End of training

checkpoint-100000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fee096821bb57d1179b9c7be17fcc9023dff3bd85dd12531fe819f9a5d2e7b10
+size 6876842324

checkpoint-100000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21763767cec9be8e0b8a66a9f79479bc6fc1de98d1d53fe03e7f1370ae8abd35
+size 14408

checkpoint-100000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:053c958d77c700ad99e74f032f1a935d65b7f6c38d20758a4ccb5fac3e1b1e2d
+size 988

checkpoint-100000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f317990e86da374fd326df8a79984be00c4fa81c26a4c9ee96c25e1a44ddf3
+size 1000

checkpoint-100000/unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
+  "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-100000/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93446350555c72688e33f01bb8985953b856ca69f913069a7c6c5937c44ee7f6
+size 3438213624

logs/instruct-pix2pix/1737646048.5677006/events.out.tfevents.1737646048.783832b1bb8b.1602.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17b28a7d771caf12a63c98e85d78451df1489587bc0f586ffb97b02a28dda6a
+size 2449

logs/instruct-pix2pix/1737646048.569629/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: false
+cache_dir: null
+center_crop: false
+checkpointing_steps: 10000
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: timbrooks/instructpix2pix-clip-filtered
+edit_prompt_column: edit_prompt
+edited_image_column: edited_image
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 8
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+learning_rate: 5.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 100000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 11
+num_validation_images: 4
+original_image_column: original_image
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+push_to_hub: true
+random_flip: true
+report_to: tensorboard
+resolution: 256
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 42
+train_batch_size: 4
+train_data_dir: null
+use_8bit_adam: false
+use_ema: false
+val_image_url: null
+validation_epochs: 1
+validation_prompt: null
+variant: null

logs/instruct-pix2pix/events.out.tfevents.1737646048.783832b1bb8b.1602.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc2ac63814d2f8c1ad7dbd7fddd42db05341e4edb3fa312f6e034cf0caae9d28
+size 4983578

safety_checker/config.json

@@ -15,7 +15,7 @@
     "num_attention_heads": 12
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.48.1",
   "vision_config": {
     "_attn_implementation_autoset": true,
     "dropout": 0.0,

text_encoder/config.json

@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float16",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.48.1",
   "vocab_size": 49408
 }

tokenizer/tokenizer_config.json

@@ -23,6 +23,7 @@
   "do_lower_case": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "model_max_length": 77,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "CLIPTokenizer",

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7fce0518929b3deb39523d1e9893b21651b08e2bf7052374950ae6a26c136bf
+oid sha256:93446350555c72688e33f01bb8985953b856ca69f913069a7c6c5937c44ee7f6
 size 3438213624