p12475398
/
LLaMA-Factory-Mirror
forked from p04798526/LLaMA-Factory-Mirror
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

chore: change yaml

This commit is contained in:
wql 2024-08-22 15:12:08 +08:00
parent fdae778fa7
commit d4cea6f9ac
7 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
results/lora_sft_2/Llama2-7B/llama2_lora_sft_1.yaml
View File

@ -29,7 +29,7 @@ learning_rate: 1.0e-4
num_train_epochs: 10.0 num_train_epochs: 10.0
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
max_steps: 1000 max_steps: 1000
include_num_input_tokens_seen: true include_num_input_tokens_seen: true

2
results/lora_sft_2/Llama2-7B/llama2_lora_sft_1_single.yaml
View File

@ -29,7 +29,7 @@ learning_rate: 1.0e-4
num_train_epochs: 10.0 num_train_epochs: 10.0
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
max_steps: 1000 max_steps: 1000
include_num_input_tokens_seen: true include_num_input_tokens_seen: true

2
results/lora_sft_2/Llama2-7B/llama2_lora_sft_2.yaml
View File

@ -29,7 +29,7 @@ learning_rate: 1.0e-4
num_train_epochs: 10.0 num_train_epochs: 10.0
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
max_steps: 1000 max_steps: 1000
include_num_input_tokens_seen: true include_num_input_tokens_seen: true

2
results/lora_sft_2/Llama2-7B/llama2_lora_sft_2_single.yaml
View File

@ -29,7 +29,7 @@ learning_rate: 1.0e-4
num_train_epochs: 10.0 num_train_epochs: 10.0
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
max_steps: 1000 max_steps: 1000
include_num_input_tokens_seen: true include_num_input_tokens_seen: true

2
results/lora_sft_2/Llama2-7B/llama2_lora_sft_3.yaml
View File

@ -29,7 +29,7 @@ learning_rate: 1.0e-4
num_train_epochs: 10.0 num_train_epochs: 10.0
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
max_steps: 1000 max_steps: 1000
include_num_input_tokens_seen: true include_num_input_tokens_seen: true

2
results/lora_sft_2/Llama2-7B/llama2_lora_sft_3_single.yaml
View File

@ -29,7 +29,7 @@ learning_rate: 1.0e-4
num_train_epochs: 10.0 num_train_epochs: 10.0
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
max_steps: 1000 max_steps: 1000
include_num_input_tokens_seen: true include_num_input_tokens_seen: true

2
results/lora_sft_2/test/test1.yaml
View File

@ -29,7 +29,7 @@ learning_rate: 1.0e-4
num_train_epochs: 10.0 num_train_epochs: 10.0
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
max_steps: 1000 max_steps: 1000
include_num_input_tokens_seen: true include_num_input_tokens_seen: true