Hugging Face's logo

wuaszdc
/
spatial-relationship-model-back

Text-to-Image
Diffusers
TensorBoard
StableDiffusionPipeline
Model card Files
xet
Metrics Community
wuaszdc commited on
Commit
e25cf5b
·
1 Parent(s): 4da6739

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. checkpoint-20000/optimizer.bin +3 -0
  2. checkpoint-20000/random_states_0.pkl +3 -0
  3. checkpoint-20000/scaler.pt +3 -0
  4. checkpoint-20000/scheduler.bin +3 -0
  5. checkpoint-20000/unet/config.json +62 -0
  6. checkpoint-20000/unet/diffusion_pytorch_model.bin +3 -0
  7. checkpoint-20000/unet_ema/config.json +69 -0
  8. checkpoint-20000/unet_ema/diffusion_pytorch_model.bin +3 -0
  9. checkpoint-40000/optimizer.bin +3 -0
  10. checkpoint-40000/random_states_0.pkl +3 -0
  11. checkpoint-40000/scaler.pt +3 -0
  12. checkpoint-40000/scheduler.bin +3 -0
  13. checkpoint-40000/unet/config.json +62 -0
  14. checkpoint-40000/unet/diffusion_pytorch_model.bin +3 -0
  15. checkpoint-40000/unet_ema/config.json +69 -0
  16. checkpoint-40000/unet_ema/diffusion_pytorch_model.bin +3 -0
  17. feature_extractor/preprocessor_config.json +28 -0
  18. logs/text2image-fine-tune/1687484281.3629444/events.out.tfevents.1687484281.g023.sol.rc.asu.edu.1227467.1 +3 -0
  19. logs/text2image-fine-tune/1687484281.4535692/hparams.yml +50 -0
  20. logs/text2image-fine-tune/1687484732.4959297/events.out.tfevents.1687484732.g023.sol.rc.asu.edu.1227888.1 +3 -0
  21. logs/text2image-fine-tune/1687484732.5515726/hparams.yml +50 -0
  22. logs/text2image-fine-tune/1687485306.054261/events.out.tfevents.1687485306.g023.sol.rc.asu.edu.1228654.1 +3 -0
  23. logs/text2image-fine-tune/1687485306.1146164/hparams.yml +50 -0
  24. logs/text2image-fine-tune/1687485686.1828926/events.out.tfevents.1687485686.g023.sol.rc.asu.edu.1229451.1 +3 -0
  25. logs/text2image-fine-tune/1687485686.2287989/hparams.yml +50 -0
  26. logs/text2image-fine-tune/1687488854.9296603/events.out.tfevents.1687488854.g012.sol.rc.asu.edu.891332.1 +3 -0
  27. logs/text2image-fine-tune/1687488854.9867501/hparams.yml +50 -0
  28. logs/text2image-fine-tune/1687489415.8570626/events.out.tfevents.1687489415.g012.sol.rc.asu.edu.892320.1 +3 -0
  29. logs/text2image-fine-tune/1687489415.8990405/hparams.yml +50 -0
  30. logs/text2image-fine-tune/1687489894.8476286/events.out.tfevents.1687489894.g012.sol.rc.asu.edu.892948.1 +3 -0
  31. logs/text2image-fine-tune/1687489894.9371443/hparams.yml +50 -0
  32. logs/text2image-fine-tune/1687490219.3755434/events.out.tfevents.1687490219.g012.sol.rc.asu.edu.893130.1 +3 -0
  33. logs/text2image-fine-tune/1687490219.4269717/hparams.yml +50 -0
  34. logs/text2image-fine-tune/1687567394.2765768/events.out.tfevents.1687567394.g012.sol.rc.asu.edu.1015146.1 +3 -0
  35. logs/text2image-fine-tune/1687567394.285055/hparams.yml +50 -0
  36. logs/text2image-fine-tune/1687567582.553664/events.out.tfevents.1687567582.g017.sol.rc.asu.edu.3986616.1 +3 -0
  37. logs/text2image-fine-tune/1687567582.5628018/hparams.yml +50 -0
  38. logs/text2image-fine-tune/1688712104.851267/events.out.tfevents.1688712104.g010.sol.rc.asu.edu.2546128.1 +3 -0
  39. logs/text2image-fine-tune/1688712105.184274/hparams.yml +50 -0
  40. logs/text2image-fine-tune/1688785360.9873862/events.out.tfevents.1688785360.g010.sol.rc.asu.edu.2589748.1 +3 -0
  41. logs/text2image-fine-tune/1688785361.2153516/hparams.yml +50 -0
  42. logs/text2image-fine-tune/events.out.tfevents.1687484281.g023.sol.rc.asu.edu.1227467.0 +3 -0
  43. logs/text2image-fine-tune/events.out.tfevents.1687484730.g023.sol.rc.asu.edu.1227888.0 +3 -0
  44. logs/text2image-fine-tune/events.out.tfevents.1687485305.g023.sol.rc.asu.edu.1228654.0 +3 -0
  45. logs/text2image-fine-tune/events.out.tfevents.1687485686.g023.sol.rc.asu.edu.1229451.0 +3 -0
  46. logs/text2image-fine-tune/events.out.tfevents.1687488854.g012.sol.rc.asu.edu.891332.0 +3 -0
  47. logs/text2image-fine-tune/events.out.tfevents.1687489415.g012.sol.rc.asu.edu.892320.0 +3 -0
  48. logs/text2image-fine-tune/events.out.tfevents.1687489894.g012.sol.rc.asu.edu.892948.0 +3 -0
  49. logs/text2image-fine-tune/events.out.tfevents.1687490219.g012.sol.rc.asu.edu.893130.0 +3 -0
  50. logs/text2image-fine-tune/events.out.tfevents.1687567394.g012.sol.rc.asu.edu.1015146.0 +3 -0
checkpoint-20000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d9c13d1711eaff1572fa71ff039a7ad5766c9f821873480100c7e392a36dd9
3
+ size 6876749651
checkpoint-20000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:632b52d6f4793e5dbc7409c5e420a9019450ea432dfe71ed2d30f7cc0df43a91
3
+ size 14663
checkpoint-20000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5e771fc1f584f9f2886467944e52c2a921d5979873e4963bea0ca857322f26
3
+ size 557
checkpoint-20000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9564e8ff9fb42a8970a60b5119ae43b907efd058c800b04b2867d62e8aad6bc
3
+ size 563
checkpoint-20000/unet/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.18.0.dev0",
4
+ "_name_or_path": "spatial-relationship/spatial-relationship-model-60-2",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "attention_head_dim": 8,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "center_input_sample": false,
16
+ "class_embed_type": null,
17
+ "class_embeddings_concat": false,
18
+ "conv_in_kernel": 3,
19
+ "conv_out_kernel": 3,
20
+ "cross_attention_dim": 768,
21
+ "cross_attention_norm": null,
22
+ "down_block_types": [
23
+ "CrossAttnDownBlock2D",
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "DownBlock2D"
27
+ ],
28
+ "downsample_padding": 1,
29
+ "dual_cross_attention": false,
30
+ "encoder_hid_dim": null,
31
+ "encoder_hid_dim_type": null,
32
+ "flip_sin_to_cos": true,
33
+ "freq_shift": 0,
34
+ "in_channels": 4,
35
+ "layers_per_block": 2,
36
+ "mid_block_only_cross_attention": null,
37
+ "mid_block_scale_factor": 1,
38
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
39
+ "norm_eps": 1e-05,
40
+ "norm_num_groups": 32,
41
+ "num_class_embeds": null,
42
+ "only_cross_attention": false,
43
+ "out_channels": 4,
44
+ "projection_class_embeddings_input_dim": null,
45
+ "resnet_out_scale_factor": 1.0,
46
+ "resnet_skip_time_act": false,
47
+ "resnet_time_scale_shift": "default",
48
+ "sample_size": 64,
49
+ "time_cond_proj_dim": null,
50
+ "time_embedding_act_fn": null,
51
+ "time_embedding_dim": null,
52
+ "time_embedding_type": "positional",
53
+ "timestep_post_act": null,
54
+ "up_block_types": [
55
+ "UpBlock2D",
56
+ "CrossAttnUpBlock2D",
57
+ "CrossAttnUpBlock2D",
58
+ "CrossAttnUpBlock2D"
59
+ ],
60
+ "upcast_attention": false,
61
+ "use_linear_projection": false
62
+ }
checkpoint-20000/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc5c366f4cee063d2a62f45521f47773cc446b432044d00872d4e70823430922
3
+ size 3438375973
checkpoint-20000/unet_ema/config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.18.0.dev0",
4
+ "_name_or_path": "spatial-relationship/spatial-relationship-model-60-2",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "attention_head_dim": 8,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "center_input_sample": false,
16
+ "class_embed_type": null,
17
+ "class_embeddings_concat": false,
18
+ "conv_in_kernel": 3,
19
+ "conv_out_kernel": 3,
20
+ "cross_attention_dim": 768,
21
+ "cross_attention_norm": null,
22
+ "decay": 0.9999,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "encoder_hid_dim": null,
32
+ "encoder_hid_dim_type": null,
33
+ "flip_sin_to_cos": true,
34
+ "freq_shift": 0,
35
+ "in_channels": 4,
36
+ "inv_gamma": 1.0,
37
+ "layers_per_block": 2,
38
+ "mid_block_only_cross_attention": null,
39
+ "mid_block_scale_factor": 1,
40
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
41
+ "min_decay": 0.0,
42
+ "norm_eps": 1e-05,
43
+ "norm_num_groups": 32,
44
+ "num_class_embeds": null,
45
+ "only_cross_attention": false,
46
+ "optimization_step": 20000,
47
+ "out_channels": 4,
48
+ "power": 0.6666666666666666,
49
+ "projection_class_embeddings_input_dim": null,
50
+ "resnet_out_scale_factor": 1.0,
51
+ "resnet_skip_time_act": false,
52
+ "resnet_time_scale_shift": "default",
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
+ "up_block_types": [
60
+ "UpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D"
64
+ ],
65
+ "upcast_attention": false,
66
+ "update_after_step": 0,
67
+ "use_ema_warmup": false,
68
+ "use_linear_projection": false
69
+ }
checkpoint-20000/unet_ema/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa69a706ab85edff167f10c02f1d963c0a4f9beefdb28960ca1bec948e11e194
3
+ size 3438366373
checkpoint-40000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aa43a1ba9ba25ea21a774b1338012f63ef5f33193fe4afb62cd1431fec4095a
3
+ size 6876749651
checkpoint-40000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a2390d8a192c7587b1fa0fcbd6e77f9ccbd3f3b4ecbddceab87a8aecb90f5c
3
+ size 14663
checkpoint-40000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94408cfb561631f4532a459d4661dd7fa62b8e58efd9fb1367ba9e9eda944629
3
+ size 557
checkpoint-40000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0651858ab464f74a92e167f623ffd8a7c3ac0508a248cccf2bdcb105a430e75
3
+ size 563
checkpoint-40000/unet/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.18.0.dev0",
4
+ "_name_or_path": "spatial-relationship/spatial-relationship-model-60-2",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "attention_head_dim": 8,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "center_input_sample": false,
16
+ "class_embed_type": null,
17
+ "class_embeddings_concat": false,
18
+ "conv_in_kernel": 3,
19
+ "conv_out_kernel": 3,
20
+ "cross_attention_dim": 768,
21
+ "cross_attention_norm": null,
22
+ "down_block_types": [
23
+ "CrossAttnDownBlock2D",
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "DownBlock2D"
27
+ ],
28
+ "downsample_padding": 1,
29
+ "dual_cross_attention": false,
30
+ "encoder_hid_dim": null,
31
+ "encoder_hid_dim_type": null,
32
+ "flip_sin_to_cos": true,
33
+ "freq_shift": 0,
34
+ "in_channels": 4,
35
+ "layers_per_block": 2,
36
+ "mid_block_only_cross_attention": null,
37
+ "mid_block_scale_factor": 1,
38
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
39
+ "norm_eps": 1e-05,
40
+ "norm_num_groups": 32,
41
+ "num_class_embeds": null,
42
+ "only_cross_attention": false,
43
+ "out_channels": 4,
44
+ "projection_class_embeddings_input_dim": null,
45
+ "resnet_out_scale_factor": 1.0,
46
+ "resnet_skip_time_act": false,
47
+ "resnet_time_scale_shift": "default",
48
+ "sample_size": 64,
49
+ "time_cond_proj_dim": null,
50
+ "time_embedding_act_fn": null,
51
+ "time_embedding_dim": null,
52
+ "time_embedding_type": "positional",
53
+ "timestep_post_act": null,
54
+ "up_block_types": [
55
+ "UpBlock2D",
56
+ "CrossAttnUpBlock2D",
57
+ "CrossAttnUpBlock2D",
58
+ "CrossAttnUpBlock2D"
59
+ ],
60
+ "upcast_attention": false,
61
+ "use_linear_projection": false
62
+ }
checkpoint-40000/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d801d7c1ecd0de99515fdee52696ad658764cee182397d8a4c26e072d45659
3
+ size 3438375973
checkpoint-40000/unet_ema/config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.18.0.dev0",
4
+ "_name_or_path": "spatial-relationship/spatial-relationship-model-60-2",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "attention_head_dim": 8,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "center_input_sample": false,
16
+ "class_embed_type": null,
17
+ "class_embeddings_concat": false,
18
+ "conv_in_kernel": 3,
19
+ "conv_out_kernel": 3,
20
+ "cross_attention_dim": 768,
21
+ "cross_attention_norm": null,
22
+ "decay": 0.9999,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "encoder_hid_dim": null,
32
+ "encoder_hid_dim_type": null,
33
+ "flip_sin_to_cos": true,
34
+ "freq_shift": 0,
35
+ "in_channels": 4,
36
+ "inv_gamma": 1.0,
37
+ "layers_per_block": 2,
38
+ "mid_block_only_cross_attention": null,
39
+ "mid_block_scale_factor": 1,
40
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
41
+ "min_decay": 0.0,
42
+ "norm_eps": 1e-05,
43
+ "norm_num_groups": 32,
44
+ "num_class_embeds": null,
45
+ "only_cross_attention": false,
46
+ "optimization_step": 40000,
47
+ "out_channels": 4,
48
+ "power": 0.6666666666666666,
49
+ "projection_class_embeddings_input_dim": null,
50
+ "resnet_out_scale_factor": 1.0,
51
+ "resnet_skip_time_act": false,
52
+ "resnet_time_scale_shift": "default",
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
+ "up_block_types": [
60
+ "UpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D"
64
+ ],
65
+ "upcast_attention": false,
66
+ "update_after_step": 0,
67
+ "use_ema_warmup": false,
68
+ "use_linear_projection": false
69
+ }
checkpoint-40000/unet_ema/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4806a647ec32335cae9ee5c3539944986d5f02047b0c691651761dcc4e7343aa
3
+ size 3438366373
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/text2image-fine-tune/1687484281.3629444/events.out.tfevents.1687484281.g023.sol.rc.asu.edu.1227467.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b247478c0da6240ad86abc16b6a7975a5c709eaed68039daf05c06c86602de
3
+ size 2369
logs/text2image-fine-tune/1687484281.4535692/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: image
8
+ center_crop: false
9
+ checkpointing_steps: 20000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: spatial-relationship-model-back
