rishitdagli commited on
Commit
eb7a78a
1 Parent(s): e3c928c

End of training

Browse files
Files changed (42) hide show
  1. checkpoint-4000/optimizer.bin +3 -0
  2. checkpoint-4000/random_states_0.pkl +3 -0
  3. checkpoint-4000/scaler.pt +3 -0
  4. checkpoint-4000/scheduler.bin +3 -0
  5. checkpoint-4000/unet/config.json +67 -0
  6. checkpoint-4000/unet/diffusion_pytorch_model.safetensors +3 -0
  7. checkpoint-4000/unet_ema/config.json +74 -0
  8. checkpoint-4000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  9. feature_extractor/preprocessor_config.json +28 -0
  10. logs/diffusion-isp/1696829881.5769048/events.out.tfevents.1696829881.gpu011.4219.1 +3 -0
  11. logs/diffusion-isp/1696829881.584409/hparams.yml +50 -0
  12. logs/diffusion-isp/1696883562.274425/events.out.tfevents.1696883562.gpu047.7817.1 +3 -0
  13. logs/diffusion-isp/1696883562.282633/hparams.yml +50 -0
  14. logs/diffusion-isp/1696952816.7710686/events.out.tfevents.1696952816.gpu038.31999.1 +3 -0
  15. logs/diffusion-isp/1696952816.777575/hparams.yml +50 -0
  16. logs/diffusion-isp/1696977884.3538234/events.out.tfevents.1696977884.gpu008.22282.1 +3 -0
  17. logs/diffusion-isp/1696977884.3622146/hparams.yml +50 -0
  18. logs/diffusion-isp/1696979969.4608314/events.out.tfevents.1696979969.gpu008.22612.1 +3 -0
  19. logs/diffusion-isp/1696979969.4689977/hparams.yml +50 -0
  20. logs/diffusion-isp/1696982383.99139/events.out.tfevents.1696982383.gpu048.32362.1 +3 -0
  21. logs/diffusion-isp/1696982383.998017/hparams.yml +50 -0
  22. logs/diffusion-isp/events.out.tfevents.1696829881.gpu011.4219.0 +3 -0
  23. logs/diffusion-isp/events.out.tfevents.1696883562.gpu047.7817.0 +3 -0
  24. logs/diffusion-isp/events.out.tfevents.1696952816.gpu038.31999.0 +3 -0
  25. logs/diffusion-isp/events.out.tfevents.1696977884.gpu008.22282.0 +3 -0
  26. logs/diffusion-isp/events.out.tfevents.1696979969.gpu008.22612.0 +3 -0
  27. logs/diffusion-isp/events.out.tfevents.1696982383.gpu048.32362.0 +3 -0
  28. model_index.json +34 -0
  29. safety_checker/config.json +28 -0
  30. safety_checker/model.safetensors +3 -0
  31. scheduler/scheduler_config.json +22 -0
  32. text_encoder/config.json +25 -0
  33. text_encoder/model.safetensors +3 -0
  34. tokenizer/added_tokens.json +4 -0
  35. tokenizer/merges.txt +0 -0
  36. tokenizer/special_tokens_map.json +6 -0
  37. tokenizer/tokenizer_config.json +32 -0
  38. tokenizer/vocab.json +0 -0
  39. unet/config.json +67 -0
  40. unet/diffusion_pytorch_model.safetensors +3 -0
  41. vae/config.json +32 -0
  42. vae/diffusion_pytorch_model.safetensors +3 -0
checkpoint-4000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaf02e45441710b4120f051974c378e280a5c0041c51e0c1baf17e053c1db72a
3
+ size 6876841875
checkpoint-4000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01348462a49896114c1aa292d013366d5cf9cc895be3f4152607c6498eec1f06
3
+ size 14663
checkpoint-4000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09a61ecdaa4a69ba865e0b9e19169660549c34c60a83537ab5ece413678520ab
3
+ size 557
checkpoint-4000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e799c66721855ee832d69fa6c72f957c8e84ab8272c5aca107dac61118a229e
3
+ size 563
checkpoint-4000/unet/config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "/scratch/ssd004/scratch/rishit/diffusion-isp-model-new/checkpoint-3500",
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": 8,
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
+ "sample_size": 64,
53
+ "time_cond_proj_dim": null,
54
+ "time_embedding_act_fn": null,
55
+ "time_embedding_dim": null,
56
+ "time_embedding_type": "positional",
57
+ "timestep_post_act": null,
58
+ "transformer_layers_per_block": 1,
59
+ "up_block_types": [
60
+ "UpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D"
64
+ ],
65
+ "upcast_attention": false,
66
+ "use_linear_projection": false
67
+ }
checkpoint-4000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be3177f2add7002d1c7692218e308940bb49f3c7617773826337c9cb581354b6
3
+ size 3438213624
checkpoint-4000/unet_ema/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "timbrooks/instruct-pix2pix",
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": 8,
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": 500,
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
+ "sample_size": 64,
58
+ "time_cond_proj_dim": null,
59
+ "time_embedding_act_fn": null,
60
+ "time_embedding_dim": null,
61
+ "time_embedding_type": "positional",
62
+ "timestep_post_act": null,
63
+ "transformer_layers_per_block": 1,
64
+ "up_block_types": [
65
+ "UpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D"
