End of training

checkpoint-10000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f207fc980900f3b9c20465ffc09a3026eecc7d6e6d1e172d8208c8cba72f28f3
+size 6876842324

checkpoint-10000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e45ceb5b74c50f3788fc25c894d2155f651a70664625e0cc165e57afb5ccde
+size 14408

checkpoint-10000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9edab58c0c3df351bc9a8b3914358cb4b7af163b56063f195d98b42d019fd11
+size 988

checkpoint-10000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20bbef0c8fecac2668563417c5ed2ebcdecc2a3024abda5059c94bc08a3f3fea
+size 1000

checkpoint-10000/unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.34.0.dev0",
+  "_name_or_path": "timbrooks/instruct-pix2pix",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 8,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

checkpoint-10000/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230702d1c1ff6d66ff91b4111485c9f399712a22c55898057d18a5b0132aa616
+size 3438213624

checkpoint-10000/unet_ema/config.json

@@ -0,0 +1,75 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.34.0.dev0",
+  "_name_or_path": "timbrooks/instruct-pix2pix",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "decay": 0.9999,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 8,
+  "inv_gamma": 1.0,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "min_decay": 0.0,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "optimization_step": 10000,
+  "out_channels": 4,
+  "power": 0.6666666666666666,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "update_after_step": 0,
+  "use_ema_warmup": false,
+  "use_linear_projection": false
+}

checkpoint-10000/unet_ema/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b69e0a5419a5ac11b4883e23fef8f703e3ed9df6b9afdd7f33db5faefe5c0d4
+size 3438213624

logs/instruct-pix2pix/1745646932.3061192/events.out.tfevents.1745646932.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-vilfkk-worker.623.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ceeefc2a75ae2bcdec00931157c88f7c5b41a58de8c9cbf093c211e4b16916
+size 2392

logs/instruct-pix2pix/1745646932.336767/hparams.yml

@@ -0,0 +1,51 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: true
+cache_dir: null
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.1
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: Aurora1609/RoboTwin
+edit_prompt_column: prompt
+edited_image_column: after
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 1.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 20
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 10000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 9
+num_validation_images: 4
+original_image_column: before
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: timbrooks/instruct-pix2pix
+push_to_hub: true
+random_flip: false
+report_to: tensorboard
+resolution: 128
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+use_ema: true
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null
+variant: null

logs/instruct-pix2pix/events.out.tfevents.1745646932.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-vilfkk-worker.623.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a864bf01562bc76ca9858557e055ecfc47223f6da14f02f83baa5169f19bfda0
+size 489961

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8e5c65e6affc479dfe006024306e169d820fbd14f068a0f50bb9201dc4769da
+oid sha256:6b69e0a5419a5ac11b4883e23fef8f703e3ed9df6b9afdd7f33db5faefe5c0d4
 size 3438213624