Downloads · 30 days
0
ad6398/colqwen-mpdocvqa-21-4-1k
colqwen-mpdocvqa-21-4-1k is a machine learning model from ad6398. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Finetune on MPDocVQA for one epoch with following parameters on H200
Downloads · 30 days
0
Access
Public
Updated Apr 22, 2025
Repo size
372 MB
Likes
0
Public
Click a slice to open those files.
.pt240 MB · 64%
From the Hugging Face model README
Finetune on MPDocVQA for one epoch with following parameters on H200
QUANTIZATION_STRATEGY ="bf16" SEED = 42
EPOCHS = 1 BATCH_SIZE_TRAIN = 16 BATCH_SIZE_EVAL = 16 GRADIENT_ACCUM_STEPS = 2 WARMUP_STEPS = 20 LEARNING_RATE = 5e-5 SAVE_STEPS = 100 EVAL_STEPS = 10 LOGGING_STEPS = 1 SAVE_TOTAL_LIMIT = 5 REPORT_TO = ["wandb"] GRADIENT_CHECKPOINTING = False EVAL_STRATEGY = "steps"