xkaska02 commited on
Commit
091dd99
·
verified ·
1 Parent(s): 420071a

End of training

Browse files
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-sa-4.0
4
+ base_model: ufal/robeczech-base
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: robeczech_lr3e-05_bs16_train287
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # robeczech_lr3e-05_bs16_train287
21
+
22
+ This model is a fine-tuned version of [ufal/robeczech-base](https://huggingface.co/ufal/robeczech-base) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.1813
25
+ - Precision: 0.9550
26
+ - Recall: 0.9585
27
+ - F1: 0.9568
28
+ - Accuracy: 0.9738
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 3e-05
48
+ - train_batch_size: 16
49
+ - eval_batch_size: 16
50
+ - seed: 42
51
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 30
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | No log | 1.0 | 18 | 1.3032 | 0.7333 | 0.0212 | 0.0413 | 0.5756 |
60
+ | No log | 2.0 | 36 | 0.8161 | 0.6145 | 0.6089 | 0.6117 | 0.8190 |
61
+ | No log | 3.0 | 54 | 0.5267 | 0.8108 | 0.8006 | 0.8056 | 0.9056 |
62
+ | No log | 4.0 | 72 | 0.3785 | 0.8914 | 0.8914 | 0.8914 | 0.9452 |
63
+ | No log | 5.0 | 90 | 0.3145 | 0.8993 | 0.8972 | 0.8982 | 0.9491 |
64
+ | No log | 6.0 | 108 | 0.2826 | 0.8949 | 0.9000 | 0.8974 | 0.9485 |
65
+ | No log | 7.0 | 126 | 0.2498 | 0.9167 | 0.9247 | 0.9207 | 0.9586 |
66
+ | No log | 8.0 | 144 | 0.2291 | 0.9320 | 0.9392 | 0.9355 | 0.9657 |
67
+ | No log | 9.0 | 162 | 0.2151 | 0.9406 | 0.9411 | 0.9409 | 0.9682 |
68
+ | No log | 10.0 | 180 | 0.1960 | 0.9453 | 0.9512 | 0.9483 | 0.9715 |
69
+ | No log | 11.0 | 198 | 0.1930 | 0.9488 | 0.9488 | 0.9488 | 0.9720 |
70
+ | No log | 12.0 | 216 | 0.1953 | 0.9429 | 0.9411 | 0.9420 | 0.9682 |
71
+ | No log | 13.0 | 234 | 0.1887 | 0.9491 | 0.9445 | 0.9468 | 0.9707 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.51.3
77
+ - Pytorch 2.6.0+cu124
78
+ - Datasets 3.5.0
79
+ - Tokenizers 0.21.1
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-key",
16
+ "2": "B-information",
17
+ "3": "B-name",
18
+ "4": "B-rank",
19
+ "5": "B-birth_date",
20
+ "6": "B-nationality",
21
+ "7": "B-death_date",
22
+ "8": "B-funeral_date",
23
+ "9": "B-grave_location",
24
+ "10": "B-grave_id",
25
+ "11": "B-information_source",
26
+ "12": "B-death_book"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "label2id": {
31
+ "LABEL_0": 0,
32
+ "LABEL_1": 1,
33
+ "LABEL_10": 10,
34
+ "LABEL_11": 11,
35
+ "LABEL_12": 12,
36
+ "LABEL_2": 2,
37
+ "LABEL_3": 3,
38
+ "LABEL_4": 4,
39
+ "LABEL_5": 5,
40
+ "LABEL_6": 6,
41
+ "LABEL_7": 7,
42
+ "LABEL_8": 8,
43
+ "LABEL_9": 9
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "max_position_embeddings": 514,
47
+ "model_type": "roberta",
48
+ "num_attention_heads": 12,
49
+ "num_hidden_layers": 12,
50
+ "pad_token_id": 1,
51
+ "position_embedding_type": "absolute",
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.51.3",
54
+ "type_vocab_size": 1,
55
+ "use_cache": true,
56
+ "vocab_size": 51997
57
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb523af0d7d573b81aed8008f2186f52c560229f8e1c23903531cb90ea9c117c
3
+ size 501604780
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[CLS]",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[PAD]",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "51960": {
37
+ "content": "[MASK]",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "[CLS]",
48
+ "eos_token": "[SEP]",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "[MASK]",
52
+ "model_max_length": 512,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28880853902d0791e9a66c238de1da453c91eb4b95c765c0fd36a364e921ac4
3
+ size 5368
vocab.json ADDED
The diff for this file is too large to render. See raw diff