temporary0-0name
commited on
Commit
•
f1f7e1d
1
Parent(s):
079b196
End of training
Browse files- README.md +133 -0
- generation_config.json +5 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- wikitext
|
8 |
+
model-index:
|
9 |
+
- name: run_3
|
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 |
+
# run_3
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the wikitext dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 7.1422
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 0.005
|
40 |
+
- train_batch_size: 8
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 8
|
44 |
+
- total_train_batch_size: 64
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: cosine
|
47 |
+
- lr_scheduler_warmup_steps: 100
|
48 |
+
- num_epochs: 5
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 7.8139 | 0.07 | 50 | 7.3922 |
|
55 |
+
| 7.3173 | 0.14 | 100 | 7.2946 |
|
56 |
+
| 7.2587 | 0.21 | 150 | 7.2339 |
|
57 |
+
| 7.2122 | 0.27 | 200 | 7.2167 |
|
58 |
+
| 7.1908 | 0.34 | 250 | 7.1945 |
|
59 |
+
| 7.171 | 0.41 | 300 | 7.1875 |
|
60 |
+
| 7.2054 | 0.48 | 350 | 7.1893 |
|
61 |
+
| 7.1899 | 0.55 | 400 | 7.1889 |
|
62 |
+
| 7.1839 | 0.62 | 450 | 7.1801 |
|
63 |
+
| 7.1571 | 0.69 | 500 | 7.1759 |
|
64 |
+
| 7.1577 | 0.75 | 550 | 7.1725 |
|
65 |
+
| 7.1799 | 0.82 | 600 | 7.1757 |
|
66 |
+
| 7.1698 | 0.89 | 650 | 7.1715 |
|
67 |
+
| 7.1705 | 0.96 | 700 | 7.1651 |
|
68 |
+
| 7.1712 | 1.03 | 750 | 7.1677 |
|
69 |
+
| 7.1418 | 1.1 | 800 | 7.1699 |
|
70 |
+
| 7.1692 | 1.17 | 850 | 7.1659 |
|
71 |
+
| 7.1376 | 1.24 | 900 | 7.1656 |
|
72 |
+
| 7.1703 | 1.3 | 950 | 7.1643 |
|
73 |
+
| 7.1534 | 1.37 | 1000 | 7.1676 |
|
74 |
+
| 7.1445 | 1.44 | 1050 | 7.1607 |
|
75 |
+
| 7.1552 | 1.51 | 1100 | 7.1596 |
|
76 |
+
| 7.1475 | 1.58 | 1150 | 7.1599 |
|
77 |
+
| 7.1401 | 1.65 | 1200 | 7.1593 |
|
78 |
+
| 7.161 | 1.72 | 1250 | 7.1606 |
|
79 |
+
| 7.1513 | 1.78 | 1300 | 7.1564 |
|
80 |
+
| 7.1465 | 1.85 | 1350 | 7.1548 |
|
81 |
+
| 7.1603 | 1.92 | 1400 | 7.1529 |
|
82 |
+
| 7.1203 | 1.99 | 1450 | 7.1533 |
|
83 |
+
| 7.1308 | 2.06 | 1500 | 7.1546 |
|
84 |
+
| 7.1244 | 2.13 | 1550 | 7.1546 |
|
85 |
+
| 7.1437 | 2.2 | 1600 | 7.1561 |
|
86 |
+
| 7.1618 | 2.26 | 1650 | 7.1517 |
|
87 |
+
| 7.1502 | 2.33 | 1700 | 7.1519 |
|
88 |
+
| 7.146 | 2.4 | 1750 | 7.1514 |
|
89 |
+
| 7.1088 | 2.47 | 1800 | 7.1520 |
|
90 |
+
| 7.1335 | 2.54 | 1850 | 7.1483 |
|
91 |
+
| 7.1388 | 2.61 | 1900 | 7.1472 |
|
92 |
+
| 7.1502 | 2.68 | 1950 | 7.1470 |
|
93 |
+
| 7.1511 | 2.75 | 2000 | 7.1479 |
|
94 |
+
| 7.1288 | 2.81 | 2050 | 7.1506 |
|
95 |
+
| 7.1416 | 2.88 | 2100 | 7.1488 |
|
96 |
+
| 7.1568 | 2.95 | 2150 | 7.1512 |
|
97 |
+
| 7.133 | 3.02 | 2200 | 7.1497 |
|
98 |
+
| 7.1178 | 3.09 | 2250 | 7.1501 |
|
99 |
+
| 7.1482 | 3.16 | 2300 | 7.1506 |
|
100 |
+
| 7.1242 | 3.23 | 2350 | 7.1504 |
|
101 |
+
| 7.1181 | 3.29 | 2400 | 7.1497 |
|
102 |
+
| 7.1133 | 3.36 | 2450 | 7.1495 |
|
103 |
+
| 7.1199 | 3.43 | 2500 | 7.1468 |
|
104 |
+
| 7.146 | 3.5 | 2550 | 7.1467 |
|
105 |
+
| 7.1284 | 3.57 | 2600 | 7.1455 |
|
106 |
+
| 7.1356 | 3.64 | 2650 | 7.1464 |
|
107 |
+
| 7.1372 | 3.71 | 2700 | 7.1445 |
|
108 |
+
| 7.1307 | 3.77 | 2750 | 7.1429 |
|
109 |
+
| 7.1407 | 3.84 | 2800 | 7.1427 |
|
110 |
+
| 7.126 | 3.91 | 2850 | 7.1426 |
|
111 |
+
| 7.1288 | 3.98 | 2900 | 7.1425 |
|
112 |
+
| 7.1223 | 4.05 | 2950 | 7.1428 |
|
113 |
+
| 7.1169 | 4.12 | 3000 | 7.1429 |
|
114 |
+
| 7.139 | 4.19 | 3050 | 7.1441 |
|
115 |
+
| 7.1231 | 4.26 | 3100 | 7.1433 |
|
116 |
+
| 7.1114 | 4.32 | 3150 | 7.1429 |
|
117 |
+
| 7.1204 | 4.39 | 3200 | 7.1429 |
|
118 |
+
| 7.0994 | 4.46 | 3250 | 7.1430 |
|
119 |
+
| 7.1039 | 4.53 | 3300 | 7.1434 |
|
120 |
+
| 7.1489 | 4.6 | 3350 | 7.1428 |
|
121 |
+
| 7.1315 | 4.67 | 3400 | 7.1426 |
|
122 |
+
| 7.1173 | 4.74 | 3450 | 7.1426 |
|
123 |
+
| 7.1241 | 4.8 | 3500 | 7.1428 |
|
124 |
+
| 7.1001 | 4.87 | 3550 | 7.1427 |
|
125 |
+
| 7.137 | 4.94 | 3600 | 7.1422 |
|
126 |
+
|
127 |
+
|
128 |
+
### Framework versions
|
129 |
+
|
130 |
+
- Transformers 4.33.1
|
131 |
+
- Pytorch 1.12.1
|
132 |
+
- Datasets 2.14.6
|
133 |
+
- Tokenizers 0.13.3
|
generation_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"pad_token_id": 0,
|
4 |
+
"transformers_version": "4.33.1"
|
5 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 438124333
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22374d04a48b82fc25ffbcc5c716fac09fa64cd372e2b3737278a5c506cdcb28
|
3 |
size 438124333
|