End of training
Browse files- README.md +69 -0
- config.json +181 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: roberta-large
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- clinc_oos
|
8 |
+
model-index:
|
9 |
+
- name: output
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# output
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the clinc_oos dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.1692
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 2e-05
|
40 |
+
- train_batch_size: 16
|
41 |
+
- eval_batch_size: 16
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_steps: 500
|
46 |
+
- num_epochs: 10
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 0.3719 | 1.0 | 954 | 0.3159 |
|
53 |
+
| 0.0131 | 2.0 | 1908 | 0.1692 |
|
54 |
+
| 0.0149 | 3.0 | 2862 | 0.1947 |
|
55 |
+
| 0.0179 | 4.0 | 3816 | 0.1907 |
|
56 |
+
| 0.04 | 5.0 | 4770 | 0.1877 |
|
57 |
+
| 0.001 | 6.0 | 5724 | 0.1908 |
|
58 |
+
| 0.0473 | 7.0 | 6678 | 0.1961 |
|
59 |
+
| 0.0007 | 8.0 | 7632 | 0.1960 |
|
60 |
+
| 0.0415 | 9.0 | 8586 | 0.1945 |
|
61 |
+
| 0.0005 | 10.0 | 9540 | 0.1971 |
|
62 |
+
|
63 |
+
|
64 |
+
### Framework versions
|
65 |
+
|
66 |
+
- Transformers 4.34.1
|
67 |
+
- Pytorch 2.1.0+cu118
|
68 |
+
- Datasets 2.14.6
|
69 |
+
- Tokenizers 0.14.1
|
config.json
ADDED
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
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": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "restaurant_reviews",
|
15 |
+
"1": "nutrition_info",
|
16 |
+
"2": "account_blocked",
|
17 |
+
"3": "oil_change_how",
|
18 |
+
"4": "time",
|
19 |
+
"5": "weather",
|
20 |
+
"6": "redeem_rewards",
|
21 |
+
"7": "interest_rate",
|
22 |
+
"8": "gas_type",
|
23 |
+
"9": "accept_reservations",
|
24 |
+
"10": "smart_home",
|
25 |
+
"11": "user_name",
|
26 |
+
"12": "report_lost_card",
|
27 |
+
"13": "repeat",
|
28 |
+
"14": "whisper_mode",
|
29 |
+
"15": "what_are_your_hobbies",
|
30 |
+
"16": "order",
|
31 |
+
"17": "jump_start",
|
32 |
+
"18": "schedule_meeting",
|
33 |
+
"19": "meeting_schedule",
|
34 |
+
"20": "freeze_account",
|
35 |
+
"21": "what_song",
|
36 |
+
"22": "meaning_of_life",
|
37 |
+
"23": "restaurant_reservation",
|
38 |
+
"24": "traffic",
|
39 |
+
"25": "make_call",
|
40 |
+
"26": "text",
|
41 |
+
"27": "bill_balance",
|
42 |
+
"28": "improve_credit_score",
|
43 |
+
"29": "change_language",
|
44 |
+
"30": "no",
|
45 |
+
"31": "measurement_conversion",
|
46 |
+
"32": "timer",
|
47 |
+
"33": "flip_coin",
|
48 |
+
"34": "do_you_have_pets",
|
49 |
+
"35": "balance",
|
50 |
+
"36": "tell_joke",
|
51 |
+
"37": "last_maintenance",
|
52 |
+
"38": "exchange_rate",
|
53 |
+
"39": "uber",
|
54 |
+
"40": "car_rental",
|
55 |
+
"41": "credit_limit",
|
56 |
+
"42": "oos",
|
57 |
+
"43": "shopping_list",
|
58 |
+
"44": "expiration_date",
|
59 |
+
"45": "routing",
|
60 |
+
"46": "meal_suggestion",
|
61 |
+
"47": "tire_change",
|
62 |
+
"48": "todo_list",
|
63 |
+
"49": "card_declined",
|
64 |
+
"50": "rewards_balance",
|
65 |
+
"51": "change_accent",
|
66 |
+
"52": "vaccines",
|
67 |
+
"53": "reminder_update",
|
68 |
+
"54": "food_last",
|
69 |
+
"55": "change_ai_name",
|
70 |
+
"56": "bill_due",
|
71 |
+
"57": "who_do_you_work_for",
|
72 |
+
"58": "share_location",
|
73 |
+
"59": "international_visa",
|
74 |
+
"60": "calendar",
|
75 |
+
"61": "translate",
|
76 |
+
"62": "carry_on",
|
77 |
+
"63": "book_flight",
|
78 |
+
"64": "insurance_change",
|
79 |
+
"65": "todo_list_update",
|
80 |
+
"66": "timezone",
|
81 |
+