69
+ ],
70
+ "upcast_attention": false,
71
+ "update_after_step": 0,
72
+ "use_ema_warmup": false,
73
+ "use_linear_projection": false
74
+ }
checkpoint-4000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f09a76479ed684c97538bf5d233edd477b6ecdd2c9f51681cf44593bce186c3
3
+ size 3438213624
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPImageProcessor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
logs/diffusion-isp/1696829881.5769048/events.out.tfevents.1696829881.gpu011.4219.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5ec073dbc47e72654f86f0d05916b5e601779005d18732c693d9289e34021af
3
+ size 2529
logs/diffusion-isp/1696829881.584409/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: /scratch/ssd004/scratch/rishit/train_cache
7
+ center_crop: false
8
+ checkpointing_steps: 500
9
+ checkpoints_total_limit: 2
10
+ conditioning_dropout_prob: 0.003
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: rishitdagli/diffusion-isp-low-light-only
14
+ edit_prompt_column: prompt
15
+ edited_image_column: ground_truth
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 0.0001
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: cosine
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 35100
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 300
32
+ num_validation_images: 4
33
+ original_image_column: input_image
34
+ output_dir: /scratch/ssd004/scratch/rishit/diffusion-isp-model-new
35
+ pretrained_model_name_or_path: timbrooks/instruct-pix2pix
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 3407
44
+ train_batch_size: 4
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
logs/diffusion-isp/1696883562.274425/events.out.tfevents.1696883562.gpu047.7817.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae8207ab47a237047b694bea01798ca25174164e856cc96cae9d8c90814406bc
3
+ size 2593
logs/diffusion-isp/1696883562.282633/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: /scratch/ssd004/scratch/rishit/train_cache
7
+ center_crop: false
8
+ checkpointing_steps: 500
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.003
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: rishitdagli/diffusion-isp-low-light-only
14
+ edit_prompt_column: prompt
15
+ edited_image_column: ground_truth
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 0.0001
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: cosine
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 35100
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 300
32
+ num_validation_images: 4
33
+ original_image_column: input_image
34
+ output_dir: /scratch/ssd004/scratch/rishit/diffusion-isp-model-new
35
+ pretrained_model_name_or_path: timbrooks/instruct-pix2pix
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: latest
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 3407
44
+ train_batch_size: 4
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
logs/diffusion-isp/1696952816.7710686/events.out.tfevents.1696952816.gpu038.31999.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76c59bc1a9851adf9b8b0cbfeb6b86f107fb0e51f810aade7b358a9d4a9b6e47
3
+ size 2593
logs/diffusion-isp/1696952816.777575/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: /scratch/ssd004/scratch/rishit/train_cache
7
+ center_crop: false
8
+ checkpointing_steps: 500
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.003
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: rishitdagli/diffusion-isp-low-light-only
14
+ edit_prompt_column: prompt
15
+ edited_image_column: ground_truth
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 0.0001
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: cosine
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 35100
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 300
32
+ num_validation_images: 4
33
+ original_image_column: input_image
34
+ output_dir: /scratch/ssd004/scratch/rishit/diffusion-isp-model-new
35
+ pretrained_model_name_or_path: timbrooks/instruct-pix2pix
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: latest
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 3407
44
+ train_batch_size: 4
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
logs/diffusion-isp/1696977884.3538234/events.out.tfevents.1696977884.gpu008.22282.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a804bc650b7477e24f861c04f72ab96d4ba65799e602b3594e17e6ee20c81b1a
3
+ size 2593
logs/diffusion-isp/1696977884.3622146/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: /scratch/ssd004/scratch/rishit/train_cache
7
+ center_crop: false
8
+ checkpointing_steps: 500
