Hugging Face's logo

tanapatentlm
/
patentdeberta_large_spec_128_pwi

Fill-Mask
Transformers
PyTorch
TensorBoard
deberta
Inference Endpoints
Model card Files Metrics Community
JYYong commited on
Commit
ec40d54
•
1 Parent(s): 975d3d3

Training in progress, step 500

Browse files
Files changed (10) hide show
  1. .gitignore +1 -0
  2. config.json +32 -0
  3. pytorch_model.bin +3 -0
  4. runs/Jul07_09-51-45_854686ae4dde/1657187518.717184/events.out.tfevents.1657187518.854686ae4dde.384372.1 +3 -0
  5. runs/Jul07_09-51-45_854686ae4dde/events.out.tfevents.1657187518.854686ae4dde.384372.0 +3 -0
  6. runs/Jul07_09-58-00_854686ae4dde/1657187886.45254/events.out.tfevents.1657187886.854686ae4dde.390116.1 +3 -0
  7. runs/Jul07_09-58-00_854686ae4dde/events.out.tfevents.1657187886.854686ae4dde.390116.0 +3 -0
  8. runs/Jul07_10-37-24_854686ae4dde/1657190253.966735/events.out.tfevents.1657190253.854686ae4dde.394114.1 +3 -0
  9. runs/Jul07_10-37-24_854686ae4dde/events.out.tfevents.1657190253.854686ae4dde.394114.0 +3 -0
  10. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tanapatentlm/patentdeberta_large_spec_512_pwi",
3
+ "architectures": [
4
+ "DebertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 128,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "pad_token_id": 0,
19
+ "pooler_dropout": 0,
20
+ "pooler_hidden_act": "gelu",
21
+ "pooler_hidden_size": 1024,
22
+ "pos_att_type": [
23
+ "c2p",
24
+ "p2c"
25
+ ],
26
+ "position_biased_input": false,
27
+ "relative_attention": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.20.1",
30
+ "type_vocab_size": 0,
31
+ "vocab_size": 50270
32
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49750fbaa98a668aa99bfe1e94f0e9c9da68bde65daec08a518317bcc4049526
3
+ size 1622068973
runs/Jul07_09-51-45_854686ae4dde/1657187518.717184/events.out.tfevents.1657187518.854686ae4dde.384372.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e401904a5bfaef9cee3602588e67ec3bb2b2880d920443143c818ea0110eaabb
3
+ size 5455
runs/Jul07_09-51-45_854686ae4dde/events.out.tfevents.1657187518.854686ae4dde.384372.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dd4183354f2d162d1a7609f7147406ec26a15e3a08a01e888d3c80aae14e738
3
+ size 3888
runs/Jul07_09-58-00_854686ae4dde/1657187886.45254/events.out.tfevents.1657187886.854686ae4dde.390116.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a129744a120b1d1251dd0f38efc3ac0a0af8154a063ef722ac02a41593c5ac3
3
+ size 5455
runs/Jul07_09-58-00_854686ae4dde/events.out.tfevents.1657187886.854686ae4dde.390116.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:345ed1633f18cc4a11de919da0a9642360f29e9d3c75ec4570fc71487dc51f8a
3
+ size 3888
runs/Jul07_10-37-24_854686ae4dde/1657190253.966735/events.out.tfevents.1657190253.854686ae4dde.394114.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed95715fe96f12313aa2f5968c17cdb022ec428b37f2c1d5b8f5e7c848acdb45
3
+ size 5455
runs/Jul07_10-37-24_854686ae4dde/events.out.tfevents.1657190253.854686ae4dde.394114.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e80077e755b9f51bb73ff825d88af2c641c7f58b4e4f9852d58f83af5dda7a14
3
+ size 6020
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32f4bb9e67722b607eacbed852808deaf99173a8ff880356f898359318ef2a83
3
+ size 3375