batterydata
commited on
Commit
•
f64a6de
1
Parent(s):
b5aa1fe
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-uncased/",
|
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": 31090
|
25 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fcd6e10001520f8c2741170f416196ca5582ce6604892d84ed3d93ca6a8b709
|
3 |
+
size 874760173
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:618813f1e78fc1cd87a5868e86b6dd175626f76787b8ff6ddb3a1e8e5484e9ac
|
3 |
+
size 437406199
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:882916ae0300639f3813fd1d0673e0c1569c66110e3055087e6f4e7da7438024
|
3 |
+
size 14657
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91d349f4ebd5eb9cf05be3d12208db7bcd5a1b00d9f20144c04df337a9805394
|
3 |
+
size 14657
|
rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a7771fa3f69bfc0a65fb865d5e8544b0d3156408176c6b7ccdad536644260a0
|
3 |
+
size 14657
|
rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17eca2e16d29ab6f55b0d7740fcdf7b0b8a4c6752bbd3e05dfa715f588562ea1
|
3 |
+
size 14657
|
rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43f1f8785a6f7b19c5e640426ee2072a381b8fab9c100006cec8731cc677e10f
|
3 |
+
size 14657
|
rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6a16c5f9786caa606d74717ce2fb0a66b388aa59e08740f28e709b4a19decc0
|
3 |
+
size 14657
|
rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24b2b919dd5da0757ffacc83cf987f91fd2b9f00ce490945276674a2c73b29cb
|
3 |
+
size 14657
|
rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a33888c8c244b3e083a4fda5182f32f73e2a206222e97408082c3d858785da6b
|
3 |
+
size 14657
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2ff253fba06a55ba17ffb3970c10bd4e12dff4c9e1662d0ef5447bb812a3f1f
|
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-uncased/", "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": 8346,
|
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": 1.910136592379583e-05,
|
13 |
+
"loss": 2.1513,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.36,
|
18 |
+
"learning_rate": 1.8202731847591663e-05,
|
19 |
+
"loss": 1.4112,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.54,
|
24 |
+
"learning_rate": 1.7304097771387492e-05,
|
25 |
+
"loss": 1.3035,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.72,
|
30 |
+
"learning_rate": 1.6405463695183324e-05,
|
31 |
+
"loss": 1.1842,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.9,
|
36 |
+
"learning_rate": 1.5506829618979153e-05,
|
37 |
+
"loss": 1.1289,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.0,
|
42 |
+
"eval_exact_match": 77.59697256385998,
|
43 |
+
"eval_f1": 86.11156390697873,
|
44 |
+
"step": 2782
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.08,
|
48 |
+
"learning_rate": 1.4608195542774984e-05,
|
49 |
+
"loss": 0.9913,
|
50 |
+
"step": 3000
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.26,
|
54 |
+
"learning_rate": 1.3709561466570813e-05,
|
55 |
+
"loss": 0.884,
|
56 |
+
"step": 3500
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.44,
|
60 |
+
"learning_rate": 1.2810927390366643e-05,
|
61 |
+
"loss": 0.88,
|
62 |
+
"step": 4000
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.62,
|
66 |
+
"learning_rate": 1.1912293314162472e-05,
|
67 |
+
"loss": 0.8624,
|
68 |
+
"step": 4500
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.8,
|
72 |
+
"learning_rate": 1.1013659237958305e-05,
|
73 |
+
"loss": 0.858,
|
74 |
+
"step": 5000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.98,
|
78 |
+
"learning_rate": 1.0115025161754135e-05,
|
79 |
+
"loss": 0.8303,
|
80 |
+
"step": 5500
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.0,
|
84 |
+
"eval_exact_match": 79.47019867549669,
|
85 |
+
"eval_f1": 87.26677361902833,
|
86 |
+
"step": 5564
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.16,
|
90 |
+
"learning_rate": 9.216391085549964e-06,
|
91 |
+
"loss": 0.6891,
|
92 |
+
"step": 6000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 2.34,
|
96 |
+
"learning_rate": 8.317757009345795e-06,
|
97 |
+
"loss": 0.6715,
|
98 |
+
"step": 6500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.52,
|
102 |
+
"learning_rate": 7.419122933141625e-06,
|
103 |
+
"loss": 0.6626,
|
104 |
+
"step": 7000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.7,
|
108 |
+
"learning_rate": 6.520488856937456e-06,
|
109 |
+
"loss": 0.6423,
|
110 |
+
"step": 7500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 2.88,
|
114 |
+
"learning_rate": 5.621854780733286e-06,
|
115 |
+
"loss": 0.6547,
|
116 |
+
"step": 8000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 3.0,
|
120 |
+
"eval_exact_match": 79.81078524124882,
|
121 |
+
"eval_f1": 87.66343771063279,
|
122 |
+
"step": 8346
|
123 |
+
}
|
124 |
+
],
|
125 |
+
"max_steps": 11128,
|
126 |
+
"num_train_epochs": 4,
|
127 |
+
"total_flos": 5.233878433057997e+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 sha256:8b86aa4544894e45e8b8f868a6ef891c50560aa940b5cf3d9f6ed1ae795208c0
|
3 |
+
size 3183
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|