Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +47 -0
- pytorch_model.bin +3 -0
- runs/Jan21_16-03-34_cds-tesla/1674291833.1681037/events.out.tfevents.1674291833.cds-tesla.3555825.1 +3 -0
- runs/Jan21_16-03-34_cds-tesla/events.out.tfevents.1674291833.cds-tesla.3555825.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "indolem/indobertweet-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_ids": 0,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "EN",
|
16 |
+
"1": "ID",
|
17 |
+
"2": "JV",
|
18 |
+
"3": "MIX_ID_EN",
|
19 |
+
"4": "MIX_ID_JV",
|
20 |
+
"5": "MIX_JV_EN",
|
21 |
+
"6": "OTH"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"EN": 0,
|
27 |
+
"ID": 1,
|
28 |
+
"JV": 2,
|
29 |
+
"MIX_ID_EN": 3,
|
30 |
+
"MIX_ID_JV": 4,
|
31 |
+
"MIX_JV_EN": 5,
|
32 |
+
"OTH": 6
|
33 |
+
},
|
34 |
+
"layer_norm_eps": 1e-12,
|
35 |
+
"max_position_embeddings": 512,
|
36 |
+
"model_type": "bert",
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_hidden_layers": 12,
|
39 |
+
"output_past": true,
|
40 |
+
"pad_token_id": 0,
|
41 |
+
"position_embedding_type": "absolute",
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.21.2",
|
44 |
+
"type_vocab_size": 2,
|
45 |
+
"use_cache": true,
|
46 |
+
"vocab_size": 31923
|
47 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fce3e4898932db2defdd5fbd6abf3bdcf1b9af255ddadaeaf8f72c83acce4477
|
3 |
+
size 439962417
|
runs/Jan21_16-03-34_cds-tesla/1674291833.1681037/events.out.tfevents.1674291833.cds-tesla.3555825.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:898257e764a3f62cab49a553c704586b99f78cdae46531457c7f7537113c8468
|
3 |
+
size 5449
|
runs/Jan21_16-03-34_cds-tesla/events.out.tfevents.1674291833.cds-tesla.3555825.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69768c4cd9dfc9f3ea8cdf8781455d404ba6ecdba02508270daa1b96699a8c4c
|
3 |
+
size 4553
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 128,
|
7 |
+
"name_or_path": "indolem/indobertweet-base-uncased",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": "/home/jupyter-145230403/.cache/huggingface/transformers/f4e40cfa6532f9592ed04e256a91ed9b5574d28a8e0ad5e760524e96d034c486.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:067a3bbe9d4ee2a20cb1b3119f73a6c4342e2e38130881d56e55c950a7ff425e
|
3 |
+
size 3375
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|