Downloads · 30 days
7
17% of all-time downloads
byt5_ft_all_clean_data_ws3000
jenspt/byt5_ft_all_clean_data_ws3000
byt5_ft_all_clean_data_ws3000 is a machine learning model from jenspt. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
trainingargs = TrainingArguments( outputdir='./results', output directory numtrainepochs=1, total number of training epochs perdevicetrainbatchsize=8, batch size per device during training perdeviceevalbatchsize=2, ba…
All-time downloads
41
Public
Repo size
2.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.2 GB · 100%
At a glance
- Library
- transformers
- Model type
- t5
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Dec 3, 2021
- SHA
- fbac5e20
Model card
From the Hugging Face model README
training_args = TrainingArguments( output_dir='./results', # output directory num_train_epochs=1, # total number of training epochs per_device_train_batch_size=8, # batch size per device during training #per_device_eval_batch_size=2, # batch size for evaluation warmup_steps=3000, # number of warmup steps for learning rate scheduler (used to be 500) weight_decay=0.01, # strength of weight decay #learning_rate=0.1e-3, # default = 5e-5=0.5e-4 logging_dir='./logs', # directory for storing logs logging_steps=50, #eval_steps = 100, overwrite_output_dir = True, save_strategy = 'epoch', #logging_strategy = 'epoch', )
- Library
- transformers
- Type
- t5
- Created
- Mar 2, 2022
- Updated
- Dec 3, 2021