Uploaded our current best model

.gitattributes

@@ -44,3 +44,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 10310000_distortion_2/final_model/eval_scatter_plot.png filter=lfs diff=lfs merge=lfs -text
 10310000_distortion_2/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 10310800_full_2/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/01_scene/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/01_scene/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/01_scene/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/02_distortion/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/02_distortion/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/02_distortion/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/03_quality/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/03_quality/checkpoint-1700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/03_quality/checkpoint-1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/03_quality/checkpoint-2100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/03_quality/checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/final_model/eval_scatter_plot_csiq_full.png filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/final_model/eval_scatter_plot_kadid-10k_validation.png filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/final_model/eval_scatter_plot_koniq-10k_testing.png filter=lfs diff=lfs merge=lfs -text
+2025-11-26-16-50-52/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text

2025-11-26-16-50-52/01_scene/checkpoint-100/README.md

@@ -0,0 +1,207 @@
+---
+base_model: src/owl3
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:src/owl3
+- lora
+- transformers
+---
+
+# 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 0.17.1

2025-11-26-16-50-52/01_scene/checkpoint-100/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "src/owl3",
+  "bias": "none",
+  "corda_config": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

2025-11-26-16-50-52/01_scene/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d227ac43dea2277cca9141fb4864c5a102a060d5be1d166e85bd92dad3c0da
+size 173507576

2025-11-26-16-50-52/01_scene/checkpoint-100/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

2025-11-26-16-50-52/01_scene/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee93be382301d69d5845cf6690508b369b886542302074061e12a619a3f09f6a
+size 346426383

2025-11-26-16-50-52/01_scene/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c45eee438afc8a5dc3aa37e234d797ee8f451c3558934c36fd101e2e774bb4f3
+size 14645

2025-11-26-16-50-52/01_scene/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441ef59f1d5d6d1eba1fd1f9f4c9a8660f66e566f1b8b3b88c35a5dad7fb26b6
+size 1465

2025-11-26-16-50-52/01_scene/checkpoint-100/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

2025-11-26-16-50-52/01_scene/checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

2025-11-26-16-50-52/01_scene/checkpoint-100/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

2025-11-26-16-50-52/01_scene/checkpoint-100/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": 0.03937990590929985,
+  "best_model_checkpoint": "outputs/2025-11-26-16-50-52/01_scene/checkpoint-100",
+  "epoch": 0.11334655709832814,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05667327854916407,
+      "grad_norm": 4.339138507843018,
+      "learning_rate": 0.000125,
+      "loss": 0.3253,
+      "step": 50
+    },
+    {
+      "epoch": 0.11334655709832814,
+      "grad_norm": 3.550264835357666,
+      "learning_rate": 0.00019997002254654227,
+      "loss": 0.0543,
+      "step": 100
+    },
+    {
+      "epoch": 0.11334655709832814,
+      "eval_loss": 0.03937990590929985,
+      "eval_runtime": 90.138,
+      "eval_samples_per_second": 11.094,
+      "eval_steps_per_second": 11.094,
+      "step": 100
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2646,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

2025-11-26-16-50-52/01_scene/checkpoint-400/README.md

@@ -0,0 +1,207 @@
+---
+base_model: src/owl3
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:src/owl3
+- lora
+- transformers
+---
+
+# 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 0.17.1

2025-11-26-16-50-52/01_scene/checkpoint-400/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "src/owl3",
+  "bias": "none",
+  "corda_config": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

2025-11-26-16-50-52/01_scene/checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816110d185222589b0a18d789a798bd7a593a095ced1a583850813114edbaa48
+size 173507576

2025-11-26-16-50-52/01_scene/checkpoint-400/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

2025-11-26-16-50-52/01_scene/checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cfcbec1b377be644f660d0a2fdc514275ddcaeff1d75dc470546804bc5c4d7e
+size 346426383

2025-11-26-16-50-52/01_scene/checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49fd7ae9b0200cc68753ba87024f2a0bcda3a02a4a85275d02a14f5d82b84970
+size 14645

2025-11-26-16-50-52/01_scene/checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b033da602049fdfa97afecf91db3cb37bbb93391e705e455fcf44171f0a17ee1
+size 1465

2025-11-26-16-50-52/01_scene/checkpoint-400/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

2025-11-26-16-50-52/01_scene/checkpoint-400/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

2025-11-26-16-50-52/01_scene/checkpoint-400/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

