bgk commited on
Commit
ba74656
·
1 Parent(s): 10a4c30

Upload 8 files

Browse files
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mobilebert-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_activation": false,
8
+ "classifier_dropout": null,
9
+ "embedding_size": 128,
10
+ "hidden_act": "relu",
11
+ "hidden_dropout_prob": 0.0,
12
+ "hidden_size": 512,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-FOOD_QUANTITY",
16
+ "2": "B-FOOD_SIZE",
17
+ "3": "B-FOOD",
18
+ "4": "I-FOOD",
19
+ "5": "B-FOOD_INGREDIENTS",
20
+ "6": "I-FOOD_INGREDIENTS",
21
+ "7": "B-DRINK_SIZE",
22
+ "8": "B-DRINK_QUANTITY",
23
+ "9": "B-DRINK",
24
+ "10": "B-PAYMENT",
25
+ "11": "I-PAYMENT",
26
+ "12": "B-DELIVERY_ADDRESS",
27
+ "13": "I-DRINK_SIZE",
28
+ "14": "I-DRINK",
29
+ "15": "I-FOOD_SIZE",
30
+ "16": "I-ING",
31
+ "17": "I-DELIVERY_ADDRESS"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 512,
35
+ "intra_bottleneck_size": 128,
36
+ "key_query_shared_bottleneck": true,
37
+ "label2id": {
38
+ "B-DELIVERY_ADDRESS": 12,
39
+ "B-DRINK": 9,
40
+ "B-DRINK_QUANTITY": 8,
41
+ "B-DRINK_SIZE": 7,
42
+ "B-FOOD": 3,
43
+ "B-FOOD_INGREDIENTS": 5,
44
+ "B-FOOD_QUANTITY": 1,
45
+ "B-FOOD_SIZE": 2,
46
+ "B-PAYMENT": 10,
47
+ "I-DELIVERY_ADDRESS": 17,
48
+ "I-DRINK": 14,
49
+ "I-DRINK_SIZE": 13,
50
+ "I-FOOD": 4,
51
+ "I-FOOD_INGREDIENTS": 6,
52
+ "I-FOOD_SIZE": 15,
53
+ "I-ING": 16,
54
+ "I-PAYMENT": 11,
55
+ "O": 0
56
+ },
57
+ "layer_norm_eps": 1e-12,
58
+ "max_position_embeddings": 512,
59
+ "model_type": "bert",
60
+ "normalization_type": "no_norm",
61
+ "num_attention_heads": 4,
62
+ "num_feedforward_networks": 4,
63
+ "num_hidden_layers": 24,
64
+ "pad_token_id": 0,
65
+ "position_embedding_type": "absolute",
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.28.1",
68
+ "trigram_input": true,
69
+ "true_hidden_size": 128,
70
+ "type_vocab_size": 2,
71
+ "use_bottleneck": true,
72
+ "use_bottleneck_attention": false,
73
+ "use_cache": true,
74
+ "vocab_size": 30522
75
+ }
eval_results.txt ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ precision recall f1-score support
2
+
3
+ DELIVERY_ADDRESS 0.9881 0.9881 0.9881 84
4
+ DRINK 0.7027 0.8000 0.7482 65
5
+ DRINK_QUANTITY 0.9804 0.9804 0.9804 51
6
+ DRINK_SIZE 0.9688 0.9538 0.9612 65
7
+ FOOD 0.8443 0.8981 0.8704 157
8
+ FOOD_INGREDIENTS 0.8540 0.9106 0.8814 302
9
+ FOOD_QUANTITY 0.9855 1.0000 0.9927 136
10
+ FOOD_SIZE 1.0000 1.0000 1.0000 33
11
+ PAYMENT 0.8816 0.9306 0.9054 72
12
+
13
+ micro avg 0.8910 0.9316 0.9108 965
14
+ macro avg 0.9117 0.9402 0.9253 965
15
+ weighted avg 0.8939 0.9316 0.9121 965
16
+
17
+ eval_loss = 0.11614906560215685
18
+ f1_score = 0.9108409321175278
19
+ precision = 0.8909811694747275
20
+ recall = 0.9316062176165804
model_args.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 3e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "google/mobilebert-uncased", "model_type": "bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 1, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 4, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 42, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": true, "labels_list": ["O", "B-FOOD_QUANTITY", "B-FOOD_SIZE", "B-FOOD", "I-FOOD", "B-FOOD_INGREDIENTS", "I-FOOD_INGREDIENTS", "B-DRINK_SIZE", "B-DRINK_QUANTITY", "B-DRINK", "B-PAYMENT", "I-PAYMENT", "B-DELIVERY_ADDRESS", "I-DRINK_SIZE", "I-DRINK", "I-FOOD_SIZE", "I-ING", "I-DELIVERY_ADDRESS"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc816b9f2b887bed53bce9f18b1daba31c0eba855543d4ff58fac3e2e8dfa095
3
+ size 215227437
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff6197efc45fb928f9cc346f8c00375ec231be4fe133a0a7ad30bcb11fa2a2b
3
+ size 3323
vocab.txt ADDED
The diff for this file is too large to render. See raw diff