haryoaw commited on
Commit
9d90f6b
1 Parent(s): 8720424

Initial Commit

Browse files
Files changed (4) hide show
  1. README.md +175 -0
  2. config.json +159 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/mdeberta-v3-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - massive
8
+ metrics:
9
+ - accuracy
10
+ - f1
11
+ model-index:
12
+ - name: scenario-KD-PR-MSV-D2_data-AmazonScience_massive_all_1_166
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # scenario-KD-PR-MSV-D2_data-AmazonScience_massive_all_1_166
20
+
21
+ This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the massive dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 1.5394
24
+ - Accuracy: 0.8627
25
+ - F1: 0.8453
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 5e-05
45
+ - train_batch_size: 32
46
+ - eval_batch_size: 32
47
+ - seed: 66
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - num_epochs: 30
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
+ |:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|
56
+ | 3.4018 | 0.27 | 5000 | 3.3570 | 0.7587 | 0.6728 |
57
+ | 2.4831 | 0.53 | 10000 | 2.6998 | 0.8028 | 0.7596 |
58
+ | 2.1077 | 0.8 | 15000 | 2.4164 | 0.8202 | 0.7862 |
59
+ | 1.5375 | 1.07 | 20000 | 2.2821 | 0.8317 | 0.8012 |
60
+ | 1.4474 | 1.34 | 25000 | 2.2615 | 0.8325 | 0.8043 |
61
+ | 1.3836 | 1.6 | 30000 | 2.1448 | 0.8366 | 0.8133 |
62
+ | 1.2782 | 1.87 | 35000 | 2.1212 | 0.8390 | 0.8135 |
63
+ | 0.983 | 2.14 | 40000 | 2.0840 | 0.8429 | 0.8209 |
64
+ | 0.9416 | 2.41 | 45000 | 2.1779 | 0.8422 | 0.8206 |
65
+ | 0.9138 | 2.67 | 50000 | 2.0942 | 0.8447 | 0.8247 |
66
+ | 0.9093 | 2.94 | 55000 | 2.0603 | 0.8454 | 0.8196 |
67
+ | 0.7465 | 3.21 | 60000 | 2.0972 | 0.8441 | 0.8245 |
68
+ | 0.6996 | 3.47 | 65000 | 2.0355 | 0.8475 | 0.8270 |
69
+ | 0.7454 | 3.74 | 70000 | 1.9610 | 0.8487 | 0.8298 |
70
+ | 0.6906 | 4.01 | 75000 | 2.0084 | 0.8467 | 0.8288 |
71
+ | 0.6203 | 4.28 | 80000 | 1.9601 | 0.8498 | 0.8306 |
72
+ | 0.6039 | 4.54 | 85000 | 1.9766 | 0.8509 | 0.8347 |
73
+ | 0.616 | 4.81 | 90000 | 1.9302 | 0.8518 | 0.8295 |
74
+ | 0.5404 | 5.08 | 95000 | 1.9323 | 0.8512 | 0.8301 |
75
+ | 0.5448 | 5.34 | 100000 | 1.9360 | 0.8533 | 0.8383 |
76
+ | 0.5377 | 5.61 | 105000 | 1.9353 | 0.8511 | 0.8292 |
77
+ | 0.5373 | 5.88 | 110000 | 1.9015 | 0.8506 | 0.8318 |
78
+ | 0.4744 | 6.15 | 115000 | 1.9116 | 0.8527 | 0.8333 |
79
+ | 0.4885 | 6.41 | 120000 | 1.8676 | 0.8543 | 0.8370 |
80
+ | 0.4886 | 6.68 | 125000 | 1.8716 | 0.8546 | 0.8344 |
81
+ | 0.4861 | 6.95 | 130000 | 1.8664 | 0.8535 | 0.8319 |
82
+ | 0.4488 | 7.22 | 135000 | 1.8560 | 0.8547 | 0.8376 |
83
+ | 0.426 | 7.48 | 140000 | 1.8350 | 0.8535 | 0.8334 |
84
+ | 0.4451 | 7.75 | 145000 | 1.8258 | 0.8544 | 0.8333 |
85
+ | 0.4299 | 8.02 | 150000 | 1.8220 | 0.8560 | 0.8370 |
86
