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: encoder
+  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: 0.922421290659245
+    - name: Recall
+      type: recall
+      value: 0.9389164305949008
+    - name: F1
+      type: f1
+      value: 0.9305957708168815
+    - name: Accuracy
+      type: accuracy
+      value: 0.9842790998169484
+---
+
+<!-- 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. -->
+
+# encoder
+
+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: 0.2344
+- Precision: 0.9224
+- Recall: 0.9389
+- F1: 0.9306
+- Accuracy: 0.9843
+
+## 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 |
+|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.657         | 0.3333 | 1441  | 0.1806          | 0.8261    | 0.8383 | 0.8322 | 0.9700   |
+| 0.0884        | 0.6667 | 2882  | 0.1383          | 0.8822    | 0.8913 | 0.8867 | 0.9783   |
+| 0.0637        | 1.0    | 4323  | 0.1343          | 0.9032    | 0.9132 | 0.9082 | 0.9811   |
+| 0.0427        | 1.3333 | 5764  | 0.1527          | 0.9014    | 0.9210 | 0.9111 | 0.9817   |
+| 0.0412        | 1.6667 | 7205  | 0.1450          | 0.9109    | 0.9301 | 0.9204 | 0.9838   |
+| 0.0391        | 2.0    | 8646  | 0.1459          | 0.9145    | 0.9221 | 0.9183 | 0.9832   |
+| 0.0235        | 2.3333 | 10087 | 0.1848          | 0.9041    | 0.9313 | 0.9175 | 0.9821   |
+| 0.0228        | 2.6667 | 11528 | 0.1539          | 0.9188    | 0.9375 | 0.9281 | 0.9846   |
+| 0.0283        | 3.0    | 12969 | 0.1513          | 0.9137    | 0.9295 | 0.9215 | 0.9833   |
+| 0.0176        | 3.3333 | 14410 | 0.1748          | 0.9232    | 0.9347 | 0.9289 | 0.9842   |
+| 0.0177        | 3.6667 | 15851 | 0.1706          | 0.9234    | 0.9331 | 0.9282 | 0.9848   |
+| 0.0191        | 4.0    | 17292 | 0.1784          | 0.9095    | 0.9309 | 0.9201 | 0.9829   |
+| 0.0131        | 4.3333 | 18733 | 0.1862          | 0.9130    | 0.9361 | 0.9244 | 0.9833   |
+| 0.0138        | 4.6667 | 20174 | 0.1883          | 0.9133    | 0.9322 | 0.9226 | 0.9827   |
+| 0.0128        | 5.0    | 21615 | 0.1986          | 0.9104    | 0.9304 | 0.9203 | 0.9820   |
+| 0.0112        | 5.3333 | 23056 | 0.2002          | 0.9172    | 0.9356 | 0.9263 | 0.9833   |
+| 0.0097        | 5.6667 | 24497 | 0.1784          | 0.9257    | 0.9394 | 0.9325 | 0.9846   |
+| 0.0068        | 6.0    | 25938 | 0.1929          | 0.9210    | 0.9333 | 0.9271 | 0.9838   |
+| 0.0068        | 6.3333 | 27379 | 0.2086          | 0.9212    | 0.9382 | 0.9296 | 0.9840   |
+| 0.0057        | 6.6667 | 28820 | 0.2035          | 0.9240    | 0.9368 | 0.9304 | 0.9844   |
+| 0.006         | 7.0    | 30261 | 0.2098          | 0.9198    | 0.9379 | 0.9287 | 0.9841   |
+| 0.0042        | 7.3333 | 31702 | 0.2236          | 0.9182    | 0.9327 | 0.9254 | 0.9835   |
+| 0.0054        | 7.6667 | 33143 | 0.2267          | 0.9196    | 0.9361 | 0.9278 | 0.9833   |
+| 0.0029        | 8.0    | 34584 | 0.2162          | 0.9257    | 0.9375 | 0.9316 | 0.9846   |
+| 0.0022        | 8.3333 | 36025 | 0.2120          | 0.9241    | 0.9403 | 0.9322 | 0.9849   |
+| 0.0045        | 8.6667 | 37466 | 0.2185          | 0.9247    | 0.9393 | 0.9319 | 0.9846   |
+| 0.0029        | 9.0    | 38907 | 0.2182          | 0.9247    | 0.9387 | 0.9316 | 0.9846   |
+| 0.0021        | 9.3333 | 40348 | 0.2316          | 0.9231    | 0.9394 | 0.9312 | 0.9842   |
+| 0.002         | 9.6667 | 41789 | 0.2358          | 0.9226    | 0.9387 | 0.9306 | 0.9842   |
+| 0.0019        | 10.0   | 43230 | 0.2344          | 0.9224    | 0.9389 | 0.9306 | 0.9843   |
+
+
+### 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 sha256:092cd77e2929ec9764f95ae12b092504006f6e5765cac0cf633a3b5b4af3b17a
+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 sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+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:d6581b5bc4fcb15a5614c632eca21ae3b29ac1dd547ffb0b6dc43a0b0c2b6f64
+size 5176