Upload folder using huggingface_hub

best/config.json

@@ -0,0 +1,20 @@
+{
+  "data_dir": "training_data",
+  "output_dir": "lora_output_v2",
+  "num_epochs": 100,
+  "learning_rate": 1e-05,
+  "weight_decay": 0.01,
+  "gradient_clip": 1.0,
+  "seed": 42,
+  "warmup_epochs": 5,
+  "gradient_accumulation_steps": 16,
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "save_every": 20,
+  "validate_every": 5,
+  "model_id": "stabilityai/stable-diffusion-xl-base-1.0",
+  "prompt": "a high quality photograph",
+  "num_timestep_buckets": 8,
+  "max_timestep": 600
+}

best/lora/README.md

@@ -0,0 +1,204 @@
+---
+base_model: /home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/unet
+library_name: peft
+tags:
+- lora
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

best/lora/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "UNet2DConditionModel",
+    "parent_library": "diffusers.models.unets.unet_2d_condition"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "to_q",
+    "to_k",
+    "ff.net.2",
+    "to_v",
+    "to_out.0",
+    "ff.net.0.proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

best/lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:163f6c55a1213b76c29d11a97bc2bb5fbe27e255effe12a77beebd18297cfdb8
+size 335115088

best/training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5248f7ef815e594b5d42a5ba92349a2ea24e2a53819f42fae80e37aa000d93a
+size 671001238

checkpoint-100/config.json

@@ -0,0 +1,20 @@
+{
+  "data_dir": "training_data",
+  "output_dir": "lora_output_v2",
+  "num_epochs": 100,
+  "learning_rate": 1e-05,
+  "weight_decay": 0.01,
+  "gradient_clip": 1.0,
+  "seed": 42,
+  "warmup_epochs": 5,
+  "gradient_accumulation_steps": 16,
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "save_every": 20,
+  "validate_every": 5,
+  "model_id": "stabilityai/stable-diffusion-xl-base-1.0",
+  "prompt": "a high quality photograph",
+  "num_timestep_buckets": 8,
+  "max_timestep": 600
+}

checkpoint-100/lora/README.md

@@ -0,0 +1,204 @@
+---
+base_model: /home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/unet
+library_name: peft
+tags:
+- lora
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-100/lora/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "UNet2DConditionModel",
+    "parent_library": "diffusers.models.unets.unet_2d_condition"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "to_q",
+    "to_k",
+    "ff.net.2",
+    "to_v",
+    "to_out.0",
+    "ff.net.0.proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-100/lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ba08005e76a5ce1a9a9f5a86d6f0638c83facaa745de94c8310137e21c2ba2
+size 335115088

checkpoint-100/training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5877b5df4b8efb7307f65af9e3192eb980dc96c004d65f214bd7ee92f9a97c1e
+size 671001238

checkpoint-20/config.json

@@ -0,0 +1,20 @@
+{
+  "data_dir": "training_data",
+  "output_dir": "lora_output_v2",
+  "num_epochs": 100,
+  "learning_rate": 1e-05,
+  "weight_decay": 0.01,
+  "gradient_clip": 1.0,
+  "seed": 42,
+  "warmup_epochs": 5,
+  "gradient_accumulation_steps": 8,
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "save_every": 20,
+  "validate_every": 5,
+  "model_id": "stabilityai/stable-diffusion-xl-base-1.0",
+  "prompt": "a high quality photograph",
+  "num_timestep_buckets": 8,
+  "max_timestep": 600
+}

checkpoint-20/lora/README.md

@@ -0,0 +1,204 @@
+---
+base_model: /home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/unet
+library_name: peft
+tags:
+- lora
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-20/lora/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "UNet2DConditionModel",
+    "parent_library": "diffusers.models.unets.unet_2d_condition"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "to_out.0",
+    "ff.net.0.proj",
+    "to_q",
+    "ff.net.2",
+    "to_k",
+    "to_v"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-20/lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b9a37af2a28dfc2a3efcafe0a8ff95e451219ffecfb370b50e497b3596262bc
+size 335115088

checkpoint-20/training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b8e17cc3ec53d1138904765921a0626c90b4584064a8ba41d56d3906cecba8
+size 670981654

checkpoint-40/config.json

@@ -0,0 +1,20 @@
+{
+  "data_dir": "training_data",
+  "output_dir": "lora_output_v2",
+  "num_epochs": 100,
+  "learning_rate": 1e-05,
+  "weight_decay": 0.01,
+  "gradient_clip": 1.0,
+  "seed": 42,
+  "warmup_epochs": 5,
+  "gradient_accumulation_steps": 8,
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "save_every": 20,
+  "validate_every": 5,
+  "model_id": "stabilityai/stable-diffusion-xl-base-1.0",
+  "prompt": "a high quality photograph",
+  "num_timestep_buckets": 8,
+  "max_timestep": 600
+}

checkpoint-40/lora/README.md

@@ -0,0 +1,204 @@
+---
+base_model: /home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/unet
+library_name: peft
+tags:
+- lora
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-40/lora/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "UNet2DConditionModel",
+    "parent_library": "diffusers.models.unets.unet_2d_condition"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "to_out.0",
+    "ff.net.0.proj",
+    "to_q",
+    "ff.net.2",
+    "to_k",
+    "to_v"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-40/lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5d8d75cf56cbb4a9ab17d9cc5b990cd175ed5f4ef74e9e765b7e5aeab0ff828
+size 335115088

