tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

use warmup_ratio as a better default than warmup steps since it's data dependent (#2897) [skip ci]

Browse Source 
* use warmup_ratio as a better default than warmup steps since it's data dependent

* replace remainder of warmup_steps
This commit is contained in:
Wing Lian
2025-07-30 06:44:06 -04:00
committed by GitHub
parent 2eb7ff95af
commit 22810c97b7
99 changed files with 100 additions and 100 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/archived/falcon/config-7b-lora.yml
View File

@@ -47,7 +47,7 @@ xformers_attention: true
flash_attention:
gptq_groupsize:
gptq_model_v1:
warmup_steps: 40
warmup_ratio: 0.1
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.0

2
examples/archived/falcon/config-7b-qlora.yml
View File

@@ -77,7 +77,7 @@ xformers_attention: true
flash_attention:
gptq_groupsize:
gptq_model_v1:
warmup_steps: 10
warmup_ratio: 0.1
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.000001

2
examples/archived/falcon/config-7b.yml
View File

@@ -44,7 +44,7 @@ xformers_attention: true
flash_attention:
gptq_groupsize:
gptq_model_v1:
warmup_steps: 40
warmup_ratio: 0.1
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.0