Training in progress, epoch 1

.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

config.json

@@ -0,0 +1,131 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large-finetuned-conll03-english",
+  "_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-AGE",
+    "1": "B-STAGE",
+    "2": "B-DATE",
+    "3": "B-IMPLICIT_DATE",
+    "4": "B-TNM",
+    "5": "B-FAMILY",
+    "6": "B-OCURRENCE_EVENT",
+    "7": "B-TOXIC_HABITS",
+    "8": "B-HABIT-QUANTITY",
+    "9": "B-TREATMENT_NAME",
+    "10": "B-LINE_CICLE_NUMBER",
+    "11": "B-SURGERY",
+    "12": "B-DRUG",
+    "13": "B-DOSE",
+    "14": "B-FREQ",
+    "15": "B-BIOMARKER",
+    "16": "B-CLINICAL_SERVICE",
+    "17": "B-COMORBIDITY",
+    "18": "B-PROGRESION",
+    "19": "B-GINECOLOGICAL_HISTORY",
+    "20": "B-GINE_OBSTETRICS",
+    "21": "B-ALLERGIES",
+    "22": "B-DURATION",
+    "23": "I-AGE",
+    "24": "I-STAGE",
+    "25": "I-DATE",
+    "26": "I-IMPLICIT_DATE",
+    "27": "I-TNM",
+    "28": "I-FAMILY",
+    "29": "I-OCURRENCE_EVENT",
+    "30": "I-TOXIC_HABITS",
+    "31": "I-HABIT-QUANTITY",
+    "32": "I-TREATMENT_NAME",
+    "33": "I-LINE_CICLE_NUMBER",
+    "34": "I-SURGERY",
+    "35": "I-DRUG",
+    "36": "I-DOSE",
+    "37": "I-FREQ",
+    "38": "I-BIOMARKER",
+    "39": "I-CLINICAL_SERVICE",
+    "40": "I-COMORBIDITY",
+    "41": "I-PROGRESION",
+    "42": "I-GINECOLOGICAL_HISTORY",
+    "43": "I-GINE_OBSTETRICS",
+    "44": "I-ALLERGIES",
+    "45": "I-DURATION",
+    "46": "B-CANCER_CONCEPT",
+    "47": "I-CANCER_CONCEPT",
+    "48": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-AGE": 0,
+    "B-ALLERGIES": 21,
+    "B-BIOMARKER": 15,
+    "B-CANCER_CONCEPT": 46,
+    "B-CLINICAL_SERVICE": 16,
+    "B-COMORBIDITY": 17,
+    "B-DATE": 2,
+    "B-DOSE": 13,
+    "B-DRUG": 12,
+    "B-DURATION": 22,
+    "B-FAMILY": 5,
+    "B-FREQ": 14,
+    "B-GINECOLOGICAL_HISTORY": 19,
+    "B-GINE_OBSTETRICS": 20,
+    "B-HABIT-QUANTITY": 8,
+    "B-IMPLICIT_DATE": 3,
+    "B-LINE_CICLE_NUMBER": 10,
+    "B-OCURRENCE_EVENT": 6,
+    "B-PROGRESION": 18,
+    "B-STAGE": 1,
+    "B-SURGERY": 11,
+    "B-TNM": 4,
+    "B-TOXIC_HABITS": 7,
+    "B-TREATMENT_NAME": 9,
+    "I-AGE": 23,
+    "I-ALLERGIES": 44,
+    "I-BIOMARKER": 38,
+    "I-CANCER_CONCEPT": 47,
+    "I-CLINICAL_SERVICE": 39,
+    "I-COMORBIDITY": 40,
+    "I-DATE": 25,
+    "I-DOSE": 36,
+    "I-DRUG": 35,
+    "I-DURATION": 45,
+    "I-FAMILY": 28,
+    "I-FREQ": 37,
+    "I-GINECOLOGICAL_HISTORY": 42,
+    "I-GINE_OBSTETRICS": 43,
+    "I-HABIT-QUANTITY": 31,
+    "I-IMPLICIT_DATE": 26,
+    "I-LINE_CICLE_NUMBER": 33,
+    "I-OCURRENCE_EVENT": 29,
+    "I-PROGRESION": 41,
+    "I-STAGE": 24,
+    "I-SURGERY": 34,
+    "I-TNM": 27,
+    "I-TOXIC_HABITS": 30,
+    "I-TREATMENT_NAME": 32,
+    "O": 48
+  },
+  "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": "4.46.3",
+  "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 sha256:947b6b7457e557e5cdf29b696ce18e8390fa4f38faaa46a04769e15dc056aa37
+size 2235612764

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 sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": false,
+  "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:f43cbbc3dfbbd1c47633fd5ae3492ce092c717e0866380668bf6366455b9b530
+size 5368