kmpartner commited on
Commit
1aab434
·
verified ·
1 Parent(s): 45823c4

Upload folder using huggingface_hub

Browse files
Files changed (30) hide show
  1. README.md +4 -1
  2. adapter_config.json +14 -7
  3. adapter_model.safetensors +1 -1
  4. checkpoint-3250/README.md +204 -0
  5. checkpoint-3250/adapter_config.json +51 -0
  6. checkpoint-3250/adapter_model.safetensors +3 -0
  7. checkpoint-3250/optimizer.bin +3 -0
  8. checkpoint-3250/random_states_0.pkl +3 -0
  9. checkpoint-3250/scaler.pt +3 -0
  10. checkpoint-3250/scheduler.bin +3 -0
  11. checkpoint-3250/unet_lora/pytorch_lora_weights.safetensors +3 -0
  12. logs/text2image-fine-tune/1754360260.4236062/events.out.tfevents.1754360260.caa3d8519329.3877.1 +3 -0
  13. logs/text2image-fine-tune/1754360260.4252396/hparams.yml +57 -0
  14. logs/text2image-fine-tune/1754360350.7752283/events.out.tfevents.1754360350.caa3d8519329.4746.1 +3 -0
  15. logs/text2image-fine-tune/1754360350.7769659/hparams.yml +57 -0
  16. logs/text2image-fine-tune/1754360457.7329438/events.out.tfevents.1754360457.caa3d8519329.5252.1 +3 -0
  17. logs/text2image-fine-tune/1754360457.734638/hparams.yml +57 -0
  18. logs/text2image-fine-tune/1754363816.1790004/events.out.tfevents.1754363816.caa3d8519329.18997.1 +3 -0
  19. logs/text2image-fine-tune/1754363816.1810744/hparams.yml +57 -0
  20. logs/text2image-fine-tune/1754363983.5439937/events.out.tfevents.1754363983.caa3d8519329.19890.1 +3 -0
  21. logs/text2image-fine-tune/1754363983.5462303/hparams.yml +57 -0
  22. logs/text2image-fine-tune/1754364120.6985843/events.out.tfevents.1754364120.caa3d8519329.20508.1 +3 -0
  23. logs/text2image-fine-tune/1754364120.7003222/hparams.yml +57 -0
  24. logs/text2image-fine-tune/events.out.tfevents.1754360260.caa3d8519329.3877.0 +3 -0
  25. logs/text2image-fine-tune/events.out.tfevents.1754360350.caa3d8519329.4746.0 +3 -0
  26. logs/text2image-fine-tune/events.out.tfevents.1754360457.caa3d8519329.5252.0 +3 -0
  27. logs/text2image-fine-tune/events.out.tfevents.1754363816.caa3d8519329.18997.0 +3 -0
  28. logs/text2image-fine-tune/events.out.tfevents.1754363983.caa3d8519329.19890.0 +3 -0
  29. logs/text2image-fine-tune/events.out.tfevents.1754364120.caa3d8519329.20508.0 +3 -0
  30. unet_lora/pytorch_lora_weights.safetensors +1 -1
README.md CHANGED
@@ -1,6 +1,8 @@
1
  ---
2
- base_model: etri-vilab/koala-700m
3
  library_name: peft
 
 
4
  ---
5
 
6
  # Model Card for Model ID
@@ -199,5 +201,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
199
  [More Information Needed]
200
  ### Framework versions
201
 
 
202
  - PEFT 0.13.2
203
  - PEFT 0.12.0
 
1
  ---
2
+ base_model: kmpartner/k512-ft-test
3
  library_name: peft
4
+ tags:
5
+ - lora
6
  ---
7
 
8
  # Model Card for Model ID
 
201
  [More Information Needed]
202
  ### Framework versions
203
 
204
+ - PEFT 0.16.0
205
  - PEFT 0.13.2
206
  - PEFT 0.12.0
adapter_config.json CHANGED
@@ -6,6 +6,9 @@
6
  },
7
  "base_model_name_or_path": null,
8
  "bias": "none",
 
