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-base
+tags:
+- generated_from_trainer
+datasets:
+- conll2003
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: XLM-RoBERTa-Base-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: 0.9051348999129678
+    - name: Recall
+      type: recall
+      value: 0.9206798866855525
+    - name: F1
+      type: f1
+      value: 0.9128412182919337
+    - name: Accuracy
+      type: accuracy
+      value: 0.9819532680090449
+---
+
+<!-- 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-Conll2003-English-NER-Finetune
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the conll2003 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1887
+- Precision: 0.9051
+- Recall: 0.9207
+- F1: 0.9128
+- Accuracy: 0.9820
+
+## 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 |
+|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.6956        | 0.3333 | 1441  | 0.1847          | 0.5575    | 0.5845 | 0.5707 | 0.9322   |
+| 0.1126        | 0.6667 | 2882  | 0.1192          | 0.8533    | 0.8762 | 0.8646 | 0.9748   |
+| 0.0678        | 1.0    | 4323  | 0.1404          | 0.8551    | 0.8899 | 0.8721 | 0.9756   |
+| 0.0528        | 1.3333 | 5764  | 0.1332          | 0.8868    | 0.9040 | 0.8953 | 0.9800   |
+| 0.0523        | 1.6667 | 7205  | 0.1352          | 0.8868    | 0.9083 | 0.8974 | 0.9800   |
+| 0.0494        | 2.0    | 8646  | 0.1437          | 0.8855    | 0.9063 | 0.8958 | 0.9793   |
+| 0.0351        | 2.3333 | 10087 | 0.1592          | 0.8867    | 0.9092 | 0.8978 | 0.9794   |
+| 0.0341        | 2.6667 | 11528 | 0.1532          | 0.8919    | 0.9131 | 0.9024 | 0.9801   |
+| 0.034         | 3.0    | 12969 | 0.1404          | 0.8967    | 0.9155 | 0.9060 | 0.9808   |
+| 0.024         | 3.3333 | 14410 | 0.1601          | 0.8978    | 0.9145 | 0.9061 | 0.9805   |
+| 0.0267        | 3.6667 | 15851 | 0.1563          | 0.9047    | 0.9180 | 0.9113 | 0.9819   |
+| 0.0255        | 4.0    | 17292 | 0.1406          | 0.9093    | 0.9193 | 0.9142 | 0.9827   |
+| 0.0199        | 4.3333 | 18733 | 0.1604          | 0.9047    | 0.9225 | 0.9135 | 0.9821   |
+| 0.0187        | 4.6667 | 20174 | 0.1541          | 0.9106    | 0.9251 | 0.9178 | 0.9829   |
+| 0.0169        | 5.0    | 21615 | 0.1692          | 0.9009    | 0.9163 | 0.9085 | 0.9814   |
+| 0.0159        | 5.3333 | 23056 | 0.1738          | 0.9012    | 0.9205 | 0.9107 | 0.9817   |
+| 0.0141        | 5.6667 | 24497 | 0.1610          | 0.9039    | 0.9178 | 0.9108 | 0.9821   |
+| 0.0141        | 6.0    | 25938 | 0.1797          | 0.8977    | 0.9164 | 0.9070 | 0.9805   |
+| 0.0105        | 6.3333 | 27379 | 0.1707          | 0.9026    | 0.9187 | 0.9106 | 0.9821   |
+| 0.0104        | 6.6667 | 28820 | 0.1832          | 0.9036    | 0.9191 | 0.9113 | 0.9812   |
+| 0.0135        | 7.0    | 30261 | 0.1743          | 0.9024    | 0.9214 | 0.9118 | 0.9817   |
+| 0.0101        | 7.3333 | 31702 | 0.1877          | 0.9006    | 0.9194 | 0.9099 | 0.9812   |
+| 0.0113        | 7.6667 | 33143 | 0.1893          | 0.9009    | 0.9187 | 0.9097 | 0.9811   |
+| 0.0088        | 8.0    | 34584 | 0.1867          | 0.9050    | 0.9196 | 0.9123 | 0.9818   |
+| 0.0068        | 8.3333 | 36025 | 0.1901          | 0.9022    | 0.9182 | 0.9101 | 0.9812   |
+| 0.0088        | 8.6667 | 37466 | 0.1956          | 0.9037    | 0.9193 | 0.9114 | 0.9813   |
+| 0.0085        | 9.0    | 38907 | 0.1873          | 0.9055    | 0.9216 | 0.9135 | 0.9820   |
+| 0.0068        | 9.3333 | 40348 | 0.1922          | 0.9049    | 0.9217 | 0.9133 | 0.9817   |
+| 0.006         | 9.6667 | 41789 | 0.1915          | 0.9047    | 0.9214 | 0.9130 | 0.9817   |
+| 0.006         | 10.0   | 43230 | 0.1887          | 0.9051    | 0.9207 | 0.9128 | 0.9820   |
+
+
+### 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-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-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": 3072,
+  "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": 12,
+  "num_hidden_layers": 12,
+  "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:f9e7c23bfac374ed0eff8f2570b7816137bb150b7f2d5cd11a5bbc8fef629c02
+size 1109863956

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 sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

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:b8019bfb333859c35ba57408d14f7607c5e781813bfbf19f8be83f446a1ac02e
+size 5112