Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +71 -0
- pytorch_model.bin +3 -0
- runs/Mar17_10-12-34_7ac9a487c85c/1710670360.3947983/events.out.tfevents.1710670360.7ac9a487c85c.4398.1 +3 -0
- runs/Mar17_10-12-34_7ac9a487c85c/events.out.tfevents.1710670360.7ac9a487c85c.4398.0 +3 -0
- special_tokens_map.json +44 -0
- tokenizer_config.json +54 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Buseak/vowelizer_1203_v9",
|
3 |
+
"architectures": [
|
4 |
+
"CanineForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 57344,
|
8 |
+
"downsampling_rate": 4,
|
9 |
+
"eos_token_id": 57345,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "a",
|
15 |
+
"1": "\u00e2",
|
16 |
+
"2": "e",
|
17 |
+
"3": "\u0131",
|
18 |
+
"4": "i",
|
19 |
+
"5": "o",
|
20 |
+
"6": "\u00f6",
|
21 |
+
"7": "u",
|
22 |
+
"8": "\u00fc",
|
23 |
+
"9": "A",
|
24 |
+
"10": "\u00c2",
|
25 |
+
"11": "E",
|
26 |
+
"12": "I",
|
27 |
+
"13": "\u0130",
|
28 |
+
"14": "O",
|
29 |
+
"15": "\u00d6",
|
30 |
+
"16": "U",
|
31 |
+
"17": "\u00dc",
|
32 |
+
"18": "NaN"
|
33 |
+
},
|
34 |
+
"initializer_range": 0.02,
|
35 |
+
"intermediate_size": 3072,
|
36 |
+
"label2id": {
|
37 |
+
"A": 9,
|
38 |
+
"E": 11,
|
39 |
+
"I": 12,
|
40 |
+
"NaN": 18,
|
41 |
+
"O": 14,
|
42 |
+
"U": 16,
|
43 |
+
"a": 0,
|
44 |
+
"e": 2,
|
45 |
+
"i": 4,
|
46 |
+
"o": 5,
|
47 |
+
"u": 7,
|
48 |
+
"\u00c2": 10,
|
49 |
+
"\u00d6": 15,
|
50 |
+
"\u00dc": 17,
|
51 |
+
"\u00e2": 1,
|
52 |
+
"\u00f6": 6,
|
53 |
+
"\u00fc": 8,
|
54 |
+
"\u0130": 13,
|
55 |
+
"\u0131": 3
|
56 |
+
},
|
57 |
+
"layer_norm_eps": 1e-12,
|
58 |
+
"local_transformer_stride": 128,
|
59 |
+
"max_position_embeddings": 16384,
|
60 |
+
"model_type": "canine",
|
61 |
+
"num_attention_heads": 12,
|
62 |
+
"num_hash_buckets": 16384,
|
63 |
+
"num_hash_functions": 8,
|
64 |
+
"num_hidden_layers": 12,
|
65 |
+
"pad_token_id": 0,
|
66 |
+
"torch_dtype": "float32",
|
67 |
+
"transformers_version": "4.28.0",
|
68 |
+
"type_vocab_size": 16,
|
69 |
+
"upsampling_kernel_size": 4,
|
70 |
+
"use_cache": true
|
71 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdf532336ca7d0239158ef9ca10843be264e0fe1674203c0562a46c41193030c
|
3 |
+
size 528607470
|
runs/Mar17_10-12-34_7ac9a487c85c/1710670360.3947983/events.out.tfevents.1710670360.7ac9a487c85c.4398.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cfa920ed706817931495660742ed3ecb70ff9af1080fbe221bcd46a037c4418
|
3 |
+
size 5876
|
runs/Mar17_10-12-34_7ac9a487c85c/events.out.tfevents.1710670360.7ac9a487c85c.4398.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a16b76b331e03de5293eb45f97f83fbc1ba17e901010f5a2bd9f5a7e6e4c957
|
3 |
+
size 5377
|
special_tokens_map.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "\u0000",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
}
|
44 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"clean_up_tokenization_spaces": true,
|
12 |
+
"cls_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"eos_token": {
|
21 |
+
"__type": "AddedToken",
|
22 |
+
"content": "",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"mask_token": {
|
29 |
+
"__type": "AddedToken",
|
30 |
+
"content": "",
|
31 |
+
"lstrip": true,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
},
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": {
|
38 |
+
"__type": "AddedToken",
|
39 |
+
"content": "\u0000",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false
|
44 |
+
},
|
45 |
+
"sep_token": {
|
46 |
+
"__type": "AddedToken",
|
47 |
+
"content": "",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false
|
52 |
+
},
|
53 |
+
"tokenizer_class": "CanineTokenizer"
|
54 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b19f7b6dc6c6604223f0b170eb55757e9ef9e6a09c4b96e429bca5ba8447fa2a
|
3 |
+
size 4024
|