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 +1,94 @@
+---
+library_name: transformers
+base_model: raulgdp/xml-roberta-large-finetuned-ner
+tags:
+- generated_from_trainer
+datasets:
+- biobert_json
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: NER-finetuning-XMLR-CM-V1
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: biobert_json
+      type: biobert_json
+      config: Biobert_json
+      split: validation
+      args: Biobert_json
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9336523819882532
+    - name: Recall
+      type: recall
+      value: 0.9595349877040018
+    - name: F1
+      type: f1
+      value: 0.9464167585446528
+    - name: Accuracy
+      type: accuracy
+      value: 0.9819591471596839
+---
+
+<!-- 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. -->
+
+# NER-finetuning-XMLR-CM-V1
+
+This model is a fine-tuned version of [raulgdp/xml-roberta-large-finetuned-ner](https://huggingface.co/raulgdp/xml-roberta-large-finetuned-ner) on the biobert_json dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0849
+- Precision: 0.9337
+- Recall: 0.9595
+- F1: 0.9464
+- 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.2697        | 1.0   | 612  | 0.0995          | 0.9022    | 0.9392 | 0.9203 | 0.9726   |
+| 0.0954        | 2.0   | 1224 | 0.0909          | 0.9171    | 0.9586 | 0.9374 | 0.9778   |
+| 0.0661        | 3.0   | 1836 | 0.0789          | 0.9337    | 0.9581 | 0.9457 | 0.9816   |
+| 0.0533        | 4.0   | 2448 | 0.0853          | 0.9317    | 0.9594 | 0.9454 | 0.9811   |
+| 0.035         | 5.0   | 3060 | 0.0849          | 0.9337    | 0.9595 | 0.9464 | 0.9820   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,93 @@
+{
+  "_name_or_path": "raulgdp/xml-roberta-large-finetuned-ner",
+  "_num_labels": 8,
+  "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_CANCER_CONCEPT",
+    "1": "B_CHEMOTHERAPY",
+    "2": "B_DATE",
+    "3": "B_DRUG",
+    "4": "B_FAMILY",
+    "5": "B_FREQ",
+    "6": "B_IMPLICIT_DATE",
+    "7": "B_INTERVAL",
+    "8": "B_METRIC",
+    "9": "B_OCURRENCE_EVENT",
+    "10": "B_QUANTITY",
+    "11": "B_RADIOTHERAPY",
+    "12": "B_SMOKER_STATUS",
+    "13": "B_STAGE",
+    "14": "B_SURGERY",
+    "15": "B_TNM",
+    "16": "I_CANCER_CONCEPT",
+    "17": "I_DATE",
+    "18": "I_DRUG",
+    "19": "I_FAMILY",
+    "20": "I_FREQ",
+    "21": "I_IMPLICIT_DATE",
+    "22": "I_INTERVAL",
+    "23": "I_METRIC",
+    "24": "I_OCURRENCE_EVENT",
+    "25": "I_SMOKER_STATUS",
+    "26": "I_STAGE",
+    "27": "I_SURGERY",
+    "28": "I_TNM",
+    "29": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B_CANCER_CONCEPT": 0,
+    "B_CHEMOTHERAPY": 1,
+    "B_DATE": 2,
+    "B_DRUG": 3,
+    "B_FAMILY": 4,
+    "B_FREQ": 5,
+    "B_IMPLICIT_DATE": 6,
+    "B_INTERVAL": 7,
+    "B_METRIC": 8,
+    "B_OCURRENCE_EVENT": 9,
+    "B_QUANTITY": 10,
+    "B_RADIOTHERAPY": 11,
+    "B_SMOKER_STATUS": 12,
+    "B_STAGE": 13,
+    "B_SURGERY": 14,
+    "B_TNM": 15,
+    "I_CANCER_CONCEPT": 16,
+    "I_DATE": 17,
+    "I_DRUG": 18,
+    "I_FAMILY": 19,
+    "I_FREQ": 20,
+    "I_IMPLICIT_DATE": 21,
+    "I_INTERVAL": 22,
+    "I_METRIC": 23,
+    "I_OCURRENCE_EVENT": 24,
+    "I_SMOKER_STATUS": 25,
+    "I_STAGE": 26,
+    "I_SURGERY": 27,
+    "I_TNM": 28,
+    "O": 29
+  },
+  "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": "4.44.2",
+  "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:e8f37a437027dc30e8c7f01c2f5203bfa33f5ff05dc7d053b82df03547308444
+size 2235534864

runs/Nov20_14-00-40_972e66497d93/events.out.tfevents.1732111411.972e66497d93.376.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2e2db2fa1cc87fe4cd8048bcf1450628670a892eb22d08f4241e3757acb790
+size 10418

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 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": true,
+  "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>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2874d5c4d02a70ba10048279bd78d0655c52c9939928b671957b0ac7422f703
+size 5176