Training in progress epoch 0
Browse files- README.md +55 -0
- config.json +147 -0
- special_tokens_map.json +7 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
+
model-index:
|
7 |
+
- name: aiuser1/sample-intent-detect-1
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
12 |
+
probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# aiuser1/sample-intent-detect-1
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 3.0456
|
19 |
+
- Validation Loss: 1.9009
|
20 |
+
- Train Accuracy: 0.6292
|
21 |
+
- Epoch: 0
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 25000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
|
41 |
+
- training_precision: float32
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
46 |
+
|:----------:|:---------------:|:--------------:|:-----:|
|
47 |
+
| 3.0456 | 1.9009 | 0.6292 | 0 |
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.33.3
|
53 |
+
- TensorFlow 2.13.0
|
54 |
+
- Datasets 2.14.5
|
55 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,147 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "datetime_query",
|
13 |
+
"1": "iot_hue_lightchange",
|
14 |
+
"2": "transport_ticket",
|
15 |
+
"3": "takeaway_query",
|
16 |
+
"4": "qa_stock",
|
17 |
+
"5": "general_greet",
|
18 |
+
"6": "recommendation_events",
|
19 |
+
"7": "music_dislikeness",
|
20 |
+
"8": "iot_wemo_off",
|
21 |
+
"9": "cooking_recipe",
|
22 |
+
"10": "qa_currency",
|
23 |
+
"11": "transport_traffic",
|
24 |
+
"12": "general_quirky",
|
25 |
+
"13": "weather_query",
|
26 |
+
"14": "audio_volume_up",
|
27 |
+
"15": "email_addcontact",
|
28 |
+
"16": "takeaway_order",
|
29 |
+
"17": "email_querycontact",
|
30 |
+
"18": "iot_hue_lightup",
|
31 |
+
"19": "recommendation_locations",
|
32 |
+
"20": "play_audiobook",
|
33 |
+
"21": "lists_createoradd",
|
34 |
+
"22": "news_query",
|
35 |
+
"23": "alarm_query",
|
36 |
+
"24": "iot_wemo_on",
|
37 |
+
"25": "general_joke",
|
38 |
+
"26": "qa_definition",
|
39 |
+
"27": "social_query",
|
40 |
+
"28": "music_settings",
|
41 |
+
"29": "audio_volume_other",
|
42 |
+
"30": "calendar_remove",
|
43 |
+
"31": "iot_hue_lightdim",
|
44 |
+
"32": "calendar_query",
|
45 |
+
"33": "email_sendemail",
|
46 |
+
"34": "iot_cleaning",
|
47 |
+
"35": "audio_volume_down",
|
48 |
+
"36": "play_radio",
|
49 |
+
"37": "cooking_query",
|
50 |
+
"38": "datetime_convert",
|
51 |
+
"39": "qa_maths",
|
52 |
+
"40": "iot_hue_lightoff",
|
53 |
+
"41": "iot_hue_lighton",
|
54 |
+
"42": "transport_query",
|
55 |
+
"43": "music_likeness",
|
56 |
+
"44": "email_query",
|
57 |
+
"45": "play_music",
|
58 |
+
"46": "audio_volume_mute",
|
59 |
+
"47": "social_post",
|
60 |
+
"48": "alarm_set",
|
61 |
+
"49": "qa_factoid",
|
62 |
+
"50": "calendar_set",
|
63 |
+
"51": "play_game",
|
64 |
+
"52": "alarm_remove",
|
65 |
+
"53": "lists_remove",
|
66 |
+
"54": "transport_taxi",
|
67 |
+
"55": "recommendation_movies",
|
68 |
+
"56": "iot_coffee",
|
69 |
+
"57": "music_query",
|
70 |
+
"58": "play_podcasts",
|
71 |
+
"59": "lists_query"
|
72 |
+
},
|
73 |
+
"initializer_range": 0.02,
|
74 |
+
"label2id": {
|
75 |
+
"alarm_query": 23,
|
76 |
+
"alarm_remove": 52,
|
77 |
+
"alarm_set": 48,
|
78 |
+
"audio_volume_down": 35,
|
79 |
+
"audio_volume_mute": 46,
|
80 |
+
"audio_volume_other": 29,
|
81 |
+
"audio_volume_up": 14,
|
82 |
+
"calendar_query": 32,
|
83 |
+
"calendar_remove": 30,
|
84 |
+
"calendar_set": 50,
|
85 |
+
"cooking_query": 37,
|
86 |
+
"cooking_recipe": 9,
|
87 |
+
"datetime_convert": 38,
|
88 |
+
"datetime_query": 0,
|
89 |
+
"email_addcontact": 15,
|
90 |
+
"email_query": 44,
|
91 |
+
"email_querycontact": 17,
|
92 |
+
"email_sendemail": 33,
|
93 |
+
"general_greet": 5,
|
94 |
+
"general_joke": 25,
|
95 |
+
"general_quirky": 12,
|
96 |
+
"iot_cleaning": 34,
|
97 |
+
"iot_coffee": 56,
|
98 |
+
"iot_hue_lightchange": 1,
|
99 |
+
"iot_hue_lightdim": 31,
|
100 |
+
"iot_hue_lightoff": 40,
|
101 |
+
"iot_hue_lighton": 41,
|
102 |
+
"iot_hue_lightup": 18,
|
103 |
+
"iot_wemo_off": 8,
|
104 |
+
"iot_wemo_on": 24,
|
105 |
+
"lists_createoradd": 21,
|
106 |
+
"lists_query": 59,
|
107 |
+
"lists_remove": 53,
|
108 |
+
"music_dislikeness": 7,
|
109 |
+
"music_likeness": 43,
|
110 |
+
"music_query": 57,
|
111 |
+
"music_settings": 28,
|
112 |
+
"news_query": 22,
|
113 |
+
"play_audiobook": 20,
|
114 |
+
"play_game": 51,
|
115 |
+
"play_music": 45,
|
116 |
+
"play_podcasts": 58,
|
117 |
+
"play_radio": 36,
|
118 |
+
"qa_currency": 10,
|
119 |
+
"qa_definition": 26,
|
120 |
+
"qa_factoid": 49,
|
121 |
+
"qa_maths": 39,
|
122 |
+
"qa_stock": 4,
|
123 |
+
"recommendation_events": 6,
|
124 |
+
"recommendation_locations": 19,
|
125 |
+
"recommendation_movies": 55,
|
126 |
+
"social_post": 47,
|
127 |
+
"social_query": 27,
|
128 |
+
"takeaway_order": 16,
|
129 |
+
"takeaway_query": 3,
|
130 |
+
"transport_query": 42,
|
131 |
+
"transport_taxi": 54,
|
132 |
+
"transport_ticket": 2,
|
133 |
+
"transport_traffic": 11,
|
134 |
+
"weather_query": 13
|
135 |
+
},
|
136 |
+
"max_position_embeddings": 512,
|
137 |
+
"model_type": "distilbert",
|
138 |
+
"n_heads": 12,
|
139 |
+
"n_layers": 6,
|
140 |
+
"pad_token_id": 0,
|
141 |
+
"qa_dropout": 0.1,
|
142 |
+
"seq_classif_dropout": 0.2,
|
143 |
+
"sinusoidal_pos_embds": false,
|
144 |
+
"tie_weights_": true,
|
145 |
+
"transformers_version": "4.33.3",
|
146 |
+
"vocab_size": 30522
|
147 |
+
}
|
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 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5a81ba960dadb40fd148a5fa163ee6bbc4b951c0e0af242c60758808cf5ea0d
|
3 |
+
size 268129984
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "DistilBertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|