End of training
Browse files- checkpoint-1000/optimizer.bin +3 -0
- checkpoint-1000/random_states_0.pkl +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.bin +3 -0
- checkpoint-1000/unet/config.json +68 -0
- checkpoint-1000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-1000/unet_ema/config.json +75 -0
- checkpoint-1000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-500/optimizer.bin +1 -1
- checkpoint-500/random_states_0.pkl +1 -1
- checkpoint-500/unet/diffusion_pytorch_model.safetensors +1 -1
- checkpoint-500/unet_ema/diffusion_pytorch_model.safetensors +1 -1
- logs/text2image-fine-tune/1728861645.9737675/events.out.tfevents.1728861645.datasec.engr.uconn.edu.1913882.1 +3 -0
- logs/text2image-fine-tune/1728861645.9751558/hparams.yml +55 -0
- logs/text2image-fine-tune/events.out.tfevents.1728861645.datasec.engr.uconn.edu.1913882.0 +3 -0
- unet/diffusion_pytorch_model.safetensors +1 -1
checkpoint-1000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a8010344b3a808e308907f88d07b165936802d90c55bc6e5dcaffda2578f418
|
| 3 |
+
size 6876750164
|
checkpoint-1000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ffaae67c4cedf3c1075b15415ab02b86386397c8c1f79a99598b2d07e1e53be
|
| 3 |
+
size 14280
|
checkpoint-1000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d8fdcd0311eba9854fff738038ed4c1a269832665b4d88ba4e4e3d02a1a7e0e
|
| 3 |
+
size 988
|
checkpoint-1000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d16ae9dedf4c45ceadc467593037d83423677715e75ab402a9f44aa81de9b84
|
| 3 |
+
size 1000
|
checkpoint-1000/unet/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.31.0.dev0",
|
| 4 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"attention_type": "default",
|
| 11 |
+
"block_out_channels": [
|
| 12 |
+
320,
|
| 13 |
+
640,
|
| 14 |
+
1280,
|
| 15 |
+
1280
|
| 16 |
+
],
|
| 17 |
+
"center_input_sample": false,
|
| 18 |
+
"class_embed_type": null,
|
| 19 |
+
"class_embeddings_concat": false,
|
| 20 |
+
"conv_in_kernel": 3,
|
| 21 |
+
"conv_out_kernel": 3,
|
| 22 |
+
"cross_attention_dim": 768,
|
| 23 |
+
"cross_attention_norm": null,
|
| 24 |
+
"down_block_types": [
|
| 25 |
+
"CrossAttnDownBlock2D",
|
| 26 |
+
"CrossAttnDownBlock2D",
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"DownBlock2D"
|
| 29 |
+
],
|
| 30 |
+
"downsample_padding": 1,
|
| 31 |
+
"dropout": 0.0,
|
| 32 |
+
"dual_cross_attention": false,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"in_channels": 4,
|
| 38 |
+
"layers_per_block": 2,
|
| 39 |
+
"mid_block_only_cross_attention": null,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 45 |
+
"num_class_embeds": null,
|
| 46 |
+
"only_cross_attention": false,
|
| 47 |
+
"out_channels": 4,
|
| 48 |
+
"projection_class_embeddings_input_dim": null,
|
| 49 |
+
"resnet_out_scale_factor": 1.0,
|
| 50 |
+
"resnet_skip_time_act": false,
|
| 51 |
+
"resnet_time_scale_shift": "default",
|
| 52 |
+
"reverse_transformer_layers_per_block": null,
|
| 53 |
+
"sample_size": 64,
|
| 54 |
+
"time_cond_proj_dim": null,
|
| 55 |
+
"time_embedding_act_fn": null,
|
| 56 |
+
"time_embedding_dim": null,
|
| 57 |
+
"time_embedding_type": "positional",
|
| 58 |
+
"timestep_post_act": null,
|
| 59 |
+
"transformer_layers_per_block": 1,
|
| 60 |
+
"up_block_types": [
|
| 61 |
+
"UpBlock2D",
|
| 62 |
+
"CrossAttnUpBlock2D",
|
| 63 |