2025-11-26-16-50-52/01_scene/checkpoint-400/trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": 0.034898512065410614,
+  "best_model_checkpoint": "outputs/2025-11-26-16-50-52/01_scene/checkpoint-400",
+  "epoch": 0.45338622839331255,
+  "eval_steps": 100,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05667327854916407,
+      "grad_norm": 4.339138507843018,
+      "learning_rate": 0.000125,
+      "loss": 0.3253,
+      "step": 50
+    },
+    {
+      "epoch": 0.11334655709832814,
+      "grad_norm": 3.550264835357666,
+      "learning_rate": 0.00019997002254654227,
+      "loss": 0.0543,
+      "step": 100
+    },
+    {
+      "epoch": 0.11334655709832814,
+      "eval_loss": 0.03937990590929985,
+      "eval_runtime": 90.138,
+      "eval_samples_per_second": 11.094,
+      "eval_steps_per_second": 11.094,
+      "step": 100
+    },
+    {
+      "epoch": 0.1700198356474922,
+      "grad_norm": 1.1671267747879028,
+      "learning_rate": 0.0001996329825692593,
+      "loss": 0.0431,
+      "step": 150
+    },
+    {
+      "epoch": 0.22669311419665628,
+      "grad_norm": 5.124600887298584,
+      "learning_rate": 0.00019892269762919834,
+      "loss": 0.0385,
+      "step": 200
+    },
+    {
+      "epoch": 0.22669311419665628,
+      "eval_loss": 0.039480071514844894,
+      "eval_runtime": 90.0332,
+      "eval_samples_per_second": 11.107,
+      "eval_steps_per_second": 11.107,
+      "step": 200
+    },
+    {
+      "epoch": 0.2833663927458204,
+      "grad_norm": 1.6820999383926392,
+      "learning_rate": 0.0001978418285949712,
+      "loss": 0.0438,
+      "step": 250
+    },
+    {
+      "epoch": 0.3400396712949844,
+      "grad_norm": 3.634084463119507,
+      "learning_rate": 0.0001963944246168898,
+      "loss": 0.0352,
+      "step": 300
+    },
+    {
+      "epoch": 0.3400396712949844,
+      "eval_loss": 0.05238571763038635,
+      "eval_runtime": 90.3736,
+      "eval_samples_per_second": 11.065,
+      "eval_steps_per_second": 11.065,
+      "step": 300
+    },
+    {
+      "epoch": 0.3967129498441485,
+      "grad_norm": 0.8966110348701477,
+      "learning_rate": 0.00019458590795804406,
+      "loss": 0.0319,
+      "step": 350
+    },
+    {
+      "epoch": 0.45338622839331255,
+      "grad_norm": 2.966634511947632,
+      "learning_rate": 0.00019242305368142622,
+      "loss": 0.0302,
+      "step": 400
+    },
+    {
+      "epoch": 0.45338622839331255,
+      "eval_loss": 0.034898512065410614,
+      "eval_runtime": 90.038,
+      "eval_samples_per_second": 11.106,
+      "eval_steps_per_second": 11.106,
+      "step": 400
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2646,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

2025-11-26-16-50-52/01_scene/checkpoint-800/README.md

@@ -0,0 +1,207 @@
+---
+base_model: src/owl3
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:src/owl3
+- lora
+- transformers
+---
+
+# 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 0.17.1

2025-11-26-16-50-52/01_scene/checkpoint-800/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "src/owl3",
+  "bias": "none",
+  "corda_config": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

2025-11-26-16-50-52/01_scene/checkpoint-800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df63a97c892d9c5cdf0356a106784c03d8816195151e18718aaf4c1bee06807d
+size 173507576

2025-11-26-16-50-52/01_scene/checkpoint-800/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

2025-11-26-16-50-52/01_scene/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006581a8b3c441c8db2d4d05664e856697615151776fe627c139ee488523a236
+size 346426383

2025-11-26-16-50-52/01_scene/checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6643285b53f3bcb404e1a18f452acfc0c02d10349609936ea13290cb5e7d9a1d
+size 14645

2025-11-26-16-50-52/01_scene/checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1b9b94d36e31ca1b4a396f1a3c56e64d286214cf956e6651be979216eaf6fb
+size 1465

2025-11-26-16-50-52/01_scene/checkpoint-800/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

2025-11-26-16-50-52/01_scene/checkpoint-800/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

2025-11-26-16-50-52/01_scene/checkpoint-800/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

