matchaoneshot
commited on
Training in progress, epoch 0
Browse files- added_tokens.json +3 -0
- config.json +19 -10
- model.safetensors +2 -2
- runs/Dec12_08-30-40_1b5c407642ff/events.out.tfevents.1733992255.1b5c407642ff.644.0 +3 -0
- special_tokens_map.json +9 -1
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -14
- training_args.bin +1 -1
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
config.json
CHANGED
@@ -1,11 +1,9 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"classifier_dropout": null,
|
8 |
-
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
@@ -309,17 +307,28 @@
|
|
309 |
"LABEL_98": 98,
|
310 |
"LABEL_99": 99
|
311 |
},
|
312 |
-
"layer_norm_eps": 1e-
|
313 |
"max_position_embeddings": 512,
|
314 |
-
"
|
|
|
|
|
315 |
"num_attention_heads": 12,
|
316 |
"num_hidden_layers": 12,
|
317 |
"pad_token_id": 0,
|
318 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
319 |
"problem_type": "multi_label_classification",
|
|
|
|
|
320 |
"torch_dtype": "float32",
|
321 |
"transformers_version": "4.46.3",
|
322 |
-
"type_vocab_size":
|
323 |
-
"
|
324 |
-
"vocab_size": 30522
|
325 |
}
|
|
|
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,
|
|
|
307 |
"LABEL_98": 98,
|
308 |
"LABEL_99": 99
|
309 |
},
|
310 |
+
"layer_norm_eps": 1e-07,
|
311 |
"max_position_embeddings": 512,
|
312 |
+
"max_relative_positions": -1,
|
313 |
+
"model_type": "deberta-v2",
|
314 |
+
"norm_rel_ebd": "layer_norm",
|
315 |
"num_attention_heads": 12,
|
316 |
"num_hidden_layers": 12,
|
317 |
"pad_token_id": 0,
|
318 |
+
"pooler_dropout": 0,
|
319 |
+
"pooler_hidden_act": "gelu",
|
320 |
+
"pooler_hidden_size": 768,
|
321 |
+
"pos_att_type": [
|
322 |
+
"p2c",
|
323 |
+
"c2p"
|
324 |
+
],
|
325 |
+
"position_biased_input": false,
|
326 |
+
"position_buckets": 256,
|
327 |
"problem_type": "multi_label_classification",
|
328 |
+
"relative_attention": true,
|
329 |
+
"share_att_key": true,
|
330 |
"torch_dtype": "float32",
|
331 |
"transformers_version": "4.46.3",
|
332 |
+
"type_vocab_size": 0,
|
333 |
+
"vocab_size": 128100
|
|
|
334 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fabe929cf5dfcccbf33e03187beb6305b43fb97db8506a5defbb3b11fa47ffd
|
3 |
+
size 738165316
|
runs/Dec12_08-30-40_1b5c407642ff/events.out.tfevents.1733992255.1b5c407642ff.644.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd0668066726292656581c267ae20b46bf97e395368eb339f140efebb3163924
|
3 |
+
size 15901
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,15 @@
|
|
1 |
{
|
|
|
2 |
"cls_token": "[CLS]",
|
|
|
3 |
"mask_token": "[MASK]",
|
4 |
"pad_token": "[PAD]",
|
5 |
"sep_token": "[SEP]",
|
6 |
-
"unk_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
|
|
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
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -8,31 +8,31 @@
|
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "[
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "[
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "[
|
29 |
"lstrip": false,
|
30 |
-
"normalized":
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
"content": "[MASK]",
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
@@ -41,15 +41,18 @@
|
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
|
|
44 |
"clean_up_tokenization_spaces": false,
|
45 |
"cls_token": "[CLS]",
|
46 |
-
"do_lower_case":
|
|
|
47 |
"mask_token": "[MASK]",
|
48 |
-
"model_max_length":
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"tokenizer_class": "
|
54 |
-
"unk_token": "[UNK]"
|
|
|
55 |
}
|
|
|
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,
|
|
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
44 |
+
"bos_token": "[CLS]",
|
45 |
"clean_up_tokenization_spaces": false,
|
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
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e76e8f9018ab261d97df157d889c6a7893776ff9e153c7c1157250b71b47e595
|
3 |
size 5304
|