checkpoint-40/training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a8a1bb321f033139ac4e8951807cf133bb3e14fa704dc5f86816aaeb2be862
+size 670981654

checkpoint-60/config.json

@@ -0,0 +1,20 @@
+{
+  "data_dir": "training_data",
+  "output_dir": "lora_output_v2",
+  "num_epochs": 100,
+  "learning_rate": 1e-05,
+  "weight_decay": 0.01,
+  "gradient_clip": 1.0,
+  "seed": 42,
+  "warmup_epochs": 5,
+  "gradient_accumulation_steps": 16,
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "save_every": 20,
+  "validate_every": 5,
+  "model_id": "stabilityai/stable-diffusion-xl-base-1.0",
+  "prompt": "a high quality photograph",
+  "num_timestep_buckets": 8,
+  "max_timestep": 600
+}

checkpoint-60/lora/README.md

@@ -0,0 +1,204 @@
+---
+base_model: /home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/unet
+library_name: peft
+tags:
+- lora
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-60/lora/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "UNet2DConditionModel",
+    "parent_library": "diffusers.models.unets.unet_2d_condition"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "to_out.0",
+    "to_q",
+    "to_k",
+    "to_v",
+    "ff.net.2",
+    "ff.net.0.proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-60/lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568cd994bc64f560f0ff103802f8ea71b7b43092b5d150319b76a6cf43794a7a
+size 335115088

checkpoint-60/training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c2f63007c177e9b5f8a8b754a2c5ebc3ee0c88abf8d7595d456483cc13b8818
+size 671001238

checkpoint-80/config.json

@@ -0,0 +1,20 @@
+{
+  "data_dir": "training_data",
+  "output_dir": "lora_output_v2",
+  "num_epochs": 100,
+  "learning_rate": 1e-05,
+  "weight_decay": 0.01,
+  "gradient_clip": 1.0,
+  "seed": 42,
+  "warmup_epochs": 5,
+  "gradient_accumulation_steps": 16,
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "save_every": 20,
+  "validate_every": 5,
+  "model_id": "stabilityai/stable-diffusion-xl-base-1.0",
+  "prompt": "a high quality photograph",
+  "num_timestep_buckets": 8,
+  "max_timestep": 600
+}

checkpoint-80/lora/README.md

@@ -0,0 +1,204 @@
+---
+base_model: /home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/unet
+library_name: peft
+tags:
+- lora
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-80/lora/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "UNet2DConditionModel",
+    "parent_library": "diffusers.models.unets.unet_2d_condition"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "to_q",
+    "to_k",
+    "ff.net.2",
+    "to_v",
+    "to_out.0",
+    "ff.net.0.proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-80/lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f84eb6d2b0c4327d16951f84319595a0798d8a0cc7b826b5a9845f96e30bc0b3
+size 335115088

checkpoint-80/training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9400715bc4e4303ef09941c50e2d1501a6951f7b91c90fc7be693ce30bfd1e3
+size 671001238

config.json

@@ -0,0 +1,20 @@
+{
+  "data_dir": "training_data",
+  "output_dir": "lora_output_v2",
+  "num_epochs": 100,
+  "learning_rate": 1e-05,
+  "weight_decay": 0.01,
+  "gradient_clip": 1.0,
+  "seed": 42,
+  "warmup_epochs": 5,
+  "gradient_accumulation_steps": 16,
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "save_every": 20,
+  "validate_every": 5,
+  "model_id": "stabilityai/stable-diffusion-xl-base-1.0",
+  "prompt": "a high quality photograph",
+  "num_timestep_buckets": 8,
+  "max_timestep": 600
+}

final/config.json

@@ -0,0 +1,20 @@
+{
+  "data_dir": "training_data",
+  "output_dir": "lora_output_v2",
+  "num_epochs": 100,
+  "learning_rate": 1e-05,
+  "weight_decay": 0.01,
+  "gradient_clip": 1.0,
+  "seed": 42,
+  "warmup_epochs": 5,
+  "gradient_accumulation_steps": 16,
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "save_every": 20,
+  "validate_every": 5,
+  "model_id": "stabilityai/stable-diffusion-xl-base-1.0",
+  "prompt": "a high quality photograph",
+  "num_timestep_buckets": 8,
+  "max_timestep": 600
+}

final/lora/README.md

@@ -0,0 +1,204 @@
+---
+base_model: /home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/unet
+library_name: peft
+tags:
+- lora
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

final/lora/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "UNet2DConditionModel",
+    "parent_library": "diffusers.models.unets.unet_2d_condition"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "to_q",
+    "to_k",
+    "ff.net.2",
+    "to_v",
+    "to_out.0",
+    "ff.net.0.proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

final/lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ba08005e76a5ce1a9a9f5a86d6f0638c83facaa745de94c8310137e21c2ba2
+size 335115088

final/training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a68b35d02f7c2e7cb911310d8f26c12719bd94ad9beb5ba1d854f5938bd04548
+size 671001238

training_log.jsonl

@@ -0,0 +1,100 @@
+{"epoch": 1, "train_loss": 17.19942092587395, "val_loss": null, "learning_rate": 4.000000000000001e-06, "epoch_time": 145.58935499191284, "total_time": 145.58935976028442, "best_val_loss": 17.19942092587395, "nan_count": 0}
+{"epoch": 2, "train_loss": 12.55613268770588, "val_loss": null, "learning_rate": 6e-06, "epoch_time": 146.4631314277649, "total_time": 292.05551624298096, "best_val_loss": 5.55613268770588, "nan_count": 0}
+{"epoch": 3, "train_loss": 8.259474676467168, "val_loss": null, "learning_rate": 8.000000000000001e-06, "epoch_time": 145.96791243553162, "total_time": 438.0265009403229, "best_val_loss": 8.259474676467168, "nan_count": 0}
+{"epoch": 4, "train_loss": 7.964921360687973, "val_loss": null, "learning_rate": 1e-05, "epoch_time": 146.06552052497864, "total_time": 584.09494805336, "best_val_loss": 4.964921360687973, "nan_count": 0}
+{"epoch": 5, "train_loss": 7.0351190459914505, "val_loss": 6.208327950419564, "learning_rate": 1e-05, "epoch_time": 160.01777362823486, "total_time": 744.1156527996063, "best_val_loss": 3.208327950419564, "nan_count": 0}
+{"epoch": 6, "train_loss": 9.778032663247238, "val_loss": null, "learning_rate": 9.99726628670463e-06, "epoch_time": 145.44241309165955, "total_time": 889.5590491294861, "best_val_loss": 3.208327950419564, "nan_count": 0}
+{"epoch": 7, "train_loss": 8.70230938885361, "val_loss": null, "learning_rate": 9.989068136093873e-06, "epoch_time": 145.6359989643097, "total_time": 1035.1985864639282, "best_val_loss": 3.208327950419564, "nan_count": 0}
+{"epoch": 8, "train_loss": 9.366116947424598, "val_loss": null, "learning_rate": 9.975414512725058e-06, "epoch_time": 145.6132140159607, "total_time": 1180.8149619102478, "best_val_loss": 3.208327950419564, "nan_count": 0}
+{"epoch": 9, "train_loss": 14.540897987526842, "val_loss": null, "learning_rate": 9.956320346634877e-06, "epoch_time": 145.92142820358276, "total_time": 1326.737675189972, "best_val_loss": 3.208327950419564, "nan_count": 0}
+{"epoch": 10, "train_loss": 4.996655541534225, "val_loss": 2.280347728807675, "learning_rate": 9.931806517013612e-06, "epoch_time": 159.60694217681885, "total_time": 1486.347716808319, "best_val_loss": 2.280347728807675, "nan_count": 0}
+{"epoch": 11, "train_loss": 4.1134332747121025, "val_loss": null, "learning_rate": 9.901899829374048e-06, "epoch_time": 145.5922462940216, "total_time": 1631.9406123161316, "best_val_loss": 2.280347728807675, "nan_count": 0}
+{"epoch": 12, "train_loss": 5.680793443702472, "val_loss": null, "learning_rate": 9.86663298624003e-06, "epoch_time": 144.39978694915771, "total_time": 1776.3436105251312, "best_val_loss": 2.280347728807675, "nan_count": 0}
+{"epoch": 13, "train_loss": 5.229802124877461, "val_loss": null, "learning_rate": 9.826044551386743e-06, "epoch_time": 144.18064284324646, "total_time": 1920.5256032943726, "best_val_loss": 2.280347728807675, "nan_count": 0}
+{"epoch": 14, "train_loss": 5.568235672001416, "val_loss": null, "learning_rate": 9.780178907671788e-06, "epoch_time": 145.47716188430786, "total_time": 2066.005401134491, "best_val_loss": 2.280347728807675, "nan_count": 0}
+{"epoch": 15, "train_loss": 7.370523032639175, "val_loss": 1.6486822170646567, "learning_rate": 9.729086208503174e-06, "epoch_time": 160.74190258979797, "total_time": 2226.7495832443237, "best_val_loss": 1.6486822170646567, "nan_count": 0}
+{"epoch": 16, "train_loss": 3.5894019457977264, "val_loss": null, "learning_rate": 9.672822322997305e-06, "epoch_time": 145.57167029380798, "total_time": 2372.3215625286102, "best_val_loss": 1.6486822170646567, "nan_count": 0}
+{"epoch": 17, "train_loss": 4.5010104613611475, "val_loss": null, "learning_rate": 9.611448774886925e-06, "epoch_time": 144.91890287399292, "total_time": 2517.243272304535, "best_val_loss": 1.6486822170646567, "nan_count": 0}
+{"epoch": 18, "train_loss": 3.4819029990506047, "val_loss": null, "learning_rate": 9.545032675245814e-06, "epoch_time": 145.5904724597931, "total_time": 2662.8364312648773, "best_val_loss": 1.6486822170646567, "nan_count": 0}
+{"epoch": 19, "train_loss": 5.438091036328115, "val_loss": null, "learning_rate": 9.473646649103819e-06, "epoch_time": 145.2338080406189, "total_time": 2808.0734555721283, "best_val_loss": 1.6486822170646567, "nan_count": 0}
+{"epoch": 20, "train_loss": 4.973662052745931, "val_loss": 1.197837292755905, "learning_rate": 9.397368756032445e-06, "epoch_time": 159.82029962539673, "total_time": 2967.8962948322296, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 21, "train_loss": 6.863651993110155, "val_loss": null, "learning_rate": 9.31628240478787e-06, "epoch_time": 144.0800268650055, "total_time": 3113.6745936870575, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 22, "train_loss": 3.1852325261725736, "val_loss": null, "learning_rate": 9.230476262104678e-06, "epoch_time": 144.9050657749176, "total_time": 3258.5832753181458, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 23, "train_loss": 3.6991982683849836, "val_loss": null, "learning_rate": 9.140044155740102e-06, "epoch_time": 145.23047804832458, "total_time": 3403.817048072815, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 24, "train_loss": 3.95262838259805, "val_loss": null, "learning_rate": 9.045084971874738e-06, "epoch_time": 144.11770796775818, "total_time": 3547.9379303455353, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 25, "train_loss": 3.4445872437441722, "val_loss": 4.225644043401668, "learning_rate": 8.94570254698197e-06, "epoch_time": 158.1483871936798, "total_time": 3706.0893836021423, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 26, "train_loss": 3.2804372601599123, "val_loss": null, "learning_rate": 8.842005554284296e-06, "epoch_time": 145.04227447509766, "total_time": 3851.1333639621735, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 27, "train_loss": 3.607025761832483, "val_loss": null, "learning_rate": 8.734107384920771e-06, "epoch_time": 144.76837968826294, "total_time": 3995.9050879478455, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 28, "train_loss": 3.5093281038027877, "val_loss": null, "learning_rate": 8.622126023955446e-06, "epoch_time": 144.69469618797302, "total_time": 4140.603454113007, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 29, "train_loss": 4.451195775601081, "val_loss": null, "learning_rate": 8.506183921362443e-06, "epoch_time": 144.09170651435852, "total_time": 4284.698315382004, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 30, "train_loss": 4.1997576663115375, "val_loss": 1.4401458956693347, "learning_rate": 8.386407858128707e-06, "epoch_time": 156.80615615844727, "total_time": 4441.507524013519, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 31, "train_loss": 3.8410931349731983, "val_loss": null, "learning_rate": 8.262928807620843e-06, "epoch_time": 143.9611668586731, "total_time": 4585.470387458801, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 32, "train_loss": 4.416647360411783, "val_loss": null, "learning_rate": 8.135881792367686e-06, "epoch_time": 144.73331475257874, "total_time": 4730.207221031189, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 33, "train_loss": 3.43881782689908, "val_loss": null, "learning_rate": 8.005405736415127e-06, "epoch_time": 144.51756763458252, "total_time": 4874.727851390839, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 34, "train_loss": 3.956570456316695, "val_loss": null, "learning_rate": 7.871643313414718e-06, "epoch_time": 145.275493144989, "total_time": 5020.006685018539, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 35, "train_loss": 3.417003455339, "val_loss": 1.345734186862645, "learning_rate": 7.734740790612137e-06, "epoch_time": 157.52464175224304, "total_time": 5177.534707546234, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 36, "train_loss": 3.192818854857856, "val_loss": null, "learning_rate": 7.594847868906076e-06, "epoch_time": 144.62704396247864, "total_time": 5322.1630783081055, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 37, "train_loss": 4.621960010170005, "val_loss": null, "learning_rate": 7.452117519152542e-06, "epoch_time": 144.45120477676392, "total_time": 5466.617178201675, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 38, "train_loss": 2.5693226069444792, "val_loss": null, "learning_rate": 7.30670581489344e-06, "epoch_time": 144.73938965797424, "total_time": 5611.360107660294, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 39, "train_loss": 3.421145873625452, "val_loss": null, "learning_rate": 7.158771761692464e-06, "epoch_time": 145.64204716682434, "total_time": 5757.004558324814, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 40, "train_loss": 5.932578617497347, "val_loss": 1.6734716096206714, "learning_rate": 7.008477123264849e-06, "epoch_time": 157.42941164970398, "total_time": 5914.437015295029, "best_val_loss": 1.197837292755905, "nan_count": 0}
+{"epoch": 41, "train_loss": 5.656617505843235, "val_loss": null, "learning_rate": 6.855986244591104e-06, "epoch_time": 143.39657282829285, "total_time": 143.3965790271759, "best_val_loss": 14.656617505843235, "nan_count": 0}
+{"epoch": 42, "train_loss": 4.776309097046033, "val_loss": null, "learning_rate": 6.701465872208216e-06, "epoch_time": 142.8288016319275, "total_time": 286.22876167297363, "best_val_loss": 11.776309097046033, "nan_count": 0}
+{"epoch": 43, "train_loss": 4.02011553304425, "val_loss": null, "learning_rate": 6.545084971874738e-06, "epoch_time": 142.45010638237, "total_time": 428.68155455589294, "best_val_loss": 21.02011553304425, "nan_count": 0}
+{"epoch": 44, "train_loss": 4.368613927586314, "val_loss": null, "learning_rate": 6.387014543809224e-06, "epoch_time": 142.8886272907257, "total_time": 571.5733850002289, "best_val_loss": 6.368613927586314, "nan_count": 0}
+{"epoch": 45, "train_loss": 3.5067328403936697, "val_loss": 1.3630286337513673, "learning_rate": 6.227427435703997e-06, "epoch_time": 157.36809968948364, "total_time": 728.9440271854401, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 46, "train_loss": 4.776196178830125, "val_loss": null, "learning_rate": 6.066498153718735e-06, "epoch_time": 143.07763409614563, "total_time": 872.0224120616913, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 47, "train_loss": 2.897143806747368, "val_loss": null, "learning_rate": 5.904402671660551e-06, "epoch_time": 142.7091383934021, "total_time": 1014.7353549003601, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 48, "train_loss": 3.4301633670693263, "val_loss": null, "learning_rate": 5.74131823855921e-06, "epoch_time": 143.206848859787, "total_time": 1157.9437563419342, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 49, "train_loss": 3.019160836259834, "val_loss": null, "learning_rate": 5.577423184847932e-06, "epoch_time": 142.6464865207672, "total_time": 1300.5940806865692, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 50, "train_loss": 5.098348380428635, "val_loss": 3.1046709630050158, "learning_rate": 5.412896727361663e-06, "epoch_time": 