End of training
Browse files- README.md +76 -0
- config.json +37 -0
- model.safetensors +3 -0
- runs/Jan18_11-38-24_3c59cc46f7a9/events.out.tfevents.1705577905.3c59cc46f7a9.1662.16 +3 -0
- runs/Jan18_11-38-24_3c59cc46f7a9/events.out.tfevents.1705577953.3c59cc46f7a9.1662.17 +3 -0
- runs/Jan18_11-46-53_3c59cc46f7a9/events.out.tfevents.1705578414.3c59cc46f7a9.1662.28 +3 -0
- runs/Jan18_11-46-53_3c59cc46f7a9/events.out.tfevents.1705578473.3c59cc46f7a9.1662.29 +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: DIALOGUE_overfit_check_fold_4
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# DIALOGUE_overfit_check_fold_4
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.3761
|
24 |
+
- Precision: 0.6341
|
25 |
+
- Recall: 0.75
|
26 |
+
- F1: 0.6746
|
27 |
+
- Accuracy: 0.75
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 0.00024
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 8
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 15
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.0375 | 1.28 | 50 | 0.0 | 1.0 | 1.0 | 1.0 | 1.0 |
|
59 |
+
| 0.5727 | 2.56 | 100 | 0.1253 | 0.9868 | 0.9868 | 0.9865 | 0.9868 |
|
60 |
+
| 0.1062 | 3.85 | 150 | 0.0009 | 1.0 | 1.0 | 1.0 | 1.0 |
|
61 |
+
| 0.4201 | 5.13 | 200 | 0.5864 | 0.6310 | 0.7353 | 0.6643 | 0.7368 |
|
62 |
+
| 0.4665 | 6.41 | 250 | 0.4016 | 0.6159 | 0.75 | 0.6583 | 0.7105 |
|
63 |
+
| 0.4445 | 7.69 | 300 | 0.3748 | 0.6341 | 0.75 | 0.6746 | 0.75 |
|
64 |
+
| 0.3779 | 8.97 | 350 | 0.3921 | 0.6159 | 0.75 | 0.6583 | 0.7105 |
|
65 |
+
| 0.3739 | 10.26 | 400 | 0.3803 | 0.6159 | 0.75 | 0.6583 | 0.7105 |
|
66 |
+
| 0.3726 | 11.54 | 450 | 0.3755 | 0.6341 | 0.75 | 0.6746 | 0.75 |
|
67 |
+
| 0.3596 | 12.82 | 500 | 0.3746 | 0.6341 | 0.75 | 0.6746 | 0.75 |
|
68 |
+
| 0.3806 | 14.1 | 550 | 0.3760 | 0.6341 | 0.75 | 0.6746 | 0.75 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.36.2
|
74 |
+
- Pytorch 2.1.0+cu121
|
75 |
+
- Datasets 2.16.1
|
76 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "Hospital-Inform",
|
13 |
+
"1": "Hospital-Request",
|
14 |
+
"2": "general-bye",
|
15 |
+
"3": "general-thank"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0,
|
20 |
+
"LABEL_1": 1,
|
21 |
+
"LABEL_2": 2,
|
22 |
+
"LABEL_3": 3
|
23 |
+
},
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "distilbert",
|
26 |
+
"n_heads": 12,
|
27 |
+
"n_layers": 6,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"problem_type": "single_label_classification",
|
30 |
+
"qa_dropout": 0.1,
|
31 |
+
"seq_classif_dropout": 0.2,
|
32 |
+
"sinusoidal_pos_embds": false,
|
33 |
+
"tie_weights_": true,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.36.2",
|
36 |
+
"vocab_size": 30522
|
37 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d07a7b4269c041cfa240eff67165d3082120907aa6d32266676f163e4fbcb509
|
3 |
+
size 267838720
|
runs/Jan18_11-38-24_3c59cc46f7a9/events.out.tfevents.1705577905.3c59cc46f7a9.1662.16
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e01d6152c1e4da7cea66efe37199c4df9d869e40664516d2ee9be191947b72f9
|
3 |
+
size 8081
|
runs/Jan18_11-38-24_3c59cc46f7a9/events.out.tfevents.1705577953.3c59cc46f7a9.1662.17
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a355573508f05ff739c5123aa91cbb4099218d2e6f0c9d4dad22297346a3c97
|
3 |
+
size 560
|
runs/Jan18_11-46-53_3c59cc46f7a9/events.out.tfevents.1705578414.3c59cc46f7a9.1662.28
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43d7be3d297aeb79dac4da1da954f92df8bd69e032959d5f1a143c1cb229c875
|
3 |
+
size 11841
|
runs/Jan18_11-46-53_3c59cc46f7a9/events.out.tfevents.1705578473.3c59cc46f7a9.1662.29
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee7accaab0d029ecfee1f7fefc646b4d8a9168e50f5d858198226b3cca58da88
|
3 |
+
size 560
|
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:c5a9374ceff024ac443e9ec084da3dcd11c902db02b98546a0f114336c414cd5
|
3 |
+
size 4728
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|