2025-11-26-16-50-52/01_scene/checkpoint-800/trainer_state.json

@@ -0,0 +1,209 @@
+{
+  "best_metric": 0.03386669233441353,
+  "best_model_checkpoint": "outputs/2025-11-26-16-50-52/01_scene/checkpoint-800",
+  "epoch": 0.9067724567866251,
+  "eval_steps": 100,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05667327854916407,
+      "grad_norm": 4.339138507843018,
+      "learning_rate": 0.000125,
+      "loss": 0.3253,
+      "step": 50
+    },
+    {
+      "epoch": 0.11334655709832814,
+      "grad_norm": 3.550264835357666,
+      "learning_rate": 0.00019997002254654227,
+      "loss": 0.0543,
+      "step": 100
+    },
+    {
+      "epoch": 0.11334655709832814,
+      "eval_loss": 0.03937990590929985,
+      "eval_runtime": 90.138,
+      "eval_samples_per_second": 11.094,
+      "eval_steps_per_second": 11.094,
+      "step": 100
+    },
+    {
+      "epoch": 0.1700198356474922,
+      "grad_norm": 1.1671267747879028,
+      "learning_rate": 0.0001996329825692593,
+      "loss": 0.0431,
+      "step": 150
+    },
+    {
+      "epoch": 0.22669311419665628,
+      "grad_norm": 5.124600887298584,
+      "learning_rate": 0.00019892269762919834,
+      "loss": 0.0385,
+      "step": 200
+    },
+    {
+      "epoch": 0.22669311419665628,
+      "eval_loss": 0.039480071514844894,
+      "eval_runtime": 90.0332,
+      "eval_samples_per_second": 11.107,
+      "eval_steps_per_second": 11.107,
+      "step": 200
+    },
+    {
+      "epoch": 0.2833663927458204,
+      "grad_norm": 1.6820999383926392,
+      "learning_rate": 0.0001978418285949712,
+      "loss": 0.0438,
+      "step": 250
+    },
+    {
+      "epoch": 0.3400396712949844,
+      "grad_norm": 3.634084463119507,
+      "learning_rate": 0.0001963944246168898,
+      "loss": 0.0352,
+      "step": 300
+    },
+    {
+      "epoch": 0.3400396712949844,
+      "eval_loss": 0.05238571763038635,
+      "eval_runtime": 90.3736,
+      "eval_samples_per_second": 11.065,
+      "eval_steps_per_second": 11.065,
+      "step": 300
+    },
+    {
+      "epoch": 0.3967129498441485,
+      "grad_norm": 0.8966110348701477,
+      "learning_rate": 0.00019458590795804406,
+      "loss": 0.0319,
+      "step": 350
+    },
+    {
+      "epoch": 0.45338622839331255,
+      "grad_norm": 2.966634511947632,
+      "learning_rate": 0.00019242305368142622,
+      "loss": 0.0302,
+      "step": 400
+    },
+    {
+      "epoch": 0.45338622839331255,
+      "eval_loss": 0.034898512065410614,
+      "eval_runtime": 90.038,
+      "eval_samples_per_second": 11.106,
+      "eval_steps_per_second": 11.106,
+      "step": 400
+    },
+    {
+      "epoch": 0.5100595069424766,
+      "grad_norm": 3.242164373397827,
+      "learning_rate": 0.00018991396426919788,
+      "loss": 0.2013,
+      "step": 450
+    },
+    {
+      "epoch": 0.5667327854916407,
+      "grad_norm": 1.3575365543365479,
+      "learning_rate": 0.00018706803926918063,
+      "loss": 0.0265,
+      "step": 500
+    },
+    {
+      "epoch": 0.5667327854916407,
+      "eval_loss": 0.039046503603458405,
+      "eval_runtime": 90.0456,
+      "eval_samples_per_second": 11.105,
+      "eval_steps_per_second": 11.105,
+      "step": 500
+    },
+    {
+      "epoch": 0.6234060640408048,
+      "grad_norm": 0.3216783106327057,
+      "learning_rate": 0.00018389594008228123,
+      "loss": 0.0388,
+      "step": 550
+    },
+    {
+      "epoch": 0.6800793425899688,
+      "grad_norm": 0.2726989686489105,
+      "learning_rate": 0.00018040955002276377,
+      "loss": 0.0307,
+      "step": 600
+    },
+    {
+      "epoch": 0.6800793425899688,
+      "eval_loss": 0.0383339487016201,
+      "eval_runtime": 90.0647,
+      "eval_samples_per_second": 11.103,
+      "eval_steps_per_second": 11.103,
+      "step": 600
+    },
+    {
+      "epoch": 0.7367526211391329,
+      "grad_norm": 3.5234360694885254,
+      "learning_rate": 0.0001766219298009918,
+      "loss": 0.0261,
+      "step": 650
+    },
+    {
+      "epoch": 0.793425899688297,
+      "grad_norm": 0.45793426036834717,
+      "learning_rate": 0.00017254726859541043,
+      "loss": 0.022,
+      "step": 700
+    },
+    {
+      "epoch": 0.793425899688297,
+      "eval_loss": 0.03573239967226982,
+      "eval_runtime": 90.0501,
+      "eval_samples_per_second": 11.105,
+      "eval_steps_per_second": 11.105,
+      "step": 700
+    },
+    {
+      "epoch": 0.8500991782374611,
+      "grad_norm": 2.6463303565979004,
+      "learning_rate": 0.00016820083089706263,
+      "loss": 0.0254,
+      "step": 750
+    },
+    {
+      "epoch": 0.9067724567866251,
+      "grad_norm": 1.4524548053741455,
+      "learning_rate": 0.0001635988993257706,
+      "loss": 0.0188,
+      "step": 800
+    },
+    {
+      "epoch": 0.9067724567866251,
+      "eval_loss": 0.03386669233441353,
+      "eval_runtime": 90.2752,
+      "eval_samples_per_second": 11.077,
+      "eval_steps_per_second": 11.077,
+      "step": 800
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2646,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

