batterydata commited on
Commit
4861740
1 Parent(s): fad3e13

best model for qa

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/projects/SolarWindowsADSP/shu/models/bert-base-uncased/",
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:f43a75852015858b4f106fcf3b97557dc1e44fed856987c34a1ce92aae7c50c9
3
+ size 871270381
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59d4c23109d477de53d64f22fdeb9b2a19d9563d6634bbef8e382ab016e2989
3
+ size 435661303
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3ef130b5be4c23ac78d5c78b2c74ac6faeea04b06d20a94ecb5d477d4dc0ec5
3
+ size 14657
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f2cac8605cdcba7c1f412fa353f4216e28b0c56e8385bb5e33aa0b696c419fa
3
+ size 14657
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68bfe7b19fdbfe8a1347f0b6e44e861829c4aacdae1b6e4cb8e4fe2989bf4f36
3
+ size 14657
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79cc1b0c72163eebc7ffdb3bf637cf2411c0c574309e12334041f4f325127fd8
3
+ size 14657
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9bebb3c4fd0377bb49c4dda50fa3ed71b8ccbee13fc05dfc937ddf6e137f922
3
+ size 14657
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d86e4b0e4155b80c9a70fd251447e043e8eb7780fd5b187d9da1d1fffa48eee8
3
+ size 14657
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a115a3bf0cc9c0979421bd200df703e8202da9b6c05157e002dab7cc240105
3
+ size 14657
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38fe06e41fd4720adca3374d9968468fee020bfc92bd2b70c2fed12b73f56458
3
+ size 14657
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d76a2ae72c909de0bf20a045aa9629e9f08ec33067dbaa2c8defe8ed942edad
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, "special_tokens_map_file": null, "name_or_path": "/projects/SolarWindowsADSP/shu/models/bert-base-uncased/", "tokenizer_class": "BertTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 8301,
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": 2.8644741597397903e-05,
13
+ "loss": 2.0959,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.36,
18
+ "learning_rate": 2.728948319479581e-05,
19
+ "loss": 1.3446,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.54,
24
+ "learning_rate": 2.5934224792193712e-05,
25
+ "loss": 1.2113,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.72,
30
+ "learning_rate": 2.4578966389591615e-05,
31
+ "loss": 1.1509,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.9,
36
+ "learning_rate": 2.3223707986989517e-05,
37
+ "loss": 1.0866,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_exact_match": 79.10122989593188,
43
+ "eval_f1": 86.91234473539434,
44
+ "step": 2767
45
+ },
46
+ {
47
+ "epoch": 1.08,
48
+ "learning_rate": 2.1868449584387424e-05,
49
+ "loss": 0.9377,
50
+ "step": 3000
51
+ },
52
+ {
53
+ "epoch": 1.26,
54
+ "learning_rate": 2.051319118178533e-05,
55
+ "loss": 0.7975,
56
+ "step": 3500
57
+ },
58
+ {
59
+ "epoch": 1.45,
60
+ "learning_rate": 1.9157932779183232e-05,
61
+ "loss": 0.814,
62
+ "step": 4000
63
+ },
64
+ {
65
+ "epoch": 1.63,
66
+ "learning_rate": 1.7802674376581135e-05,
67
+ "loss": 0.7997,
68
+ "step": 4500
69
+ },
70
+ {
71
+ "epoch": 1.81,
72
+ "learning_rate": 1.644741597397904e-05,
73
+ "loss": 0.8012,
74
+ "step": 5000
75
+ },
76
+ {
77
+ "epoch": 1.99,
78
+ "learning_rate": 1.5092157571376944e-05,
79
+ "loss": 0.791,
80
+ "step": 5500
81
+ },
82
+ {
83
+ "epoch": 2.0,
84
+ "eval_exact_match": 79.78240302743615,
85
+ "eval_f1": 87.66969355486262,
86
+ "step": 5534
87
+ },
88
+ {
89
+ "epoch": 2.17,
90
+ "learning_rate": 1.3736899168774846e-05,
91
+ "loss": 0.5813,
92
+ "step": 6000
93
+ },
94
+ {
95
+ "epoch": 2.35,
96
+ "learning_rate": 1.238164076617275e-05,
97
+ "loss": 0.571,
98
+ "step": 6500
99
+ },
100
+ {
101
+ "epoch": 2.53,
102
+ "learning_rate": 1.1026382363570653e-05,
103
+ "loss": 0.5749,
104
+ "step": 7000
105
+ },
106
+ {
107
+ "epoch": 2.71,
108
+ "learning_rate": 9.671123960968558e-06,
109
+ "loss": 0.5654,
110
+ "step": 7500
111
+ },
112
+ {
113
+ "epoch": 2.89,
114
+ "learning_rate": 8.315865558366462e-06,
115
+ "loss": 0.568,
116
+ "step": 8000
117
+ },
118
+ {
119
+ "epoch": 3.0,
120
+ "eval_exact_match": 80.9271523178808,
121
+ "eval_f1": 88.19682357031269,
122
+ "step": 8301
123
+ }
124
+ ],
125
+ "max_steps": 11068,
126
+ "num_train_epochs": 4,
127
+ "total_flos": 5.204717742535475e+16,
128
+ "trial_name": null,
129
+ "trial_params": null
130
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c09975532a15ca0dbb6b1282a1f3b0496193a23e1f7547e78234b8c6ccbaa2b
3
+ size 3119
vocab.txt ADDED
The diff for this file is too large to render. See raw diff