IvashinMaxim commited on
Commit
9914629
1 Parent(s): 53fea99

End of training

Browse files
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: cointegrated/rubert-tiny2
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: 128Bert
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
+ # 128Bert
17
+
18
+ This model is a fine-tuned version of [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.8346
21
+ - Accuracy: 0.7033
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 128
42
+ - eval_batch_size: 128
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 10
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
+ | 1.1934 | 1.0 | 2074 | 1.1488 | 0.6027 |
53
+ | 1.0626 | 2.0 | 4148 | 1.0247 | 0.6459 |
54
+ | 0.9729 | 3.0 | 6222 | 0.9483 | 0.6658 |
55
+ | 0.908 | 4.0 | 8296 | 0.9041 | 0.6811 |
56
+ | 0.8684 | 5.0 | 10370 | 0.8771 | 0.6897 |
57
+ | 0.8348 | 6.0 | 12444 | 0.8593 | 0.6956 |
58
+ | 0.8055 | 7.0 | 14518 | 0.8507 | 0.6991 |
59
+ | 0.7924 | 8.0 | 16592 | 0.8410 | 0.7017 |
60
+ | 0.7857 | 9.0 | 18666 | 0.8349 | 0.7037 |
61
+ | 0.7732 | 10.0 | 20740 | 0.8346 | 0.7033 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.40.1
67
+ - Pytorch 2.2.1+cu121
68
+ - Datasets 2.19.0
69
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "emb_size": 312,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "Turgenev",
15
+ "1": "Tolstoy",
16
+ "2": "Dostoevsky",
17
+ "3": "Gogol",
18
+ "4": "Chekhov",
19
+ "5": "Pushkin",
20
+ "6": "Lermontov"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 600,
24
+ "label2id": {
25
+ "Chekhov": 4,
26
+ "Dostoevsky": 2,
27
+ "Gogol": 3,
28
+ "Lermontov": 6,
29
+ "Pushkin": 5,
30
+ "Tolstoy": 1,
31
+ "Turgenev": 0
32
+ },
33
+ "layer_norm_eps": 1e-12,
34
+ "max_position_embeddings": 2048,
35
+ "model_type": "bert",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 3,
38
+ "pad_token_id": 0,
39
+ "position_embedding_type": "absolute",
40
+ "problem_type": "single_label_classification",
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.40.1",
43
+ "type_vocab_size": 2,
44
+ "use_cache": true,
45
+ "vocab_size": 83828
46
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87fb16e9c980c0d7e56a49b2736f33f7b32cd88259efb691e2a25a36411a0783
3
+ size 116790396
runs/May02_17-56-12_4c5383f46064/events.out.tfevents.1714672573.4c5383f46064.236.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43eba8889ec35c965eb09d428c24e80d8bf7b5fdf7e10c05ecef462f967f97a5
3
+ size 17353
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 2048,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f628d1d36a28c5cb9b402ccd414f2da7645795e6ceb895ebf8d0893e5f51469a
3
+ size 4984
vocab.txt ADDED
The diff for this file is too large to render. See raw diff