155.2999849319458, "total_time": 1455.8975348472595, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 51, "train_loss": 2.4326022625693846, "val_loss": null, "learning_rate": 5.247918773366112e-06, "epoch_time": 143.18976354599, "total_time": 1599.0884413719177, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 52, "train_loss": 5.461688357930527, "val_loss": null, "learning_rate": 5.082669723831793e-06, "epoch_time": 143.71299242973328, "total_time": 1742.8048348426819, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 53, "train_loss": 5.603210950971374, "val_loss": null, "learning_rate": 4.917330276168208e-06, "epoch_time": 143.43928027153015, "total_time": 1886.2469091415405, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 54, "train_loss": 6.067611928258298, "val_loss": null, "learning_rate": 4.752081226633888e-06, "epoch_time": 143.32387614250183, "total_time": 2029.5735266208649, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 55, "train_loss": 2.77310240741095, "val_loss": 2.746287005708406, "learning_rate": 4.587103272638339e-06, "epoch_time": 154.77045392990112, "total_time": 2184.347396373749, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 56, "train_loss": 3.860994441892641, "val_loss": null, "learning_rate": 4.42257681515207e-06, "epoch_time": 142.17878985404968, "total_time": 2326.5279154777527, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 57, "train_loss": 2.9203537055549935, "val_loss": null, "learning_rate": 4.25868176144079e-06, "epoch_time": 142.62657165527344, "total_time": 2469.156108379364, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 58, "train_loss": 2.23516917033121, "val_loss": null, "learning_rate": 4.0955973283394525e-06, "epoch_time": 143.16495561599731, "total_time": 2612.3243548870087, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 59, "train_loss": 2.700702446988887, "val_loss": null, "learning_rate": 3.9335018462812664e-06, "epoch_time": 142.84920525550842, "total_time": 2755.1775584220886, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 60, "train_loss": 1.440890104437454, "val_loss": 2.50316003494357, "learning_rate": 3.7725725642960047e-06, "epoch_time": 155.63533520698547, "total_time": 2910.815747022629, "best_val_loss": 1.3630286337513673, "nan_count": 0}
+{"epoch": 61, "train_loss": 2.488782158002465, "val_loss": null, "learning_rate": 3.6129854561907786e-06, "epoch_time": 143.37962675094604, "total_time": 143.3796329498291, "best_val_loss": 20.488782158002465, "nan_count": 0}
+{"epoch": 62, "train_loss": 1.74859287728452, "val_loss": null, "learning_rate": 3.4549150281252635e-06, "epoch_time": 142.21597123146057, "total_time": 285.59905791282654, "best_val_loss": 9.74859287728452, "nan_count": 0}
+{"epoch": 63, "train_loss": 2.27188630646043, "val_loss": null, "learning_rate": 3.298534127791785e-06, "epoch_time": 142.50022792816162, "total_time": 428.103568315506, "best_val_loss": 15.27188630646043, "nan_count": 0}
+{"epoch": 64, "train_loss": 1.821349680899746, "val_loss": null, "learning_rate": 3.1440137554088957e-06, "epoch_time": 142.3607213497162, "total_time": 570.4668045043945, "best_val_loss": 7.821349680899746, "nan_count": 0}
+{"epoch": 65, "train_loss": 3.4137809784643145, "val_loss": 1.3539129746587653, "learning_rate": 2.991522876735154e-06, "epoch_time": 156.72560334205627, "total_time": 727.1954562664032, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 66, "train_loss": 4.995955479543449, "val_loss": null, "learning_rate": 2.8412282383075362e-06, "epoch_time": 142.54419708251953, "total_time": 869.7405939102173, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 67, "train_loss": 2.958466476608171, "val_loss": null, "learning_rate": 2.693294185106562e-06, "epoch_time": 141.25971150398254, "total_time": 1011.0031368732452, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 68, "train_loss": 4.273237870377488, "val_loss": null, "learning_rate": 2.5478824808474613e-06, "epoch_time": 141.45464634895325, "total_time": 1152.4606049060822, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 69, "train_loss": 3.591097270141148, "val_loss": null, "learning_rate": 2.4051521310939258e-06, "epoch_time": 142.30907249450684, "total_time": 1294.7727823257446, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 70, "train_loss": 5.640156377595849, "val_loss": 2.092350325106006, "learning_rate": 2.265259209387867e-06, "epoch_time": 155.33024954795837, "total_time": 1450.1059267520905, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 71, "train_loss": 2.1183283414458858, "val_loss": null, "learning_rate": 2.1283566865852824e-06, "epoch_time": 142.02368235588074, "total_time": 1592.131136894226, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 72, "train_loss": 3.601663330500014, "val_loss": null, "learning_rate": 1.9945942635848745e-06, "epoch_time": 142.66171622276306, "total_time": 1734.7952601909637, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 73, "train_loss": 3.029718443321892, "val_loss": null, "learning_rate": 1.864118207632315e-06, "epoch_time": 142.56201457977295, "total_time": 1877.3608639240265, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 74, "train_loss": 3.356624772298771, "val_loss": null, "learning_rate": 1.7370711923791567e-06, "epoch_time": 141.64917373657227, "total_time": 2019.0135290622711, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 75, "train_loss": 2.158899751388365, "val_loss": 1.7367651415498635, "learning_rate": 1.6135921418712959e-06, "epoch_time": 154.80637192726135, "total_time": 