Hugging Face's logo

haryoaw
/
scenario-TCR-xlmv-en-massive

Text Classification
Transformers
PyTorch
xlm-roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
haryoaw commited on
Commit
10d655b
•
1 Parent(s): 67eb182

Initial Commit

Browse files
Files changed (4) hide show
  1. README.md +187 -0
  2. config.json +153 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,187 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: xlm-roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - massive
8
+ metrics:
9
+ - accuracy
10
+ - f1
11
+ model-index:
12
+ - name: scenario-TCR_data-en-massive_all_1_1
13
+ results:
14
+ - task:
15
+ name: Text Classification
16
+ type: text-classification
17
+ dataset:
18
+ name: massive
19
+ type: massive
20
+ config: all_1.1
21
+ split: validation
22
+ args: all_1.1
23
+ metrics:
24
+ - name: Accuracy
25
+ type: accuracy
26
+ value: 0.6663001649257834
27
+ - name: F1
28
+ type: f1
29
+ value: 0.6006849005734807
30
+ ---
31
+
32
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
33
+ should probably proofread and complete it, then remove this comment. -->
34
+
35
+ # scenario-TCR_data-en-massive_all_1_1
36
+
37
+ This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the massive dataset.
38
+ It achieves the following results on the evaluation set:
39
+ - Loss: 2.7850
40
+ - Accuracy: 0.6663
41
+ - F1: 0.6007
42
+
43
+ ## Model description
44
+
45
+ More information needed
46
+
47
+ ## Intended uses & limitations
48
+
49
+ More information needed
50
+
51
+ ## Training and evaluation data
52
+
53
+ More information needed
54
+
55
+ ## Training procedure
56
+
57
+ ### Training hyperparameters
58
+
59
+ The following hyperparameters were used during training:
60
+ - learning_rate: 5e-05
61
+ - train_batch_size: 32
62
+ - eval_batch_size: 32
63
+ - seed: 42
64
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
+ - lr_scheduler_type: linear
66
+ - num_epochs: 30
67
+
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
72
+ | No log | 0.28 | 100 | 2.8668 | 0.3066 | 0.1117 |
73
+ | No log | 0.56 | 200 | 2.0971 | 0.4939 | 0.2673 |
74
+ | No log | 0.83 | 300 | 1.7751 | 0.5692 | 0.3808 |
75
+ | No log | 1.11 | 400 | 1.5796 | 0.6089 | 0.4444 |
76
+ | 1.8216 | 1.39 | 500 | 1.5696 | 0.6234 | 0.4919 |
77
