End of training
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +17 -0
- checkpoint-1000/optimizer.bin +3 -0
- checkpoint-1000/pytorch_model.bin +3 -0
- checkpoint-1000/random_states_0.pkl +3 -0
- checkpoint-1000/scheduler.bin +3 -0
- checkpoint-1500/optimizer.bin +3 -0
- checkpoint-1500/pytorch_model.bin +3 -0
- checkpoint-1500/random_states_0.pkl +3 -0
- checkpoint-1500/scheduler.bin +3 -0
- checkpoint-2000/optimizer.bin +3 -0
- checkpoint-2000/pytorch_model.bin +3 -0
- checkpoint-2000/random_states_0.pkl +3 -0
- checkpoint-2000/scheduler.bin +3 -0
- checkpoint-2500/optimizer.bin +3 -0
- checkpoint-2500/pytorch_model.bin +3 -0
- checkpoint-2500/random_states_0.pkl +3 -0
- checkpoint-2500/scheduler.bin +3 -0
- checkpoint-3000/optimizer.bin +3 -0
- checkpoint-3000/pytorch_model.bin +3 -0
- checkpoint-3000/random_states_0.pkl +3 -0
- checkpoint-3000/scheduler.bin +3 -0
- checkpoint-500/optimizer.bin +3 -0
- checkpoint-500/pytorch_model.bin +3 -0
- checkpoint-500/random_states_0.pkl +3 -0
- checkpoint-500/scheduler.bin +3 -0
- learned_embeds-steps-1000.bin +3 -0
- learned_embeds-steps-1500.bin +3 -0
- learned_embeds-steps-2000.bin +3 -0
- learned_embeds-steps-2500.bin +3 -0
- learned_embeds-steps-3000.bin +3 -0
- learned_embeds-steps-500.bin +3 -0
- learned_embeds.bin +3 -0
- logs/textual_inversion/1689253167.607172/events.out.tfevents.1689253167.asimov.336221.1 +3 -0
- logs/textual_inversion/1689253167.609333/hparams.yml +48 -0
- logs/textual_inversion/1689253273.6435933/events.out.tfevents.1689253273.asimov.337244.1 +3 -0
- logs/textual_inversion/1689253273.6458743/hparams.yml +48 -0
- logs/textual_inversion/1689253409.366505/events.out.tfevents.1689253409.asimov.338271.1 +3 -0
- logs/textual_inversion/1689253409.3687513/hparams.yml +48 -0
- logs/textual_inversion/1689254068.9782665/events.out.tfevents.1689254068.asimov.343083.1 +3 -0
- logs/textual_inversion/1689254068.9806187/hparams.yml +48 -0
- logs/textual_inversion/1689255471.5416772/events.out.tfevents.1689255471.asimov.352802.1 +3 -0
- logs/textual_inversion/1689255471.5432942/hparams.yml +48 -0
- logs/textual_inversion/1689255529.8736153/events.out.tfevents.1689255529.asimov.353336.1 +3 -0
- logs/textual_inversion/1689255529.876004/hparams.yml +48 -0
- logs/textual_inversion/1689339474.8780582/events.out.tfevents.1689339474.asimov.1129689.1 +3 -0
- logs/textual_inversion/1689339474.8803751/hparams.yml +48 -0
- logs/textual_inversion/1689341156.5645792/events.out.tfevents.1689341156.asimov.1141610.1 +3 -0
- logs/textual_inversion/1689341156.567027/hparams.yml +48 -0
- logs/textual_inversion/1689341606.0289376/events.out.tfevents.1689341606.asimov.1155434.1 +3 -0
- logs/textual_inversion/1689341606.0312734/hparams.yml +48 -0
README.md
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
license: creativeml-openrail-m
|
4 |
+
base_model: /home/plitsis/text-inv/audioldm-m-full
|
5 |
+
tags:
|
6 |
+
- stable-diffusion
|
7 |
+
- stable-diffusion-diffusers
|
8 |
+
- text-to-image
|
9 |
+
- diffusers
|
10 |
+
- textual_inversion
|
11 |
+
inference: true
|
12 |
+
---
|
13 |
+
|
14 |
+
# Textual inversion text2image fine-tuning - manosp/audio_inversion_cat
|
15 |
+
These are textual inversion adaption weights for /home/plitsis/text-inv/audioldm-m-full. You can find some example images in the following.