2173.823189020157, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 76, "train_loss": 2.051477667151226, "val_loss": null, "learning_rate": 1.4938160786375571e-06, "epoch_time": 141.70708513259888, "total_time": 2315.53196144104, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 77, "train_loss": 2.035622535806356, "val_loss": null, "learning_rate": 1.3778739760445552e-06, "epoch_time": 142.36884546279907, "total_time": 2457.904289960861, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 78, "train_loss": 2.66036241442586, "val_loss": null, "learning_rate": 1.2658926150792321e-06, "epoch_time": 142.21520614624023, "total_time": 2600.12118935585, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 79, "train_loss": 5.332712841577207, "val_loss": null, "learning_rate": 1.157994445715706e-06, "epoch_time": 141.9722261428833, "total_time": 2742.0967559814453, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 80, "train_loss": 3.920014873607498, "val_loss": 2.47870918873109, "learning_rate": 1.0542974530180327e-06, "epoch_time": 155.21941447257996, "total_time": 2897.3196337223053, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 81, "train_loss": 2.137357483863727, "val_loss": null, "learning_rate": 9.549150281252633e-07, "epoch_time": 142.88429069519043, "total_time": 3041.94571018219, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 82, "train_loss": 4.8302023015683515, "val_loss": null, "learning_rate": 8.599558442598998e-07, "epoch_time": 143.12128472328186, "total_time": 3185.069757461548, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 83, "train_loss": 2.897690278928106, "val_loss": null, "learning_rate": 7.695237378953224e-07, "epoch_time": 141.9867081642151, "total_time": 3327.059638261795, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 84, "train_loss": 2.0897918677060967, "val_loss": null, "learning_rate": 6.837175952121305e-07, "epoch_time": 142.559903383255, "total_time": 3469.6231877803802, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 85, "train_loss": 2.6611573710494367, "val_loss": 3.7101728804409504, "learning_rate": 6.026312439675553e-07, "epoch_time": 155.1181299686432, "total_time": 3624.743953704834, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 86, "train_loss": 4.695689321971602, "val_loss": null, "learning_rate": 5.263533508961827e-07, "epoch_time": 142.60703897476196, "total_time": 3767.3530497550964, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 87, "train_loss": 4.102894639410078, "val_loss": null, "learning_rate": 4.549673247541875e-07, "epoch_time": 143.00318336486816, "total_time": 3910.357787132263, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 88, "train_loss": 2.502149013486794, "val_loss": null, "learning_rate": 3.885512251130763e-07, "epoch_time": 142.2848289012909, "total_time": 4052.646143913269, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 89, "train_loss": 2.40733334747557, "val_loss": null, "learning_rate": 3.271776770026963e-07, "epoch_time": 142.28666615486145, "total_time": 4194.934349060059, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 90, "train_loss": 2.4609227897444117, "val_loss": 2.19206017628312, "learning_rate": 2.7091379149682683e-07, "epoch_time": 155.36214113235474, "total_time": 4350.29993724823, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 91, "train_loss": 5.39812266294741, "val_loss": null, "learning_rate": 2.198210923282118e-07, "epoch_time": 142.426442861557, "total_time": 4492.728514432907, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 92, "train_loss": 3.1869998760107494, "val_loss": null, "learning_rate": 1.7395544861325718e-07, "epoch_time": 142.7557623386383, "total_time": 4635.487599611282, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 93, "train_loss": 2.5547544927672585, "val_loss": null, "learning_rate": 1.333670137599713e-07, "epoch_time": 143.1071343421936, "total_time": 4778.598335981369, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 94, "train_loss": 2.7601734893732806, "val_loss": null, "learning_rate": 9.810017062595322e-08, "epoch_time": 142.9020233154297, "total_time": 4921.503479719162, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 95, "train_loss": 3.5168714061767483, "val_loss": 2.0100861305469, "learning_rate": 6.819348298638839e-08, "epoch_time": 154.88099265098572, "total_time": 5076.388066530228, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 96, "train_loss": 3.9447177040545887, "val_loss": null, "learning_rate": 4.367965336512403e-08, "epoch_time": 141.7728033065796, "total_time": 5218.162786960602, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 97, "train_loss": 4.051030349847861, "val_loss": null, "learning_rate": 2.4585487274942922e-08, "epoch_time": 143.004798412323, "total_time": 5361.170787096024, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 98, "train_loss": 3.638974545474372, "val_loss": null, "learning_rate": 1.0931863906127327e-08, "epoch_time": 142.5158703327179, "total_time": 5503.689896821976, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 99, "train_loss": 2.435705656734191, "val_loss": null, "learning_rate": 2.7337132953697555e-09, "epoch_time": 142.18374347686768, "total_time": 5645.876638650894, "best_val_loss": 1.3539129746587653, "nan_count": 0}
+{"epoch": 100, "train_loss": 2.9739026984122265, "val_loss": 1.6748288934168063, "learning_rate": 0.0, "epoch_time": 155.27468371391296, "total_time": 5801.154787063599, "best_val_loss": 1.3539129746587653, "nan_count": 0}