+
"CrossAttnUpBlock2D",
|
| 64 |
+
"CrossAttnUpBlock2D"
|
| 65 |
+
],
|
| 66 |
+
"upcast_attention": false,
|
| 67 |
+
"use_linear_projection": false
|
| 68 |
+
}
|
checkpoint-1000/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0acf4111de629d829078e7e548c16ab9cf88cfbef1ba372c3d6a2a9e239b3e78
|
| 3 |
+
size 3438167536
|
checkpoint-1000/unet_ema/config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.31.0.dev0",
|
| 4 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"attention_type": "default",
|
| 11 |
+
"block_out_channels": [
|
| 12 |
+
320,
|
| 13 |
+
640,
|
| 14 |
+
1280,
|
| 15 |
+
1280
|
| 16 |
+
],
|
| 17 |
+
"center_input_sample": false,
|
| 18 |
+
"class_embed_type": null,
|
| 19 |
+
"class_embeddings_concat": false,
|
| 20 |
+
"conv_in_kernel": 3,
|
| 21 |
+
"conv_out_kernel": 3,
|
| 22 |
+
"cross_attention_dim": 768,
|
| 23 |
+
"cross_attention_norm": null,
|
| 24 |
+
"decay": 0.9999,
|
| 25 |
+
"down_block_types": [
|
| 26 |
+
"CrossAttnDownBlock2D",
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"CrossAttnDownBlock2D",
|
| 29 |
+
"DownBlock2D"
|
| 30 |
+
],
|
| 31 |
+
"downsample_padding": 1,
|
| 32 |
+
"dropout": 0.0,
|
| 33 |
+
"dual_cross_attention": false,
|
| 34 |
+
"encoder_hid_dim": null,
|
| 35 |
+
"encoder_hid_dim_type": null,
|
| 36 |
+
"flip_sin_to_cos": true,
|
| 37 |
+
"freq_shift": 0,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"inv_gamma": 1.0,
|
| 40 |
+
"layers_per_block": 2,
|
| 41 |
+
"mid_block_only_cross_attention": null,
|
| 42 |
+
"mid_block_scale_factor": 1,
|
| 43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 44 |
+
"min_decay": 0.0,
|
| 45 |
+
"norm_eps": 1e-05,
|
| 46 |
+
"norm_num_groups": 32,
|
| 47 |
+
"num_attention_heads": null,
|
| 48 |
+
"num_class_embeds": null,
|
| 49 |
+
"only_cross_attention": false,
|
| 50 |
+
"optimization_step": 1000,
|
| 51 |
+
"out_channels": 4,
|
| 52 |
+
"power": 0.6666666666666666,
|
| 53 |
+
"projection_class_embeddings_input_dim": null,
|
| 54 |
+
"resnet_out_scale_factor": 1.0,
|
| 55 |
+
"resnet_skip_time_act": false,
|
| 56 |
+
"resnet_time_scale_shift": "default",
|
| 57 |
+
"reverse_transformer_layers_per_block": null,
|
| 58 |
+
"sample_size": 64,
|
| 59 |
+
"time_cond_proj_dim": null,
|
| 60 |
+
"time_embedding_act_fn": null,
|
| 61 |
+
"time_embedding_dim": null,
|
| 62 |
+
"time_embedding_type": "positional",
|
| 63 |
+
"timestep_post_act": null,
|
| 64 |
+
"transformer_layers_per_block": 1,
|
| 65 |
+
"up_block_types": [
|
| 66 |
+
"UpBlock2D",
|
| 67 |
+
"CrossAttnUpBlock2D",
|
| 68 |
+
"CrossAttnUpBlock2D",
|
| 69 |
+
"CrossAttnUpBlock2D"
|
| 70 |
+
],
|
| 71 |
+
"upcast_attention": false,
|
| 72 |
+
"update_after_step": 0,
|
| 73 |
+
"use_ema_warmup": false,
|
| 74 |
+
"use_linear_projection": false
|
| 75 |
+
}
|
checkpoint-1000/unet_ema/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1e7409cb507ca30cd8e6a9a69df068e7ccc1e22818c51bfc293ed2b9066b46b
|
| 3 |
+
size 3438167536
|
checkpoint-500/optimizer.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6876750164
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e27a1edf42c444507f6f3ecf89abb23a8f656326e688cae4a3b202766ef0961
|
| 3 |
size 6876750164
|
checkpoint-500/random_states_0.pkl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14280
