Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +48 -0
- pytorch_model.bin +3 -0
- runs/Mar12_17-48-20_d8120e2be914/1647107857.373035/events.out.tfevents.1647107857.d8120e2be914.71.1 +3 -0
- runs/Mar12_17-48-20_d8120e2be914/events.out.tfevents.1647107857.d8120e2be914.71.0 +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-*/
|
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Seznam/small-e-czech",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 128,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 256,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "B-PER",
|
15 |
+
"2": "I-PER",
|
16 |
+
"3": "B-ORG",
|
17 |
+
"4": "I-ORG",
|
18 |
+
"5": "B-LOC",
|
19 |
+
"6": "I-LOC"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 1024,
|
23 |
+
"label2id": {
|
24 |
+
"B-LOC": "5",
|
25 |
+
"B-ORG": "3",
|
26 |
+
"B-PER": "1",
|
27 |
+
"I-LOC": "6",
|
28 |
+
"I-ORG": "4",
|
29 |
+
"I-PER": "2",
|
30 |
+
"O": "0"
|
31 |
+
},
|
32 |
+
"layer_norm_eps": 1e-12,
|
33 |
+
"max_position_embeddings": 512,
|
34 |
+
"model_type": "electra",
|
35 |
+
"num_attention_heads": 4,
|
36 |
+
"num_hidden_layers": 12,
|
37 |
+
"pad_token_id": 0,
|
38 |
+
"position_embedding_type": "absolute",
|
39 |
+
"summary_activation": "gelu",
|
40 |
+
"summary_last_dropout": 0.1,
|
41 |
+
"summary_type": "first",
|
42 |
+
"summary_use_proj": true,
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.17.0",
|
45 |
+
"type_vocab_size": 2,
|
46 |
+
"use_cache": true,
|
47 |
+
"vocab_size": 30522
|
48 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e797b553580ddaf7e088453e07906b26fcf981a16ffb105d212624bb496f637
|
3 |
+
size 54025453
|
runs/Mar12_17-48-20_d8120e2be914/1647107857.373035/events.out.tfevents.1647107857.d8120e2be914.71.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9215da47efb1001c90da1734e573e02ddea320b0c7eb2d6c6d4c2b70fe7f018b
|
3 |
+
size 4814
|
runs/Mar12_17-48-20_d8120e2be914/events.out.tfevents.1647107857.d8120e2be914.71.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ec4871b6898a2e07d80e2328094a8e98670008fa8030f7bb5ec86a42c491d6e
|
3 |
+
size 4952
|
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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "special_tokens_map_file": null, "name_or_path": "Seznam/small-e-czech", "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 sha256:2e910783621137bd162ef68fe103faec636b765f1de1cd705fb41d37f927d81d
|
3 |
+
size 3055
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|