duynhatran
commited on
Commit
•
58de04c
1
Parent(s):
4d8d419
Training in progress, step 500
Browse files
config.json
CHANGED
@@ -1,18 +1,19 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "microsoft/deberta-base",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"hidden_act": "gelu",
|
8 |
-
"hidden_dropout_prob": 0.
|
9 |
"hidden_size": 768,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 3072,
|
12 |
"layer_norm_eps": 1e-07,
|
13 |
"max_position_embeddings": 512,
|
14 |
"max_relative_positions": -1,
|
15 |
-
"model_type": "deberta",
|
|
|
16 |
"num_attention_heads": 12,
|
17 |
"num_hidden_layers": 12,
|
18 |
"pad_token_id": 0,
|
@@ -20,13 +21,15 @@
|
|
20 |
"pooler_hidden_act": "gelu",
|
21 |
"pooler_hidden_size": 768,
|
22 |
"pos_att_type": [
|
23 |
-
"
|
24 |
-
"
|
25 |
],
|
26 |
"position_biased_input": false,
|
|
|
27 |
"relative_attention": true,
|
|
|
28 |
"torch_dtype": "float32",
|
29 |
"transformers_version": "4.42.4",
|
30 |
"type_vocab_size": 0,
|
31 |
-
"vocab_size":
|
32 |
}
|
|
|
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": 0.5,
|
9 |
"hidden_size": 768,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 3072,
|
12 |
"layer_norm_eps": 1e-07,
|
13 |
"max_position_embeddings": 512,
|
14 |
"max_relative_positions": -1,
|
15 |
+
"model_type": "deberta-v2",
|
16 |
+
"norm_rel_ebd": "layer_norm",
|
17 |
"num_attention_heads": 12,
|
18 |
"num_hidden_layers": 12,
|
19 |
"pad_token_id": 0,
|
|
|
21 |
"pooler_hidden_act": "gelu",
|
22 |
"pooler_hidden_size": 768,
|
23 |
"pos_att_type": [
|
24 |
+
"p2c",
|
25 |
+
"c2p"
|
26 |
],
|
27 |
"position_biased_input": false,
|
28 |
+
"position_buckets": 256,
|
29 |
"relative_attention": true,
|
30 |
+
"share_att_key": true,
|
31 |
"torch_dtype": "float32",
|
32 |
"transformers_version": "4.42.4",
|
33 |
"type_vocab_size": 0,
|
34 |
+
"vocab_size": 128100
|
35 |
}
|
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:e07b7308f6f36be00733bed8b37148023cf0947ae2619c59031dcb48dd880f01
|
3 |
+
size 737719272
|
runs/Sep04_16-42-01_0ecfd9ff1619/events.out.tfevents.1725468135.0ecfd9ff1619.2927.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1dd4abf1e0ae2c85997e560b7c31502b6689a0dddc8ce479fd54efef36237dc
|
3 |
+
size 5927
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d32be354cdec47d29bc1f8e98e13bd37902babd35bd9a8299642238b1051981c
|
3 |
size 5176
|