alicore commited on
Commit
3242c8a
1 Parent(s): c0459fc

End of training

Browse files
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: PartAI/TookaBERT-Base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: my_model
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # my_model
20
+
21
+ This model is a fine-tuned version of [PartAI/TookaBERT-Base](https://huggingface.co/PartAI/TookaBERT-Base) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 1.7588
24
+ - Precision: 0.4745
25
+ - Recall: 0.1738
26
+ - F1: 0.2544
27
+ - Accuracy: 0.6770
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 2e-05
47
+ - train_batch_size: 1
48
+ - eval_batch_size: 1
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 3
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 1.0 | 19 | 2.2673 | 0.3636 | 0.0214 | 0.0404 | 0.6355 |
59
+ | No log | 2.0 | 38 | 1.9224 | 0.3710 | 0.0615 | 0.1055 | 0.6459 |
60
+ | No log | 3.0 | 57 | 1.7588 | 0.4745 | 0.1738 | 0.2544 | 0.6770 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.42.4
66
+ - Pytorch 2.3.1+cu121
67
+ - Datasets 2.20.0
68
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PartAI/TookaBERT-Base",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 3,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-Age_Group",
16
+ "2": "B-Barcode",
17
+ "3": "B-Benefits",
18
+ "4": "B-Brand",
19
+ "5": "B-Case_Material",
20
+ "6": "B-Color",
21
+ "7": "B-Country_of_Origin",
22
+ "8": "B-Durability",
23
+ "9": "B-Feature",
24
+ "10": "B-Final_Result",
25
+ "11": "B-Flat_and_Angled_Shape",
26
+ "12": "B-Form",
27
+ "13": "B-Fragrance",
28
+ "14": "B-Ideal_for_Eyebrow_Shadows_and_Natural_Designs",
29
+ "15": "B-Ingredients",
30
+ "16": "B-Manufacturer",
31
+ "17": "B-Model",
32
+ "18": "B-Packaging_Type",
33
+ "19": "B-Performance",
34
+ "20": "B-Price",
35
+ "21": "B-Product_Code",
36
+ "22": "B-Product_Name",
37
+ "23": "B-Quantity",
38
+ "24": "B-Size",
39
+ "25": "B-Skin_Type",
40
+ "26": "B-Type",
41
+ "27": "B-Usage",
42
+ "28": "B-Volume",
43
+ "29": "B-\u0628\u0627\u0631\u06a9\u062f",
44
+ "30": "B-\u0628\u0627\u0641\u062a",
45
+ "31": "B-\u062c\u0646\u0633\u06cc\u062a",
46
+ "32": "B-\u062d\u062c\u0645",
47
+ "33": "B-\u0633\u0646",
48
+ "34": "B-\u0636\u062f_\u0622\u0628",
49
+ "35": "B-\u0641\u0627\u0642\u062f_\u0686\u0631\u0628\u06cc",
50
+ "36": "B-\u0646\u062a\u06cc\u062c\u0647_\u0646\u0647\u0627\u06cc\u06cc",
51
+ "37": "B-\u0646\u0648\u0639_\u0645\u062d\u0641\u0638\u0647",
52
+ "38": "B-\u0646\u0648\u0639_\u067e\u0648\u0633\u062a",
53
+ "39": "B-\u0648\u06cc\u0698\u06af\u06cc",
54
+ "40": "B-\u06a9\u0627\u0631\u0627\u06cc\u06cc_\u0645\u062d\u0635\u0648\u0644",
55
+ "41": "B-\u06a9\u062f_\u0645\u062d\u0635\u0648\u0644",
56
+ "42": "B-\u06a9\u0634\u0648\u0631_\u0633\u0627\u0632\u0646\u062f\u0647",
57
+ "43": "I-Additional_Information",
58
+ "44": "I-Benefits",
59
+ "45": "I-Brand",
60
+ "46": "I-Feature",
61
+ "47": "I-Flat_and_Angled_Shape",
62
+ "48": "I-Form",
63
+ "49": "I-Fragrance",
64
+ "50": "I-Ideal_for_Eyebrow_Shadows_and_Natural_Designs",
65
+ "51": "I-Ingredients",
66
+ "52": "I-Performance",
67
+ "53": "I-Price",
68
+ "54": "I-Product_Name",
69
+ "55": "I-Quantity",
70
+ "56": "I-Skin_Type",
71
+ "57": "I-Usage",
72
+ "58": "I-Volume",
73
+ "59": "I-\u062c\u0646\u0633\u06cc\u062a",
74
+ "60": "I-\u062d\u062c\u0645",
75
+ "61": "I-\u0646\u0648\u0639_\u0645\u062d\u0641\u0638\u0647",
76
+ "62": "I-\u0646\u0648\u0639_\u067e\u0648\u0633\u062a",
77
+ "63": "I-\u0648\u06cc\u0698\u06af\u06cc",
78
+ "64": "I-\u06a9\u0627\u0631\u0627\u06cc\u06cc_\u0645\u062d\u0635\u0648\u0644"
79
+ },
80
+ "initializer_range": 0.02,
81
+ "intermediate_size": 3072,
82
+ "label2id": {
83
+ "B-Age_Group": 1,
84
+ "B-Barcode": 2,
85
+ "B-Benefits": 3,
86
+ "B-Brand": 4,
87
+ "B-Case_Material": 5,
88
+ "B-Color": 6,
89
+ "B-Country_of_Origin": 7,
90
+ "B-Durability": 8,
91
