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 +1,121 @@
+---
+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-FP16-BinaryClass-WeightedLoss
+  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: 0.9526306589757035
+    - name: Recall
+      type: recall
+      value: 0.964943342776204
+    - name: F1
+      type: f1
+      value: 0.9587474711935965
+    - name: Accuracy
+      type: accuracy
+      value: 0.9901367502961128
+---
+
+<!-- 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-FP16-BinaryClass-WeightedLoss
+
+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: 0.1188
+- Precision: 0.9526
+- Recall: 0.9649
+- F1: 0.9587
+- Accuracy: 0.9901
+
+## 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
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.2739        | 0.3333 | 1441  | 0.0632          | 0.9412    | 0.9373 | 0.9392 | 0.9863   |
+| 0.0329        | 0.6667 | 2882  | 0.0572          | 0.9435    | 0.9347 | 0.9391 | 0.9865   |
+| 0.024         | 1.0    | 4323  | 0.0679          | 0.9433    | 0.9536 | 0.9484 | 0.9882   |
+| 0.0181        | 1.3333 | 5764  | 0.0652          | 0.9458    | 0.9618 | 0.9537 | 0.9897   |
+| 0.0187        | 1.6667 | 7205  | 0.0625          | 0.9531    | 0.9492 | 0.9511 | 0.9895   |
+| 0.0176        | 2.0    | 8646  | 0.0685          | 0.9488    | 0.9573 | 0.9530 | 0.9896   |
+| 0.0108        | 2.3333 | 10087 | 0.0931          | 0.9470    | 0.9625 | 0.9547 | 0.9897   |
+| 0.0117        | 2.6667 | 11528 | 0.0808          | 0.9489    | 0.9632 | 0.9560 | 0.9900   |
+| 0.0107        | 3.0    | 12969 | 0.0672          | 0.9531    | 0.9602 | 0.9566 | 0.9908   |
+| 0.0076        | 3.3333 | 14410 | 0.0973          | 0.9470    | 0.9587 | 0.9528 | 0.9897   |
+| 0.0085        | 3.6667 | 15851 | 0.0741          | 0.9574    | 0.9549 | 0.9561 | 0.9906   |
+| 0.0092        | 4.0    | 17292 | 0.0807          | 0.9492    | 0.9621 | 0.9556 | 0.9901   |
+| 0.0049        | 4.3333 | 18733 | 0.0886          | 0.9527    | 0.9623 | 0.9575 | 0.9906   |
+| 0.0058        | 4.6667 | 20174 | 0.0871          | 0.9516    | 0.9639 | 0.9577 | 0.9904   |
+| 0.0047        | 5.0    | 21615 | 0.0928          | 0.9541    | 0.9610 | 0.9576 | 0.9903   |
+| 0.0041        | 5.3333 | 23056 | 0.1145          | 0.9491    | 0.9667 | 0.9578 | 0.9899   |
+| 0.0048        | 5.6667 | 24497 | 0.0854          | 0.9554    | 0.9623 | 0.9588 | 0.9907   |
+| 0.0032        | 6.0    | 25938 | 0.1107          | 0.9488    | 0.9651 | 0.9569 | 0.9899   |
+| 0.003         | 6.3333 | 27379 | 0.1038          | 0.9524    | 0.9674 | 0.9599 | 0.9907   |
+| 0.0032        | 6.6667 | 28820 | 0.1038          | 0.9533    | 0.9651 | 0.9592 | 0.9904   |
+| 0.0034        | 7.0    | 30261 | 0.1038          | 0.9534    | 0.9667 | 0.9600 | 0.9906   |
+| 0.0025        | 7.3333 | 31702 | 0.1103          | 0.9528    | 0.9619 | 0.9574 | 0.9899   |
+| 0.003         | 7.6667 | 33143 | 0.1177          | 0.9506    | 0.9644 | 0.9575 | 0.9899   |
+| 0.0022        | 8.0    | 34584 | 0.1151          | 0.9511    | 0.9633 | 0.9572 | 0.9900   |
+| 0.0016        | 8.3333 | 36025 | 0.1141          | 0.9528    | 0.9651 | 0.9589 | 0.9904   |
+| 0.0025        | 8.6667 | 37466 | 0.1090          | 0.9550    | 0.9626 | 0.9588 | 0.9905   |
+| 0.0024        | 9.0    | 38907 | 0.1115          | 0.9546    | 0.9653 | 0.9599 | 0.9906   |
+| 0.002         | 9.3333 | 40348 | 0.1148          | 0.9536    | 0.9639 | 0.9587 | 0.9903   |
+| 0.0014        | 9.6667 | 41789 | 0.1201          | 0.9522    | 0.9655 | 0.9588 | 0.9902   |
+| 0.0015        | 10.0   | 43230 | 0.1188          | 0.9526    | 0.9649 | 0.9587 | 0.9901   |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,38 @@
+{
+  "_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-MISC",
+    "1": "I-MISC",
+    "2": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-MISC": 0,
+    "I-MISC": 1,
+    "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": "4.41.1",
+  "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:fc591e20e6f399dbbfccc365d76347757a20c9d5ffe5da4ff2e5b0a2ca126901
+size 1109845500

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:bfd611d34af4bb2ea5e9d83cf09624d76c42f82a84fe8607532ee7e1578f5d5b
+size 5176