 498631280

runs/Jun06_12-19-37_8b985dd3eeed/events.out.tfevents.1717676643.8b985dd3eeed.2286.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de05be562f2f940fe370c590f9d47c5095f45ff4b2ea46d4a7c18c610a5a346f
+size 560

runs/Jun06_12-35-37_8b985dd3eeed/events.out.tfevents.1717677338.8b985dd3eeed.2286.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816c0f43357262f207d7ca5a8d3a5c3bc40561ce4f5f110b2246f281aef629b0
+size 7597

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,57 +1,57 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "[UNK]",
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
-      "content": "[MASK]",
+      "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "3": {
-      "content": "[CLS]",
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "[SEP]",
-      "lstrip": false,
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
   "model_max_length": 128,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8eb6841e029ba7f831f6293c00a45c33c8ca0999295c52df3bd2b6afcf2e8b4
+oid sha256:9dd5f3bd7087a11069e6556652177038dc260fb1a489c0754256ea10e11d5842
 size 5048