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.003
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: rishitdagli/diffusion-isp-low-light-only
14
+ edit_prompt_column: prompt
15
+ edited_image_column: ground_truth
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 0.0001
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: cosine
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 35100
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 300
32
+ num_validation_images: 4
33
+ original_image_column: input_image
34
+ output_dir: /scratch/ssd004/scratch/rishit/diffusion-isp-model-new
35
+ pretrained_model_name_or_path: timbrooks/instruct-pix2pix
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: latest
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 3407
44
+ train_batch_size: 4
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
logs/diffusion-isp/1696979969.4608314/events.out.tfevents.1696979969.gpu008.22612.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5455d8fccfb053d43e1f2d8a746bedeb5f02a1940ed38623921001d229c7ecb9
3
+ size 2593
logs/diffusion-isp/1696979969.4689977/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: /scratch/ssd004/scratch/rishit/train_cache
7
+ center_crop: false
8
+ checkpointing_steps: 500
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.003
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: rishitdagli/diffusion-isp-low-light-only
14
+ edit_prompt_column: prompt
15
+ edited_image_column: ground_truth
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 0.0001
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: cosine
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 11700
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 100
32
+ num_validation_images: 4
33
+ original_image_column: input_image
34
+ output_dir: /scratch/ssd004/scratch/rishit/diffusion-isp-model-new
35
+ pretrained_model_name_or_path: timbrooks/instruct-pix2pix
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: latest
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 3407
44
+ train_batch_size: 4
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
logs/diffusion-isp/1696982383.99139/events.out.tfevents.1696982383.gpu048.32362.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:560ee1f764dd59f9b7204675a20ed60b27ff2d8297f5849213dd84faab38ebcf
3
+ size 2593
logs/diffusion-isp/1696982383.998017/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: /scratch/ssd004/scratch/rishit/train_cache
7
+ center_crop: false
8
+ checkpointing_steps: 500
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.003
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: rishitdagli/diffusion-isp-low-light-only
14
+ edit_prompt_column: prompt
15
+ edited_image_column: ground_truth
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 0.0001
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: cosine
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 117
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 1
32
+ num_validation_images: 4
33
+ original_image_column: input_image
34
+ output_dir: /scratch/ssd004/scratch/rishit/diffusion-isp-model-new
35
+ pretrained_model_name_or_path: timbrooks/instruct-pix2pix
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: latest
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 3407
44
+ train_batch_size: 4
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
logs/diffusion-isp/events.out.tfevents.1696829881.gpu011.4219.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:638963c7037932b26c0356f2b886bd34de916c63eb3fda21ac3c9e8d244b2f6a
3
+ size 122461
logs/diffusion-isp/events.out.tfevents.1696883562.gpu047.7817.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd32d2c2216b007c017c3f4cf802b4c54da1901fad5db15daa835a98ad3d5c7e
3
+ size 98088
logs/diffusion-isp/events.out.tfevents.1696952816.gpu038.31999.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4081c9b159da3a179c62ad0e0890f0f58dcc1413f2c7e12d735c933a706bba3e
3
+ size 24588
logs/diffusion-isp/events.out.tfevents.1696977884.gpu008.22282.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:829c047551f1097915dc1ab48d74b40c57e8f05e3a71b9c3ea709a81f4304f8e
3
+ size 3910
logs/diffusion-isp/events.out.tfevents.1696979969.gpu008.22612.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43a07345caee8ddf2ddc8b56b6eb8e8fbb3fc58eacafd832c77e5cbdfc71fcf1
3
+ size 4596
logs/diffusion-isp/events.out.tfevents.1696982383.gpu048.32362.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48a5b8a0761261bdcc498100f745eed9bd5ee42744ffa5a74d1b597e0920c7a7
3
+ size 88
