SharonTudi
commited on
End of training
Browse files- README.md +53 -53
- config.json +16 -17
- model.safetensors +2 -2
- runs/Jan24_18-39-27_cbbbf18f120b/events.out.tfevents.1706121568.cbbbf18f120b.1412.0 +3 -0
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# DIALOGUE_one
|
20 |
|
21 |
-
This model is a fine-tuned version of [
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
- Precision: 0.9762
|
25 |
- Recall: 0.9737
|
26 |
- F1: 0.9736
|
@@ -55,59 +55,59 @@ The following hyperparameters were used during training:
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
-
| 1.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
-
| 0.
|
93 |
-
| 0.
|
94 |
-
| 0.
|
95 |
-
| 0.
|
96 |
-
| 0.
|
97 |
-
| 0.
|
98 |
-
| 0.
|
99 |
-
| 0.
|
100 |
-
| 0.
|
101 |
-
| 0.
|
102 |
-
| 0.
|
103 |
-
| 0.
|
104 |
-
| 0.
|
105 |
-
| 0.
|
106 |
|
107 |
|
108 |
### Framework versions
|
109 |
|
110 |
-
- Transformers 4.37.
|
111 |
- Pytorch 2.1.0+cu121
|
112 |
- Datasets 2.16.1
|
113 |
-
- Tokenizers 0.15.
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: distilbert-base-cased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
|
|
18 |
|
19 |
# DIALOGUE_one
|
20 |
|
21 |
+
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.1162
|
24 |
- Precision: 0.9762
|
25 |
- Recall: 0.9737
|
26 |
- F1: 0.9736
|
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 1.1718 | 0.62 | 30 | 0.7204 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
59 |
+
| 0.5326 | 1.25 | 60 | 0.2354 | 0.9637 | 0.9605 | 0.9604 | 0.9605 |
|
60 |
+
| 0.2144 | 1.88 | 90 | 0.1127 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
61 |
+
| 0.0577 | 2.5 | 120 | 0.0236 | 1.0 | 1.0 | 1.0 | 1.0 |
|
62 |
+
| 0.0417 | 3.12 | 150 | 0.0598 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
63 |
+
| 0.0191 | 3.75 | 180 | 0.0617 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
64 |
+
| 0.0069 | 4.38 | 210 | 0.0785 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
65 |
+
| 0.0051 | 5.0 | 240 | 0.0715 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
66 |
+
| 0.0038 | 5.62 | 270 | 0.0879 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
67 |
+
| 0.0033 | 6.25 | 300 | 0.0812 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
68 |
+
| 0.0027 | 6.88 | 330 | 0.0864 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
69 |
+
| 0.0025 | 7.5 | 360 | 0.0867 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
70 |
+
| 0.002 | 8.12 | 390 | 0.0943 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
71 |
+
| 0.0019 | 8.75 | 420 | 0.0954 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
72 |
+
| 0.0017 | 9.38 | 450 | 0.1012 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
73 |
+
| 0.0015 | 10.0 | 480 | 0.0986 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
74 |
+
| 0.0013 | 10.62 | 510 | 0.1019 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
75 |
+
| 0.0013 | 11.25 | 540 | 0.1041 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
76 |
+
| 0.0012 | 11.88 | 570 | 0.1052 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
77 |
+
| 0.0011 | 12.5 | 600 | 0.1076 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
78 |
+
| 0.001 | 13.12 | 630 | 0.1086 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
79 |
+
| 0.001 | 13.75 | 660 | 0.1080 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
80 |
+
| 0.0009 | 14.38 | 690 | 0.1078 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
81 |
+
| 0.0009 | 15.0 | 720 | 0.1038 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
82 |
+
| 0.0008 | 15.62 | 750 | 0.1002 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
83 |
+
| 0.0007 | 16.25 | 780 | 0.1014 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
84 |
+
| 0.0007 | 16.88 | 810 | 0.1039 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
85 |
+
| 0.0007 | 17.5 | 840 | 0.1057 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
86 |
+
| 0.0007 | 18.12 | 870 | 0.1086 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
87 |
+
