mbiskho commited on
Commit
7f69975
·
1 Parent(s): 8d07e4f

End of training

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +41 -0
  2. feature_extractor/preprocessor_config.json +29 -0
  3. logs/text2image-fine-tune/1700276988.6039283/events.out.tfevents.1700276988.80de5b839da9.447.1 +3 -0
  4. logs/text2image-fine-tune/1700276988.6055439/hparams.yml +50 -0
  5. logs/text2image-fine-tune/1700278423.942323/events.out.tfevents.1700278423.80de5b839da9.447.3 +3 -0
  6. logs/text2image-fine-tune/1700278423.9439828/hparams.yml +50 -0
  7. logs/text2image-fine-tune/1700278649.9631958/events.out.tfevents.1700278649.80de5b839da9.447.5 +3 -0
  8. logs/text2image-fine-tune/1700278649.965001/hparams.yml +50 -0
  9. logs/text2image-fine-tune/1700279168.1335294/events.out.tfevents.1700279168.80de5b839da9.447.7 +3 -0
  10. logs/text2image-fine-tune/1700279168.1353276/hparams.yml +50 -0
  11. logs/text2image-fine-tune/1700279417.953292/events.out.tfevents.1700279417.80de5b839da9.447.9 +3 -0
  12. logs/text2image-fine-tune/1700279417.9549506/hparams.yml +50 -0
  13. logs/text2image-fine-tune/1700279534.1508427/events.out.tfevents.1700279534.80de5b839da9.447.11 +3 -0
  14. logs/text2image-fine-tune/1700279534.1526353/hparams.yml +50 -0
  15. logs/text2image-fine-tune/1700279681.6604285/events.out.tfevents.1700279681.80de5b839da9.447.13 +3 -0
  16. logs/text2image-fine-tune/1700279681.6622183/hparams.yml +50 -0
  17. logs/text2image-fine-tune/1700280182.33909/events.out.tfevents.1700280182.80de5b839da9.447.15 +3 -0
  18. logs/text2image-fine-tune/1700280182.3410344/hparams.yml +50 -0
  19. logs/text2image-fine-tune/1700280333.3105345/events.out.tfevents.1700280333.80de5b839da9.447.17 +3 -0
  20. logs/text2image-fine-tune/1700280333.3122373/hparams.yml +50 -0
  21. logs/text2image-fine-tune/1700280460.6569817/events.out.tfevents.1700280460.80de5b839da9.447.19 +3 -0
  22. logs/text2image-fine-tune/1700280460.6589375/hparams.yml +50 -0
  23. logs/text2image-fine-tune/1700280595.628941/events.out.tfevents.1700280595.80de5b839da9.447.21 +3 -0
  24. logs/text2image-fine-tune/1700280595.630901/hparams.yml +50 -0
  25. logs/text2image-fine-tune/1700281831.7564473/events.out.tfevents.1700281831.80de5b839da9.447.23 +3 -0
  26. logs/text2image-fine-tune/1700281831.7630205/hparams.yml +50 -0
  27. logs/text2image-fine-tune/1700281989.7927587/events.out.tfevents.1700281989.80de5b839da9.447.25 +3 -0
  28. logs/text2image-fine-tune/1700281989.7943757/hparams.yml +50 -0
  29. logs/text2image-fine-tune/1700282133.076914/events.out.tfevents.1700282133.80de5b839da9.447.27 +3 -0
  30. logs/text2image-fine-tune/1700282133.0788531/hparams.yml +50 -0
  31. logs/text2image-fine-tune/1700282321.4285438/events.out.tfevents.1700282321.80de5b839da9.447.29 +3 -0
  32. logs/text2image-fine-tune/1700282321.4304307/hparams.yml +50 -0
  33. logs/text2image-fine-tune/1700282568.5162885/events.out.tfevents.1700282568.80de5b839da9.447.31 +3 -0
  34. logs/text2image-fine-tune/1700282568.5182576/hparams.yml +50 -0
  35. logs/text2image-fine-tune/1700282834.8656893/events.out.tfevents.1700282834.80de5b839da9.447.33 +3 -0
  36. logs/text2image-fine-tune/1700282834.86746/hparams.yml +50 -0
  37. logs/text2image-fine-tune/1700283578.0860934/events.out.tfevents.1700283578.80de5b839da9.447.35 +3 -0
  38. logs/text2image-fine-tune/1700283578.0878408/hparams.yml +50 -0
  39. logs/text2image-fine-tune/1700283661.4017792/events.out.tfevents.1700283661.80de5b839da9.447.37 +3 -0
  40. logs/text2image-fine-tune/1700283661.4036915/hparams.yml +50 -0
  41. logs/text2image-fine-tune/1700283801.7683764/events.out.tfevents.1700283801.80de5b839da9.447.39 +3 -0
  42. logs/text2image-fine-tune/1700283801.7706254/hparams.yml +50 -0
  43. logs/text2image-fine-tune/1700283933.183076/events.out.tfevents.1700283933.80de5b839da9.447.41 +3 -0
  44. logs/text2image-fine-tune/1700283933.1849864/hparams.yml +50 -0
  45. logs/text2image-fine-tune/1700283981.5200212/events.out.tfevents.1700283981.80de5b839da9.447.43 +3 -0
  46. logs/text2image-fine-tune/1700283981.5224116/hparams.yml +50 -0
  47. logs/text2image-fine-tune/1700284065.265048/events.out.tfevents.1700284065.80de5b839da9.447.45 +3 -0
  48. logs/text2image-fine-tune/1700284065.2668698/hparams.yml +50 -0
  49. logs/text2image-fine-tune/1700284312.925678/events.out.tfevents.1700284312.80de5b839da9.447.47 +3 -0
  50. logs/text2image-fine-tune/1700284312.9276397/hparams.yml +50 -0
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: stabilityai/stable-diffusion-2-1
5
+ datasets:
6
