ShihHsuanChen commited on
Commit
f7a7507
·
0 Parent(s):
Files changed (6) hide show
  1. .gitattributes +1 -0
  2. README.md +0 -0
  3. config.json +51 -0
  4. model.safetensors +3 -0
  5. train_config.json +1 -0
  6. train_log.csv +21 -0
.gitattributes ADDED
@@ -0,0 +1 @@
 
 
1
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
README.md ADDED
File without changes
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 768,
9
+ "id2label": {
10
+ "0": "sadness",
11
+ "1": "joy",
12
+ "2": "love",
13
+ "3": "anger",
14
+ "4": "fear",
15
+ "5": "surprise"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "anger": 3,
21
+ "fear": 4,
22
+ "joy": 1,
23
+ "love": 2,
24
+ "sadness": 0,
25
+ "surprise": 5
26
+ },
27
+ "layer_norm_eps": 1e-07,
28
+ "legacy": true,
29
+ "max_position_embeddings": 512,
30
+ "max_relative_positions": -1,
31
+ "model_type": "deberta-v2",
32
+ "norm_rel_ebd": "layer_norm",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 12,
35
+ "pad_token_id": 0,
36
+ "pooler_dropout": 0,
37
+ "pooler_hidden_act": "gelu",
38
+ "pooler_hidden_size": 768,
39
+ "pos_att_type": [
40
+ "p2c",
41
+ "c2p"
42
+ ],
43
+ "position_biased_input": false,
44
+ "position_buckets": 256,
45
+ "relative_attention": true,
46
+ "share_att_key": true,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.51.3",
49
+ "type_vocab_size": 0,
50
+ "vocab_size": 128100
51
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be53921899723ea498ad2ececca0fddbc4e3a679147b7935903bf83ae645c7b9
3
+ size 737731584
train_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 567, "ddp": true, "learning_rate": 5e-05, "train_batch_size": 80, "valid_batch_size": 80, "lr_scheduler_type": "linear", "num_epochs": 20, "num_warmup_steps": 125, "max_train_steps": null, "max_valid_steps": null, "max_length": 72}
train_log.csv ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,lr,train_loss,valid_loss,valid_accuracy
2
+ 1,4e-05,0.6908868551254272,0.6089823941389719,0.8083333422740301
3
+ 2,4.8001066098081025e-05,0.3298718333244324,0.19640956446528435,0.9239583512147268
4
+ 3,4.5335820895522394e-05,0.19889609515666962,0.13936338853091002,0.940625011920929
5
+ 4,4.2670575692963755e-05,0.12645851075649261,0.11494975987200935,0.9489583472410837
6
+ 5,4.000533049040512e-05,0.09315995872020721,0.11977107791850965,0.9468750158945719
7
+ 6,3.7340085287846486e-05,0.08274087309837341,0.1362296549292902,0.9375000099341074
8
+ 7,3.467484008528785e-05,0.07604973763227463,0.1645363668600718,0.939583346247673
9
+ 8,3.200959488272921e-05,0.057310208678245544,0.16730575651551285,0.9343750129143397
10
+ 9,2.934434968017058e-05,0.0632554441690445,0.1683110591645042,0.9437500139077505
11
+ 10,2.6679104477611942e-05,0.08436565846204758,0.19473591508964697,0.9447916746139526
12
+ 11,2.4013859275053304e-05,0.01617152988910675,0.18308352880800763,0.9416666626930237
13
+ 12,2.1348614072494673e-05,0.03712035343050957,0.21083885338157415,0.9479166716337204
14
+ 13,1.8683368869936034e-05,0.021857302635908127,0.2227405613909165,0.940625011920929
15
+ 14,1.60181236673774e-05,0.004591828212141991,0.25835480727255344,0.9406250069538752
16
+ 15,1.3352878464818763e-05,0.009411506354808807,0.2548551845053832,0.9354166785875956
17
+ 16,1.0687633262260128e-05,0.0017591080395504832,0.24660054633083442,0.9385416706403097
18
+ 17,8.022388059701493e-06,0.001765915541909635,0.2517154838424176,0.9416666726271311
19
+ 18,5.357142857142857e-06,0.001407127594575286,0.2756552553425233,0.9375000049670538
20
+ 19,2.6918976545842217e-06,0.0009788793977349997,0.2826926866546273,0.9364583442608515
21
+ 20,2.6652452025586355e-08,0.0011572353541851044,0.28512330415348214,0.9364583442608515