UchihaMadara
commited on
Commit
•
a610cd7
1
Parent(s):
e457c4c
Upload folder using huggingface_hub
Browse files- README.md +23 -0
- config.json +46 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +66 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
# Pretrained checkpoint: microsoft/deberta-large
|
3 |
+
# Traning hyperparameters:
|
4 |
+
The following hyperparameters were used during training:
|
5 |
+
- learning_rate: 2e-05
|
6 |
+
- train_batch_size: 16
|
7 |
+
- eval_batch_size: 16
|
8 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
9 |
+
- lr_scheduler_type: linear
|
10 |
+
- num_epochs: 5
|
11 |
+
- prompt_format: sentence aspect - sentiment
|
12 |
+
|
13 |
+
# Training results
|
14 |
+
|
15 |
+
|Epoch | Train loss| Subtask 3 f1 | Subtask 3 precision | Subtask 3 recall | Subtask4 accuracy |
|
16 |
+
|:----:|:---------:|:------------:|:-------------------:|:----------------:|:-----------------:|
|
17 |
+
|1|355.13336368463933|0.8388829215896885|0.9330943847072879|0.7619512195121951|0.8360975609756097|
|
18 |
+
|2|171.31726237665862|0.9082615306639635|0.9451476793248945|0.8741463414634146|0.8809756097560976|
|
19 |
+
|3|96.62600621895399|0.9191321499013807|0.9292123629112662|0.9092682926829269|0.8985365853658537|
|
20 |
+
|4|46.02018972591031|0.920743639921722|0.9234543670264965|0.9180487804878049|0.8848780487804878|
|
21 |
+
|5|18.8767371326976|0.9239130434782609|0.9359359359359359|0.9121951219512195|0.9014634146341464|
|
22 |
+
|
23 |
+
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"id2label": {
|
11 |
+
"0": "positive",
|
12 |
+
"1": "neutral",
|
13 |
+
"2": "negative",
|
14 |
+
"3": "conflict",
|
15 |
+
"4": "none"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 4096,
|
19 |
+
"label2id": {
|
20 |
+
"conflict": 3,
|
21 |
+
"negative": 2,
|
22 |
+
"neutral": 1,
|
23 |
+
"none": 4,
|
24 |
+
"positive": 0
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-07,
|
27 |
+
"max_position_embeddings": 512,
|
28 |
+
"max_relative_positions": -1,
|
29 |
+
"model_type": "deberta",
|
30 |
+
"num_attention_heads": 16,
|
31 |
+
"num_hidden_layers": 24,
|
32 |
+
"pad_token_id": 0,
|
33 |
+
"pooler_dropout": 0,
|
34 |
+
"pooler_hidden_act": "gelu",
|
35 |
+
"pooler_hidden_size": 1024,
|
36 |
+
"pos_att_type": [
|
37 |
+
"c2p",
|
38 |
+
"p2c"
|
39 |
+
],
|
40 |
+
"position_biased_input": false,
|
41 |
+
"relative_attention": true,
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.29.2",
|
44 |
+
"type_vocab_size": 0,
|
45 |
+
"vocab_size": 50265
|
46 |
+
}
|
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:d0a0bde3f473270e483bae16508bb853747923e2c70fcfe69736fd31c636f7ab
|
3 |
+
size 1625010865
|
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 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"clean_up_tokenization_spaces": true,
|
13 |
+
"cls_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "[CLS]",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"do_lower_case": false,
|
22 |
+
"eos_token": {
|
23 |
+
"__type": "AddedToken",
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"errors": "replace",
|
31 |
+
"mask_token": {
|
32 |
+
"__type": "AddedToken",
|
33 |
+
"content": "[MASK]",
|
34 |
+
"lstrip": true,
|
35 |
+
"normalized": true,
|
36 |
+
"rstrip": false,
|
37 |
+
"single_word": false
|
38 |
+
},
|
39 |
+
"model_max_length": 512,
|
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 |
+
"tokenizer_class": "DebertaTokenizer",
|
57 |
+
"unk_token": {
|
58 |
+
"__type": "AddedToken",
|
59 |
+
"content": "[UNK]",
|
60 |
+
"lstrip": false,
|
61 |
+
"normalized": true,
|
62 |
+
"rstrip": false,
|
63 |
+
"single_word": false
|
64 |
+
},
|
65 |
+
"vocab_type": "gpt2"
|
66 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|