Training in progress, epoch 1
Browse files- config.json +45 -0
- dict.txt +0 -0
- model.safetensors +3 -0
- runs/Jan28_03-12-08_d1cf8e6db031/events.out.tfevents.1706411537.d1cf8e6db031.1479.0 +3 -0
- runs/Jan28_03-15-05_d1cf8e6db031/events.out.tfevents.1706411708.d1cf8e6db031.1479.1 +3 -0
- runs/Jan28_03-18-10_d1cf8e6db031/events.out.tfevents.1706411893.d1cf8e6db031.1479.2 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vietgpt/bert-30M-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 512,
|
13 |
+
"id2label": {
|
14 |
+
"0": "toxic",
|
15 |
+
"1": "education",
|
16 |
+
"2": "req_intro",
|
17 |
+
"3": "user_info",
|
18 |
+
"4": "noise",
|
19 |
+
"5": "greating"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 1024,
|
23 |
+
"label2id": {
|
24 |
+
"education": 1,
|
25 |
+
"greating": 5,
|
26 |
+
"noise": 4,
|
27 |
+
"req_intro": 2,
|
28 |
+
"toxic": 0,
|
29 |
+
"user_info": 3
|
30 |
+
},
|
31 |
+
"layer_norm_eps": 1e-05,
|
32 |
+
"max_position_embeddings": 514,
|
33 |
+
"model_type": "bert",
|
34 |
+
"num_attention_heads": 4,
|
35 |
+
"num_hidden_layers": 4,
|
36 |
+
"pad_token_id": 1,
|
37 |
+
"position_embedding_type": "absolute",
|
38 |
+
"problem_type": "single_label_classification",
|
39 |
+
"tokenizer_class": "BartphoTokenizer",
|
40 |
+
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.37.1",
|
42 |
+
"type_vocab_size": 1,
|
43 |
+
"use_cache": true,
|
44 |
+
"vocab_size": 50001
|
45 |
+
}
|
dict.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a7acbc9963c7897f1d92ace76a1c128c0f70f4c08363b83cbe3a363cb6427d1
|
3 |
+
size 138176792
|
runs/Jan28_03-12-08_d1cf8e6db031/events.out.tfevents.1706411537.d1cf8e6db031.1479.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b78698f807790328e19027cd39a59653d0c227b8c593480ea1e825242ff7ef0
|
3 |
+
size 4801
|
runs/Jan28_03-15-05_d1cf8e6db031/events.out.tfevents.1706411708.d1cf8e6db031.1479.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:473645303c7524096a8d1edc9c2cd44f748fbb925d701fc508dea66428eb7f76
|
3 |
+
size 4801
|
runs/Jan28_03-18-10_d1cf8e6db031/events.out.tfevents.1706411893.d1cf8e6db031.1479.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fffad58346e126788f3bde7e728d2b2761e0fc6e2425344997d7dd6a96e2fb2
|
3 |
+
size 5118
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e63e0e8f2d912f8ebf14402e66c2afef07b078099b953efb690d18c6c00af23a
|
3 |
+
size 1027111
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
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": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"50000": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"sp_model_kwargs": {},
|
53 |
+
"tokenizer_class": "BartphoTokenizer",
|
54 |
+
"unk_token": "<unk>"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:353217c6b85c331799939aee0a3d3904569af9a0d4f73290b65904277be2b36e
|
3 |
+
size 4792
|