Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Training_Result/regular/checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+RuleMaze/quest/checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+RuleMaze/regular/checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text

RuleMaze/quest/checkpoint/README.md

@@ -0,0 +1,208 @@
+---
+base_model: /network_space/server127_2/shared/chenyu/model/Qwen/Qwen2.5-VL-3B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/network_space/server127_2/shared/chenyu/model/Qwen/Qwen2.5-VL-3B-Instruct
+- llama-factory
+- 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 0.18.1

RuleMaze/quest/checkpoint/adapter_config.json

@@ -0,0 +1,151 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/network_space/server127_2/shared/chenyu/model/Qwen/Qwen2.5-VL-3B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "layers.22.mlp.gate_proj",
+    "layers.28.mlp.gate_proj",
+    "layers.16.mlp.down_proj",
+    "layers.12.mlp.down_proj",
+    "layers.31.mlp.up_proj",
+    "layers.12.mlp.up_proj",
+    "layers.20.mlp.gate_proj",
+    "layers.4.mlp.up_proj",
+    "layers.11.mlp.up_proj",
+    "layers.0.mlp.down_proj",
+    "layers.17.mlp.down_proj",
+    "layers.29.mlp.down_proj",
+    "layers.19.mlp.down_proj",
+    "layers.4.mlp.gate_proj",
+    "layers.26.mlp.up_proj",
+    "layers.22.mlp.up_proj",
+    "layers.0.mlp.gate_proj",
+    "layers.24.mlp.down_proj",
+    "layers.23.mlp.down_proj",
+    "layers.25.mlp.up_proj",
+    "35.mlp.gate_proj",
+    "layers.21.mlp.gate_proj",
+    "layers.6.mlp.up_proj",
+    "layers.10.mlp.gate_proj",
+    "layers.18.mlp.up_proj",
+    "35.mlp.up_proj",
+    "layers.21.mlp.up_proj",
+    "layers.13.mlp.gate_proj",
+    "layers.10.mlp.up_proj",
+    "layers.20.mlp.down_proj",
+    "layers.31.mlp.gate_proj",
+    "layers.22.mlp.down_proj",
+    "layers.30.mlp.up_proj",
+    "layers.4.mlp.down_proj",
+    "layers.19.mlp.up_proj",
+    "layers.2.mlp.up_proj",
+    "layers.9.mlp.gate_proj",
+    "v_proj",
+    "layers.8.mlp.up_proj",
+    "layers.6.mlp.down_proj",
+    "o_proj",
+    "layers.3.mlp.up_proj",
+    "layers.7.mlp.gate_proj",
+    "layers.5.mlp.gate_proj",
+    "layers.13.mlp.down_proj",
+    "layers.10.mlp.down_proj",
+    "layers.27.mlp.gate_proj",
+    "33.mlp.gate_proj",
+    "layers.9.mlp.down_proj",
+    "layers.20.mlp.up_proj",
+    "layers.21.mlp.down_proj",
+    "layers.1.mlp.up_proj",
+    "34.mlp.down_proj",
+    "33.mlp.up_proj",
+    "layers.28.mlp.up_proj",
+    "layers.26.mlp.down_proj",
+    "q_proj",
+    "layers.31.mlp.down_proj",
+    "layers.30.mlp.gate_proj",
+    "32.mlp.up_proj",
+    "layers.3.mlp.down_proj",
+    "layers.8.mlp.down_proj",
+    "layers.16.mlp.gate_proj",
+    "35.mlp.down_proj",
+    "34.mlp.up_proj",
+    "layers.14.mlp.up_proj",
+    "layers.19.mlp.gate_proj",
+    "layers.14.mlp.down_proj",
+    "33.mlp.down_proj",
+    "layers.30.mlp.down_proj",
+    "layers.18.mlp.down_proj",
+    "layers.25.mlp.down_proj",
+    "layers.27.mlp.down_proj",
+    "layers.17.mlp.up_proj",
+    "layers.14.mlp.gate_proj",
+    "layers.27.mlp.up_proj",
+    "layers.1.mlp.down_proj",
+    "layers.12.mlp.gate_proj",
+    "layers.1.mlp.gate_proj",
+    "layers.8.mlp.gate_proj",
+    "layers.15.mlp.up_proj",
+    "layers.3.mlp.gate_proj",
+    "layers.24.mlp.gate_proj",
+    "layers.29.mlp.up_proj",
+    "layers.11.mlp.down_proj",
+    "layers.23.mlp.gate_proj",
+    "layers.7.mlp.down_proj",
+    "layers.13.mlp.up_proj",
+    "layers.7.mlp.up_proj",
+    "layers.26.mlp.gate_proj",
+    "layers.17.mlp.gate_proj",
+    "layers.24.mlp.up_proj",
+    "layers.23.mlp.up_proj",
+    "layers.5.mlp.down_proj",
+    "layers.6.mlp.gate_proj",
+    "layers.5.mlp.up_proj",
+    "layers.2.mlp.down_proj",
+    "layers.15.mlp.gate_proj",
+    "layers.9.mlp.up_proj",
+    "layers.2.mlp.gate_proj",
+    "32.mlp.down_proj",
+    "layers.25.mlp.gate_proj",
+    "32.mlp.gate_proj",
+    "layers.18.mlp.gate_proj",
+    "layers.28.mlp.down_proj",
+    "layers.0.mlp.up_proj",
+    "layers.16.mlp.up_proj",
+    "layers.15.mlp.down_proj",
+    "layers.29.mlp.gate_proj",
+    "34.mlp.gate_proj",
+    "k_proj",
+    "layers.11.mlp.gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

RuleMaze/quest/checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2be344fb886b0c36f686530a35318bc8ab25b25ec13b895629b9e5277b41bb1
+size 59941192

RuleMaze/quest/checkpoint/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

RuleMaze/quest/checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8cc0c75d723b02e04bbc95059ff6b2dcabb0c1733d31eaefd006de385030546
+size 120158586

RuleMaze/quest/checkpoint/processor_config.json

@@ -0,0 +1,59 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen2_5_VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen2VLVideoProcessor"
+  }
+}

RuleMaze/quest/checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca6265e8e2262bb5c15a70d21454a6b211b9b2d32d9dc8148906e78ea170eaf
+size 15024

RuleMaze/quest/checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d7aae23c0ad281a5723c42d3d0c2b4dad0be21eba7d073650ee2fc41e43602
+size 15024

RuleMaze/quest/checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:465be5b0a5af7606f9f257a8f2d7c4169c76acb06f8360d1e9ee648b1a569c0e
+size 15024

RuleMaze/quest/checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d0ec1844e355f804002cdc7088f40050d1244340689686f1b8dadac9301738f
+size 15024

RuleMaze/quest/checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e8dcba69a61d43e4b38d0cbe20f5e18c589211ffb15a8c62a403c46c00f702a
+size 1064