training_summary.json

@@ -0,0 +1,428 @@
+{
+  "config": {
+    "data_dir": "training_data",
+    "output_dir": "lora_output_v2",
+    "num_epochs": 100,
+    "learning_rate": 1e-05,
+    "weight_decay": 0.01,
+    "gradient_clip": 1.0,
+    "seed": 42,
+    "warmup_epochs": 5,
+    "gradient_accumulation_steps": 16,
+    "lora_rank": 32,
+    "lora_alpha": 64,
+    "lora_dropout": 0.05,
+    "save_every": 20,
+    "validate_every": 5,
+    "model_id": "stabilityai/stable-diffusion-xl-base-1.0",
+    "prompt": "a high quality photograph",
+    "num_timestep_buckets": 8,
+    "max_timestep": 600
+  },
+  "metrics_history": [
+    {
+      "epoch": 61,
+      "train_loss": 20.488782158002465,
+      "val_loss": null,
+      "learning_rate": 3.6129854561907786e-06,
+      "epoch_time": 143.37962675094604,
+      "total_time": 143.3796329498291,
+      "best_val_loss": 20.488782158002465,
+      "nan_count": 0
+    },
+    {
+      "epoch": 62,
+      "train_loss": 9.74859287728452,
+      "val_loss": null,
+      "learning_rate": 3.4549150281252635e-06,
+      "epoch_time": 142.21597123146057,
+      "total_time": 285.59905791282654,
+      "best_val_loss": 9.74859287728452,
+      "nan_count": 0
+    },
+    {
+      "epoch": 63,
+      "train_loss": 15.27188630646043,
+      "val_loss": null,
+      "learning_rate": 3.298534127791785e-06,
+      "epoch_time": 142.50022792816162,
+      "total_time": 428.103568315506,
+      "best_val_loss": 15.27188630646043,
+      "nan_count": 0
+    },
+    {
+      "epoch": 64,
+      "train_loss": 7.821349680899746,
+      "val_loss": null,
+      "learning_rate": 3.1440137554088957e-06,
+      "epoch_time": 142.3607213497162,
+      "total_time": 570.4668045043945,
+      "best_val_loss": 7.821349680899746,
+      "nan_count": 0
+    },
+    {
+      "epoch": 65,
+      "train_loss": 3.4137809784643145,
+      "val_loss": 1.3539129746587653,
+      "learning_rate": 2.991522876735154e-06,
+      "epoch_time": 156.72560334205627,
+      "total_time": 727.1954562664032,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 66,
+      "train_loss": 4.995955479543449,
+      "val_loss": null,
+      "learning_rate": 2.8412282383075362e-06,
+      "epoch_time": 142.54419708251953,
+      "total_time": 869.7405939102173,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 67,
+      "train_loss": 2.958466476608171,
+      "val_loss": null,
+      "learning_rate": 2.693294185106562e-06,
+      "epoch_time": 141.25971150398254,
+      "total_time": 1011.0031368732452,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 68,
+      "train_loss": 4.273237870377488,
+      "val_loss": null,
+      "learning_rate": 2.5478824808474613e-06,
+      "epoch_time": 141.45464634895325,
+      "total_time": 1152.4606049060822,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 69,
+      "train_loss": 12.591097270141148,
+      "val_loss": null,
+      "learning_rate": 2.4051521310939258e-06,
+      "epoch_time": 142.30907249450684,
+      "total_time": 1294.7727823257446,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 70,
+      "train_loss": 5.640156377595849,
+      "val_loss": 3.092350325106006,
+      "learning_rate": 2.265259209387867e-06,
+      "epoch_time": 155.33024954795837,
+      "total_time": 1450.1059267520905,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 71,
+      "train_loss": 2.1183283414458858,
+      "val_loss": null,
+      "learning_rate": 2.1283566865852824e-06,
+      "epoch_time": 142.02368235588074,
+      "total_time": 1592.131136894226,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 72,
+      "train_loss": 4.601663330500014,
+      "val_loss": null,
+      "learning_rate": 1.9945942635848745e-06,
+      "epoch_time": 142.66171622276306,
+      "total_time": 1734.7952601909637,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 73,
+      "train_loss": 5.029718443321892,
+      "val_loss": null,
+      "learning_rate": 1.864118207632315e-06,
+      "epoch_time": 142.56201457977295,
+      "total_time": 1877.3608639240265,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 74,
+      "train_loss": 7.356624772298771,
+      "val_loss": null,
+      "learning_rate": 1.7370711923791567e-06,
+      "epoch_time": 141.64917373657227,
+      "total_time": 2019.0135290622711,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 75,
+      "train_loss": 11.158899751388365,
+      "val_loss": 2.7367651415498635,
+      "learning_rate": 1.6135921418712959e-06,
+      "epoch_time": 154.80637192726135,
+      "total_time": 2173.823189020157,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 76,
+      "train_loss": 4.051477667151226,
+      "val_loss": null,
+      "learning_rate": 1.4938160786375571e-06,
+      "epoch_time": 141.70708513259888,
+      "total_time": 2315.53196144104,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 77,
+      "train_loss": 3.035622535806356,
+      "val_loss": null,
+      "learning_rate": 1.3778739760445552e-06,
+      "epoch_time": 142.36884546279907,
+      "total_time": 2457.904289960861,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 78,
+      "train_loss": 10.66036241442586,
+      "val_loss": null,
+      "learning_rate": 1.2658926150792321e-06,
+      "epoch_time": 142.21520614624023,
+      "total_time": 2600.12118935585,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 79,
+      "train_loss": 5.332712841577207,
+      "val_loss": null,
+      "learning_rate": 1.157994445715706e-06,
+      "epoch_time": 141.9722261428833,
