ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update examples

Browse Source 
Former-commit-id: 779603055ae9216ff549f5285caac8c0c0a1e9fb
This commit is contained in:
hiyouga
2024-05-13 20:39:36 +08:00
parent 5f5f948806
commit e4972c8fc4
22 changed files with 36 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/extras/badam/llama3_lora_sft.yaml
View File

@@ -15,7 +15,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@@ -36,6 +35,7 @@ warmup_steps: 0.1
pure_bf16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

5
examples/extras/fsdp_qlora/llama3_lora_sft.yaml
View File

@@ -8,12 +8,14 @@ do_train: true
finetuning_type: lora
lora_target: q_proj,v_proj
# ddp
ddp_timeout: 180000000
# dataset
dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@@ -34,6 +36,7 @@ warmup_steps: 0.1
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/extras/galore/llama3_full_sft.yaml
View File

@@ -16,7 +16,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@@ -37,6 +36,7 @@ warmup_steps: 0.1
pure_bf16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

4
examples/extras/llama_pro/llama3_freeze_sft.yaml
View File

@@ -14,7 +14,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@@ -32,9 +31,10 @@ learning_rate: 0.0001
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_steps: 0.1
pure_bf16: true
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

4
examples/extras/loraplus/llama3_lora_sft.yaml
View File

@@ -13,7 +13,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@@ -31,9 +30,10 @@ learning_rate: 0.0001
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_steps: 0.1
pure_bf16: true
fp16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

2
examples/extras/mod/llama3_full_sft.yaml
View File

@@ -12,7 +12,6 @@ dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
@@ -34,6 +33,7 @@ warmup_steps: 0.1
pure_bf16: true
# eval
val_size: 0.1
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500