RuleMaze/quest/checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

RuleMaze/quest/checkpoint/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

RuleMaze/quest/checkpoint/trainer_state.json

@@ -0,0 +1,906 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.281573498964804,
+  "eval_steps": 3000,
+  "global_step": 12000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06901311249137336,
+      "grad_norm": 1.6816006898880005,
+      "learning_rate": 3.4161490683229816e-06,
+      "loss": 0.6591953277587891,
+      "step": 100
+    },
+    {
+      "epoch": 0.13802622498274672,
+      "grad_norm": 0.6589540243148804,
+      "learning_rate": 6.86680469289165e-06,
+      "loss": 0.2923994827270508,
+      "step": 200
+    },
+    {
+      "epoch": 0.2070393374741201,
+      "grad_norm": 1.2133013010025024,
+      "learning_rate": 1.0317460317460318e-05,
+      "loss": 0.18498283386230469,
+      "step": 300
+    },
+    {
+      "epoch": 0.27605244996549344,
+      "grad_norm": 1.0459880828857422,
+      "learning_rate": 1.3768115942028985e-05,
+      "loss": 0.16723533630371093,
+      "step": 400
+    },
+    {
+      "epoch": 0.3450655624568668,
+      "grad_norm": 1.483292818069458,
+      "learning_rate": 1.7218771566597654e-05,
+      "loss": 0.15117901802062989,
+      "step": 500
+    },
+    {
+      "epoch": 0.4140786749482402,
+      "grad_norm": 1.5424000024795532,
+      "learning_rate": 2.0669427191166323e-05,
+      "loss": 0.1323984432220459,
+      "step": 600
+    },
+    {
+      "epoch": 0.4830917874396135,
+      "grad_norm": 0.7599974274635315,
+      "learning_rate": 2.412008281573499e-05,
+      "loss": 0.11645044326782227,
+      "step": 700
+    },
+    {
+      "epoch": 0.5521048999309869,
+      "grad_norm": 0.715633749961853,
+      "learning_rate": 2.757073844030366e-05,
+      "loss": 0.10420452117919922,
+      "step": 800
+    },
+    {
+      "epoch": 0.6211180124223602,
+      "grad_norm": 1.7199045419692993,
+      "learning_rate": 3.102139406487233e-05,
+      "loss": 0.09004179000854493,
+      "step": 900
+    },
+    {
+      "epoch": 0.6901311249137336,
+      "grad_norm": 1.2357006072998047,
+      "learning_rate": 3.4472049689440996e-05,
+      "loss": 0.08238659858703613,
+      "step": 1000
+    },
+    {
+      "epoch": 0.759144237405107,
+      "grad_norm": 0.5357984304428101,
+      "learning_rate": 3.7922705314009665e-05,
+      "loss": 0.07050128936767579,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8281573498964804,
+      "grad_norm": 0.4577958881855011,
+      "learning_rate": 4.1373360938578333e-05,
+      "loss": 0.059500017166137696,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8971704623878537,
+      "grad_norm": 0.5463616251945496,
+      "learning_rate": 4.4824016563146996e-05,
+      "loss": 0.05880669116973877,
+      "step": 1300
+    },
+    {
+      "epoch": 0.966183574879227,
+      "grad_norm": 1.8560669422149658,
+      "learning_rate": 4.827467218771567e-05,
+      "loss": 0.053169384002685546,
+      "step": 1400
+    },
+    {
+      "epoch": 1.0351966873706004,
+      "grad_norm": 1.4429179430007935,
+      "learning_rate": 5.172532781228434e-05,
+      "loss": 0.04906704902648926,
+      "step": 1500
+    },
+    {
+      "epoch": 1.1042097998619738,
+      "grad_norm": 0.5594888925552368,
+      "learning_rate": 5.517598343685301e-05,
+      "loss": 0.04453295707702637,
+      "step": 1600
+    },
+    {
+      "epoch": 1.173222912353347,
+      "grad_norm": 1.2935067415237427,
+      "learning_rate": 5.862663906142167e-05,
+      "loss": 0.04573007583618164,
+      "step": 1700
+    },
+    {
+      "epoch": 1.2422360248447206,
+      "grad_norm": 1.148449182510376,
+      "learning_rate": 6.207729468599034e-05,
+      "loss": 0.03800388097763061,
+      "step": 1800
+    },
+    {
+      "epoch": 1.311249137336094,
+      "grad_norm": 0.6981308460235596,
+      "learning_rate": 6.5527950310559e-05,
+      "loss": 0.03885750293731689,
+      "step": 1900
+    },
+    {
+      "epoch": 1.3802622498274673,
+      "grad_norm": 0.62127685546875,
+      "learning_rate": 6.897860593512768e-05,
+      "loss": 0.03810855865478516,
+      "step": 2000
+    },
+    {
+      "epoch": 1.4492753623188406,
+      "grad_norm": 0.7466416954994202,
+      "learning_rate": 7.242926155969635e-05,
+      "loss": 0.03464083433151245,
+      "step": 2100
+    },
+    {
+      "epoch": 1.518288474810214,
+      "grad_norm": 0.9254693984985352,
+      "learning_rate": 7.587991718426502e-05,
+      "loss": 0.03223170757293701,
+      "step": 2200
+    },
+    {
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.3020302355289459,
+      "learning_rate": 7.933057280883368e-05,
+      "loss": 0.03271255731582642,
+      "step": 2300
+    },
+    {
+      "epoch": 1.6563146997929605,
+      "grad_norm": 1.07040274143219,
+      "learning_rate": 8.278122843340234e-05,
+      "loss": 0.030880575180053712,
+      "step": 2400
+    },
+    {
+      "epoch": 1.725327812284334,
+      "grad_norm": 2.1029250621795654,
+      "learning_rate": 8.623188405797103e-05,
+      "loss": 0.02905160665512085,
+      "step": 2500
+    },
+    {
+      "epoch": 1.7943409247757074,
+      "grad_norm": 0.3471164107322693,
+      "learning_rate": 8.968253968253969e-05,
+      "loss": 0.026902031898498536,
+      "step": 2600
+    },
+    {
+      "epoch": 1.8633540372670807,
+      "grad_norm": 0.5531296133995056,
+      "learning_rate": 9.313319530710835e-05,
+      "loss": 0.027059719562530518,
+      "step": 2700
+    },
+    {
+      "epoch": 1.9323671497584543,
+      "grad_norm": 0.16381041705608368,
+      "learning_rate": 9.658385093167702e-05,
+      "loss": 0.02538679838180542,
+      "step": 2800
+    },
+    {
+      "epoch": 2.0013802622498273,
+      "grad_norm": 0.3163216710090637,
+      "learning_rate": 9.99999996372913e-05,
+      "loss": 0.02327730655670166,
+      "step": 2900
+    },
+    {
+      "epoch": 2.070393374741201,
+      "grad_norm": 0.24789570271968842,
+      "learning_rate": 9.999630005418305e-05,
+      "loss": 0.018836562633514405,
+      "step": 3000
+    },
+    {
+      "epoch": 2.070393374741201,
+      "eval_loss": 0.02921237424015999,
+      "eval_runtime": 181.6758,
+      "eval_samples_per_second": 30.984,
+      "eval_steps_per_second": 7.75,
+      "step": 3000
+    },
+    {
+      "epoch": 2.139406487232574,
+      "grad_norm": 0.7237645983695984,
+      "learning_rate": 9.998534692157168e-05,
+      "loss": 0.021141095161437987,
+      "step": 3100
+    },
+    {
+      "epoch": 2.2084195997239475,
+      "grad_norm": 0.7793195247650146,
+      "learning_rate": 9.99671418285566e-05,
+      "loss": 0.022475566864013672,
+      "step": 3200
+    },
+    {
+      "epoch": 2.277432712215321,
+      "grad_norm": 0.37524935603141785,
+      "learning_rate": 9.994168741636414e-05,
+      "loss": 0.01790332794189453,
+      "step": 3300
+    },
+    {
+      "epoch": 2.346445824706694,
+      "grad_norm": 0.3501254916191101,
+      "learning_rate": 9.990898737796431e-05,
+      "loss": 0.01794546365737915,
+      "step": 3400
+    },
+    {
+      "epoch": 2.4154589371980677,
+      "grad_norm": 0.3263097107410431,
+      "learning_rate": 9.986904645753517e-05,
+      "loss": 0.017757058143615723,
+      "step": 3500
+    },
+    {
+      "epoch": 2.4844720496894412,
+      "grad_norm": 0.1627577245235443,
+      "learning_rate": 9.982187044977433e-05,
+      "loss": 0.0191100811958313,
+      "step": 3600
+    },
+    {
+      "epoch": 2.5534851621808143,
+      "grad_norm": 0.2708640694618225,
+      "learning_rate": 9.976746619905848e-05,
+      "loss": 0.01647867798805237,
+      "step": 3700
+    },
+    {
+      "epoch": 2.622498274672188,
+      "grad_norm": 0.19428923726081848,
+      "learning_rate": 9.970584159845019e-05,
+      "loss": 0.019564281702041626,
+      "step": 3800
+    },
+    {
+      "epoch": 2.691511387163561,
+      "grad_norm": 0.27478209137916565,
+      "learning_rate": 9.963700558855286e-05,
+      "loss": 0.01532339096069336,
+      "step": 3900
+    },
+    {
+      "epoch": 2.7605244996549345,
+      "grad_norm": 0.6304217576980591,
+      "learning_rate": 9.956096815621365e-05,
