HowMannyMore commited on
Commit
deae966
1 Parent(s): 511786f

amazon_intent_finetune_roberta

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bert-base-cased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ model-index:
10
+ - name: intent-finetuned-intent-detection
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # intent-finetuned-intent-detection
18
+
19
+ This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.6938
22
+ - Accuracy: 0.8638
23
+ - F1: 0.8593
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 2e-05
43
+ - train_batch_size: 64
44
+ - eval_batch_size: 128
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 5
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
+ | 3.0316 | 1.0 | 180 | 1.7788 | 0.6819 | 0.6352 |
56
+ | 1.4515 | 2.0 | 360 | 1.0539 | 0.7956 | 0.7735 |
57
+ | 0.9212 | 3.0 | 540 | 0.8143 | 0.8457 | 0.8382 |
58
+ | 0.6883 | 4.0 | 720 | 0.7246 | 0.8601 | 0.8544 |
59
+ | 0.583 | 5.0 | 900 | 0.6938 | 0.8638 | 0.8593 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.38.2
65
+ - Pytorch 2.2.1+cu121
66
+ - Datasets 2.18.0
67
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "alarm_query",
14
+ "1": "alarm_remove",
15
+ "2": "alarm_set",
16
+ "3": "audio_volume_down",
17
+ "4": "audio_volume_mute",
18
+ "5": "audio_volume_other",
19
+ "6": "audio_volume_up",
20
+ "7": "calendar_query",
21
+ "8": "calendar_remove",
22
+ "9": "calendar_set",
23
+ "10": "cooking_query",
24
+ "11": "cooking_recipe",
25
+ "12": "datetime_convert",
26
+ "13": "datetime_query",
27
+ "14": "email_addcontact",
28
+ "15": "email_query",
29
+ "16": "email_querycontact",
30
+ "17": "email_sendemail",
31
+ "18": "general_greet",
32
+ "19": "general_joke",
33
+ "20": "general_quirky",
34
+ "21": "iot_cleaning",
35
+ "22": "iot_coffee",
36
+ "23": "iot_hue_lightchange",
37
+ "24": "iot_hue_lightdim",
38
+ "25": "iot_hue_lightoff",
39
+ "26": "iot_hue_lighton",
40
+ "27": "iot_hue_lightup",
41
+ "28": "iot_wemo_off",
42
+ "29": "iot_wemo_on",
43
+ "30": "lists_createoradd",
44
+ "31": "lists_query",
45
+ "32": "lists_remove",
46
+ "33": "music_dislikeness",
47
+ "34": "music_likeness",
48
+ "35": "music_query",
49
+ "36": "music_settings",
50
+ "37": "news_query",
51
+ "38": "play_audiobook",
52
+ "39": "play_game",
53
+ "40": "play_music",
54
+ "41": "play_podcasts",
55
+ "42": "play_radio",
56
+ "43": "qa_currency",
57
+ "44": "qa_definition",
58
+ "45": "qa_factoid",
59
+ "46": "qa_maths",
60
+ "47": "qa_stock",
61
+ "48": "recommendation_events",
62
+ "49": "recommendation_locations",
63
+ "50": "recommendation_movies",
64
+ "51": "social_post",
65
+ "52": "social_query",
66
+ "53": "takeaway_order",
67
+ "54": "takeaway_query",
68
+ "55": "transport_query",
69
+ "56": "transport_taxi",
70
+ "57": "transport_ticket",
71
+ "58": "transport_traffic",
72
+ "59": "weather_query"
73
+ },
74
+ "initializer_range": 0.02,
75
+ "intermediate_size": 3072,
76
+ "label2id": {
77
+ "alarm_query": 0,
78
+ "alarm_remove": 1,
79
+ "alarm_set": 2,
80
+ "audio_volume_down": 3,
81
+ "audio_volume_mute": 4,
82
+ "audio_volume_other": 5,
83
+ "audio_volume_up": 6,
84
+ "calendar_query": 7,
85
+ "calendar_remove": 8,
86
+ "calendar_set": 9,
87
+ "cooking_query": 10,
88
+ "cooking_recipe": 11,
89
+ "datetime_convert": 12,
90
+ "datetime_query": 13,
91
+ "email_addcontact": 14,
92
+ "email_query": 15,
93
+ "email_querycontact": 16,
94
+ "email_sendemail": 17,
95
+ "general_greet": 18,
96
+ "general_joke": 19,
97
+ "general_quirky": 20,
98
+ "iot_cleaning": 21,
99
+ "iot_coffee": 22,
100
+ "iot_hue_lightchange": 23,
101
+ "iot_hue_lightdim": 24,
102
+ "iot_hue_lightoff": 25,
103
+ "iot_hue_lighton": 26,
104
+ "iot_hue_lightup": 27,
105
+ "iot_wemo_off": 28,
106
+ "iot_wemo_on": 29,
107
+ "lists_createoradd": 30,
108
+ "lists_query": 31,
109
+ "lists_remove": 32,
110
+ "music_dislikeness": 33,
111
+ "music_likeness": 34,
112
+ "music_query": 35,
113
+ "music_settings": 36,
114
+ "news_query": 37,
115
+ "play_audiobook": 38,
116
+ "play_game": 39,
117
+ "play_music": 40,
118
+ "play_podcasts": 41,
119
+ "play_radio": 42,
120
+ "qa_currency": 43,
121
+ "qa_definition": 44,
122
+ "qa_factoid": 45,
123
+ "qa_maths": 46,
124
+ "qa_stock": 47,
125
+ "recommendation_events": 48,
126
+ "recommendation_locations": 49,
127
+ "recommendation_movies": 50,
128
+ "social_post": 51,
129
+ "social_query": 52,
130
+ "takeaway_order": 53,
131
+ "takeaway_query": 54,
132
+ "transport_query": 55,
133
+ "transport_taxi": 56,
134
+ "transport_ticket": 57,
135
+ "transport_traffic": 58,
136
+ "weather_query": 59
137
+ },
138
+ "layer_norm_eps": 1e-12,
139
+ "max_position_embeddings": 512,
140
+ "model_type": "bert",
141
+ "num_attention_heads": 12,
142
+ "num_hidden_layers": 12,
143
+ "pad_token_id": 0,
144
+ "position_embedding_type": "absolute",
145
+ "problem_type": "single_label_classification",
146
+ "torch_dtype": "float32",
147
+ "transformers_version": "4.38.2",
148
+ "type_vocab_size": 2,
149
+ "use_cache": true,
150
+ "vocab_size": 28996
151
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f944b2a8df7548d78b2aa5ee0407ac48af719d7c3d926f3cff180f96c994ad8a
3
+ size 433449176
runs/Apr16_11-56-51_0a575836a554/events.out.tfevents.1713268636.0a575836a554.1166.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:000d03fbabb37aa6a8191814a88db6eb50591586ec0dfe67349eec826a4ace4a
3
+ size 11159
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f1fbfb9694d30155f9f3afaa711c9a8616d9649f2503545c5bd0dbef60c354f
3
+ size 4984
vocab.txt ADDED
The diff for this file is too large to render. See raw diff