Initial Commit
Browse files- README.md +117 -0
- config.json +159 -0
- eval_results_ml.json +1 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: mit
|
4 |
+
base_model: microsoft/mdeberta-v3-base
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- massive
|
9 |
+
metrics:
|
10 |
+
- accuracy
|
11 |
+
- f1
|
12 |
+
model-index:
|
13 |
+
- name: scenario-NON-KD-SCR-D2_data-AmazonScience_massive_all_1_144
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Text Classification
|
17 |
+
type: text-classification
|
18 |
+
dataset:
|
19 |
+
name: massive
|
20 |
+
type: massive
|
21 |
+
config: all_1.1
|
22 |
+
split: validation
|
23 |
+
args: all_1.1
|
24 |
+
metrics:
|
25 |
+
- name: Accuracy
|
26 |
+
type: accuracy
|
27 |
+
value: 0.8158178516024065
|
28 |
+
- name: F1
|
29 |
+
type: f1
|
30 |
+
value: 0.790068262479823
|
31 |
+
---
|
32 |
+
|
33 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
34 |
+
should probably proofread and complete it, then remove this comment. -->
|
35 |
+
|
36 |
+
# scenario-NON-KD-SCR-D2_data-AmazonScience_massive_all_1_144
|
37 |
+
|
38 |
+
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the massive dataset.
|
39 |
+
It achieves the following results on the evaluation set:
|
40 |
+
- Loss: 1.9525
|
41 |
+
- Accuracy: 0.8158
|
42 |
+
- F1: 0.7901
|
43 |
+
|
44 |
+
## Model description
|
45 |
+
|
46 |
+
More information needed
|
47 |
+
|
48 |
+
## Intended uses & limitations
|
49 |
+
|
50 |
+
More information needed
|
51 |
+
|
52 |
+
## Training and evaluation data
|
53 |
+
|
54 |
+
More information needed
|
55 |
+
|
56 |
+
## Training procedure
|
57 |
+
|
58 |
+
### Training hyperparameters
|
59 |
+
|
60 |
+
The following hyperparameters were used during training:
|
61 |
+
- learning_rate: 5e-05
|
62 |
+
- train_batch_size: 32
|
63 |
+
- eval_batch_size: 32
|
64 |
+
- seed: 44
|
65 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
66 |
+
- lr_scheduler_type: linear
|
67 |
+
- num_epochs: 10
|
68 |
+
|
69 |
+
### Training results
|
70 |
+
|
71 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
72 |
+
|:-------------:|:------:|:------:|:---------------:|:--------:|:------:|
|
73 |
+
| 1.2857 | 0.2672 | 5000 | 1.2982 | 0.6464 | 0.5527 |
|
74 |
+
| 0.9859 | 0.5344 | 10000 | 1.0042 | 0.7331 | 0.6625 |
|
75 |
+
| 0.8126 | 0.8017 | 15000 | 0.9054 | 0.7613 | 0.6991 |
|
76 |
+
| 0.5568 | 1.0689 | 20000 | 0.8391 | 0.7828 | 0.7319 |
|
77 |
+
| 0.5531 | 1.3361 | 25000 | 0.8316 | 0.7886 | 0.7394 |
|
78 |
+
| 0.5497 | 1.6033 | 30000 | 0.7894 | 0.8011 | 0.7618 |
|
79 |
+
