bgk commited on
Commit
3402ea8
·
1 Parent(s): 291d5da

Upload 10 files

Browse files
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
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-DELIVERY_ADDRESS"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 3072,
34
+ "label2id": {
35
+ "B-DELIVERY_ADDRESS": 12,
36
+ "B-DRINK": 9,
37
+ "B-DRINK_QUANTITY": 8,
38
+ "B-DRINK_SIZE": 7,
39
+ "B-FOOD": 3,
40
+ "B-FOOD_INGREDIENTS": 5,
41
+ "B-FOOD_QUANTITY": 1,
42
+ "B-FOOD_SIZE": 2,
43
+ "B-PAYMENT": 10,
44
+ "I-DELIVERY_ADDRESS": 16,
45
+ "I-DRINK": 14,
46
+ "I-DRINK_SIZE": 13,
47
+ "I-FOOD": 4,
48
+ "I-FOOD_INGREDIENTS": 6,
49
+ "I-FOOD_SIZE": 15,
50
+ "I-PAYMENT": 11,
51
+ "O": 0
52
+ },
53
+ "layer_norm_eps": 1e-05,
54
+ "max_position_embeddings": 514,
55
+ "model_type": "roberta",
56
+ "num_attention_heads": 12,
57
+ "num_hidden_layers": 12,
58
+ "pad_token_id": 1,
59
+ "position_embedding_type": "absolute",
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.25.1",
62
+ "type_vocab_size": 1,
63
+ "use_cache": true,
64
+ "vocab_size": 50265
65
+ }
eval_results.txt ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ precision recall f1-score support
2
+
3
+ DELIVERY_ADDRESS 1.0000 1.0000 1.0000 80
4
+ DRINK 0.9636 0.9298 0.9464 57
5
+ DRINK_QUANTITY 0.9318 0.9762 0.9535 42
6
+ DRINK_SIZE 0.9298 0.9636 0.9464 55
7
+ FOOD 1.0000 0.9938 0.9969 161
8
+ FOOD_INGREDIENTS 0.9412 0.9590 0.9500 317
9
+ FOOD_QUANTITY 1.0000 0.9932 0.9966 146
10
+ FOOD_SIZE 0.9310 0.9643 0.9474 28
11
+ PAYMENT 0.9595 0.9861 0.9726 72
12
+
13
+ micro avg 0.9659 0.9749 0.9704 958
14
+ macro avg 0.9619 0.9740 0.9678 958
15
+ weighted avg 0.9663 0.9749 0.9705 958
16
+
17
+ eval_loss = 0.06323894620355633
18
+ f1_score = 0.9703896103896104
19
+ precision = 0.9658738366080661
20
+ recall = 0.9749478079331941
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
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": "roberta-base", "model_type": "roberta", "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-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:debea87560cb635a7d7b2ba32c2670f65baa6ac51fafd6e6fb910d065e6e47f3
3
+ size 496345197
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "do_lower_case": false,
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "name_or_path": "roberta-base",
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "special_tokens_map_file": null,
14
+ "tokenizer_class": "RobertaTokenizer",
15
+ "trim_offsets": true,
16
+ "unk_token": "<unk>"
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85b5e7e5c2e89e7a472fae83f7015dea02ebd7d9760753b443cdaf7accc1705
3
+ size 3259
vocab.json ADDED
The diff for this file is too large to render. See raw diff