Model save

README.md

@@ -1,3 +1,75 @@
 ---
-license: mit
+base_model: alexyalunin/RuBioBERT
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: nerel-bio-RuBioBERT-al
+  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. -->
+
+# nerel-bio-RuBioBERT-al
+
+This model is a fine-tuned version of [alexyalunin/RuBioBERT](https://huggingface.co/alexyalunin/RuBioBERT) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9026
+- Precision: 0.7943
+- Recall: 0.7969
+- F1: 0.7956
+- Accuracy: 0.8601
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0824        | 1.0   | 107  | 0.7494          | 0.7913    | 0.7941 | 0.7927 | 0.8564   |
+| 0.0463        | 2.0   | 214  | 0.8337          | 0.7781    | 0.7814 | 0.7798 | 0.8491   |
+| 0.0368        | 3.0   | 321  | 0.8365          | 0.7893    | 0.7941 | 0.7917 | 0.8538   |
+| 0.0214        | 4.0   | 428  | 0.8609          | 0.7888    | 0.7875 | 0.7882 | 0.8561   |
+| 0.0117        | 5.0   | 535  | 0.8701          | 0.7926    | 0.7913 | 0.7919 | 0.8577   |
+| 0.0069        | 6.0   | 642  | 0.8605          | 0.7889    | 0.7906 | 0.7897 | 0.8558   |
+| 0.004         | 7.0   | 749  | 0.8890          | 0.7932    | 0.7997 | 0.7964 | 0.8597   |
+| 0.0035        | 8.0   | 856  | 0.8995          | 0.7922    | 0.7967 | 0.7944 | 0.8589   |
+| 0.0021        | 9.0   | 963  | 0.9024          | 0.7943    | 0.7969 | 0.7956 | 0.8601   |
+| 0.0014        | 10.0  | 1070 | 0.9026          | 0.7943    | 0.7969 | 0.7956 | 0.8601   |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,125 @@
+{
+  "_name_or_path": "alexyalunin/RuBioBERT",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ACTIVITY",
+    "1": "ADMINISTRATION_ROUTE",
+    "2": "ANATOMY",
+    "3": "CHEM",
+    "4": "DEVICE",
+    "5": "DISO",
+    "6": "FINDING",
+    "7": "FOOD",
+    "8": "GENE",
+    "9": "INJURY_POISONING",
+    "10": "HEALTH_CARE_ACTIVITY",
+    "11": "LABPROC",
+    "12": "LIVB",
+    "13": "MEDPROC",
+    "14": "MENTALPROC",
+    "15": "PHYS",
+    "16": "SCIPROC",
+    "17": "AGE",
+    "18": "CITY",
+    "19": "COUNTRY",
+    "20": "DATE",
+    "21": "DISTRICT",
+    "22": "EVENT",
+    "23": "FAMILY",
+    "24": "FACILITY",
+    "25": "LOCATION",
+    "26": "MONEY",
+    "27": "NATIONALITY",
+    "28": "NUMBER",
+    "29": "ORDINAL",
+    "30": "ORGANIZATION",
+    "31": "PERCENT",
+    "32": "PERSON",
+    "33": "PRODUCT",
+    "34": "PROFESSION",
+    "35": "STATE_OR_PROVINCE",
+    "36": "TIME",
+    "37": "AWARD",
+    "38": "CRIME",
+    "39": "IDEOLOGY",
+    "40": "LANGUAGE",
+    "41": "LAW",
+    "42": "PENALTY",
+    "43": "RELIGION",
+    "44": "WORK_OF_ART"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ACTIVITY": 0,
+    "ADMINISTRATION_ROUTE": 1,
+    "AGE": 17,
+    "ANATOMY": 2,
+    "AWARD": 37,
+    "CHEM": 3,
+    "CITY": 18,
+    "COUNTRY": 19,
+    "CRIME": 38,
+    "DATE": 20,
+    "DEVICE": 4,
+    "DISO": 5,
+    "DISTRICT": 21,
+    "EVENT": 22,
+    "FACILITY": 24,
+    "FAMILY": 23,
+    "FINDING": 6,
+    "FOOD": 7,
+    "GENE": 8,
+    "HEALTH_CARE_ACTIVITY": 10,
+    "IDEOLOGY": 39,
+    "INJURY_POISONING": 9,
+    "LABPROC": 11,
+    "LANGUAGE": 40,
+    "LAW": 41,
+    "LIVB": 12,
+    "LOCATION": 25,
+    "MEDPROC": 13,
+    "MENTALPROC": 14,
+    "MONEY": 26,
+    "NATIONALITY": 27,
+    "NUMBER": 28,
+    "ORDINAL": 29,
+    "ORGANIZATION": 30,
+    "PENALTY": 42,
+    "PERCENT": 31,
+    "PERSON": 32,
+    "PHYS": 15,
+    "PRODUCT": 33,
+    "PROFESSION": 34,
+    "RELIGION": 43,
+    "SCIPROC": 16,
+    "STATE_OR_PROVINCE": 35,
+    "TIME": 36,
+    "WORK_OF_ART": 44
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 120138
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee86b1d40d71965c06f66916e70faee2e3c0fcf44f5dc8ccb4f8155181a3339e
+size 711028724

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "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": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49631093f34a5de60a822b33c8e428bdad43a3447b643ffb5a473e543d18de08
+size 4984