initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,3 @@
+---
+license: mit
+---

args.json

@@ -0,0 +1,42 @@
+{
+    "output_dir": "exps",
+    "exp_name": "sit-xl-1-dinov2-b-enc8-ldm-only-e2e-vavae-0.5-4m",
+    "logging_dir": "logs",
+    "report_to": "wandb",
+    "sampling_steps": 10000,
+    "resume_step": 0,
+    "continue_train_exp_dir": null,
+    "wandb_history_path": null,
+    "model": "SiT-XL/1",
+    "num_classes": 1000,
+    "encoder_depth": 8,
+    "qk_norm": false,
+    "fused_attn": true,
+    "compile": true,
+    "data_dir": "data",
+    "resolution": 256,
+    "batch_size": 256,
+    "allow_tf32": true,
+    "mixed_precision": "fp16",
+    "epochs": 1400,
+    "max_train_steps": 4000000,
+    "checkpointing_steps": 50000,
+    "gradient_accumulation_steps": 1,
+    "learning_rate": 0.0001,
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.999,
+    "adam_weight_decay": 0.0,
+    "adam_epsilon": 1e-08,
+    "max_grad_norm": 1.0,
+    "seed": 0,
+    "num_workers": 4,
+    "path_type": "linear",
+    "prediction": "v",
+    "cfg_prob": 0.1,
+    "enc_type": "dinov2-vit-b",
+    "proj_coeff": 0.5,
+    "weighting": "uniform",
+    "vae": "f16d32",
+    "vae_latents_name": "e2e-vavae-400k",
+    "vae_ckpt": "pretrained/e2e-vavae-400k/e2e-vavae-400k.pt"
+}

checkpoints/4000000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:752f3a0dd1c051a7167724a575213f4d5e8fd2f85d50655b759cc97b90804c39
+size 10930619205