Cleaning up some new config files

This commit is contained in:
Jake Poznanski 2025-08-04 20:49:33 +00:00
parent d7cb315878
commit 66c7d823b5
41 changed files with 2 additions and 1 deletions

View File

@ -2,7 +2,7 @@
# Project metadata
project_name: olmocr-qwen-vl-training
run_name: qwen2.5-vl-7b-olmocrv2_1epoch_compile_v2
run_name: qwen2.5-vl-7b-olmocrv3_1epoch_prompt_first
# Model configuration
model:
@ -37,6 +37,7 @@ dataset:
- name: NewYamlFinetuningPromptWithNoAnchoring
- name: FrontMatterOutputFormat
- name: InstructUserMessages
prompt_first: true
- name: Tokenizer
masking_index: -100
end_of_message_token: "<|im_end|>"