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: cosine_with_restarts
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20220
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 20
33
+ output_dir: /scratch/dzhan120/spatial-relationship-model-back
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: wuaszdc/spatial-relationship-model-quarter
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 2
47
+ train_data_dir: /scratch/dzhan120/download
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1687484732.4959297/events.out.tfevents.1687484732.g023.sol.rc.asu.edu.1227888.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f431f7dc56ca70302273798a759240d19201d179c470649773e34c4a89da7a90
3
+ size 2382
logs/text2image-fine-tune/1687484732.5515726/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: additional_feature
8
+ center_crop: false
9
+ checkpointing_steps: 20000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: spatial-relationship-model-back
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: cosine_with_restarts
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20220
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 20
33
+ output_dir: /scratch/dzhan120/spatial-relationship-model-back
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: wuaszdc/spatial-relationship-model-quarter
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 2
47
+ train_data_dir: /scratch/dzhan120/download
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1687485306.054261/events.out.tfevents.1687485306.g023.sol.rc.asu.edu.1228654.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b84c4e342c5344d9050d245b8e50137aa8b3111cd9bcf04127ac9ce4677e5a46
3
+ size 2388
logs/text2image-fine-tune/1687485306.1146164/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: additional_feature
8
+ center_crop: false
9
+ checkpointing_steps: 20000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: spatial-relationship-model-back
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: cosine_with_restarts
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20220
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 20
33
+ output_dir: /scratch/dzhan120/spatial-relationship-model-back
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: wuaszdc/spatial-relationship-model-quarter
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 2
47
+ train_data_dir: /scratch/dzhan120/download/train
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1687485686.1828926/events.out.tfevents.1687485686.g023.sol.rc.asu.edu.1229451.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab13b2956b2da6daf23d4c8187d1dd18104dab5c1210cf4996edf342810ac011
3
+ size 2370
logs/text2image-fine-tune/1687485686.2287989/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: additional_feature
8
+ center_crop: false
9
+ checkpointing_steps: 20000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: spatial-relationship-model-back
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: cosine_with_restarts
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 3260
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 20
33
+ output_dir: /scratch/dzhan120/spatial-relationship-model-back
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: wuaszdc/spatial-relationship-model-quarter
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 2
47
+ train_data_dir: download/train
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1687488854.9296603/events.out.tfevents.1687488854.g012.sol.rc.asu.edu.891332.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:506c7308c195803b7b4fdbd95df35d91dd138af08383c71acf6e0661afb2f424
3
+ size 2370
logs/text2image-fine-tune/1687488854.9867501/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: additional_feature
8
+ center_crop: false
9
+ checkpointing_steps: 20000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: spatial-relationship-model-back
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: cosine_with_restarts
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20220
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 20
33
+ output_dir: /scratch/dzhan120/spatial-relationship-model-back
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: wuaszdc/spatial-relationship-model-quarter
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 2
47
+ train_data_dir: download/train
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1687489415.8570626/events.out.tfevents.1687489415.g012.sol.rc.asu.edu.892320.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e4b202acc14e752ab8350b68638eb8cb6faca385c664675f53978d91cef045
3
+ size 2370
logs/text2image-fine-tune/1687489415.8990405/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: additional_feature
8
+ center_crop: false
9
+ checkpointing_steps: 20000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: spatial-relationship-model-back
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: cosine_with_restarts
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20220
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 20
33
+ output_dir: /scratch/dzhan120/spatial-relationship-model-back
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: wuaszdc/spatial-relationship-model-quarter
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 2
47
+ train_data_dir: download/train
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1687489894.8476286/events.out.tfevents.1687489894.g012.sol.rc.asu.edu.892948.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3642d5b9e0ae6c79ab291513be74f33a6d89f4e7e7ec381b642091d031f3ff50
3
+ size 2370
logs/text2image-fine-tune/1687489894.9371443/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: additional_feature
8
+ center_crop: false
9
+ checkpointing_steps: 20000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: spatial-relationship-model-back
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: cosine_with_restarts
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20220
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 20
33
+ output_dir: /scratch/dzhan120/spatial-relationship-model-back
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: wuaszdc/spatial-relationship-model-quarter
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 2
47
+ train_data_dir: download/train
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1687490219.3755434/events.out.tfevents.1687490219.g012.sol.rc.asu.edu.893130.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b78aa484bf9ee37049d656d7d8d02c0af9ef255ee40472d30862feb3374a54cc
3
+ size 2370
logs/text2image-fine-tune/1687490219.4269717/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: additional_feature
8
+ center_crop: false
9
+ checkpointing_steps: 20000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: spatial-relationship-model-back
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: cosine_with_restarts
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20220
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 20
33
+ output_dir: /scratch/dzhan120/spatial-relationship-model-back
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: wuaszdc/spatial-relationship-model-quarter
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 2
47
+ train_data_dir: download/train
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1687567394.2765768/events.out.tfevents.1687567394.g012.sol.rc.asu.edu.1015146.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f641aafd9ce7f8960e0968e731d2fbabdb0e7cb3f0adb1fc6533eb098b9d7c4
3
+ size 2384
logs/text2image-fine-tune/1687567394.285055/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: additional_feature
8
+ center_crop: false
9
+ checkpointing_steps: 20000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: spatial-relationship-model-back
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: cosine_with_restarts
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20060
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 20
33
+ output_dir: /scratch/dzhan120/spatial-relationship-model-back
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: wuaszdc/spatial-relationship-model-quarter
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 2
47
+ train_data_dir: /scratch/dzhan120/download2/
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1687567582.553664/events.out.tfevents.1687567582.g017.sol.rc.asu.edu.3986616.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65edb5fbead8729df308885a5c4505a6087c07271105281506fc21242177c156
3
+ size 2384
logs/text2image-fine-tune/1687567582.5628018/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: additional_feature
8
+ center_crop: false
9
+ checkpointing_steps: 20000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: spatial-relationship-model-back
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: cosine_with_restarts
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 20060
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 20
33
+ output_dir: /scratch/dzhan120/spatial-relationship-model-back
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: wuaszdc/spatial-relationship-model-quarter
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 2
47
+ train_data_dir: /scratch/dzhan120/download2/
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1688712104.851267/events.out.tfevents.1688712104.g010.sol.rc.asu.edu.2546128.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f34de2865a7fb14c80529c0ee42c6280c67e3b89f55e9c6ae067316f447bf982
3
+ size 2394
logs/text2image-fine-tune/1688712105.184274/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: additional_feature
8
+ center_crop: false
9
+ checkpointing_steps: 20000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: spatial-relationship-model-back
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: cosine_with_restarts
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 50300
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 50
33
+ output_dir: /scratch/dzhan120/spatial-relationship-model-back
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: spatial-relationship/spatial-relationship-model-60-2
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 2
47
+ train_data_dir: /scratch/dzhan120/download3/
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1688785360.9873862/events.out.tfevents.1688785360.g010.sol.rc.asu.edu.2589748.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07cc82fa3e6e8a5332d81488f66ffe004d23517a9b82a39d77a227a0b911b7b0
3
+ size 2394
logs/text2image-fine-tune/1688785361.2153516/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: additional_feature
8
+ center_crop: false
9
+ checkpointing_steps: 20000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: spatial-relationship-model-back
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: cosine_with_restarts
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 49100
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 50
33
+ output_dir: /scratch/dzhan120/spatial-relationship-model-back
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: spatial-relationship/spatial-relationship-model-60-2
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 2
47
+ train_data_dir: /scratch/dzhan120/download3/
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/events.out.tfevents.1687484281.g023.sol.rc.asu.edu.1227467.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:138298a66171be310916e948b6152397a91cadc28658dadedce471335a0054df
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1687484730.g023.sol.rc.asu.edu.1227888.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c1ce35b15df38d61cfd1ba4750767aca9cde40471f5f5567b296f9f8f424ac7
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1687485305.g023.sol.rc.asu.edu.1228654.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ff35cc848499a5d7f42a65ddf99491dbd3851edb43192678c120866b4ddc52a
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1687485686.g023.sol.rc.asu.edu.1229451.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b289a0f1a35d40b5e10c085264f002a58ed580dba4c588c35c867bff1864ed42
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1687488854.g012.sol.rc.asu.edu.891332.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b85d7a04801092388945d66bdd1f6c0f886dc4d629afe1dd1e752a9e6c54fc3
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1687489415.g012.sol.rc.asu.edu.892320.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05443396f7518fdc6413a397d894b622df25a4c5b473db33130fdcc605657649
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1687489894.g012.sol.rc.asu.edu.892948.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df7aed7db0f19f0a9fd3d0cc28308ec73fabb11a1ba645b2ec9d9c7cd877798
3
+ size 1960
logs/text2image-fine-tune/events.out.tfevents.1687490219.g012.sol.rc.asu.edu.893130.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5ad9c24a76c5c33c7d9ebdd157ff435df6ddac9b5c57cbcb9a281359c29f2e8
3
+ size 1096
logs/text2image-fine-tune/events.out.tfevents.1687567394.g012.sol.rc.asu.edu.1015146.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa77d45cc5c1785bc9f02b7fca85e4647975b188e920c93ab3e90c46baac74c0
3
+ size 8389