Hugging Face's logo

Harshatheeswar
/
Ltg_bert

Fill-Mask
Transformers
PyTorch
TensorBoard
ltgbert
Generated from Trainer
custom_code
Model card Files
xet
Metrics Community
Harshatheeswar commited on
Commit
c2f4e5b
·
verified ·
1 Parent(s): d440b87

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. config.json +27 -0
  2. pytorch_model.bin +3 -0
  3. runs/Nov26_18-11-59_5256e233a9e1/events.out.tfevents.1732644722.5256e233a9e1.1192.0 +3 -0
  4. runs/Nov26_18-50-05_5256e233a9e1/events.out.tfevents.1732647006.5256e233a9e1.1192.1 +3 -0
  5. special_tokens_map.json +51 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +79 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "babylm/ltgbert-10m-2024",
3
+ "architectures": [
4
+ "LtgBertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "auto_map": {
8
+ "AutoConfig": "babylm/ltgbert-10m-2024--configuration_ltgbert.LtgBertConfig",
9
+ "AutoModelForMaskedLM": "babylm/ltgbert-10m-2024--modeling_ltgbert.LtgBertForMaskedLM",
10
+ "AutoModelForSequenceClassification": "babylm/ltgbert-10m-2024--modeling_ltgbert.LtgBertForSequenceClassification"
11
+ },
12
+ "classifier_dropout": 0.2,
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "intermediate_size": 2048,
16
+ "layer_norm_eps": 1e-07,
17
+ "max_position_embeddings": 512,
18
+ "model_type": "ltgbert",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "output_all_encoded_layers": true,
22
+ "pad_token_id": 4,
23
+ "position_bucket_size": 32,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.46.2",
26
+ "vocab_size": 16384
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b271e34e3a1b6ea58c184da5c386ba4ac036e5e76940347d49fbfb50f89097a
3
+ size 418132726
runs/Nov26_18-11-59_5256e233a9e1/events.out.tfevents.1732644722.5256e233a9e1.1192.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82aebfe4b88a649d8ccc5270854abf003ba05794d2a4b4e196c124af7fb113a8
3
+ size 15792
runs/Nov26_18-50-05_5256e233a9e1/events.out.tfevents.1732647006.5256e233a9e1.1192.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:794b57689acb06d16fccc4699a2592ed693b5737d9c7ded14806da6d2bb541e5
3
+ size 15753
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<cls>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "<sep>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<cls>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<sep>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "bos_token": "<s>",
61
+ "clean_up_tokenization_spaces": true,
62
+ "cls_token": "<cls>",
63
+ "eos_token": "</s>",
64
+ "mask_token": "<mask>",
65
+ "model_max_length": 128,
66
+ "pad_token": "<pad>",
67
+ "sep_token": "<sep>",
68
+ "special_tokens": [
69
+ "<s>",
70
+ "<pad>",
71
+ "</s>",
72
+ "<unk>",
73
+ "<mask>",
74
+ "<cls>",
75
+ "<sep>"
76
+ ],
77
+ "tokenizer_class": "PreTrainedTokenizerFast",
78
+ "unk_token": "<unk>"
79
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29d6d4dcc3943c25a156ce5a4a122634002a0b0438f8be4cb164f948fcc1e8fe
3
+ size 5304