Hugging Face's logo

CodeNinja1126
/
test-model

Text Classification
Transformers
PyTorch
JAX
bert
Model card Files Community
1
CodeNinja1126 commited on
Commit
bedd36f
·
1 Parent(s): 8de1739

test uploading

Browse files
Files changed (6) hide show
  1. config.json +117 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. scheduler.pt +3 -0
  5. trainer_state.json +136 -0
  6. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "directionality": "bidi",
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31",
44
+ "32": "LABEL_32",
45
+ "33": "LABEL_33",
46
+ "34": "LABEL_34",
47
+ "35": "LABEL_35",
48
+ "36": "LABEL_36",
49
+ "37": "LABEL_37",
50
+ "38": "LABEL_38",
51
+ "39": "LABEL_39",
52
+ "40": "LABEL_40",
53
+ "41": "LABEL_41"
54
+ },
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 3072,
57
+ "label2id": {
58
+ "LABEL_0": 0,
59
+ "LABEL_1": 1,
60
+ "LABEL_10": 10,
61
+ "LABEL_11": 11,
62
+ "LABEL_12": 12,
63
+ "LABEL_13": 13,
64
+ "LABEL_14": 14,
65
+ "LABEL_15": 15,
66
+ "LABEL_16": 16,
67
+ "LABEL_17": 17,
68
+ "LABEL_18": 18,
69
+ "LABEL_19": 19,
70
+ "LABEL_2": 2,
71
+ "LABEL_20": 20,
72
+ "LABEL_21": 21,
73
+ "LABEL_22": 22,
74
+ "LABEL_23": 23,
75
+ "LABEL_24": 24,
76
+ "LABEL_25": 25,
77
+ "LABEL_26": 26,
78
+ "LABEL_27": 27,
79
+ "LABEL_28": 28,
80
+ "LABEL_29": 29,
81
+ "LABEL_3": 3,
82
+ "LABEL_30": 30,
83
+ "LABEL_31": 31,
84
+ "LABEL_32": 32,
85
+ "LABEL_33": 33,
86
+ "LABEL_34": 34,
87
+ "LABEL_35": 35,
88
+ "LABEL_36": 36,
89
+ "LABEL_37": 37,
90
+ "LABEL_38": 38,
91
+ "LABEL_39": 39,
92
+ "LABEL_4": 4,
93
+ "LABEL_40": 40,
94
+ "LABEL_41": 41,
95
+ "LABEL_5": 5,
96
+ "LABEL_6": 6,
97
+ "LABEL_7": 7,
98
+ "LABEL_8": 8,
99
+ "LABEL_9": 9
100
+ },
101
+ "layer_norm_eps": 1e-12,
102
+ "max_position_embeddings": 512,
103
+ "model_type": "bert",
104
+ "num_attention_heads": 12,
105
+ "num_hidden_layers": 12,
106
+ "pad_token_id": 0,
107
+ "pooler_fc_size": 768,
108
+ "pooler_num_attention_heads": 12,
109
+ "pooler_num_fc_layers": 3,
110
+ "pooler_size_per_head": 128,
111
+ "pooler_type": "first_token_transform",
112
+ "position_embedding_type": "absolute",
113
+ "transformers_version": "4.5.1",
114
+ "type_vocab_size": 2,
115
+ "use_cache": true,
116
+ "vocab_size": 119547
117
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd383ef3a6ef0fd2c3465b736b4ba1b9b3def4dcb640173dd66fbe8f986c873
3
+ size 1423211985
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:394cbefa666a7d0ebf447165a0e4236e0b8c59f1ca222f998a1effe42426f42a
3
+ size 711632265
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a864503c515100ad6e1db9fd2edf5f6ed5585e7801426a37353d2ebcdc7ba897
3
+ size 559
trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.552397868561279,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.18,
12
+ "learning_rate": 1e-05,
13
+ "loss": 2.61,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.36,
18
+ "learning_rate": 2e-05,
19
+ "loss": 2.239,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.53,
24
+ "learning_rate": 3e-05,
25
+ "loss": 2.1544,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 0.71,
30
+ "learning_rate": 4e-05,
31
+ "loss": 2.1588,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 0.89,
36
+ "learning_rate": 5e-05,
37
+ "loss": 2.1616,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 1.07,
42
+ "learning_rate": 4.714611872146119e-05,
43
+ "loss": 2.1307,
44
+ "step": 600
45
+ },
46
+ {
47
+ "epoch": 1.24,
48
+ "learning_rate": 4.4292237442922375e-05,
49
+ "loss": 2.099,
50
+ "step": 700
51
+ },
52
+ {
53
+ "epoch": 1.42,
54
+ "learning_rate": 4.143835616438356e-05,
55
+ "loss": 2.0643,
56
+ "step": 800
57
+ },
58
+ {
59
+ "epoch": 1.6,
60
+ "learning_rate": 3.8584474885844754e-05,
61
+ "loss": 1.9641,
62
+ "step": 900
63
+ },
64
+ {
65
+ "epoch": 1.78,
66
+ "learning_rate": 3.573059360730594e-05,
67
+ "loss": 2.02,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 1.95,
72
+ "learning_rate": 3.287671232876712e-05,
73
+ "loss": 1.9874,
74
+ "step": 1100
75
+ },
76
+ {
77
+ "epoch": 2.13,
78
+ "learning_rate": 3.0022831050228313e-05,
79
+ "loss": 1.9012,
80
+ "step": 1200
81
+ },
82
+ {
83
+ "epoch": 2.31,
84
+ "learning_rate": 2.71689497716895e-05,
85
+ "loss": 1.8334,
86
+ "step": 1300
87
+ },
88
+ {
89
+ "epoch": 2.49,
90
+ "learning_rate": 2.4315068493150686e-05,
91
+ "loss": 1.8206,
92
+ "step": 1400
93
+ },
94
+ {
95
+ "epoch": 2.66,
96
+ "learning_rate": 2.1461187214611872e-05,
97
+ "loss": 1.8217,
98
+ "step": 1500
99
+ },
100
+ {
101
+ "epoch": 2.84,
102
+ "learning_rate": 1.8607305936073062e-05,
103
+ "loss": 1.7761,
104
+ "step": 1600
105
+ },
106
+ {
107
+ "epoch": 3.02,
108
+ "learning_rate": 1.5753424657534248e-05,
109
+ "loss": 1.7351,
110
+ "step": 1700
111
+ },
112
+ {
113
+ "epoch": 3.2,
114
+ "learning_rate": 1.2899543378995434e-05,
115
+ "loss": 1.6358,
116
+ "step": 1800
117
+ },
118
+ {
119
+ "epoch": 3.37,
120
+ "learning_rate": 1.004566210045662e-05,
121
+ "loss": 1.5685,
122
+ "step": 1900
123
+ },
124
+ {
125
+ "epoch": 3.55,
126
+ "learning_rate": 7.191780821917809e-06,
127
+ "loss": 1.6077,
128
+ "step": 2000
129
+ }
130
+ ],
131
+ "max_steps": 2252,
132
+ "num_train_epochs": 4,
133
+ "total_flos": 3412844614972800.0,
134
+ "trial_name": null,
135
+ "trial_params": null
136
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0dd4ac53c9fbcc673a15a1d678b47fea175ddb9236ae3c5708465393da2332d
3
+ size 2287