| 0.0007 | 18.75 | 900 | 0.1076 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
88 |
+
| 0.0006 | 19.38 | 930 | 0.1075 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
89 |
+
| 0.0006 | 20.0 | 960 | 0.1065 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
90 |
+
| 0.0006 | 20.62 | 990 | 0.1066 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
91 |
+
| 0.0006 | 21.25 | 1020 | 0.1084 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
92 |
+
| 0.0005 | 21.88 | 1050 | 0.1094 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
93 |
+
| 0.0005 | 22.5 | 1080 | 0.1097 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
94 |
+
| 0.0005 | 23.12 | 1110 | 0.1118 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
95 |
+
| 0.0005 | 23.75 | 1140 | 0.1135 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
96 |
+
| 0.0005 | 24.38 | 1170 | 0.1140 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
97 |
+
| 0.0005 | 25.0 | 1200 | 0.1139 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
98 |
+
| 0.0004 | 25.62 | 1230 | 0.1145 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
99 |
+
| 0.0004 | 26.25 | 1260 | 0.1148 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
100 |
+
| 0.0005 | 26.88 | 1290 | 0.1146 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
101 |
+
| 0.0005 | 27.5 | 1320 | 0.1153 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
102 |
+
| 0.0005 | 28.12 | 1350 | 0.1154 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
103 |
+
| 0.0005 | 28.75 | 1380 | 0.1157 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
104 |
+
| 0.0005 | 29.38 | 1410 | 0.1161 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
105 |
+
| 0.0004 | 30.0 | 1440 | 0.1162 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
106 |
|
107 |
|
108 |
### Framework versions
|
109 |
|
110 |
+
- Transformers 4.37.1
|
111 |
- Pytorch 2.1.0+cu121
|
112 |
- Datasets 2.16.1
|
113 |
+
- Tokenizers 0.15.1
|
config.json
CHANGED
@@ -1,14 +1,13 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
"0": "Hospital-Inform",
|
14 |
"1": "Hospital-Request",
|
@@ -16,24 +15,24 @@
|
|
16 |
"3": "general-thank"
|
17 |
},
|
18 |
"initializer_range": 0.02,
|
19 |
-
"intermediate_size": 3072,
|
20 |
"label2id": {
|
21 |
"LABEL_0": 0,
|
22 |
"LABEL_1": 1,
|
23 |
"LABEL_2": 2,
|
24 |
"LABEL_3": 3
|
25 |
},
|
26 |
-
"layer_norm_eps": 1e-12,
|
27 |
"max_position_embeddings": 512,
|
28 |
-
"model_type": "
|
29 |
-
"
|
30 |
-
"
|
|
|
31 |
"pad_token_id": 0,
|
32 |
-
"position_embedding_type": "absolute",
|
33 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
34 |
"torch_dtype": "float32",
|
35 |
-
"transformers_version": "4.37.
|
36 |
-
"type_vocab_size": 2,
|
37 |
-
"use_cache": true,
|
38 |
"vocab_size": 28996
|
39 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
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",
|
|
|
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 |
+
"output_past": true,
|
29 |
"pad_token_id": 0,
|
|
|
30 |
"problem_type": "single_label_classification",
|
31 |
+
"qa_dropout": 0.1,
|
32 |
+
"seq_classif_dropout": 0.2,
|
33 |
+
"sinusoidal_pos_embds": false,
|
34 |
+
"tie_weights_": true,
|
35 |
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.37.1",
|
|
|
|
|
37 |
"vocab_size": 28996
|
38 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef203c014ca693c91fdb0106e4b721f1f1168df800e00c1b1fdf136992b42599
|
3 |
+
size 263150840
|
runs/Jan24_18-39-27_cbbbf18f120b/events.out.tfevents.1706121568.cbbbf18f120b.1412.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c07c5fff203482f69865ce11d7c7709d0344104ed9fa01be212ddae8ba28b312
|
3 |
+
size 34968
|
tokenizer_config.json
CHANGED
@@ -52,6 +52,6 @@
|
|
52 |
"sep_token": "[SEP]",
|
53 |
"strip_accents": null,
|
54 |
"tokenize_chinese_chars": true,
|
55 |
-
"tokenizer_class": "
|
56 |
"unk_token": "[UNK]"
|
57 |
}
|
|
|
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
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb54994d82787ddf5f907dccc1c9c0423195a230a1783094d0f87cc2174296ca
|
3 |
size 4664
|