metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert-base-chinese-finetuning-wallstreetcn-morning-news-vix-sz50-v1
results: []
language:
- zh
widget:
- >-
text:A股创业板六年新高；纳指跌落高位，标普又新高，创史上第二大中概IPO和今年美股最大IPO的滴滴首日冲高回落，市值破800亿美元，叮咚买菜次日涨逾60%；美元逾两月新高，金银铜6月大跌，原油半年涨超50%。\n中国6月官方制造业PMI为50.9，价格指数从高位回落。\n央行等六部门：充分发挥信贷等金融子市场合力，增强政策的针对性和可操作性。\n人社部
“十四五”
发展规划要求，基本养老保险参保率达95％，城镇新增就业逾5000万人。\n沪深交所7月19日起下调基金交易经手费收费标准。\n奈雪的茶赴港上市首日破发，收盘大跌14%，市值跌破300亿港元。\n港股上市倒计时，小鹏汽车定价165港元/股。\n格力2020股东会通过员工持股计划等议案，董明珠称接班人不是我说你行就行，是你能行才行。\n美国6月小非农ADP新增就业高于预期，绝对值较5月有所回落。\n美联储逆回购用量史上首次逼近1万亿美元。\n媒体称拜登最早下周颁布新行政令，限制多个行业的寡头垄断。\n亚马逊称FTC新任主席有偏见，寻求其回避反垄断调查。\n散户最爱平台Robinhood遭FINRA创纪录罚款7000万美元，被指坑害百万客户。
bert-base-chinese-finetuning-wallstreetcn-morning-news-vix-sz50-v1
This model is a fine-tuned version of bert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0050
- Accuracy: 0.6538
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 19 | 0.6986 | 0.5 |
| No log | 2.0 | 38 | 0.6988 | 0.5 |
| No log | 3.0 | 57 | 0.7804 | 0.5 |
| No log | 4.0 | 76 | 0.6912 | 0.5 |
| No log | 5.0 | 95 | 0.8595 | 0.5192 |
| No log | 6.0 | 114 | 0.7574 | 0.5962 |
| No log | 7.0 | 133 | 1.6235 | 0.6154 |
| No log | 8.0 | 152 | 1.2308 | 0.6346 |
| No log | 9.0 | 171 | 1.1341 | 0.6923 |
| No log | 10.0 | 190 | 1.0050 | 0.6538 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3