Training in progress, epoch 0
Browse files- .gitignore +1 -0
- added_tokens.json +3 -0
- config.json +79 -0
- pytorch_model.bin +3 -0
- runs/Mar22_19-19-19_d2218ad5dd62/1679512767.9209464/events.out.tfevents.1679512767.d2218ad5dd62.605.3 +3 -0
- runs/Mar22_19-19-19_d2218ad5dd62/events.out.tfevents.1679512767.d2218ad5dd62.605.2 +3 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
.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 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"4": "LABEL_4",
|
16 |
+
"5": "LABEL_5",
|
17 |
+
"6": "LABEL_6",
|
18 |
+
"7": "LABEL_7",
|
19 |
+
"8": "LABEL_8",
|
20 |
+
"9": "LABEL_9",
|
21 |
+
"10": "LABEL_10",
|
22 |
+
"11": "LABEL_11",
|
23 |
+
"12": "LABEL_12",
|
24 |
+
"13": "LABEL_13",
|
25 |
+
"14": "LABEL_14",
|
26 |
+
"15": "LABEL_15",
|
27 |
+
"16": "LABEL_16",
|
28 |
+
"17": "LABEL_17",
|
29 |
+
"18": "LABEL_18",
|
30 |
+
"19": "LABEL_19"
|
31 |
+
},
|
32 |
+
"initializer_range": 0.02,
|
33 |
+
"intermediate_size": 3072,
|
34 |
+
"label2id": {
|
35 |
+
"LABEL_0": 0,
|
36 |
+
"LABEL_1": 1,
|
37 |
+
"LABEL_10": 10,
|
38 |
+
"LABEL_11": 11,
|
39 |
+
"LABEL_12": 12,
|
40 |
+
"LABEL_13": 13,
|
41 |
+
"LABEL_14": 14,
|
42 |
+
"LABEL_15": 15,
|
43 |
+
"LABEL_16": 16,
|
44 |
+
"LABEL_17": 17,
|
45 |
+
"LABEL_18": 18,
|
46 |
+
"LABEL_19": 19,
|
47 |
+
"LABEL_2": 2,
|
48 |
+
"LABEL_3": 3,
|
49 |
+
"LABEL_4": 4,
|
50 |
+
"LABEL_5": 5,
|
51 |
+
"LABEL_6": 6,
|
52 |
+
"LABEL_7": 7,
|
53 |
+
"LABEL_8": 8,
|
54 |
+
"LABEL_9": 9
|
55 |
+
},
|
56 |
+
"layer_norm_eps": 1e-07,
|
57 |
+
"max_position_embeddings": 512,
|
58 |
+
"max_relative_positions": -1,
|
59 |
+
"model_type": "deberta-v2",
|
60 |
+
"norm_rel_ebd": "layer_norm",
|
61 |
+
"num_attention_heads": 12,
|
62 |
+
"num_hidden_layers": 12,
|
63 |
+
"pad_token_id": 0,
|
64 |
+
"pooler_dropout": 0,
|
65 |
+
"pooler_hidden_act": "gelu",
|
66 |
+
"pooler_hidden_size": 768,
|
67 |
+
"pos_att_type": [
|
68 |
+
"p2c",
|
69 |
+
"c2p"
|
70 |
+
],
|
71 |
+
"position_biased_input": false,
|
72 |
+
"position_buckets": 256,
|
73 |
+
"relative_attention": true,
|
74 |
+
"share_att_key": true,
|
75 |
+
"torch_dtype": "float32",
|
76 |
+
"transformers_version": "4.27.2",
|
77 |
+
"type_vocab_size": 0,
|
78 |
+
"vocab_size": 128100
|
79 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c71a6a5b07fcbdb54a332e15d720ee1438383f50354e0c0deaf88c300970bf58
|
3 |
+
size 737824121
|
runs/Mar22_19-19-19_d2218ad5dd62/1679512767.9209464/events.out.tfevents.1679512767.d2218ad5dd62.605.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82e9e79ea602b39c7ad1094eeadda0811a2f372526b9a0437bea5365b2702049
|
3 |
+
size 5817
|
runs/Mar22_19-19-19_d2218ad5dd62/events.out.tfevents.1679512767.d2218ad5dd62.605.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c871598bda913d22deac76d96008dbbf29390dc2069c72f1e43fb9c21eeb61da
|
3 |
+
size 5408
|
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 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
5 |
+
"eos_token": "[SEP]",
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"pad_token": "[PAD]",
|
9 |
+
"sep_token": "[SEP]",
|
10 |
+
"sp_model_kwargs": {},
|
11 |
+
"special_tokens_map_file": null,
|
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 sha256:23a80515fd5823c7838b3dd6c79b5a4b53edf94e4f2b6522d73f5c98c3e48249
|
3 |
+
size 3579
|