fix eval_steps to be a sane default (#797)

* fix eval_steps to be a sane default

* update docs for fractional eval_steps

examples/llama-2/gptq-lora.yml

@@ -37,7 +37,7 @@ wandb_log_model:
 output_dir: ./model-out
 gradient_accumulation_steps: 1
 micro_batch_size: 1
-num_epochs: 3
+num_epochs: 4
 optimizer: adamw_torch
 adam_beta2: 0.95
 adam_eps: 0.00001

examples/llama-2/lora.yml

@@ -34,7 +34,7 @@ wandb_log_model:
 
 gradient_accumulation_steps: 4
 micro_batch_size: 2
-num_epochs: 3
+num_epochs: 4
 optimizer: adamw_bnb_8bit
 lr_scheduler: cosine
 learning_rate: 0.0002
@@ -54,7 +54,7 @@ xformers_attention:
 flash_attention: true
 
 warmup_steps: 10
-eval_steps: 20
+eval_steps: 0.05
 eval_table_size:
 eval_table_max_new_tokens: 128
 save_steps:

examples/llama-2/qlora.yml

@@ -36,7 +36,7 @@ wandb_log_model:
 
 gradient_accumulation_steps: 4
 micro_batch_size: 2
-num_epochs: 3
+num_epochs: 4
 optimizer: paged_adamw_32bit
 lr_scheduler: cosine
 learning_rate: 0.0002
@@ -56,7 +56,7 @@ xformers_attention:
 flash_attention: true
 
 warmup_steps: 10
-eval_steps: 20
+eval_steps: 0.05
 eval_table_size:
 save_steps:
 debug:

examples/llama-2/relora.yml

@@ -40,7 +40,7 @@ wandb_log_model:
 
 gradient_accumulation_steps: 4
 micro_batch_size: 4
-num_epochs: 3
+num_epochs: 4
 optimizer: adamw_bnb_8bit
 lr_scheduler: cosine
 learning_rate: 0.0002
@@ -60,7 +60,7 @@ xformers_attention:
 flash_attention: true
 
 warmup_steps: 10
-eval_steps: 20
+eval_steps: 0.05
 save_steps: 50
 debug:
 deepspeed:

examples/llama-2/tiny-llama.yml

@@ -34,7 +34,7 @@ wandb_log_model:
 
 gradient_accumulation_steps: 4
 micro_batch_size: 2
-num_epochs: 3
+num_epochs: 4
 optimizer: adamw_bnb_8bit
 lr_scheduler: cosine
 learning_rate: 0.0002
@@ -54,7 +54,7 @@ xformers_attention:
 flash_attention: true
 
 warmup_steps: 10
-eval_steps: 20
+eval_steps: 0.05
 eval_table_size:
 save_steps:
 debug: