| dataset: |
| align_stage_components: |
| - download/llava-laion-cc-sbu-558k/chat.json |
| - download/llava-laion-cc-sbu-558k |
| dataset_id: llava-v15 |
| dataset_root_dir: data |
| finetune_stage_components: |
| - download/llava-v1.5-instruct/llava_v1_5_mix665k.json |
| - download/llava-v1.5-instruct |
| type: llava-v15 |
| hf_token: hf_token.txt |
| model: |
| align_epochs: 1 |
| align_global_batch_size: 8 |
| 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: 8 |
| align_train_strategy: fsdp-shard-grad-op |
| align_warmup_ratio: 0.03 |
| align_weight_decay: 0.0 |
| arch_specifier: no-align+fused-gelu-mlp |
| enable_gradient_checkpointing: true |
| enable_mixed_precision_training: true |
| finetune_epochs: 2 |
| finetune_global_batch_size: 192 |
| 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: 24 |
| finetune_train_strategy: fsdp-full-shard |
| finetune_warmup_ratio: 0.03 |
| finetune_weight_decay: 0.1 |
| image_resize_strategy: resize-naive |
| llm_backbone_id: moxin-7b-pure |
| llm_max_length: 2048 |
| model_id: prism-moxin-dinosiglip-224px+7b |
| reduce_in_full_precision: false |
| type: prism-moxin-dinosiglip-224px+7b |
| vision_backbone_id: dinosiglip-vit-so-224px |
| pretrained_checkpoint: null |
| run_id: prism-moxin-dinosiglip-224px+7b+stage-finetune+x7 |
| run_root_dir: runs |
| seed: 7 |
| stage: finetune |
| trackers: |
| - jsonl |
| - wandb |
| wandb_entity: arash-akbari-stu-northeastern-university |
| wandb_project: Moxin-VLM |
|
|