+      "loss": 0.015121045112609864,
+      "step": 4000
+    },
+    {
+      "epoch": 2.829537612146308,
+      "grad_norm": 0.24556516110897064,
+      "learning_rate": 9.947774033307444e-05,
+      "loss": 0.01376125454902649,
+      "step": 4100
+    },
+    {
+      "epoch": 2.898550724637681,
+      "grad_norm": 0.22283633053302765,
+      "learning_rate": 9.938733419397148e-05,
+      "loss": 0.01422502040863037,
+      "step": 4200
+    },
+    {
+      "epoch": 2.9675638371290542,
+      "grad_norm": 0.17323362827301025,
+      "learning_rate": 9.928976285518347e-05,
+      "loss": 0.013914072513580322,
+      "step": 4300
+    },
+    {
+      "epoch": 3.036576949620428,
+      "grad_norm": 0.3366715610027313,
+      "learning_rate": 9.918504047252866e-05,
+      "loss": 0.012446303367614747,
+      "step": 4400
+    },
+    {
+      "epoch": 3.1055900621118013,
+      "grad_norm": 0.579430341720581,
+      "learning_rate": 9.907318223931104e-05,
+      "loss": 0.010887300968170166,
+      "step": 4500
+    },
+    {
+      "epoch": 3.1746031746031744,
+      "grad_norm": 0.1589874029159546,
+      "learning_rate": 9.895420438411616e-05,
+      "loss": 0.009336315393447876,
+      "step": 4600
+    },
+    {
+      "epoch": 3.243616287094548,
+      "grad_norm": 0.3313974142074585,
+      "learning_rate": 9.882812416845659e-05,
+      "loss": 0.01209233283996582,
+      "step": 4700
+    },
+    {
+      "epoch": 3.3126293995859215,
+      "grad_norm": 0.20725291967391968,
+      "learning_rate": 9.869495988426765e-05,
+      "loss": 0.01219676375389099,
+      "step": 4800
+    },
+    {
+      "epoch": 3.3816425120772946,
+      "grad_norm": 0.32415810227394104,
+      "learning_rate": 9.85547308512535e-05,
+      "loss": 0.011185965538024902,
+      "step": 4900
+    },
+    {
+      "epoch": 3.450655624568668,
+      "grad_norm": 0.6780321598052979,
+      "learning_rate": 9.84074574140843e-05,
+      "loss": 0.010217201709747315,
+      "step": 5000
+    },
+    {
+      "epoch": 3.5196687370600412,
+      "grad_norm": 0.4579280912876129,
+      "learning_rate": 9.825316093944449e-05,
+      "loss": 0.009207376837730407,
+      "step": 5100
+    },
+    {
+      "epoch": 3.588681849551415,
+      "grad_norm": 0.2888343930244446,
+      "learning_rate": 9.809186381293293e-05,
+      "loss": 0.008018433451652526,
+      "step": 5200
+    },
+    {
+      "epoch": 3.657694962042788,
+      "grad_norm": 0.41798698902130127,
+      "learning_rate": 9.792358943581512e-05,
+      "loss": 0.008765748143196106,
+      "step": 5300
+    },
+    {
+      "epoch": 3.7267080745341614,
+      "grad_norm": 0.22403675317764282,
+      "learning_rate": 9.774836222162811e-05,
+      "loss": 0.01168360948562622,
+      "step": 5400
+    },
+    {
+      "epoch": 3.795721187025535,
+      "grad_norm": 0.2777250409126282,
+      "learning_rate": 9.756620759263859e-05,
+      "loss": 0.007222639918327331,
+      "step": 5500
+    },
+    {
+      "epoch": 3.864734299516908,
+      "grad_norm": 0.2178342044353485,
+      "learning_rate": 9.73771519761545e-05,
+      "loss": 0.00962002992630005,
+      "step": 5600
+    },
+    {
+      "epoch": 3.9337474120082816,
+      "grad_norm": 0.4984281361103058,
+      "learning_rate": 9.718122280069101e-05,
+      "loss": 0.008592043519020081,
+      "step": 5700
+    },
+    {
+      "epoch": 4.002760524499655,
+      "grad_norm": 0.13588963449001312,
+      "learning_rate": 9.697844849199104e-05,
+      "loss": 0.008585309982299805,
+      "step": 5800
+    },
+    {
+      "epoch": 4.071773636991028,
+      "grad_norm": 0.38846534490585327,
+      "learning_rate": 9.67688584689013e-05,
+      "loss": 0.005256276726722717,
+      "step": 5900
+    },
+    {
+      "epoch": 4.140786749482402,
+      "grad_norm": 0.023833556100726128,
+      "learning_rate": 9.655248313910406e-05,
+      "loss": 0.005661345720291137,
+      "step": 6000
+    },
+    {
+      "epoch": 4.140786749482402,
+      "eval_loss": 0.03166082128882408,
+      "eval_runtime": 181.1836,
+      "eval_samples_per_second": 31.068,
+      "eval_steps_per_second": 7.771,
+      "step": 6000
+    },
+    {
+      "epoch": 4.209799861973775,
+      "grad_norm": 0.6761375665664673,
+      "learning_rate": 9.63293538947056e-05,
+      "loss": 0.00854755997657776,
+      "step": 6100
+    },
+    {
+      "epoch": 4.278812974465148,
+      "grad_norm": 0.17318780720233917,
+      "learning_rate": 9.609950310768186e-05,
+      "loss": 0.006477295756340027,
+      "step": 6200
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 0.41419535875320435,
+      "learning_rate": 9.586296412518169e-05,
+      "loss": 0.006662110686302185,
+      "step": 6300
+    },
+    {
+      "epoch": 4.416839199447895,
+      "grad_norm": 0.23430900275707245,
+      "learning_rate": 9.561977126468895e-05,
+      "loss": 0.008465226292610168,
+      "step": 6400
+    },
+    {
+      "epoch": 4.485852311939269,
+      "grad_norm": 0.4777432978153229,
+      "learning_rate": 9.536995980904358e-05,
+      "loss": 0.008400806188583375,
+      "step": 6500
+    },
+    {
+      "epoch": 4.554865424430642,
+      "grad_norm": 0.12053324282169342,
+      "learning_rate": 9.511356600132268e-05,
+      "loss": 0.0058623385429382325,
+      "step": 6600
+    },
+    {
+      "epoch": 4.623878536922016,
+      "grad_norm": 0.2965043783187866,
+      "learning_rate": 9.485062703958248e-05,
+      "loss": 0.006002122163772583,
+      "step": 6700
+    },
+    {
+      "epoch": 4.692891649413388,
+      "grad_norm": 0.09787727892398834,
+      "learning_rate": 9.45811810714613e-05,
+      "loss": 0.005868737101554871,
+      "step": 6800
+    },
+    {
+      "epoch": 4.761904761904762,
+      "grad_norm": 0.2600211203098297,
+      "learning_rate": 9.430526718864529e-05,
+      "loss": 0.005710598230361939,
+      "step": 6900
+    },
+    {
+      "epoch": 4.830917874396135,
+      "grad_norm": 0.2016928344964981,
+      "learning_rate": 9.402292542119675e-05,
+      "loss": 0.0066363120079040525,
+      "step": 7000
+    },
+    {
+      "epoch": 4.899930986887509,
+      "grad_norm": 0.22014115750789642,
+      "learning_rate": 9.373419673174664e-05,
+      "loss": 0.00683988630771637,
+      "step": 7100
+    },
+    {
+      "epoch": 4.9689440993788825,
+      "grad_norm": 0.1540168821811676,
+      "learning_rate": 9.343912300955152e-05,
+      "loss": 0.006956667304039001,
+      "step": 7200
+    },
+    {
+      "epoch": 5.037957211870255,
+      "grad_norm": 0.07650943845510483,
+      "learning_rate": 9.313774706441632e-05,
+      "loss": 0.005676180124282837,
+      "step": 7300
+    },
+    {
+      "epoch": 5.106970324361629,
+      "grad_norm": 0.33717188239097595,
+      "learning_rate": 9.283011262048334e-05,
+      "loss": 0.005521973371505737,
+      "step": 7400
+    },
+    {
+      "epoch": 5.175983436853002,
+      "grad_norm": 0.005147412419319153,
+      "learning_rate": 9.25162643098886e-05,
+      "loss": 0.0038105571269989014,
+      "step": 7500
+    },
+    {
+      "epoch": 5.244996549344376,
+      "grad_norm": 0.16790005564689636,
+      "learning_rate": 9.219624766628675e-05,
+      "loss": 0.00456691026687622,
+      "step": 7600
+    },
+    {
+      "epoch": 5.314009661835748,
+      "grad_norm": 0.10933786630630493,
+      "learning_rate": 9.187010911824475e-05,
+      "loss": 0.005703316926956177,
+      "step": 7700
+    },
+    {
+      "epoch": 5.383022774327122,
+      "grad_norm": 0.22020448744297028,
+      "learning_rate": 9.153789598250606e-05,
+      "loss": 0.00373211532831192,
+      "step": 7800
+    },
+    {
+      "epoch": 5.4520358868184955,
+      "grad_norm": 0.02716304175555706,
+      "learning_rate": 9.119965645712579e-05,
+      "loss": 0.004552946388721466,
+      "step": 7900
+    },
+    {
+      "epoch": 5.521048999309869,
+      "grad_norm": 0.0344187393784523,
+      "learning_rate": 9.085543961447808e-05,
+      "loss": 0.0033217817544937134,
+      "step": 8000
+    },
+    {
+      "epoch": 5.590062111801243,
+      "grad_norm": 0.07475689798593521,
+      "learning_rate": 9.050529539413655e-05,
+      "loss": 0.004494180977344513,
+      "step": 8100
+    },
+    {
+      "epoch": 5.659075224292615,
+      "grad_norm": 0.06090749427676201,
+      "learning_rate": 9.014927459562901e-05,
+      "loss": 0.0038747549057006835,
+      "step": 8200
+    },
+    {
+      "epoch": 5.728088336783989,
+      "grad_norm": 0.3817507028579712,
+      "learning_rate": 8.978742887106742e-05,
+      "loss": 0.0035914430022239686,
+      "step": 8300
+    },
+    {
+      "epoch": 5.797101449275362,
+      "grad_norm": 0.0885179191827774,
+      "learning_rate": 8.941981071765397e-05,
+      "loss": 0.0046504676342010495,
+      "step": 8400
+    },
+    {
+      "epoch": 5.866114561766736,
+      "grad_norm": 0.05214108154177666,
+      "learning_rate": 8.904647347006491e-05,
+      "loss": 0.004471878707408905,
+      "step": 8500
+    },
+    {
+      "epoch": 5.935127674258109,
+      "grad_norm": 0.06531859189271927,
+      "learning_rate": 8.866747129271244e-05,
+      "loss": 0.004513611793518066,
+      "step": 8600
+    },
+    {
+      "epoch": 6.004140786749482,
+      "grad_norm": 0.0673370286822319,
+      "learning_rate": 8.828285917188661e-05,
+      "loss": 0.004545169174671173,
+      "step": 8700
+    },
+    {
+      "epoch": 6.073153899240856,
+      "grad_norm": 0.41905659437179565,
+      "learning_rate": 8.789269290777772e-05,
+      "loss": 0.0034026417136192324,
+      "step": 8800
+    },
+    {
+      "epoch": 6.142167011732229,
+      "grad_norm": 0.20389963686466217,
+      "learning_rate": 8.74970291063808e-05,
+      "loss": 0.003790842294692993,
+      "step": 8900
+    },
+    {
+      "epoch": 6.211180124223603,
+      "grad_norm": 0.005800154991447926,
+      "learning_rate": 8.709592517128303e-05,
+      "loss": 0.00427827000617981,
+      "step": 9000
+    },
+    {
+      "epoch": 6.211180124223603,
+      "eval_loss": 0.02816120535135269,
+      "eval_runtime": 181.7766,
+      "eval_samples_per_second": 30.967,
+      "eval_steps_per_second": 7.746,
+      "step": 9000
+    },
+    {
+      "epoch": 6.280193236714976,
+      "grad_norm": 1.0103602409362793,
+      "learning_rate": 8.668943929533559e-05,
+      "loss": 0.004533968567848205,
+      "step": 9100
+    },
+    {
+      "epoch": 6.349206349206349,
+      "grad_norm": 0.22238457202911377,
+      "learning_rate": 8.627763045221097e-05,
+      "loss": 0.0028093403577804568,
+      "step": 9200
+    },
+    {
+      "epoch": 6.418219461697722,
+      "grad_norm": 0.011495680548250675,
+      "learning_rate": 8.586055838784687e-05,
+      "loss": 0.004271593689918518,
+      "step": 9300
+    },
+    {
+      "epoch": 6.487232574189096,
+      "grad_norm": 0.21627311408519745,
+      "learning_rate": 8.543828361177825e-05,
+      "loss": 0.006068320870399475,
+      "step": 9400
+    },
+    {
+      "epoch": 6.5562456866804695,
+      "grad_norm": 0.7513999342918396,
+      "learning_rate": 8.501086738835843e-05,
+      "loss": 0.003060971200466156,
+      "step": 9500
+    },
+    {
+      "epoch": 6.625258799171843,
+      "grad_norm": 0.29959240555763245,
+      "learning_rate": 8.457837172787082e-05,
+      "loss": 0.0029618120193481445,
+      "step": 9600
+    },
+    {
+      "epoch": 6.694271911663216,
+      "grad_norm": 0.30377644300460815,
+      "learning_rate": 8.414085937753229e-05,
+      "loss": 0.00355678915977478,
+      "step": 9700
+    },
+    {
+      "epoch": 6.763285024154589,
+      "grad_norm": 0.053236573934555054,
+      "learning_rate": 8.369839381238977e-05,
+      "loss": 0.0033687394857406616,
+      "step": 9800
+    },
+    {
+      "epoch": 6.832298136645963,
+      "grad_norm": 0.1835521012544632,
+      "learning_rate": 8.325103922611114e-05,
+      "loss": 0.002790749371051788,
+      "step": 9900
+    },
+    {
+      "epoch": 6.901311249137336,
+      "grad_norm": 0.03666497394442558,
+      "learning_rate": 8.279886052167185e-05,
+      "loss": 0.003270851969718933,
+      "step": 10000
+    },
+    {
+      "epoch": 6.97032436162871,
+      "grad_norm": 0.21567919850349426,
+      "learning_rate": 8.234192330193881e-05,
+      "loss": 0.004674305319786072,
+      "step": 10100
+    },
+    {
+      "epoch": 7.0393374741200825,
+      "grad_norm": 0.25714561343193054,
+      "learning_rate": 8.18802938601525e-05,
+      "loss": 0.0025664740800857544,
+      "step": 10200
+    },
+    {
+      "epoch": 7.108350586611456,
+      "grad_norm": 0.0016106347320601344,
+      "learning_rate": 8.14140391703091e-05,
+      "loss": 0.001942284107208252,
+      "step": 10300
+    },
+    {
+      "epoch": 7.17736369910283,
+      "grad_norm": 0.0061345831491053104,
+      "learning_rate": 8.094322687744371e-05,
+      "loss": 0.0024612732231616974,
+      "step": 10400
+    },
+    {
+      "epoch": 7.246376811594203,
+      "grad_norm": 0.4842909574508667,
+      "learning_rate": 8.046792528781642e-05,
+      "loss": 0.002561650574207306,
+      "step": 10500
+    },
+    {
+      "epoch": 7.315389924085577,
+      "grad_norm": 0.003960311878472567,
+      "learning_rate": 7.998820335900217e-05,
+      "loss": 0.0013421116769313812,
+      "step": 10600
+    },
+    {
+      "epoch": 7.384403036576949,
+      "grad_norm": 0.007439567707479,
+      "learning_rate": 7.950413068988638e-05,
+      "loss": 0.003062557876110077,
+      "step": 10700
+    },
+    {
+      "epoch": 7.453416149068323,
+      "grad_norm": 0.08753065019845963,
+      "learning_rate": 7.901577751056739e-05,
+      "loss": 0.00208556205034256,
+      "step": 10800
+    },
+    {
+      "epoch": 7.522429261559696,
+      "grad_norm": 0.014604340307414532,
+      "learning_rate": 7.85232146721673e-05,
+      "loss": 0.002812923789024353,
+      "step": 10900
+    },
+    {
+      "epoch": 7.59144237405107,
+      "grad_norm": 0.7260613441467285,
+      "learning_rate": 7.802651363655285e-05,
+      "loss": 0.002836261689662933,
+      "step": 11000
+    },
+    {
+      "epoch": 7.660455486542443,
+      "grad_norm": 0.004646544810384512,
+      "learning_rate": 7.75257464659676e-05,
+      "loss": 0.002893007695674896,
+      "step": 11100
+    },
+    {
+      "epoch": 7.729468599033816,
+      "grad_norm": 0.0021574676502496004,
+      "learning_rate": 7.702098581257692e-05,
+      "loss": 0.003359476923942566,
+      "step": 11200
+    },
+    {
+      "epoch": 7.79848171152519,
+      "grad_norm": 0.04375157505273819,
+      "learning_rate": 7.651230490792762e-05,
+      "loss": 0.0026143118739128113,
+      "step": 11300
+    },
+    {
+      "epoch": 7.867494824016563,
+      "grad_norm": 0.025788860395550728,
+      "learning_rate": 7.599977755232328e-05,
+      "loss": 0.0021833184361457823,
+      "step": 11400
+    },
+    {
+      "epoch": 7.936507936507937,
+      "grad_norm": 0.0044431621208786964,
+      "learning_rate": 7.548347810411729e-05,
+      "loss": 0.003199644684791565,
+      "step": 11500
+    },
+    {
+      "epoch": 8.00552104899931,
+      "grad_norm": 0.02362344227731228,
+      "learning_rate": 7.496348146892469e-05,
+      "loss": 0.003279160261154175,
+      "step": 11600
+    },
+    {
+      "epoch": 8.074534161490684,
+      "grad_norm": 0.0023468986619263887,
+      "learning_rate": 7.443986308875479e-05,
+      "loss": 0.0017800283432006835,
+      "step": 11700
+    },
+    {
+      "epoch": 8.143547273982056,
+      "grad_norm": 0.02598908729851246,
+      "learning_rate": 7.391269893106592e-05,
+      "loss": 0.0010919257253408433,
+      "step": 11800
+    },
+    {
+      "epoch": 8.21256038647343,
+      "grad_norm": 0.034161508083343506,
+      "learning_rate": 7.338206547774395e-05,
+      "loss": 0.0038761073350906373,
+      "step": 11900
+    },
+    {
+      "epoch": 8.281573498964804,
+      "grad_norm": 0.6880965828895569,
+      "learning_rate": 7.284803971400614e-05,
+      "loss": 0.0018247830867767333,
+      "step": 12000
+    },
+    {
+      "epoch": 8.281573498964804,
+      "eval_loss": 0.03933844342827797,
+      "eval_runtime": 181.0173,
+      "eval_samples_per_second": 31.096,
+      "eval_steps_per_second": 7.778,
+      "step": 12000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 28980,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 3000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.146516808737751e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

RuleMaze/quest/checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aadc8739cc804af8e34dcfdb1cdfdbe9e425622c9bdefc332ef109b8e76a679
+size 5560

RuleMaze/regular/checkpoint/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen2.5-VL-3B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-VL-3B-Instruct
+- llama-factory
+- 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 0.18.1

RuleMaze/regular/checkpoint/adapter_config.json

@@ -0,0 +1,151 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "layers.25.mlp.up_proj",
+    "layers.29.mlp.down_proj",
+    "layers.19.mlp.up_proj",
+    "layers.6.mlp.gate_proj",
+    "layers.27.mlp.up_proj",
+    "layers.3.mlp.down_proj",
+    "34.mlp.gate_proj",
+    "layers.17.mlp.down_proj",
+    "layers.23.mlp.down_proj",
+    "layers.20.mlp.down_proj",
+    "layers.19.mlp.down_proj",
+    "layers.24.mlp.up_proj",
+    "layers.11.mlp.up_proj",
+    "layers.9.mlp.up_proj",
+    "layers.5.mlp.up_proj",
+    "layers.18.mlp.down_proj",
+    "33.mlp.up_proj",
+    "layers.9.mlp.gate_proj",
+    "layers.17.mlp.gate_proj",
+    "layers.11.mlp.down_proj",
+    "35.mlp.gate_proj",
+    "layers.16.mlp.down_proj",
+    "layers.13.mlp.gate_proj",
+    "32.mlp.gate_proj",
+    "layers.1.mlp.up_proj",
+    "layers.21.mlp.up_proj",
+    "layers.22.mlp.down_proj",
+    "layers.29.mlp.gate_proj",
+    "layers.24.mlp.gate_proj",
+    "layers.31.mlp.down_proj",
+    "34.mlp.up_proj",
+    "layers.2.mlp.gate_proj",
+    "layers.29.mlp.up_proj",
+    "layers.20.mlp.gate_proj",
+    "layers.24.mlp.down_proj",
+    "layers.12.mlp.up_proj",
+    "layers.26.mlp.down_proj",
+    "layers.16.mlp.up_proj",
+    "layers.26.mlp.up_proj",
+    "layers.30.mlp.gate_proj",
+    "layers.20.mlp.up_proj",
+    "layers.14.mlp.up_proj",
+    "layers.4.mlp.up_proj",
+    "layers.11.mlp.gate_proj",
+    "layers.30.mlp.down_proj",
+    "layers.18.mlp.up_proj",
+    "35.mlp.up_proj",
+    "layers.0.mlp.gate_proj",
+    "layers.30.mlp.up_proj",
+    "layers.31.mlp.up_proj",
+    "layers.9.mlp.down_proj",
+    "layers.0.mlp.up_proj",
+    "layers.7.mlp.gate_proj",
+    "layers.1.mlp.down_proj",
+    "32.mlp.down_proj",
+    "layers.15.mlp.down_proj",
+    "layers.1.mlp.gate_proj",
+    "layers.4.mlp.down_proj",
+    "layers.21.mlp.down_proj",
+    "layers.6.mlp.up_proj",
+    "layers.28.mlp.up_proj",
+    "layers.18.mlp.gate_proj",
+    "layers.4.mlp.gate_proj",
+    "layers.22.mlp.up_proj",
+    "layers.28.mlp.down_proj",
+    "layers.14.mlp.gate_proj",
+    "layers.19.mlp.gate_proj",
+    "layers.27.mlp.gate_proj",
+    "layers.2.mlp.up_proj",
+    "layers.0.mlp.down_proj",
+    "layers.12.mlp.gate_proj",
+    "layers.13.mlp.down_proj",
+    "layers.25.mlp.gate_proj",
+    "layers.8.mlp.down_proj",
+    "layers.10.mlp.gate_proj",
+    "layers.17.mlp.up_proj",
+    "layers.28.mlp.gate_proj",
+    "layers.10.mlp.up_proj",
+    "layers.5.mlp.down_proj",
+    "layers.3.mlp.up_proj",
+    "layers.7.mlp.down_proj",
+    "layers.5.mlp.gate_proj",
+    "layers.22.mlp.gate_proj",
+    "layers.14.mlp.down_proj",
+    "layers.3.mlp.gate_proj",
+    "layers.31.mlp.gate_proj",
+    "layers.10.mlp.down_proj",
+    "layers.25.mlp.down_proj",
+    "layers.7.mlp.up_proj",
+    "layers.15.mlp.gate_proj",
+    "34.mlp.down_proj",
+    "33.mlp.gate_proj",
+    "layers.15.mlp.up_proj",
+    "layers.8.mlp.up_proj",
+    "o_proj",
+    "layers.21.mlp.gate_proj",
+    "layers.13.mlp.up_proj",
+    "35.mlp.down_proj",
+    "33.mlp.down_proj",
+    "layers.23.mlp.up_proj",
+    "v_proj",
+    "layers.12.mlp.down_proj",
+    "k_proj",
+    "layers.26.mlp.gate_proj",
+    "layers.27.mlp.down_proj",
+    "layers.2.mlp.down_proj",
+    "layers.8.mlp.gate_proj",
+    "layers.6.mlp.down_proj",
+    "q_proj",
+    "layers.16.mlp.gate_proj",
+    "layers.23.mlp.gate_proj",
+    "32.mlp.up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

RuleMaze/regular/checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf52d4b66818a7a2e0d3243b02ecb78711c63ba0158a4b956f5a83b2027a658c
+size 59941192

RuleMaze/regular/checkpoint/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

RuleMaze/regular/checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:513b24837e7ef8e50a2785dd12de8a00f3cdfce128916f5aeb5923ced0fd39e9
+size 120166091

RuleMaze/regular/checkpoint/processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen2_5_VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen2VLVideoProcessor"
+  }
+}

RuleMaze/regular/checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5093d9ced672268085b82fa39d1b89e5ac93a3a18a59a989b271295a07b9ccd1
+size 15429

RuleMaze/regular/checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd8ca6e1eafc6a6c0f5863cd14662300324e69b710f6a1ecdc76adb93466629
+size 15429

RuleMaze/regular/checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:079788f0c27c34946197f1a3ccfb099be63e60d3b81ca2e1708fdc43e5084bae
+size 15429

RuleMaze/regular/checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a726b049d7cadd85deeef60294818bb0e9a8a2fd746e6f39716d53fd11134cc
+size 15429

RuleMaze/regular/checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22dd245f056fd9b359294f8c8cce5390d8d6edd9343c9dc8c6dfc14c3c8ce49
+size 1465

RuleMaze/regular/checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

RuleMaze/regular/checkpoint/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

RuleMaze/regular/checkpoint/trainer_state.json

@@ -0,0 +1,906 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 13.157981349424027,
+  "eval_steps": 3000,
+  "global_step": 12000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10970927043335162,
+      "grad_norm": 0.468578577041626,
+      "learning_rate": 5.4276315789473686e-06,
+      "loss": 0.5462883758544922,
+      "step": 100
+    },
+    {
+      "epoch": 0.21941854086670323,
+      "grad_norm": 0.45979681611061096,
+      "learning_rate": 1.0910087719298246e-05,
+      "loss": 0.2727891731262207,
+      "step": 200
+    },
+    {
+      "epoch": 0.32912781130005486,
+      "grad_norm": 0.6285035610198975,
+      "learning_rate": 1.6392543859649124e-05,
+      "loss": 0.20325206756591796,
+      "step": 300
+    },
+    {
+      "epoch": 0.43883708173340646,
+      "grad_norm": 0.49440646171569824,
+      "learning_rate": 2.1875e-05,
+      "loss": 0.17335186004638672,
+      "step": 400
+    },
+    {
+      "epoch": 0.5485463521667581,
+      "grad_norm": 0.3639424443244934,
+      "learning_rate": 2.735745614035088e-05,
+      "loss": 0.1450818157196045,
+      "step": 500
+    },
+    {
+      "epoch": 0.6582556226001097,
+      "grad_norm": 0.8926243782043457,
+      "learning_rate": 3.2839912280701755e-05,
+      "loss": 0.129285945892334,
+      "step": 600
+    },
+    {
+      "epoch": 0.7679648930334614,
+      "grad_norm": 0.6681469082832336,
+      "learning_rate": 3.8322368421052634e-05,
+      "loss": 0.10414340019226075,
+      "step": 700
+    },
+    {
+      "epoch": 0.8776741634668129,
+      "grad_norm": 0.470255583524704,
+      "learning_rate": 4.3804824561403514e-05,
+      "loss": 0.0889210319519043,
+      "step": 800
+    },
+    {
+      "epoch": 0.9873834339001646,
+      "grad_norm": 0.6484633684158325,
+      "learning_rate": 4.928728070175439e-05,
+      "loss": 0.08110878944396972,
+      "step": 900
+    },
+    {
+      "epoch": 1.0965441579813495,
+      "grad_norm": 0.42188429832458496,
+      "learning_rate": 5.4769736842105266e-05,
+      "loss": 0.0681976318359375,
+      "step": 1000
+    },
+    {
+      "epoch": 1.206253428414701,
+      "grad_norm": 0.38744252920150757,
+      "learning_rate": 6.0252192982456145e-05,
+      "loss": 0.059779272079467774,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3159626988480526,
+      "grad_norm": 0.634701669216156,
+      "learning_rate": 6.573464912280702e-05,
+      "loss": 0.05309516906738281,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4256719692814044,
+      "grad_norm": 0.3459165692329407,
+      "learning_rate": 7.12171052631579e-05,
+      "loss": 0.04944893360137939,
+      "step": 1300
+    },
+    {
+      "epoch": 1.535381239714756,
+      "grad_norm": 0.6033017635345459,
+      "learning_rate": 7.669956140350878e-05,
+      "loss": 0.04666784286499023,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6450905101481075,
+      "grad_norm": 0.6594127416610718,
+      "learning_rate": 8.218201754385966e-05,
+      "loss": 0.04396382808685303,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7547997805814592,
+      "grad_norm": 0.1653222292661667,
+      "learning_rate": 8.766447368421054e-05,
+      "loss": 0.041247625350952145,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8645090510148108,
+      "grad_norm": 0.3759867548942566,
+      "learning_rate": 9.314692982456141e-05,
+      "loss": 0.03404149293899536,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9742183214481623,
+      "grad_norm": 0.23973219096660614,
+      "learning_rate": 9.862938596491229e-05,
+      "loss": 0.03183579921722412,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0833790455293473,
+      "grad_norm": 0.325320303440094,
+      "learning_rate": 9.999484984691653e-05,
+      "loss": 0.03078770637512207,
+      "step": 1900
+    },
+    {
+      "epoch": 2.193088315962699,
+      "grad_norm": 0.16789975762367249,
+      "learning_rate": 9.9971962417026e-05,
+      "loss": 0.027160501480102538,
+      "step": 2000
+    },
+    {
+      "epoch": 2.3027975863960504,
+      "grad_norm": 0.39737239480018616,
+      "learning_rate": 9.993077384438713e-05,
+      "loss": 0.024041428565979003,
+      "step": 2100
+    },
+    {
+      "epoch": 2.412506856829402,
+      "grad_norm": 0.36602410674095154,
+      "learning_rate": 9.987129921341749e-05,
+      "loss": 0.023267135620117188,
+      "step": 2200
+    },
+    {
+      "epoch": 2.5222161272627535,
+      "grad_norm": 0.05183083936572075,
+      "learning_rate": 9.97935603054052e-05,
+      "loss": 0.02218881607055664,
+      "step": 2300
+    },
+    {
+      "epoch": 2.6319253976961052,
+      "grad_norm": 0.23794086277484894,
+      "learning_rate": 9.969758559053199e-05,
+      "loss": 0.019391658306121825,
+      "step": 2400
+    },
+    {
+      "epoch": 2.741634668129457,
+      "grad_norm": 0.46757692098617554,
+      "learning_rate": 9.958341021744668e-05,
+      "loss": 0.015924193859100343,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8513439385628088,
+      "grad_norm": 0.3365223705768585,
+      "learning_rate": 9.945107600039271e-05,
+      "loss": 0.016793460845947267,
+      "step": 2600
+    },
+    {
+      "epoch": 2.96105320899616,
+      "grad_norm": 0.10865141451358795,
+      "learning_rate": 9.930063140389458e-05,
+      "loss": 0.015737195014953614,
+      "step": 2700
+    },
+    {
+      "epoch": 3.070213933077345,
+      "grad_norm": 0.12908822298049927,
+      "learning_rate": 9.913213152500879e-05,
+      "loss": 0.012379565238952638,
+      "step": 2800
+    },
+    {
+      "epoch": 3.179923203510697,
+      "grad_norm": 0.39894333481788635,
+      "learning_rate": 9.89456380731457e-05,
+      "loss": 0.010362827777862548,
+      "step": 2900
+    },
+    {
+      "epoch": 3.289632473944048,
+      "grad_norm": 0.18888452649116516,
+      "learning_rate": 9.874121934746984e-05,
+      "loss": 0.010273929834365845,
+      "step": 3000
+    },
+    {
+      "epoch": 3.289632473944048,
+      "eval_loss": 0.11601941287517548,
+      "eval_runtime": 116.5005,
+      "eval_samples_per_second": 27.631,
+      "eval_steps_per_second": 6.91,
+      "step": 3000
+    },
+    {
+      "epoch": 3.3993417443774,
+      "grad_norm": 0.24296416342258453,
+      "learning_rate": 9.851895021188692e-05,
+      "loss": 0.008741957545280456,
+      "step": 3100
+    },
+    {
+      "epoch": 3.5090510148107517,
+      "grad_norm": 0.18995995819568634,
+      "learning_rate": 9.827891206762634e-05,
+      "loss": 0.009190759658813476,
+      "step": 3200
+    },
+    {
+      "epoch": 3.618760285244103,
+      "grad_norm": 0.1456049531698227,
+      "learning_rate": 9.802119282342995e-05,
+      "loss": 0.009634263515472412,
+      "step": 3300
+    },
+    {
+      "epoch": 3.7284695556774547,
+      "grad_norm": 0.9678109288215637,
+      "learning_rate": 9.774588686335731e-05,
+      "loss": 0.008319487571716308,
+      "step": 3400
+    },
+    {
+      "epoch": 3.8381788261108065,
+      "grad_norm": 0.08138152211904526,
+      "learning_rate": 9.74530950122196e-05,
+      "loss": 0.009371925592422486,
+      "step": 3500
+    },
+    {
+      "epoch": 3.947888096544158,
+      "grad_norm": 0.5730862617492676,
+      "learning_rate": 9.71429244986547e-05,
+      "loss": 0.007398140430450439,
+      "step": 3600
+    },
+    {
+      "epoch": 4.057048820625343,
+      "grad_norm": 0.508908748626709,
+      "learning_rate": 9.681548891585711e-05,
+      "loss": 0.00682299017906189,
+      "step": 3700
+    },
+    {
+      "epoch": 4.1667580910586945,
+      "grad_norm": 0.507350504398346,
+      "learning_rate": 9.647090817997684e-05,
+      "loss": 0.0053677594661712645,
+      "step": 3800
+    },
+    {
+      "epoch": 4.276467361492046,
+      "grad_norm": 0.24189727008342743,
+      "learning_rate": 9.610930848620274e-05,
+      "loss": 0.003890502452850342,
+      "step": 3900
+    },
+    {
+      "epoch": 4.386176631925398,
+      "grad_norm": 0.012589801102876663,
+      "learning_rate": 9.573082226254632e-05,
+      "loss": 0.006510751247406006,
+      "step": 4000
+    },
+    {
+      "epoch": 4.495885902358749,
+      "grad_norm": 0.06403769552707672,
+      "learning_rate": 9.533558812134284e-05,
+      "loss": 0.00700473427772522,
+      "step": 4100
+    },
+    {
+      "epoch": 4.605595172792101,
+      "grad_norm": 0.04759138450026512,
+      "learning_rate": 9.492375080848754e-05,
+      "loss": 0.008159146308898926,
+      "step": 4200
+    },
+    {
+      "epoch": 4.7153044432254525,
+      "grad_norm": 0.1282065361738205,
+      "learning_rate": 9.449546115042562e-05,
+      "loss": 0.0043099141120910645,
+      "step": 4300
+    },
+    {
+      "epoch": 4.825013713658804,
+      "grad_norm": 0.06390748172998428,
+      "learning_rate": 9.405087599891538e-05,
+      "loss": 0.006736204624176025,
+      "step": 4400
+    },
+    {
+      "epoch": 4.934722984092156,
+      "grad_norm": 0.3489040434360504,
+      "learning_rate": 9.35901581735846e-05,
+      "loss": 0.005642812252044677,
+      "step": 4500
+    },
+    {
+      "epoch": 5.0438837081733405,
+      "grad_norm": 0.06407257169485092,
+      "learning_rate": 9.311347640230149e-05,
+      "loss": 0.004873534739017487,
+      "step": 4600
+    },
+    {
+      "epoch": 5.153592978606692,
+      "grad_norm": 0.4154542088508606,
+      "learning_rate": 9.262100525938174e-05,
+      "loss": 0.003611042499542236,
+      "step": 4700
+    },
+    {
+      "epoch": 5.263302249040044,
+      "grad_norm": 0.35824549198150635,
+      "learning_rate": 9.211292510165441e-05,
+      "loss": 0.004827427566051483,
+      "step": 4800
+    },
+    {
+      "epoch": 5.373011519473396,
+      "grad_norm": 0.018712563440203667,
+      "learning_rate": 9.158942200241036e-05,
+      "loss": 0.0049249035120010375,
+      "step": 4900
+    },
+    {
+      "epoch": 5.482720789906747,
+      "grad_norm": 0.38031527400016785,
+      "learning_rate": 9.105068768325671e-05,
+      "loss": 0.003927983045578003,
+      "step": 5000
+    },
+    {
+      "epoch": 5.5924300603400985,
+      "grad_norm": 0.15979327261447906,
+      "learning_rate": 9.049691944390318e-05,
+      "loss": 0.004007718861103058,
+      "step": 5100
+    },
+    {
+      "epoch": 5.70213933077345,
+      "grad_norm": 0.16055099666118622,
+      "learning_rate": 8.99283200899053e-05,
+      "loss": 0.0029034724831581114,
+      "step": 5200
+    },
+    {
+      "epoch": 5.811848601206802,
+      "grad_norm": 0.04370570927858353,
+      "learning_rate": 8.934509785839125e-05,
+      "loss": 0.002957637310028076,
+      "step": 5300
+    },
+    {
+      "epoch": 5.921557871640154,
+      "grad_norm": 0.4308537244796753,
+      "learning_rate": 8.874746634179962e-05,
+      "loss": 0.006440707445144653,
+      "step": 5400
+    },
+    {
+      "epoch": 6.030718595721338,
+      "grad_norm": 0.0070524257607758045,
+      "learning_rate": 8.813564440965575e-05,
+      "loss": 0.003051069974899292,
+      "step": 5500
+    },
+    {
+      "epoch": 6.14042786615469,
+      "grad_norm": 0.0011389772407710552,
+      "learning_rate": 8.750985612841563e-05,
+      "loss": 0.0020513579249382017,
+      "step": 5600
+    },
+    {
+      "epoch": 6.250137136588042,
+      "grad_norm": 0.3267161250114441,
+      "learning_rate": 8.687033067940638e-05,
+      "loss": 0.0032824283838272096,
+      "step": 5700
+    },
+    {
+      "epoch": 6.359846407021394,
+      "grad_norm": 0.22967475652694702,
+      "learning_rate": 8.621730227489358e-05,
+      "loss": 0.0017755647003650666,
+      "step": 5800
+    },
+    {
+      "epoch": 6.4695556774547445,
+      "grad_norm": 0.11276954412460327,
+      "learning_rate": 8.555101007230614e-05,
+      "loss": 0.0023945705592632294,
+      "step": 5900
+    },
+    {
+      "epoch": 6.579264947888096,
+      "grad_norm": 0.029238076880574226,
+      "learning_rate": 8.487169808665014e-05,
+      "loss": 0.007325031161308289,
+      "step": 6000
+    },
+    {
+      "epoch": 6.579264947888096,
+      "eval_loss": 0.09214479476213455,
+      "eval_runtime": 116.3647,
+      "eval_samples_per_second": 27.663,
+      "eval_steps_per_second": 6.918,
+      "step": 6000
+    },
+    {
+      "epoch": 6.688974218321448,
+      "grad_norm": 0.04784254729747772,
+      "learning_rate": 8.417961510114356e-05,
+      "loss": 0.003531929850578308,
+      "step": 6100
+    },
+    {
+      "epoch": 6.7986834887548,
+      "grad_norm": 0.025865700095891953,
+      "learning_rate": 8.347501457610494e-05,
+      "loss": 0.004350661635398865,
+      "step": 6200
+    },
+    {
+      "epoch": 6.9083927591881515,
+      "grad_norm": 0.07848550379276276,
+      "learning_rate": 8.275815455612899e-05,
+      "loss": 0.003835231363773346,
+      "step": 6300
+    },
+    {
+      "epoch": 7.017553483269336,
+      "grad_norm": 0.5314407348632812,
+      "learning_rate": 8.20292975755834e-05,
+      "loss": 0.003852725923061371,
+      "step": 6400
+    },
+    {
+      "epoch": 7.127262753702688,
+      "grad_norm": 0.004145840182900429,
+      "learning_rate": 8.12887105624614e-05,
+      "loss": 0.0037556231021881104,
+      "step": 6500
+    },
+    {
+      "epoch": 7.23697202413604,
+      "grad_norm": 0.01268320344388485,
+      "learning_rate": 8.053666474062508e-05,
+      "loss": 0.0029447203874588012,
+      "step": 6600
+    },
+    {
+      "epoch": 7.346681294569391,
+      "grad_norm": 0.16281633079051971,
+      "learning_rate": 7.97734355304757e-05,
+      "loss": 0.002923213243484497,
+      "step": 6700
+    },
+    {
+      "epoch": 7.456390565002743,
+      "grad_norm": 0.14518429338932037,
+      "learning_rate": 7.89993024480868e-05,
+      "loss": 0.0024193134903907777,
+      "step": 6800
+    },
+    {
+      "epoch": 7.566099835436094,
+      "grad_norm": 0.3797168433666229,
+      "learning_rate": 7.821454900283775e-05,
+      "loss": 0.0024912458658218383,
+      "step": 6900
+    },
+    {
+      "epoch": 7.675809105869446,
+      "grad_norm": 0.5517730712890625,
+      "learning_rate": 7.741946259358434e-05,
+      "loss": 0.0023130226135253907,
+      "step": 7000
+    },
+    {
+      "epoch": 7.7855183763027975,
+      "grad_norm": 0.22722378373146057,
+      "learning_rate": 7.661433440340549e-05,