model_index.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionInstructPix2PixPipeline",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "timbrooks/instruct-pix2pix",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "requires_safety_checker": false,
10
+ "safety_checker": [
11
+ "stable_diffusion",
12
+ "StableDiffusionSafetyChecker"
13
+ ],
14
+ "scheduler": [
15
+ "diffusers",
16
+ "EulerAncestralDiscreteScheduler"
17
+ ],
18
+ "text_encoder": [
19
+ "transformers",
20
+ "CLIPTextModel"
21
+ ],
22
+ "tokenizer": [
23
+ "transformers",
24
+ "CLIPTokenizer"
25
+ ],
26
+ "unet": [
27
+ "diffusers",
28
+ "UNet2DConditionModel"
29
+ ],
30
+ "vae": [
31
+ "diffusers",
32
+ "AutoencoderKL"
33
+ ]
34
+ }
safety_checker/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/h/rishit/.cache/huggingface/hub/models--timbrooks--instruct-pix2pix/snapshots/31519b5cb02a7fd89b906d88731cd4d6a7bbf88d/safety_checker",
3
+ "architectures": [
4
+ "StableDiffusionSafetyChecker"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 768,
10
+ "text_config": {
11
+ "dropout": 0.0,
12
+ "hidden_size": 768,
13
+ "intermediate_size": 3072,
14
+ "model_type": "clip_text_model",
15
+ "num_attention_heads": 12
16
+ },
17
+ "torch_dtype": "float32",
18
+ "transformers_version": "4.34.0",
19
+ "vision_config": {
20
+ "dropout": 0.0,
21
+ "hidden_size": 1024,
22
+ "intermediate_size": 4096,
23
+ "model_type": "clip_vision_model",
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 24,
26
+ "patch_size": 14
27
+ }
28
+ }
safety_checker/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
3
+ size 1215979664
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "EulerAncestralDiscreteScheduler",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "algorithm_type": "dpmsolver++",
5
+ "beta_end": 0.012,
6
+ "beta_schedule": "scaled_linear",
7
+ "beta_start": 0.00085,
8
+ "clip_sample": false,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "lower_order_final": true,
11
+ "num_train_timesteps": 1000,
12
+ "prediction_type": "epsilon",
13
+ "sample_max_value": 1.0,
14
+ "set_alpha_to_one": false,
15
+ "skip_prk_steps": true,
16
+ "solver_order": 2,
17
+ "solver_type": "midpoint",
18
+ "steps_offset": 1,
19
+ "thresholding": false,
20
+ "timestep_spacing": "linspace",
21
+ "trained_betas": null
22
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "timbrooks/instruct-pix2pix",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "quick_gelu",
11
+ "hidden_size": 768,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 768,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.34.0",
24
+ "vocab_size": 49408
25
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
3
+ size 246144152
tokenizer/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 49407,
3
+ "<|startoftext|>": 49406
4
+ }
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|startoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "additional_special_tokens": [],
22
+ "bos_token": "<|startoftext|>",
23
+ "clean_up_tokenization_spaces": true,
24
+ "do_lower_case": true,
25
+ "eos_token": "<|endoftext|>",
26
+ "errors": "replace",
27
+ "model_max_length": 77,
28
+ "pad_token": "<|endoftext|>",
29
+ "tokenizer_class": "CLIPTokenizer",
30
+ "tokenizer_file": null,
31
+ "unk_token": "<|endoftext|>"
32
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "/scratch/ssd004/scratch/rishit/diffusion-isp-model-new/checkpoint-4000",
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": 8,
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
+ "sample_size": 64,
53
+ "time_cond_proj_dim": null,
54
+ "time_embedding_act_fn": null,
55
+ "time_embedding_dim": null,
56
+ "time_embedding_type": "positional",
57
+ "timestep_post_act": null,
58
+ "transformer_layers_per_block": 1,
59
+ "up_block_types": [
60
+ "UpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D"
64
+ ],
65
+ "upcast_attention": false,
66
+ "use_linear_projection": false
67
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f09a76479ed684c97538bf5d233edd477b6ecdd2c9f51681cf44593bce186c3
3
+ size 3438213624
vae/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "timbrooks/instruct-pix2pix",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "force_upcast": true,
19
+ "in_channels": 3,
20
+ "latent_channels": 4,
21
+ "layers_per_block": 2,
22
+ "norm_num_groups": 32,
23
+ "out_channels": 3,
24
+ "sample_size": 512,
25
+ "scaling_factor": 0.18215,
26
+ "up_block_types": [
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D"
31
+ ]
32
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
3
+ size 167335342