+      "total_time": 2742.0967559814453,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 80,
+      "train_loss": 3.920014873607498,
+      "val_loss": 24.47870918873109,
+      "learning_rate": 1.0542974530180327e-06,
+      "epoch_time": 155.21941447257996,
+      "total_time": 2897.3196337223053,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 81,
+      "train_loss": 6.137357483863727,
+      "val_loss": null,
+      "learning_rate": 9.549150281252633e-07,
+      "epoch_time": 142.88429069519043,
+      "total_time": 3041.94571018219,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 82,
+      "train_loss": 4.8302023015683515,
+      "val_loss": null,
+      "learning_rate": 8.599558442598998e-07,
+      "epoch_time": 143.12128472328186,
+      "total_time": 3185.069757461548,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 83,
+      "train_loss": 2.897690278928106,
+      "val_loss": null,
+      "learning_rate": 7.695237378953224e-07,
+      "epoch_time": 141.9867081642151,
+      "total_time": 3327.059638261795,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 84,
+      "train_loss": 2.0897918677060967,
+      "val_loss": null,
+      "learning_rate": 6.837175952121305e-07,
+      "epoch_time": 142.559903383255,
+      "total_time": 3469.6231877803802,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 85,
+      "train_loss": 2.6611573710494367,
+      "val_loss": 3.7101728804409504,
+      "learning_rate": 6.026312439675553e-07,
+      "epoch_time": 155.1181299686432,
+      "total_time": 3624.743953704834,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 86,
+      "train_loss": 7.695689321971602,
+      "val_loss": null,
+      "learning_rate": 5.263533508961827e-07,
+      "epoch_time": 142.60703897476196,
+      "total_time": 3767.3530497550964,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 87,
+      "train_loss": 9.102894639410078,
+      "val_loss": null,
+      "learning_rate": 4.549673247541875e-07,
+      "epoch_time": 143.00318336486816,
+      "total_time": 3910.357787132263,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 88,
+      "train_loss": 2.502149013486794,
+      "val_loss": null,
+      "learning_rate": 3.885512251130763e-07,
+      "epoch_time": 142.2848289012909,
+      "total_time": 4052.646143913269,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 89,
+      "train_loss": 5.40733334747557,
+      "val_loss": null,
+      "learning_rate": 3.271776770026963e-07,
+      "epoch_time": 142.28666615486145,
+      "total_time": 4194.934349060059,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 90,
+      "train_loss": 2.4609227897444117,
+      "val_loss": 27.69206017628312,
+      "learning_rate": 2.7091379149682683e-07,
+      "epoch_time": 155.36214113235474,
+      "total_time": 4350.29993724823,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 91,
+      "train_loss": 5.39812266294741,
+      "val_loss": null,
+      "learning_rate": 2.198210923282118e-07,
+      "epoch_time": 142.426442861557,
+      "total_time": 4492.728514432907,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 92,
+      "train_loss": 3.1869998760107494,
+      "val_loss": null,
+      "learning_rate": 1.7395544861325718e-07,
+      "epoch_time": 142.7557623386383,
+      "total_time": 4635.487599611282,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 93,
+      "train_loss": 2.5547544927672585,
+      "val_loss": null,
+      "learning_rate": 1.333670137599713e-07,
+      "epoch_time": 143.1071343421936,
+      "total_time": 4778.598335981369,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 94,
+      "train_loss": 2.7601734893732806,
+      "val_loss": null,
+      "learning_rate": 9.810017062595322e-08,
+      "epoch_time": 142.9020233154297,
+      "total_time": 4921.503479719162,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 95,
+      "train_loss": 3.5168714061767483,
+      "val_loss": 9.10100861305469,
+      "learning_rate": 6.819348298638839e-08,
+      "epoch_time": 154.88099265098572,
+      "total_time": 5076.388066530228,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 96,
+      "train_loss": 3.9447177040545887,
+      "val_loss": null,
+      "learning_rate": 4.367965336512403e-08,
+      "epoch_time": 141.7728033065796,
+      "total_time": 5218.162786960602,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 97,
+      "train_loss": 6.051030349847861,
+      "val_loss": null,
+      "learning_rate": 2.4585487274942922e-08,
+      "epoch_time": 143.004798412323,
+      "total_time": 5361.170787096024,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 98,
+      "train_loss": 6.638974545474372,
+      "val_loss": null,
+      "learning_rate": 1.0931863906127327e-08,
+      "epoch_time": 142.5158703327179,
+      "total_time": 5503.689896821976,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 99,
+      "train_loss": 9.435705656734191,
+      "val_loss": null,
+      "learning_rate": 2.7337132953697555e-09,
+      "epoch_time": 142.18374347686768,
+      "total_time": 5645.876638650894,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    },
+    {
+      "epoch": 100,
+      "train_loss": 7.9739026984122265,
+      "val_loss": 3.4748288934168063,
+      "learning_rate": 0.0,
+      "epoch_time": 155.27468371391296,
+      "total_time": 5801.154787063599,
+      "best_val_loss": 1.3539129746587653,
+      "nan_count": 0
+    }
+  ],
+  "final_train_loss": 7.9739026984122265,
+  "best_val_loss": 1.3539129746587653,
+  "total_epochs": 40,
+  "timestamp": "2025-12-05T22:13:47.777813"
+}