2025-11-26-16-50-52/01_scene/trainer_state.json

@@ -0,0 +1,614 @@
+{
+  "best_metric": 0.03386669233441353,
+  "best_model_checkpoint": "outputs/2025-11-26-16-50-52/01_scene/checkpoint-800",
+  "epoch": 2.9974497024652877,
+  "eval_steps": 100,
+  "global_step": 2646,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05667327854916407,
+      "grad_norm": 4.339138507843018,
+      "learning_rate": 0.000125,
+      "loss": 0.3253,
+      "step": 50
+    },
+    {
+      "epoch": 0.11334655709832814,
+      "grad_norm": 3.550264835357666,
+      "learning_rate": 0.00019997002254654227,
+      "loss": 0.0543,
+      "step": 100
+    },
+    {
+      "epoch": 0.11334655709832814,
+      "eval_loss": 0.03937990590929985,
+      "eval_runtime": 90.138,
+      "eval_samples_per_second": 11.094,
+      "eval_steps_per_second": 11.094,
+      "step": 100
+    },
+    {
+      "epoch": 0.1700198356474922,
+      "grad_norm": 1.1671267747879028,
+      "learning_rate": 0.0001996329825692593,
+      "loss": 0.0431,
+      "step": 150
+    },
+    {
+      "epoch": 0.22669311419665628,
+      "grad_norm": 5.124600887298584,
+      "learning_rate": 0.00019892269762919834,
+      "loss": 0.0385,
+      "step": 200
+    },
+    {
+      "epoch": 0.22669311419665628,
+      "eval_loss": 0.039480071514844894,
+      "eval_runtime": 90.0332,
+      "eval_samples_per_second": 11.107,
+      "eval_steps_per_second": 11.107,
+      "step": 200
+    },
+    {
+      "epoch": 0.2833663927458204,
+      "grad_norm": 1.6820999383926392,
+      "learning_rate": 0.0001978418285949712,
+      "loss": 0.0438,
+      "step": 250
+    },
+    {
+      "epoch": 0.3400396712949844,
+      "grad_norm": 3.634084463119507,
+      "learning_rate": 0.0001963944246168898,
+      "loss": 0.0352,
+      "step": 300
+    },
+    {
+      "epoch": 0.3400396712949844,
+      "eval_loss": 0.05238571763038635,
+      "eval_runtime": 90.3736,
+      "eval_samples_per_second": 11.065,
+      "eval_steps_per_second": 11.065,
+      "step": 300
+    },
+    {
+      "epoch": 0.3967129498441485,
+      "grad_norm": 0.8966110348701477,
+      "learning_rate": 0.00019458590795804406,
+      "loss": 0.0319,
+      "step": 350
+    },
+    {
+      "epoch": 0.45338622839331255,
+      "grad_norm": 2.966634511947632,
+      "learning_rate": 0.00019242305368142622,
+      "loss": 0.0302,
+      "step": 400
+    },
+    {
+      "epoch": 0.45338622839331255,
+      "eval_loss": 0.034898512065410614,
+      "eval_runtime": 90.038,
+      "eval_samples_per_second": 11.106,
+      "eval_steps_per_second": 11.106,
+      "step": 400
+    },
+    {
+      "epoch": 0.5100595069424766,
+      "grad_norm": 3.242164373397827,
+      "learning_rate": 0.00018991396426919788,
+      "loss": 0.2013,
+      "step": 450
+    },
+    {
+      "epoch": 0.5667327854916407,
+      "grad_norm": 1.3575365543365479,
+      "learning_rate": 0.00018706803926918063,
+      "loss": 0.0265,
+      "step": 500
+    },
+    {
+      "epoch": 0.5667327854916407,
+      "eval_loss": 0.039046503603458405,
+      "eval_runtime": 90.0456,
+      "eval_samples_per_second": 11.105,
+      "eval_steps_per_second": 11.105,
+      "step": 500
+    },
+    {
+      "epoch": 0.6234060640408048,
+      "grad_norm": 0.3216783106327057,
+      "learning_rate": 0.00018389594008228123,
+      "loss": 0.0388,
+      "step": 550
+    },
+    {
+      "epoch": 0.6800793425899688,
+      "grad_norm": 0.2726989686489105,
+      "learning_rate": 0.00018040955002276377,
+      "loss": 0.0307,
+      "step": 600
+    },
+    {
+      "epoch": 0.6800793425899688,
+      "eval_loss": 0.0383339487016201,
+      "eval_runtime": 90.0647,
+      "eval_samples_per_second": 11.103,
+      "eval_steps_per_second": 11.103,
+      "step": 600
+    },
+    {
+      "epoch": 0.7367526211391329,
+      "grad_norm": 3.5234360694885254,
+      "learning_rate": 0.0001766219298009918,
+      "loss": 0.0261,
+      "step": 650
