End of training

.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 +1,120 @@
+---
+license: mit
+base_model: xlm-roberta-large
+tags:
+- generated_from_trainer
+datasets:
+- conll2003
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: XLM-RoBERTa-Large-Conll2003-English-NER-Finetune
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: conll2003
+      type: conll2003
+      config: conll2003
+      split: test
+      args: conll2003
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9247648902821317
+    - name: Recall
+      type: recall
+      value: 0.9401558073654391
+    - name: F1
+      type: f1
+      value: 0.932396839332748
+    - name: Accuracy
+      type: accuracy
+      value: 0.9851405190050608
+---
+
+<!-- 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-Large-Conll2003-English-NER-Finetune
+
+This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the conll2003 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2205
+- Precision: 0.9248
+- Recall: 0.9402
+- F1: 0.9324
+- Accuracy: 0.9851
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.6457        | 0.3333 | 1441  | 0.1841          | 0.8167    | 0.8336 | 0.8250 | 0.9674   |
+| 0.0893        | 0.6667 | 2882  | 0.1399          | 0.8827    | 0.8950 | 0.8888 | 0.9781   |
+| 0.0637        | 1.0    | 4323  | 0.1449          | 0.8939    | 0.9024 | 0.8981 | 0.9802   |
+| 0.0457        | 1.3333 | 5764  | 0.1552          | 0.8955    | 0.9163 | 0.9057 | 0.9816   |
+| 0.0387        | 1.6667 | 7205  | 0.1566          | 0.9041    | 0.9233 | 0.9136 | 0.9825   |
+| 0.0401        | 2.0    | 8646  | 0.1493          | 0.8982    | 0.9311 | 0.9144 | 0.9824   |
+| 0.0276        | 2.3333 | 10087 | 0.1655          | 0.9038    | 0.9299 | 0.9167 | 0.9820   |
+| 0.0248        | 2.6667 | 11528 | 0.1783          | 0.9127    | 0.9309 | 0.9217 | 0.9829   |
+| 0.0266        | 3.0    | 12969 | 0.1601          | 0.9120    | 0.9340 | 0.9228 | 0.9833   |
+| 0.0166        | 3.3333 | 14410 | 0.1801          | 0.9181    | 0.9288 | 0.9234 | 0.9842   |
+| 0.0187        | 3.6667 | 15851 | 0.1717          | 0.9170    | 0.9325 | 0.9247 | 0.9843   |
+| 0.0185        | 4.0    | 17292 | 0.1653          | 0.9190    | 0.9343 | 0.9266 | 0.9844   |
+| 0.0126        | 4.3333 | 18733 | 0.1845          | 0.9176    | 0.9343 | 0.9259 | 0.9843   |
+| 0.0133        | 4.6667 | 20174 | 0.1855          | 0.9174    | 0.9322 | 0.9247 | 0.9837   |
+| 0.0119        | 5.0    | 21615 | 0.1782          | 0.9168    | 0.9329 | 0.9248 | 0.9843   |
+| 0.01          | 5.3333 | 23056 | 0.1892          | 0.9173    | 0.9366 | 0.9269 | 0.9843   |
+| 0.0083        | 5.6667 | 24497 | 0.1800          | 0.9251    | 0.9343 | 0.9297 | 0.9845   |
+| 0.0079        | 6.0    | 25938 | 0.1868          | 0.9237    | 0.9352 | 0.9294 | 0.9851   |
+| 0.0059        | 6.3333 | 27379 | 0.2073          | 0.9178    | 0.9350 | 0.9263 | 0.9842   |
+| 0.0068        | 6.6667 | 28820 | 0.2061          | 0.9195    | 0.9379 | 0.9286 | 0.9843   |
+| 0.0062        | 7.0    | 30261 | 0.2011          | 0.9215    | 0.9377 | 0.9295 | 0.9846   |
+| 0.0037        | 7.3333 | 31702 | 0.2100          | 0.9209    | 0.9373 | 0.9290 | 0.9846   |
+| 0.0043        | 7.6667 | 33143 | 0.2145          | 0.9202    | 0.9389 | 0.9295 | 0.9847   |
+| 0.0039        | 8.0    | 34584 | 0.2070          | 0.9256    | 0.9377 | 0.9316 | 0.9852   |
+| 0.0024        | 8.3333 | 36025 | 0.2138          | 0.9218    | 0.9394 | 0.9306 | 0.9851   |
+| 0.0034        | 8.6667 | 37466 | 0.2159          | 0.9229    | 0.9394 | 0.9311 | 0.9849   |
+| 0.003         | 9.0    | 38907 | 0.2156          | 0.9244    | 0.9377 | 0.9310 | 0.9846   |
+| 0.002         | 9.3333 | 40348 | 0.2201          | 0.9252    | 0.9402 | 0.9326 | 0.9849   |
+| 0.0015        | 9.6667 | 41789 | 0.2217          | 0.9245    | 0.9393 | 0.9318 | 0.9850   |
+| 0.0028        | 10.0   | 43230 | 0.2205          | 0.9248    | 0.9402 | 0.9324 | 0.9851   |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "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": 1024,
+  "id2label": {
+    "0": "B-LOC",
+    "1": "B-MISC",
+    "2": "B-ORG",
+    "3": "B-PER",
+    "4": "I-LOC",
+    "5": "I-MISC",
+    "6": "I-ORG",
+    "7": "I-PER",
+    "8": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-LOC": 0,
+    "B-MISC": 1,
+    "B-ORG": 2,
+    "B-PER": 3,
+    "I-LOC": 4,
+    "I-MISC": 5,
+    "I-ORG": 6,
+    "I-PER": 7,
+    "O": 8
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "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 sha256:8de63b42dfd0359712224b59db7100314d5f24eab570b1dac9c77a5a3647a691
+size 2235448756

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 sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

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:ae2299bba8221340343166c40a08bcc08943721a8abc39c8323371520e114d9e
+size 5112