Training complete

README.md

@@ -0,0 +1,57 @@
+---
+license: mit
+base_model: ukr-models/xlm-roberta-base-uk
+tags:
+- generated_from_trainer
+datasets:
+- conll2003
+model-index:
+- name: bert-finetuned-ner
+ 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-ner
+
+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 conll2003 dataset.
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log | 1.0 | 20 | 1.9275 | 0.0065 | 0.0545 | 0.0116 | 0.0337 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -1,11 +1,12 @@
 {
- "_name_or_path": "bert-base-cased",
+ "_name_or_path": "ukr-models/xlm-roberta-base-uk",
  "architectures": [
- "BertForTokenClassification"
+ "XLMRobertaForTokenClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
+ "bos_token_id": 0,
  "classifier_dropout": null,
- "gradient_checkpointing": false,
+ "eos_token_id": 2,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
@@ -33,16 +34,17 @@
  "I-PER": 2,
  "O": 0
  },
- "layer_norm_eps": 1e-12,
- "max_position_embeddings": 512,
- "model_type": "bert",
+ "layer_norm_eps": 1e-05,
+ "max_position_embeddings": 514,
+ "model_type": "xlm-roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
- "pad_token_id": 0,
+ "output_past": true,
+ "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
- "transformers_version": "4.41.0",
- "type_vocab_size": 2,
+ "transformers_version": "4.41.2",
+ "type_vocab_size": 1,
  "use_cache": true,
- "vocab_size": 28996
+ "vocab_size": 31274
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5a8c53ad4d524b624a80371203963b05bac3641a25af0930dbaff263477142
-size 430929740
+oid sha256:a0d4aaa89abcbc3add75152be2e316a84b2e970497f6f7244a87a341ee65bc72
+size 437931412

runs/Jun07_07-36-01_f59316124154/events.out.tfevents.1717745769.f59316124154.229.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8632b5250e80bf1969b4933040d697b99b6fe434e1e198f649d7596da8456f
+size 6043

sentencepiece.bpe.model

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

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
- "cls_token": "[CLS]",
- "mask_token": "[MASK]",
- "pad_token": "[PAD]",
- "sep_token": "[SEP]",
- "unk_token": "[UNK]"
+ "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

@@ -1,55 +1,57 @@
 {
+ "add_prefix_space": true,
  "added_tokens_decoder": {
  "0": {
- "content": "[PAD]",
+ "content": "<s>",
  "lstrip": false,
  "normalized": false,
  "rstrip": false,
  "single_word": false,
  "special": true
  },
- "100": {
- "content": "[UNK]",
+ "1": {
+ "content": "<pad>",
  "lstrip": false,
  "normalized": false,
  "rstrip": false,
  "single_word": false,
  "special": true
  },
- "101": {
- "content": "[CLS]",
+ "2": {
+ "content": "</s>",
  "lstrip": false,
  "normalized": false,
  "rstrip": false,
  "single_word": false,
  "special": true
  },
- "102": {
- "content": "[SEP]",
+ "3": {
+ "content": "<unk>",
  "lstrip": false,
  "normalized": false,
  "rstrip": false,
  "single_word": false,
  "special": true
  },
- "103": {
- "content": "[MASK]",
- "lstrip": false,
- "normalized": false,
+ "31273": {
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
  "special": true
  }
  },
+ "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
- "cls_token": "[CLS]",
- "do_lower_case": false,
- "mask_token": "[MASK]",
- "model_max_length": 512,
- "pad_token": "[PAD]",
- "sep_token": "[SEP]",
- "strip_accents": null,
- "tokenize_chinese_chars": true,
- "tokenizer_class": "BertTokenizer",
- "unk_token": "[UNK]"
+ "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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0800a8dfc34e28ccbb79c26f635836305321f64aef3f1eeed3aafacba40f3816
+oid sha256:9edf8e98eee9058351918bac0b2d5615c785318f8e5e227f5c34ee61fd501eb8
 size 5112