hung200504
commited on
Commit
•
2311b3b
1
Parent(s):
0b4519d
bert-cased
Browse files- README.md +35 -57
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -40,67 +40,45 @@ The following hyperparameters were used during training:
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
- num_epochs:
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
-
| 11.3132 | 0.09 | 5 | 12.
|
50 |
-
| 11.
|
51 |
-
| 10.
|
52 |
-
| 11.
|
53 |
-
| 11.
|
54 |
-
| 11.
|
55 |
-
| 10.
|
56 |
-
| 10.
|
57 |
-
| 10.
|
58 |
-
| 10.
|
59 |
-
| 10.
|
60 |
-
| 10.
|
61 |
-
| 10.
|
62 |
-
| 10.
|
63 |
-
| 10.
|
64 |
-
| 10.
|
65 |
-
| 10.
|
66 |
-
| 10.
|
67 |
-
|
|
68 |
-
| 10.
|
69 |
-
| 9.
|
70 |
-
|
|
71 |
-
|
|
72 |
-
| 9.
|
73 |
-
|
|
74 |
-
|
|
75 |
-
| 9.
|
76 |
-
|
|
77 |
-
| 9.
|
78 |
-
|
|
79 |
-
| 9.
|
80 |
-
| 9.
|
81 |
-
|
|
82 |
-
| 9.6037 | 3.09 | 170 | 10.5750 |
|
83 |
-
| 9.5624 | 3.18 | 175 | 10.5468 |
|
84 |
-
| 9.2702 | 3.27 | 180 | 10.5202 |
|
85 |
-
| 9.1347 | 3.36 | 185 | 10.4947 |
|
86 |
-
| 9.8154 | 3.45 | 190 | 10.4706 |
|
87 |
-
| 9.4045 | 3.55 | 195 | 10.4475 |
|
88 |
-
| 9.2453 | 3.64 | 200 | 10.4262 |
|
89 |
-
| 9.1087 | 3.73 | 205 | 10.4062 |
|
90 |
-
| 8.985 | 3.82 | 210 | 10.3875 |
|
91 |
-
| 9.0054 | 3.91 | 215 | 10.3705 |
|
92 |
-
| 9.4764 | 4.0 | 220 | 10.3545 |
|
93 |
-
| 9.13 | 4.09 | 225 | 10.3401 |
|
94 |
-
| 9.4397 | 4.18 | 230 | 10.3272 |
|
95 |
-
| 9.0841 | 4.27 | 235 | 10.3153 |
|
96 |
-
| 9.5885 | 4.36 | 240 | 10.3048 |
|
97 |
-
| 9.4137 | 4.45 | 245 | 10.2958 |
|
98 |
-
| 9.1068 | 4.55 | 250 | 10.2878 |
|
99 |
-
| 9.1388 | 4.64 | 255 | 10.2816 |
|
100 |
-
| 8.8014 | 4.73 | 260 | 10.2763 |
|
101 |
-
| 8.9782 | 4.82 | 265 | 10.2727 |
|
102 |
-
| 9.222 | 4.91 | 270 | 10.2701 |
|
103 |
-
| 9.292 | 5.0 | 275 | 10.2691 |
|
104 |
|
105 |
|
106 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 11.0923
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 3
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 11.3132 | 0.09 | 5 | 12.3056 |
|
50 |
+
| 11.4114 | 0.18 | 10 | 12.2307 |
|
51 |
+
| 10.9764 | 0.27 | 15 | 12.1584 |
|
52 |
+
| 11.0818 | 0.36 | 20 | 12.0885 |
|
53 |
+
| 11.0423 | 0.45 | 25 | 12.0202 |
|
54 |
+
| 11.0449 | 0.55 | 30 | 11.9548 |
|
55 |
+
| 10.3108 | 0.64 | 35 | 11.8919 |
|
56 |
+
| 10.9207 | 0.73 | 40 | 11.8320 |
|
57 |
+
| 10.4606 | 0.82 | 45 | 11.7743 |
|
58 |
+
| 10.3376 | 0.91 | 50 | 11.7188 |
|
59 |
+
| 10.091 | 1.0 | 55 | 11.6658 |
|
60 |
+
| 10.2796 | 1.09 | 60 | 11.6154 |
|
61 |
+
| 10.3783 | 1.18 | 65 | 11.5677 |
|
62 |
+
| 10.5827 | 1.27 | 70 | 11.5216 |
|
63 |
+
| 10.1084 | 1.36 | 75 | 11.4785 |
|
64 |
+
| 10.5279 | 1.45 | 80 | 11.4372 |
|
65 |
+
| 10.2497 | 1.55 | 85 | 11.3984 |
|
66 |
+
| 10.1908 | 1.64 | 90 | 11.3618 |
|
67 |
+
| 10.0181 | 1.73 | 95 | 11.3275 |
|
68 |
+
| 10.2313 | 1.82 | 100 | 11.2956 |
|
69 |
+
| 9.7781 | 1.91 | 105 | 11.2663 |
|
70 |
+
| 10.1123 | 2.0 | 110 | 11.2391 |
|
71 |
+
| 10.0491 | 2.09 | 115 | 11.2141 |
|
72 |
+
| 9.869 | 2.18 | 120 | 11.1916 |
|
73 |
+
| 10.0292 | 2.27 | 125 | 11.1714 |
|
74 |
+
| 10.1515 | 2.36 | 130 | 11.1534 |
|
75 |
+
| 9.7539 | 2.45 | 135 | 11.1377 |
|
76 |
+
| 10.1323 | 2.55 | 140 | 11.1242 |
|
77 |
+
| 9.6956 | 2.64 | 145 | 11.1136 |
|
78 |
+
| 10.1937 | 2.73 | 150 | 11.1050 |
|
79 |
+
| 9.9615 | 2.82 | 155 | 11.0983 |
|
80 |
+
| 9.9249 | 2.91 | 160 | 11.0940 |
|
81 |
+
| 10.1271 | 3.0 | 165 | 11.0923 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
82 |
|
83 |
|
84 |
### Framework versions
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 430953062
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76f8db24159f21692b0feb6bbb56eb12b732e394cd378337c71c143119dbcaee
|
3 |
size 430953062
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4472
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be1f1739ca19b12ae4954ca2293c0ba9612dbedb3757bbb9e1b064d30756b5bf
|
3 |
size 4472
|