 
 
9
  "fan_in_fan_out": false,
10
  "inference_mode": true,
11
  "init_lora_weights": true,
@@ -14,31 +17,35 @@
14
  "layers_to_transform": null,
15
  "loftq_config": {},
16
  "lora_alpha": 64,
 
17
  "lora_dropout": 0.0,
18
  "megatron_config": null,
19
  "megatron_core": "megatron.core",
20
  "modules_to_save": null,
21
  "peft_type": "LORA",
 
22
  "r": 64,
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "proj_in",
27
  "to_k",
28
- "conv_shortcut",
29
- "upsamplers.0.conv",
30
  "conv2",
 
 
 
 
31
  "proj_out",
32
  "conv1",
33
  "to_out.0",
34
  "time_emb_proj",
35
- "downsamplers.0.conv",
36
- "ff.net.2",
37
- "ff.net.0.proj",
38
  "to_q",
39
- "to_v"
 
40
  ],
41
  "task_type": null,
 
42
  "use_dora": false,
 
43
  "use_rslora": false
44
  }
 
6
  },
7
  "base_model_name_or_path": null,
8
  "bias": "none",
9
+ "corda_config": null,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
  "fan_in_fan_out": false,
13
  "inference_mode": true,
14
  "init_lora_weights": true,
 
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
  "lora_alpha": 64,
20
+ "lora_bias": false,
21
  "lora_dropout": 0.0,
22
  "megatron_config": null,
23
  "megatron_core": "megatron.core",
24
  "modules_to_save": null,
25
  "peft_type": "LORA",
26
+ "qalora_group_size": 16,
27
  "r": 64,
28
  "rank_pattern": {},
29
  "revision": null,
30
  "target_modules": [
 
31
  "to_k",
32
+ "proj_in",
 
33
  "conv2",
34
+ "upsamplers.0.conv",
35
+ "to_v",
36
+ "ff.net.0.proj",
37
+ "downsamplers.0.conv",
38
  "proj_out",
39
  "conv1",
40
  "to_out.0",
41
  "time_emb_proj",
 
 
 