+    },
+    {
+      "epoch": 0.793425899688297,
+      "grad_norm": 0.45793426036834717,
+      "learning_rate": 0.00017254726859541043,
+      "loss": 0.022,
+      "step": 700
+    },
+    {
+      "epoch": 0.793425899688297,
+      "eval_loss": 0.03573239967226982,
+      "eval_runtime": 90.0501,
+      "eval_samples_per_second": 11.105,
+      "eval_steps_per_second": 11.105,
+      "step": 700
+    },
+    {
+      "epoch": 0.8500991782374611,
+      "grad_norm": 2.6463303565979004,
+      "learning_rate": 0.00016820083089706263,
+      "loss": 0.0254,
+      "step": 750
+    },
+    {
+      "epoch": 0.9067724567866251,
+      "grad_norm": 1.4524548053741455,
+      "learning_rate": 0.0001635988993257706,
+      "loss": 0.0188,
+      "step": 800
+    },
+    {
+      "epoch": 0.9067724567866251,
+      "eval_loss": 0.03386669233441353,
+      "eval_runtime": 90.2752,
+      "eval_samples_per_second": 11.077,
+      "eval_steps_per_second": 11.077,
+      "step": 800
+    },
+    {
+      "epoch": 0.9634457353357891,
+      "grad_norm": 1.8023526668548584,
+      "learning_rate": 0.0001587587136322047,
+      "loss": 0.0165,
+      "step": 850
+    },
+    {
+      "epoch": 1.0192689147067158,
+      "grad_norm": 2.767707586288452,
+      "learning_rate": 0.00015369840611434952,
+      "loss": 0.0167,
+      "step": 900
+    },
+    {
+      "epoch": 1.0192689147067158,
+      "eval_loss": 0.03767446056008339,
+      "eval_runtime": 90.0949,
+      "eval_samples_per_second": 11.099,
+      "eval_steps_per_second": 11.099,
+      "step": 900
+    },
+    {
+      "epoch": 1.07594219325588,
+      "grad_norm": 1.664818286895752,
+      "learning_rate": 0.0001484369336903102,
+      "loss": 0.0128,
+      "step": 950
+    },
+    {
+      "epoch": 1.1326154718050438,
+      "grad_norm": 1.7656521797180176,
+      "learning_rate": 0.00014299400688192834,
+      "loss": 0.0143,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1326154718050438,
+      "eval_loss": 0.03644219785928726,
+      "eval_runtime": 90.3385,
+      "eval_samples_per_second": 11.069,
+      "eval_steps_per_second": 11.069,
+      "step": 1000
+    },
+    {
+      "epoch": 1.189288750354208,
+      "grad_norm": 2.3746185302734375,
+      "learning_rate": 0.00013739001597524786,
+      "loss": 0.009,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2459620289033722,
+      "grad_norm": 0.08090117573738098,
+      "learning_rate": 0.00013164595463444938,
+      "loss": 0.0118,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2459620289033722,
+      "eval_loss": 0.04246201366186142,
+      "eval_runtime": 90.0776,
+      "eval_samples_per_second": 11.102,
+      "eval_steps_per_second": 11.102,
+      "step": 1100
+    },
+    {
+      "epoch": 1.302635307452536,
+      "grad_norm": 0.5375736355781555,
+      "learning_rate": 0.00012578334125540997,
+      "loss": 0.0072,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3593085860017002,
+      "grad_norm": 0.021600479260087013,
+      "learning_rate": 0.00011982413835351374,
+      "loss": 0.0085,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3593085860017002,
+      "eval_loss": 0.04923948645591736,
+      "eval_runtime": 90.089,
+      "eval_samples_per_second": 11.1,
+      "eval_steps_per_second": 11.1,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4159818645508642,
+      "grad_norm": 0.4288318157196045,
+      "learning_rate": 0.00011379067028770236,
+      "loss": 0.0078,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4726551431000283,
+      "grad_norm": 0.5142509937286377,
+      "learning_rate": 0.00010770553962898767,
+      "loss": 0.0076,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4726551431000283,
+      "eval_loss": 0.04984404519200325,
+      "eval_runtime": 90.3286,
+      "eval_samples_per_second": 11.071,
+      "eval_steps_per_second": 11.071,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5293284216491925,
