checkpoint phase2_animetimm/step18750

phase2_animetimm/step18750/adapter_config.json

@@ -0,0 +1,56 @@
+{
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "mlp.0",
+    "layer2",
+    "adaln_modulation_mlp.1",
+    "k_proj",
+    "adaln_modulation_mlp.2",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "adaln_modulation_cross_attn.2",
+    "layer1",
+    "adaln_modulation_cross_attn.1",
+    "output_proj",
+    "adaln_modulation_self_attn.1",
+    "mlp.2",
+    "adaln_modulation_self_attn.2"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

phase2_animetimm/step18750/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a52a9b9612e15fe70f01c6311b469b15615b68724a00fca683360e0fcb0709c
+size 277206000

phase2_animetimm/step18750/tr_anime_bkt.toml

@@ -0,0 +1,31 @@
+output_dir = '/workspace/out_anime'
+dataset = '/workspace/ds_anime_bkt.toml'
+epochs = 2
+micro_batch_size_per_gpu = 4
+gradient_accumulation_steps = 1
+save_every_n_steps = 3125
+checkpoint_every_n_minutes = 30
+activation_checkpointing = true
+gradient_clipping = 1.0
+warmup_steps = 100
+caching_batch_size = 8
+map_num_proc = 8
+save_dtype = 'bfloat16'
+[model]
+type = 'anima'
+transformer_path = '/workspace/hf/hub/models--circlestone-labs--Anima/snapshots/38371ccdbd541b114a9ddbc6b77cb31dae2c4027/split_files/diffusion_models/anima-base-v1.0.safetensors'
+vae_path = '/workspace/hf/hub/models--circlestone-labs--Anima/snapshots/38371ccdbd541b114a9ddbc6b77cb31dae2c4027/split_files/vae/qwen_image_vae.safetensors'
+llm_path = '/workspace/hf/hub/models--circlestone-labs--Anima/snapshots/38371ccdbd541b114a9ddbc6b77cb31dae2c4027/split_files/text_encoders/qwen_3_06b_base.safetensors'
+dtype = 'bfloat16'
+llm_adapter_lr = 0
+[adapter]
+type = 'lora'
+rank = 64
+dtype = 'bfloat16'
+init_from_existing = '/workspace/out_vlm/20260704_06-35-33/epoch2'
+[optimizer]
+type = 'adamw_optimi'
+lr = 5e-5
+betas = [0.9, 0.99]
+weight_decay = 0.01
+eps = 1e-8