Training complete

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: indolem/indobertweet-base-uncased
+license: mit
+base_model: intfloat/multilingual-e5-small
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # digidawfinal2
 
-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 [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6873
-- Accuracy: 0.809
-- Precision: 0.4145
-- Recall: 0.6521
-- F1: 0.4225
+- Loss: 0.6325
+- Accuracy: 0.826
+- Precision: 0.4849
+- Recall: 0.3920
+- F1: 0.4038
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.8998        | 1.0   | 156  | 0.5670          | 0.8      | 0.3607    | 0.5861 | 0.3709 |
-| 0.5034        | 2.0   | 312  | 0.6026          | 0.812    | 0.4137    | 0.6687 | 0.4475 |
-| 0.2645        | 3.0   | 468  | 0.6873          | 0.809    | 0.4145    | 0.6521 | 0.4225 |
+| 1.3648        | 1.0   | 157  | 0.7544          | 0.8      | 0.1481    | 0.1495 | 0.1451 |
+| 1.0523        | 2.0   | 314  | 0.7241          | 0.791    | 0.3328    | 0.3616 | 0.3064 |
+| 0.8635        | 3.0   | 471  | 0.6325          | 0.826    | 0.4849    | 0.3920 | 0.4038 |
 
 
 ### Framework versions

config.json

@@ -1,16 +1,13 @@
 {
-  "_name_or_path": "indolem/indobertweet-base-uncased",
+  "_name_or_path": "intfloat/multilingual-e5-small",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_ids": 0,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 384,
   "id2label": {
     "0": "Ideologi",
     "1": "Politik",
@@ -22,7 +19,7 @@
     "7": "Demografi"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 1536,
   "label2id": {
     "Demografi": 7,
     "Ekonomi": 2,
@@ -38,13 +35,13 @@
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "tokenizer_class": "XLMRobertaTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 31923
+  "vocab_size": 250037
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e86815fa41ef527f51be61b063ce079da8e85d5311fe249365c05dfc3ec04a40
-size 442280976
+oid sha256:d05a7d8768fdae289fb43cddadb768dcac2c59e572bced6ab1a4c1820eb77131
+size 470650904

runs/Jun16_07-27-34_0a5ef3c8edb2/events.out.tfevents.1718522856.0a5ef3c8edb2.445.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a09974da0300ebff22dea8a303757718f15a2ff5d17adf347125e2346fc46c9
+size 7654

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -1,7 +1,51 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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": false,
+    "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
+  }
 }

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "[UNK]",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "[MASK]",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,15 +25,15 @@
       "special": true
     },
     "3": {
-      "content": "[CLS]",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "[SEP]",
+    "250001": {
+      "content": "<mask>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -41,17 +41,15 @@
       "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>",
+  "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>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c8a1866d2b6d5094aa47c28677ade500a70452416913d7d550302cd5b01224
+oid sha256:680e2446d2f0205d1768183ab4ccd123ad3f32e6320a811354d0cd1ff134474a
 size 5112