| 0.5099 | 1.8706 | 35000 | 0.7805 | 0.8050 | 0.7616 |
|
80 |
+
| 0.3327 | 2.1378 | 40000 | 0.8676 | 0.8040 | 0.7633 |
|
81 |
+
| 0.3482 | 2.4050 | 45000 | 0.8556 | 0.8060 | 0.7700 |
|
82 |
+
| 0.3506 | 2.6722 | 50000 | 0.8309 | 0.8087 | 0.7816 |
|
83 |
+
| 0.3508 | 2.9394 | 55000 | 0.8149 | 0.8105 | 0.7683 |
|
84 |
+
| 0.221 | 3.2067 | 60000 | 0.9645 | 0.8070 | 0.7760 |
|
85 |
+
| 0.222 | 3.4739 | 65000 | 0.9305 | 0.8113 | 0.7836 |
|
86 |
+
| 0.2414 | 3.7411 | 70000 | 0.9195 | 0.8122 | 0.7846 |
|
87 |
+
| 0.2032 | 4.0083 | 75000 | 0.9858 | 0.8141 | 0.7855 |
|
88 |
+
| 0.1457 | 4.2756 | 80000 | 1.0865 | 0.8130 | 0.7885 |
|
89 |
+
| 0.155 | 4.5428 | 85000 | 1.0413 | 0.8133 | 0.7830 |
|
90 |
+
| 0.1535 | 4.8100 | 90000 | 1.0934 | 0.8157 | 0.7887 |
|
91 |
+
| 0.0888 | 5.0772 | 95000 | 1.2135 | 0.8152 | 0.7896 |
|
92 |
+
| 0.0931 | 5.3444 | 100000 | 1.3402 | 0.8121 | 0.7857 |
|
93 |
+
| 0.1024 | 5.6117 | 105000 | 1.2838 | 0.8107 | 0.7848 |
|
94 |
+
| 0.1044 | 5.8789 | 110000 | 1.3039 | 0.8133 | 0.7885 |
|
95 |
+
| 0.0595 | 6.1461 | 115000 | 1.4268 | 0.8129 | 0.7877 |
|
96 |
+
| 0.0678 | 6.4133 | 120000 | 1.4729 | 0.8132 | 0.7866 |
|
97 |
+
| 0.0676 | 6.6806 | 125000 | 1.5201 | 0.8127 | 0.7859 |
|
98 |
+
| 0.0779 | 6.9478 | 130000 | 1.4956 | 0.8151 | 0.7905 |
|
99 |
+
| 0.0429 | 7.2150 | 135000 | 1.6860 | 0.8142 | 0.7897 |
|
100 |
+
| 0.0507 | 7.4822 | 140000 | 1.6751 | 0.8124 | 0.7842 |
|
101 |
+
| 0.0463 | 7.7495 | 145000 | 1.7002 | 0.8133 | 0.7866 |
|
102 |
+
| 0.034 | 8.0167 | 150000 | 1.7596 | 0.8135 | 0.7885 |
|
103 |
+
| 0.0254 | 8.2839 | 155000 | 1.8539 | 0.8133 | 0.7876 |
|
104 |
+
| 0.0294 | 8.5511 | 160000 | 1.8675 | 0.8146 | 0.7862 |
|
105 |
+
| 0.0296 | 8.8183 | 165000 | 1.8644 | 0.8142 | 0.7862 |
|
106 |
+
| 0.0174 | 9.0856 | 170000 | 1.9111 | 0.8151 | 0.7899 |
|
107 |
+
| 0.0159 | 9.3528 | 175000 | 1.9342 | 0.8156 | 0.7896 |
|
108 |
+
| 0.0171 | 9.6200 | 180000 | 1.9399 | 0.8161 | 0.7901 |
|
109 |
+
| 0.0209 | 9.8872 | 185000 | 1.9525 | 0.8158 | 0.7901 |
|
110 |
+
|
111 |
+
|
112 |
+
### Framework versions
|
113 |
+
|
114 |
+
- Transformers 4.44.2
|
115 |
+
- Pytorch 2.1.1+cu121
|
116 |
+
- Datasets 2.14.5
|
117 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/mdeberta-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,
|
10 |
+
"id2label": {
|
11 |
+
"0": "LABEL_0",
|
12 |
+
"1": "LABEL_1",
|
13 |
+
"2": "LABEL_2",
|
14 |
+
"3": "LABEL_3",
|
15 |
+
"4": "LABEL_4",
|
16 |
+
"5": "LABEL_5",
|
17 |
+
"6": "LABEL_6",
|
18 |
+
"7": "LABEL_7",
|
19 |
+
"8": "LABEL_8",
|
20 |
+
"9": "LABEL_9",
|
21 |
+
"10": "LABEL_10",
|
22 |
+