42
  "to_q",
43
+ "ff.net.2",
44
+ "conv_shortcut"
45
  ],
46
  "task_type": null,
47
+ "trainable_token_indices": null,
48
  "use_dora": false,
49
+ "use_qalora": false,
50
  "use_rslora": false
51
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a7fce899e131a79f0ec56284d3b3cbd97486d86b5a3afd6802556447a8d5e90
3
  size 251887560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466ec8eab2643532dddc8166cd9a426bb22b65c13cac87c2877573890996e99d
3
  size 251887560
checkpoint-3250/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: kmpartner/k512-ft-test
3
+ library_name: peft
4
+ tags:
5
+ - lora
6
+ ---
7
+
8
+ # Model Card for Model ID
9
+
10
+ <!-- Provide a quick summary of what the model is/does. -->
11
+
12
+
13
+
14
+ ## Model Details
15
+
16
+ ### Model Description
17
+
18
+ <!-- Provide a longer summary of what this model is. -->
19
+
20
+
21
+
22
+ - **Developed by:** [More Information Needed]
23
+ - **Funded by [optional]:** [More Information Needed]
24
+ - **Shared by [optional]:** [More Information Needed]
25
+ - **Model type:** [More Information Needed]
26
+ - **Language(s) (NLP):** [More Information Needed]
27
+ - **License:** [More Information Needed]
28
+ - **Finetuned from model [optional]:** [More Information Needed]
29
+
30
+ ### Model Sources [optional]
31
+
32
+ <!-- Provide the basic links for the model. -->
33
+
34
+ - **Repository:** [More Information Needed]
35
+ - **Paper [optional]:** [More Information Needed]
36
+ - **Demo [optional]:** [More Information Needed]
37
+
38
+ ## Uses
39
+
40
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
41
+
42
+ ### Direct Use
43
+
44
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
45
+
46
+ [More Information Needed]
47
+
48
+ ### Downstream Use [optional]
49
+
50
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Out-of-Scope Use
55
+
56
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
57
+
58
+ [More Information Needed]
59
+
60
+ ## Bias, Risks, and Limitations
61
+
62
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ### Recommendations
67
+
68
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
69
+
70
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
71
+
72
+ ## How to Get Started with the Model
73
+
74
+ Use the code below to get started with the model.
75
+
76
+ [More Information Needed]
77
+
78
+ ## Training Details
79
+
80
+ ### Training Data
81
+
82
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
83
+
84
+ [More Information Needed]
85
+
86
+ ### Training Procedure
87
+
88
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
89
+
90
+ #### Preprocessing [optional]
91
+
92
+ [More Information Needed]
93
+
94
+
95
+ #### Training Hyperparameters
96
+
97
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
98
+
99
+ #### Speeds, Sizes, Times [optional]
100
+
101
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
102
+
103
+ [More Information Needed]
104
+
105
+ ## Evaluation
106
+
107
+ <!-- This section describes the evaluation protocols and provides the results. -->
108
+
109
+ ### Testing Data, Factors & Metrics
110
+
111
+ #### Testing Data
112
+
113
+ <!-- This should link to a Dataset Card if possible. -->
114
+
115
+ [More Information Needed]
116
+
117
+ #### Factors
118
+
119
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Metrics
124
+
125
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
126
+
127
+ [More Information Needed]
128
+
129
+ ### Results
130
+
131
+ [More Information Needed]
132
+
133
+ #### Summary
134
+
135
+
136
+
137
+ ## Model Examination [optional]
138
+
139
+ <!-- Relevant interpretability work for the model goes here -->
140
+
141
+ [More Information Needed]
142
+
143
+ ## Environmental Impact
144
+
145
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
146
+
147
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
148
+
149
+ - **Hardware Type:** [More Information Needed]
150
+ - **Hours used:** [More Information Needed]
151
