Model save
Browse files- README.md +67 -0
- all_results.json +9 -0
- config.json +132 -0
- eval_results.json +9 -0
- logs/events.out.tfevents.1723542185.pop-os.482473.0 +3 -0
- logs/events.out.tfevents.1723542389.pop-os.497642.0 +3 -0
- logs/events.out.tfevents.1723572123.pop-os.2168794.0 +3 -0
- logs/events.out.tfevents.1723656174.pop-os.2168794.1 +3 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
model-index:
|
10 |
+
- name: para-multi-finetuning
|
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 |
+
# para-multi-finetuning
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.7937
|
22 |
+
- Accuracy: 0.8072
|
23 |
+
- F1: 0.8054
|
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: 5e-05
|
43 |
+
- train_batch_size: 8
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 500
|
49 |
+
- num_epochs: 5
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
54 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|
|
55 |
+
| 1.0969 | 1.0 | 65741 | 0.9992 | 0.7559 | 0.7478 |
|
56 |
+
| 0.7092 | 2.0 | 131482 | 0.8674 | 0.7820 | 0.7787 |
|
57 |
+
| 0.4966 | 3.0 | 197223 | 0.8120 | 0.7975 | 0.7927 |
|
58 |
+
| 0.739 | 4.0 | 262964 | 0.7937 | 0.8072 | 0.8054 |
|
59 |
+
| 0.4707 | 5.0 | 328705 | 0.8312 | 0.8109 | 0.8089 |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- Transformers 4.43.3
|
65 |
+
- Pytorch 2.4.0+cu121
|
66 |
+
- Datasets 2.20.0
|
67 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.8072491215260348,
|
4 |
+
"eval_f1": 0.8053783422859715,
|
5 |
+
"eval_loss": 0.7936691641807556,
|
6 |
+
"eval_runtime": 460.123,
|
7 |
+
"eval_samples_per_second": 380.994,
|
8 |
+
"eval_steps_per_second": 47.624
|
9 |
+
}
|
config.json
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "auto_and_transport",
|
16 |
+
"1": "auto_and_transport/car_rental",
|
17 |
+
"2": "auto_and_transport/gas_and_fuel",
|
18 |
+
"3": "auto_and_transport/parking",
|
19 |
+
"4": "auto_and_transport/public_transportation",
|
20 |
+
"5": "auto_and_transport/service_and_parts",
|
21 |
+
"6": "auto_and_transport/taxi",
|
22 |
+
"7": "bills_and_utilities",
|
23 |
+
"8": "bills_and_utilities/internet",
|
24 |
+
"9": "bills_and_utilities/phone",
|
25 |
+
"10": "bills_and_utilities/television",
|
26 |
+
"11": "bills_and_utilities/utilities",
|
27 |
+
"12": "business_services",
|
28 |
+
"13": "business_services/accounting",
|
29 |
+
"14": "business_services/advertising",
|
30 |
+
"15": "business_services/office_supplies",
|
31 |
+
"16": "business_services/shipping",
|
32 |
+
"17": "education",
|
33 |
+
"18": "education/books_and_supplies",
|
34 |
+
"19": "education/student_loan",
|
35 |
+
"20": "education/tuition",
|
36 |
+
"21": "entertainment",
|
37 |
+
"22": "entertainment/amusement",
|
38 |
+
"23": "entertainment/arts",
|
39 |
+
"24": "entertainment/gambling",
|
40 |
+
"25": "entertainment/games",
|
41 |
+
"26": "entertainment/movies_and_music",
|
42 |
+
"27": "entertainment/newspapers_and_magazines",
|
43 |
+
"28": "fees_and_charges",
|
44 |
+
"29": "fees_and_charges/bankruptcy",
|
45 |
+
"30": "fees_and_charges/collections_agency",
|
46 |
+
"31": "fees_and_charges/loans",
|
47 |
+
"32": "fees_and_charges/loans/auto",
|
48 |
+
"33": "fees_and_charges/loans/high_cost",
|
49 |
+
"34": "fees_and_charges/loans/pawn",
|
50 |
+
"35": "fees_and_charges/loans/payday",
|
51 |
+
"36": "fees_and_charges/provider_fee",
|
52 |
+
"37": "fees_and_charges/provider_fee/penalty",
|
53 |
+
"38": "fees_and_charges/provider_fee/penalty/nsf",
|
54 |
+
"39": "fees_and_charges/provider_fee/penalty/overdraft",
|
55 |
+
"40": "fees_and_charges/provider_fee/penalty/stop_payment",
|
56 |
+
"41": "fees_and_charges/provider_fee/recurring",
|
57 |
+
"42": "fees_and_charges/service_fee",
|
58 |
+
"43": "fees_and_charges/service_fee/laundromat",
|
59 |
+
"44": "fees_and_charges/taxes",
|
60 |
+
"45": "fees_and_charges/union",
|
61 |
+
"46": "food_and_dining",
|
62 |
+