+ - lambdalabs/pokemon-blip-captions
7
+ tags:
8
+ - stable-diffusion
9
+ - stable-diffusion-diffusers
10
+ - text-to-image
11
+ - diffusers
12
+ inference: true
13
+ ---
14
+
15
+ # Text-to-image finetuning - mbiskho/text-to-image
16
+
17
+ ## Pipeline usage
18
+
19
+ You can use the pipeline like so:
20
+
21
+ ```python
22
+ from diffusers import DiffusionPipeline
23
+ import torch
24
+
25
+ pipeline = DiffusionPipeline.from_pretrained("mbiskho/text-to-image", torch_dtype=torch.float16)
26
+ image = pipeline(prompt).images[0]
27
+ image.save("my_image.png")
28
+ ```
29
+
30
+ ## Training info
31
+
32
+ These are the key hyperparameters used during training:
33
+
34
+ * Epochs: 1
35
+ * Learning rate: 0.0001
36
+ * Batch size: 1
37
+ * Gradient accumulation steps: 1
38
+ * Image resolution: 10
39
+ * Mixed-precision: None
40
+
41
+
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "use_square_size": false
29
+ }
logs/text2image-fine-tune/1700276988.6039283/events.out.tfevents.1700276988.80de5b839da9.447.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bad734d722f3ff242d1cc13d8849b4b643441189ca91fe800878c99d370b6a2
3
+ size 2209
logs/text2image-fine-tune/1700276988.6055439/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 833
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: false
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700278423.942323/events.out.tfevents.1700278423.80de5b839da9.447.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:027665498a7618987f482849cbe56f844fd057312dbcac8115f0ef5bdfd13c87
3
+ size 2209
logs/text2image-fine-tune/1700278423.9439828/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 833
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: false
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700278649.9631958/events.out.tfevents.1700278649.80de5b839da9.447.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c11307211f7821f576d08b01d3a693da2a13bea528d1a951fd9f9cf01f9341a
3
+ size 2209
logs/text2image-fine-tune/1700278649.965001/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: false
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700279168.1335294/events.out.tfevents.1700279168.80de5b839da9.447.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85743e87ed6ee9a8108fe6e560b7382dbecc1fcf94b113988eb336a9e24d815a
3
+ size 2209
logs/text2image-fine-tune/1700279168.1353276/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: false
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700279417.953292/events.out.tfevents.1700279417.80de5b839da9.447.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39269d46ea5bc8b3f72a42b00f58bf5df35856a3ead9ff319444521cdc97dcb3
3
+ size 2209
logs/text2image-fine-tune/1700279417.9549506/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: false
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700279534.1508427/events.out.tfevents.1700279534.80de5b839da9.447.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c99bea172566b1208a61d719d246a98ba67ed4004090627fe60f462f9b99e218
3
+ size 2209
logs/text2image-fine-tune/1700279534.1526353/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: false
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700279681.6604285/events.out.tfevents.1700279681.80de5b839da9.447.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e61cf866c275a5e39d060b111de34596fa89a0ae952b6a0626c14a27b2014ff
3
+ size 2209
logs/text2image-fine-tune/1700279681.6622183/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: false
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700280182.33909/events.out.tfevents.1700280182.80de5b839da9.447.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808e210bdaf5e3ae2773bb58e089a860969760e33e66ea99745163b0a01fe598
3
+ size 2337
logs/text2image-fine-tune/1700280182.3410344/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700280333.3105345/events.out.tfevents.1700280333.80de5b839da9.447.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55b7d248f3a5d5190e0a1b147e7104f7dea77e0ed3b2186e6fecdc81eaf4fdc5
3
+ size 2337
logs/text2image-fine-tune/1700280333.3122373/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700280460.6569817/events.out.tfevents.1700280460.80de5b839da9.447.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cddec036c8a21da771fd825bcb59336b00f6cf6a0e115585593beac4cab82043
3
+ size 2337
logs/text2image-fine-tune/1700280460.6589375/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700280595.628941/events.out.tfevents.1700280595.80de5b839da9.447.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:890208e678a48bf784188a2148e2fdf1b574ac54f5dac824c95c6ae56a977574
