smerchi commited on
Commit
1b076d0
1 Parent(s): d5fbc0e

Model save

Browse files
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: SI2M-Lab/DarijaBERT
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: darija_test4
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # darija_test4
16
+
17
+ This model is a fine-tuned version of [SI2M-Lab/DarijaBERT](https://huggingface.co/SI2M-Lab/DarijaBERT) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2337
20
+ - Accuracy: 0.9402
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: 0.0003
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
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_ratio: 0.05
46
+ - num_epochs: 10
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 0.691 | 1.0 | 209 | 0.6551 | 0.6388 |
54
+ | 0.48 | 2.0 | 418 | 0.5391 | 0.8086 |
55
+ | 0.7983 | 3.0 | 627 | 0.6059 | 0.7105 |
56
+ | 0.7509 | 4.0 | 836 | 0.5645 | 0.7201 |
57
+ | 0.6031 | 5.0 | 1045 | 0.5616 | 0.7249 |
58
+ | 0.4155 | 6.0 | 1254 | 0.5425 | 0.8062 |
59
+ | 0.5307 | 7.0 | 1463 | 0.5160 | 0.7943 |
60
+ | 0.4064 | 8.0 | 1672 | 0.4301 | 0.8469 |
61
+ | 0.3983 | 9.0 | 1881 | 0.3789 | 0.8971 |
62
+ | 0.4016 | 10.0 | 2090 | 0.2337 | 0.9402 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - Transformers 4.42.4
68
+ - Pytorch 2.4.0+cu121
69
+ - Datasets 2.21.0
70
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "SI2M-Lab/DarijaBERT",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "cls_token": "[CLS]",
9
+ "do_lower_case": true,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "*6",
16
+ "1": "autre"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "*6": 0,
22
+ "autre": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "mask_token": "[MASK]",
26
+ "max_len": 128,
27
+ "max_position_embeddings": 512,
28
+ "model_max_length": 128,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token": "[PAD]",
33
+ "pad_token_id": 0,
34
+ "position_embedding_type": "absolute",
35
+ "problem_type": "single_label_classification",
36
+ "sep_token": "[SEP]",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.42.4",
39
+ "type_vocab_size": 2,
40
+ "unk_token": "[UNK]",
41
+ "use_cache": true,
42
+ "vocab_size": 80000
43
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a995be96ce9f3c99a6d06ba5d005e45667122ed811a2185057600f111bf9b338
3
+ size 589955072
runs/Aug29_13-28-50_0b1055bdc6cf/events.out.tfevents.1724938139.0b1055bdc6cf.735.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ed3039dd45eb83e4bd7a8e9aca5018a2dc2eb1d0b6b583c8dc1d8508f644b84
3
+ size 52745
runs/Aug29_13-28-50_0b1055bdc6cf/events.out.tfevents.1724938519.0b1055bdc6cf.735.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97ff7fe17cbb9a921df92b9996265102bf0d3c53cfa26f6f06427f3f36b9145d
3
+ size 411
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd9b471186e31452080d85043025a5b4a887c2612f2452545dead5d8b703dcac
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff