End of training
Browse files- README.md +60 -0
- added_tokens.json +8 -0
- config.json +26 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +71 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Tural/language-modeling-from-scratch
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- squad
|
7 |
+
model-index:
|
8 |
+
- name: How_to_fine-tune_a_model_for_common_downstream_tasks_V2
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# How_to_fine-tune_a_model_for_common_downstream_tasks_V2
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [Tural/language-modeling-from-scratch](https://huggingface.co/Tural/language-modeling-from-scratch) on the squad dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 3.4298
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 2e-05
|
39 |
+
- train_batch_size: 24
|
40 |
+
- eval_batch_size: 32
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 3
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
50 |
+
| 3.647 | 1.0 | 3650 | 3.6697 |
|
51 |
+
| 3.4239 | 2.0 | 7300 | 3.4835 |
|
52 |
+
| 3.2087 | 3.0 | 10950 | 3.4298 |
|
53 |
+
|
54 |
+
|
55 |
+
### Framework versions
|
56 |
+
|
57 |
+
- Transformers 4.34.0
|
58 |
+
- Pytorch 2.0.0
|
59 |
+
- Datasets 2.14.5
|
60 |
+
- Tokenizers 0.14.1
|
added_tokens.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[CLS]": 2,
|
3 |
+
"[FRN]": 5,
|
4 |
+
"[MASK]": 4,
|
5 |
+
"[PAD]": 1,
|
6 |
+
"[SEP]": 3,
|
7 |
+
"[UNK]": 0
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Tural/language-modeling-from-scratch",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.34.0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b87b239160e1c51fc1def342865551b440266023bb6a414778e2d154c19b0c4e
|
3 |
+
size 435640489
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[UNK]",
|
4 |
+
"[PAD]",
|
5 |
+
"[CLS]",
|
6 |
+
"[SEP]",
|
7 |
+
"[MASK]",
|
8 |
+
"[FRN]"
|
9 |
+
],
|
10 |
+
"cls_token": "[CLS]",
|
11 |
+
"mask_token": "[MASK]",
|
12 |
+
"pad_token": "[PAD]",
|
13 |
+
"sep_token": "[SEP]",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[PAD]",
|
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 |
+
"5": {
|
44 |
+
"content": "[FRN]",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"additional_special_tokens": [
|
53 |
+
"[UNK]",
|
54 |
+
"[PAD]",
|
55 |
+
"[CLS]",
|
56 |
+
"[SEP]",
|
57 |
+
"[MASK]",
|
58 |
+
"[FRN]"
|
59 |
+
],
|
60 |
+
"clean_up_tokenization_spaces": true,
|
61 |
+
"cls_token": "[CLS]",
|
62 |
+
"do_lower_case": true,
|
63 |
+
"mask_token": "[MASK]",
|
64 |
+
"model_max_length": 1000000000000000019884624838656,
|
65 |
+
"pad_token": "[PAD]",
|
66 |
+
"sep_token": "[SEP]",
|
67 |
+
"strip_accents": null,
|
68 |
+
"tokenize_chinese_chars": true,
|
69 |
+
"tokenizer_class": "BertTokenizer",
|
70 |
+
"unk_token": "[UNK]"
|
71 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:280fb88cf03710cc641cbd374f463f95e8a9666c6fe13b038bad26745f762a64
|
3 |
+
size 4155
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|