3
+ size 2337
logs/text2image-fine-tune/1700280595.630901/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700281831.7564473/events.out.tfevents.1700281831.80de5b839da9.447.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b8760817bfa50af4ecaa56912fba927b8588e2c192c3451be1ee27ef571ea6
3
+ size 2337
logs/text2image-fine-tune/1700281831.7630205/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700281989.7927587/events.out.tfevents.1700281989.80de5b839da9.447.25 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d55e72beda187d1515669afedd1227528b97aa470c1d36358c06daa2b8924534
3
+ size 2337
logs/text2image-fine-tune/1700281989.7943757/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700282133.076914/events.out.tfevents.1700282133.80de5b839da9.447.27 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:573de855ad474486a9a1b2b5f73d4ff34d4f082c543faa0db47dad644950f2aa
3
+ size 2337
logs/text2image-fine-tune/1700282133.0788531/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700282321.4285438/events.out.tfevents.1700282321.80de5b839da9.447.29 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3d9266ae8d426cf9ebcd775578635a53969a5be118c05e8898b5a937dfb50f4
3
+ size 2337
logs/text2image-fine-tune/1700282321.4304307/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700282568.5162885/events.out.tfevents.1700282568.80de5b839da9.447.31 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c4326e956d3cdf1aa6fcaaa1f6899c0a4937ce336426c4189a1b60ef5f8c3c4
3
+ size 2337
logs/text2image-fine-tune/1700282568.5182576/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700282834.8656893/events.out.tfevents.1700282834.80de5b839da9.447.33 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04b6592eb4876df589dfcf7d51cbbc3c2f4fd24d7f70b027a741d9fefd1f5ebb
3
+ size 2337
logs/text2image-fine-tune/1700282834.86746/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700283578.0860934/events.out.tfevents.1700283578.80de5b839da9.447.35 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c74976cc4fbbff335f4607eec5be4106ba94b5e58dcae4d92525d7798a3a31da
3
+ size 2337
logs/text2image-fine-tune/1700283578.0878408/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700283661.4017792/events.out.tfevents.1700283661.80de5b839da9.447.37 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47c6aaa582d0292002b56119ef5cecf6f6d5241b8162714831c10c8be0abdc16
3
+ size 2337
logs/text2image-fine-tune/1700283661.4036915/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700283801.7683764/events.out.tfevents.1700283801.80de5b839da9.447.39 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7724e29bb65d80fab7152b59cb3a108276dc8ca39fe9d1f9a33eaec116a9e48
3
+ size 2337
logs/text2image-fine-tune/1700283801.7706254/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700283933.183076/events.out.tfevents.1700283933.80de5b839da9.447.41 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959f6f09b04ad8ebb2e02ddc2131abb2a1fc31b899986c4178600a88031d32cf
3
+ size 2337
logs/text2image-fine-tune/1700283933.1849864/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700283981.5200212/events.out.tfevents.1700283981.80de5b839da9.447.43 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84840bf812b8a2366a275d1e2ef0f2626a6fc73d232bc46c91d0715b1305d1a8
3
+ size 2337
logs/text2image-fine-tune/1700283981.5224116/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700284065.265048/events.out.tfevents.1700284065.80de5b839da9.447.45 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ad78010d726fdc7ee5fc13a9d0c409cc2324bfd7738cf083c54cf5708267e7
3
+ size 2337
logs/text2image-fine-tune/1700284065.2668698/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/1700284312.925678/events.out.tfevents.1700284312.80de5b839da9.447.47 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c815a6f2fe404c91a4d48961b203ea0fe2dd9c39adbdb86039533d5ed7e3d0c2
3
+ size 2337
logs/text2image-fine-tune/1700284312.9276397/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: null
7
+ caption_column: text
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: mbiskho/text-to-image
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0.0
21
+ learning_rate: 0.0001
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10
29
+ mixed_precision: null
30
+ noise_offset: 0.0
31
+ non_ema_revision: null
32
+ num_train_epochs: 1
33
+ output_dir: sd-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 10
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5