napatswift/xlm-roberta-base-ner-th

.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
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: ner_model
+  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. -->
+
+# ner_model
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1247
+- Precision: 0.8073
+- Recall: 0.8695
+- F1: 0.8372
+- Accuracy: 0.9655
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 0.4   | 100  | 0.5360          | 0.4604    | 0.4644 | 0.4624 | 0.8846   |
+| No log        | 0.81  | 200  | 0.2882          | 0.6137    | 0.6619 | 0.6369 | 0.9307   |
+| No log        | 1.21  | 300  | 0.2128          | 0.7236    | 0.7649 | 0.7437 | 0.9442   |
+| No log        | 1.62  | 400  | 0.1811          | 0.7146    | 0.7925 | 0.7515 | 0.9494   |
+| 0.4608        | 2.02  | 500  | 0.1594          | 0.7369    | 0.8021 | 0.7681 | 0.9542   |
+| 0.4608        | 2.43  | 600  | 0.1532          | 0.7494    | 0.8331 | 0.7890 | 0.9572   |
+| 0.4608        | 2.83  | 700  | 0.1403          | 0.7660    | 0.8417 | 0.8021 | 0.9594   |
+| 0.4608        | 3.24  | 800  | 0.1342          | 0.7909    | 0.8428 | 0.8160 | 0.9625   |
+| 0.4608        | 3.64  | 900  | 0.1325          | 0.7867    | 0.8572 | 0.8204 | 0.9626   |
+| 0.1256        | 4.05  | 1000 | 0.1275          | 0.8056    | 0.8632 | 0.8334 | 0.9648   |
+| 0.1256        | 4.45  | 1100 | 0.1229          | 0.8131    | 0.8643 | 0.8379 | 0.9657   |
+| 0.1256        | 4.86  | 1200 | 0.1247          | 0.8073    | 0.8695 | 0.8372 | 0.9655   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,104 @@
+{
+  "_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-PERSON",
+    "1": "I-PERSON",
+    "2": "O",
+    "3": "B-ORGANIZATION",
+    "4": "B-LOCATION",
+    "5": "I-ORGANIZATION",
+    "6": "I-LOCATION",
+    "7": "B-DATE",
+    "8": "I-DATE",
+    "9": "B-TIME",
+    "10": "I-TIME",
+    "11": "B-MONEY",
+    "12": "I-MONEY",
+    "13": "B-FACILITY",
+    "14": "I-FACILITY",
+    "15": "B-URL",
+    "16": "I-URL",
+    "17": "B-PERCENT",
+    "18": "I-PERCENT",
+    "19": "B-LEN",
+    "20": "I-LEN",
+    "21": "B-AGO",
+    "22": "I-AGO",
+    "23": "B-LAW",
+    "24": "I-LAW",
+    "25": "B-PHONE",
+    "26": "I-PHONE",
+    "27": "B-EMAIL",
+    "28": "I-EMAIL",
+    "29": "B-ZIP",
+    "30": "B-TEMPERATURE",
+    "31": "I-TEMPERATURE",
+    "32": "B-DTAE",
+    "33": "I-DTAE",
+    "34": "B-DATA",
+    "35": "I-DATA"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AGO": 21,
+    "B-DATA": 34,
+    "B-DATE": 7,
+    "B-DTAE": 32,
+    "B-EMAIL": 27,
+    "B-FACILITY": 13,
+    "B-LAW": 23,
+    "B-LEN": 19,
+    "B-LOCATION": 4,
+    "B-MONEY": 11,
+    "B-ORGANIZATION": 3,
+    "B-PERCENT": 17,
+    "B-PERSON": 0,
+    "B-PHONE": 25,
+    "B-TEMPERATURE": 30,
+    "B-TIME": 9,
+    "B-URL": 15,
+    "B-ZIP": 29,
+    "I-AGO": 22,
+    "I-DATA": 35,
+    "I-DATE": 8,
+    "I-DTAE": 33,
+    "I-EMAIL": 28,
+    "I-FACILITY": 14,
+    "I-LAW": 24,
+    "I-LEN": 20,
+    "I-LOCATION": 6,
+    "I-MONEY": 12,
+    "I-ORGANIZATION": 5,
+    "I-PERCENT": 18,
+    "I-PERSON": 1,
+    "I-PHONE": 26,
+    "I-TEMPERATURE": 31,
+    "I-TIME": 10,
+    "I-URL": 16,
+    "O": 2
+  },
+  "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": "4.35.2",
+  "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 sha256:4aefda7884fb440417793161d199f7745446b12d729e38e4c02c7b747ed2e778
+size 1109947016

runs/Jan24_13-29-47_049e1b241bd9/events.out.tfevents.1706102987.049e1b241bd9.174.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68822f12e8cbb1453b385df441be03de83a185543f2594b52980c200f7714f9d
+size 12033

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:f1cc44ad7faaeec47241864835473fd5403f2da94673f3f764a77ebcb0a803ec
+size 17083009

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 sha256:52a5fd532b3a9a10647359362874cdb150c4e39c82574d6f9aaa6ebef6310505
+size 4536