Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +32 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Jan17_16-29-47_692d173bedf6/1673973015.5810778/events.out.tfevents.1673973015.692d173bedf6.129.1 +3 -0
- runs/Jan17_16-29-47_692d173bedf6/events.out.tfevents.1673973015.692d173bedf6.129.0 +3 -0
- runs/Jan17_16-34-07_692d173bedf6/1673973371.4976876/events.out.tfevents.1673973371.692d173bedf6.129.3 +3 -0
- runs/Jan17_16-34-07_692d173bedf6/1673974025.1044576/events.out.tfevents.1673974025.692d173bedf6.129.5 +3 -0
- runs/Jan17_16-34-07_692d173bedf6/events.out.tfevents.1673973371.692d173bedf6.129.2 +3 -0
- runs/Jan17_16-34-07_692d173bedf6/events.out.tfevents.1673974025.692d173bedf6.129.4 +3 -0
- runs/Jan17_16-49-38_692d173bedf6/1673974189.2620456/events.out.tfevents.1673974189.692d173bedf6.9539.1 +3 -0
- runs/Jan17_16-49-38_692d173bedf6/1673976959.6184778/events.out.tfevents.1673976959.692d173bedf6.9539.2 +3 -0
- runs/Jan17_16-49-38_692d173bedf6/events.out.tfevents.1673974189.692d173bedf6.9539.0 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +67 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaForSequenceClassification"
|
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": 512,
|
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": "4.25.1",
|
30 |
+
"type_vocab_size": 0,
|
31 |
+
"vocab_size": 50265
|
32 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1db01269435cf914cd76cb4d66a9efb9b9e72b79432ce97b1b1124479c7f02e
|
3 |
+
size 1624998577
|
runs/Jan17_16-29-47_692d173bedf6/1673973015.5810778/events.out.tfevents.1673973015.692d173bedf6.129.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec2e0adbb4e6f38af9798d44d53d5163824edb78aeeb59cf12edd502de69aef8
|
3 |
+
size 5543
|
runs/Jan17_16-29-47_692d173bedf6/events.out.tfevents.1673973015.692d173bedf6.129.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38112b055ac590b1c213211c3cb4fc97a7da01ab1cd74ba4bc05cd3175ab5f42
|
3 |
+
size 3815
|
runs/Jan17_16-34-07_692d173bedf6/1673973371.4976876/events.out.tfevents.1673973371.692d173bedf6.129.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:214cecfe8409bd32302151ff96378c48e280bf4f698b461e909185f851af6539
|
3 |
+
size 5543
|
runs/Jan17_16-34-07_692d173bedf6/1673974025.1044576/events.out.tfevents.1673974025.692d173bedf6.129.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:360570709f9cb412fe40c622553f9a8d52ca310c6e856fa7d50347cdb976b59c
|
3 |
+
size 5543
|
runs/Jan17_16-34-07_692d173bedf6/events.out.tfevents.1673973371.692d173bedf6.129.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:926a151091d325bd1c18bee2ba952074f83e7188a876f2f1521d69dc33eabfc7
|
3 |
+
size 4130
|
runs/Jan17_16-34-07_692d173bedf6/events.out.tfevents.1673974025.692d173bedf6.129.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:946fb42b1a23f43fad002459a67bbade151d94575d43062d09c1c5565425fe0f
|
3 |
+
size 3816
|
runs/Jan17_16-49-38_692d173bedf6/1673974189.2620456/events.out.tfevents.1673974189.692d173bedf6.9539.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de9194b14a8214fa41d2f41fdd1a31e23b4c92bf39c9b237b5c7d4f7020f39e4
|
3 |
+
size 5543
|
runs/Jan17_16-49-38_692d173bedf6/1673976959.6184778/events.out.tfevents.1673976959.692d173bedf6.9539.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9293ad497eee2beefac48ae9c1ee48bda1b2cf373e3a4f2ae5c49069927a612a
|
3 |
+
size 5543
|
runs/Jan17_16-49-38_692d173bedf6/events.out.tfevents.1673974189.692d173bedf6.9539.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f9246fddaa148362d97fc0fe59b720d57cc4d78ebc504a65c117111caea5ed9
|
3 |
+
size 10425
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "[CLS]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "[SEP]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "[MASK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "[PAD]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "[SEP]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "[UNK]",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
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 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "[CLS]",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"cls_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "[CLS]",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"do_lower_case": false,
|
21 |
+
"eos_token": {
|
22 |
+
"__type": "AddedToken",
|
23 |
+
"content": "[SEP]",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
},
|
29 |
+
"errors": "replace",
|
30 |
+
"mask_token": {
|
31 |
+
"__type": "AddedToken",
|
32 |
+
"content": "[MASK]",
|
33 |
+
"lstrip": true,
|
34 |
+
"normalized": true,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
+
"model_max_length": 512,
|
39 |
+
"name_or_path": "microsoft/deberta-large",
|
40 |
+
"pad_token": {
|
41 |
+
"__type": "AddedToken",
|
42 |
+
"content": "[PAD]",
|
43 |
+
"lstrip": false,
|
44 |
+
"normalized": true,
|
45 |
+
"rstrip": false,
|
46 |
+
"single_word": false
|
47 |
+
},
|
48 |
+
"sep_token": {
|
49 |
+
"__type": "AddedToken",
|
50 |
+
"content": "[SEP]",
|
51 |
+
"lstrip": false,
|
52 |
+
"normalized": true,
|
53 |
+
"rstrip": false,
|
54 |
+
"single_word": false
|
55 |
+
},
|
56 |
+
"special_tokens_map_file": null,
|
57 |
+
"tokenizer_class": "DebertaTokenizer",
|
58 |
+
"unk_token": {
|
59 |
+
"__type": "AddedToken",
|
60 |
+
"content": "[UNK]",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false
|
65 |
+
},
|
66 |
+
"vocab_type": "gpt2"
|
67 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4549e7eb1d20bb870bfd4525a01126152824cef853b2097844f568105fc8bf80
|
3 |
+
size 3451
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|