"47": "food_and_dining/alcohol_and_bars",
|
63 |
+
"48": "food_and_dining/cafes_and_restaurants",
|
64 |
+
"49": "food_and_dining/groceries",
|
65 |
+
"50": "food_and_dining/marijuana",
|
66 |
+
"51": "gifts_and_donations",
|
67 |
+
"52": "gifts_and_donations/charity",
|
68 |
+
"53": "gifts_and_donations/gifts",
|
69 |
+
"54": "health_and_fitness",
|
70 |
+
"55": "health_and_fitness/doctor",
|
71 |
+
"56": "health_and_fitness/personal_care",
|
72 |
+
"57": "health_and_fitness/pharmacy",
|
73 |
+
"58": "health_and_fitness/sports",
|
74 |
+
"59": "health_and_fitness/wellness",
|
75 |
+
"60": "home",
|
76 |
+
"61": "home/home_improvement",
|
77 |
+
"62": "home/home_services",
|
78 |
+
"63": "home/home_supplies",
|
79 |
+
"64": "home/mortgage",
|
80 |
+
"65": "home/mortgage_and_rent",
|
81 |
+
"66": "home/rent",
|
82 |
+
"67": "income",
|
83 |
+
"68": "income/bonus",
|
84 |
+
"69": "income/child_support",
|
85 |
+
"70": "income/government",
|
86 |
+
"71": "income/investment_income",
|
87 |
+
"72": "income/paycheck",
|
88 |
+
"73": "income/pension",
|
89 |
+
"74": "insurance",
|
90 |
+
"75": "insurance/car_insurance",
|
91 |
+
"76": "insurance/health_insurance",
|
92 |
+
"77": "insurance/life_insurance",
|
93 |
+
"78": "insurance/property_insurance",
|
94 |
+
"79": "kids",
|
95 |
+
"80": "kids/baby_supplies",
|
96 |
+
"81": "kids/babysitter_and_daycare",
|
97 |
+
"82": "kids/toys",
|
98 |
+
"83": "pets",
|
99 |
+
"84": "pets/pet_food_and_supplies",
|
100 |
+
"85": "pets/pet_grooming",
|
101 |
+
"86": "pets/veterinary",
|
102 |
+
"87": "shopping",
|
103 |
+
"88": "shopping/clothing",
|
104 |
+
"89": "shopping/electronics_and_software",
|
105 |
+
"90": "shopping/sporting_goods",
|
106 |
+
"91": "transfer",
|
107 |
+
"92": "transfer/atm",
|
108 |
+
"93": "transfer/credit_card",
|
109 |
+
"94": "transfer/email",
|
110 |
+
"95": "transfer/wire",
|
111 |
+
"96": "travel",
|
112 |
+
"97": "travel/hotel",
|
113 |
+
"98": "travel/transportation",
|
114 |
+
"99": "travel/vacation"
|
115 |
+
},
|
116 |
+
"initializer_range": 0.02,
|
117 |
+
"intermediate_size": 3072,
|
118 |
+
"layer_norm_eps": 1e-05,
|
119 |
+
"max_position_embeddings": 514,
|
120 |
+
"model_type": "xlm-roberta",
|
121 |
+
"num_attention_heads": 12,
|
122 |
+
"num_hidden_layers": 12,
|
123 |
+
"output_past": true,
|
124 |
+
"pad_token_id": 1,
|
125 |
+
"position_embedding_type": "absolute",
|
126 |
+
"problem_type": "single_label_classification",
|
127 |
+
"torch_dtype": "float32",
|
128 |
+
"transformers_version": "4.43.3",
|
129 |
+
"type_vocab_size": 1,
|
130 |
+
"use_cache": true,
|
131 |
+
"vocab_size": 250002
|
132 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.8072491215260348,
|
4 |
+
"eval_f1": 0.8053783422859715,
|
5 |
+
"eval_loss": 0.7936691641807556,
|
6 |
+
"eval_runtime": 460.123,
|
7 |
+
"eval_samples_per_second": 380.994,
|
8 |
+
"eval_steps_per_second": 47.624
|
9 |
+
}
|
logs/events.out.tfevents.1723542185.pop-os.482473.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87466d2c37327c0ffe5b1e4cbc399c8ab60f226b488931006c76a89140cae70b
|
3 |
+
size 8280
|
logs/events.out.tfevents.1723542389.pop-os.497642.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab83aa1d7faeddcd534447da47505c474c76ee53f49ab60fcffe6ccee02162d3
|
3 |
+
size 4004047
|
logs/events.out.tfevents.1723572123.pop-os.2168794.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b7d060cb8d92fefd6c0ce724d36909997b6b2d2376542969b93dc3c929baaf3
|
3 |
+
size 7071435
|
logs/events.out.tfevents.1723656174.pop-os.2168794.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4aaa31116ce653ce98e3260bbc5f55d2a57dd7bc58283674daeaa4b49a7bb306
|
3 |
+
size 464
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e30963d6734eb68852fc990259522829bd4c07447a845e46472679e30471ad39
|
3 |
+
size 1112506464
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67bb42d498b9fc9d45bb6a1ef61e4593d6f698799d8c4666ad6f5f7aa316f7a2
|
3 |
+
size 5240
|