SharonTudi
commited on
End of training
Browse files- README.md +51 -51
- config.json +3 -2
- model.safetensors +2 -2
- runs/Jan19_11-17-46_eab14bd28cfb/events.out.tfevents.1705663074.eab14bd28cfb.651.7 +3 -0
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: distilbert-base-
|
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 [distilbert-base-
|
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
|
@@ -55,54 +55,54 @@ 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
|
|
|
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: 0.1862
|
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 |
+
| 1.1763 | 0.62 | 30 | 0.7339 | 0.9083 | 0.8553 | 0.8420 | 0.8553 |
|
59 |
+
| 0.5684 | 1.25 | 60 | 0.2496 | 0.9524 | 0.9474 | 0.9472 | 0.9474 |
|
60 |
+
| 0.2445 | 1.88 | 90 | 0.1581 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
61 |
+
| 0.0728 | 2.5 | 120 | 0.0472 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
62 |
+
| 0.038 | 3.12 | 150 | 0.1179 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
63 |
+
| 0.012 | 3.75 | 180 | 0.0859 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
64 |
+
| 0.0065 | 4.38 | 210 | 0.1251 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
65 |
+
| 0.0046 | 5.0 | 240 | 0.1168 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
66 |
+
| 0.0034 | 5.62 | 270 | 0.1213 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
67 |
+
| 0.0028 | 6.25 | 300 | 0.1257 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
68 |
+
| 0.0025 | 6.88 | 330 | 0.1355 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
69 |
+
| 0.0022 | 7.5 | 360 | 0.1392 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
70 |
+
| 0.0019 | 8.12 | 390 | 0.1435 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
71 |
+
| 0.0016 | 8.75 | 420 | 0.1442 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
72 |
+
| 0.0014 | 9.38 | 450 | 0.1474 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
73 |
+
| 0.0013 | 10.0 | 480 | 0.1490 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
74 |
+
| 0.0012 | 10.62 | 510 | 0.1514 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
75 |
+
| 0.0011 | 11.25 | 540 | 0.1534 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
76 |
+
| 0.0011 | 11.88 | 570 | 0.1549 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
77 |
+
| 0.001 | 12.5 | 600 | 0.1599 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
78 |
+
| 0.0009 | 13.12 | 630 | 0.1642 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
79 |
+
| 0.0009 | 13.75 | 660 | 0.1657 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
80 |
+
| 0.0008 | 14.38 | 690 | 0.1659 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
81 |
+
| 0.0008 | 15.0 | 720 | 0.1681 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
82 |
+
| 0.0007 | 15.62 | 750 | 0.1689 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
83 |
+
| 0.0007 | 16.25 | 780 | 0.1707 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
84 |
+
| 0.0006 | 16.88 | 810 | 0.1722 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
85 |
+
| 0.0006 | 17.5 | 840 | 0.1720 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
86 |
+
| 0.0006 | 18.12 | 870 | 0.1749 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
87 |
+
| 0.0006 | 18.75 | 900 | 0.1765 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
88 |
+
| 0.0005 | 19.38 | 930 | 0.1774 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
89 |
+
| 0.0005 | 20.0 | 960 | 0.1776 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
90 |
+
| 0.0005 | 20.62 | 990 | 0.1778 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
91 |
+
| 0.0005 | 21.25 | 1020 | 0.1794 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
92 |
+
| 0.0005 | 21.88 | 1050 | 0.1804 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
93 |
+
| 0.0004 | 22.5 | 1080 | 0.1810 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
94 |
+
| 0.0005 | 23.12 | 1110 | 0.1819 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
95 |
+
| 0.0004 | 23.75 | 1140 | 0.1825 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
96 |
+
| 0.0004 | 24.38 | 1170 | 0.1830 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
97 |
+
| 0.0004 | 25.0 | 1200 | 0.1836 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
98 |
+
| 0.0004 | 25.62 | 1230 | 0.1841 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
99 |
+
| 0.0004 | 26.25 | 1260 | 0.1845 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
100 |
+
| 0.0004 | 26.88 | 1290 | 0.1848 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
101 |
+
| 0.0004 | 27.5 | 1320 | 0.1856 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
102 |
+
| 0.0004 | 28.12 | 1350 | 0.1858 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
103 |
+
| 0.0004 | 28.75 | 1380 | 0.1861 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
104 |
+
| 0.0004 | 29.38 | 1410 | 0.1862 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
105 |
+
| 0.0004 | 30.0 | 1440 | 0.1862 | 0.9762 | 0.9737 | 0.9736 | 0.9737 |
|
106 |
|
107 |
|
108 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
@@ -25,6 +25,7 @@
|
|
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,
|
@@ -33,5 +34,5 @@
|
|
33 |
"tie_weights_": true,
|
34 |
"torch_dtype": "float32",
|
35 |
"transformers_version": "4.36.2",
|
36 |
-
"vocab_size":
|
37 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
|
|
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,
|
|
|
34 |
"tie_weights_": true,
|
35 |
"torch_dtype": "float32",
|
36 |
"transformers_version": "4.36.2",
|
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:e6553f38536959c3669985b4cd855c25f1af78594021109a39c0e832cb059210
|
3 |
+
size 263150840
|
runs/Jan19_11-17-46_eab14bd28cfb/events.out.tfevents.1705663074.eab14bd28cfb.651.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fff0f34ac4a18bcfa2bd2b4bc08f631978b50456f1a14f03fb825cef7e346b1c
|
3 |
+
size 34967
|
tokenizer_config.json
CHANGED
@@ -44,7 +44,7 @@
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_basic_tokenize": true,
|
47 |
-
"do_lower_case":
|
48 |
"mask_token": "[MASK]",
|
49 |
"model_max_length": 512,
|
50 |
"never_split": null,
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
"mask_token": "[MASK]",
|
49 |
"model_max_length": 512,
|
50 |
"never_split": null,
|
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:acc62f5a95f15dd638e7c3c75d3dfc7e5279ea8c3aa1d9b0619c35dce2266f30
|
3 |
size 4664
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|