minigpt4 / train_configs /minigpt4_stage2_align.yaml
Vision-CAIR's picture
Upload 89 files
181722d
# Copyright (c) 2022, salesforce.com, inc.
# All rights reserved.
# SPDX-License-Identifier: BSD-3-Clause
# For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause
model:
arch: mini_gpt4
model_type: pretrain_vicuna
freeze_vit: True
freeze_qformer: True
max_txt_len: 160
end_sym: "###"
prompt_path: "prompts/alignment.txt"
prompt_template: '###Human: {} ###Assistant: '
ckpt: '/ibex/project/c2133/vicuna_jun_checkpoint_wihtout_prompt/20230412162/checkpoint_3.pth'
datasets:
cc_align:
vis_processor:
train:
name: "blip2_image_train"
image_size: 224
text_processor:
train:
name: "blip_caption"
run:
task: image_text_pretrain
# optimizer
lr_sched: "linear_warmup_cosine_lr"
init_lr: 3e-5
min_lr: 1e-5
warmup_lr: 1e-6
weight_decay: 0.05
max_epoch: 5
iters_per_epoch: 200
batch_size_train: 12
batch_size_eval: 12
num_workers: 4
warmup_steps: 200
seed: 42
output_dir: "/ibex/project/c2133/vicuna_ckpt_test/minigpt4_stage2_align"
amp: True
resume_ckpt_path: null
evaluate: False
train_splits: ["train"]
device: "cuda"
world_size: 1
dist_url: "env://"
distributed: True