indo-ner-stage2-gold-final

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- precision
+- recall
+model-index:
+- name: local_stage2_final
+  results: []
+---
+
+<!-- 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. -->
+
+# local_stage2_final
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1903
+- F1: 0.8202
+- Precision: 0.7998
+- Recall: 0.8417
+
+## 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-06
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|
+| 0.3264        | 1.0   | 926  | 0.2126          | 0.7851 | 0.7626    | 0.8091 |
+| 0.1823        | 2.0   | 1852 | 0.1930          | 0.8056 | 0.7806    | 0.8322 |
+| 0.1444        | 3.0   | 2778 | 0.1894          | 0.8155 | 0.7939    | 0.8382 |
+| 0.1293        | 4.0   | 3704 | 0.1885          | 0.8192 | 0.7993    | 0.8400 |
+| 0.1184        | 5.0   | 4630 | 0.1903          | 0.8202 | 0.7998    | 0.8417 |
+
+
+### Framework versions
+
+- Transformers 4.57.3
+- Pytorch 2.9.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,114 @@
+{
+  "_num_labels": 5,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-CRD",
+    "2": "B-DAT",
+    "3": "B-EVT",
+    "4": "B-FAC",
+    "5": "B-GPE",
+    "6": "B-LAN",
+    "7": "B-LAW",
+    "8": "B-LOC",
+    "9": "B-MON",
+    "10": "B-NOR",
+    "11": "B-ORD",
+    "12": "B-ORG",
+    "13": "B-PER",
+    "14": "B-PRC",
+    "15": "B-PRD",
+    "16": "B-QTY",
+    "17": "B-REG",
+    "18": "B-TIM",
+    "19": "B-WOA",
+    "20": "I-CRD",
+    "21": "I-DAT",
+    "22": "I-EVT",
+    "23": "I-FAC",
+    "24": "I-GPE",
+    "25": "I-LAN",
+    "26": "I-LAW",
+    "27": "I-LOC",
+    "28": "I-MON",
+    "29": "I-NOR",
+    "30": "I-ORD",
+    "31": "I-ORG",
+    "32": "I-PER",
+    "33": "I-PRC",
+    "34": "I-PRD",
+    "35": "I-QTY",
+    "36": "I-REG",
+    "37": "I-TIM",
+    "38": "I-WOA"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "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": 0
+  },
+  "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": 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",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41ff1ea2cf913676675fd9d9ba03830a51e6bc5b0821c850177e948eba1057c
+size 495546332

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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": "[SEP]",
+    "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

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 128,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced4e35556928af2ab28a610c4ae6c9ecd0c158972549028b9ff09f99eee0d7a
+size 5841