dadashzadeh commited on
Commit
7e6c330
1 Parent(s): 2a9b3c2

End of training

Browse files
README.md CHANGED
@@ -1,72 +1,74 @@
1
- ---
2
- license: apache-2.0
3
- base_model: dadashzadeh/tiny-bert-Sentiment-persian
4
- tags:
5
- - generated_from_trainer
6
- metrics:
7
- - accuracy
8
- model-index:
9
- - name: tiny-bert-Sentiment-persian
10
- results: []
11
- language:
12
- - fa
13
- pipeline_tag: text-classification
14
- datasets:
15
- - hezarai/sentiment-dksf
16
- ---
17
-
18
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
19
- should probably proofread and complete it, then remove this comment. -->
20
-
21
- # tiny-bert-Sentiment-persian
22
-
23
- This model is a fine-tuned version of [dadashzadeh/tiny-bert-Sentiment-persian](https://huggingface.co/dadashzadeh/tiny-bert-Sentiment-persian) on an unknown dataset.
24
- It achieves the following results on the evaluation set:
25
- - Loss: 1.1799
26
- - Accuracy: 0.7313
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: 2e-05
46
- - train_batch_size: 1
47
- - eval_batch_size: 1
48
- - seed: 45
49
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
- - lr_scheduler_type: linear
51
- - num_epochs: 8
52
-
53
- ### Training results
54
-
55
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
- |:-------------:|:-----:|:------:|:---------------:|:--------:|
57
- | 1.3201 | 1.0 | 28602 | 1.1799 | 0.7313 |
58
- | 1.1258 | 2.0 | 57204 | 1.3399 | 0.7205 |
59
- | 1.19 | 3.0 | 85806 | 1.2192 | 0.7516 |
60
- | 1.1178 | 4.0 | 114408 | 1.2138 | 0.7594 |
61
- | 1.1292 | 5.0 | 143010 | 1.2117 | 0.7611 |
62
- | 1.0537 | 6.0 | 171612 | 1.3268 | 0.7413 |
63
- | 1.0113 | 7.0 | 200214 | 1.3229 | 0.7460 |
64
- | 1.1022 | 8.0 | 228816 | 1.2681 | 0.7525 |
65
-
66
-
67
- ### Framework versions
68
-
69
- - Transformers 4.41.2
70
- - Pytorch 2.3.0+cu121
71
- - Datasets 2.20.0
72
- - Tokenizers 0.19.1
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: dadashzadeh/tiny-bert-Sentiment-persian
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 [dadashzadeh/tiny-bert-Sentiment-persian](https://huggingface.co/dadashzadeh/tiny-bert-Sentiment-persian) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6553
21
+ - Accuracy: 0.7611
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: 2e-05
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 2
43
+ - seed: 45
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 8
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 12
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-------:|:-----:|:---------------:|:--------:|
55
+ | 0.6157 | 0.9999 | 3575 | 0.6703 | 0.7577 |
56
+ | 0.5833 | 1.9999 | 7150 | 0.7599 | 0.7171 |
57
+ | 0.6015 | 2.9998 | 10725 | 0.6824 | 0.7590 |
58
+ | 0.5601 | 4.0 | 14301 | 0.6780 | 0.7533 |
59
+ | 0.5699 | 4.9999 | 17876 | 0.7071 | 0.7356 |
60
+ | 0.5519 | 5.9999 | 21451 | 0.6931 | 0.7391 |
61
+ | 0.5436 | 6.9998 | 25026 | 0.6736 | 0.7629 |
62
+ | 0.5482 | 8.0 | 28602 | 0.6567 | 0.7685 |
63
+ | 0.5367 | 8.9999 | 32177 | 0.6553 | 0.7611 |
64
+ | 0.5399 | 9.9999 | 35752 | 0.6691 | 0.7616 |
65
+ | 0.5112 | 10.9998 | 39327 | 0.6785 | 0.7564 |
66
+ | 0.5113 | 11.9992 | 42900 | 0.6773 | 0.7572 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.40.2
72
+ - Pytorch 2.2.2+cu118
73
+ - Datasets 2.19.1
74
+ - Tokenizers 0.19.1
config.json CHANGED
@@ -1,36 +1,36 @@
1
- {
2
- "_name_or_path": "dadashzadeh/tiny-bert-Sentiment-persian",
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
- }
 
1
+ {
2
+ "_name_or_path": "dadashzadeh/tiny-bert-Sentiment-persian",
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": "4.40.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41c571d5293d482935a24f34f5a33681b2a71ce913503c392e931772f8992667
3
  size 17549828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ef4528420a026802cd2e895670e161d3040cf4e55ddfd853d0cabda99a7fc9
3
  size 17549828
runs/Jul12_00-15-57_DESKTOP-LR846SV/events.out.tfevents.1720730759.DESKTOP-LR846SV.20864.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aba2f5e8280a5d8c526642c86ee8ada49d41eb4ef75bdd1c0320ca8e727e8aa5
3
+ size 18788
runs/Jul12_00-25-25_DESKTOP-LR846SV/events.out.tfevents.1720731341.DESKTOP-LR846SV.20864.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b299ea485e8ce54232a3ca81a44fe4244685b1af4d1797a7fa06fc66ad548ef
3
+ size 5568
runs/Jul12_00-27-03_DESKTOP-LR846SV/events.out.tfevents.1720731425.DESKTOP-LR846SV.20864.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6391cd1ad3aab3e4e3318f53d106f50cae17ad4950ee748b2fbf7387d932477b
3
+ size 27366
runs/Jul12_00-27-03_DESKTOP-LR846SV/events.out.tfevents.1720732953.DESKTOP-LR846SV.20864.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35971d01928706977aafb4d679699e6373f03b7be6ed1dffbb4ffed2fceb42d8
3
+ size 417
special_tokens_map.json CHANGED
@@ -1,37 +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
- }
 
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_config.json CHANGED
@@ -1,61 +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
- }
 
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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51e39a41f4f4bdc1121d3489185bbf82cdda2d455c729fe00d356ea1ba78a78b
3
- size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc6d781bd06086b07c62ae8d94dad59bd177e1067740d9126154824f56f8d12
3
+ size 5048