haryoaw commited on
Commit
4c735bd
1 Parent(s): 70fdb0a

Initial Commit

Browse files
Files changed (4) hide show
  1. README.md +100 -0
  2. config.json +152 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: facebook/xlm-v-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - massive
8
+ metrics:
9
+ - accuracy
10
+ - f1
11
+ model-index:
12
+ - name: scenario-TCR-XLMV_data-AmazonScience_massive_all_1_1_beta2
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: 0.8495213591130955
27
+ - name: F1
28
+ type: f1
29
+ value: 0.8257523979629272
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-XLMV_data-AmazonScience_massive_all_1_1_beta2
36
+
37
+ This model is a fine-tuned version of [facebook/xlm-v-base](https://huggingface.co/facebook/xlm-v-base) on the massive dataset.
38
+ It achieves the following results on the evaluation set:
39
+ - Loss: 0.8678
40
+ - Accuracy: 0.8495
41
+ - F1: 0.8258
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: 67
64
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
+ - lr_scheduler_type: linear
66
+ - num_epochs: 500
67
+
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
+ |:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|
72
+ | 0.6252 | 0.27 | 5000 | 0.7387 | 0.8183 | 0.7743 |
73
+ | 0.4497 | 0.53 | 10000 | 0.6721 | 0.8363 | 0.7908 |
74
+ | 0.3806 | 0.8 | 15000 | 0.6702 | 0.8451 | 0.8090 |
75
+ | 0.303 | 1.07 | 20000 | 0.7162 | 0.8457 | 0.8130 |
76
+ | 0.2732 | 1.34 | 25000 | 0.7250 | 0.8475 | 0.8178 |
77
+ | 0.2574 | 1.6 | 30000 | 0.7626 | 0.8449 | 0.8188 |
78
+ | 0.2565 | 1.87 | 35000 | 0.7255 | 0.8506 | 0.8251 |
79
+ | 0.2074 | 2.14 | 40000 | 0.7439 | 0.8524 | 0.8268 |
80
+ | 0.2139 | 2.41 | 45000 | 0.8088 | 0.8478 | 0.8233 |
81
+ | 0.2007 | 2.67 | 50000 | 0.7556 | 0.8476 | 0.8223 |
82
+ | 0.2012 | 2.94 | 55000 | 0.7599 | 0.8505 | 0.8250 |
83
+ | 0.1698 | 3.21 | 60000 | 0.8283 | 0.8481 | 0.8255 |
84
+ | 0.1728 | 3.47 | 65000 | 0.7996 | 0.8521 | 0.8320 |
85
+ | 0.1711 | 3.74 | 70000 | 0.7974 | 0.8520 | 0.8292 |
86
+ | 0.1623 | 4.01 | 75000 | 0.8819 | 0.8485 | 0.8223 |
87
+ | 0.1502 | 4.28 | 80000 | 0.8330 | 0.8534 | 0.8320 |
88
+ | 0.1605 | 4.54 | 85000 | 0.8250 | 0.8499 | 0.8264 |
89
+ | 0.1659 | 4.81 | 90000 | 0.8318 | 0.8493 | 0.8237 |
90
+ | 0.1241 | 5.08 | 95000 | 0.9368 | 0.8518 | 0.8191 |
91
+ | 0.1361 | 5.34 | 100000 | 0.9396 | 0.8510 | 0.8237 |
92
+ | 0.1481 | 5.61 | 105000 | 0.8678 | 0.8495 | 0.8258 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.33.3
98
+ - Pytorch 2.1.1+cu121
99
+ - Datasets 2.14.5
100
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/xlm-v-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
+ "pad_token_id": 1,
145
+ "position_embedding_type": "absolute",
146
+ "problem_type": "single_label_classification",
147
+ "torch_dtype": "float32",
148
+ "transformers_version": "4.33.3",
149
+ "type_vocab_size": 1,
150
+ "use_cache": true,
151
+ "vocab_size": 901629
152
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:016a70b901251380108687a1c773d0d16d1affc3546fb47404dc3ea75d728a91
3
+ size 3114226670
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7540a02cc64900e7cfd91005665cbfd14c741c6fd46b1b70ff9e73d166eae9a4
3
+ size 4600