+      "grad_norm": 0.4817846417427063,
+      "learning_rate": 0.00010159154248672667,
+      "loss": 0.0056,
+      "step": 1350
+    },
+    {
+      "epoch": 1.5860017001983566,
+      "grad_norm": 3.8564178943634033,
+      "learning_rate": 9.547158310986322e-05,
+      "loss": 0.0084,
+      "step": 1400
+    },
+    {
+      "epoch": 1.5860017001983566,
+      "eval_loss": 0.04620128124952316,
+      "eval_runtime": 90.0981,
+      "eval_samples_per_second": 11.099,
+      "eval_steps_per_second": 11.099,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6426749787475206,
+      "grad_norm": 0.38633376359939575,
+      "learning_rate": 8.936858808305755e-05,
+      "loss": 0.0044,
+      "step": 1450
+    },
+    {
+      "epoch": 1.6993482572966845,
+      "grad_norm": 0.0634835809469223,
+      "learning_rate": 8.330542043914149e-05,
+      "loss": 0.0049,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6993482572966845,
+      "eval_loss": 0.058556605130434036,
+      "eval_runtime": 90.1882,
+      "eval_samples_per_second": 11.088,
+      "eval_steps_per_second": 11.088,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7560215358458486,
+      "grad_norm": 0.17512574791908264,
+      "learning_rate": 7.730479400965156e-05,
+      "loss": 0.007,
+      "step": 1550
+    },
+    {
+      "epoch": 1.8126948143950128,
+      "grad_norm": 0.7759736776351929,
+      "learning_rate": 7.138918833430014e-05,
+      "loss": 0.0057,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8126948143950128,
+      "eval_loss": 0.05251866579055786,
+      "eval_runtime": 90.2837,
+      "eval_samples_per_second": 11.076,
+      "eval_steps_per_second": 11.076,
+      "step": 1600
+    },
+    {
+      "epoch": 1.869368092944177,
+      "grad_norm": 2.2165539264678955,
+      "learning_rate": 6.55807644481498e-05,
+      "loss": 0.0074,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9260413714933409,
+      "grad_norm": 0.005767249036580324,
+      "learning_rate": 5.990128186196971e-05,
+      "loss": 0.0034,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9260413714933409,
+      "eval_loss": 0.05016641691327095,
+      "eval_runtime": 90.0478,
+      "eval_samples_per_second": 11.105,
+      "eval_steps_per_second": 11.105,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9827146500425048,
+      "grad_norm": 0.031133009120821953,
+      "learning_rate": 5.437201704678196e-05,
+      "loss": 0.0031,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0385378294134315,
+      "grad_norm": 0.014959041960537434,
+      "learning_rate": 4.901368372797065e-05,
+      "loss": 0.0037,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0385378294134315,
+      "eval_loss": 0.05385539308190346,
+      "eval_runtime": 90.2625,
+      "eval_samples_per_second": 11.079,
+      "eval_steps_per_second": 11.079,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0952111079625957,
+      "grad_norm": 1.9791584014892578,
+      "learning_rate": 4.3846355287547944e-05,
+      "loss": 0.0024,
+      "step": 1850
+    },
+    {
+      "epoch": 2.15188438651176,
+      "grad_norm": 2.0488200187683105,
+      "learning_rate": 3.8889389565274035e-05,
+      "loss": 0.0025,
+      "step": 1900
+    },
+    {
+      "epoch": 2.15188438651176,
+      "eval_loss": 0.059098273515701294,
+      "eval_runtime": 90.2105,
+      "eval_samples_per_second": 11.085,
+      "eval_steps_per_second": 11.085,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2085576650609235,
+      "grad_norm": 0.021802732720971107,
+      "learning_rate": 3.416135634034054e-05,
+      "loss": 0.0031,
+      "step": 1950
+    },
+    {
+      "epoch": 2.2652309436100877,
+      "grad_norm": 0.00933904480189085,
+      "learning_rate": 2.9679967765285032e-05,
+      "loss": 0.0017,
+      "step": 2000
+    },
+    {
+      "epoch": 2.2652309436100877,
+      "eval_loss": 0.06034567207098007,
+      "eval_runtime": 90.0945,
+      "eval_samples_per_second": 11.099,
