Downloads · 30 days
0
midjourney-falcon-7b-beta1
RoversX/midjourney-falcon-7b-beta1
midjourney-falcon-7b-beta1 is a machine learning model from RoversX. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Access
Public
Updated Jul 28, 2023
Repo size
18.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin18.9 MB · 100%
At a glance
- Access
- Public
- Created
- Jul 28, 2023
- Updated
- Jul 28, 2023
- SHA
- a3796d54
Model card
From the Hugging Face model README
Model Card for Model ID
Using Google Colab
training_args = transformers.TrainingArguments(
per_device_train_batch_size=1,
gradient_accumulation_steps=4,
num_train_epochs=3,
learning_rate=2e-4,
fp16=True,
save_total_limit=3,
logging_steps=1,
output_dir="experiments",
optim="paged_adamw_8bit",
lr_scheduler_type="cosine",
warmup_ratio=0.05,
)
trainer = transformers.Trainer(
model=model,
train_dataset=data,
args=training_args,
data_collator=transformers.DataCollatorForLanguageModeling(tokenizer, mlm=False)
)
model.config.use_cache = False
trainer.train()
TrainOutput(global_step=216, training_loss=1.8804574598454766, metrics={'train_runtime': 306.7499, 'train_samples_per_second': 2.826, 'train_steps_per_second': 0.704, 'total_flos': 1277315019871488.0, 'train_loss': 1.8804574598454766, 'epoch': 2.99})
- Created
- Jul 28, 2023
- Updated
- Jul 28, 2023