G-ML-Hyly commited on
Commit
81791e5
1 Parent(s): cc3b24b

G-ML-Hyly/gls

Browse files
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: cdp-gls
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
+ # cdp-gls
17
+
18
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 3.0808
21
+ - Accuracy: 0.4839
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: 16
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 10
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 3.4949 | 1.0 | 10 | 3.4712 | 0.0645 |
53
+ | 3.4362 | 2.0 | 20 | 3.4293 | 0.1452 |
54
+ | 3.3557 | 3.0 | 30 | 3.3663 | 0.2581 |
55
+ | 3.2469 | 4.0 | 40 | 3.3081 | 0.3710 |
56
+ | 3.1742 | 5.0 | 50 | 3.2495 | 0.3871 |
57
+ | 3.0934 | 6.0 | 60 | 3.1932 | 0.4032 |
58
+ | 3.0142 | 7.0 | 70 | 3.1443 | 0.4516 |
59
+ | 2.9634 | 8.0 | 80 | 3.1101 | 0.4516 |
60
+ | 2.9353 | 9.0 | 90 | 3.0889 | 0.4839 |
61
+ | 2.9034 | 10.0 | 100 | 3.0808 | 0.4839 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.38.0.dev0
67
+ - Pytorch 2.1.2+cu121
68
+ - Datasets 2.15.0
69
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "all dimensions",
13
+ "1": "all dimensions in crstal by assist",
14
+ "2": "all dimensions in crstal by medium",
15
+ "3": "all dimensions in crstal by source",
16
+ "4": "all metrics",
17
+ "5": "applied by assist",
18
+ "6": "applied by medium",
19
+ "7": "applied by source",
20
+ "8": "assist",
21
+ "9": "created leads by assist",
22
+ "10": "created leads by medium",
23
+ "11": "created leads by source",
24
+ "12": "crstal by assist",
25
+ "13": "crstal by medium",
26
+ "14": "crstal by source",
27
+ "15": "crstal milestones",
28
+ "16": "date range",
29
+ "17": "direct source",
30
+ "18": "lead gen analysis",
31
+ "19": "leased by assist",
32
+ "20": "leased by medium",
33
+ "21": "leased by source",
34
+ "22": "medium",
35
+ "23": "property name",
36
+ "24": "prospect journey",
37
+ "25": "source",
38
+ "26": "toured by assist",
39
+ "27": "toured by medium",
40
+ "28": "toured by source",
41
+ "29": "tours scheduled by assist",
42
+ "30": "tours scheduled by medium",
43
+ "31": "tours scheduled by source",
44
+ "32": "unspecified source"
45
+ },
46
+ "initializer_range": 0.02,
47
+ "label2id": {
48
+ "all dimensions": 0,
49
+ "all dimensions in crstal by assist": 1,
50
+ "all dimensions in crstal by medium": 2,
51
+ "all dimensions in crstal by source": 3,
52
+ "all metrics": 4,
53
+ "applied by assist": 5,
54
+ "applied by medium": 6,
55
+ "applied by source": 7,
56
+ "assist": 8,
57
+ "created leads by assist": 9,
58
+ "created leads by medium": 10,
59
+ "created leads by source": 11,
60
+ "crstal by assist": 12,
61
+ "crstal by medium": 13,
62
+ "crstal by source": 14,
63
+ "crstal milestones": 15,
64
+ "date range": 16,
65
+ "direct source": 17,
66
+ "lead gen analysis": 18,
67
+ "leased by assist": 19,
68
+ "leased by medium": 20,
69
+ "leased by source": 21,
70
+ "medium": 22,
71
+ "property name": 23,
72
+ "prospect journey": 24,
73
+ "source": 25,
74
+ "toured by assist": 26,
75
+ "toured by medium": 27,
76
+ "toured by source": 28,
77
+ "tours scheduled by assist": 29,
78
+ "tours scheduled by medium": 30,
79
+ "tours scheduled by source": 31,
80
+ "unspecified source": 32
81
+ },
82
+ "max_position_embeddings": 512,
83
+ "model_type": "distilbert",
84
+ "n_heads": 12,
85
+ "n_layers": 6,
86
+ "pad_token_id": 0,
87
+ "problem_type": "single_label_classification",
88
+ "qa_dropout": 0.1,
89
+ "seq_classif_dropout": 0.2,
90
+ "sinusoidal_pos_embds": false,
91
+ "tie_weights_": true,
92
+ "torch_dtype": "float32",
93
+ "transformers_version": "4.38.0.dev0",
94
+ "vocab_size": 30522
95
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c9a21ab7eeea0d41056af446a37453e2c255d18cfc38864fc4c7e981af5f713
3
+ size 267927932
runs/Feb06_22-57-23_LAPTOP-BN4LH857/events.out.tfevents.1707242246.LAPTOP-BN4LH857.35660.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0845bc5e59ea3387691992a72497868ab9b181bd57f8e6fb12909bc7e6c85e80
3
+ size 4530
runs/Feb06_23-03-08_LAPTOP-BN4LH857/events.out.tfevents.1707242590.LAPTOP-BN4LH857.35660.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddc2ac4f321050eb5b169b1e67e6ea77cedfc25e948b3805086ac29d5e0eea0b
3
+ size 5450
runs/Feb07_08-14-18_LAPTOP-BN4LH857/events.out.tfevents.1707275659.LAPTOP-BN4LH857.21796.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2696e66ac2630b8ed785162df6c7e7d9008ab1373495698ff6f3537ed0907641
3
+ size 4539
runs/Feb07_08-19-47_LAPTOP-BN4LH857/events.out.tfevents.1707275987.LAPTOP-BN4LH857.21796.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e70927f0e02ad2b11c7dfbc21faddbcfa1ced43460a3c85fdaa32c987d1ff98b
3
+ size 5871
runs/Mar15_12-59-18_LAPTOP-BN4LH857/events.out.tfevents.1710489563.LAPTOP-BN4LH857.35824.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9f8a9b66dcddfba06884aef86f0ae35f7ad68fa91767f66f9fd13aa9e1984da
3
+ size 100260
runs/Mar15_20-46-04_LAPTOP-BN4LH857/events.out.tfevents.1710517568.LAPTOP-BN4LH857.35824.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b147b8379181af2e781d296fd8e7024f81158856fc0447148b6a99c51b148b18
3
+ size 11370
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3da0894fc187f087f144a78940d46060d1c83541a604a72b2bd1e9fc878fda2
3
+ size 4728
vocab.txt ADDED
The diff for this file is too large to render. See raw diff