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 +1,93 @@
+{
+  "_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": "4.46.2",
+  "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 sha256:760e0e0833cb069b440bcd5216719f05d9818aca0774e3843aeb7c429024ffe5
+size 2235534864

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 sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

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 sha256:259ff9a1fcc3c7b1f82e995540346d823f778dfb272c6898f61e8dacbb657f73
+size 5304