+ | 1.8216 | 1.67 | 600 | 1.6751 | 0.6098 | 0.5122 |
78
+ | 1.8216 | 1.94 | 700 | 1.4933 | 0.6292 | 0.5400 |
79
+ | 1.8216 | 2.22 | 800 | 1.4954 | 0.6431 | 0.5461 |
80
+ | 1.8216 | 2.5 | 900 | 1.4810 | 0.6465 | 0.5400 |
81
+ | 0.5885 | 2.78 | 1000 | 1.7160 | 0.6084 | 0.5306 |
82
+ | 0.5885 | 3.06 | 1100 | 1.4351 | 0.6632 | 0.5878 |
83
+ | 0.5885 | 3.33 | 1200 | 1.5652 | 0.6415 | 0.5632 |
84
+ | 0.5885 | 3.61 | 1300 | 1.5121 | 0.6593 | 0.5666 |
85
+ | 0.5885 | 3.89 | 1400 | 1.5149 | 0.6595 | 0.5815 |
86
+ | 0.3358 | 4.17 | 1500 | 1.5927 | 0.6627 | 0.5909 |
87
+ | 0.3358 | 4.44 | 1600 | 1.5611 | 0.6656 | 0.5775 |
88
+ | 0.3358 | 4.72 | 1700 | 1.7512 | 0.6357 | 0.5696 |
89
+ | 0.3358 | 5.0 | 1800 | 1.5428 | 0.6668 | 0.5968 |
90
+ | 0.3358 | 5.28 | 1900 | 1.6718 | 0.6638 | 0.5925 |
91
+ | 0.2166 | 5.56 | 2000 | 1.7788 | 0.6384 | 0.5716 |
92
+ | 0.2166 | 5.83 | 2100 | 1.6970 | 0.6578 | 0.5847 |
93
+ | 0.2166 | 6.11 | 2200 | 1.7591 | 0.6460 | 0.5891 |
94
+ | 0.2166 | 6.39 | 2300 | 1.7743 | 0.6576 | 0.5895 |
95
+ | 0.2166 | 6.67 | 2400 | 1.9936 | 0.6358 | 0.5722 |
96
+ | 0.1521 | 6.94 | 2500 | 1.9608 | 0.6341 | 0.5720 |
97
+ | 0.1521 | 7.22 | 2600 | 1.8215 | 0.6567 | 0.5845 |
98
+ | 0.1521 | 7.5 | 2700 | 2.2601 | 0.6184 | 0.5620 |
99
+ | 0.1521 | 7.78 | 2800 | 2.0000 | 0.6492 | 0.5844 |
100
+ | 0.1521 | 8.06 | 2900 | 1.8825 | 0.6689 | 0.5884 |
101
+ | 0.0972 | 8.33 | 3000 | 1.9969 | 0.6499 | 0.5754 |
102
+ | 0.0972 | 8.61 | 3100 | 2.0284 | 0.6475 | 0.5888 |
103
+ | 0.0972 | 8.89 | 3200 | 2.0733 | 0.6445 | 0.5778 |
104
+ | 0.0972 | 9.17 | 3300 | 2.1821 | 0.6401 | 0.5766 |
105
+ | 0.0972 | 9.44 | 3400 | 2.1044 | 0.6540 | 0.5882 |
106
+ | 0.0821 | 9.72 | 3500 | 2.2485 | 0.6388 | 0.5783 |
107
+ | 0.0821 | 10.0 | 3600 | 2.1973 | 0.6474 | 0.5805 |
108
+ | 0.0821 | 10.28 | 3700 | 2.2481 | 0.6441 | 0.5746 |
109
+ | 0.0821 | 10.56 | 3800 | 2.3463 | 0.6307 | 0.5712 |
110
+ | 0.0821 | 10.83 | 3900 | 2.1873 | 0.6514 | 0.5838 |
111
+ | 0.0599 | 11.11 | 4000 | 2.2346 | 0.6465 | 0.5769 |
112
+ | 0.0599 | 11.39 | 4100 | 2.1812 | 0.6539 | 0.5863 |
113
+ | 0.0599 | 11.67 | 4200 | 2.2318 | 0.6528 | 0.5897 |
114
+ | 0.0599 | 11.94 | 4300 | 2.2913 | 0.6413 | 0.5821 |
115
+ | 0.0599 | 12.22 | 4400 | 2.1780 | 0.6571 | 0.5899 |
116
+ | 0.0465 | 12.5 | 4500 | 2.2604 | 0.6611 | 0.5965 |
117
