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
+vocab.txt filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "imvladikon/alephbertgimmel-base-512",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "TREATMENT",
+    "1": "PROTECTED_HEALTH_INFORMATION_EMAIL",
+    "2": "PROTECTED_HEALTH_INFORMATION_LOCATION",
+    "3": "RESPIRATORY_RATE",
+    "4": "PROTECTED_HEALTH_INFORMATION_MEDICAL_RECORD",
+    "5": "ALCOHOL_USE",
+    "6": "SYMPTOM",
+    "7": "PROTECTED_HEALTH_INFORMATION_NAME",
+    "8": "0",
+    "9": "ALCOHOL_DRUGS",
+    "10": "BLOOD_PRESSURE",
+    "11": "TOBACCO_USE",
+    "12": "MEASUREMENT",
+    "13": "OBSERVATION",
+    "14": "AFFECTED_BODY_PARTS",
+    "15": "ANATOMY",
+    "16": "PROTECTED_HEALTH_INFORMATION_DATE",
+    "17": "PROTECTED_HEALTH_INFORMATION_PHONE_NUMBER",
+    "18": "TEMPERATURE",
+    "19": "DIAGNOSIS",
+    "20": "PROTECTED_HEALTH_INFORMATION_AGE",
+    "21": "MEDICAL_CONDITION",
+    "22": "PULSE",
+    "23": "TEST",
+    "24": "MEDICATION",
+    "25": "AFFECTED_ORGANS"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 8,
+    "AFFECTED_BODY_PARTS": 14,
+    "AFFECTED_ORGANS": 25,
+    "ALCOHOL_DRUGS": 9,
+    "ALCOHOL_USE": 5,
+    "ANATOMY": 15,
+    "BLOOD_PRESSURE": 10,
+    "DIAGNOSIS": 19,
+    "MEASUREMENT": 12,
+    "MEDICAL_CONDITION": 21,
+    "MEDICATION": 24,
+    "OBSERVATION": 13,
+    "PROTECTED_HEALTH_INFORMATION_AGE": 20,
+    "PROTECTED_HEALTH_INFORMATION_DATE": 16,
+    "PROTECTED_HEALTH_INFORMATION_EMAIL": 1,
+    "PROTECTED_HEALTH_INFORMATION_LOCATION": 2,
+    "PROTECTED_HEALTH_INFORMATION_MEDICAL_RECORD": 4,
+    "PROTECTED_HEALTH_INFORMATION_NAME": 7,
+    "PROTECTED_HEALTH_INFORMATION_PHONE_NUMBER": 17,
+    "PULSE": 22,
+    "RESPIRATORY_RATE": 3,
+    "SYMPTOM": 6,
+    "TEMPERATURE": 18,
+    "TEST": 23,
+    "TOBACCO_USE": 11,
+    "TREATMENT": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 128000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ed566dd4e1d6a9e3a7c3084bc93fd95f2585c964d4cb46113af73de25b373a
+size 735166697

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation": true,
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6527476441d1838c27663980ba124a3796232b9e004777db5334050f642165a7
+size 4091

vocab.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c8eb3d9f7ef0b8f036227785d1dbdc90926ba6816d3899736832d912ccd52e2
+size 1296919