forked from p04798526/LLaMA-Factory-Mirror
update examples
This commit is contained in:
parent
8baf3b22b0
commit
2f78b5d62a
|
@ -30,7 +30,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -31,7 +31,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -30,7 +30,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -32,7 +32,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -29,7 +29,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -31,7 +31,7 @@ learning_rate: 5.0e-6
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -30,7 +30,7 @@ learning_rate: 5.0e-6
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -30,7 +30,7 @@ learning_rate: 1.0e-5
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### generate
|
### generate
|
||||||
|
|
|
@ -28,7 +28,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -25,11 +25,11 @@ overwrite_output_dir: true
|
||||||
### train
|
### train
|
||||||
per_device_train_batch_size: 1
|
per_device_train_batch_size: 1
|
||||||
gradient_accumulation_steps: 8
|
gradient_accumulation_steps: 8
|
||||||
learning_rate: 1.0e-5
|
learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -29,7 +29,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -30,7 +30,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -30,7 +30,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -30,7 +30,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -29,7 +29,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -29,7 +29,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -29,7 +29,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
|
@ -31,7 +31,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 3.0
|
num_train_epochs: 3.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
|
|
||||||
### eval
|
### eval
|
||||||
|
|
Loading…
Reference in New Issue