Training completed

.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

@@ -0,0 +1,77 @@
+---
+license: mit
+base_model: xlm-roberta-base
+tags:
+- generated_from_trainer
+datasets:
+- id_nergrit_corpus
+metrics:
+- f1
+model-index:
+- name: xlm-roberta-base-finetuned-panx-Indo
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: id_nergrit_corpus
+      type: id_nergrit_corpus
+      config: ner
+      split: validation
+      args: ner
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.83694517516389
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# xlm-roberta-base-finetuned-panx-Indo
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the id_nergrit_corpus dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1919
+- F1: 0.8369
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 24
+- eval_batch_size: 24
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.3999        | 1.0   | 523  | 0.2013          | 0.8147 |
+| 0.1624        | 2.0   | 1046 | 0.1942          | 0.8249 |
+| 0.1097        | 3.0   | 1569 | 0.1919          | 0.8369 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,110 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-CRD",
+    "1": "B-DAT",
+    "2": "B-EVT",
+    "3": "B-FAC",
+    "4": "B-GPE",
+    "5": "B-LAN",
+    "6": "B-LAW",
+    "7": "B-LOC",
+    "8": "B-MON",
+    "9": "B-NOR",
+    "10": "B-ORD",
+    "11": "B-ORG",
+    "12": "B-PER",
+    "13": "B-PRC",
+    "14": "B-PRD",
+    "15": "B-QTY",
+    "16": "B-REG",
+    "17": "B-TIM",
+    "18": "B-WOA",
+    "19": "I-CRD",
+    "20": "I-DAT",
+    "21": "I-EVT",
+    "22": "I-FAC",
+    "23": "I-GPE",
+    "24": "I-LAN",
+    "25": "I-LAW",
+    "26": "I-LOC",
+    "27": "I-MON",
+    "28": "I-NOR",
+    "29": "I-ORD",
+    "30": "I-ORG",
+    "31": "I-PER",
+    "32": "I-PRC",
+    "33": "I-PRD",
+    "34": "I-QTY",
+    "35": "I-REG",
+    "36": "I-TIM",
+    "37": "I-WOA",
+    "38": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-CRD": 0,
+    "B-DAT": 1,
+    "B-EVT": 2,
+    "B-FAC": 3,
+    "B-GPE": 4,
+    "B-LAN": 5,
+    "B-LAW": 6,
+    "B-LOC": 7,
+    "B-MON": 8,
+    "B-NOR": 9,
+    "B-ORD": 10,
+    "B-ORG": 11,
+    "B-PER": 12,
+    "B-PRC": 13,
+    "B-PRD": 14,
+    "B-QTY": 15,
+    "B-REG": 16,
+    "B-TIM": 17,
+    "B-WOA": 18,
+    "I-CRD": 19,
+    "I-DAT": 20,
+    "I-EVT": 21,
+    "I-FAC": 22,
+    "I-GPE": 23,
+    "I-LAN": 24,
+    "I-LAW": 25,
+    "I-LOC": 26,
+    "I-MON": 27,
+    "I-NOR": 28,
+    "I-ORD": 29,
+    "I-ORG": 30,
+    "I-PER": 31,
+    "I-PRC": 32,
+    "I-PRD": 33,
+    "I-QTY": 34,
+    "I-REG": 35,
+    "I-TIM": 36,
+    "I-WOA": 37,
+    "O": 38
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b184c0c8b4a068a85bf4ca0b7ebf93b34206377f59b1b107e8521e79453b5b13
+size 1109956244

runs/Jun25_06-39-29_d0292c30bc17/events.out.tfevents.1719297616.d0292c30bc17.3120.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bf9d88f1190335489434dfc539a08fb6daa3c7b27632794f1ccf758db848aa1
+size 6533

runs/Jun25_06-53-39_d0292c30bc17/events.out.tfevents.1719298463.d0292c30bc17.3120.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2f692cc25903e1b8719cac1989649fda48a2fc4317e63e8881dcdd332cd57e6
+size 8260

sentencepiece.bpe.model

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

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c088c06cf975b7097e469bd69630cdb0d675c6db1ce3af1042b6e19c6d01f22
+size 17082999

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "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>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ca65cdd66bec073b649b95a3f04afd561564d83fa71b3536c86440d76bb3691
+size 5112