File size: 1,597 Bytes
ab77cfe |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
dataset:
align_stage_components:
- download/videollava/valley_llavaimage.json
- download/videollava
dataset_id: videollava
dataset_root_dir: data
finetune_stage_components:
- download/videollava/videochatgpt_llavaimage_tune.json
- download/videollava
type: videollava
dataset_class: FinetuneVideoDataset
hf_token: .hf_token
model:
align_epochs: 1
align_global_batch_size: 256
align_learning_rate: 0.001
align_lr_scheduler_type: linear-warmup+cosine-decay
align_max_grad_norm: 1.0
align_max_steps: null
align_per_device_batch_size: 16
align_train_strategy: fsdp-shard-grad-op
align_warmup_ratio: 0.03
align_weight_decay: 0.0
arch_specifier: no-align+linear
enable_gradient_checkpointing: true
enable_mixed_precision_training: true
feature_fusion: first
finetune_epochs: 1
finetune_global_batch_size: 128
finetune_learning_rate: 2.0e-05
finetune_lr_scheduler_type: linear-warmup+cosine-decay
finetune_max_grad_norm: 1.0
finetune_max_steps: null
finetune_per_device_batch_size: 4
finetune_train_strategy: fsdp-full-shard
finetune_warmup_ratio: 0.03
finetune_weight_decay: 0.1
image_resize_strategy: resize-naive
llm_backbone_id: llama2-7b-pure
llm_max_length: 2048
model_id: languagebind-single
num_frames:
- 16
projector_token_length: 64
reduce_in_full_precision: false
type: languagebind-single
video_backbone_ids:
- languagebind-video
visual_feature_length: 4112
pretrained_checkpoint: null
run_id: languagebind-single
run_root_dir: runs
seed: 7
slurm_id: '441692'
stage: finetune
trackers:
- jsonl
- wandb
|