From c93a5b8b8f54b63d92577bf75ba1e1c0122ada1a Mon Sep 17 00:00:00 2001
From: wql <wengqinlan18@163.com>
Date: Tue, 20 Aug 2024 09:42:58 +0800
Subject: [PATCH] add: add include_num_input_tokens_seen

---
 .../llama2_lora_sft_1_test_token.yaml         | 41 +++++++++++++++++++
 1 file changed, 41 insertions(+)
 create mode 100644 results/lora_sft/Llama2-7B_2/llama2_lora_sft_1_test_token.yaml

diff --git a/results/lora_sft/Llama2-7B_2/llama2_lora_sft_1_test_token.yaml b/results/lora_sft/Llama2-7B_2/llama2_lora_sft_1_test_token.yaml
new file mode 100644
index 00000000..dd8f4233
--- /dev/null
+++ b/results/lora_sft/Llama2-7B_2/llama2_lora_sft_1_test_token.yaml
@@ -0,0 +1,41 @@
+### model
+model_name_or_path: modelscope/Llama-2-7b-ms
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: llama2
+cutoff_len: 1024
+max_samples: 10000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: ./results/lora_sft/Llama2-7B_2/llama2_lora_sft_1_test_token
+logging_steps: 3
+save_steps: 100
+plot_loss: true
+overwrite_output_dir: true
+
+### train
+per_device_train_batch_size: 2
+gradient_accumulation_steps: 8
+learning_rate: 1.0e-4
+num_train_epochs: 10.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+bf16: true
+ddp_timeout: 180000000
+max_steps: 100
+include_num_input_tokens_seen: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 2
+eval_strategy: steps
+eval_steps: 500
\ No newline at end of file