ElliotWeiner commited on
Commit
bb60ae8
1 Parent(s): 09d8aec

ElliotWeiner/BERT Fine-Tuned Advisor Classifier 1

Browse files
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: bert-base-uncased
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - f1
9
+ - accuracy
10
+ model-index:
11
+ - name: bert-finetuned-advisor-feedback
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # bert-finetuned-advisor-feedback
19
+
20
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.0577
23
+ - F1: 0.9377
24
+ - Roc Auc: 0.9605
25
+ - Accuracy: 0.8564
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 2e-05
45
+ - train_batch_size: 8
46
+ - eval_batch_size: 8
47
+ - seed: 42
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - num_epochs: 8
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
55
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
56
+ | No log | 1.0 | 404 | 0.2224 | 0.4395 | 0.6424 | 0.0866 |
57
+ | 0.2972 | 2.0 | 808 | 0.1361 | 0.8395 | 0.8720 | 0.5866 |
58
+ | 0.1464 | 3.0 | 1212 | 0.0951 | 0.9056 | 0.9269 | 0.7599 |
59
+ | 0.0841 | 4.0 | 1616 | 0.0770 | 0.9226 | 0.9472 | 0.8168 |
60
+ | 0.0529 | 5.0 | 2020 | 0.0653 | 0.9344 | 0.9569 | 0.8540 |
61
+ | 0.0529 | 6.0 | 2424 | 0.0603 | 0.9357 | 0.9565 | 0.8490 |
62
+ | 0.0384 | 7.0 | 2828 | 0.0577 | 0.9377 | 0.9605 | 0.8564 |
63
+ | 0.0323 | 8.0 | 3232 | 0.0569 | 0.9366 | 0.9579 | 0.8540 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.44.2
69
+ - Pytorch 2.4.1+cu121
70
+ - Datasets 3.0.0
71
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "Communication_Positive",
14
+ "1": "Relationship_Positive",
15
+ "2": "Empathy_Positive",
16
+ "3": "Advocacy_Positive",
17
+ "4": "Resources_Positive",
18
+ "5": "AcademicSupport_Positive",
19
+ "6": "NonAcademic_Positive",
20
+ "7": "Communication_Negative",
21
+ "8": "Relationship_Negative",
22
+ "9": "Empathy_Negative",
23
+ "10": "Advocacy_Negative",
24
+ "11": "Resources_Negative",
25
+ "12": "AcademicSupport_Negative",
26
+ "13": "NonAcademic_Negative"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "label2id": {
31
+ "AcademicSupport_Negative": 12,
32
+ "AcademicSupport_Positive": 5,
33
+ "Advocacy_Negative": 10,
34
+ "Advocacy_Positive": 3,
35
+ "Communication_Negative": 7,
36
+ "Communication_Positive": 0,
37
+ "Empathy_Negative": 9,
38
+ "Empathy_Positive": 2,
39
+ "NonAcademic_Negative": 13,
40
+ "NonAcademic_Positive": 6,
41
+ "Relationship_Negative": 8,
42
+ "Relationship_Positive": 1,
43
+ "Resources_Negative": 11,
44
+ "Resources_Positive": 4
45
+ },
46
+ "layer_norm_eps": 1e-12,
47
+ "max_position_embeddings": 512,
48
+ "model_type": "bert",
49
+ "num_attention_heads": 12,
50
+ "num_hidden_layers": 12,
51
+ "pad_token_id": 0,
52
+ "position_embedding_type": "absolute",
53
+ "problem_type": "multi_label_classification",
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.44.2",
56
+ "type_vocab_size": 2,
57
+ "use_cache": true,
58
+ "vocab_size": 30522
59
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:081cbe61fe6508c86360333ce7218c4cd5f3ffa06cf37568349577962e4ad366
3
+ size 437995560
runs/Sep23_17-31-42_2b5c4dfc1497/events.out.tfevents.1727112783.2b5c4dfc1497.3546.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:464bd28bd8270b49cf2c7ff288991bde439bf6b5afc0ba2bfa70b15fbe0fdf4f
3
+ size 10904
runs/Sep23_17-31-42_2b5c4dfc1497/events.out.tfevents.1727113535.2b5c4dfc1497.3546.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:544dd71dc476a5ea6d8cbfcdcb515d73071c678549cef6f2f6c0ada6cbb8ecfd
3
+ size 508
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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43fe3649d2dced7c308024bcaa47dfe135a4e31a96904cc5d33354f9b2e8325e
3
+ size 5240
vocab.txt ADDED
The diff for this file is too large to render. See raw diff