|
16 |
+
|
17 |
+
|
checkpoint-1000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3835afc454c34978e3941077c74bdffcb94b6be0ed7f1c7c007b8dbfbae7bf3
|
3 |
+
size 308835885
|
checkpoint-1000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c191d112fffc02f54dde8b5f21688d5e6ddcee03c9766397660118089e251312
|
3 |
+
size 501305793
|
checkpoint-1000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:370bb2ac90d68f7d442e75a4e9cbd8421d6c586524db10dc71bd78f652b4c7c4
|
3 |
+
size 14663
|
checkpoint-1000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbb19b948b33a080098712534e53a991114e50367c7efbe3f9b4d0cec03eb540
|
3 |
+
size 563
|
checkpoint-1500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf08437c4c60c64dda9c8b630b7c122e65231635ce00b96c92deb3ef8b759aee
|
3 |
+
size 308835885
|
checkpoint-1500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b513277fbdd570b4587571c7d9eec8205f133b0e77cb355550c41e2297819c29
|
3 |
+
size 501305793
|
checkpoint-1500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e06b3accca0325018ab318b75a69cb1ff15bb76a78b44b63a47bdf1a17ec2476
|
3 |
+
size 14663
|
checkpoint-1500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7abf0b3af2013b920618166f35e17d899fce776df72f2c2a64c13989f4b8a6a8
|
3 |
+
size 563
|
checkpoint-2000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82ca10b500af0d487c4cca81728d8da4855bec556f5fb6cdd993efcd8d8ff3e5
|
3 |
+
size 308835885
|
checkpoint-2000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c9617ba68d9d54d27dc1afc38d1a6c0e0b777d687e30a2b5999ccf19749b98d
|
3 |
+
size 501305793
|
checkpoint-2000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c336619d9d24c7033212ed90f3378f8e0479628d702499fb453b3c9487fcd26f
|
3 |
+
size 14663
|
checkpoint-2000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ce55ada40659c32ea01f44d7732f0406a6c9004376f7e5579de396b3481cc2d
|
3 |
+
size 563
|
checkpoint-2500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e63f4b53e7859c62f7a62d6af2b1657476cd2d8e08471d5894ccae549356ea75
|
3 |
+
size 308835885
|
checkpoint-2500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bea81a2b783d764607d6397992841d9a56900ff6297cf7334820e89015cd7f7b
|
3 |
+
size 501305793
|
checkpoint-2500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13814b23fa7a7a44a01f14a1b6866b802adb24f13dd69e7bfddd15cad8b67650
|
3 |
+
size 14663
|
checkpoint-2500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:496e5a35d8686f4bf9ce59c376f5f501ec4a1034cf3b70deb1f3d2c047fab2d4
|
3 |
+
size 563
|
checkpoint-3000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:372be70ecf9b473e6d5b7fb0848052178bfb80037e759f2eafcd2de05a261272
|
3 |
+
size 308835885
|
checkpoint-3000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:130637ef67b408e832bbd91d18a701aef83b8468a553795e8c975ff8a36f34d5
|
3 |
+
size 501305793
|
checkpoint-3000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e99c31ee3bc28544967367920700cac156eff3180f7dbb8aa0fe973e9fde258e
|
3 |
+
size 14663
|
checkpoint-3000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2056b541ceef5d77999a48951b85854f6503b83d58bc070e970ec3531e56e169
|
3 |
+
size 563
|
checkpoint-500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7018fe4408f6d7d21cff60e0782fe1b88c99700b6ae34cb0e53492066aa65b0
|
3 |
+
size 308835885
|
checkpoint-500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e943cf719326b7b4437310236f102ca16dd44e2651f5c778f9fe8c38c5b9f236
|
3 |
+
size 501305793
|
checkpoint-500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cba8d6da2ca07410f1002fedba84459662fdb0ecfa3395598d5853a2f8595f5
|
3 |
+
size 14663
|
checkpoint-500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:478ff7b9adcb1fba8f74abd29e0dfb41133888ecf608d07ea8ae2143e019d098
|
3 |
+
size 563
|
learned_embeds-steps-1000.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:471e987bed8b982ff73be253099d86598f9a13c7f74de6767bab52cecc966150
|
3 |
+
size 4001
|
learned_embeds-steps-1500.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec40d8034863bc0446bce95d962a0a44ed5340c7782dea98b789dee306f2bdb5
|
3 |
+
size 4001
|
learned_embeds-steps-2000.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:167aa84be482fb43dd0c69e5241a939cd276622cc4df62a9317db13810ed2c6f
|
3 |
+
size 4001
|
learned_embeds-steps-2500.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8bbeb98c379857c83cb36c545c11b87438dc78c36c9d24b3b5a0f2507135a1b
|
3 |
+
size 4001
|
learned_embeds-steps-3000.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4d8453e5958a2a4a2f6e9242abb2e3f550c26d8020ab21880df218667c7f23c
|
3 |
+
size 4001
|
learned_embeds-steps-500.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6eac54ba5a548d667b706f35b2951b269fe42ece45f24ff288c3f8a516dc24ed
|
3 |
+
size 3998
|
learned_embeds.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c17bdb1436b101c6a4b08a73f4d4a8c4e50a757c9f03d12509009beafe758dae
|
3 |
+
size 3840
|
logs/textual_inversion/1689253167.607172/events.out.tfevents.1689253167.asimov.336221.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1db5beaee33f3c48107f5a1c994e3fdb7d1765fc349df8c8646fb400b6473e2
|
3 |
+
size 2434
|
logs/textual_inversion/1689253167.609333/hparams.yml
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 500
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
dataloader_num_workers: 0
|
10 |
+
duration: 10.0
|
11 |
+
enable_xformers_memory_efficient_attention: false
|
12 |
+
gradient_accumulation_steps: 4
|
13 |
+
gradient_checkpointing: false
|
14 |
+
hub_model_id: null
|
15 |
+
hub_token: null
|
16 |
+
initializer_token: cat
|
17 |
+
learnable_property: object
|
18 |
+
learning_rate: 0.002
|
19 |
+
local_rank: 0
|
20 |
+
logging_dir: logs
|
21 |
+
lr_num_cycles: 1
|
22 |
+
lr_scheduler: constant
|
23 |
+
lr_warmup_steps: 0
|
24 |
+
max_train_steps: 3000
|
25 |
+
mixed_precision: 'no'
|
26 |
+
num_train_epochs: 12
|
27 |
+
num_validation_images: 4
|
28 |
+
num_vectors: 1
|
29 |
+
output_dir: audio_inversion_cat
|
30 |
+
placeholder_token: <cat-meow>
|
31 |
+
pretrained_model_name_or_path: /home/plitsis/text-inv/audioldm-m-full
|
32 |
+
push_to_hub: true
|
33 |
+
repeats: 100
|
34 |
+
report_to: tensorboard
|
35 |
+
resolution: 512
|
36 |
+
resume_from_checkpoint: latest
|
37 |
+
revision: null
|
38 |
+
sample_rate: 16000
|
39 |
+
save_as_full_pipeline: false
|
40 |
+
save_steps: 500
|
41 |
+
scale_lr: true
|
42 |
+
seed: null
|
43 |
+
tokenizer_name: null
|
44 |
+
train_batch_size: 1
|
45 |
+
train_data_dir: /home/plitsis/text-inv/meows
|
46 |
+
validation_epochs: null
|
47 |
+
validation_prompt: null
|
48 |
+
validation_steps: 100
|
logs/textual_inversion/1689253273.6435933/events.out.tfevents.1689253273.asimov.337244.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:749e0acf37b1639c4dabc94073c0c173b8ea16b2bffffd6b2e6305d7c21709ea
|
3 |
+
size 2434
|
logs/textual_inversion/1689253273.6458743/hparams.yml
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 500
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
dataloader_num_workers: 0
|
10 |
+
duration: 10.0
|
11 |
+
enable_xformers_memory_efficient_attention: false
|
12 |
+
gradient_accumulation_steps: 4
|
13 |
+
gradient_checkpointing: false
|
14 |
+
hub_model_id: null
|
15 |
+
hub_token: null
|
16 |
+
initializer_token: cat
|
17 |
+
learnable_property: object
|
18 |
+
learning_rate: 0.002
|
19 |
+
local_rank: 0
|
20 |
+
logging_dir: logs
|
21 |
+
lr_num_cycles: 1
|
22 |
+
lr_scheduler: constant
|
23 |
+
lr_warmup_steps: 0
|
24 |
+
max_train_steps: 3000
|
25 |
+
mixed_precision: 'no'
|
26 |
+
num_train_epochs: 12
|
27 |
+
num_validation_images: 4
|
28 |
+
num_vectors: 1
|
29 |
+
output_dir: audio_inversion_cat
|
30 |
+
placeholder_token: <cat-meow>
|
31 |
+
pretrained_model_name_or_path: /home/plitsis/text-inv/audioldm-m-full
|
32 |
+
push_to_hub: true
|
33 |
+
repeats: 100
|
34 |
+
report_to: tensorboard
|
35 |
+
resolution: 512
|
36 |
+
resume_from_checkpoint: latest
|
37 |
+
revision: null
|
38 |
+
sample_rate: 16000
|
39 |
+
save_as_full_pipeline: false
|
40 |
+
save_steps: 500
|
41 |
+
scale_lr: true
|
42 |
+
seed: null
|
43 |
+
tokenizer_name: null
|
44 |
+
train_batch_size: 1
|
45 |
+
train_data_dir: /home/plitsis/text-inv/meows
|
46 |
+
validation_epochs: null
|
47 |
+
validation_prompt: null
|
48 |
+
validation_steps: 100
|
logs/textual_inversion/1689253409.366505/events.out.tfevents.1689253409.asimov.338271.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71a3963653d0db4e67906ae807bb3d5c8dfec3ee8b7f2dd37e89da5fb7da551a
|
3 |
+
size 2434
|
logs/textual_inversion/1689253409.3687513/hparams.yml
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 500
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
dataloader_num_workers: 0
|
10 |
+
duration: 10.0
|
11 |
+
enable_xformers_memory_efficient_attention: false
|
12 |
+
gradient_accumulation_steps: 4
|
13 |
+
gradient_checkpointing: false
|
14 |
+
hub_model_id: null
|
15 |
+
hub_token: null
|
16 |
+
initializer_token: cat
|
17 |
+
learnable_property: object
|
18 |
+
learning_rate: 0.002
|
19 |
+
local_rank: 0
|
20 |
+
logging_dir: logs
|
21 |
+
lr_num_cycles: 1
|
22 |
+
lr_scheduler: constant
|
23 |
+
lr_warmup_steps: 0
|
24 |
+
max_train_steps: 3000
|
25 |
+
mixed_precision: 'no'
|
26 |
+
num_train_epochs: 12
|
27 |
+
num_validation_images: 4
|
28 |
+
num_vectors: 1
|
29 |
+
output_dir: audio_inversion_cat
|
30 |
+
placeholder_token: <cat-meow>
|
31 |
+
pretrained_model_name_or_path: /home/plitsis/text-inv/audioldm-m-full
|
32 |
+
push_to_hub: true
|
33 |
+
repeats: 100
|
34 |
+
report_to: tensorboard
|
35 |
+
resolution: 512
|
36 |
+
resume_from_checkpoint: latest
|
37 |
+
revision: null
|
38 |
+
sample_rate: 16000
|
39 |
+
save_as_full_pipeline: false
|
40 |
+
save_steps: 500
|
41 |
+
scale_lr: true
|
42 |
+
seed: null
|
43 |
+
tokenizer_name: null
|
44 |
+
train_batch_size: 1
|
45 |
+
train_data_dir: /home/plitsis/text-inv/meows
|
46 |
+
validation_epochs: null
|
47 |
+
validation_prompt: null
|
48 |
+
validation_steps: 100
|