+ | 0.4207 | 8.28 | 155000 | 1.8048 | 0.8559 | 0.8373 |
87
+ | 0.4033 | 8.55 | 160000 | 1.8295 | 0.8538 | 0.8367 |
88
+ | 0.4039 | 8.82 | 165000 | 1.7818 | 0.8566 | 0.8391 |
89
+ | 0.3874 | 9.09 | 170000 | 1.7857 | 0.8563 | 0.8391 |
90
+ | 0.3843 | 9.35 | 175000 | 1.7860 | 0.8548 | 0.8374 |
91
+ | 0.3882 | 9.62 | 180000 | 1.8074 | 0.8558 | 0.8374 |
92
+ | 0.3866 | 9.89 | 185000 | 1.7823 | 0.8583 | 0.8404 |
93
+ | 0.36 | 10.15 | 190000 | 1.7294 | 0.8571 | 0.8375 |
94
+ | 0.3592 | 10.42 | 195000 | 1.7363 | 0.8578 | 0.8399 |
95
+ | 0.3628 | 10.69 | 200000 | 1.7460 | 0.8582 | 0.8385 |
96
+ | 0.3579 | 10.96 | 205000 | 1.7431 | 0.8580 | 0.8399 |
97
+ | 0.3448 | 11.22 | 210000 | 1.7398 | 0.8564 | 0.8378 |
98
+ | 0.3512 | 11.49 | 215000 | 1.7193 | 0.8584 | 0.8402 |
99
+ | 0.3367 | 11.76 | 220000 | 1.7197 | 0.8594 | 0.8425 |
100
+ | 0.327 | 12.03 | 225000 | 1.7189 | 0.8576 | 0.8385 |
101
+ | 0.3248 | 12.29 | 230000 | 1.6991 | 0.8602 | 0.8398 |
102
+ | 0.3306 | 12.56 | 235000 | 1.7119 | 0.8577 | 0.8404 |
103
+ | 0.3181 | 12.83 | 240000 | 1.6892 | 0.8606 | 0.8414 |
104
+ | 0.3167 | 13.09 | 245000 | 1.6647 | 0.8590 | 0.8380 |
105
+ | 0.3149 | 13.36 | 250000 | 1.6780 | 0.8590 | 0.8414 |
106
+ | 0.3221 | 13.63 | 255000 | 1.6626 | 0.8601 | 0.8437 |
107
+ | 0.3147 | 13.9 | 260000 | 1.7135 | 0.8595 | 0.8418 |
108
+ | 0.2954 | 14.16 | 265000 | 1.6915 | 0.8581 | 0.8390 |
109
+ | 0.2912 | 14.43 | 270000 | 1.6699 | 0.8582 | 0.8392 |
110
+ | 0.3123 | 14.7 | 275000 | 1.6659 | 0.8589 | 0.8399 |
111
+ | 0.3047 | 14.96 | 280000 | 1.6654 | 0.8610 | 0.8443 |
112
+ | 0.2916 | 15.23 | 285000 | 1.6408 | 0.8600 | 0.8421 |
113
+ | 0.282 | 15.5 | 290000 | 1.6729 | 0.8580 | 0.8405 |
114
+ | 0.2843 | 15.77 | 295000 | 1.6475 | 0.8600 | 0.8416 |
115
+ | 0.2764 | 16.03 | 300000 | 1.6342 | 0.8607 | 0.8426 |
116
+ | 0.2726 | 16.3 | 305000 | 1.6541 | 0.8597 | 0.8425 |
117
+ | 0.2895 | 16.57 | 310000 | 1.6280 | 0.8597 | 0.8413 |
118
+ | 0.2744 | 16.84 | 315000 | 1.6453 | 0.8607 | 0.8422 |
119
+ | 0.2727 | 17.1 | 320000 | 1.6319 | 0.8600 | 0.8432 |
120
+ | 0.2708 | 17.37 | 325000 | 1.6395 | 0.8599 | 0.8427 |
121
+ | 0.271 | 17.64 | 330000 | 1.6232 | 0.8600 | 0.8403 |
122
+ | 0.2695 | 17.9 | 335000 | 1.6294 | 0.8597 | 0.8419 |
123
+ | 0.2698 | 18.17 | 340000 | 1.6158 | 0.8620 | 0.8438 |
124
+ | 0.2582 | 18.44 | 345000 | 1.6214 | 0.8625 | 0.8448 |
125
+ | 0.2614 | 18.71 | 350000 | 1.6112 | 0.8610 | 0.8431 |
126
+ | 0.2583 | 18.97 | 355000 | 1.5978 | 0.8620 | 0.8440 |
127
+ | 0.258 | 19.24 | 360000 | 1.5902 | 0.8623 | 0.8446 |
128
+ | 0.2498 | 19.51 | 365000 | 1.6081 | 0.8611 | 0.8427 |
129
+ | 0.2569 | 19.77 | 370000 | 1.6165 | 0.8604 | 0.8420 |
130
+ | 0.2395 | 20.04 | 375000 | 1.5880 | 0.8614 | 0.8433 |
131
+ | 0.2527 | 20.31 | 380000 | 1.6055 | 0.8599 | 0.8428 |
132
+ | 0.2504 | 20.58 | 385000 | 1.5929 | 0.8614 | 0.8443 |
