Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +80 -0
- pytorch_model.bin +3 -0
- runs/Jul13_14-03-15_jordy-OMEN/1657713806.4483178/events.out.tfevents.1657713806.jordy-OMEN.105106.1 +3 -0
- runs/Jul13_14-03-15_jordy-OMEN/events.out.tfevents.1657713806.jordy-OMEN.105106.0 +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 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
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 |
+
"id2label": {
|
13 |
+
"0": "ADJ",
|
14 |
+
"1": "ADP",
|
15 |
+
"2": "ADV",
|
16 |
+
"3": "AUX",
|
17 |
+
"4": "CCONJ",
|
18 |
+
"5": "DET",
|
19 |
+
"6": "INTJ",
|
20 |
+
"7": "NOUN",
|
21 |
+
"8": "NUM",
|
22 |
+
"9": "PART",
|
23 |
+
"10": "PRON",
|
24 |
+
"11": "PROPN",
|
25 |
+
"12": "PUNCT",
|
26 |
+
"13": "SCONJ",
|
27 |
+
"14": "SYM",
|
28 |
+
"15": "VERB",
|
29 |
+
"16": "X"
|
30 |
+
},
|
31 |
+
"initializer_range": 0.02,
|
32 |
+
"intermediate_size": 3072,
|
33 |
+
"label2id": {
|
34 |
+
"ADJ": 0,
|
35 |
+
"ADP": 1,
|
36 |
+
"ADV": 2,
|
37 |
+
"AUX": 3,
|
38 |
+
"CCONJ": 4,
|
39 |
+
"DET": 5,
|
40 |
+
"INTJ": 6,
|
41 |
+
"NOUN": 7,
|
42 |
+
"NUM": 8,
|
43 |
+
"PART": 9,
|
44 |
+
"PRON": 10,
|
45 |
+
"PROPN": 11,
|
46 |
+
"PUNCT": 12,
|
47 |
+
"SCONJ": 13,
|
48 |
+
"SYM": 14,
|
49 |
+
"VERB": 15,
|
50 |
+
"X": 16
|
51 |
+
},
|
52 |
+
"layer_norm_eps": 1e-12,
|
53 |
+
"max_position_embeddings": 512,
|
54 |
+
"model_type": "bert",
|
55 |
+
"num_attention_heads": 12,
|
56 |
+
"num_hidden_layers": 12,
|
57 |
+
"pad_token_id": 0,
|
58 |
+
"position_embedding_type": "absolute",
|
59 |
+
"test_args": {
|
60 |
+
"Y": "labels",
|
61 |
+
"dataset": "wietsedv/udpos28",
|
62 |
+
"model": "bert-base-cased",
|
63 |
+
"setting": "udpos",
|
64 |
+
"subset": "en",
|
65 |
+
"subword_alignment": "all",
|
66 |
+
"task": "POS",
|
67 |
+
"train_args": {
|
68 |
+
"batch_size": 4,
|
69 |
+
"epochs": 3,
|
70 |
+
"learning_rate": 2e-05,
|
71 |
+
"warmup_ratio": 0.1,
|
72 |
+
"weight_decay": 0.01
|
73 |
+
}
|
74 |
+
},
|
75 |
+
"torch_dtype": "float32",
|
76 |
+
"transformers_version": "4.18.0",
|
77 |
+
"type_vocab_size": 2,
|
78 |
+
"use_cache": true,
|
79 |
+
"vocab_size": 28996
|
80 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8902cda1d5916f5f7950acef6330575c36241b60313a713b2f440841f4d334a8
|
3 |
+
size 431001457
|
runs/Jul13_14-03-15_jordy-OMEN/1657713806.4483178/events.out.tfevents.1657713806.jordy-OMEN.105106.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46103c941ee15774e821c9dfdb04b4fef74411fe427720a10ca68350155e91fa
|
3 |
+
size 4922
|
runs/Jul13_14-03-15_jordy-OMEN/events.out.tfevents.1657713806.jordy-OMEN.105106.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8838c32afdd85ba19f362219aa054f394b8da62039c3eae4eacee63bbd00d203
|
3 |
+
size 6245
|
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": "bert-base-cased", "tokenizer_class": "BertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:405f28b0d4e537c95744a78dacd8a0c08c03894a7a7af8d96d5234fef4564ed7
|
3 |
+
size 3119
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|