+ - **Cloud Provider:** [More Information Needed]
152
+ - **Compute Region:** [More Information Needed]
153
+ - **Carbon Emitted:** [More Information Needed]
154
+
155
+ ## Technical Specifications [optional]
156
+
157
+ ### Model Architecture and Objective
158
+
159
+ [More Information Needed]
160
+
161
+ ### Compute Infrastructure
162
+
163
+ [More Information Needed]
164
+
165
+ #### Hardware
166
+
167
+ [More Information Needed]
168
+
169
+ #### Software
170
+
171
+ [More Information Needed]
172
+
173
+ ## Citation [optional]
174
+
175
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
176
+
177
+ **BibTeX:**
178
+
179
+ [More Information Needed]
180
+
181
+ **APA:**
182
+
183
+ [More Information Needed]
184
+
185
+ ## Glossary [optional]
186
+
187
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
188
+
189
+ [More Information Needed]
190
+
191
+ ## More Information [optional]
192
+
193
+ [More Information Needed]
194
+
195
+ ## Model Card Authors [optional]
196
+
197
+ [More Information Needed]
198
+
199
+ ## Model Card Contact
200
+
201
+ [More Information Needed]
202
+ ### Framework versions
203
+
204
+ - PEFT 0.16.0
checkpoint-3250/adapter_config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "UNet2DConditionModel",
5
+ "parent_library": "diffusers.models.unets.unet_2d_condition"
6
+ },
7
+ "base_model_name_or_path": null,
8
+ "bias": "none",
9
+ "corda_config": null,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "qalora_group_size": 16,
27
+ "r": 64,
28
+ "rank_pattern": {},
29
+ "revision": null,
30
+ "target_modules": [
31
+ "to_k",
32
+ "proj_in",
33
+ "conv2",
34
+ "upsamplers.0.conv",
35
+ "to_v",
36
+ "ff.net.0.proj",
37
+ "downsamplers.0.conv",
38
+ "proj_out",
39
+ "conv1",
40
+ "to_out.0",
41
+ "time_emb_proj",
42
+ "to_q",
43
+ "ff.net.2",
44
+ "conv_shortcut"
45
+ ],
46
+ "task_type": null,
47
+ "trainable_token_indices": null,
48
+ "use_dora": false,
49
+ "use_qalora": false,
50
+ "use_rslora": false
51
+ }
checkpoint-3250/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466ec8eab2643532dddc8166cd9a426bb22b65c13cac87c2877573890996e99d
3
+ size 251887560
checkpoint-3250/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:825832c5375dd90f1850cf9d810dc6ae9023314391982955ba0df4a44b709ad1
3
+ size 129845599
checkpoint-3250/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee99bb3896b669174abe7d4fa57c013cb8014b583e9cccef7b4996821e80a7ca
3
+ size 14821
checkpoint-3250/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7de04b602caad0a5525863548f697c382a89d14095516f22d3e21aa65274b287
3
+ size 1383
checkpoint-3250/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989a1aaa5a599116947236958c486e9d70b18652c45a0bb091ba96c9b4a7ce02
3
+ size 1401
checkpoint-3250/unet_lora/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faed0a1308e5dd5f380d6c541b65b1a329ba26621c3124db2ced56872351f879
3
+ size 251890168
logs/text2image-fine-tune/1754360260.4236062/events.out.tfevents.1754360260.caa3d8519329.3877.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7965708a08c721a68a6aa5ded8d31e3e59ad707ad73cacbdf2198a72b0cccc6
3
+ size 3059
logs/text2image-fine-tune/1754360260.4252396/hparams.yml ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ cast_teacher_unet: false
8
+ center_crop: false
9
+ checkpointing_steps: 1000
10
+ checkpoints_total_limit: 10
11
+ dataloader_num_workers: 2
12
+ enable_xformers_memory_efficient_attention: true
13
+ gradient_accumulation_steps: 1
14
+ gradient_checkpointing: true
15
+ hub_model_id: null
16
+ hub_token: null
17
+ huber_c: 0.001
18
+ interpolation_type: bilinear
19
+ learning_rate: 5.0e-06
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lora_alpha: 64
23
+ lora_dropout: 0.0
24
+ lora_rank: 64
25
+ lora_target_modules: null
26
+ loss_type: huber
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: 4000000
31
+ max_train_steps: 4000
32
+ mixed_precision: fp16
33
+ num_ddim_timesteps: 50
34
+ num_train_epochs: 1
35
+ output_dir: k7mlcmdistill-test
36
+ pretrained_teacher_model: etri-vilab/koala-700m
37
+ pretrained_vae_model_name_or_path: null
38
+ proportion_empty_prompts: 0
39
+ push_to_hub: false
40
+ random_flip: false
41
+ report_to: tensorboard
42
+ resolution: 512
43
+ resume_from_checkpoint: ./k7mlcmdistill-test/checkpoint-3000
44
+ revision: null
45
+ scale_lr: false
46
+ seed: null
47
+ teacher_revision: null
48
+ timestep_scaling_factor: 10.0
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 8
51
+ train_shards_path_or_url: pipe:curl -L -s https://huggingface.co/datasets/laion/conceptual-captions-12m-webdataset/resolve/main/data/{00000..00002}.tar?download=true
52
+ use_8bit_adam: true
53
+ use_fix_crop_and_size: false
54
+ vae_encode_batch_size: 8
55
+ validation_steps: 10000000
56
+ w_max: 15.0
57
+ w_min: 3.0
logs/text2image-fine-tune/1754360350.7752283/events.out.tfevents.1754360350.caa3d8519329.4746.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da1bc180b7033a7fc0f416dd9895bf8461239eb9861948c006eb5ef5e4f3d030
3
+ size 3059
logs/text2image-fine-tune/1754360350.7769659/hparams.yml ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ cast_teacher_unet: false
8
+ center_crop: false
9
+ checkpointing_steps: 1000
10
+ checkpoints_total_limit: 10
11
+ dataloader_num_workers: 2
12
+ enable_xformers_memory_efficient_attention: true
13
+ gradient_accumulation_steps: 1
14
+ gradient_checkpointing: true
15
+ hub_model_id: null
16
+ hub_token: null
17
+ huber_c: 0.001
18
+ interpolation_type: bilinear
19
+ learning_rate: 5.0e-06
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lora_alpha: 64
23
+ lora_dropout: 0.0
24
+ lora_rank: 64
25
+ lora_target_modules: null
26
+ loss_type: huber
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: 4000000
31
+ max_train_steps: 4000
32
+ mixed_precision: fp16
33
+ num_ddim_timesteps: 50
34
+ num_train_epochs: 1
35
+ output_dir: k7mlcmdistill-test
36
+ pretrained_teacher_model: etri-vilab/koala-700m
37
+ pretrained_vae_model_name_or_path: null
38
+ proportion_empty_prompts: 0
39
+ push_to_hub: false
40
+ random_flip: false
41
+ report_to: tensorboard
42
+ resolution: 512
43
+ resume_from_checkpoint: ./k7mlcmdistill-test/checkpoint-3000
44
+ revision: null
45
+ scale_lr: false
46
+ seed: null
47
+ teacher_revision: null
48
+ timestep_scaling_factor: 10.0
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 4
51
+ train_shards_path_or_url: pipe:curl -L -s https://huggingface.co/datasets/laion/conceptual-captions-12m-webdataset/resolve/main/data/{00000..00002}.tar?download=true
52
+ use_8bit_adam: true
53
+ use_fix_crop_and_size: false
54
+ vae_encode_batch_size: 8
55
+ validation_steps: 10000000
56
+ w_max: 15.0
57
+ w_min: 3.0
logs/text2image-fine-tune/1754360457.7329438/events.out.tfevents.1754360457.caa3d8519329.5252.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18118793e2715d040c4f6db54a907499492e1968fcd3905c686518fcec9d0d2d
3
+ size 3059
logs/text2image-fine-tune/1754360457.734638/hparams.yml ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ cast_teacher_unet: false
8
+ center_crop: false
9
+ checkpointing_steps: 1000
10
+ checkpoints_total_limit: 10
11
+ dataloader_num_workers: 2
12
+ enable_xformers_memory_efficient_attention: true
13
+ gradient_accumulation_steps: 2
14
+ gradient_checkpointing: true
15
+ hub_model_id: null
16
+ hub_token: null
17
+ huber_c: 0.001
18
+ interpolation_type: bilinear
19
+ learning_rate: 5.0e-06
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lora_alpha: 64
23
+ lora_dropout: 0.0
24
+ lora_rank: 64
25
+ lora_target_modules: null
26
+ loss_type: huber
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: 4000000
31
+ max_train_steps: 4000
32
+ mixed_precision: fp16
33
+ num_ddim_timesteps: 50
34
+ num_train_epochs: 1
35
+ output_dir: k7mlcmdistill-test
36
+ pretrained_teacher_model: etri-vilab/koala-700m
37
+ pretrained_vae_model_name_or_path: null
38
+ proportion_empty_prompts: 0
