batterydata commited on
Commit
a4371bf
1 Parent(s): 984cbea

best model for qa

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/projects/SolarWindowsADSP/shu/models/revision/bert/batteryonlybert-uncased2/",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.17.0.dev0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffd39560632aea44c3c3958dba1a016235eb799a225db8bf84d31d8111e45b7e
3
+ size 871270381
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f50c8763ac4d852593567a777d4d275a82d6f48d4c4da368d3329f759b7c86a
3
+ size 435661303
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2ac74408151aae454944403e85e323191707cba3c973506697924347dd106d
3
+ size 14657
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5e2e14ed0a6f36e1cd2882c8c76267c146d1a5c7e2da4c357db0f25cdc4b8e1
3
+ size 14657
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0e095a80323336245784a8a9964e70a2250e0fbe078ec500ca9bd51a2acbc2a
3
+ size 14657
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b3860b7ab7b6e0a0d6bd7e577b49ec3877d0def7a3653adf9c26c194c82f3c4
3
+ size 14657
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13ef451c8a493ec47cfcab59e04783f9d7d96ab007d7c8728074adc7cfed45f
3
+ size 14657
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b77a82c8e91a0293d06380dfed10167112b2b081a0211b0ed5b7a9c7286bbf8
3
+ size 14657
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c2cca5f111fdcf2a7bf145262686f713f155774c29721d491c288b39b605b7f
3
+ size 14657
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d65818774c138b83f0817d05217e48490d6041d5c2bf6028235cd3623a223549
3
+ size 14657
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f076bbb0231bad2239d9fa1cae5e4c934711e2acf7eaa1c000ca7dcd553ea12
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
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, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_type": "bert", "special_tokens_map_file": null, "name_or_path": "/projects/SolarWindowsADSP/shu/models/revision/bert/batteryonlybert-uncased2/", "tokenizer_class": "BertTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 11148,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.09,
12
+ "learning_rate": 1.9551489056332974e-05,
13
+ "loss": 2.3375,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 1.910297811266595e-05,
19
+ "loss": 1.5119,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.27,
24
+ "learning_rate": 1.8654467168998925e-05,
25
+ "loss": 1.3999,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.36,
30
+ "learning_rate": 1.82059562253319e-05,
31
+ "loss": 1.2924,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.45,
36
+ "learning_rate": 1.7757445281664872e-05,
37
+ "loss": 1.2685,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.54,
42
+ "learning_rate": 1.7308934337997848e-05,
43
+ "loss": 1.2121,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.63,
48
+ "learning_rate": 1.6860423394330823e-05,
49
+ "loss": 1.2076,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.72,
54
+ "learning_rate": 1.64119124506638e-05,
55
+ "loss": 1.1561,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.81,
60
+ "learning_rate": 1.596340150699677e-05,
61
+ "loss": 1.1587,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.9,
66
+ "learning_rate": 1.5514890563329747e-05,
67
+ "loss": 1.0862,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.99,
72
+ "learning_rate": 1.506637961966272e-05,
73
+ "loss": 1.1046,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.0,
78
+ "eval_exact_match": 77.8713339640492,
79
+ "eval_f1": 86.11994528825018,
80
+ "step": 5574
81
+ },
82
+ {
83
+ "epoch": 1.08,
84
+ "learning_rate": 1.4617868675995694e-05,
85
+ "loss": 0.8899,
86
+ "step": 6000
87
+ },
88
+ {
89
+ "epoch": 1.17,
90
+ "learning_rate": 1.416935773232867e-05,
91
+ "loss": 0.8613,
92
+ "step": 6500
93
+ },
94
+ {
95
+ "epoch": 1.26,
96
+ "learning_rate": 1.3720846788661644e-05,
97
+ "loss": 0.849,
98
+ "step": 7000
99
+ },
100
+ {
101
+ "epoch": 1.35,
102
+ "learning_rate": 1.3272335844994619e-05,
103
+ "loss": 0.8372,
104
+ "step": 7500
105
+ },
106
+ {
107
+ "epoch": 1.44,
108
+ "learning_rate": 1.2823824901327593e-05,
109
+ "loss": 0.8675,
110
+ "step": 8000
111
+ },
112
+ {
113
+ "epoch": 1.52,
114
+ "learning_rate": 1.2375313957660568e-05,
115
+ "loss": 0.8772,
116
+ "step": 8500
117
+ },
118
+ {
119
+ "epoch": 1.61,
120
+ "learning_rate": 1.1926803013993542e-05,
121
+ "loss": 0.8653,
122
+ "step": 9000
123
+ },
124
+ {
125
+ "epoch": 1.7,
126
+ "learning_rate": 1.1478292070326518e-05,
127
+ "loss": 0.8589,
128
+ "step": 9500
129
+ },
130
+ {
131
+ "epoch": 1.79,
132
+ "learning_rate": 1.1029781126659492e-05,
133
+ "loss": 0.8644,
134
+ "step": 10000
135
+ },
136
+ {
137
+ "epoch": 1.88,
138
+ "learning_rate": 1.0581270182992467e-05,
139
+ "loss": 0.8288,
140
+ "step": 10500
141
+ },
142
+ {
143
+ "epoch": 1.97,
144
+ "learning_rate": 1.0132759239325441e-05,
145
+ "loss": 0.8487,
146
+ "step": 11000
147
+ },
148
+ {
149
+ "epoch": 2.0,
150
+ "eval_exact_match": 79.52696310312204,
151
+ "eval_f1": 87.21705377119197,
152
+ "step": 11148
153
+ }
154
+ ],
155
+ "max_steps": 22296,
156
+ "num_train_epochs": 4,
157
+ "total_flos": 3.4955234174304256e+16,
158
+ "trial_name": null,
159
+ "trial_params": null
160
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89a1d06d90f72302a533122c91000cabfcd06dc7d2c7fddad5dadb2d542209da
3
+ size 3183
vocab.txt ADDED
The diff for this file is too large to render. See raw diff