End of training

README.md

@@ -0,0 +1,75 @@
+---
+license: mit
+base_model: ukr-models/xlm-roberta-base-uk
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: xddModel
+ 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. -->
+
+# xddModel
+
+This model is a fine-tuned version of [ukr-models/xlm-roberta-base-uk](https://huggingface.co/ukr-models/xlm-roberta-base-uk) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1495
+- Precision: 0.8533
+- Recall: 0.8819
+- F1: 0.8674
+- Accuracy: 0.9625
+
+## 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log | 1.0 | 175 | 0.1730 | 0.7640 | 0.8340 | 0.7975 | 0.9463 |
+| No log | 2.0 | 350 | 0.1552 | 0.8131 | 0.8585 | 0.8352 | 0.9527 |
+| 0.2473 | 3.0 | 525 | 0.1334 | 0.8433 | 0.8718 | 0.8573 | 0.9611 |
+| 0.2473 | 4.0 | 700 | 0.1305 | 0.8429 | 0.8784 | 0.8603 | 0.9615 |
+| 0.2473 | 5.0 | 875 | 0.1293 | 0.8541 | 0.8788 | 0.8663 | 0.9626 |
+| 0.0833 | 6.0 | 1050 | 0.1346 | 0.8449 | 0.8828 | 0.8634 | 0.9621 |
+| 0.0833 | 7.0 | 1225 | 0.1386 | 0.8449 | 0.8827 | 0.8634 | 0.9624 |
+| 0.0833 | 8.0 | 1400 | 0.1474 | 0.8548 | 0.8851 | 0.8697 | 0.9632 |
+| 0.0558 | 9.0 | 1575 | 0.1496 | 0.8485 | 0.8830 | 0.8654 | 0.9622 |
+| 0.0558 | 10.0 | 1750 | 0.1495 | 0.8533 | 0.8819 | 0.8674 | 0.9625 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,52 @@
+{
+ "_name_or_path": "ukr-models/xlm-roberta-base-uk",
+ "architectures": [
+ "XLMRobertaForTokenClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "bos_token_id": 0,
+ "classifier_dropout": null,
+ "eos_token_id": 2,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "o",
+ "1": "geo_region",
+ "2": "geo_city",
+ "3": "geo_district",
+ "4": "central_city",
+ "5": "geo_street",
+ "6": "geo_address",
+ "7": "geo_building",
+ "8": "geo_region_oblast",
+ "9": "geo_microdistrict"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "central_city": 4,
+ "geo_address": 6,
+ "geo_building": 7,
+ "geo_city": 2,
+ "geo_district": 3,
+ "geo_microdistrict": 9,
+ "geo_region": 1,
+ "geo_region_oblast": 8,
+ "geo_street": 5,
+ "o": 0
+ },
+ "layer_norm_eps": 1e-05,
+ "max_position_embeddings": 514,
+ "model_type": "xlm-roberta",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 12,
+ "output_past": true,
+ "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": 31274
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f3c10a0ed0dab676bb3e12167cf51dd8a2a167ec88dd87d48d00195e244055
+size 437934488

runs/Apr21_08-20-29_8bd65b148147/events.out.tfevents.1713687630.8bd65b148147.204.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d4906609b6e90ed46e6228311eecd3f9a1ad4ea100ff34d01050d0526328cb
+size 10826

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e60d59d103a3650d675c36c75b3a9c4b47e2c494eeea699f21ccd6e055f78feb
+size 854151

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+ "bos_token": "<s>",
+ "cls_token": "<s>",
+ "eos_token": "</s>",
+ "mask_token": {
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<pad>",
+ "sep_token": "</s>",
+ "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "31273": {
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<s>",
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "<s>",
+ "eos_token": "</s>",
+ "extra_ids": 0,
+ "mask_token": "<mask>",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "<pad>",
+ "sep_token": "</s>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "XLMRobertaTokenizer",
+ "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:add4b542781ad0991f2e79e82afe8e4734261df80bb56669f22260d3e169263d
+size 4856