logs/textual_inversion/1689254068.9782665/events.out.tfevents.1689254068.asimov.343083.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e76bb814aafd669e7b771c0564f7ca3292af9baa5ecbf0802775db742b8cdf76
|
3 |
+
size 2434
|
logs/textual_inversion/1689254068.9806187/hparams.yml
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 500
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
dataloader_num_workers: 0
|
10 |
+
duration: 10.0
|
11 |
+
enable_xformers_memory_efficient_attention: false
|
12 |
+
gradient_accumulation_steps: 4
|
13 |
+
gradient_checkpointing: false
|
14 |
+
hub_model_id: null
|
15 |
+
hub_token: null
|
16 |
+
initializer_token: cat
|
17 |
+
learnable_property: object
|
18 |
+
learning_rate: 0.002
|
19 |
+
local_rank: 0
|
20 |
+
logging_dir: logs
|
21 |
+
lr_num_cycles: 1
|
22 |
+
lr_scheduler: constant
|
23 |
+
lr_warmup_steps: 0
|
24 |
+
max_train_steps: 3000
|
25 |
+
mixed_precision: 'no'
|
26 |
+
num_train_epochs: 12
|
27 |
+
num_validation_images: 4
|
28 |
+
num_vectors: 1
|
29 |
+
output_dir: audio_inversion_cat
|
30 |
+
placeholder_token: <cat-meow>
|
31 |
+
pretrained_model_name_or_path: /home/plitsis/text-inv/audioldm-m-full
|
32 |
+
push_to_hub: true
|
33 |
+
repeats: 100
|
34 |
+
report_to: tensorboard
|
35 |
+
resolution: 512
|
36 |
+
resume_from_checkpoint: latest
|
37 |
+
revision: null
|
38 |
+
sample_rate: 16000
|
39 |
+
save_as_full_pipeline: false
|
40 |
+
save_steps: 500
|
41 |
+
scale_lr: true
|
42 |
+
seed: null
|
43 |
+
tokenizer_name: null
|
44 |
+
train_batch_size: 1
|
45 |
+
train_data_dir: /home/plitsis/text-inv/meows
|
46 |
+
validation_epochs: null
|
47 |
+
validation_prompt: null
|
48 |
+
validation_steps: 100
|
logs/textual_inversion/1689255471.5416772/events.out.tfevents.1689255471.asimov.352802.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09347a213041978dc7293ed532e97cc694dbf5574c69d2d2fdd6067e75b6733a
|
3 |
+
size 2434
|
logs/textual_inversion/1689255471.5432942/hparams.yml
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 500
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
dataloader_num_workers: 0
|
10 |
+
duration: 10.0
|
11 |
+
enable_xformers_memory_efficient_attention: false
|
12 |
+
gradient_accumulation_steps: 4
|
13 |
+
gradient_checkpointing: false
|
14 |
+
hub_model_id: null
|
15 |
+
hub_token: null
|
16 |
+
initializer_token: cat
|
17 |
+
learnable_property: object
|
18 |
+
learning_rate: 0.002
|
19 |
+
local_rank: 0
|
20 |
+
logging_dir: logs
|
21 |
+
lr_num_cycles: 1
|
22 |
+
lr_scheduler: constant
|
23 |
+
lr_warmup_steps: 0
|
24 |
+
max_train_steps: 3000
|
25 |
+
mixed_precision: 'no'
|
26 |
+
num_train_epochs: 12
|
27 |
+
num_validation_images: 4
|
28 |
+
num_vectors: 1
|
29 |
+
output_dir: audio_inversion_cat
|
30 |
+
placeholder_token: <cat-meow>
|
31 |
+
pretrained_model_name_or_path: /home/plitsis/text-inv/audioldm-m-full
|
32 |
+
push_to_hub: true
|
33 |
+
repeats: 100
|
34 |
+
report_to: tensorboard
|
35 |
+
resolution: 512
|
36 |
+
resume_from_checkpoint: latest
|
37 |
+
revision: null
|
38 |
+
sample_rate: 16000
|
39 |
+
save_as_full_pipeline: false
|
40 |
+
save_steps: 500
|
41 |
+
scale_lr: true
|
42 |
+
seed: null
|
43 |
+
tokenizer_name: null
|
44 |
+
train_batch_size: 1
|
45 |
+
train_data_dir: /home/plitsis/text-inv/meows
|
46 |
+
validation_epochs: null
|
47 |
+
validation_prompt: null
|
48 |
+
validation_steps: 100
|
