eskayML/interview_classfier
Browse files- .gitattributes +1 -0
- README.md +79 -0
- config.json +49 -0
- model.safetensors +3 -0
- runs/May24_12-14-46_1a84f68f1e0f/events.out.tfevents.1716552888.1a84f68f1e0f.235.0 +0 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +0 -0
- vocab.txt +0 -0
.gitattributes
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: interview_classifier
|
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 |
+
# interview_classifier
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0840
|
21 |
+
- Accuracy: 0.9682
|
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: 2
|
42 |
+
- eval_batch_size: 2
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 20
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| No log | 1.0 | 79 | 2.2062 | 0.2739 |
|
53 |
+
| No log | 2.0 | 158 | 2.0045 | 0.4076 |
|
54 |
+
| No log | 3.0 | 237 | 1.6355 | 0.5414 |
|
55 |
+
| No log | 4.0 | 316 | 1.2068 | 0.6624 |
|
56 |
+
| No log | 5.0 | 395 | 0.7999 | 0.8408 |
|
57 |
+
| No log | 6.0 | 474 | 0.5501 | 0.8917 |
|
58 |
+
| 1.5743 | 7.0 | 553 | 0.3843 | 0.9299 |
|
59 |
+
| 1.5743 | 8.0 | 632 | 0.2837 | 0.9427 |
|
60 |
+
| 1.5743 | 9.0 | 711 | 0.2162 | 0.9554 |
|
61 |
+
| 1.5743 | 10.0 | 790 | 0.1692 | 0.9682 |
|
62 |
+
| 1.5743 | 11.0 | 869 | 0.1464 | 0.9682 |
|
63 |
+
| 1.5743 | 12.0 | 948 | 0.1195 | 0.9682 |
|
64 |
+
| 0.2976 | 13.0 | 1027 | 0.1085 | 0.9682 |
|
65 |
+
| 0.2976 | 14.0 | 1106 | 0.0934 | 0.9682 |
|
66 |
+
| 0.2976 | 15.0 | 1185 | 0.0940 | 0.9682 |
|
67 |
+
| 0.2976 | 16.0 | 1264 | 0.0869 | 0.9682 |
|
68 |
+
| 0.2976 | 17.0 | 1343 | 0.0844 | 0.9682 |
|
69 |
+
| 0.2976 | 18.0 | 1422 | 0.0844 | 0.9682 |
|
70 |
+
| 0.1102 | 19.0 | 1501 | 0.0822 | 0.9682 |
|
71 |
+
| 0.1102 | 20.0 | 1580 | 0.0840 | 0.9682 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- Transformers 4.41.0
|
77 |
+
- Pytorch 2.3.0+cu121
|
78 |
+
- Datasets 2.19.1
|
79 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "Value equation: quality/cost/efficiency/patient-satisfaction",
|
13 |
+
"1": "Credentialing / Quality Assurance Infrastructure",
|
14 |
+
"2": "Finanicial Impact",
|
15 |
+
"3": "Health System Characteristics",
|
16 |
+
"4": "Clinical utility & efficiency-Provider perspective",
|
17 |
+
"5": "Workflow related problems",
|
18 |
+
"6": "Provider characteristcs",
|
19 |
+
"7": "Training",
|
20 |
+
"8": "Patient/Physican interaction in LUS",
|
21 |
+
"9": "Imaging modalities in general"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"label2id": {
|
25 |
+
"Clinical utility & efficiency-Provider perspective": 4,
|
26 |
+
"Credentialing / Quality Assurance Infrastructure": 1,
|
27 |
+
"Finanicial Impact": 2,
|
28 |
+
"Health System Characteristics": 3,
|
29 |
+
"Imaging modalities in general": 9,
|
30 |
+
"Patient/Physican interaction in LUS": 8,
|
31 |
+
"Provider characteristcs": 6,
|
32 |
+
"Training": 7,
|
33 |
+
"Value equation: quality/cost/efficiency/patient-satisfaction": 0,
|
34 |
+
"Workflow related problems": 5
|
35 |
+
},
|
36 |
+
"max_position_embeddings": 512,
|
37 |
+
"model_type": "distilbert",
|
38 |
+
"n_heads": 12,
|
39 |
+
"n_layers": 6,
|
40 |
+
"pad_token_id": 0,
|
41 |
+
"problem_type": "single_label_classification",
|
42 |
+
"qa_dropout": 0.1,
|
43 |
+
"seq_classif_dropout": 0.2,
|
44 |
+
"sinusoidal_pos_embds": false,
|
45 |
+
"tie_weights_": true,
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.41.0",
|
48 |
+
"vocab_size": 30522
|
49 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a7bc671fabaa78d7fb0577e3416cf17e050ef0426c47bbfe165b1384de91d5f
|
3 |
+
size 267857176
|
runs/May24_12-14-46_1a84f68f1e0f/events.out.tfevents.1716552888.1a84f68f1e0f.235.0
ADDED
Binary file (13.1 kB). View file
|
|
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": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"max_length": 512,
|
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
Binary file (5.11 kB). View file
|
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|