"11": "LABEL_11",
|
23 |
+
"12": "LABEL_12",
|
24 |
+
"13": "LABEL_13",
|
25 |
+
"14": "LABEL_14",
|
26 |
+
"15": "LABEL_15",
|
27 |
+
"16": "LABEL_16",
|
28 |
+
"17": "LABEL_17",
|
29 |
+
"18": "LABEL_18",
|
30 |
+
"19": "LABEL_19",
|
31 |
+
"20": "LABEL_20",
|
32 |
+
"21": "LABEL_21",
|
33 |
+
"22": "LABEL_22",
|
34 |
+
"23": "LABEL_23",
|
35 |
+
"24": "LABEL_24",
|
36 |
+
"25": "LABEL_25",
|
37 |
+
"26": "LABEL_26",
|
38 |
+
"27": "LABEL_27",
|
39 |
+
"28": "LABEL_28",
|
40 |
+
"29": "LABEL_29",
|
41 |
+
"30": "LABEL_30",
|
42 |
+
"31": "LABEL_31",
|
43 |
+
"32": "LABEL_32",
|
44 |
+
"33": "LABEL_33",
|
45 |
+
"34": "LABEL_34",
|
46 |
+
"35": "LABEL_35",
|
47 |
+
"36": "LABEL_36",
|
48 |
+
"37": "LABEL_37",
|
49 |
+
"38": "LABEL_38",
|
50 |
+
"39": "LABEL_39",
|
51 |
+
"40": "LABEL_40",
|
52 |
+
"41": "LABEL_41",
|
53 |
+
"42": "LABEL_42",
|
54 |
+
"43": "LABEL_43",
|
55 |
+
"44": "LABEL_44",
|
56 |
+
"45": "LABEL_45",
|
57 |
+
"46": "LABEL_46",
|
58 |
+
"47": "LABEL_47",
|
59 |
+
"48": "LABEL_48",
|
60 |
+
"49": "LABEL_49",
|
61 |
+
"50": "LABEL_50",
|
62 |
+
"51": "LABEL_51",
|
63 |
+
"52": "LABEL_52",
|
64 |
+
"53": "LABEL_53",
|
65 |
+
"54": "LABEL_54",
|
66 |
+
"55": "LABEL_55",
|
67 |
+
"56": "LABEL_56",
|
68 |
+
"57": "LABEL_57",
|
69 |
+
"58": "LABEL_58",
|
70 |
+
"59": "LABEL_59"
|
71 |
+
},
|
72 |
+
"initializer_range": 0.02,
|
73 |
+
"intermediate_size": 3072,
|
74 |
+
"label2id": {
|
75 |
+
"LABEL_0": 0,
|
76 |
+
"LABEL_1": 1,
|
77 |
+
"LABEL_10": 10,
|
78 |
+
"LABEL_11": 11,
|
79 |
+
"LABEL_12": 12,
|
80 |
+
"LABEL_13": 13,
|
81 |
+
"LABEL_14": 14,
|
82 |
+
"LABEL_15": 15,
|
83 |
+
"LABEL_16": 16,
|
84 |
+
"LABEL_17": 17,
|
85 |
+
"LABEL_18": 18,
|
86 |
+
"LABEL_19": 19,
|
87 |
+
"LABEL_2": 2,
|
88 |
+
"LABEL_20": 20,
|
89 |
+
"LABEL_21": 21,
|
90 |
+
"LABEL_22": 22,
|
91 |
+
"LABEL_23": 23,
|
92 |
+
"LABEL_24": 24,
|
93 |
+
"LABEL_25": 25,
|
94 |
+
"LABEL_26": 26,
|
95 |
+
"LABEL_27": 27,
|
96 |
+
"LABEL_28": 28,
|
97 |
+
"LABEL_29": 29,
|
98 |
+
"LABEL_3": 3,
|
99 |
+
"LABEL_30": 30,
|
100 |
+
"LABEL_31": 31,
|
101 |
+
"LABEL_32": 32,
|
102 |
+
"LABEL_33": 33,
|
103 |
+
"LABEL_34": 34,
|
104 |
+
"LABEL_35": 35,
|
105 |
+
"LABEL_36": 36,
|
106 |
+
"LABEL_37": 37,
|
107 |
+
"LABEL_38": 38,
|
108 |
+
"LABEL_39": 39,
|
109 |
+
"LABEL_4": 4,
|
110 |
+
"LABEL_40": 40,
|
111 |
+
"LABEL_41": 41,
|
112 |
+
"LABEL_42": 42,
|
113 |
+
"LABEL_43": 43,
|
114 |
+
"LABEL_44": 44,
|
115 |
+
"LABEL_45": 45,
|
116 |
+
"LABEL_46": 46,
|
117 |
+
"LABEL_47": 47,
|
118 |
+
"LABEL_48": 48,
|
119 |
+
"LABEL_49": 49,
|
120 |
+
"LABEL_5": 5,
|