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3baf994da4a6190a0e87274479ee07ffc4f612278ff5e00ddba8bdf724632f63
|
| 3 |
size 14280
|
checkpoint-500/unet/diffusion_pytorch_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3438167536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b790a64e91dea33521b78d4091570905a1daf56f2f0eac7d464bd3aee0c5e5cc
|
| 3 |
size 3438167536
|
checkpoint-500/unet_ema/diffusion_pytorch_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3438167536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaa53007eedfa6fa0870d4b70b1b5b7fc0f54672a48b59800dfc915202f489a4
|
| 3 |
size 3438167536
|
logs/text2image-fine-tune/1728861645.9737675/events.out.tfevents.1728861645.datasec.engr.uconn.edu.1913882.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34333a1aa48a7bcf33bfa0f64d577bb2d861977b5a8a3903ca12b172afe6208c
|
| 3 |
+
size 2655
|
logs/text2image-fine-tune/1728861645.9751558/hparams.yml
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.01
|
| 5 |
+
allow_tf32: false
|
| 6 |
+
cache_dir: null
|
| 7 |
+
caption_column: text
|
| 8 |
+
center_crop: true
|
| 9 |
+
checkpointing_steps: 500
|
| 10 |
+
checkpoints_total_limit: null
|
| 11 |
+
dataloader_num_workers: 0
|
| 12 |
+
dataset_config_name: null
|
| 13 |
+
dataset_name: haorandai/png_randomnoise_mammal_solid_orange_20_with20constraints
|
| 14 |
+
dream_detail_preservation: 1.0
|
| 15 |
+
dream_training: false
|
| 16 |
+
enable_xformers_memory_efficient_attention: false
|
| 17 |
+
foreach_ema: false
|
| 18 |
+
gradient_accumulation_steps: 4
|
| 19 |
+
gradient_checkpointing: true
|
| 20 |
+
hub_model_id: null
|
| 21 |
+
hub_token: null
|
| 22 |
+
image_column: image
|
| 23 |
+
input_perturbation: 0
|
| 24 |
+
learning_rate: 1.0e-05
|
| 25 |
+
local_rank: -1
|
| 26 |
+
logging_dir: logs
|
| 27 |
+
lr_scheduler: constant
|
| 28 |
+
lr_warmup_steps: 500
|
| 29 |
+
max_grad_norm: 1.0
|
| 30 |
+
max_train_samples: null
|
| 31 |
+
max_train_steps: 1000
|
| 32 |
+
mixed_precision: fp16
|
| 33 |
+
noise_offset: 0
|
| 34 |
+
non_ema_revision: null
|
| 35 |
+
num_train_epochs: 100
|
| 36 |
+
offload_ema: false
|
| 37 |
+
output_dir: /mnt/nvme1n1p1/home/biw23007/haoran/oct11_randomnoise_finetune_model_dir_1e-05_1000_withconstraint/haorandai/png_randomnoise_mammal_solid_orange_20_with20constraints/
|
| 38 |
+
prediction_type: null
|
| 39 |
+
pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
|
| 40 |
+
push_to_hub: true
|
| 41 |
+
random_flip: true
|
| 42 |
+
report_to: tensorboard
|
| 43 |
+
resolution: 224
|
| 44 |
+
resume_from_checkpoint: null
|
| 45 |
+
revision: null
|
| 46 |
+
scale_lr: false
|
| 47 |
+
seed: null
|
| 48 |
+
snr_gamma: null
|
| 49 |
+
tracker_project_name: text2image-fine-tune
|
| 50 |
+
train_batch_size: 1
|
| 51 |
+
train_data_dir: null
|
| 52 |
+
use_8bit_adam: false
|
| 53 |
+
use_ema: true
|
| 54 |
+
validation_epochs: 5
|
| 55 |
+
variant: null
|
logs/text2image-fine-tune/events.out.tfevents.1728861645.datasec.engr.uconn.edu.1913882.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89c581377315e8a3e957beb46c78bc849df3fa54910fd183b9156b77973d9228
|
| 3 |
+
size 48961
|
unet/diffusion_pytorch_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3438167536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1e7409cb507ca30cd8e6a9a69df068e7ccc1e22818c51bfc293ed2b9066b46b
|
| 3 |
size 3438167536
|