Upload wan22_t2v_low LoRA final checkpoint (epoch 300)

README.md

@@ -0,0 +1,18 @@
+---
+tags:
+- lora
+- diffusion-pipe
+- wan22_t2v_low
+base_model: unknown
+---
+
+# romanri85/t3ess5a-wan22-red-and-black-low-lora
+
+LoRA trained with [diffusion-pipe](https://github.com/tdrussell/diffusion-pipe) via serverless RunPod worker.
+
+## Training Details
+
+- **Model type**: wan22_t2v_low
+- **Epochs**: 300
+- **LoRA rank**: 32
+- **Learning rate**: 2e-05

adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k",
+    "ffn.0",
+    "v",
+    "q",
+    "o",
+    "ffn.2"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8677e306daaba347369c25476a3f0f9b4c8e6d092f8a319b6621419b8725cd15
+size 306807976

training_config.toml

@@ -0,0 +1,38 @@
+output_dir = "/tmp/job_2585f190-3bf9-4398-acc3-9030f40fcf0f/training_outputs/wan22_t2v_low_lora"
+dataset = "/tmp/job_2585f190-3bf9-4398-acc3-9030f40fcf0f/dataset.toml"
+epochs = 300
+micro_batch_size_per_gpu = 1
+pipeline_stages = 1
+gradient_accumulation_steps = 1
+gradient_clipping = 1.0
+warmup_steps = 100
+save_every_n_epochs = 25
+checkpoint_every_n_minutes = 120
+activation_checkpointing = true
+partition_method = "parameters"
+save_dtype = "bfloat16"
+caching_batch_size = 1
+steps_per_print = 1
+video_clip_mode = "single_middle"
+
+[model]
+type = "wan"
+ckpt_path = "/workspace/models/models/Wan/Wan2.2-T2V-A14B"
+transformer_path = "/workspace/models/models/Wan/Wan2.2-T2V-A14B/low_noise_model"
+dtype = "bfloat16"
+transformer_dtype = "float8"
+min_t = 0
+max_t = 0.875
+timestep_sample_method = "logit_normal"
+
+[adapter]
+type = "lora"
+rank = 32
+dtype = "bfloat16"
+
+[optimizer]
+type = "AdamW8bitKahan"
+lr = 2e-5
+betas = [ 0.9, 0.99,]
+weight_decay = 0.01
+eps = 1e-8

trigger_word.txt

@@ -0,0 +1 @@
+t3ess5a