End of training

README.md

@@ -0,0 +1,69 @@
+---
+base_model: ai-forever/ruBert-large
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: ruBert-large-finetuned-pos
+  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. -->
+
+# ruBert-large-finetuned-pos
+
+This model is a fine-tuned version of [ai-forever/ruBert-large](https://huggingface.co/ai-forever/ruBert-large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1115
+- Precision: 0.8617
+- Recall: 0.8901
+- F1: 0.8757
+- Accuracy: 0.8922
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 249  | 0.1606          | 0.8280    | 0.8462 | 0.8370 | 0.8235   |
+| No log        | 2.0   | 498  | 0.1197          | 0.8817    | 0.9011 | 0.8913 | 0.8922   |
+| 0.0726        | 3.0   | 747  | 0.1207          | 0.8617    | 0.8901 | 0.8757 | 0.8824   |
+| 0.0726        | 4.0   | 996  | 0.1115          | 0.8617    | 0.8901 | 0.8757 | 0.8922   |
+| 0.0016        | 5.0   | 1245 | 0.1136          | 0.8723    | 0.9011 | 0.8865 | 0.9020   |
+
+
+### Framework versions
+
+- Transformers 4.39.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,147 @@
+{
+  "_name_or_path": "ai-forever/ruBert-large",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "Not",
+    "2": "Abbr",
+    "3": "Adj",
+    "4": "Adv",
+    "5": "Adv/action_des\u0441",
+    "6": "Adv/action_time",
+    "7": "Adv/measure",
+    "8": "Adv/place",
+    "9": "Adv/emph",
+    "10": "Advt",
+    "11": "Advt1",
+    "12": "Aux",
+    "13": "Bracket",
+    "14": "Colon",
+    "15": "Comma",
+    "16": "Conj.comp",
+    "17": "Coord",
+    "18": "Dash",
+    "19": "Dot",
+    "20": "Ellipsis",
+    "21": "Fw",
+    "22": "Interj.",
+    "23": "Interrog.word",
+    "24": "Introduct",
+    "25": "Mark/excl",
+    "26": "Mark/quest",
+    "27": "Measure",
+    "28": "N",
+    "29": "Num",
+    "30": "Num/ordinal",
+    "31": "Part/dem",
+    "32": "Part/excl",
+    "33": "Part/limit",
+    "34": "Part/imp",
+    "35": "Part/intens",
+    "36": "Part/neg",
+    "37": "Part/quest",
+    "38": "Part/soft",
+    "39": "Prep",
+    "40": "Pron",
+    "41": "Pron/attr",
+    "42": "Pron/dem",
+    "43": "Pron/neg",
+    "44": "Pron/pos",
+    "45": "Pron/rel",
+    "46": "Particip/adj",
+    "47": "Particip/v",
+    "48": "Punct",
+    "49": "Quote",
+    "50": "Semicolon",
+    "51": "State",
+    "52": "Sub",
+    "53": "Vf",
+    "54": "Vinf",
+    "55": "Vm"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Abbr": 2,
+    "Adj": 3,
+    "Adv": 4,
+    "Adv/action_des\u0441": 5,
+    "Adv/action_time": 6,
+    "Adv/emph": 9,
+    "Adv/measure": 7,
+    "Adv/place": 8,
+    "Advt": 10,
+    "Advt1": 11,
+    "Aux": 12,
+    "Bracket": 13,
+    "Colon": 14,
+    "Comma": 15,
+    "Conj.comp": 16,
+    "Coord": 17,
+    "Dash": 18,
+    "Dot": 19,
+    "Ellipsis": 20,
+    "Fw": 21,
+    "Interj.": 22,
+    "Interrog.word": 23,
+    "Introduct": 24,
+    "Mark/excl": 25,
+    "Mark/quest": 26,
+    "Measure": 27,
+    "N": 28,
+    "Not": 1,
+    "Num": 29,
+    "Num/ordinal": 30,
+    "O": 0,
+    "Part/dem": 31,
+    "Part/excl": 32,
+    "Part/imp": 34,
+    "Part/intens": 35,
+    "Part/limit": 33,
+    "Part/neg": 36,
+    "Part/quest": 37,
+    "Part/soft": 38,
+    "Particip/adj": 46,
+    "Particip/v": 47,
+    "Prep": 39,
+    "Pron": 40,
+    "Pron/attr": 41,
+    "Pron/dem": 42,
+    "Pron/neg": 43,
+    "Pron/pos": 44,
+    "Pron/rel": 45,
+    "Punct": 48,
+    "Quote": 49,
+    "Semicolon": 50,
+    "State": 51,
+    "Sub": 52,
+    "Vf": 53,
+    "Vinf": 54,
+    "Vm": 55
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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": "4.39.0",
+  "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:e0069ba49c1ebe2cc1b2eab8fa6852cd5765e27bdc9e8035aaef8b169ec3ab06
+size 1703712944

