End of training
Browse files- README.md +83 -0
- config.json +63 -0
- emissions.csv +2 -0
- model.safetensors +3 -0
- runs/Feb13_22-36-37_78ddadfe6cfb/events.out.tfevents.1707863822.78ddadfe6cfb.1216.0 +3 -0
- runs/Feb13_22-56-48_78ddadfe6cfb/events.out.tfevents.1707865023.78ddadfe6cfb.1216.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: BAAI/bge-base-en-v1.5
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: IKI-Category-multilabel_bge
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# IKI-Category-multilabel_bge
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.4541
|
19 |
+
- Precision-micro: 0.75
|
20 |
+
- Precision-samples: 0.7708
|
21 |
+
- Precision-weighted: 0.7517
|
22 |
+
- Recall-micro: 0.7880
|
23 |
+
- Recall-samples: 0.7858
|
24 |
+
- Recall-weighted: 0.7880
|
25 |
+
- F1-micro: 0.7685
|
26 |
+
- F1-samples: 0.7537
|
27 |
+
- F1-weighted: 0.7615
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 4.5e-05
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 8
|
49 |
+
- seed: 42
|
50 |
+
- gradient_accumulation_steps: 2
|
51 |
+
- total_train_batch_size: 16
|
52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
53 |
+
- lr_scheduler_type: linear
|
54 |
+
- lr_scheduler_warmup_steps: 200
|
55 |
+
- num_epochs: 15
|
56 |
+
|
57 |
+
### Training results
|
58 |
+
|
59 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision-micro | Precision-samples | Precision-weighted | Recall-micro | Recall-samples | Recall-weighted | F1-micro | F1-samples | F1-weighted |
|
60 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------------:|:-----------------:|:------------------:|:------------:|:--------------:|:---------------:|:--------:|:----------:|:-----------:|
|
61 |
+
| 0.8999 | 0.99 | 94 | 0.8742 | 0.3889 | 0.0272 | 0.1308 | 0.0169 | 0.0188 | 0.0169 | 0.0323 | 0.0202 | 0.0280 |
|
62 |
+
| 0.7377 | 2.0 | 189 | 0.6770 | 0.4727 | 0.4996 | 0.5333 | 0.5639 | 0.5782 | 0.5639 | 0.5143 | 0.4883 | 0.4998 |
|
63 |
+
| 0.5582 | 2.99 | 283 | 0.5552 | 0.5111 | 0.5585 | 0.5685 | 0.7229 | 0.7357 | 0.7229 | 0.5988 | 0.5959 | 0.6175 |
|
64 |
+
| 0.3943 | 4.0 | 378 | 0.4713 | 0.5616 | 0.6397 | 0.5869 | 0.7904 | 0.8071 | 0.7904 | 0.6567 | 0.6761 | 0.6611 |
|
65 |
+
| 0.2883 | 4.99 | 472 | 0.4555 | 0.6384 | 0.6969 | 0.6444 | 0.7446 | 0.7641 | 0.7446 | 0.6874 | 0.6901 | 0.6854 |
|
66 |
+
| 0.2112 | 6.0 | 567 | 0.4459 | 0.6443 | 0.6968 | 0.6637 | 0.7855 | 0.7942 | 0.7855 | 0.7079 | 0.7123 | 0.7068 |
|
67 |
+
| 0.1608 | 6.99 | 661 | 0.4212 | 0.6508 | 0.7071 | 0.6586 | 0.7904 | 0.7931 | 0.7904 | 0.7138 | 0.7161 | 0.7116 |
|
68 |
+
| 0.1247 | 8.0 | 756 | 0.4177 | 0.6633 | 0.7145 | 0.6650 | 0.7976 | 0.8006 | 0.7976 | 0.7243 | 0.7193 | 0.7195 |
|
69 |
+
| 0.1031 | 8.99 | 850 | 0.4435 | 0.7277 | 0.7523 | 0.7306 | 0.7855 | 0.7875 | 0.7855 | 0.7555 | 0.7425 | 0.7487 |
|
70 |
+
| 0.0851 | 10.0 | 945 | 0.4522 | 0.7380 | 0.7623 | 0.7465 | 0.7807 | 0.7795 | 0.7807 | 0.7588 | 0.7432 | 0.7516 |
|
71 |
+
| 0.074 | 10.99 | 1039 | 0.4548 | 0.7359 | 0.7663 | 0.7368 | 0.7855 | 0.7910 | 0.7855 | 0.7599 | 0.7490 | 0.7521 |
|
72 |
+
| 0.0648 | 12.0 | 1134 | 0.4430 | 0.7425 | 0.7676 | 0.7437 | 0.7783 | 0.7781 | 0.7783 | 0.76 | 0.7461 | 0.7540 |
|
73 |
+
| 0.0605 | 12.99 | 1228 | 0.4478 | 0.7366 | 0.7651 | 0.7379 | 0.7952 | 0.7948 | 0.7952 | 0.7648 | 0.7545 | 0.7579 |
|
74 |
+
| 0.0566 | 14.0 | 1323 | 0.4574 | 0.7506 | 0.7708 | 0.7519 | 0.7904 | 0.7893 | 0.7904 | 0.7700 | 0.7546 | 0.7625 |
|
75 |
+
| 0.0546 | 14.92 | 1410 | 0.4541 | 0.75 | 0.7708 | 0.7517 | 0.7880 | 0.7858 | 0.7880 | 0.7685 | 0.7537 | 0.7615 |
|
76 |
+
|
77 |
+
|
78 |
+
