o2poi commited on
Commit
22cfb69
1 Parent(s): e02916c

upload trained model

Browse files
all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9105504751205444,
4
+ "eval_loss": 0.5452536344528198,
5
+ "eval_runtime": 1.4363,
6
+ "eval_samples": 872,
7
+ "eval_samples_per_second": 607.136,
8
+ "train_runtime": 1978.9597,
9
+ "train_samples": 134698,
10
+ "train_samples_per_second": 5.318
11
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "inner_group_num": 1,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "albert",
22
+ "net_structure_type": 0,
23
+ "num_attention_heads": 12,
24
+ "num_hidden_groups": 1,
25
+ "num_hidden_layers": 12,
26
+ "num_memory_blocks": 0,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "transformers_version": "4.6.1",
31
+ "type_vocab_size": 2,
32
+ "vocab_size": 30000
33
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9105504751205444,
4
+ "eval_loss": 0.5452536344528198,
5
+ "eval_runtime": 1.4363,
6
+ "eval_samples": 872,
7
+ "eval_samples_per_second": 607.136
8
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c9d67fd1e48ef91403bbe74676be7a03207222e7474fe3c3cb84752026b8b4c
3
+ size 46756715
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
3
+ size 760289
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-base-v2"}
train_results.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_runtime": 1978.9597,
4
+ "train_samples": 134698,
5
+ "train_samples_per_second": 5.318
6
+ }
trainer_state.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 10525,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.24,
12
+ "learning_rate": 1.9049881235154395e-05,
13
+ "loss": 0.3611,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.48,
18
+ "learning_rate": 1.809976247030879e-05,
19
+ "loss": 0.2398,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.71,
24
+ "learning_rate": 1.7149643705463184e-05,
25
+ "loss": 0.2149,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.95,
30
+ "learning_rate": 1.6199524940617578e-05,
31
+ "loss": 0.1939,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.19,
36
+ "learning_rate": 1.5249406175771972e-05,
37
+ "loss": 0.1514,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.43,
42
+ "learning_rate": 1.4299287410926367e-05,
43
+ "loss": 0.139,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.66,
48
+ "learning_rate": 1.3349168646080762e-05,
49
+ "loss": 0.136,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.9,
54
+ "learning_rate": 1.2399049881235155e-05,
55
+ "loss": 0.1295,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 2.14,
60
+ "learning_rate": 1.144893111638955e-05,
61
+ "loss": 0.1054,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 2.38,
66
+ "learning_rate": 1.0498812351543943e-05,
67
+ "loss": 0.0848,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 2.61,
72
+ "learning_rate": 9.548693586698338e-06,
73
+ "loss": 0.0881,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 2.85,
78
+ "learning_rate": 8.598574821852733e-06,
79
+ "loss": 0.087,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 3.09,
84
+ "learning_rate": 7.648456057007126e-06,
85
+ "loss": 0.0715,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 3.33,
90
+ "learning_rate": 6.698337292161521e-06,
91
+ "loss": 0.0534,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 3.56,
96
+ "learning_rate": 5.748218527315916e-06,
97
+ "loss": 0.0513,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 3.8,
102
+ "learning_rate": 4.798099762470309e-06,
103
+ "loss": 0.0528,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 4.04,
108
+ "learning_rate": 3.8479809976247036e-06,
109
+ "loss": 0.0494,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 4.28,
114
+ "learning_rate": 2.897862232779098e-06,
115
+ "loss": 0.0283,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 4.51,
120
+ "learning_rate": 1.947743467933492e-06,
121
+ "loss": 0.0324,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 4.75,
126
+ "learning_rate": 9.976247030878861e-07,
127
+ "loss": 0.0275,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 4.99,
132
+ "learning_rate": 4.750593824228029e-08,
133
+ "loss": 0.0308,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 5.0,
138
+ "step": 10525,
139
+ "total_flos": 14161246092288.0,
140
+ "train_runtime": 1978.9597,
141
+ "train_samples_per_second": 5.318
142
+ }
143
+ ],
144
+ "max_steps": 10525,
145
+ "num_train_epochs": 5,
146
+ "total_flos": 14161246092288.0,
147
+ "trial_name": null,
148
+ "trial_params": null
149
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e8656ad9924b92bad18ebc35230ffc7a62547640414e60761fab0096d840c39
3
+ size 2415