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

* use warmup_ratio as a better default than warmup steps since it's data dependent * replace remainder of warmup_steps
2025-07-30 06:44:06 -04:00
parent 2eb7ff95af
commit 22810c97b7
99 changed files with 100 additions and 100 deletions
--- a/examples/mistral/config.yml
+++ b/examples/mistral/config.yml
@@ -38,7 +38,7 @@ resume_from_checkpoint:
 logging_steps: 1
 flash_attention: true

-warmup_steps: 10
+warmup_ratio: 0.1
 evals_per_epoch: 4
 saves_per_epoch: 1
 weight_decay: 0.0
--- a/examples/mistral/lora-mps.yml
+++ b/examples/mistral/lora-mps.yml
@@ -59,7 +59,7 @@ sdp_attention: true
 loss_watchdog_threshold: 5.0
 loss_watchdog_patience: 3

-warmup_steps: 10
+warmup_ratio: 0.1
 evals_per_epoch: 4
 saves_per_epoch: 1
 weight_decay: 0.0
--- a/examples/mistral/lora.yml
+++ b/examples/mistral/lora.yml
@@ -59,7 +59,7 @@ flash_attention: true
 loss_watchdog_threshold: 5.0
 loss_watchdog_patience: 3

-warmup_steps: 10
+warmup_ratio: 0.1
 evals_per_epoch: 4
 saves_per_epoch: 1
 weight_decay: 0.0
--- a/examples/mistral/mistral-dpo-qlora.yml
+++ b/examples/mistral/mistral-dpo-qlora.yml
@@ -73,7 +73,7 @@ resume_from_checkpoint:
 logging_steps: 1
 flash_attention: false

-warmup_steps: 10
+warmup_ratio: 0.1
 evals_per_epoch: 4
 saves_per_epoch: 1
 weight_decay: 0.0
--- a/examples/mistral/mistral-qlora-fsdp.yml
+++ b/examples/mistral/mistral-qlora-fsdp.yml
@@ -56,7 +56,7 @@ flash_attention: true
 loss_watchdog_threshold: 5.0
 loss_watchdog_patience: 3

-warmup_steps: 10
+warmup_ratio: 0.1
 evals_per_epoch: 4
 saves_per_epoch: 1

--- a/examples/mistral/mistral-qlora-orpo.yml
+++ b/examples/mistral/mistral-qlora-orpo.yml
@@ -64,7 +64,7 @@ flash_attention: true
 loss_watchdog_threshold: 5.0
 loss_watchdog_patience: 3

-warmup_steps: 10
+warmup_ratio: 0.1
 evals_per_epoch: 4
 saves_per_epoch: 1
 weight_decay: 0.0
--- a/examples/mistral/mixtral-8x22b-qlora-fsdp.yml
+++ b/examples/mistral/mixtral-8x22b-qlora-fsdp.yml
@@ -54,7 +54,7 @@ flash_attention: true
 loss_watchdog_threshold: 5.0
 loss_watchdog_patience: 3

-warmup_steps: 10
+warmup_ratio: 0.1
 evals_per_epoch: 4
 saves_per_epoch: 1

--- a/examples/mistral/mixtral-qlora-fsdp.yml
+++ b/examples/mistral/mixtral-qlora-fsdp.yml
@@ -56,7 +56,7 @@ flash_attention: true
 loss_watchdog_threshold: 5.0
 loss_watchdog_patience: 3

-warmup_steps: 10
+warmup_ratio: 0.1
 evals_per_epoch: 4
 saves_per_epoch: 1

--- a/examples/mistral/mixtral.yml
+++ b/examples/mistral/mixtral.yml
@@ -74,7 +74,7 @@ flash_attention: true
 loss_watchdog_threshold: 5.0
 loss_watchdog_patience: 3

-warmup_steps: 10
+warmup_ratio: 0.1
 evals_per_epoch: 4
 saves_per_epoch: 1

--- a/examples/mistral/qlora.yml
+++ b/examples/mistral/qlora.yml
@@ -59,7 +59,7 @@ flash_attention: true
 loss_watchdog_threshold: 5.0
 loss_watchdog_patience: 3

-warmup_steps: 10
+warmup_ratio: 0.1
 evals_per_epoch: 4
 saves_per_epoch: 1
 weight_decay: 0.0