121 |
+
"LABEL_50": 50,
|
122 |
+
"LABEL_51": 51,
|
123 |
+
"LABEL_52": 52,
|
124 |
+
"LABEL_53": 53,
|
125 |
+
"LABEL_54": 54,
|
126 |
+
"LABEL_55": 55,
|
127 |
+
"LABEL_56": 56,
|
128 |
+
"LABEL_57": 57,
|
129 |
+
"LABEL_58": 58,
|
130 |
+
"LABEL_59": 59,
|
131 |
+
"LABEL_6": 6,
|
132 |
+
"LABEL_7": 7,
|
133 |
+
"LABEL_8": 8,
|
134 |
+
"LABEL_9": 9
|
135 |
+
},
|
136 |
+
"layer_norm_eps": 1e-07,
|
137 |
+
"max_position_embeddings": 512,
|
138 |
+
"max_relative_positions": -1,
|
139 |
+
"model_type": "deberta-v2",
|
140 |
+
"norm_rel_ebd": "layer_norm",
|
141 |
+
"num_attention_heads": 12,
|
142 |
+
"num_hidden_layers": 6,
|
143 |
+
"pad_token_id": 0,
|
144 |
+
"pooler_dropout": 0,
|
145 |
+
"pooler_hidden_act": "gelu",
|
146 |
+
"pooler_hidden_size": 768,
|
147 |
+
"pos_att_type": [
|
148 |
+
"p2c",
|
149 |
+
"c2p"
|
150 |
+
],
|
151 |
+
"position_biased_input": false,
|
152 |
+
"position_buckets": 256,
|
153 |
+
"relative_attention": true,
|
154 |
+
"share_att_key": true,
|
155 |
+
"torch_dtype": "float32",
|
156 |
+
"transformers_version": "4.44.2",
|
157 |
+
"type_vocab_size": 0,
|
158 |
+
"vocab_size": 251000
|
159 |
+
}
|
eval_results_ml.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"zh-CN": {"f1": 0.7662833162101182, "accuracy": 0.8096839273705447}, "id-ID": {"f1": 0.791936085937182, "accuracy": 0.8298587760591796}, "he-IL": {"f1": 0.7546995868698819, "accuracy": 0.8090114324142569}, "ca-ES": {"f1": 0.7716627285190718, "accuracy": 0.8137188971082717}, "lv-LV": {"f1": 0.7756578263764201, "accuracy": 0.8026227303295226}, "el-GR": {"f1": 0.7728765565056955, "accuracy": 0.8177538668459986}, "sv-SE": {"f1": 0.7632187394667299, "accuracy": 0.8157363819771352}, "ms-MY": {"f1": 0.7878501426458103, "accuracy": 0.82817753866846}, "ko-KR": {"f1": 0.7609420439653891, "accuracy": 0.8096839273705447}, "hi-IN": {"f1": 0.7690039456608021, "accuracy": 0.8096839273705447}, "es-ES": {"f1": 0.7598383609511135, "accuracy": 0.8080026899798252}, "jv-ID": {"f1": 0.7554621226813978, "accuracy": 0.8039677202420982}, "am-ET": {"f1": 0.7085069676445124, "accuracy": 0.7484868863483524}, "tl-PH": {"f1": 0.7509640040573857, "accuracy": 0.7972427706792199}, "hy-AM": {"f1": 0.7374190519240533, "accuracy": 0.7999327505043712}, "fi-FI": {"f1": 0.7579482093300729, "accuracy": 0.7948890383322125}, "sl-SL": {"f1": 0.7377782065280359, "accuracy": 0.7948890383322125}, "af-ZA": {"f1": 0.7556122198128261, "accuracy": 0.8059852051109617}, "km-KH": {"f1": 0.6890731324720444, "accuracy": 0.7420981842636181}, "ml-IN": {"f1": 0.7572675222479256, "accuracy": 