dadashzadeh commited on
Commit
d0dd3ff
1 Parent(s): 20bd515

End of training

Browse files
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: philschmid/tiny-bert-sst2-distilled
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: tiny-bert-Sentiment-persian
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # tiny-bert-Sentiment-persian
17
+
18
+ This model is a fine-tuned version of [philschmid/tiny-bert-sst2-distilled](https://huggingface.co/philschmid/tiny-bert-sst2-distilled) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.8137
21
+ - Accuracy: 0.6423
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-08
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 12
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
+ | 0.8627 | 1.0 | 3576 | 0.8142 | 0.6410 |
53
+ | 0.8555 | 2.0 | 7152 | 0.8140 | 0.6415 |
54
+ | 0.874 | 3.0 | 10728 | 0.8138 | 0.6419 |
55
+ | 0.8566 | 4.0 | 14304 | 0.8137 | 0.6423 |
56
+ | 0.8739 | 5.0 | 17880 | 0.8137 | 0.6423 |
57
+ | 0.8917 | 6.0 | 21456 | 0.8138 | 0.6432 |
58
+ | 0.866 | 7.0 | 25032 | 0.8137 | 0.6432 |
59
+ | 0.8613 | 8.0 | 28608 | 0.8137 | 0.6432 |
60
+ | 0.875 | 9.0 | 32184 | 0.8137 | 0.6441 |
61
+ | 0.8838 | 10.0 | 35760 | 0.8137 | 0.6441 |
62
+ | 0.8682 | 11.0 | 39336 | 0.8137 | 0.6441 |
63
+ | 0.8736 | 12.0 | 42912 | 0.8137 | 0.6441 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.41.2
69
+ - Pytorch 2.3.0+cu121
70
+ - Datasets 2.20.0
71
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "philschmid/tiny-bert-sst2-distilled",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive",
14
+ "2": "neutral"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 512,
18
+ "label2id": {
19
+ "negative": 0,
20
+ "neutral": 2,
21
+ "positive": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 2,
27
+ "num_hidden_layers": 2,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:652715ae4f3405c317651c7181a530f4a5013e9652f8b7d34e0558a71aa079ce
3
+ size 17549828
runs/Jul10_23-39-01_0acce8ee3931/events.out.tfevents.1720654745.0acce8ee3931.378.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c01f7e4c26d1d6448725ed61764ada55fa3c06e0c9ee43d2077b6d8695ba1b4
3
+ size 18325
runs/Jul10_23-49-37_0acce8ee3931/events.out.tfevents.1720655381.0acce8ee3931.378.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a08385eb3fd55e3d19e8cc18d8dc51d7a60b8af3453076dde7e87f4a94889f0
3
+ size 27496
runs/Jul10_23-49-37_0acce8ee3931/events.out.tfevents.1720656108.0acce8ee3931.378.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:289219b3f80515cf926d4b26a65e98c1747331b178973e7b40d24e9d188f4201
3
+ size 417
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 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "stride": 0,
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "[UNK]"
61
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0d23684fd872c3b0b10a1f8ec73e35efc5b6ea439382747e5afadebcc7b4cd
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff