add model
Browse files- .gitignore +1 -0
- README.md +69 -0
- config.json +44 -0
- pytorch_model.bin +3 -0
- runs/Sep16_00-21-54_83d5b9720907/1631751762.9967196/events.out.tfevents.1631751762.83d5b9720907.75.1 +3 -0
- runs/Sep16_00-21-54_83d5b9720907/events.out.tfevents.1631751762.83d5b9720907.75.0 +3 -0
- runs/Sep16_00-21-54_83d5b9720907/events.out.tfevents.1631752423.83d5b9720907.75.2 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
model-index:
|
7 |
+
- name: rubert-base-cased-sentence-finetuned-headlines_X
|
8 |
+
results:
|
9 |
+
- task:
|
10 |
+
name: Text Classification
|
11 |
+
type: text-classification
|
12 |
+
metrics:
|
13 |
+
- name: Accuracy
|
14 |
+
type: accuracy
|
15 |
+
value: 0.952
|
16 |
+
---
|
17 |
+
|
18 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
19 |
+
should probably proofread and complete it, then remove this comment. -->
|
20 |
+
|
21 |
+
# rubert-base-cased-sentence-finetuned-headlines_X
|
22 |
+
|
23 |
+
This model is a fine-tuned version of [DeepPavlov/rubert-base-cased-sentence](https://huggingface.co/DeepPavlov/rubert-base-cased-sentence) on an unknown dataset.
|
24 |
+
It achieves the following results on the evaluation set:
|
25 |
+
- Loss: 0.2535
|
26 |
+
- Accuracy: 0.952
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 2e-05
|
46 |
+
- train_batch_size: 32
|
47 |
+
- eval_batch_size: 32
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 5
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
57 |
+
| No log | 1.0 | 157 | 0.2759 | 0.912 |
|
58 |
+
| No log | 2.0 | 314 | 0.2538 | 0.936 |
|
59 |
+
| No log | 3.0 | 471 | 0.2556 | 0.945 |
|
60 |
+
| 0.1908 | 4.0 | 628 | 0.2601 | 0.95 |
|
61 |
+
| 0.1908 | 5.0 | 785 | 0.2535 | 0.952 |
|
62 |
+
|
63 |
+
|
64 |
+
### Framework versions
|
65 |
+
|
66 |
+
- Transformers 4.10.2
|
67 |
+
- Pytorch 1.9.0+cu102
|
68 |
+
- Datasets 1.12.1
|
69 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "DeepPavlov/rubert-base-cased-sentence",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"LABEL_0": 0,
|
22 |
+
"LABEL_1": 1,
|
23 |
+
"LABEL_2": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "bert",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"output_past": true,
|
31 |
+
"pad_token_id": 0,
|
32 |
+
"pooler_fc_size": 768,
|
33 |
+
"pooler_num_attention_heads": 12,
|
34 |
+
"pooler_num_fc_layers": 3,
|
35 |
+
"pooler_size_per_head": 128,
|
36 |
+
"pooler_type": "first_token_transform",
|
37 |
+
"position_embedding_type": "absolute",
|
38 |
+
"problem_type": "single_label_classification",
|
39 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.10.2",
|
41 |
+
"type_vocab_size": 2,
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 119547
|
44 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f02f9ae48a72d0b35fa1df2ec383f138c7f89e7e88269b7a42b7cd6b71ac53a
|
3 |
+
size 711507117
|
runs/Sep16_00-21-54_83d5b9720907/1631751762.9967196/events.out.tfevents.1631751762.83d5b9720907.75.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cdd4c32b4152525df8e12bc02f5927ab6360d2b61537b35d3cf155a81cf0516
|
3 |
+
size 4225
|
runs/Sep16_00-21-54_83d5b9720907/events.out.tfevents.1631751762.83d5b9720907.75.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:168f2ade443ba7106dd2221a3498a67d2165d5e4de34be7a12dd73f9d37e13ea
|
3 |
+
size 5493
|
runs/Sep16_00-21-54_83d5b9720907/events.out.tfevents.1631752423.83d5b9720907.75.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71143a89ee5f76e0ded7c0419c0d9eefcd593e7838c4a76983f1b9cfe8871ac5
|
3 |
+
size 363
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/root/.cache/huggingface/transformers/0c7965501fba622370adf334149813060bb231408a6582b155bf623cd1f81d47.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "DeepPavlov/rubert-base-cased-sentence", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26e1f04498360a66cee2b21a13df66468c035ab8ef6f4357fefe1fa59acb7d6c
|
3 |
+
size 2671
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|