Hugging Face's logo

hypo69
/
my_model_from_existing_datasets

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
hypo69 commited on
Commit
5187026
·
verified ·
1 Parent(s): 30c0cb3

Training in progress, step 6

Browse files
Files changed (20) hide show
  1. README.md +53 -0
  2. config.json +102 -0
  3. final_model_after_training/config.json +102 -0
  4. final_model_after_training/model.safetensors +3 -0
  5. final_model_after_training/special_tokens_map.json +7 -0
  6. final_model_after_training/tokenizer.json +0 -0
  7. final_model_after_training/tokenizer_config.json +56 -0
  8. final_model_after_training/training_args.bin +3 -0
  9. final_model_after_training/vocab.txt +0 -0
  10. model.safetensors +3 -0
  11. runs/May17_13-37-42_887428ad6657/events.out.tfevents.1747489067.887428ad6657.30493.5 +3 -0
  12. runs/May17_14-07-55_887428ad6657/events.out.tfevents.1747490877.887428ad6657.30493.6 +3 -0
  13. runs/May17_14-14-06_887428ad6657/events.out.tfevents.1747491247.887428ad6657.30493.7 +3 -0
  14. runs/May17_14-18-07_887428ad6657/events.out.tfevents.1747491487.887428ad6657.30493.8 +3 -0
  15. runs/May17_15-10-54_887428ad6657/events.out.tfevents.1747494655.887428ad6657.62473.0 +3 -0
  16. special_tokens_map.json +7 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +56 -0
  19. training_args.bin +3 -0
  20. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: distilbert-base-uncased
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: my_model_from_existing_datasets
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
+ # my_model_from_existing_datasets
16
+
17
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 3
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.51.3
51
+ - Pytorch 2.6.0+cu124
52
+ - Datasets 2.14.4
53
+ - Tokenizers 0.21.1
config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13",
25
+ "14": "LABEL_14",
26
+ "15": "LABEL_15",
27
+ "16": "LABEL_16",
28
+ "17": "LABEL_17",
29
+ "18": "LABEL_18",
30
+ "19": "LABEL_19",
31
+ "20": "LABEL_20",
32
+ "21": "LABEL_21",
33
+ "22": "LABEL_22",
34
+ "23": "LABEL_23",
35
+ "24": "LABEL_24",
36
+ "25": "LABEL_25",
37
+ "26": "LABEL_26",
38
+ "27": "LABEL_27",
39
+ "28": "LABEL_28",
40
+ "29": "LABEL_29",
41
+ "30": "LABEL_30",
42
+ "31": "LABEL_31",
43
+ "32": "LABEL_32",
44
+ "33": "LABEL_33",
45
+ "34": "LABEL_34",
46
+ "35": "LABEL_35",
47
+ "36": "LABEL_36"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1,
53
+ "LABEL_10": 10,
54
+ "LABEL_11": 11,
55
+ "LABEL_12": 12,
56
+ "LABEL_13": 13,
57
+ "LABEL_14": 14,
58
+ "LABEL_15": 15,
59
+ "LABEL_16": 16,
60
+ "LABEL_17": 17,
61
+ "LABEL_18": 18,
62
+ "LABEL_19": 19,
63
+ "LABEL_2": 2,
64
+ "LABEL_20": 20,
65
+ "LABEL_21": 21,
66
+ "LABEL_22": 22,
67
+ "LABEL_23": 23,
68
+ "LABEL_24": 24,
69
+ "LABEL_25": 25,
70
+ "LABEL_26": 26,
71
+ "LABEL_27": 27,
72
+ "LABEL_28": 28,
73
+ "LABEL_29": 29,
74
+ "LABEL_3": 3,
75
+ "LABEL_30": 30,
76
+ "LABEL_31": 31,
77
+ "LABEL_32": 32,
78
+ "LABEL_33": 33,
79
+ "LABEL_34": 34,
80
+ "LABEL_35": 35,
81
+ "LABEL_36": 36,
82
+ "LABEL_4": 4,
83
+ "LABEL_5": 5,
84
+ "LABEL_6": 6,
85
+ "LABEL_7": 7,
86
+ "LABEL_8": 8,
87
+ "LABEL_9": 9
88
+ },
89
+ "max_position_embeddings": 512,
90
+ "model_type": "distilbert",
91
+ "n_heads": 12,
92
+ "n_layers": 6,
93
+ "pad_token_id": 0,
94
+ "problem_type": "single_label_classification",
95
+ "qa_dropout": 0.1,
96
+ "seq_classif_dropout": 0.2,
97
+ "sinusoidal_pos_embds": false,
98
+ "tie_weights_": true,
99
+ "torch_dtype": "float32",
100
+ "transformers_version": "4.51.3",
101
+ "vocab_size": 30522
102
+ }
final_model_after_training/config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13",
25
+ "14": "LABEL_14",