133
+ | 0.2494 | 20.84 | 390000 | 1.5841 | 0.8624 | 0.8444 |
134
+ | 0.2434 | 21.11 | 395000 | 1.5833 | 0.8614 | 0.8446 |
135
+ | 0.243 | 21.38 | 400000 | 1.5739 | 0.8619 | 0.8438 |
136
+ | 0.2389 | 21.65 | 405000 | 1.5816 | 0.8619 | 0.8438 |
137
+ | 0.2467 | 21.91 | 410000 | 1.5844 | 0.8616 | 0.8439 |
138
+ | 0.2352 | 22.18 | 415000 | 1.5748 | 0.8628 | 0.8446 |
139
+ | 0.2323 | 22.45 | 420000 | 1.5654 | 0.8623 | 0.8427 |
140
+ | 0.2314 | 22.71 | 425000 | 1.5537 | 0.8627 | 0.8449 |
141
+ | 0.238 | 22.98 | 430000 | 1.5613 | 0.8624 | 0.8424 |
142
+ | 0.223 | 23.25 | 435000 | 1.5661 | 0.8626 | 0.8441 |
143
+ | 0.2287 | 23.52 | 440000 | 1.5714 | 0.8627 | 0.8447 |
144
+ | 0.239 | 23.78 | 445000 | 1.5594 | 0.8634 | 0.8455 |
145
+ | 0.2275 | 24.05 | 450000 | 1.5629 | 0.8615 | 0.8436 |
146
+ | 0.2232 | 24.32 | 455000 | 1.5725 | 0.8618 | 0.8451 |
147
+ | 0.2267 | 24.58 | 460000 | 1.5550 | 0.8627 | 0.8455 |
148
+ | 0.2248 | 24.85 | 465000 | 1.5574 | 0.8633 | 0.8455 |
149
+ | 0.2214 | 25.12 | 470000 | 1.5602 | 0.8613 | 0.8432 |
150
+ | 0.2205 | 25.39 | 475000 | 1.5599 | 0.8617 | 0.8432 |
151
+ | 0.2189 | 25.65 | 480000 | 1.5395 | 0.8620 | 0.8452 |
152
+ | 0.2174 | 25.92 | 485000 | 1.5577 | 0.8625 | 0.8445 |
153
+ | 0.2148 | 26.19 | 490000 | 1.5533 | 0.8628 | 0.8457 |
154
+ | 0.2175 | 26.46 | 495000 | 1.5496 | 0.8619 | 0.8443 |
155
+ | 0.2121 | 26.72 | 500000 | 1.5509 | 0.8617 | 0.8443 |
156
+ | 0.2163 | 26.99 | 505000 | 1.5560 | 0.8624 | 0.8453 |
157
+ | 0.211 | 27.26 | 510000 | 1.5491 | 0.8629 | 0.8459 |
158
+ | 0.2142 | 27.52 | 515000 | 1.5576 | 0.8607 | 0.8438 |
159
+ | 0.2084 | 27.79 | 520000 | 1.5522 | 0.8624 | 0.8456 |
160
+ | 0.2119 | 28.06 | 525000 | 1.5429 | 0.8621 | 0.8449 |
161
+ | 0.2008 | 28.33 | 530000 | 1.5452 | 0.8627 | 0.8465 |
162
+ | 0.2084 | 28.59 | 535000 | 1.5458 | 0.8628 | 0.8464 |
163
+ | 0.2086 | 28.86 | 540000 | 1.5454 | 0.8622 | 0.8446 |
164
+ | 0.2102 | 29.13 | 545000 | 1.5487 | 0.8622 | 0.8449 |
165
+ | 0.2118 | 29.39 | 550000 | 1.5448 | 0.8621 | 0.8451 |
166
+ | 0.2049 | 29.66 | 555000 | 1.5411 | 0.8626 | 0.8454 |
167
+ | 0.2026 | 29.93 | 560000 | 1.5394 | 0.8627 | 0.8453 |
168
+
169
+
170
+ ### Framework versions
171
+
172
+ - Transformers 4.33.3
173
+ - Pytorch 2.1.1+cu121
174
+ - Datasets 2.14.5
175
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/mdeberta-v3-base",
3
+ "architectures": [
4
+ "DebertaForSequenceClassificationKD"
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": "4.33.3",
157
+ "type_vocab_size": 0,
158
+ "vocab_size": 251000
159
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33068fbbb01b0aa84b2472b00f118aaad990800e8bd3fb3b5315a290cd240b4
3
+ size 946915690
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fdcd1076d3e0ab36e14063e58207a7a7fe5f7b8fb6c8a1ee41c1dd6cd702d17
3
+ size 4600