vishnuhaasan commited on
Commit
ad0801c
1 Parent(s): b5f01fc

End of training

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert/distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: distilbert-base-jul4
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # distilbert-base-jul4
15
+
16
+ This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.4076
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 500
44
+ - num_epochs: 10
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 0.5366 | 1.0 | 2161 | 0.3331 |
51
+ | 0.233 | 2.0 | 4322 | 0.2973 |
52
+ | 0.2538 | 3.0 | 6483 | 0.3052 |
53
+ | 0.1026 | 4.0 | 8644 | 0.3407 |
54
+ | 0.3053 | 5.0 | 10805 | 0.3259 |
55
+ | 0.1347 | 6.0 | 12966 | 0.3799 |
56
+ | 0.1464 | 7.0 | 15127 | 0.3561 |
57
+ | 0.0001 | 8.0 | 17288 | 0.3638 |
58
+ | 0.0002 | 9.0 | 19449 | 0.3972 |
59
+ | 0.0 | 10.0 | 21610 | 0.4076 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.41.2
65
+ - Pytorch 2.3.0+cu121
66
+ - Datasets 2.20.0
67
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/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": "Cold outreach/Introduction emails",
13
+ "1": "Value Proposition Emails",
14
+ "2": "Appointment request emails",
15
+ "3": "Appointment Reminder Emails",
16
+ "4": "Follow up emails",
17
+ "5": "Upselling emails",
18
+ "6": "Cross-Selling emails",
19
+ "7": "Abandoned cart emails",
20
+ "8": "Quotation Emails",
21
+ "9": "Sales Order Emails",
22
+ "10": "Order Confirmation Emails",
23
+ "11": "Invoice Email",
24
+ "12": "Offer/Promotion Emails",
25
+ "13": "Renewal Reminder Emails",
26
+ "14": "Feedback/Survey Emails",
27
+ "15": "Event Invitation Emails",
28
+ "16": "Contract/Agreement Emails",
29
+ "17": "Product Recall or Issue Notification Emails",
30
+ "18": "Competitor Comparison Emails",
31
+ "19": "Warranty Information Emails",
32
+ "20": "Onboarding Emails",
33
+ "21": "Inquiry Emails",
34
+ "22": "Request for Quotation",
35
+ "23": "Support request emails",
36
+ "24": "Order Placement Emails",
37
+ "25": "Order modification emails.",
38
+ "26": "Order cancellation emails.",
39
+ "27": "Exchange/Return request emails.",
40
+ "28": "Refund request",
41
+ "29": "Purchase Order Emails",
42
+ "30": "Appointment scheduling",
43
+ "31": "Appointment postpone",
44
+ "32": "Referral emails",
45
+ "33": "Product upgrade emails",
46
+ "34": "Warranty claim emails",
47
+ "35": "Service renewal emails",
48
+ "36": "Complaint or Issue Reporting Emails",
49
+ "37": "Feedback Emails",
50
+ "38": "Request for Meeting or Demo",
51
+ "39": "Price Negotiation Emails",
52
+ "40": "Delivery Date Negotiation Emails"
53
+ },
54
+ "initializer_range": 0.02,
55
+ "max_position_embeddings": 512,
56
+ "model_type": "distilbert",
57
+ "n_heads": 12,
58
+ "n_layers": 6,
59
+ "pad_token_id": 0,
60
+ "problem_type": "single_label_classification",
61
+ "qa_dropout": 0.1,
62
+ "seq_classif_dropout": 0.2,
63
+ "sinusoidal_pos_embds": false,
64
+ "tie_weights_": true,
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.41.2",
67
+ "vocab_size": 30522
68
+ }
logs/events.out.tfevents.1720160579.a5286c7627ae.7469.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72a14c9d73bcba1cc7a273bf86b61ff889d900d11c6d533ed31ac65b0067a31e
3
+ size 467326
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffee5cc5eb1d309ac84ba97c376436e051465c3c7d5f315921ab49caad119d83
3
+ size 267952540
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_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16503b2d4e758734772dafa6164497d495ef5313b24a55e30bc5813d21af153c
3
+ size 5176
vocab.txt ADDED
The diff for this file is too large to render. See raw diff