logs/textual_inversion/1689255529.8736153/events.out.tfevents.1689255529.asimov.353336.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98d8d4de311b7568505792189c9df08e13f0a609cc1602b9c7cfedc377c03a43
|
3 |
+
size 2434
|
logs/textual_inversion/1689255529.876004/hparams.yml
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 500
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
dataloader_num_workers: 0
|
10 |
+
duration: 10.0
|
11 |
+
enable_xformers_memory_efficient_attention: false
|
12 |
+
gradient_accumulation_steps: 4
|
13 |
+
gradient_checkpointing: false
|
14 |
+
hub_model_id: null
|
15 |
+
hub_token: null
|
16 |
+
initializer_token: cat
|
17 |
+
learnable_property: object
|
18 |
+
learning_rate: 0.002
|
19 |
+
local_rank: 0
|
20 |
+
logging_dir: logs
|
21 |
+
lr_num_cycles: 1
|
22 |
+
lr_scheduler: constant
|
23 |
+
lr_warmup_steps: 0
|
24 |
+
max_train_steps: 3000
|
25 |
+
mixed_precision: 'no'
|
26 |
+
num_train_epochs: 12
|
27 |
+
num_validation_images: 4
|
28 |
+
num_vectors: 1
|
29 |
+
output_dir: audio_inversion_cat
|
30 |
+
placeholder_token: <cat-meow>
|
31 |
+
pretrained_model_name_or_path: /home/plitsis/text-inv/audioldm-m-full
|
32 |
+
push_to_hub: true
|
33 |
+
repeats: 100
|
34 |
+
report_to: tensorboard
|
35 |
+
resolution: 512
|
36 |
+
resume_from_checkpoint: latest
|
37 |
+
revision: null
|
38 |
+
sample_rate: 16000
|
39 |
+
save_as_full_pipeline: false
|
40 |
+
save_steps: 500
|
41 |
+
scale_lr: true
|
42 |
+
seed: null
|
43 |
+
tokenizer_name: null
|
44 |
+
train_batch_size: 1
|
45 |
+
train_data_dir: /home/plitsis/text-inv/meows
|
46 |
+
validation_epochs: null
|
47 |
+
validation_prompt: null
|
48 |
+
validation_steps: 100
|
logs/textual_inversion/1689339474.8780582/events.out.tfevents.1689339474.asimov.1129689.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dec93592d41d5a4a5970c156fbd8a956bd84313a95bbf1064e66cef99b38a463
|
3 |
+
size 2434
|
logs/textual_inversion/1689339474.8803751/hparams.yml
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 500
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
dataloader_num_workers: 0
|
10 |
+
duration: 10.0
|
11 |
+
enable_xformers_memory_efficient_attention: false
|
12 |
+
gradient_accumulation_steps: 4
|
13 |
+
gradient_checkpointing: false
|
14 |
+
hub_model_id: null
|
15 |
+
hub_token: null
|
16 |
+
initializer_token: cat
|
17 |
+
learnable_property: object
|
18 |
+
learning_rate: 0.002
|
19 |
+
local_rank: 0
|
20 |
+
logging_dir: logs
|
21 |
+
lr_num_cycles: 1
|
22 |
+
lr_scheduler: constant
|
23 |
+
lr_warmup_steps: 0
|
24 |
+
max_train_steps: 3000
|
25 |
+
mixed_precision: 'no'
|
26 |
+
num_train_epochs: 12
|
27 |
+
num_validation_images: 4
|
28 |
+
num_vectors: 1
|
29 |
+
output_dir: audio_inversion_cat
|
30 |
+
placeholder_token: <cat-meow>
|
31 |
+
pretrained_model_name_or_path: /home/plitsis/text-inv/audioldm-m-full
|
32 |
+
push_to_hub: true
|
33 |
+
repeats: 100
|
34 |
+
report_to: tensorboard
|
35 |
+
resolution: 512
|
36 |
+
resume_from_checkpoint: latest
|
37 |
+
revision: null
|
38 |
+
sample_rate: 16000
|
39 |
+
save_as_full_pipeline: false
|
40 |
+
save_steps: 500
|
41 |
+
scale_lr: true
|
42 |
+
seed: null
|
43 |
+
tokenizer_name: null
|
44 |
+
train_batch_size: 1
|
45 |
+
train_data_dir: /home/plitsis/text-inv/meows
|
46 |
+
validation_epochs: null
|
47 |
+
validation_prompt: null
|
48 |
+
validation_steps: 100
|