+ | 0.0465 | 12.78 | 4600 | 2.1850 | 0.6650 | 0.5997 |
118
+ | 0.0465 | 13.06 | 4700 | 2.2568 | 0.6617 | 0.5962 |
119
+ | 0.0465 | 13.33 | 4800 | 2.2311 | 0.6648 | 0.5906 |
120
+ | 0.0465 | 13.61 | 4900 | 2.3589 | 0.6568 | 0.5949 |
121
+ | 0.0269 | 13.89 | 5000 | 2.5143 | 0.6506 | 0.5905 |
122
+ | 0.0269 | 14.17 | 5100 | 2.5963 | 0.6421 | 0.5841 |
123
+ | 0.0269 | 14.44 | 5200 | 2.3170 | 0.6703 | 0.6001 |
124
+ | 0.0269 | 14.72 | 5300 | 2.3151 | 0.6662 | 0.5984 |
125
+ | 0.0269 | 15.0 | 5400 | 2.7048 | 0.6390 | 0.5751 |
126
+ | 0.0228 | 15.28 | 5500 | 2.3686 | 0.6626 | 0.5990 |
127
+ | 0.0228 | 15.56 | 5600 | 2.5169 | 0.6536 | 0.5968 |
128
+ | 0.0228 | 15.83 | 5700 | 2.5162 | 0.6500 | 0.5911 |
129
+ | 0.0228 | 16.11 | 5800 | 2.5161 | 0.6531 | 0.5955 |
130
+ | 0.0228 | 16.39 | 5900 | 2.6153 | 0.6473 | 0.5926 |
131
+ | 0.0183 | 16.67 | 6000 | 2.5704 | 0.6455 | 0.5847 |
132
+ | 0.0183 | 16.94 | 6100 | 2.8607 | 0.6329 | 0.5718 |
133
+ | 0.0183 | 17.22 | 6200 | 2.6057 | 0.6440 | 0.5871 |
134
+ | 0.0183 | 17.5 | 6300 | 2.5630 | 0.6575 | 0.5966 |
135
+ | 0.0183 | 17.78 | 6400 | 2.6760 | 0.6554 | 0.5934 |
136
+ | 0.0127 | 18.06 | 6500 | 2.7133 | 0.6532 | 0.5947 |
137
+ | 0.0127 | 18.33 | 6600 | 2.7012 | 0.6522 | 0.5934 |
138
+ | 0.0127 | 18.61 | 6700 | 2.6611 | 0.6513 | 0.5855 |
139
+ | 0.0127 | 18.89 | 6800 | 2.6626 | 0.6484 | 0.5852 |
140
+ | 0.0127 | 19.17 | 6900 | 2.7077 | 0.6482 | 0.5878 |
141
+ | 0.0127 | 19.44 | 7000 | 2.6134 | 0.6614 | 0.5913 |
142
+ | 0.0127 | 19.72 | 7100 | 2.6991 | 0.6563 | 0.5903 |
143
+ | 0.0127 | 20.0 | 7200 | 2.7596 | 0.6500 | 0.5818 |
144
+ | 0.0127 | 20.28 | 7300 | 2.6609 | 0.6621 | 0.5922 |
145
+ | 0.0127 | 20.56 | 7400 | 2.6349 | 0.6644 | 0.5952 |
146
+ | 0.0094 | 20.83 | 7500 | 2.5675 | 0.6701 | 0.5977 |
147
+ | 0.0094 | 21.11 | 7600 | 2.6176 | 0.6687 | 0.5987 |
148
+ | 0.0094 | 21.39 | 7700 | 2.8201 | 0.6551 | 0.5887 |
149
+ | 0.0094 | 21.67 | 7800 | 2.7250 | 0.6604 | 0.5922 |
150
+ | 0.0094 | 21.94 | 7900 | 2.7049 | 0.6587 | 0.5939 |
151
+ | 0.0061 | 22.22 | 8000 | 2.6681 | 0.6596 | 0.5971 |
152
+ | 0.0061 | 22.5 | 8100 | 2.6907 | 0.6608 | 0.5932 |
153
+ | 0.0061 | 22.78 | 8200 | 2.7454 | 0.6574 | 0.5912 |
154
+ | 0.0061 | 23.06 | 8300 | 2.7095 | 0.6597 | 0.5952 |
155
+ | 0.0061 | 23.33 | 8400 | 2.6966 | 0.6606 | 0.5958 |
156
