Training complete
Browse files- README.md +57 -0
- config.json +12 -10
- model.safetensors +2 -2
- runs/Jun07_07-36-01_f59316124154/events.out.tfevents.1717745769.f59316124154.229.0 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +13 -5
- tokenizer.json +0 -0
- tokenizer_config.json +23 -21
- training_args.bin +1 -1
README.md
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: ukr-models/xlm-roberta-base-uk
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- conll2003
|
8 |
+
model-index:
|
9 |
+
- name: bert-finetuned-ner
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# bert-finetuned-ner
|
17 |
+
|
18 |
+
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.
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 2e-05
|
38 |
+
- train_batch_size: 1
|
39 |
+
- eval_batch_size: 1
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 1
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
49 |
+
| No log | 1.0 | 20 | 1.9275 | 0.0065 | 0.0545 | 0.0116 | 0.0337 |
|
50 |
+
|
51 |
+
|
52 |
+
### Framework versions
|
53 |
+
|
54 |
+
- Transformers 4.41.2
|
55 |
+
- Pytorch 2.3.0+cu121
|
56 |
+
- Datasets 2.19.2
|
57 |
+
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -1,11 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
7 |
"classifier_dropout": null,
|
8 |
-
"
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
@@ -33,16 +34,17 @@
|
|
33 |
"I-PER": 2,
|
34 |
"O": 0
|
35 |
},
|
36 |
-
"layer_norm_eps": 1e-
|
37 |
-
"max_position_embeddings":
|
38 |
-
"model_type": "
|
39 |
"num_attention_heads": 12,
|
40 |
"num_hidden_layers": 12,
|
41 |
-
"
|
|
|
42 |
"position_embedding_type": "absolute",
|
43 |
"torch_dtype": "float32",
|
44 |
-
"transformers_version": "4.41.
|
45 |
-
"type_vocab_size":
|
46 |
"use_cache": true,
|
47 |
-
"vocab_size":
|
48 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "ukr-models/xlm-roberta-base-uk",
|
3 |
"architectures": [
|
4 |
+
"XLMRobertaForTokenClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
"hidden_size": 768,
|
|
|
34 |
"I-PER": 2,
|
35 |
"O": 0
|
36 |
},
|
37 |
+
"layer_norm_eps": 1e-05,
|
38 |
+
"max_position_embeddings": 514,
|
39 |
+
"model_type": "xlm-roberta",
|
40 |
"num_attention_heads": 12,
|
41 |
"num_hidden_layers": 12,
|
42 |
+
"output_past": true,
|
43 |
+
"pad_token_id": 1,
|
44 |
"position_embedding_type": "absolute",
|
45 |
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.41.2",
|
47 |
+
"type_vocab_size": 1,
|
48 |
"use_cache": true,
|
49 |
+
"vocab_size": 31274
|
50 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0d4aaa89abcbc3add75152be2e316a84b2e970497f6f7244a87a341ee65bc72
|
3 |
+
size 437931412
|
runs/Jun07_07-36-01_f59316124154/events.out.tfevents.1717745769.f59316124154.229.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd8632b5250e80bf1969b4933040d697b99b6fe434e1e198f649d7596da8456f
|
3 |
+
size 6043
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e60d59d103a3650d675c36c75b3a9c4b47e2c494eeea699f21ccd6e055f78feb
|
3 |
+
size 854151
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,15 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,55 +1,57 @@
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
-
"content": "
|
37 |
-
"lstrip":
|
38 |
-
"normalized":
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
-
"cls_token": "
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"tokenizer_class": "
|
54 |
-
"unk_token": "
|
55 |
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": true,
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
5 |
+
"content": "<s>",
|
6 |
"lstrip": false,
|
7 |
"normalized": false,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
"lstrip": false,
|
23 |
"normalized": false,
|
24 |
"rstrip": false,
|
25 |
"single_word": false,
|
26 |
"special": true
|
27 |
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
"lstrip": false,
|
31 |
"normalized": false,
|
32 |
"rstrip": false,
|
33 |
"single_word": false,
|
34 |
"special": true
|
35 |
},
|
36 |
+
"31273": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
"rstrip": false,
|
41 |
"single_word": false,
|
42 |
"special": true
|
43 |
}
|
44 |
},
|
45 |
+
"bos_token": "<s>",
|
46 |
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"extra_ids": 0,
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 1000000000000000019884624838656,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"sp_model_kwargs": {},
|
55 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
56 |
+
"unk_token": "<unk>"
|
57 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9edf8e98eee9058351918bac0b2d5615c785318f8e5e227f5c34ee61fd501eb8
|
3 |
size 5112
|