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

update examples

Browse Source 
Former-commit-id: bcb010be7732ae137f156932100ee4d02a93725c
This commit is contained in:
hiyouga
2024-12-05 08:48:25 +00:00
parent c7b27bd70b
commit 39865d8a1f
7 changed files with 13 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/train_full/llama3_full_sft_ds3.yaml → examples/train_full/llama3_full_sft.yaml
View File

@@ -5,7 +5,7 @@ model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
stage: sft
do_train: true
finetuning_type: full
deepspeed: examples/deepspeed/ds_z3_config.json
deepspeed: examples/deepspeed/ds_z3_config.json # choices: [ds_z0_config.json, ds_z2_config.json, ds_z3_config.json]
### dataset
dataset: identity,alpaca_en_demo

7
examples/train_full/qwen2vl_full_sft.yaml
View File

@@ -5,10 +5,11 @@ model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
stage: sft
do_train: true
finetuning_type: full
deepspeed: examples/deepspeed/ds_z3_config.json
freeze_vision_tower: true # choices: [true, false]
deepspeed: examples/deepspeed/ds_z3_config.json # choices: [ds_z0_config.json, ds_z2_config.json, ds_z3_config.json]
### dataset
dataset: mllm_demo,identity
dataset: mllm_demo,identity,alpaca_en_demo
template: qwen2_vl
cutoff_len: 2048
max_samples: 1000
@@ -26,7 +27,7 @@ overwrite_output_dir: true
per_device_train_batch_size: 1
gradient_accumulation_steps: 2
learning_rate: 1.0e-5
num_train_epochs: 3.0
num_train_epochs: 30.0
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: true