Hugging Face's logo

bobox
/
DeBERTa3-s-CustomPoolin-toytest-step1-checkpoints-tmp

PyTorch
TensorBoard
deberta-v2
Model card Files Metrics Community
bobox commited on
Commit
5deaae0
•
1 Parent(s): ade1ea9

Training in progress, step 305

Browse files
Files changed (17) hide show
  1. added_tokens.json +3 -0
  2. config.json +35 -0
  3. pytorch_model.bin +3 -0
  4. runs/Oct28_11-53-29_3c3f53392730/events.out.tfevents.1730116445.3c3f53392730.368.0 +3 -0
  5. runs/Oct28_11-57-01_3c3f53392730/events.out.tfevents.1730116631.3c3f53392730.368.1 +3 -0
  6. runs/Oct28_12-00-24_3c3f53392730/events.out.tfevents.1730116830.3c3f53392730.6576.0 +3 -0
  7. runs/Oct28_12-11-31_3c3f53392730/events.out.tfevents.1730117497.3c3f53392730.9951.0 +3 -0
  8. runs/Oct28_12-19-12_3c3f53392730/events.out.tfevents.1730117958.3c3f53392730.12245.0 +3 -0
  9. runs/Oct28_12-21-08_3c3f53392730/events.out.tfevents.1730118074.3c3f53392730.13137.0 +3 -0
  10. runs/Oct28_12-24-47_3c3f53392730/events.out.tfevents.1730118293.3c3f53392730.14471.0 +3 -0
  11. runs/Oct28_12-45-05_3c3f53392730/events.out.tfevents.1730119512.3c3f53392730.19692.0 +3 -0
  12. runs/Oct28_12-49-13_3c3f53392730/events.out.tfevents.1730119760.3c3f53392730.21334.0 +3 -0
  13. special_tokens_map.json +15 -0
  14. spm.model +3 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +58 -0
  17. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-small",
3
+ "architectures": [
4
+ "DebertaV2Model"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.44.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57c90603cd53748313e111bacadbca362be5ab2596e4cc509d8f0c45cd399ec
3
+ size 565251810
runs/Oct28_11-53-29_3c3f53392730/events.out.tfevents.1730116445.3c3f53392730.368.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34ce1de2b89f5f15c09ec411c4b587af66f9418a4ddd288f218fa734d439cd0e
3
+ size 4427
runs/Oct28_11-57-01_3c3f53392730/events.out.tfevents.1730116631.3c3f53392730.368.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dfdc0cdf04af3f49ab434de5ef8a85515a8558af59601a8d98a071fe75965c3
3
+ size 4427
runs/Oct28_12-00-24_3c3f53392730/events.out.tfevents.1730116830.3c3f53392730.6576.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af00eb6f7e8489ec676a7fbbe7a6dd4b34b879845db88bf64ae261c89aaf3305
3
+ size 4427
runs/Oct28_12-11-31_3c3f53392730/events.out.tfevents.1730117497.3c3f53392730.9951.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c95aeaaa2add0ea0369d2b2e49ec0ebe85160f1855ebff15d701d5764b076f0e
3
+ size 4427
runs/Oct28_12-19-12_3c3f53392730/events.out.tfevents.1730117958.3c3f53392730.12245.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6edb1a95c14097075be7cd4802bf0fe905f1e1747982eb2783db0f764774b4fb
3
+ size 4184
runs/Oct28_12-21-08_3c3f53392730/events.out.tfevents.1730118074.3c3f53392730.13137.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6de1849af0144476bf50e520905c9787e9696f610d796823df7675c3b6b25bd4
3
+ size 4427
runs/Oct28_12-24-47_3c3f53392730/events.out.tfevents.1730118293.3c3f53392730.14471.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5358883f159f85a132382d0512ffcaaf62a66f761eb6948a1d76a7dff66ef969
3
+ size 34733
runs/Oct28_12-45-05_3c3f53392730/events.out.tfevents.1730119512.3c3f53392730.19692.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f31639bbbc33d4720f2519938a2a8bb3d0f5259465683dd9202985abfc5ad3
3
+ size 7531
runs/Oct28_12-49-13_3c3f53392730/events.out.tfevents.1730119760.3c3f53392730.21334.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a95f6cf02e692620f8265454c00e27a13e5c8842ae3389d2d1f9a5adaa593ab
3
+ size 74330
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
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": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fdb17fe2085f73bdf532d3d0579a9cf6fc49d8c98add89223c5b3cc0f4b11cf
3
+ size 5624