update
Browse files- config.json +53 -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 +64 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"finetuning_task": "ner",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "O",
|
15 |
+
"1": "B-ingredient",
|
16 |
+
"2": "I-ingredient",
|
17 |
+
"3": "B-cuisines",
|
18 |
+
"4": "I-cuisines",
|
19 |
+
"5": "B-mealcourse",
|
20 |
+
"6": "I-mealcourse",
|
21 |
+
"7": "B-occasion",
|
22 |
+
"8": "I-occasion",
|
23 |
+
"9": "B-negingredient",
|
24 |
+
"10": "I-negingredient"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 3072,
|
28 |
+
"label2id": {
|
29 |
+
"O": 0,
|
30 |
+
"B-ingredient": 1,
|
31 |
+
"I-ingredient": 2,
|
32 |
+
"B-cuisines": 3,
|
33 |
+
"I-cuisines": 4,
|
34 |
+
"B-mealcourse": 5,
|
35 |
+
"I-mealcourse": 6,
|
36 |
+
"B-occasion": 7,
|
37 |
+
"I-occasion": 8,
|
38 |
+
"B-negingredient": 9,
|
39 |
+
"I-negingredient": 10
|
40 |
+
},
|
41 |
+
"layer_norm_eps": 1e-12,
|
42 |
+
"max_position_embeddings": 512,
|
43 |
+
"model_type": "bert",
|
44 |
+
"num_attention_heads": 12,
|
45 |
+
"num_hidden_layers": 12,
|
46 |
+
"pad_token_id": 0,
|
47 |
+
"position_embedding_type": "absolute",
|
48 |
+
"torch_dtype": "float32",
|
49 |
+
"transformers_version": "4.10.2",
|
50 |
+
"type_vocab_size": 2,
|
51 |
+
"use_cache": true,
|
52 |
+
"vocab_size": 30522
|
53 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea8d9dca1fc27d019aa8168af63779ab60f093dbddabde7fc1431f504f79856a
|
3 |
+
size 871325677
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60871126264002ed9e1b61eb645682cfc3310dcc09c6cdf18c407f4d20260cb0
|
3 |
+
size 435688951
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c18c33e987ba7fe4f0a4967089e57ea964281e7f9a6fa4badc71045e013e3490
|
3 |
+
size 14657
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5310269891ade9041511a2fd0c674ef0a1964b98dcbbf22b21423b31d2117b0
|
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 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.848484848484849,
|
5 |
+
"global_step": 4000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.61,
|
12 |
+
"learning_rate": 4.3939393939393944e-05,
|
13 |
+
"loss": 0.1499,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.21,
|
18 |
+
"learning_rate": 3.787878787878788e-05,
|
19 |
+
"loss": 0.0214,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.82,
|
24 |
+
"learning_rate": 3.181818181818182e-05,
|
25 |
+
"loss": 0.0066,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.42,
|
30 |
+
"learning_rate": 2.575757575757576e-05,
|
31 |
+
"loss": 0.0032,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 3.03,
|
36 |
+
"learning_rate": 1.9696969696969697e-05,
|
37 |
+
"loss": 0.0015,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.64,
|
42 |
+
"learning_rate": 1.3636363636363637e-05,
|
43 |
+
"loss": 0.0011,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 4.24,
|
48 |
+
"learning_rate": 7.5757575757575764e-06,
|
49 |
+
"loss": 0.0012,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.85,
|
54 |
+
"learning_rate": 1.5151515151515152e-06,
|
55 |
+
"loss": 0.0003,
|
56 |
+
"step": 4000
|
57 |
+
}
|
58 |
+
],
|
59 |
+
"max_steps": 4125,
|
60 |
+
"num_train_epochs": 5,
|
61 |
+
"total_flos": 618627535241304.0,
|
62 |
+
"trial_name": null,
|
63 |
+
"trial_params": null
|
64 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:502b6b799b8144676ab61aa6778aae686ceedfdcd73e8648183deda27d504b75
|
3 |
+
size 2607
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|