39
+ push_to_hub: false
40
+ random_flip: false
41
+ report_to: tensorboard
42
+ resolution: 512
43
+ resume_from_checkpoint: ./k7mlcmdistill-test/checkpoint-3000
44
+ revision: null
45
+ scale_lr: false
46
+ seed: null
47
+ teacher_revision: null
48
+ timestep_scaling_factor: 10.0
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 4
51
+ train_shards_path_or_url: pipe:curl -L -s https://huggingface.co/datasets/laion/conceptual-captions-12m-webdataset/resolve/main/data/{00000..00002}.tar?download=true
52
+ use_8bit_adam: true
53
+ use_fix_crop_and_size: false
54
+ vae_encode_batch_size: 8
55
+ validation_steps: 10000000
56
+ w_max: 15.0
57
+ w_min: 3.0
logs/text2image-fine-tune/1754363816.1790004/events.out.tfevents.1754363816.caa3d8519329.18997.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba64395c6c7eedcabbd3f31ecf8e2c2a79739e4f8b4eb7d1893ef908749cc0f3
3
+ size 3059
logs/text2image-fine-tune/1754363816.1810744/hparams.yml ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ cast_teacher_unet: false
8
+ center_crop: false
9
+ checkpointing_steps: 1000
10
+ checkpoints_total_limit: 10
11
+ dataloader_num_workers: 2
12
+ enable_xformers_memory_efficient_attention: true
13
+ gradient_accumulation_steps: 2
14
+ gradient_checkpointing: true
15
+ hub_model_id: null
16
+ hub_token: null
17
+ huber_c: 0.001
18
+ interpolation_type: bilinear
19
+ learning_rate: 5.0e-06
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lora_alpha: 64
23
+ lora_dropout: 0.0
24
+ lora_rank: 64
25
+ lora_target_modules: null
26
+ loss_type: huber
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: 4000000
31
+ max_train_steps: 4000
32
+ mixed_precision: fp16
33
+ num_ddim_timesteps: 50
34
+ num_train_epochs: 1
35
+ output_dir: k7mlcmdistill-test
36
+ pretrained_teacher_model: etri-vilab/koala-700m
37
+ pretrained_vae_model_name_or_path: null
38
+ proportion_empty_prompts: 0
39
+ push_to_hub: false
40
+ random_flip: false
41
+ report_to: tensorboard
42
+ resolution: 512
43
+ resume_from_checkpoint: ./k7mlcmdistill-test/checkpoint-3000
44
+ revision: null
45
+ scale_lr: false
46
+ seed: null
47
+ teacher_revision: null
48
+ timestep_scaling_factor: 10.0
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 4
51
+ train_shards_path_or_url: pipe:curl -L -s https://huggingface.co/datasets/laion/conceptual-captions-12m-webdataset/resolve/main/data/{00000..00002}.tar?download=true
52
+ use_8bit_adam: true
53
+ use_fix_crop_and_size: false
54
+ vae_encode_batch_size: 8
55
+ validation_steps: 10000000
56
+ w_max: 15.0
57
+ w_min: 3.0
logs/text2image-fine-tune/1754363983.5439937/events.out.tfevents.1754363983.caa3d8519329.19890.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ae352a912b635ac251534e8a99043b7791b7dccb279010f68090d742dfe4b4c
3
+ size 3059
logs/text2image-fine-tune/1754363983.5462303/hparams.yml ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ cast_teacher_unet: false
8
+ center_crop: false
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: 10
11
+ dataloader_num_workers: 2
12
+ enable_xformers_memory_efficient_attention: true
13
+ gradient_accumulation_steps: 2
14
+ gradient_checkpointing: true
15
+ hub_model_id: null
16
+ hub_token: null
17
+ huber_c: 0.001
18
+ interpolation_type: bilinear
19
+ learning_rate: 5.0e-06
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lora_alpha: 64
23
+ lora_dropout: 0.0
24
+ lora_rank: 64
25
+ lora_target_modules: null
26
+ loss_type: huber
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: 4000000
31
+ max_train_steps: 3500
32
+ mixed_precision: fp16
33
+ num_ddim_timesteps: 50
34
+ num_train_epochs: 1
35
+ output_dir: k7mlcmdistill-test
36
+ pretrained_teacher_model: etri-vilab/koala-700m
37
+ pretrained_vae_model_name_or_path: null
38
+ proportion_empty_prompts: 0
39
+ push_to_hub: false
40
+ random_flip: false
41
+ report_to: tensorboard
42
+ resolution: 512
43
+ resume_from_checkpoint: ./k7mlcmdistill-test/checkpoint-3000
