Buseak commited on
Commit
56c87a4
1 Parent(s): 4f1850b

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/canine-c",
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": "\u0130",
15
+ "1": "\u00d6",
16
+ "2": "\u00dc",
17
+ "3": "\u0131",
18
+ "4": "\u00f6",
19
+ "5": "\u00fc",
20
+ "6": "\u011e",
21
+ "7": "\u011f",
22
+ "8": "\u00c7",
23
+ "9": "\u00e7",
24
+ "10": "\u015e",
25
+ "11": "\u015f",
26
+ "12": "NaN"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "label2id": {
31
+ "NaN": 12,
32
+ "\u00c7": 8,
33
+ "\u00d6": 1,
34
+ "\u00dc": 2,
35
+ "\u00e7": 9,
36
+ "\u00f6": 4,
37
+ "\u00fc": 5,
38
+ "\u011e": 6,
39
+ "\u011f": 7,
40
+ "\u0130": 0,
41
+ "\u0131": 3,
42
+ "\u015e": 10,
43
+ "\u015f": 11
44
+ },
45
+ "layer_norm_eps": 1e-12,
46
+ "local_transformer_stride": 128,
47
+ "max_position_embeddings": 16384,
48
+ "model_type": "canine",
49
+ "num_attention_heads": 12,
50
+ "num_hash_buckets": 16384,
51
+ "num_hash_functions": 8,
52
+ "num_hidden_layers": 12,
53
+ "pad_token_id": 0,
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.35.2",
56
+ "type_vocab_size": 16,
57
+ "upsampling_kernel_size": 4,
58
+ "use_cache": true
59
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48992e2374c30be949788d4788334e6cab2b5c1454ada60f6c9ef60844df775b
3
+ size 528401764
runs/Jan07_13-54-47_a8972bef4227/events.out.tfevents.1704635688.a8972bef4227.3341.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f2e4d83d871ea9e9be0bcec8e570f7ee8a42eb38e9cd0c6d4f478c6c39bf6aa
3
+ size 5330
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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "\u0000",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "57344": {
13
+ "content": "",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "57345": {
21
+ "content": "",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "57347": {
29
+ "content": "",
30
+ "lstrip": true,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "",
38
+ "clean_up_tokenization_spaces": true,
39
+ "cls_token": "",
40
+ "eos_token": "",
41
+ "mask_token": "",
42
+ "model_max_length": 2048,
43
+ "pad_token": "\u0000",
44
+ "sep_token": "",
45
+ "tokenizer_class": "CanineTokenizer"
46
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03d0e68192d7e0c747340a7ac87317d04e47c384568e278a9664f3967482c7f5
3
+ size 4600