End of training

checkpoint-5000/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e19a2e1e947722a4df781aa9f27a0b06fc04d75370c1d066a8cca8e70bda7174
+oid sha256:51a3ce546e2135e92fde77c34fde0a707c44c3f978152142bc65f9fa4286437a
 size 6876842324

checkpoint-5000/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e87cf6fa747a099bc4b7c3c6a4ed4a0c3f683f5910e34f6622d0ee21e44c29b
-size 14344
+oid sha256:6933243b49a33fb967c5acfbb734aeec38889730c050a12876aac313cee88aa0
+size 14408

checkpoint-5000/unet/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.30.0.dev0",
+  "_diffusers_version": "0.33.0.dev0",
   "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "act_fn": "silu",
   "addition_embed_type": null,

checkpoint-5000/unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbabcc9cf08b34fc51fbb198755f700f45e89ed92dcfbb82545f1ff6fa5bc656
+oid sha256:ccf3f72480160ea25661bfd9c48ed32352e9da426686b695207bb873d3d8c07a
 size 3438213624

feature_extractor/preprocessor_config.json

@@ -1,21 +1,4 @@
 {
-  "_valid_processor_keys": [
-    "images",
-    "do_resize",
-    "size",
-    "resample",
-    "do_center_crop",
-    "crop_size",
-    "do_rescale",
-    "rescale_factor",
-    "do_normalize",
-    "image_mean",
-    "image_std",
-    "do_convert_rgb",
-    "return_tensors",
-    "data_format",
-    "input_data_format"
-  ],
   "crop_size": {
     "height": 224,
     "width": 224

logs/instruct-pix2pix/1736513441.048257/events.out.tfevents.1736513441.172d0f35d57d.2175.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2ea3b7c655cbc075f0e1b69bcbcda1211fc6731f37a6d99f56cf68586f6982c
+size 2438

logs/instruct-pix2pix/1736513441.0499015/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: 5000
+checkpoints_total_limit: 1
+conditioning_dropout_prob: 0.05
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: instruction-tuning-sd/cartoonization
+edit_prompt_column: edit_prompt
+edited_image_column: cartoonized_image
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+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: 5000
+mixed_precision: fp16
+non_ema_revision: null
+num_train_epochs: 16
+num_validation_images: 4
+original_image_column: original_image
+output_dir: instruct-pix2pix-model
+pretrained_model_name_or_path: runwayml/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.1736513441.172d0f35d57d.2175.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9514e2bd3df93c94022016018ba5629de246684a58cb0af5a8aaa7c90834f02f
+size 244961

model_index.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "StableDiffusionInstructPix2PixPipeline",
-  "_diffusers_version": "0.30.0.dev0",
+  "_diffusers_version": "0.33.0.dev0",
   "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "feature_extractor": [
     "transformers",

safety_checker/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/safety_checker",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/451f4fe16113bff5a5d2269ed5ad43b0592e9a14/safety_checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],
@@ -15,8 +15,9 @@
     "num_attention_heads": 12
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.47.1",
   "vision_config": {
+    "_attn_implementation_autoset": true,
     "dropout": 0.0,
     "hidden_size": 1024,
     "intermediate_size": 4096,

scheduler/scheduler_config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.30.0.dev0",
+  "_diffusers_version": "0.33.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,

text_encoder/config.json

@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float16",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.47.1",
   "vocab_size": 49408
 }

tokenizer/tokenizer_config.json

@@ -19,10 +19,11 @@
     }
   },
   "bos_token": "<|startoftext|>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "do_lower_case": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "model_max_length": 77,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "CLIPTokenizer",

unet/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.30.0.dev0",
+  "_diffusers_version": "0.33.0.dev0",
   "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "act_fn": "silu",
   "addition_embed_type": null,

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbabcc9cf08b34fc51fbb198755f700f45e89ed92dcfbb82545f1ff6fa5bc656
+oid sha256:ccf3f72480160ea25661bfd9c48ed32352e9da426686b695207bb873d3d8c07a
 size 3438213624

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.30.0.dev0",
+  "_diffusers_version": "0.33.0.dev0",
   "_name_or_path": "runwayml/stable-diffusion-v1-5",
   "act_fn": "silu",
   "block_out_channels": [
@@ -21,6 +21,7 @@
   "latents_mean": null,
   "latents_std": null,
   "layers_per_block": 2,
+  "mid_block_add_attention": true,
   "norm_num_groups": 32,
   "out_channels": 3,
   "sample_size": 512,