"67": "cancel_reservation",
|
82 |
+
"68": "transactions",
|
83 |
+
"69": "credit_score",
|
84 |
+
"70": "report_fraud",
|
85 |
+
"71": "spending_history",
|
86 |
+
"72": "directions",
|
87 |
+
"73": "spelling",
|
88 |
+
"74": "insurance",
|
89 |
+
"75": "what_is_your_name",
|
90 |
+
"76": "reminder",
|
91 |
+
"77": "where_are_you_from",
|
92 |
+
"78": "distance",
|
93 |
+
"79": "payday",
|
94 |
+
"80": "flight_status",
|
95 |
+
"81": "find_phone",
|
96 |
+
"82": "greeting",
|
97 |
+
"83": "alarm",
|
98 |
+
"84": "order_status",
|
99 |
+
"85": "confirm_reservation",
|
100 |
+
"86": "cook_time",
|
101 |
+
"87": "damaged_card",
|
102 |
+
"88": "reset_settings",
|
103 |
+
"89": "pin_change",
|
104 |
+
"90": "replacement_card_duration",
|
105 |
+
"91": "new_card",
|
106 |
+
"92": "roll_dice",
|
107 |
+
"93": "income",
|
108 |
+
"94": "taxes",
|
109 |
+
"95": "date",
|
110 |
+
"96": "who_made_you",
|
111 |
+
"97": "pto_request",
|
112 |
+
"98": "tire_pressure",
|
113 |
+
"99": "how_old_are_you",
|
114 |
+
"100": "rollover_401k",
|
115 |
+
"101": "pto_request_status",
|
116 |
+
"102": "how_busy",
|
117 |
+
"103": "application_status",
|
118 |
+
"104": "recipe",
|
119 |
+
"105": "calendar_update",
|
120 |
+
"106": "play_music",
|
121 |
+
"107": "yes",
|
122 |
+
"108": "direct_deposit",
|
123 |
+
"109": "credit_limit_change",
|
124 |
+
"110": "gas",
|
125 |
+
"111": "pay_bill",
|
126 |
+
"112": "ingredients_list",
|
127 |
+
"113": "lost_luggage",
|
128 |
+
"114": "goodbye",
|
129 |
+
"115": "what_can_i_ask_you",
|
130 |
+
"116": "book_hotel",
|
131 |
+
"117": "are_you_a_bot",
|
132 |
+
"118": "next_song",
|
133 |
+
"119": "change_speed",
|
134 |
+
"120": "plug_type",
|
135 |
+
"121": "maybe",
|
136 |
+
"122": "w2",
|
137 |
+
"123": "oil_change_when",
|
138 |
+
"124": "thank_you",
|
139 |
+
"125": "shopping_list_update",
|
140 |
+
"126": "pto_balance",
|
141 |
+
"127": "order_checks",
|
142 |
+
"128": "travel_alert",
|
143 |
+
"129": "fun_fact",
|
144 |
+
"130": "sync_device",
|
145 |
+
"131": "schedule_maintenance",
|
146 |
+
"132": "apr",
|
147 |
+
"133": "transfer",
|
148 |
+
"134": "ingredient_substitution",
|
149 |
+
"135": "calories",
|
150 |
+
"136": "current_location",
|
151 |
+
"137": "international_fees",
|
152 |
+
"138": "calculator",
|
153 |
+
"139": "definition",
|
154 |
+
"140": "next_holiday",
|
155 |
+
"141": "update_playlist",
|
156 |
+
"142": "mpg",
|
157 |
+
"143": "min_payment",
|
158 |
+
"144": "change_user_name",
|
159 |
+
"145": "restaurant_suggestion",
|
160 |
+
"146": "travel_notification",
|
161 |
+
"147": "cancel",
|
162 |
+
"148": "pto_used",
|
163 |
+
"149": "travel_suggestion",
|
164 |
+
"150": "change_volume"
|
165 |
+
},
|
166 |
+
"initializer_range": 0.02,
|
167 |
+
"intermediate_size": 4096,
|
168 |
+
"layer_norm_eps": 1e-05,
|
169 |
+
"max_position_embeddings": 514,
|
170 |
+
"model_type": "roberta",
|
171 |
+
"num_attention_heads": 16,
|
172 |
+
"num_hidden_layers": 24,
|
173 |
+
"pad_token_id": 1,
|
174 |
+
"position_embedding_type": "absolute",
|
175 |
+
"problem_type": "single_label_classification",
|
176 |
+
"torch_dtype": "float32",
|
177 |
+
"transformers_version": "4.34.1",
|
178 |
+
"type_vocab_size": 1,
|
179 |
+
"use_cache": true,
|
180 |
+
"vocab_size": 50265
|
181 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69137e7ab31f06c259e9b5699f10430f475a2353552c383cf461517cf507291a
|
3 |
+
size 1422194094
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4bdc42c6711b5b5ef53133c65350fa18c6b4cdd184e1b4f3a8690beec5b485b
|
3 |
+
size 4472
|