Training complete

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: intfloat/multilingual-e5-base
+license: apache-2.0
+base_model: indolem/indobertweet-base-uncased
 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 [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) on an unknown dataset.
+This model is a fine-tuned version of [indolem/indobertweet-base-uncased](https://huggingface.co/indolem/indobertweet-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.1093
-- Accuracy: 0.095
-- Precision: 0.0784
-- Recall: 0.1217
-- F1: 0.0557
+- Loss: 5.0189
+- Accuracy: 0.126
+- Precision: 0.2318
+- Recall: 0.1268
+- F1: 0.0802
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.9895        | 1.0   | 156  | 4.4196          | 0.089    | 0.0792    | 0.1167 | 0.0479 |
-| 0.6357        | 2.0   | 312  | 4.8610          | 0.089    | 0.0952    | 0.1160 | 0.0495 |
-| 0.3968        | 3.0   | 468  | 5.1093          | 0.095    | 0.0784    | 0.1217 | 0.0557 |
+| 0.9331        | 1.0   | 156  | 3.9962          | 0.137    | 0.1228    | 0.1378 | 0.0826 |
+| 0.536         | 2.0   | 312  | 4.6163          | 0.125    | 0.1130    | 0.1259 | 0.0754 |
+| 0.2959        | 3.0   | 468  | 5.0189          | 0.126    | 0.2318    | 0.1268 | 0.0802 |
 
 
 ### Framework versions

config.json

@@ -1,12 +1,13 @@
 {
-  "_name_or_path": "intfloat/multilingual-e5-base",
+  "_name_or_path": "indolem/indobertweet-base-uncased",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "eos_token_ids": 0,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -32,18 +33,18 @@
     "Sosial Budaya": 3,
     "Sumber Daya Alam": 5
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "output_past": true,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 31923
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06ee67d15bfef3111dfca931f3b8cece9c25a2c4be6943b93321341dd2b0ea91
-size 1112223464
+oid sha256:339f517a2cbf7a48082210b66656041312c294c82bc2dca5685825eb6f415656
+size 442280976

runs/Jun12_07-08-15_f13255a39794/events.out.tfevents.1718176096.f13255a39794.362.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b7e09d30e196a5699b031cf491656767f4a396e48dee08790ed52ddf0ee458
+size 5949

runs/Jun12_07-11-28_f13255a39794/events.out.tfevents.1718176288.f13255a39794.362.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f86d7712e4d4c420fcea9cbb682050d93b3176580da8182df1cd7dba24293c
+size 7673

special_tokens_map.json

@@ -1,51 +1,7 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "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.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c088c06cf975b7097e469bd69630cdb0d675c6db1ce3af1042b6e19c6d01f22
-size 17082999
+oid sha256:569da783bde8185e4bc7ac63a9b6d3b53f97694aa4723c03715fd3e81eac7f22
+size 737950

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,30 +25,33 @@
       "special": true
     },
     "3": {
-      "content": "<unk>",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
-      "content": "<mask>",
-      "lstrip": true,
+    "4": {
+      "content": "[SEP]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
   "model_max_length": 128,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fff0c7ddbb4b8f2c8b645ad9e7943faec7b3ef95908271592c591c59b9476ac
+oid sha256:724d3da91f84c1d216a2d86660b34eac395f4e44c74a7a7612e9bb9aa6ffc753
 size 5048