storytold/FineTrainers-Conditioning
2
0
Fork 0
mirror of https://github.com/storytold/FineTrainers-Conditioning.git synced 2026-10-20 07:45:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixed optimizers parsing error in bash scripts (#61)

Browse Source 
* replaced lambda statements with local functions to work with pickle in dataset.py and moved collate function outside of main and added its own class in cogvideox_image_to_video_lora.py

* fixed merge issue

* fixed row deletion merge

* fixed row deletion merge

* fixed comma-separated param issue in bash
This commit is contained in:
Johan Mellin
2024-10-21 00:30:51 +02:00
committed by GitHub
parent db9b295408
commit 7a6dff2d9f
4 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -78,7 +78,7 @@ Before starting the training, please check whether the dataset has been prepared
```bash ```bash
LEARNING_RATES=("1e-4" "1e-3") LEARNING_RATES=("1e-4" "1e-3")
LR_SCHEDULES=("cosine_with_restarts") LR_SCHEDULES=("cosine_with_restarts")
OPTIMIZERS=("adamw", "adam") OPTIMIZERS=("adamw" "adam")
MAX_TRAIN_STEPS=("3000") MAX_TRAIN_STEPS=("3000")
``` ```
README_zh.md
+1 -1
View File
@@ -77,7 +77,7 @@ diffusers（该分支为 CogVideoX 的图像到视频添加了 LoRA 加载支持
``` ```
LEARNING_RATES=("1e-4" "1e-3") LEARNING_RATES=("1e-4" "1e-3")
LR_SCHEDULES=("cosine_with_restarts") LR_SCHEDULES=("cosine_with_restarts")
OPTIMIZERS=("adamw", "adam") OPTIMIZERS=("adamw" "adam")
MAX_TRAIN_STEPS=("3000") MAX_TRAIN_STEPS=("3000")
``` ```
train_image_to_video_lora.sh
+1 -1
View File
@@ -10,7 +10,7 @@ GPU_IDS="0"
# Experiment with as many hyperparameters as you want! # Experiment with as many hyperparameters as you want!
LEARNING_RATES=("1e-4" "1e-3") LEARNING_RATES=("1e-4" "1e-3")
LR_SCHEDULES=("cosine_with_restarts") LR_SCHEDULES=("cosine_with_restarts")
OPTIMIZERS=("adamw", "adam") OPTIMIZERS=("adamw" "adam")
MAX_TRAIN_STEPS=("3000") MAX_TRAIN_STEPS=("3000")
# Single GPU uncompiled training # Single GPU uncompiled training
train_text_to_video_lora.sh
+1 -1
View File
@@ -10,7 +10,7 @@ GPU_IDS="0"
# Experiment with as many hyperparameters as you want! # Experiment with as many hyperparameters as you want!
LEARNING_RATES=("1e-4" "1e-3") LEARNING_RATES=("1e-4" "1e-3")
LR_SCHEDULES=("cosine_with_restarts") LR_SCHEDULES=("cosine_with_restarts")
OPTIMIZERS=("adamw", "adam") OPTIMIZERS=("adamw" "adam")
MAX_TRAIN_STEPS=("3000") MAX_TRAIN_STEPS=("3000")
# Single GPU uncompiled training # Single GPU uncompiled training