new evals_per_epoch and saves_per_epoch to make things cleaner (#944)

* new evals_per_epoch and saves_per_epoch to make things cleaner * update per PR feedback
2023-12-12 15:35:23 -05:00
parent f1de29dd1e
commit 5f79b8242f
37 changed files with 102 additions and 70 deletions
--- a/examples/code-llama/13b/lora.yml
+++ b/examples/code-llama/13b/lora.yml
@@ -54,8 +54,8 @@ xformers_attention:
 flash_attention: true

 warmup_steps: 10
-eval_steps: 0.05
-save_steps:
+evals_per_epoch: 4
+saves_per_epoch: 1
 debug:
 deepspeed:
 weight_decay: 0.0
--- a/examples/code-llama/13b/qlora.yml
+++ b/examples/code-llama/13b/qlora.yml
@@ -56,8 +56,8 @@ xformers_attention:
 flash_attention: true

 warmup_steps: 10
-eval_steps: 0.05
-save_steps:
+evals_per_epoch: 4
+saves_per_epoch: 1
 debug:
 deepspeed:
 weight_decay: 0.0
--- a/examples/code-llama/34b/lora.yml
+++ b/examples/code-llama/34b/lora.yml
@@ -54,8 +54,8 @@ xformers_attention:
 flash_attention: true

 warmup_steps: 10
-eval_steps: 0.05
-save_steps:
+evals_per_epoch: 4
+saves_per_epoch: 1
 debug:
 deepspeed:
 weight_decay: 0.0
--- a/examples/code-llama/34b/qlora.yml
+++ b/examples/code-llama/34b/qlora.yml
@@ -56,8 +56,8 @@ xformers_attention:
 flash_attention: true

 warmup_steps: 10
-eval_steps: 0.05
-save_steps:
+evals_per_epoch: 4
+saves_per_epoch: 1
 debug:
 deepspeed:
 weight_decay: 0.0
--- a/examples/code-llama/7b/lora.yml
+++ b/examples/code-llama/7b/lora.yml
@@ -54,8 +54,8 @@ xformers_attention:
 flash_attention: true

 warmup_steps: 10
-eval_steps: 0.05
-save_steps:
+evals_per_epoch: 4
+saves_per_epoch: 1
 debug:
 deepspeed:
 weight_decay: 0.0
--- a/examples/code-llama/7b/qlora.yml
+++ b/examples/code-llama/7b/qlora.yml
@@ -56,8 +56,8 @@ xformers_attention:
 flash_attention: true

 warmup_steps: 10
-eval_steps: 0.05
-save_steps:
+evals_per_epoch: 4
+saves_per_epoch: 1
 debug:
 deepspeed:
 weight_decay: 0.0