AyoubChLin commited on
Commit
2e8aef3
·
verified ·
1 Parent(s): 827c0d6

Model save

Browse files
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: distilbert-base-multilingual-cased
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: companydocs-v2-doc-cls-distilmbert
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
+ # companydocs-v2-doc-cls-distilmbert
18
+
19
+ This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0005
22
+ - Accuracy: 1.0
23
+ - F1 Macro: 1.0
24
+ - F1 Weighted: 1.0
25
+ - Precision Macro: 1.0
26
+ - Recall Macro: 1.0
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 3e-05
46
+ - train_batch_size: 128
47
+ - eval_batch_size: 256
48
+ - seed: 42
49
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_steps: 202
52
+ - num_epochs: 1
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Weighted | Precision Macro | Recall Macro |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|:---------------:|:------------:|
58
+ | 0.0006 | 1.0 | 2028 | 0.0005 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 5.19.0
64
+ - Pytorch 2.8.0+cu129
65
+ - Datasets 5.1.0
66
+ - Tokenizers 0.23.3
best/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": null,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "dtype": "float32",
11
+ "eos_token_id": null,
12
+ "hidden_dim": 3072,
13
+ "id2label": {
14
+ "0": "account_statement",
15
+ "1": "credit_note",
16
+ "2": "employment_certificate",
17
+ "3": "goods_received_note",
18
+ "4": "inventory_report",
19
+ "5": "invoice",
20
+ "6": "packing_slip",
21
+ "7": "payslip",
22
+ "8": "purchase_order",
23
+ "9": "quote",
24
+ "10": "receipt",
25
+ "11": "shipping_order",
26
+ "12": "work_order"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "label2id": {
30
+ "account_statement": 0,
31
+ "credit_note": 1,
32
+ "employment_certificate": 2,
33
+ "goods_received_note": 3,
34
+ "inventory_report": 4,
35
+ "invoice": 5,
36
+ "packing_slip": 6,
37
+ "payslip": 7,
38
+ "purchase_order": 8,
39
+ "quote": 9,
40
+ "receipt": 10,
41
+ "shipping_order": 11,
42
+ "work_order": 12
43
+ },
44
+ "max_position_embeddings": 512,
45
+ "model_type": "distilbert",
46
+ "n_heads": 12,
47
+ "n_layers": 6,
48
+ "output_past": true,
49
+ "pad_token_id": 0,
50
+ "problem_type": "single_label_classification",
51
+ "qa_dropout": 0.1,
52
+ "seq_classif_dropout": 0.2,
53
+ "sinusoidal_pos_embds": false,
54
+ "tie_weights_": true,
55
+ "tie_word_embeddings": true,
56
+ "transformers_version": "5.19.0",
57
+ "use_cache": false,
58
+ "vocab_size": 119547
59
+ }
best/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7a5a51a047955a5fe55d97e6562f6cc9547aa37f7dfb6a3016cae312180900f
3
+ size 541351212
best/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
best/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
best/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c7b82b4f8bd706e0692560de4ccf91fa462af68076ea2df3f8454c4d8f4eaa7
3
+ size 5265