batterydata
commited on
Commit
•
eab08da
1
Parent(s):
923101c
best model for qa
Browse files- config.json +25 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +130 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/projects/SolarWindowsADSP/shu/models/revision/bert/batteryscibert-cased/",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.17.0.dev0",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 31116
|
25 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:911ef92015e7ab1a4d5f33e2da577d6eb8ebff7a30bc7d5258140063b0193f23
|
3 |
+
size 874919917
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68e6dd08cba70443649e9cee664b023e0ecc4e82bededaaf9c44524e57a13c25
|
3 |
+
size 437486071
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd1af8d8304655b94035c71de052ea4a2a1c93d3f530f939c314f57445021fd7
|
3 |
+
size 14657
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95101a13f0d4ce7ffaa3ba56f816e138b73804ba09feeface4484867c279632c
|
3 |
+
size 14657
|
rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d039fd5a7226ae7104d945555f30ab032494d801bf72da66be4e2a581e10bcd
|
3 |
+
size 14657
|
rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bfe597543c01ef4960fb56174c74cbba99ea90890573757013d09894338a667
|
3 |
+
size 14657
|
rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2999db9de808ed144ee34bfa73a3956d4e38ef7e2ffc7c95dda7321b71be4519
|
3 |
+
size 14657
|
rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5301369d4baf27ab2a522076a54aa41376303ddfd98c4f194a28705b641e6095
|
3 |
+
size 14657
|
rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04960e269537352a6ca6029c44ca9bf06b3086ebccd5944b5a10547059548854
|
3 |
+
size 14657
|
rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5b1a17321ee7a547808268d9e1bfac64b1ce1e7bb5e16907cc8ac036ad8a149
|
3 |
+
size 14657
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0e6c477ec355b808fd9b5d499f0924289f7b68e9b506debd7715453bbe445b6
|
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/revision/bert/batteryscibert-cased/", "do_basic_tokenize": true, "never_split": null, "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": 8427,
|
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": 1.911000355998576e-05,
|
13 |
+
"loss": 2.0667,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.36,
|
18 |
+
"learning_rate": 1.822000711997152e-05,
|
19 |
+
"loss": 1.382,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.53,
|
24 |
+
"learning_rate": 1.733001067995728e-05,
|
25 |
+
"loss": 1.2498,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.71,
|
30 |
+
"learning_rate": 1.644001423994304e-05,
|
31 |
+
"loss": 1.1809,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.89,
|
36 |
+
"learning_rate": 1.55500177999288e-05,
|
37 |
+
"loss": 1.1255,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.0,
|
42 |
+
"eval_exact_match": 76.79280983916746,
|
43 |
+
"eval_f1": 85.50356159934326,
|
44 |
+
"step": 2809
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.07,
|
48 |
+
"learning_rate": 1.4660021359914563e-05,
|
49 |
+
"loss": 1.0414,
|
50 |
+
"step": 3000
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.25,
|
54 |
+
"learning_rate": 1.3770024919900323e-05,
|
55 |
+
"loss": 0.8871,
|
56 |
+
"step": 3500
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.42,
|
60 |
+
"learning_rate": 1.2880028479886081e-05,
|
61 |
+
"loss": 0.908,
|
62 |
+
"step": 4000
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.6,
|
66 |
+
"learning_rate": 1.1990032039871841e-05,
|
67 |
+
"loss": 0.864,
|
68 |
+
"step": 4500
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.78,
|
72 |
+
"learning_rate": 1.1100035599857601e-05,
|
73 |
+
"loss": 0.868,
|
74 |
+
"step": 5000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.96,
|
78 |
+
"learning_rate": 1.0210039159843361e-05,
|
79 |
+
"loss": 0.8678,
|
80 |
+
"step": 5500
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.0,
|
84 |
+
"eval_exact_match": 79.16745506149479,
|
85 |
+
"eval_f1": 86.76959997899563,
|
86 |
+
"step": 5618
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.14,
|
90 |
+
"learning_rate": 9.320042719829121e-06,
|
91 |
+
"loss": 0.7097,
|
92 |
+
"step": 6000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 2.31,
|
96 |
+
"learning_rate": 8.430046279814883e-06,
|
97 |
+
"loss": 0.6732,
|
98 |
+
"step": 6500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.49,
|
102 |
+
"learning_rate": 7.540049839800642e-06,
|
103 |
+
"loss": 0.6801,
|
104 |
+
"step": 7000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.67,
|
108 |
+
"learning_rate": 6.650053399786402e-06,
|
109 |
+
"loss": 0.6832,
|
110 |
+
"step": 7500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 2.85,
|
114 |
+
"learning_rate": 5.7600569597721615e-06,
|
115 |
+
"loss": 0.678,
|
116 |
+
"step": 8000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 3.0,
|
120 |
+
"eval_exact_match": 79.65941343424787,
|
121 |
+
"eval_f1": 87.43123506757227,
|
122 |
+
"step": 8427
|
123 |
+
}
|
124 |
+
],
|
125 |
+
"max_steps": 11236,
|
126 |
+
"num_train_epochs": 4,
|
127 |
+
"total_flos": 5.284674541505741e+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 sha256:5d774f45757f413983d8022ec2f9f9d47bafa1d3630bd1deee42b71700d72390
|
3 |
+
size 3183
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|