+      "eval_steps_per_second": 11.099,
+      "step": 2000
+    },
+    {
+      "epoch": 2.321904222159252,
+      "grad_norm": 0.00511200213804841,
+      "learning_rate": 2.5462012012746407e-05,
+      "loss": 0.002,
+      "step": 2050
+    },
+    {
+      "epoch": 2.378577500708416,
+      "grad_norm": 0.002153645269572735,
+      "learning_rate": 2.1523290383631732e-05,
+      "loss": 0.0031,
+      "step": 2100
+    },
+    {
+      "epoch": 2.378577500708416,
+      "eval_loss": 0.06627824157476425,
+      "eval_runtime": 90.4408,
+      "eval_samples_per_second": 11.057,
+      "eval_steps_per_second": 11.057,
+      "step": 2100
+    },
+    {
+      "epoch": 2.43525077925758,
+      "grad_norm": 0.04121919348835945,
+      "learning_rate": 1.7878558112301648e-05,
+      "loss": 0.0009,
+      "step": 2150
+    },
+    {
+      "epoch": 2.4919240578067443,
+      "grad_norm": 0.04373983293771744,
+      "learning_rate": 1.4541469090528393e-05,
+      "loss": 0.001,
+      "step": 2200
+    },
+    {
+      "epoch": 2.4919240578067443,
+      "eval_loss": 0.06941419839859009,
+      "eval_runtime": 90.2245,
+      "eval_samples_per_second": 11.083,
+      "eval_steps_per_second": 11.083,
+      "step": 2200
+    },
+    {
+      "epoch": 2.5485973363559085,
+      "grad_norm": 7.789440631866455,
+      "learning_rate": 1.1524524717302532e-05,
+      "loss": 0.001,
+      "step": 2250
+    },
+    {
+      "epoch": 2.605270614905072,
+      "grad_norm": 0.01206847745925188,
+      "learning_rate": 8.839027066106675e-06,
+      "loss": 0.0004,
+      "step": 2300
+    },
+    {
+      "epoch": 2.605270614905072,
+      "eval_loss": 0.06566739082336426,
+      "eval_runtime": 90.2027,
+      "eval_samples_per_second": 11.086,
+      "eval_steps_per_second": 11.086,
+      "step": 2300
+    },
+    {
+      "epoch": 2.6619438934542363,
+      "grad_norm": 0.017873864620923996,
+      "learning_rate": 6.4950365451009295e-06,
+      "loss": 0.0024,
+      "step": 2350
+    },
+    {
+      "epoch": 2.7186171720034005,
+      "grad_norm": 8.548991203308105,
+      "learning_rate": 4.501334208833807e-06,
+      "loss": 0.0031,
+      "step": 2400
+    },
+    {
+      "epoch": 2.7186171720034005,
+      "eval_loss": 0.07288677245378494,
+      "eval_runtime": 90.4099,
+      "eval_samples_per_second": 11.061,
+      "eval_steps_per_second": 11.061,
+      "step": 2400
+    },
+    {
+      "epoch": 2.7752904505525646,
+      "grad_norm": 0.008294968865811825,
+      "learning_rate": 2.8653888626656855e-06,
+      "loss": 0.0034,
+      "step": 2450
+    },
+    {
+      "epoch": 2.8319637291017283,
+      "grad_norm": 0.8166434168815613,
+      "learning_rate": 1.5933290831391612e-06,
+      "loss": 0.0022,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8319637291017283,
+      "eval_loss": 0.06702987104654312,
+      "eval_runtime": 90.0868,
+      "eval_samples_per_second": 11.1,
+      "eval_steps_per_second": 11.1,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8886370076508925,
+      "grad_norm": 0.009677646681666374,
+      "learning_rate": 6.899202591125642e-07,
+      "loss": 0.0029,
+      "step": 2550
+    },
+    {
+      "epoch": 2.9453102862000566,
+      "grad_norm": 0.050994016230106354,
+      "learning_rate": 1.5854673966592127e-07,
+      "loss": 0.0016,
+      "step": 2600
+    },
+    {
+      "epoch": 2.9453102862000566,
+      "eval_loss": 0.06189265847206116,
+      "eval_runtime": 90.2429,
+      "eval_samples_per_second": 11.081,
+      "eval_steps_per_second": 11.081,
+      "step": 2600
+    },
+    {
+      "epoch": 2.9974497024652877,
+      "step": 2646,
+      "total_flos": 0.0,
+      "train_loss": 0.022518052387270213,
+      "train_runtime": 6849.0772,
+      "train_samples_per_second": 3.092,
+      "train_steps_per_second": 0.386
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2646,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

