smerchi commited on
Commit
24cd2c7
1 Parent(s): 10ef04f

End of training

Browse files
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bert-base-multilingual-cased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ model-index:
10
+ - name: results
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
+ # results
18
+
19
+ This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0189
22
+ - Accuracy: 0.9981
23
+ - F1: 0.9981
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
+ - num_epochs: 10
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
+ | No log | 1.0 | 260 | 0.1823 | 0.9597 | 0.9601 |
55
+ | 0.1563 | 2.0 | 520 | 0.0255 | 0.9962 | 0.9962 |
56
+ | 0.1563 | 3.0 | 780 | 0.0359 | 0.9942 | 0.9943 |
57
+ | 0.0358 | 4.0 | 1040 | 0.0373 | 0.9942 | 0.9943 |
58
+ | 0.0358 | 5.0 | 1300 | 0.0135 | 0.9981 | 0.9981 |
59
+ | 0.0216 | 6.0 | 1560 | 0.0151 | 0.9981 | 0.9981 |
60
+ | 0.0216 | 7.0 | 1820 | 0.0177 | 0.9981 | 0.9981 |
61
+ | 0.0022 | 8.0 | 2080 | 0.0184 | 0.9981 | 0.9981 |
62
+ | 0.0022 | 9.0 | 2340 | 0.0187 | 0.9981 | 0.9981 |
63
+ | 0.0015 | 10.0 | 2600 | 0.0189 | 0.9981 | 0.9981 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.42.4
69
+ - Pytorch 2.4.0+cu121
70
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "problem_type": "single_label_classification",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.42.4",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 119547
32
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12ea990574978e23415d86b2e6fc076514cc05e95e042837b8a800d33b2e9b34
3
+ size 711443456
runs/Sep04_10-05-47_84e1b696ac09/events.out.tfevents.1725444349.84e1b696ac09.359.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec56a77ed596691409f2cd3962a4f82a835f94e5f354256669433c6dd6e7de7d
3
+ size 7963
runs/Sep04_10-05-47_84e1b696ac09/events.out.tfevents.1725444612.84e1b696ac09.359.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce4f00193a9f61e52a5f714852e9ce43f8eea875bb6c428005c5d029edc853ed
3
+ size 457
runs/Sep04_10-26-19_84e1b696ac09/events.out.tfevents.1725445580.84e1b696ac09.359.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c17918bb329995bb24752575b93b1d80559783e078d494c77b8b345005c0b1f
3
+ size 9862
runs/Sep04_10-26-19_84e1b696ac09/events.out.tfevents.1725446185.84e1b696ac09.359.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67899924b20b95dffb2fd19aa559d5a2cc552d082f6cdf384b07f58135122d77
3
+ size 457
runs/Sep04_11-18-42_84e1b696ac09/events.out.tfevents.1725448723.84e1b696ac09.359.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6eca5c12ee5072d08cf8880f1ee090c800d7dc9f32049ce23d1411376f6d4df
3
+ size 10073
runs/Sep04_11-18-42_84e1b696ac09/events.out.tfevents.1725449545.84e1b696ac09.359.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cbc72dfcc28140882cd1d60acefa8f1a57a85a85910b0feefd6c91ce4a0a781
3
+ size 457
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
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:dbb62e30687d4b5f55795a82b97acc54d6ac7c9c56ea905b034602c16ed07994
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff