Upload checkpoint 10

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,202 @@
+---
+base_model: ./UIGEN-7B-Instruct/
+library_name: peft
+---
+
+# 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 0.14.0

README.md

@@ -0,0 +1,202 @@
+---
+base_model: smirki/UIGEN-T1.1-Qwen-7B
+library_name: peft
+---
+
+# 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 0.14.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./UIGEN-7B-Instruct/",
+  "bias": "none",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2488ac58fabaa8982a33883a7bc2f0427170d1804ead6a9942b2ba64eea7dd44
+size 645975704

added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daa7220638cdeec5aec0a5f2dfa63bfa6d43b16e730ff8226a77e21bad005682
+size 328476596

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2be6092f8bdd5f11bceb64a6dc6159bc51d45bf4743c5b84781ecfa1cb5975
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e7c1450531a830fa34f988021335e0c4c746e4893e21a244c7912fcb343396
+size 1064

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11add1ccce473bcd467355ba4e231ba727eee54501528658b0d6fa18112957e
+size 11422253

tokenizer_config.json

@@ -0,0 +1,217 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,333 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0517464424320828,
+  "eval_steps": 500,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 3375.541748046875,
+      "epoch": 0.00517464424320828,
+      "grad_norm": 0.12644390761852264,
+      "kl": 0.0,
+      "learning_rate": 4.166666666666667e-08,
+      "loss": 0.0,
+      "reward": 0.40281581226736307,
+      "reward_std": 0.878997789695859,
+      "rewards/accessibility_reward_func": 0.026833334006369114,
+      "rewards/animation_reward_func": 0.02666666731238365,
+      "rewards/color_theory_reward_func": 0.03033333271741867,
+      "rewards/design_system_reward_func": 0.0833333358168602,
+      "rewards/element_spacing_reward_func": 0.0143382353708148,
+      "rewards/enhanced_html_validity_reward_func": 0.035500000230968,
+      "rewards/framer_aesthetic_bonus_reward_func": 0.07500000298023224,
+      "rewards/general_responsiveness_reward_func": 0.004000000189989805,
+      "rewards/hover_reward_func": 0.015000000596046448,
+      "rewards/image_size_reward_func": 0.005375000182539225,
+      "rewards/interactivity_reward_func": 0.05000000447034836,
+      "rewards/link_validity_reward_func": 0.0036250001285225153,
+      "rewards/lorem_picsum_reward_func": 0.00037500001781154424,
+      "rewards/mobile_responsiveness_reward_func": 0.0,
+      "rewards/section_size_reward_func": 0.0,
+      "rewards/tailwind_cdn_reward_func": 0.005833333358168602,
+      "rewards/text_contrast_reward_func": 0.0016666667070239782,
+      "rewards/think_tag_reward_func": 0.02000000001862645,
+      "rewards/visual_hierarchy_reward_func": 0.004935897421091795,
+      "step": 1
+    },
+    {
+      "completion_length": 3269.5834350585938,
+      "epoch": 0.01034928848641656,
+      "grad_norm": 1.7859678268432617,
+      "kl": 0.0,
+      "learning_rate": 8.333333333333334e-08,
+      "loss": 0.0,
+      "reward": 0.5783839523792267,
+      "reward_std": 1.3122798325493932,
+      "rewards/accessibility_reward_func": 0.042583334259688854,
+      "rewards/animation_reward_func": 0.04000000096857548,
+      "rewards/color_theory_reward_func": 0.045499999076128006,
+      "rewards/design_system_reward_func": 0.1250000037252903,
+      "rewards/element_spacing_reward_func": 0.020208333618938923,
+      "rewards/enhanced_html_validity_reward_func": 0.03808333398774266,
+      "rewards/framer_aesthetic_bonus_reward_func": 0.11250000447034836,
+      "rewards/general_responsiveness_reward_func": 0.006000000284984708,
+      "rewards/hover_reward_func": 0.02250000089406967,
+      "rewards/image_size_reward_func": 0.00900000031106174,
+      "rewards/interactivity_reward_func": 0.07500000670552254,
+      "rewards/link_validity_reward_func": 0.00450000015553087,
+      "rewards/lorem_picsum_reward_func": 0.000541666682693176,
+      "rewards/mobile_responsiveness_reward_func": 0.0,
+      "rewards/section_size_reward_func": 0.0,
+      "rewards/tailwind_cdn_reward_func": 0.008750000037252903,
+      "rewards/text_contrast_reward_func": 0.0025000000605359674,
+      "rewards/think_tag_reward_func": 0.018333332845941186,
+      "rewards/visual_hierarchy_reward_func": 0.007383928867056966,
+      "step": 2
+    },
+    {
+      "completion_length": 3709.5001220703125,
+      "epoch": 0.015523932729624839,
+      "grad_norm": 0.14484886825084686,
+      "kl": 0.000433405366493389,
+      "learning_rate": 1.2500000000000002e-07,
+      "loss": 0.0,
+      "reward": 0.578418267890811,
+      "reward_std": 0.9803256597369909,
+      "rewards/accessibility_reward_func": 0.03500000201165676,
+      "rewards/animation_reward_func": 0.04000000096857548,
+      "rewards/color_theory_reward_func": 0.043166667222976685,
+      "rewards/design_system_reward_func": 0.1250000037252903,
+      "rewards/element_spacing_reward_func": 0.021875000093132257,
+      "rewards/enhanced_html_validity_reward_func": 0.038083333522081375,
+      "rewards/framer_aesthetic_bonus_reward_func": 0.10750000178813934,
+      "rewards/general_responsiveness_reward_func": 0.007750000339001417,
+      "rewards/hover_reward_func": 0.02250000089406967,
+      "rewards/image_size_reward_func": 0.009750000201165676,
+      "rewards/interactivity_reward_func": 0.07500000670552254,
+      "rewards/link_validity_reward_func": 0.0048749998095445335,
+      "rewards/lorem_picsum_reward_func": 0.0006250000151339918,
+      "rewards/mobile_responsiveness_reward_func": 0.0006666667177341878,
+      "rewards/section_size_reward_func": 0.0,
+      "rewards/tailwind_cdn_reward_func": 0.008750000037252903,
+      "rewards/text_contrast_reward_func": 0.0033333332976326346,
+      "rewards/think_tag_reward_func": 0.026666666846722364,
+      "rewards/visual_hierarchy_reward_func": 0.007876602932810783,
+      "step": 3
+    },
+    {
+      "completion_length": 3860.7500610351562,
+      "epoch": 0.02069857697283312,
+      "grad_norm": 0.12912344932556152,
+      "kl": 0.00043934735731454566,
+      "learning_rate": 1.6666666666666668e-07,
+      "loss": 0.0,
+      "reward": 0.7566360970959067,
+      "reward_std": 1.4153302712365985,
+      "rewards/accessibility_reward_func": 0.04900000151246786,
+      "rewards/animation_reward_func": 0.05533333495259285,
+      "rewards/color_theory_reward_func": 0.05833333358168602,
+      "rewards/design_system_reward_func": 0.1666666716337204,
+      "rewards/element_spacing_reward_func": 0.02916666679084301,
+      "rewards/enhanced_html_validity_reward_func": 0.0408333339728415,
+      "rewards/framer_aesthetic_bonus_reward_func": 0.14750000834465027,
+      "rewards/general_responsiveness_reward_func": 0.009000000078231096,
+      "rewards/hover_reward_func": 0.030000001192092896,
+      "rewards/image_size_reward_func": 0.012375000398606062,
+      "rewards/interactivity_reward_func": 0.10000000894069672,
+      "rewards/link_validity_reward_func": 0.007250000257045031,
+      "rewards/lorem_picsum_reward_func": 0.0007916666945675388,
+      "rewards/mobile_responsiveness_reward_func": 0.0,
+      "rewards/section_size_reward_func": 0.0,
+      "rewards/tailwind_cdn_reward_func": 0.011666666716337204,
+      "rewards/text_contrast_reward_func": 0.005000000004656613,
+      "rewards/think_tag_reward_func": 0.02333333296701312,
+      "rewards/visual_hierarchy_reward_func": 0.010386029724031687,
+      "step": 4
+    },
+    {
+      "completion_length": 4449.666748046875,
+      "epoch": 0.0258732212160414,
+      "grad_norm": 0.10886913537979126,
+      "kl": 0.00040846195770427585,
+      "learning_rate": 2.0833333333333333e-07,
+      "loss": 0.0,
+      "reward": 0.9373456230387092,
+      "reward_std": 1.5362365646287799,
+      "rewards/accessibility_reward_func": 0.07000000216066837,
+      "rewards/animation_reward_func": 0.07266666740179062,
+      "rewards/color_theory_reward_func": 0.07466666586697102,
+      "rewards/design_system_reward_func": 0.2083333395421505,
+      "rewards/element_spacing_reward_func": 0.034319296944886446,
+      "rewards/enhanced_html_validity_reward_func": 0.04241666803136468,
+      "rewards/framer_aesthetic_bonus_reward_func": 0.17500000819563866,
+      "rewards/general_responsiveness_reward_func": 0.013000000035390258,
+      "rewards/hover_reward_func": 0.03750000149011612,
+      "rewards/image_size_reward_func": 0.013624999905005097,
+      "rewards/interactivity_reward_func": 0.1250000111758709,
+      "rewards/link_validity_reward_func": 0.010250000865198672,
+      "rewards/lorem_picsum_reward_func": 0.0009583333740010858,
+      "rewards/mobile_responsiveness_reward_func": 0.0006666667177341878,
+      "rewards/section_size_reward_func": 0.0,
+      "rewards/tailwind_cdn_reward_func": 0.014583333395421505,
+      "rewards/text_contrast_reward_func": 0.00750000006519258,
+      "rewards/think_tag_reward_func": 0.02500000037252903,
+      "rewards/visual_hierarchy_reward_func": 0.011859558057039976,
+      "step": 5
+    },
+    {
+      "completion_length": 3829.541748046875,
+      "epoch": 0.031047865459249677,
+      "grad_norm": 0.11395324766635895,
+      "kl": 0.0004633670541807078,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 0.0,
+      "reward": 1.103904644958675,
+      "reward_std": 1.5650687320157886,
+      "rewards/accessibility_reward_func": 0.07816666923463345,
+      "rewards/animation_reward_func": 0.09400000236928463,
+      "rewards/color_theory_reward_func": 0.0845833346247673,
+      "rewards/design_system_reward_func": 0.2500000037252903,
+      "rewards/element_spacing_reward_func": 0.04301470750942826,
+      "rewards/enhanced_html_validity_reward_func": 0.04433333361521363,
+      "rewards/framer_aesthetic_bonus_reward_func": 0.21249999850988388,
+      "rewards/general_responsiveness_reward_func": 0.011999999871477485,
+      "rewards/hover_reward_func": 0.04500000178813934,
+      "rewards/image_size_reward_func": 0.01624999986961484,
+      "rewards/interactivity_reward_func": 0.15000000968575478,
+      "rewards/link_validity_reward_func": 0.011875000083819032,
+      "rewards/lorem_picsum_reward_func": 0.0011666666541714221,
+      "rewards/mobile_responsiveness_reward_func": 0.0,
+      "rewards/section_size_reward_func": 0.0,
+      "rewards/tailwind_cdn_reward_func": 0.01750000100582838,
+      "rewards/text_contrast_reward_func": 0.00583333324175328,
+      "rewards/think_tag_reward_func": 0.023333333898335695,
+      "rewards/visual_hierarchy_reward_func": 0.014348214725032449,
+      "step": 6
+    },
+    {
+      "completion_length": 4055.83349609375,
+      "epoch": 0.03622250970245795,
+      "grad_norm": 0.10929117351770401,
+      "kl": 0.000453724896942731,
+      "learning_rate": 2.916666666666667e-07,
+      "loss": 0.0,
+      "reward": 1.4172477573156357,
+      "reward_std": 1.936814159154892,
+      "rewards/accessibility_reward_func": 0.09975000470876694,
+      "rewards/animation_reward_func": 0.09400000050663948,
+      "rewards/color_theory_reward_func": 0.11900000460445881,
+      "rewards/design_system_reward_func": 0.3333333358168602,
+      "rewards/element_spacing_reward_func": 0.051814084872603416,
+      "rewards/enhanced_html_validity_reward_func": 0.050583334639668465,
+      "rewards/framer_aesthetic_bonus_reward_func": 0.2874999977648258,
+      "rewards/general_responsiveness_reward_func": 0.018000000389292836,
+      "rewards/hover_reward_func": 0.06000000238418579,
+      "rewards/image_size_reward_func": 0.013999999733641744,
+      "rewards/interactivity_reward_func": 0.20000001043081284,
+      "rewards/link_validity_reward_func": 0.013375000678934157,
+      "rewards/lorem_picsum_reward_func": 0.0014999999839346856,
+      "rewards/mobile_responsiveness_reward_func": 0.0,
+      "rewards/section_size_reward_func": 0.0,
+      "rewards/tailwind_cdn_reward_func": 0.023333335295319557,
+      "rewards/text_contrast_reward_func": 0.008333333069458604,
+      "rewards/think_tag_reward_func": 0.02499999920837581,
+      "rewards/visual_hierarchy_reward_func": 0.017725358135066926,
+      "step": 7
+    },
+    {
+      "completion_length": 4102.666748046875,
+      "epoch": 0.04139715394566624,
+      "grad_norm": 0.1363147795200348,
+      "kl": 0.0003966327421949245,
+      "learning_rate": 3.3333333333333335e-07,
+      "loss": 0.0,
+      "reward": 0.7400073558092117,
+      "reward_std": 1.3520178319886327,
+      "rewards/accessibility_reward_func": 0.0624166673514992,
+      "rewards/animation_reward_func": 0.0560000017285347,
+      "rewards/color_theory_reward_func": 0.05833333358168602,
+      "rewards/design_system_reward_func": 0.1666666716337204,
+      "rewards/element_spacing_reward_func": 0.02857142873108387,
+      "rewards/enhanced_html_validity_reward_func": 0.03866666695103049,
+      "rewards/framer_aesthetic_bonus_reward_func": 0.1275000013411045,
+      "rewards/general_responsiveness_reward_func": 0.010000000009313226,
+      "rewards/hover_reward_func": 0.030000001192092896,
+      "rewards/image_size_reward_func": 0.007625000027474016,
+      "rewards/interactivity_reward_func": 0.10000000894069672,
+      "rewards/link_validity_reward_func": 0.004250000114552677,
+      "rewards/lorem_picsum_reward_func": 0.0006666666849923786,
+      "rewards/mobile_responsiveness_reward_func": 0.0006666667177341878,
+      "rewards/section_size_reward_func": 0.0,
+      "rewards/tailwind_cdn_reward_func": 0.008750000037252903,
+      "rewards/text_contrast_reward_func": 0.005000000121071935,
+      "rewards/think_tag_reward_func": 0.024999999906867743,
+      "rewards/visual_hierarchy_reward_func": 0.009894231334328651,
+      "step": 8
+    },
+    {
+      "completion_length": 3891.3334350585938,
+      "epoch": 0.04657179818887452,
+      "grad_norm": 1.1345418691635132,
+      "kl": 0.003981367131927982,
+      "learning_rate": 3.75e-07,
+      "loss": 0.0002,
+      "reward": 0.866581498645246,
+      "reward_std": 1.4129546987824142,
+      "rewards/accessibility_reward_func": 0.057750002946704626,
+      "rewards/animation_reward_func": 0.06666666828095913,
+      "rewards/color_theory_reward_func": 0.055416667833924294,
+      "rewards/design_system_reward_func": 0.2083333395421505,
+      "rewards/element_spacing_reward_func": 0.03586309542879462,
+      "rewards/enhanced_html_validity_reward_func": 0.04041666863486171,
+      "rewards/framer_aesthetic_bonus_reward_func": 0.1612500064074993,
+      "rewards/general_responsiveness_reward_func": 0.010000000474974513,
+      "rewards/hover_reward_func": 0.03750000149011612,
+      "rewards/image_size_reward_func": 0.009125000215135515,
+      "rewards/interactivity_reward_func": 0.1250000111758709,
+      "rewards/link_validity_reward_func": 0.006875000195577741,
+      "rewards/lorem_picsum_reward_func": 0.000666666695906315,
+      "rewards/mobile_responsiveness_reward_func": 0.0,
+      "rewards/section_size_reward_func": 0.0,
+      "rewards/tailwind_cdn_reward_func": 0.011666666716337204,
+      "rewards/text_contrast_reward_func": 0.004166666651144624,
+      "rewards/think_tag_reward_func": 0.021666667191311717,
+      "rewards/visual_hierarchy_reward_func": 0.014218345284461975,
+      "step": 9
+    },
+    {
+      "completion_length": 4518.2918701171875,
+      "epoch": 0.0517464424320828,
+      "grad_norm": 0.13834819197654724,
+      "kl": 0.0004231790080666542,
+      "learning_rate": 4.1666666666666667e-07,
+      "loss": 0.0,
+      "reward": 0.4099843604490161,
+      "reward_std": 0.8722708746790886,
+      "rewards/accessibility_reward_func": 0.04491666704416275,
+      "rewards/animation_reward_func": 0.016666667070239782,
+      "rewards/color_theory_reward_func": 0.027416666969656944,
+      "rewards/design_system_reward_func": 0.0833333358168602,
+      "rewards/element_spacing_reward_func": 0.011679293122142553,
+      "rewards/enhanced_html_validity_reward_func": 0.03500000014901161,
+      "rewards/framer_aesthetic_bonus_reward_func": 0.06750000268220901,
+      "rewards/general_responsiveness_reward_func": 0.006000000052154064,
+      "rewards/hover_reward_func": 0.015000000596046448,
+      "rewards/image_size_reward_func": 0.005875000264495611,
+      "rewards/interactivity_reward_func": 0.05000000447034836,
+      "rewards/link_validity_reward_func": 0.004999999888241291,
+      "rewards/lorem_picsum_reward_func": 0.00041666667675599456,
+      "rewards/mobile_responsiveness_reward_func": 0.0,
+      "rewards/section_size_reward_func": 0.001500000013038516,
+      "rewards/tailwind_cdn_reward_func": 0.005833333358168602,
+      "rewards/text_contrast_reward_func": 0.0024999999441206455,
+      "rewards/think_tag_reward_func": 0.02833333285525441,
+      "rewards/visual_hierarchy_reward_func": 0.00301339291036129,
+      "step": 10
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 10,
+  "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": 6,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17076a25afee4f8ac67e7c762d9e3723db466b1ba66737c2c8fdc3a6c26b7609
+size 5816