+ | 0.0028 | 23.61 | 8500 | 2.7210 | 0.6637 | 0.5996 |
157
+ | 0.0028 | 23.89 | 8600 | 2.6735 | 0.6631 | 0.5949 |
158
+ | 0.0028 | 24.17 | 8700 | 2.6844 | 0.6659 | 0.5969 |
159
+ | 0.0028 | 24.44 | 8800 | 2.6903 | 0.6616 | 0.5889 |
160
+ | 0.0028 | 24.72 | 8900 | 3.0441 | 0.6395 | 0.5798 |
161
+ | 0.0048 | 25.0 | 9000 | 2.8181 | 0.6588 | 0.5940 |
162
+ | 0.0048 | 25.28 | 9100 | 2.7249 | 0.6673 | 0.5971 |
163
+ | 0.0048 | 25.56 | 9200 | 2.7154 | 0.6674 | 0.5962 |
164
+ | 0.0048 | 25.83 | 9300 | 2.6837 | 0.6694 | 0.5972 |
165
+ | 0.0048 | 26.11 | 9400 | 2.7153 | 0.6669 | 0.5973 |
166
+ | 0.0027 | 26.39 | 9500 | 2.7366 | 0.6664 | 0.5987 |
167
+ | 0.0027 | 26.67 | 9600 | 2.7943 | 0.6636 | 0.5959 |
168
+ | 0.0027 | 26.94 | 9700 | 2.7079 | 0.6706 | 0.6002 |
169
+ | 0.0027 | 27.22 | 9800 | 2.7941 | 0.6651 | 0.5993 |
170
+ | 0.0027 | 27.5 | 9900 | 2.8876 | 0.6575 | 0.5953 |
171
+ | 0.0024 | 27.78 | 10000 | 2.8470 | 0.6603 | 0.5958 |
172
+ | 0.0024 | 28.06 | 10100 | 2.8501 | 0.6606 | 0.5955 |
173
+ | 0.0024 | 28.33 | 10200 | 2.8663 | 0.6606 | 0.5953 |
174
+ | 0.0024 | 28.61 | 10300 | 2.8620 | 0.6597 | 0.5948 |
175
+ | 0.0024 | 28.89 | 10400 | 2.8211 | 0.6629 | 0.5977 |
176
+ | 0.0019 | 29.17 | 10500 | 2.7943 | 0.6653 | 0.5999 |
177
+ | 0.0019 | 29.44 | 10600 | 2.7875 | 0.6658 | 0.6000 |
178
+ | 0.0019 | 29.72 | 10700 | 2.7908 | 0.6657 | 0.6003 |
179
+ | 0.0019 | 30.0 | 10800 | 2.7850 | 0.6663 | 0.6007 |
180
+
181
+
182
+ ### Framework versions
183
+
184
+ - Transformers 4.33.3
185
+ - Pytorch 2.1.1+cu121
186
+ - Datasets 2.14.5
187
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20",
35
+ "21": "LABEL_21",
36
+ "22": "LABEL_22",
37
+ "23": "LABEL_23",
38
+ "24": "LABEL_24",
39
+ "25": "LABEL_25",
40
+ "26": "LABEL_26",
41
+ "27": "LABEL_27",
42
+ "28": "LABEL_28",
43
+ "29": "LABEL_29",
44
+ "30": "LABEL_30",
45
+ "31": "LABEL_31",
46
+ "32": "LABEL_32",
47
+ "33": "LABEL_33",
48
+ "34": "LABEL_34",
49
+ "35": "LABEL_35",
50
+ "36": "LABEL_36",
51
+ "37": "LABEL_37",
52
+ "38": "LABEL_38",
53
+ "39": "LABEL_39",
54
+ "40": "LABEL_40",
55
+ "41": "LABEL_41",
56
+ "42": "LABEL_42",
57
+ "43": "LABEL_43",
58
+ "44": "LABEL_44",
59
+ "45": "LABEL_45",
60
+ "46": "LABEL_46",
61
+ "47": "LABEL_47",
62
+ "48": "LABEL_48",
63
+ "49": "LABEL_49",
64
+ "50": "LABEL_50",
65
+ "51": "LABEL_51",
66
