add model
Browse files- .gitignore +1 -0
- README.md +70 -0
- config.json +36 -0
- pytorch_model.bin +3 -0
- runs/Mar20_12-10-55_DESKTOP-QEJTC97/1647774667.864169/events.out.tfevents.1647774667.DESKTOP-QEJTC97.6852.1 +3 -0
- runs/Mar20_12-10-55_DESKTOP-QEJTC97/events.out.tfevents.1647774667.DESKTOP-QEJTC97.6852.0 +3 -0
- runs/Mar20_12-10-55_DESKTOP-QEJTC97/events.out.tfevents.1647794929.DESKTOP-QEJTC97.6852.2 +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 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- spearmanr
|
6 |
+
model-index:
|
7 |
+
- name: koelectra-sts-v0.6
|
8 |
+
results:
|
9 |
+
- task:
|
10 |
+
name: Text Classification
|
11 |
+
type: text-classification
|
12 |
+
metrics:
|
13 |
+
- name: Spearmanr
|
14 |
+
type: spearmanr
|
15 |
+
value: 0.8711267002878285
|
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 |
+
# koelectra-sts-v0.6
|
22 |
+
|
23 |
+
This model was trained from scratch on an unknown dataset.
|
24 |
+
It achieves the following results on the evaluation set:
|
25 |
+
- Loss: 0.0065
|
26 |
+
- Pearson: 0.9988
|
27 |
+
- Spearmanr: 0.8711
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 2e-05
|
47 |
+
- train_batch_size: 16
|
48 |
+
- eval_batch_size: 16
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 5
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
|
57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:---------:|
|
58 |
+
| 0.045 | 1.0 | 12500 | 0.0186 | 0.9963 | 0.8703 |
|
59 |
+
| 0.0173 | 2.0 | 25000 | 0.0338 | 0.9930 | 0.8693 |
|
60 |
+
| 0.0133 | 3.0 | 37500 | 0.0100 | 0.9980 | 0.8709 |
|
61 |
+
| 0.0101 | 4.0 | 50000 | 0.0065 | 0.9988 | 0.8711 |
|
62 |
+
| 0.01 | 5.0 | 62500 | 0.0064 | 0.9987 | 0.8711 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.10.0
|
68 |
+
- Pytorch 1.10.1+cu113
|
69 |
+
- Datasets 1.17.0
|
70 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./koelectra-sts-v0.5/checkpoint-31250",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 768,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "electra",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"problem_type": "regression",
|
28 |
+
"summary_activation": "gelu",
|
29 |
+
"summary_last_dropout": 0.1,
|
30 |
+
"summary_type": "first",
|
31 |
+
"summary_use_proj": true,
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.10.0",
|
34 |
+
"type_vocab_size": 2,
|
35 |
+
"vocab_size": 35000
|
36 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:331beb808cdf8c9695502dcf5042fc9da98d4bc12d6dad0567c1fa7858c3ce85
|
3 |
+
size 451773805
|
runs/Mar20_12-10-55_DESKTOP-QEJTC97/1647774667.864169/events.out.tfevents.1647774667.DESKTOP-QEJTC97.6852.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55e3e8711bfeb30e1f62c30e3233d83bac5ca32be7f7759dc10297337fdf2d04
|
3 |
+
size 4218
|
runs/Mar20_12-10-55_DESKTOP-QEJTC97/events.out.tfevents.1647774667.DESKTOP-QEJTC97.6852.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7aeb57e9647b3fae58b3d215aadfcdf1326ce823dd695387b3c93b139283c8a
|
3 |
+
size 25411
|
runs/Mar20_12-10-55_DESKTOP-QEJTC97/events.out.tfevents.1647794929.DESKTOP-QEJTC97.6852.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab097a37dc457bc9935353ec2fff077eebf289f215692461e4c9318ead719dbb
|
3 |
+
size 422
|
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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "./koelectra-sts-v0.5/checkpoint-31250", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45fe8f2f064e3937188f2ac58c2aac55f532c005d50a17c888c64b219a0e59fa
|
3 |
+
size 2671
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|