26
+ "15": "LABEL_15",
27
+ "16": "LABEL_16",
28
+ "17": "LABEL_17",
29
+ "18": "LABEL_18",
30
+ "19": "LABEL_19",
31
+ "20": "LABEL_20",
32
+ "21": "LABEL_21",
33
+ "22": "LABEL_22",
34
+ "23": "LABEL_23",
35
+ "24": "LABEL_24",
36
+ "25": "LABEL_25",
37
+ "26": "LABEL_26",
38
+ "27": "LABEL_27",
39
+ "28": "LABEL_28",
40
+ "29": "LABEL_29",
41
+ "30": "LABEL_30",
42
+ "31": "LABEL_31",
43
+ "32": "LABEL_32",
44
+ "33": "LABEL_33",
45
+ "34": "LABEL_34",
46
+ "35": "LABEL_35",
47
+ "36": "LABEL_36"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1,
53
+ "LABEL_10": 10,
54
+ "LABEL_11": 11,
55
+ "LABEL_12": 12,
56
+ "LABEL_13": 13,
57
+ "LABEL_14": 14,
58
+ "LABEL_15": 15,
59
+ "LABEL_16": 16,
60
+ "LABEL_17": 17,
61
+ "LABEL_18": 18,
62
+ "LABEL_19": 19,
63
+ "LABEL_2": 2,
64
+ "LABEL_20": 20,
65
+ "LABEL_21": 21,
66
+ "LABEL_22": 22,
67
+ "LABEL_23": 23,
68
+ "LABEL_24": 24,
69
+ "LABEL_25": 25,
70
+ "LABEL_26": 26,
71
+ "LABEL_27": 27,
72
+ "LABEL_28": 28,
73
+ "LABEL_29": 29,
74
+ "LABEL_3": 3,
75
+ "LABEL_30": 30,
76
+ "LABEL_31": 31,
77
+ "LABEL_32": 32,
78
+ "LABEL_33": 33,
79
+ "LABEL_34": 34,
80
+ "LABEL_35": 35,
81
+ "LABEL_36": 36,
82
+ "LABEL_4": 4,
83
+ "LABEL_5": 5,
84
+ "LABEL_6": 6,
85
+ "LABEL_7": 7,
86
+ "LABEL_8": 8,
87
+ "LABEL_9": 9
88
+ },
89
+ "max_position_embeddings": 512,
90
+ "model_type": "distilbert",
91
+ "n_heads": 12,
92
+ "n_layers": 6,
93
+ "pad_token_id": 0,
94
+ "problem_type": "single_label_classification",
95
+ "qa_dropout": 0.1,
96
+ "seq_classif_dropout": 0.2,
97
+ "sinusoidal_pos_embds": false,
98
+ "tie_weights_": true,
99
+ "torch_dtype": "float32",
100
+ "transformers_version": "4.51.3",
101
+ "vocab_size": 30522
102
+ }
final_model_after_training/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bf96a06719ce000f72d47bb832c8dcd4f4c7712fc4c19420716b8c1a5d80ea2
3
+ size 267940236
final_model_after_training/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
+ }
final_model_after_training/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
final_model_after_training/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
final_model_after_training/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:178d52bce00ec8cb7bec33d1c0a15ba9dd04bd09d5643e44ed454530c1cb3015
3
+ size 5368
final_model_after_training/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf6bc76071fd24240820f2f5185157da99b4698a80930aa4f14e5b64f2b5ce1
3
+ size 267940236
runs/May17_13-37-42_887428ad6657/events.out.tfevents.1747489067.887428ad6657.30493.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:893472bef198e96f1dad6c88df8f20d05fdf94987b0561ef56737347cd802e62
3
+ size 6397
runs/May17_14-07-55_887428ad6657/events.out.tfevents.1747490877.887428ad6657.30493.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c0704a359d2996438df62ce67fba1b4418c192c090074c6e1d78e65d7277f4
3
+ size 7724
runs/May17_14-14-06_887428ad6657/events.out.tfevents.1747491247.887428ad6657.30493.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ee438d35a355d439d3525aa99d7b75dc87680c9af43c7e8901042d39e9affc0
3
+ size 7724
runs/May17_14-18-07_887428ad6657/events.out.tfevents.1747491487.887428ad6657.30493.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c01d915001931f9a1393cb1df5ddb196cf8385acc97aceb82ce965daa45f694f
3
+ size 7724
runs/May17_15-10-54_887428ad6657/events.out.tfevents.1747494655.887428ad6657.62473.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b289ddc5a2c095c2916db2d174e299c31b2f26f9feffe50f75a0be7c68a0300
3
+ size 7169
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2f5c8b3a07de363dce5e9169136ef2a4a40496c15787ea3a46c88c566a0216
3
+ size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff