Training in progress, epoch 1
Browse files- config.json +148 -0
- logs/events.out.tfevents.1700961698.serv-3318.864794.4 +3 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gokuls/model_v1_complete_training_wt_init_48_tiny_freeze_new_ffn_1",
|
| 3 |
+
"activation": "relu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.05,
|
| 8 |
+
"dim": 128,
|
| 9 |
+
"dropout": 0.05,
|
| 10 |
+
"hidden_dim": 128,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "datetime_query",
|
| 13 |
+
"1": "iot_hue_lightchange",
|
| 14 |
+
"10": "qa_currency",
|
| 15 |
+
"11": "transport_traffic",
|
| 16 |
+
"12": "general_quirky",
|
| 17 |
+
"13": "weather_query",
|
| 18 |
+
"14": "audio_volume_up",
|
| 19 |
+
"15": "email_addcontact",
|
| 20 |
+
"16": "takeaway_order",
|
| 21 |
+
"17": "email_querycontact",
|
| 22 |
+
"18": "iot_hue_lightup",
|
| 23 |
+
"19": "recommendation_locations",
|
| 24 |
+
"2": "transport_ticket",
|
| 25 |
+
"20": "play_audiobook",
|
| 26 |
+
"21": "lists_createoradd",
|
| 27 |
+
"22": "news_query",
|
| 28 |
+
"23": "alarm_query",
|
| 29 |
+
"24": "iot_wemo_on",
|
| 30 |
+
"25": "general_joke",
|
| 31 |
+
"26": "qa_definition",
|
| 32 |
+
"27": "social_query",
|
| 33 |
+
"28": "music_settings",
|
| 34 |
+
"29": "audio_volume_other",
|
| 35 |
+
"3": "takeaway_query",
|
| 36 |
+
"30": "calendar_remove",
|
| 37 |
+
"31": "iot_hue_lightdim",
|
| 38 |
+
"32": "calendar_query",
|
| 39 |
+
"33": "email_sendemail",
|
| 40 |
+
"34": "iot_cleaning",
|
| 41 |
+
"35": "audio_volume_down",
|
| 42 |
+
"36": "play_radio",
|
| 43 |
+
"37": "cooking_query",
|
| 44 |
+
"38": "datetime_convert",
|
| 45 |
+
"39": "qa_maths",
|
| 46 |
+
"4": "qa_stock",
|
| 47 |
+
"40": "iot_hue_lightoff",
|
| 48 |
+
"41": "iot_hue_lighton",
|
| 49 |
+
"42": "transport_query",
|
| 50 |
+
"43": "music_likeness",
|
| 51 |
+
"44": "email_query",
|
| 52 |
+
"45": "play_music",
|
| 53 |
+
"46": "audio_volume_mute",
|
| 54 |
+
"47": "social_post",
|
| 55 |
+
"48": "alarm_set",
|
| 56 |
+
"49": "qa_factoid",
|
| 57 |
+
"5": "general_greet",
|
| 58 |
+
"50": "calendar_set",
|
| 59 |
+
"51": "play_game",
|
| 60 |
+
"52": "alarm_remove",
|
| 61 |
+
"53": "lists_remove",
|
| 62 |
+
"54": "transport_taxi",
|
| 63 |
+
"55": "recommendation_movies",
|
| 64 |
+
"56": "iot_coffee",
|
| 65 |
+
"57": "music_query",
|
| 66 |
+
"58": "play_podcasts",
|
| 67 |
+
"59": "lists_query",
|
| 68 |
+
"6": "recommendation_events",
|
| 69 |
+
"7": "music_dislikeness",
|
| 70 |
+
"8": "iot_wemo_off",
|
| 71 |
+
"9": "cooking_recipe"
|
| 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": "hybridbert",
|
| 138 |
+
"n_heads": 2,
|
| 139 |
+
"n_layers": 2,
|
| 140 |
+
"pad_token_id": 0,
|
| 141 |
+
"problem_type": "single_label_classification",
|
| 142 |
+
"qa_dropout": 0.1,
|
| 143 |
+
"seq_classif_dropout": 0.1,
|
| 144 |
+
"sinusoidal_pos_embds": true,
|
| 145 |
+
"torch_dtype": "float32",
|
| 146 |
+
"transformers_version": "4.35.2",
|
| 147 |
+
"vocab_size": 30522
|
| 148 |
+
}
|
logs/events.out.tfevents.1700961698.serv-3318.864794.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f4bfb70f5e4c371f16010a04e719757e2bcd931906ace1f841cc86751204b4e
|
| 3 |
+
size 7985
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6a541ee5ba71c0b8ae1475184befd5848b5aee179edd922d01810b19931024a
|
| 3 |
+
size 16990232
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
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": true,
|
| 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 sha256:86a679486b1ed89e2b3f1f57ade8e705a3e48b2f3afd703c12fb5d8d31f06c9e
|
| 3 |
+
size 4219
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|