Media1129 commited on
Commit
1173ac5
·
1 Parent(s): 10ca0cc
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-ingredient",
15
+ "2": "I-ingredient",
16
+ "3": "B-cuisines",
17
+ "4": "I-cuisines",
18
+ "5": "B-mealcourse",
19
+ "6": "I-mealcourse",
20
+ "7": "B-occasion",
21
+ "8": "I-occasion"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "O": 0,
27
+ "B-ingredient": 1,
28
+ "I-ingredient": 2,
29
+ "B-cuisines": 3,
30
+ "I-cuisines": 4,
31
+ "B-mealcourse": 5,
32
+ "I-mealcourse": 6,
33
+ "B-occasion": 7,
34
+ "I-occasion": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.9.1",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff6a6f697a3fc336e9f457d77c88a8afb711a063f90d2c63e53c387e63861a0
3
+ size 871313389
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e0cab81f7a6fb8a8527535cbee19dc01ed3e5a49e9c4814648c162c50f776ed
3
+ size 435682807
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a39fc30bf80407b22bf79807bf94b3a87eaa09fb5ef02c713bca3b99c040b86
3
+ size 14657
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b527f87d257966e7136f6ca9dd64a09446e5da7f70aed91cb135ea204c09578e
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 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.083815028901734,
5
+ "global_step": 3000,
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": 4.909682080924856e-05,
13
+ "loss": 0.0971,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.36,
18
+ "learning_rate": 4.8193641618497106e-05,
19
+ "loss": 0.0082,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.54,
24
+ "learning_rate": 4.729046242774567e-05,
25
+ "loss": 0.0066,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.72,
30
+ "learning_rate": 4.6387283236994224e-05,
31
+ "loss": 0.0064,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.9,
36
+ "learning_rate": 4.548410404624278e-05,
37
+ "loss": 0.005,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.08,
42
+ "learning_rate": 4.458092485549133e-05,
43
+ "loss": 0.0034,
44
+ "step": 3000
45
+ }
46
+ ],
47
+ "max_steps": 27680,
48
+ "num_train_epochs": 10,
49
+ "total_flos": 463298261491656.0,
50
+ "trial_name": null,
51
+ "trial_params": null
52
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee47459564e4a253ef0de354edb2599d52ccff8d0e270cdefc632a1107d6498a
3
+ size 2607
vocab.txt ADDED
The diff for this file is too large to render. See raw diff