2025-11-26-16-50-52/01_scene/training_arguments.json

@@ -0,0 +1,145 @@
+{
+  "output_dir": "outputs/2025-11-26-16-50-52/01_scene",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": true,
+  "do_predict": false,
+  "eval_strategy": "steps",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 1,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 8,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 0.0002,
+  "weight_decay": 0.0,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 3,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": {},
+  "warmup_ratio": 0.03,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "outputs/2025-11-26-16-50-52/01_scene/runs/Nov26_16-50-56_fbi-mass-surveillance-network",
+  "logging_strategy": "steps",
+  "logging_first_step": false,
+  "logging_steps": 50,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "best",
+  "save_steps": 100,
+  "save_total_limit": 5,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "restore_callback_states_from_checkpoint": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": null,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": [],
+  "dataloader_drop_last": false,
+  "eval_steps": 100,
+  "dataloader_num_workers": 12,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "outputs/2025-11-26-16-50-52/01_scene",
+  "disable_tqdm": false,
+  "remove_unused_columns": false,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "eval_loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": [],
+  "fsdp_min_num_params": 0,
+  "fsdp_config": {
+    "min_num_params": 0,
+    "xla": false,
+    "xla_fsdp_v2": false,
+    "xla_fsdp_grad_ckpt": false
+  },
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "split_batches": false,
+    "dispatch_batches": null,
+    "even_batches": true,
+    "use_seedable_sampler": true,
+    "non_blocking": false,
+    "gradient_accumulation_kwargs": null
+  },
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [],
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": false,
+  "resume_from_checkpoint": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_token": "<HUB_TOKEN>",
+  "hub_private_repo": null,
+  "hub_always_push": false,
+  "gradient_checkpointing": false,
+  "gradient_checkpointing_kwargs": null,
+  "include_inputs_for_metrics": false,
+  "include_for_metrics": [],
+  "eval_do_concat_batches": true,
+  "fp16_backend": "auto",
+  "evaluation_strategy": null,
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 1800,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "dispatch_batches": null,
+  "split_batches": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null,
+  "optim_target_modules": null,
+  "batch_eval_metrics": false,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": false
+}

2025-11-26-16-50-52/02_distortion/checkpoint-100/README.md

@@ -0,0 +1,207 @@
+---
+base_model: src/owl3
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:src/owl3
+- lora
+- transformers
+---
+
+# 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 0.17.1

2025-11-26-16-50-52/02_distortion/checkpoint-100/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "src/owl3",
+  "bias": "none",
+  "corda_config": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

2025-11-26-16-50-52/02_distortion/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb1386821747de6d1a5b0ba73dbf4d24188c9f3e9b27b573f4002e94649a9dde
+size 173507576

2025-11-26-16-50-52/02_distortion/checkpoint-100/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

2025-11-26-16-50-52/02_distortion/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8346e7a936237a4735b950a17fe81223785ebef1b9b837352f0ab78466d619cd
+size 346426383

2025-11-26-16-50-52/02_distortion/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c45eee438afc8a5dc3aa37e234d797ee8f451c3558934c36fd101e2e774bb4f3
+size 14645

2025-11-26-16-50-52/02_distortion/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441ef59f1d5d6d1eba1fd1f9f4c9a8660f66e566f1b8b3b88c35a5dad7fb26b6
+size 1465