logs/textual_inversion/1689341156.5645792/events.out.tfevents.1689341156.asimov.1141610.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d198f797a66ccc25c3aabd5ef098680e544f7ae98dd28fe842f72ce8e4a03b17
|
3 |
+
size 2434
|
logs/textual_inversion/1689341156.567027/hparams.yml
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 500
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
dataloader_num_workers: 0
|
10 |
+
duration: 10.0
|
11 |
+
enable_xformers_memory_efficient_attention: false
|
12 |
+
gradient_accumulation_steps: 4
|
13 |
+
gradient_checkpointing: false
|
14 |
+
hub_model_id: null
|
15 |
+
hub_token: null
|
16 |
+
initializer_token: cat
|
17 |
+
learnable_property: object
|
18 |
+
learning_rate: 0.002
|
19 |
+
local_rank: 0
|
20 |
+
logging_dir: logs
|
21 |
+
lr_num_cycles: 1
|
22 |
+
lr_scheduler: constant
|
23 |
+
lr_warmup_steps: 0
|
24 |
+
max_train_steps: 3000
|
25 |
+
mixed_precision: 'no'
|
26 |
+
num_train_epochs: 12
|
27 |
+
num_validation_images: 4
|
28 |
+
num_vectors: 1
|
29 |
+
output_dir: audio_inversion_cat
|
30 |
+
placeholder_token: <cat-meow>
|
31 |
+
pretrained_model_name_or_path: /home/plitsis/text-inv/audioldm-m-full
|
32 |
+
push_to_hub: true
|
33 |
+
repeats: 100
|
34 |
+
report_to: tensorboard
|
35 |
+
resolution: 512
|
36 |
+
resume_from_checkpoint: latest
|
37 |
+
revision: null
|
38 |
+
sample_rate: 16000
|
39 |
+
save_as_full_pipeline: false
|
40 |
+
save_steps: 500
|
41 |
+
scale_lr: true
|
42 |
+
seed: null
|
43 |
+
tokenizer_name: null
|
44 |
+
train_batch_size: 1
|
45 |
+
train_data_dir: /home/plitsis/text-inv/meows
|
46 |
+
validation_epochs: null
|
47 |
+
validation_prompt: null
|
48 |
+
validation_steps: 100
|
logs/textual_inversion/1689341606.0289376/events.out.tfevents.1689341606.asimov.1155434.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f801c3df049df6e697f347895cbd9212fadec9a31911336d67968ceb93f082f1
|
3 |
+
size 2434
|
logs/textual_inversion/1689341606.0312734/hparams.yml
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 500
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
dataloader_num_workers: 0
|
10 |
+
duration: 10.0
|
11 |
+
enable_xformers_memory_efficient_attention: false
|
12 |
+
gradient_accumulation_steps: 4
|
13 |
+
gradient_checkpointing: false
|
14 |
+
hub_model_id: null
|
15 |
+
hub_token: null
|
16 |
+
initializer_token: cat
|
17 |
+
learnable_property: object
|
18 |
+
learning_rate: 0.002
|
19 |
+
local_rank: 0
|
20 |
+
logging_dir: logs
|
21 |
+
lr_num_cycles: 1
|
22 |
+
lr_scheduler: constant
|
23 |
+
lr_warmup_steps: 0
|
24 |
+
max_train_steps: 3000
|
25 |
+
mixed_precision: 'no'
|
26 |
+
num_train_epochs: 12
|
27 |
+
num_validation_images: 4
|
28 |
+
num_vectors: 1
|
29 |
+
output_dir: audio_inversion_cat
|
30 |
+
placeholder_token: <cat-meow>
|
31 |
+
pretrained_model_name_or_path: /home/plitsis/text-inv/audioldm-m-full
|
32 |
+
push_to_hub: true
|
33 |
+
repeats: 100
|
34 |
+
report_to: tensorboard
|
35 |
+
resolution: 512
|
36 |
+
resume_from_checkpoint: latest
|
37 |
+
revision: null
|
38 |
+
sample_rate: 16000
|
39 |
+
save_as_full_pipeline: false
|
40 |
+
save_steps: 500
|
41 |
+
scale_lr: true
|
42 |
+
seed: null
|
43 |
+
tokenizer_name: null
|
44 |
+
train_batch_size: 1
|
45 |
+
train_data_dir: /home/plitsis/text-inv/meows
|
46 |
+
validation_epochs: null
|
47 |
+
validation_prompt: null
|
48 |
+
validation_steps: 100
|