michaellutz commited on
Commit
34d97cf
·
1 Parent(s): 277165a

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "LABEL_0": 0,
20
+ "LABEL_1": 1,
21
+ "LABEL_2": 2,
22
+ "LABEL_3": 3
23
+ },
24
+ "layer_norm_eps": 1e-07,
25
+ "max_position_embeddings": 512,
26
+ "max_relative_positions": -1,
27
+ "model_type": "deberta-v2",
28
+ "norm_rel_ebd": "layer_norm",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 0,
32
+ "pooler_dropout": 0,
33
+ "pooler_hidden_act": "gelu",
34
+ "pooler_hidden_size": 768,
35
+ "pos_att_type": [
36
+ "p2c",
37
+ "c2p"
38
+ ],
39
+ "position_biased_input": false,
40
+ "position_buckets": 256,
41
+ "relative_attention": true,
42
+ "share_att_key": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.31.0",
45
+ "type_vocab_size": 0,
46
+ "vocab_size": 128100
47
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35da0b34937b9fadd64930404a8dc10a7e4a57de8ba48dcdb95b18ce1e4d9ac7
3
+ size 737770485
runs/Aug02_19-29-38_91ce1136aa0e/events.out.tfevents.1691004645.91ce1136aa0e.661.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:390e6c8b71ae8aa26843deabc53fd97232b27560de7b0d3b8c52bd602167ba17
3
+ size 4613
runs/Aug02_19-29-38_91ce1136aa0e/events.out.tfevents.1691005040.91ce1136aa0e.661.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e78883ef2170b422a1eecda7b30a70213e44894a6760ace16ca21c5edce2d6
3
+ size 4613
runs/Aug02_19-55-17_91ce1136aa0e/events.out.tfevents.1691006126.91ce1136aa0e.661.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a906110b4011a396bf97336af27b9a4db0638d7803f4fb4215c83c7f02b44499
3
+ size 4936
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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": "[UNK]"
9
+ }
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": false,
6
+ "eos_token": "[SEP]",
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "split_by_punct": false,
13
+ "tokenizer_class": "DebertaV2Tokenizer",
14
+ "unk_token": "[UNK]",
15
+ "vocab_type": "spm"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:592a165621cf2b494282001dad45610339e9d771a773851444b0d3a006ff8e49
3
+ size 4027