bodunok/bert-finetuned-tags-rus

README.md

@@ -0,0 +1,65 @@
+---
+base_model: DeepPavlov/rubert-base-cased
+tags:
+- generated_from_trainer
+model-index:
+- name: bert-finetuned-tags-rus
+  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. -->
+
+# bert-finetuned-tags-rus
+
+This model is a fine-tuned version of [DeepPavlov/rubert-base-cased](https://huggingface.co/DeepPavlov/rubert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0065
+
+## 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: 2e-05
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 92   | 0.0600          |
+| No log        | 2.0   | 184  | 0.0318          |
+| No log        | 3.0   | 276  | 0.0195          |
+| No log        | 4.0   | 368  | 0.0154          |
+| No log        | 5.0   | 460  | 0.0123          |
+| 0.0598        | 6.0   | 552  | 0.0093          |
+| 0.0598        | 7.0   | 644  | 0.0079          |
+| 0.0598        | 8.0   | 736  | 0.0078          |
+| 0.0598        | 9.0   | 828  | 0.0070          |
+| 0.0598        | 10.0  | 920  | 0.0065          |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.0.1+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "DeepPavlov/rubert-base-cased",
+  "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": "I-PER",
+    "1": "B-ORG",
+    "2": "O",
+    "3": "B-PER",
+    "4": "I-LOC",
+    "5": "I-ORG",
+    "6": "B-LOC",
+    "7": "<PAD>"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 6,
+    "B-ORG": 1,
+    "B-PER": 3,
+    "I-LOC": 4,
+    "I-ORG": 5,
+    "I-PER": 0,
+    "O": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "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",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc81fbc29a664e7927b4b2bfc6e8767eb46563bb6ab6a98f46c31f560ed22c35
+size 709099360

runs/Apr18_04-17-51_l-214bfc42-59df-41e6-8d08-897075e7899d/events.out.tfevents.1713413872.l-214bfc42-59df-41e6-8d08-897075e7899d.14268.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d5b7049530b61ce29a59061c3f65d131108eaf8b2d93e7715e9b092d683ec7
+size 5159

runs/Apr18_04-18-08_l-214bfc42-59df-41e6-8d08-897075e7899d/events.out.tfevents.1713413895.l-214bfc42-59df-41e6-8d08-897075e7899d.14268.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f06d07993ffc4c1f303190708e2106e1f4db79c9c0debb899c111f128342a85
+size 8426

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 +1,57 @@
+{
+  "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:ebe99ba91c8538f36d481ade5b61371414fa91a468a27535a9fecfb690fbb5d8
+size 4539