+ "52": "LABEL_52",
67
+ "53": "LABEL_53",
68
+ "54": "LABEL_54",
69
+ "55": "LABEL_55",
70
+ "56": "LABEL_56",
71
+ "57": "LABEL_57",
72
+ "58": "LABEL_58",
73
+ "59": "LABEL_59"
74
+ },
75
+ "initializer_range": 0.02,
76
+ "intermediate_size": 3072,
77
+ "label2id": {
78
+ "LABEL_0": 0,
79
+ "LABEL_1": 1,
80
+ "LABEL_10": 10,
81
+ "LABEL_11": 11,
82
+ "LABEL_12": 12,
83
+ "LABEL_13": 13,
84
+ "LABEL_14": 14,
85
+ "LABEL_15": 15,
86
+ "LABEL_16": 16,
87
+ "LABEL_17": 17,
88
+ "LABEL_18": 18,
89
+ "LABEL_19": 19,
90
+ "LABEL_2": 2,
91
+ "LABEL_20": 20,
92
+ "LABEL_21": 21,
93
+ "LABEL_22": 22,
94
+ "LABEL_23": 23,
95
+ "LABEL_24": 24,
96
+ "LABEL_25": 25,
97
+ "LABEL_26": 26,
98
+ "LABEL_27": 27,
99
+ "LABEL_28": 28,
100
+ "LABEL_29": 29,
101
+ "LABEL_3": 3,
102
+ "LABEL_30": 30,
103
+ "LABEL_31": 31,
104
+ "LABEL_32": 32,
105
+ "LABEL_33": 33,
106
+ "LABEL_34": 34,
107
+ "LABEL_35": 35,
108
+ "LABEL_36": 36,
109
+ "LABEL_37": 37,
110
+ "LABEL_38": 38,
111
+ "LABEL_39": 39,
112
+ "LABEL_4": 4,
113
+ "LABEL_40": 40,
114
+ "LABEL_41": 41,
115
+ "LABEL_42": 42,
116
+ "LABEL_43": 43,
117
+ "LABEL_44": 44,
118
+ "LABEL_45": 45,
119
+ "LABEL_46": 46,
120
+ "LABEL_47": 47,
121
+ "LABEL_48": 48,
122
+ "LABEL_49": 49,
123
+ "LABEL_5": 5,
124
+ "LABEL_50": 50,
125
+ "LABEL_51": 51,
126
+ "LABEL_52": 52,
127
+ "LABEL_53": 53,
128
+ "LABEL_54": 54,
129
+ "LABEL_55": 55,
130
+ "LABEL_56": 56,
131
+ "LABEL_57": 57,
132
+ "LABEL_58": 58,
133
+ "LABEL_59": 59,
134
+ "LABEL_6": 6,
135
+ "LABEL_7": 7,
136
+ "LABEL_8": 8,
137
+ "LABEL_9": 9
138
+ },
139
+ "layer_norm_eps": 1e-05,
140
+ "max_position_embeddings": 514,
141
+ "model_type": "xlm-roberta",
142
+ "num_attention_heads": 12,
143
+ "num_hidden_layers": 12,
144
+ "output_past": true,
145
+ "pad_token_id": 1,
146
+ "position_embedding_type": "absolute",
147
+ "problem_type": "single_label_classification",
148
+ "torch_dtype": "float32",
149
+ "transformers_version": "4.33.3",
150
+ "type_vocab_size": 1,
151
+ "use_cache": true,
152
+ "vocab_size": 250002
153
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2c1ef2db7c607709b2a068979655517f4c9366bbe4972fcaeafd212dfedae37
3
+ size 1112428526
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7356b2f36aeac07891deaed157cfb990fa0c3fb55b8aeb9293df9b12f2872374
3
+ size 4600