|
wandb_version: 1 |
|
|
|
model: |
|
desc: null |
|
value: |
|
type: one-stage+7b |
|
model_id: one-stage+7b_qformer2_256 |
|
arch_specifier: qformer2_256 |
|
vision_backbone_id: clip-vit-l-336px |
|
llm_backbone_id: vicuna-v15-7b |
|
image_resize_strategy: letterbox |
|
llm_max_length: 2048 |
|
align_epochs: 1 |
|
align_max_steps: null |
|
align_global_batch_size: 256 |
|
align_per_device_batch_size: 16 |
|
align_learning_rate: 0.001 |
|
align_weight_decay: 0.0 |
|
align_max_grad_norm: 1.0 |
|
align_lr_scheduler_type: linear-warmup+cosine-decay |
|
align_warmup_ratio: 0.03 |
|
align_train_strategy: fsdp-shard-grad-op |
|
finetune_epochs: 1 |
|
finetune_max_steps: null |
|
finetune_global_batch_size: 128 |
|
finetune_per_device_batch_size: 16 |
|
finetune_learning_rate: 2.0e-05 |
|
finetune_weight_decay: 0.1 |
|
finetune_max_grad_norm: 1.0 |
|
finetune_lr_scheduler_type: linear-warmup+cosine-decay |
|
finetune_warmup_ratio: 0.03 |
|
finetune_train_strategy: fsdp-full-shard |
|
enable_gradient_checkpointing: true |
|
enable_mixed_precision_training: true |
|
reduce_in_full_precision: false |
|
dataset: |
|
desc: null |
|
value: |
|
type: llava-v15 |
|
dataset_id: llava-v15 |
|
align_stage_components: |
|
- download/llava-laion-cc-sbu-558k/chat.json |
|
- download/llava-laion-cc-sbu-558k |
|
finetune_stage_components: |
|
- download/llava-v1.5-instruct/llava_v1_5_mix665k.json |
|
- download/llava-v1.5-instruct |
|
dataset_root_dir: data |
|
stage: |
|
desc: null |
|
value: finetune |
|
pretrained_checkpoint: |
|
desc: null |
|
value: /home/lilei/prismatic-vlms/runs/llava-qformer/stage1_qformer2_256/checkpoints/latest-checkpoint.pt |
|
run_id: |
|
desc: null |
|
value: s1_s2_qformer2_256 |
|
run_root_dir: |
|
desc: null |
|
value: runs |
|
seed: |
|
desc: null |
|
value: 7 |
|
hf_token: |
|
desc: null |
|
value: .hf_token |
|
trackers: |
|
desc: null |
|
value: |
|
- jsonl |
|
- wandb |
|
wandb_project: |
|
desc: null |
|
value: hf-vlms |
|
wandb_entity: |
|
desc: null |
|
value: lilei_stones |
|
max_length: |
|
desc: null |
|
value: 4096 |
|
_wandb: |
|
desc: null |
|
value: |
|
python_version: 3.10.13 |
|
cli_version: 0.16.3 |
|
framework: huggingface |
|
huggingface_version: 4.38.1 |
|
is_jupyter_run: false |
|
is_kaggle_kernel: false |
|
start_time: 1710329288.064789 |
|
t: |
|
1: |
|
- 1 |
|
- 11 |
|
- 41 |
|
- 49 |
|
- 51 |
|
- 55 |
|
- 63 |
|
- 71 |
|
2: |
|
- 1 |
|
- 11 |
|
- 41 |
|
- 49 |
|
- 51 |
|
- 55 |
|
- 63 |
|
- 71 |
|
3: |
|
- 2 |
|
- 13 |
|
- 16 |
|
- 23 |
|
4: 3.10.13 |
|
5: 0.16.3 |
|
6: 4.38.1 |
|
8: |
|
- 5 |
|
13: linux-x86_64 |
|
|