0.8069939475453934}, "bn-BD": {"f1": 0.7437141399115078, "accuracy": 0.796570275722932}, "zh-TW": {"f1": 0.7776751382297559, "accuracy": 0.7958977807666443}, "mn-MN": {"f1": 0.7767218654514655, "accuracy": 0.8174176193678547}, "th-TH": {"f1": 0.7941892608022791, "accuracy": 0.8103564223268326}, "ur-PK": {"f1": 0.7444451193761809, "accuracy": 0.7908540685944856}, "my-MM": {"f1": 0.7460507100912702, "accuracy": 0.7972427706792199}, "cy-GB": {"f1": 0.738387716586206, "accuracy": 0.7979152656355077}, "hu-HU": {"f1": 0.7430028758685533, "accuracy": 0.7881640887693342}, "ja-JP": {"f1": 0.7678909759702931, "accuracy": 0.808338937457969}, "sq-AL": {"f1": 0.7814638611193184, "accuracy": 0.7989240080699395}, "it-IT": {"f1": 0.7787302675572307, "accuracy": 0.8295225285810356}, "ru-RU": {"f1": 0.7814629919692825, "accuracy": 0.8211163416274377}, "de-DE": {"f1": 0.7533074303816854, "accuracy": 0.8053127101546739}, "fr-FR": {"f1": 0.7715758795456081, "accuracy": 0.8133826496301277}, "vi-VN": {"f1": 0.7599538441367071, "accuracy": 0.8029589778076665}, "is-IS": {"f1": 0.7698857108361212, "accuracy": 0.8113651647612643}, "kn-IN": {"f1": 0.7406854018951025, "accuracy": 0.7908540685944856}, "nl-NL": {"f1": 0.7822114085697252, "accuracy": 0.8190988567585743}, "ta-IN": {"f1": 0.7482914737771544, "accuracy": 0.7854741089441829}, "tr-TR": {"f1": 0.7450953099750486, "accuracy": 0.7955615332885003}, "az-AZ": {"f1": 0.7953001260325713, "accuracy": 0.8127101546738399}, "te-IN": {"f1": 0.7350467977273795, "accuracy": 0.7881640887693342}, "pt-PT": {"f1": 0.7601369696806045, "accuracy": 0.8090114324142569}, "ka-GE": {"f1": 0.7317818920681861, "accuracy": 0.7639542703429725}, "ro-RO": {"f1": 0.7659765947189487, "accuracy": 0.8093476798924009}, "da-DK": {"f1": 0.7666088714747586, "accuracy": 0.8227975790181573}, "ar-SA": {"f1": 0.7077296786746656, "accuracy": 0.7468056489576328}, "nb-NO": {"f1": 0.7602826217015248, "accuracy": 0.8190988567585743}, "sw-KE": {"f1": 0.7407670028895473, "accuracy": 0.7844653665097512}, "fa-IR": {"f1": 0.7672339912551724, "accuracy": 0.8184263618022865}, "pl-PL": {"f1": 0.7699483673864845, "accuracy": 0.8080026899798252}, "en-US": {"f1": 0.7782275509992851, "accuracy": 0.8217888365837256}, "all": {"f1": 0.7579118440386778, "accuracy": 0.8021830220888728}}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:382350467badbca264403e2aca38c82736d849a37d610f021048a69ce7167173
|
3 |
+
size 945325776
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:350494c250a7a02b29e526f46ad3e0c2d10caa4ca30ba758344a4189a1488a08
|
3 |
+
size 5304
|