+ "B-Feature": 9,
92
+ "B-Final_Result": 10,
93
+ "B-Flat_and_Angled_Shape": 11,
94
+ "B-Form": 12,
95
+ "B-Fragrance": 13,
96
+ "B-Ideal_for_Eyebrow_Shadows_and_Natural_Designs": 14,
97
+ "B-Ingredients": 15,
98
+ "B-Manufacturer": 16,
99
+ "B-Model": 17,
100
+ "B-Packaging_Type": 18,
101
+ "B-Performance": 19,
102
+ "B-Price": 20,
103
+ "B-Product_Code": 21,
104
+ "B-Product_Name": 22,
105
+ "B-Quantity": 23,
106
+ "B-Size": 24,
107
+ "B-Skin_Type": 25,
108
+ "B-Type": 26,
109
+ "B-Usage": 27,
110
+ "B-Volume": 28,
111
+ "B-\u0628\u0627\u0631\u06a9\u062f": 29,
112
+ "B-\u0628\u0627\u0641\u062a": 30,
113
+ "B-\u062c\u0646\u0633\u06cc\u062a": 31,
114
+ "B-\u062d\u062c\u0645": 32,
115
+ "B-\u0633\u0646": 33,
116
+ "B-\u0636\u062f_\u0622\u0628": 34,
117
+ "B-\u0641\u0627\u0642\u062f_\u0686\u0631\u0628\u06cc": 35,
118
+ "B-\u0646\u062a\u06cc\u062c\u0647_\u0646\u0647\u0627\u06cc\u06cc": 36,
119
+ "B-\u0646\u0648\u0639_\u0645\u062d\u0641\u0638\u0647": 37,
120
+ "B-\u0646\u0648\u0639_\u067e\u0648\u0633\u062a": 38,
121
+ "B-\u0648\u06cc\u0698\u06af\u06cc": 39,
122
+ "B-\u06a9\u0627\u0631\u0627\u06cc\u06cc_\u0645\u062d\u0635\u0648\u0644": 40,
123
+ "B-\u06a9\u062f_\u0645\u062d\u0635\u0648\u0644": 41,
124
+ "B-\u06a9\u0634\u0648\u0631_\u0633\u0627\u0632\u0646\u062f\u0647": 42,
125
+ "I-Additional_Information": 43,
126
+ "I-Benefits": 44,
127
+ "I-Brand": 45,
128
+ "I-Feature": 46,
129
+ "I-Flat_and_Angled_Shape": 47,
130
+ "I-Form": 48,
131
+ "I-Fragrance": 49,
132
+ "I-Ideal_for_Eyebrow_Shadows_and_Natural_Designs": 50,
133
+ "I-Ingredients": 51,
134
+ "I-Performance": 52,
135
+ "I-Price": 53,
136
+ "I-Product_Name": 54,
137
+ "I-Quantity": 55,
138
+ "I-Skin_Type": 56,
139
+ "I-Usage": 57,
140
+ "I-Volume": 58,
141
+ "I-\u062c\u0646\u0633\u06cc\u062a": 59,
142
+ "I-\u062d\u062c\u0645": 60,
143
+ "I-\u0646\u0648\u0639_\u0645\u062d\u0641\u0638\u0647": 61,
144
+ "I-\u0646\u0648\u0639_\u067e\u0648\u0633\u062a": 62,
145
+ "I-\u0648\u06cc\u0698\u06af\u06cc": 63,
146
+ "I-\u06a9\u0627\u0631\u0627\u06cc\u06cc_\u0645\u062d\u0635\u0648\u0644": 64,
147
+ "O": 0
148
+ },
149
+ "layer_norm_eps": 1e-12,
150
+ "max_position_embeddings": 512,
151
+ "model_type": "bert",
152
+ "num_attention_heads": 12,
153
+ "num_hidden_layers": 12,
154
+ "pad_token_id": 0,
155
+ "position_embedding_type": "absolute",
156
+ "torch_dtype": "float32",
157
+ "transformers_version": "4.42.4",
158
+ "type_vocab_size": 2,
159
+ "use_cache": true,
160
+ "vocab_size": 48000
161
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1377e21d4256d795a5f5557ad8a21b653a9b3420dc00bdd55981f3e73e156a1
3
+ size 489482308
runs/Aug06_12-48-35_9eec24a54a61/events.out.tfevents.1722948516.9eec24a54a61.479.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7343875e5d56935726061e7da00dda73ce98e41d61f9f5f276f349be49ac65b
3
+ size 9325
runs/Aug06_12-52-13_9eec24a54a61/events.out.tfevents.1722948733.9eec24a54a61.479.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90deb9fefccf9fa534813942ebac61110648a1b0de009fd49f37d2c3ef68346
3
+ size 11062
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "</s>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "<unk>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "</s>",
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": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "eos_token": "</s>",
47
+ "mask_token": "<mask>",
48
+ "max_length": null,
49
+ "model_input_names": [
50
+ "input_ids",
51
+ "attention_mask"
52
+ ],
53
+ "model_max_length": 512,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "<pad>",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
+ "sep_token": "</s>",
59
+ "tokenizer_class": "PreTrainedTokenizerFast",
60
+ "truncation_side": "right",
61
+ "unk_token": "<unk>"
62
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4225edf12a7e80151cba6b8a54429997daa967adb963f5ea6babaecd87da401a
3
+ size 5112