44
+ revision: null
45
+ scale_lr: false
46
+ seed: null
47
+ teacher_revision: null
48
+ timestep_scaling_factor: 10.0
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 4
51
+ train_shards_path_or_url: pipe:curl -L -s https://huggingface.co/datasets/laion/conceptual-captions-12m-webdataset/resolve/main/data/{00000..00002}.tar?download=true
52
+ use_8bit_adam: true
53
+ use_fix_crop_and_size: false
54
+ vae_encode_batch_size: 8
55
+ validation_steps: 10000000
56
+ w_max: 15.0
57
+ w_min: 3.0
logs/text2image-fine-tune/1754364120.6985843/events.out.tfevents.1754364120.caa3d8519329.20508.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824e6b1d669b386032b0d483591c2451b4b3350ba75bd34a6017799f438a771f
3
+ size 3059
logs/text2image-fine-tune/1754364120.7003222/hparams.yml ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ cast_teacher_unet: false
8
+ center_crop: false
9
+ checkpointing_steps: 250
10
+ checkpoints_total_limit: 10
11
+ dataloader_num_workers: 2
12
+ enable_xformers_memory_efficient_attention: true
13
+ gradient_accumulation_steps: 2
14
+ gradient_checkpointing: true
15
+ hub_model_id: null
16
+ hub_token: null
17
+ huber_c: 0.001
18
+ interpolation_type: bilinear
19
+ learning_rate: 5.0e-06
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lora_alpha: 64
23
+ lora_dropout: 0.0
24
+ lora_rank: 64
25
+ lora_target_modules: null
26
+ loss_type: huber
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: 4000000
31
+ max_train_steps: 3250
32
+ mixed_precision: fp16
33
+ num_ddim_timesteps: 50
34
+ num_train_epochs: 1
35
+ output_dir: k7mlcmdistill-test
36
+ pretrained_teacher_model: etri-vilab/koala-700m
37
+ pretrained_vae_model_name_or_path: null
38
+ proportion_empty_prompts: 0
39
+ push_to_hub: false
40
+ random_flip: false
41
+ report_to: tensorboard
42
+ resolution: 512
43
+ resume_from_checkpoint: ./k7mlcmdistill-test/checkpoint-3000
44
+ revision: null
45
+ scale_lr: false
46
+ seed: null
47
+ teacher_revision: null
48
+ timestep_scaling_factor: 10.0
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 4
51
+ train_shards_path_or_url: pipe:curl -L -s https://huggingface.co/datasets/laion/conceptual-captions-12m-webdataset/resolve/main/data/{00000..00002}.tar?download=true
52
+ use_8bit_adam: true
53
+ use_fix_crop_and_size: false
54
+ vae_encode_batch_size: 8
55
+ validation_steps: 10000000
56
+ w_max: 15.0
57
+ w_min: 3.0
logs/text2image-fine-tune/events.out.tfevents.1754360260.caa3d8519329.3877.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ad4d710b54158f5d5649f9922e3014ac1a3cb92e23c2c84f325b1218efef79
3
+ size 172
logs/text2image-fine-tune/events.out.tfevents.1754360350.caa3d8519329.4746.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af3886a02b95c92419f615841c6c3ca67b759696fe40e9cb0cdacd108978fa42
3
+ size 928
logs/text2image-fine-tune/events.out.tfevents.1754360457.caa3d8519329.5252.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a50ce10cff9c7a188305f42bc9bba4e1823bf65351b0fde8e7ff6d5ac2c5495a
3
+ size 104332
logs/text2image-fine-tune/events.out.tfevents.1754363816.caa3d8519329.18997.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb3b37f282587c62e9c3197135e822189c80a711d8d9183be4b23ecc953fd2a2
3
+ size 1600
logs/text2image-fine-tune/events.out.tfevents.1754363983.caa3d8519329.19890.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5621eb71cdf369cfae6c5c91e3d0459a787d79e09fe604bbf0706848617e8d0e
3
+ size 1012
logs/text2image-fine-tune/events.out.tfevents.1754364120.caa3d8519329.20508.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c4183b50491413899054c183ed1894892dbcd660a1e44b7810ff02e8428d09
3
+ size 42088
unet_lora/pytorch_lora_weights.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55eec582e42d11759f07fcde6b877ae2bb001a46c023eae7dd3202860ae93124
3
  size 251890168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faed0a1308e5dd5f380d6c541b65b1a329ba26621c3124db2ced56872351f879
3
  size 251890168