yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-12-02 10:10:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Mini train config

Browse Source
This commit is contained in:
Jake Poznanski 2024-10-03 10:32:15 -07:00
parent 4505a49420
commit 2227605bfb
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
pdelfin/train/config/qwen2vl-7b-lora.yaml
View File

@ -30,16 +30,16 @@ train_data:
sources:
- name: openai_batch_data_v5_1_eval # TODO This is just for testing the job, once ready change to a real train dataset
query_glob_path: s3://ai2-oe-data/jakep/pdfdata/openai_batch_data_v5_1_eval/*.jsonl
response_glob_path: s3://ai2-oe-data/jakep/pdfdata/openai_batch_done_v5_1_eval/*.jsonl
response_glob_path: s3://ai2-oe-data/jakep/pdfdata/openai_batch_done_v5_1_eval/*.json
valid_data:
sources:
- name: openai_batch_data_v5_1_eval
query_glob_path: s3://ai2-oe-data/jakep/pdfdata/openai_batch_data_v5_1_eval/*.jsonl
response_glob_path: s3://ai2-oe-data/jakep/pdfdata/openai_batch_done_v5_1_eval/*.jsonl
response_glob_path: s3://ai2-oe-data/jakep/pdfdata/openai_batch_done_v5_1_eval/*.json
- name: openai_batch_data_v5_1_iabooks_eval
query_glob_path: s3://ai2-oe-data/jakep/pdfdata/openai_batch_data_v5_1_iabooks_eval/*.jsonl
response_glob_path: s3://ai2-oe-data/jakep/pdfdata/openai_batch_done_v5_1_iabooks_eval/*.jsonl
response_glob_path: s3://ai2-oe-data/jakep/pdfdata/openai_batch_done_v5_1_iabooks_eval/*.json
@ -51,7 +51,7 @@ hparams:
gradient_checkpointing: false
clip_grad_norm: 1.0
learning_rate: 3e-4
max_steps: 2000
max_steps: 500
pad_multiple_of: 16
log_every_steps: 50
eval_every_steps: 100