apunkt/doc-to-lora
1
0
Fork 0
mirror of https://github.com/SakanaAI/doc-to-lora.git synced 2026-07-23 17:01:04 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

set lr to 1e-5

Browse source
This commit is contained in:
51616 2025-01-06 11:57:52 +00:00
parent a6104c2c68
commit 03cefa7f13
4 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

2
configs/context_numbers_128.yaml
View file

@ -20,7 +20,7 @@ per_device_train_batch_size: 64
per_device_eval_batch_size: 64
max_val_samples_per_ds: 50
# optim: schedule_free_adamw
learning_rate: 0.0001
learning_rate: 0.00001
# lr_scheduler_type: "constant_with_warmup"
neftune_noise_alpha: 1
weight_decay: 0.1

2
configs/context_numbers_256.yaml
View file

@ -20,7 +20,7 @@ per_device_train_batch_size: 32
per_device_eval_batch_size: 32
max_val_samples_per_ds: 20
# optim: schedule_free_adamw
learning_rate: 0.0001
learning_rate: 0.00001
# lr_scheduler_type: "constant_with_warmup"
neftune_noise_alpha: 1
weight_decay: 0.1

2
configs/pwc.yaml
View file

@ -20,7 +20,7 @@ per_device_train_batch_size: 32
per_device_eval_batch_size: 32
max_val_samples_per_ds: 20
# optim: schedule_free_adamw
learning_rate: 0.0001
learning_rate: 0.00001
# lr_scheduler_type: "constant_with_warmup"
neftune_noise_alpha: 1
weight_decay: 0.1

2
configs/pwc_and_ctx_numbers_256.yaml
View file

@ -20,7 +20,7 @@ per_device_train_batch_size: 32
per_device_eval_batch_size: 32
max_val_samples_per_ds: 20
# optim: schedule_free_adamw
learning_rate: 0.0001
learning_rate: 0.00001
# lr_scheduler_type: "constant_with_warmup"
neftune_noise_alpha: 1
weight_decay: 0.1