### Framework versions
|
79 |
+
|
80 |
+
- Transformers 4.35.2
|
81 |
+
- Pytorch 2.1.0+cu121
|
82 |
+
- Datasets 2.17.0
|
83 |
+
- Tokenizers 0.15.1
|
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BAAI/bge-base-en-v1.5",
|
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": "Active mobility",
|
14 |
+
"1": "Alternative fuels",
|
15 |
+
"2": "Aviation improvements",
|
16 |
+
"3": "Comprehensive transport planning",
|
17 |
+
"4": "Digital solutions",
|
18 |
+
"5": "Economic instruments",
|
19 |
+
"6": "Education and behavioral change",
|
20 |
+
"7": "Electric mobility",
|
21 |
+
"8": "Freight efficiency improvements",
|
22 |
+
"9": "Improve infrastructure",
|
23 |
+
"10": "Land use",
|
24 |
+
"11": "Other Transport Category",
|
25 |
+
"12": "Public transport improvement",
|
26 |
+
"13": "Shipping improvements",
|
27 |
+
"14": "Transport demand management",
|
28 |
+
"15": "Vehicle improvements"
|
29 |
+
},
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 3072,
|
32 |
+
"label2id": {
|
33 |
+
"Active mobility": 0,
|
34 |
+
"Alternative fuels": 1,
|
35 |
+
"Aviation improvements": 2,
|
36 |
+
"Comprehensive transport planning": 3,
|
37 |
+
"Digital solutions": 4,
|
38 |
+
"Economic instruments": 5,
|
39 |
+
"Education and behavioral change": 6,
|
40 |
+
"Electric mobility": 7,
|
41 |
+
"Freight efficiency improvements": 8,
|
42 |
+
"Improve infrastructure": 9,
|
43 |
+
"Land use": 10,
|
44 |
+
"Other Transport Category": 11,
|
45 |
+
"Public transport improvement": 12,
|
46 |
+
"Shipping improvements": 13,
|
47 |
+
"Transport demand management": 14,
|
48 |
+
"Vehicle improvements": 15
|
49 |
+
},
|
50 |
+
"layer_norm_eps": 1e-12,
|
51 |
+
"max_position_embeddings": 512,
|
52 |
+
"model_type": "bert",
|
53 |
+
"num_attention_heads": 12,
|
54 |
+
"num_hidden_layers": 12,
|
55 |
+
"pad_token_id": 0,
|
56 |
+
"position_embedding_type": "absolute",
|
57 |
+
"problem_type": "multi_label_classification",
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.35.2",
|
60 |
+
"type_vocab_size": 2,
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 30522
|
63 |
+
}
|
emissions.csv
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
2 |
+
2024-02-13T23:25:59,codecarbon,fe3751ff-c8bd-4ab3-aab4-d58b1339aedd,1735.1764719486237,0.02489628814029973,1.434798623816107e-05,42.5,40.35687700653838,4.753046035766602,0.020473451719350298,0.032251047189706,0.002280241278595821,0.055004740187652126,United States,USA,iowa,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.4,2,Intel(R) Xeon(R) CPU @ 2.30GHz,1,1 x Tesla T4,-95.8517,41.2591,12.674789428710938,machine,N,1.0
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a279b1d170f46e65206193462fac5739d181aab947d8b840b3ca2971917c4aaf
|
3 |
+
size 438001712
|
runs/Feb13_22-36-37_78ddadfe6cfb/events.out.tfevents.1707863822.78ddadfe6cfb.1216.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29dc26e220c770d850856b9a6852e0b93a4d80c6452edfde4ec62354dd0232af
|
3 |
+
size 19321
|
runs/Feb13_22-56-48_78ddadfe6cfb/events.out.tfevents.1707865023.78ddadfe6cfb.1216.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5db1013d3eab8bca1bcc95ede9123191c8f8cc2b4cc34eb50d0b9d8359287f38
|
3 |
+
size 19963
|
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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"problem_type": "multi_label_classification",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": null,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a74e43b8ffa62eedb4b87c874e2814de7870fcf7e9802c9741ec5ace21dcd292
|
3 |
+
size 4600
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|