udpate
Browse files- README.md +0 -1
- config.json +40 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.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 +88 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
hello
|
|
|
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"finetuning_task": "ner",
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "B-dishname",
|
15 |
+
"2": "I-dishname",
|
16 |
+
"3": "B-ingredient",
|
17 |
+
"4": "I-ingredient"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"O": 0,
|
23 |
+
"B-dishname": 1,
|
24 |
+
"I-dishname": 2,
|
25 |
+
"B-ingredient": 3,
|
26 |
+
"I-ingredient": 4
|
27 |
+
},
|
28 |
+
"layer_norm_eps": 1e-12,
|
29 |
+
"max_position_embeddings": 512,
|
30 |
+
"model_type": "bert",
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_hidden_layers": 12,
|
33 |
+
"pad_token_id": 0,
|
34 |
+
"position_embedding_type": "absolute",
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.9.1",
|
37 |
+
"type_vocab_size": 2,
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 30522
|
40 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f537e459ec617fce5b577642790c7dd7de7809984feba4f5afb7f7bfa3e4b70
|
3 |
+
size 871288813
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11231443801f102fbeecc81ddc5441014b362552c1a32c43d48c045a8d1b7fb2
|
3 |
+
size 435670519
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf382caced15f295b3679d6632b970d9ec3454b7774aef9a374ef86bf9499cb3
|
3 |
+
size 14657
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a301a8ec22c933c6589dfe6f625b0f9dade0c9a1b4c3adb07b32cf4ee3e4f92
|
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_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 14.319809069212411,
|
5 |
+
"global_step": 6000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.19,
|
12 |
+
"learning_rate": 4.701670644391408e-05,
|
13 |
+
"loss": 0.0411,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 2.39,
|
18 |
+
"learning_rate": 4.4033412887828165e-05,
|
19 |
+
"loss": 0.003,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 3.58,
|
24 |
+
"learning_rate": 4.105011933174224e-05,
|
25 |
+
"loss": 0.0014,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 4.77,
|
30 |
+
"learning_rate": 3.806682577565633e-05,
|
31 |
+
"loss": 0.0001,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 5.97,
|
36 |
+
"learning_rate": 3.5083532219570406e-05,
|
37 |
+
"loss": 0.002,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 7.16,
|
42 |
+
"learning_rate": 3.210023866348449e-05,
|
43 |
+
"loss": 0.0036,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 8.35,
|
48 |
+
"learning_rate": 2.911694510739857e-05,
|
49 |
+
"loss": 0.0021,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 9.55,
|
54 |
+
"learning_rate": 2.613365155131265e-05,
|
55 |
+
"loss": 0.0015,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 10.74,
|
60 |
+
"learning_rate": 2.3150357995226732e-05,
|
61 |
+
"loss": 0.0011,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 11.93,
|
66 |
+
"learning_rate": 2.0167064439140813e-05,
|
67 |
+
"loss": 0.0015,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 13.13,
|
72 |
+
"learning_rate": 1.718377088305489e-05,
|
73 |
+
"loss": 0.0002,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 14.32,
|
78 |
+
"learning_rate": 1.4200477326968974e-05,
|
79 |
+
"loss": 0.0003,
|
80 |
+
"step": 6000
|
81 |
+
}
|
82 |
+
],
|
83 |
+
"max_steps": 8380,
|
84 |
+
"num_train_epochs": 20,
|
85 |
+
"total_flos": 555202280044620.0,
|
86 |
+
"trial_name": null,
|
87 |
+
"trial_params": null
|
88 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebf3f13481f08899407fd6301c5ecba4d0de0958b41967dd6c4ab2150f280919
|
3 |
+
size 2607
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|