Upload folder using huggingface_hub

checkpoint-12000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5648154976fc4fde821ae254460f65ad69dbad398c4058e1644451f1bbe19415
+size 536933354

checkpoint-12000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00f17ad23b77ae32e75542811c0ca53695319adfe6912eb92d5d6e2cb390801f
+size 14344

checkpoint-12000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1f9d6a63312bf6188d8844a7d621f2ecda20b6c0aee9e19ddcea1c480954ba
+size 988

checkpoint-12000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fa42bc0f349bf17974b501b2e04e150f941778516a7dc2dafa712c6dbb5f91
+size 1000

checkpoint-12000/unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.22.1",
+  "_name_or_path": "runwayml/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": 4,
+  "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-12000/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6337e20b8367850ea28d34bbaf58fa214bed4881c3b19cecda8ee19d825644b
+size 3438167536

feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

logs/val_losses.json

@@ -0,0 +1,50 @@
+Loss,Steps
+13.924886368215084,300
+13.898816347122192,600
+13.876210033893585,900
+13.781322866678238,1200
+13.619608834385872,1500
+13.531631827354431,1800
+13.578811183571815,2100
+13.430870205163956,2400
+13.026913091540337,2700
+13.224607847630978,3000
+13.210528515279293,3300
+13.419452093541622,3600
+13.193679422140121,3900
+13.338919587433338,4200
+13.013121768832207,4500
+13.113897733390331,4800
+13.015163213014603,5100
+13.098058924078941,5400
+12.930486470460892,5700
+13.069866463541985,6000
+12.994856111705303,6300
+13.204674579203129,6600
+12.836261197924614,6900
+13.04555580765009,7200
+12.902658842504025,7500
+12.718411929905415,7800
+12.814554579555988,8100
+12.966766975820065,8400
+13.061861403286457,8700
+13.153495028614998,9000
+12.841042682528496,9300
+13.086694195866585,9600
+12.678017847239971,9900
+12.624796479940414,10200
+12.942170694470406,10500
+12.864688195288181,10800
+13.176438391208649,11100
+12.898421697318554,11400
+13.05261229723692,11700
+12.536481343209743,12000
+12.849453695118427,12300
+12.85201981663704,12600
+13.021664597094059,12900
+12.831861689686775,13200
+12.772942177951336,13500
+12.833313263952732,13800
+12.676795601844788,14100
+12.735884554684162,14400
+12.809430591762066,14700

mimic/unet_full_textEn_freeze_vae_freeze_experiments_ratio_1.0_training_seed_42_dataset_split_seed_42_LR_1e-05/feature_extractor/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  },
+  "use_square_size": false
+}

mimic/unet_full_textEn_freeze_vae_freeze_experiments_ratio_1.0_training_seed_42_dataset_split_seed_42_LR_1e-05/model_index.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.22.1",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

mimic/unet_full_textEn_freeze_vae_freeze_experiments_ratio_1.0_training_seed_42_dataset_split_seed_42_LR_1e-05/scheduler/scheduler_config.json

@@ -0,0 +1,15 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.22.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}