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 +1,75 @@
+---
+license: mit
+base_model: xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: xlm-roberta-base-finetuned-ner-thesis-dseb
+  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. -->
+
+# xlm-roberta-base-finetuned-ner-thesis-dseb
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1471
+- Precision: 0.7995
+- Recall: 0.9088
+- F1: 0.8506
+- Accuracy: 0.9605
+
+## 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: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 1.7775        | 1.0   | 31   | 0.3746          | 0.6199    | 0.6839 | 0.6503 | 0.8978   |
+| 0.1886        | 2.0   | 62   | 0.0734          | 0.9590    | 0.9301 | 0.9444 | 0.9875   |
+| 0.0821        | 3.0   | 93   | 0.0413          | 0.9697    | 0.9651 | 0.9674 | 0.9928   |
+| 0.0427        | 4.0   | 124  | 0.0400          | 0.9491    | 0.9635 | 0.9562 | 0.9911   |
+| 0.0352        | 5.0   | 155  | 0.0397          | 0.9421    | 0.9571 | 0.9496 | 0.9899   |
+| 0.0315        | 6.0   | 186  | 0.0410          | 0.9371    | 0.9579 | 0.9474 | 0.9895   |
+| 0.0344        | 7.0   | 217  | 0.0386          | 0.9612    | 0.9643 | 0.9627 | 0.9922   |
+| 0.0292        | 8.0   | 248  | 0.0383          | 0.9574    | 0.9651 | 0.9612 | 0.9921   |
+| 0.0286        | 9.0   | 279  | 0.0387          | 0.9543    | 0.9619 | 0.9581 | 0.9913   |
+| 0.0259        | 10.0  | 310  | 0.0415          | 0.9430    | 0.9595 | 0.9512 | 0.9901   |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,58 @@
+{
+  "_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": "O",
+    "1": "B-NAME",
+    "2": "I-NAME",
+    "3": "B-DATE",
+    "4": "I-DATE",
+    "5": "B-UNI",
+    "6": "I-UNI",
+    "7": "B-MAJ",
+    "8": "I-MAJ",
+    "9": "B-MAIL",
+    "10": "I-MAIL",
+    "11": "B-UNI_ABRREV",
+    "12": "I-PHONE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-DATE": 3,
+    "B-MAIL": 9,
+    "B-MAJ": 7,
+    "B-NAME": 1,
+    "B-UNI": 5,
+    "B-UNI_ABBREV": 11,
+    "I-DATE": 4,
+    "I-MAIL": 10,
+    "I-MAJ": 8,
+    "I-NAME": 2,
+    "I-PHONE": 12,
+    "I-UNI": 6,
+    "O": 0
+  },
+  "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": "4.42.3",
+  "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 sha256:13cecb2a6666b1ff8f1229bb2448e808e6c397b4542736c221a9a928e4522565
+size 1109876260

runs/Jul02_08-39-37_20cb1e4754d1/events.out.tfevents.1719910174.20cb1e4754d1.282.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d21243dd7c73912d640dca834b0756480f831b496e6257e50055df2b068e0103
+size 13638

runs/Jul02_08-39-37_20cb1e4754d1/events.out.tfevents.1719910363.20cb1e4754d1.282.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b914329ff735f2bc569d69325e1e2f2a72620464582a402c326d692a74cbf995
+size 1032

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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 sha256:527e9c3d048bd7bc6abe2e63ff7b8e37110134364244cee2292407ff334ca3b9
+size 5176