Model save

README.md

@@ -0,0 +1,75 @@
+---
+base_model: alexyalunin/RuBioRoBERTa
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: nerel-bio-RuBioRoBERTa-base
+  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-RuBioRoBERTa-base
+
+This model is a fine-tuned version of [alexyalunin/RuBioRoBERTa](https://huggingface.co/alexyalunin/RuBioRoBERTa) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5262
+- Precision: 0.8251
+- Recall: 0.8335
+- F1: 0.8293
+- Accuracy: 0.8827
+
+## 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: 6
+- eval_batch_size: 6
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 102  | 1.7932          | 0.4125    | 0.4094 | 0.4110 | 0.5484   |
+| No log        | 2.0   | 204  | 0.5751          | 0.7711    | 0.7635 | 0.7673 | 0.8392   |
+| No log        | 3.0   | 306  | 0.4426          | 0.8053    | 0.8163 | 0.8107 | 0.8727   |
+| No log        | 4.0   | 408  | 0.4545          | 0.8070    | 0.8049 | 0.8060 | 0.8707   |
+| 0.8666        | 5.0   | 510  | 0.4854          | 0.8100    | 0.8024 | 0.8062 | 0.8693   |
+| 0.8666        | 6.0   | 612  | 0.4791          | 0.8194    | 0.8210 | 0.8202 | 0.8805   |
+| 0.8666        | 7.0   | 714  | 0.4975          | 0.8202    | 0.8306 | 0.8254 | 0.8816   |
+| 0.8666        | 8.0   | 816  | 0.4997          | 0.8217    | 0.8304 | 0.8260 | 0.8817   |
+| 0.8666        | 9.0   | 918  | 0.5237          | 0.8237    | 0.8318 | 0.8277 | 0.8821   |
+| 0.0548        | 10.0  | 1020 | 0.5262          | 0.8251    | 0.8335 | 0.8293 | 0.8827   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,122 @@
+{
+  "_name_or_path": "alexyalunin/RuBioRoBERTa",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "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": 4096,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1440fa09f5f49c5441c3863ecaf1209c36a164f42c91ef9fee6a11cf3293783c
+size 1417473100

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "c": ".cache",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c19964f690434ae8cf1576af359f052742366b64bd30131ddc8982f3e5e902
+size 4984