runs/Mar22_09-58-05_91f1920f28f1/events.out.tfevents.1711101486.91f1920f28f1.2737.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace1c8043aa5222f016bcae8793ed8264aca0824bb7391fc77122a1f189ba14d
+size 7492

runs/Mar22_10-05-26_91f1920f28f1/events.out.tfevents.1711101928.91f1920f28f1.2737.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2caa2c27ddfbfeb955a9b33d6af28327f5199a96d0945c1c603222ece94cd0f1
+size 7492

runs/Mar22_10-06-59_91f1920f28f1/events.out.tfevents.1711102020.91f1920f28f1.2737.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8ca9bfa7fa95e80ed79a967384b7f0ea562088c6504fdbdd58b709bf5dd9fa7
+size 7028

runs/Mar22_10-10-03_91f1920f28f1/events.out.tfevents.1711102204.91f1920f28f1.2737.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eef35971228f09d3329ee4f1a0780fbf1696d0c02426cb0b81c9755abff1bce
+size 7028

runs/Mar22_10-14-29_91f1920f28f1/events.out.tfevents.1711102470.91f1920f28f1.2737.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e3a7211af2c6b2d7b0798f3685a03b66eceedef519a1089051ab123f7c69b70
+size 7028

runs/Mar22_10-16-43_91f1920f28f1/events.out.tfevents.1711102604.91f1920f28f1.2737.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a6d4c3b783558d969f574bedfd6142564c237d231a2bbf5c444b83e4b252416
+size 7028

runs/Mar22_10-27-18_91f1920f28f1/events.out.tfevents.1711103239.91f1920f28f1.2737.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbce295dbae89eb42c4be6ff0f4b4fbdc1e2b030049cc504d41c65fbdfa077ab
+size 7028

runs/Mar22_10-27-49_91f1920f28f1/events.out.tfevents.1711103271.91f1920f28f1.2737.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e3375e7ad807f115875a0794db7eaa6bf741331677b87e1b9df2813d26ab5f
+size 7028

runs/Mar22_10-28-10_91f1920f28f1/events.out.tfevents.1711103291.91f1920f28f1.2737.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd7b41372d40361fb42ba2c02a8bef36feb4a9b256288084836787784d48117
+size 7028

runs/Mar22_10-29-25_91f1920f28f1/events.out.tfevents.1711103368.91f1920f28f1.2737.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6080e115b63820b0b88eabdf887eae3c6e4776d940cff92c23ea7f5543d73d5c
+size 10164

runs/Mar22_10-29-25_91f1920f28f1/events.out.tfevents.1711104948.91f1920f28f1.2737.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90eeec390b0b8b458cf7152ed177554e135d13e462c38693cebf7ab5ab4b0480
+size 560

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 +1,60 @@
+{
+  "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": true,
+  "mask_token": "[MASK]",
+  "max_length": 100,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "padding": true,
+  "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 sha256:07c3766f54af02eeda73147e68b03bbb23055780932f4d58fc8736d9901f590a
+size 4920