danilka200300 commited on
Commit
9be2e6e
·
verified ·
1 Parent(s): 3519ec0

best-new-cool-rubert-tiny-turbo

Browse files
Files changed (4) hide show
  1. README.md +73 -0
  2. config.json +28 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: sergeyzh/rubert-tiny-turbo
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - recall
10
+ - precision
11
+ - f1
12
+ model-index:
13
+ - name: results
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
+ # results
21
+
22
+ This model is a fine-tuned version of [sergeyzh/rubert-tiny-turbo](https://huggingface.co/sergeyzh/rubert-tiny-turbo) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.3458
25
+ - Accuracy: 0.9519
26
+ - Recall: 0.7081
27
+ - Precision: 0.6032
28
+ - F1: 0.6514
29
+ - Roc Auc: 0.9524
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 5e-05
49
+ - train_batch_size: 16
50
+ - eval_batch_size: 16
51
+ - seed: 42
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - lr_scheduler_warmup_steps: 500
55
+ - num_epochs: 5
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1 | Roc Auc |
60
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-------:|
61
+ | 0.5072 | 1.0 | 634 | 0.4108 | 0.9479 | 0.6335 | 0.5829 | 0.6071 | 0.9404 |
62
+ | 0.3303 | 2.0 | 1268 | 0.3458 | 0.9519 | 0.7081 | 0.6032 | 0.6514 | 0.9524 |
63
+ | 0.1088 | 3.0 | 1902 | 0.5147 | 0.9673 | 0.6522 | 0.7955 | 0.7167 | 0.9458 |
64
+ | 0.1927 | 4.0 | 2536 | 0.5223 | 0.9523 | 0.7764 | 0.5952 | 0.6739 | 0.9415 |
65
+ | 0.0008 | 5.0 | 3170 | 0.6438 | 0.9657 | 0.7019 | 0.7434 | 0.7220 | 0.9319 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.45.1
71
+ - Pytorch 2.4.0
72
+ - Datasets 3.0.1
73
+ - Tokenizers 0.20.0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sergeyzh/rubert-tiny-turbo",
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
+ "initializer_range": 0.02,
14
+ "intermediate_size": 600,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 3,
20
+ "pad_token_id": 0,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.45.1",
25
+ "type_vocab_size": 2,
26
+ "use_cache": true,
27
+ "vocab_size": 83828
28
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a49d30c42f8e9563d0adf40d49f736c6d60b2480cea0656492782bef9f09f020
3
+ size 116784136
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:603889aab4a44365784639eba1745e94729a7cdb03725fc8288a48c5d6158d53
3
+ size 5176