+      "loss": 0.0026683008670806887,
+      "step": 7100
+    },
+    {
+      "epoch": 7.895227646736149,
+      "grad_norm": 0.07195847481489182,
+      "learning_rate": 7.579945929296352e-05,
+      "loss": 0.00318217933177948,
+      "step": 7200
+    },
+    {
+      "epoch": 8.004388370817335,
+      "grad_norm": 0.07402148842811584,
+      "learning_rate": 7.49751356925181e-05,
+      "loss": 0.0024203072488307954,
+      "step": 7300
+    },
+    {
+      "epoch": 8.114097641250686,
+      "grad_norm": 0.0004932262236252427,
+      "learning_rate": 7.414166549263253e-05,
+      "loss": 0.0005915772542357445,
+      "step": 7400
+    },
+    {
+      "epoch": 8.223806911684036,
+      "grad_norm": 0.14862555265426636,
+      "learning_rate": 7.329935393361286e-05,
+      "loss": 0.0015757225453853607,
+      "step": 7500
+    },
+    {
+      "epoch": 8.333516182117389,
+      "grad_norm": 0.11636239290237427,
+      "learning_rate": 7.244850949372044e-05,
+      "loss": 0.0014248163998126983,
+      "step": 7600
+    },
+    {
+      "epoch": 8.44322545255074,
+      "grad_norm": 0.02938424050807953,
+      "learning_rate": 7.158944377619829e-05,
+      "loss": 0.0008066059648990632,
+      "step": 7700
+    },
+    {
+      "epoch": 8.552934722984093,
+      "grad_norm": 0.003459229366853833,
+      "learning_rate": 7.072247139515337e-05,
+      "loss": 0.0007172146439552307,
+      "step": 7800
+    },
+    {
+      "epoch": 8.662643993417444,
+      "grad_norm": 1.0215219259262085,
+      "learning_rate": 6.984790986033582e-05,
+      "loss": 0.0024658374488353728,
+      "step": 7900
+    },
+    {
+      "epoch": 8.772353263850796,
+      "grad_norm": 0.04188821464776993,
+      "learning_rate": 6.896607946085818e-05,
+      "loss": 0.003845172226428986,
+      "step": 8000
+    },
+    {
+      "epoch": 8.882062534284147,
+      "grad_norm": 0.21492426097393036,
+      "learning_rate": 6.807730314789622e-05,
+      "loss": 0.0034224957227706907,
+      "step": 8100
+    },
+    {
+      "epoch": 8.991771804717498,
+      "grad_norm": 0.001628322177566588,
+      "learning_rate": 6.71819064164153e-05,
+      "loss": 0.0017799775302410126,
+      "step": 8200
+    },
+    {
+      "epoch": 9.100932528798683,
+      "grad_norm": 0.10092741996049881,
+      "learning_rate": 6.628021718596485e-05,
+      "loss": 0.0018181195855140686,
+      "step": 8300
+    },
+    {
+      "epoch": 9.210641799232036,
+      "grad_norm": 0.011512243188917637,
+      "learning_rate": 6.537256568058492e-05,
+      "loss": 0.0007427728176116943,
+      "step": 8400
+    },
+    {
+      "epoch": 9.320351069665387,
+      "grad_norm": 0.05302899330854416,
+      "learning_rate": 6.445928430786898e-05,
+      "loss": 0.0031538277864456175,
+      "step": 8500
+    },
+    {
+      "epoch": 9.430060340098738,
+      "grad_norm": 0.003643701085820794,
+      "learning_rate": 6.354070753722674e-05,
+      "loss": 0.0019684681296348572,
+      "step": 8600
+    },
+    {
+      "epoch": 9.53976961053209,
+      "grad_norm": 0.005743952933698893,
+      "learning_rate": 6.261717177739202e-05,
+      "loss": 0.002124977260828018,
+      "step": 8700
+    },
+    {
+      "epoch": 9.649478880965441,
+      "grad_norm": 0.0006560595938935876,
+      "learning_rate": 6.168901525322048e-05,
+      "loss": 0.002307926416397095,
+      "step": 8800
+    },
+    {
+      "epoch": 9.759188151398794,
+      "grad_norm": 0.014800022356212139,
+      "learning_rate": 6.075657788182201e-05,
+      "loss": 0.0020691359043121336,
+      "step": 8900
+    },
+    {
+      "epoch": 9.868897421832145,
+      "grad_norm": 0.00023062083346303552,
+      "learning_rate": 5.982020114807359e-05,
+      "loss": 0.0011634621024131774,
+      "step": 9000
+    },
+    {
+      "epoch": 9.868897421832145,
+      "eval_loss": 0.10657082498073578,
+      "eval_runtime": 116.1296,
+      "eval_samples_per_second": 27.719,
+      "eval_steps_per_second": 6.932,
+      "step": 9000
+    },
+    {
+      "epoch": 9.978606692265496,
+      "grad_norm": 0.005069139879196882,
+      "learning_rate": 5.888022797955783e-05,
+      "loss": 0.000807158499956131,
+      "step": 9100
+    },
+    {
+      "epoch": 10.087767416346681,
+      "grad_norm": 0.0007675938541069627,
+      "learning_rate": 5.793700262097326e-05,
+      "loss": 0.000818609818816185,
+      "step": 9200
+    },
+    {
+      "epoch": 10.197476686780034,
+      "grad_norm": 8.392518066102639e-05,
+      "learning_rate": 5.699087050806219e-05,
+      "loss": 0.0002204919047653675,
+      "step": 9300
+    },
+    {
+      "epoch": 10.307185957213385,
+      "grad_norm": 0.001035814406350255,
+      "learning_rate": 5.604217814110233e-05,
+      "loss": 0.0010148981213569642,
+      "step": 9400
+    },
+    {
+      "epoch": 10.416895227646735,
+      "grad_norm": 0.0005645599449053407,
+      "learning_rate": 5.509127295800873e-05,
+      "loss": 0.0009634912759065628,
+      "step": 9500
+    },
+    {
+      "epoch": 10.526604498080088,
+      "grad_norm": 0.006124628707766533,
+      "learning_rate": 5.413850320709213e-05,
+      "loss": 0.002135903686285019,
+      "step": 9600
+    },
+    {
+      "epoch": 10.636313768513439,
+      "grad_norm": 0.015287889167666435,
+      "learning_rate": 5.318421781952063e-05,
+      "loss": 0.001537524163722992,
+      "step": 9700
+    },
+    {
+      "epoch": 10.746023038946792,
+      "grad_norm": 0.0016915776068344712,
+      "learning_rate": 5.2228766281531184e-05,
+      "loss": 0.000581161379814148,
+      "step": 9800
+    },
+    {
+      "epoch": 10.855732309380143,
+      "grad_norm": 0.039407797157764435,
+      "learning_rate": 5.127249850643801e-05,
+      "loss": 0.0010789106786251068,
+      "step": 9900
+    },
+    {
+      "epoch": 10.965441579813493,
+      "grad_norm": 0.0032954695634543896,
+      "learning_rate": 5.031576470648437e-05,
+      "loss": 0.0008925460278987885,
+      "step": 10000
+    },
+    {
+      "epoch": 11.074602303894679,
+      "grad_norm": 0.0008019655360840261,
+      "learning_rate": 4.935891526458493e-05,
+      "loss": 0.0006475619226694107,
+      "step": 10100
+    },
+    {
+      "epoch": 11.184311574328031,
+      "grad_norm": 0.001246742787770927,
+      "learning_rate": 4.840230060600579e-05,
+      "loss": 0.001001117080450058,
+      "step": 10200
+    },
+    {
+      "epoch": 11.294020844761382,
+      "grad_norm": 0.004168672487139702,
+      "learning_rate": 4.744627107002866e-05,
+      "loss": 0.0009924402087926865,
+      "step": 10300
+    },
+    {
+      "epoch": 11.403730115194733,
+      "grad_norm": 0.006193607579916716,
+      "learning_rate": 4.649117678164694e-05,
+      "loss": 0.0007412029802799225,
+      "step": 10400
+    },
+    {
+      "epoch": 11.513439385628086,
+      "grad_norm": 0.04498029127717018,
+      "learning_rate": 4.5537367523339915e-05,
+      "loss": 0.001676485538482666,
+      "step": 10500
+    },
+    {
+      "epoch": 11.623148656061437,
+      "grad_norm": 0.0013482400681823492,
+      "learning_rate": 4.458519260697263e-05,
+      "loss": 0.0006184951961040497,
+      "step": 10600
+    },
+    {
+      "epoch": 11.73285792649479,
+      "grad_norm": 0.04078209772706032,
+      "learning_rate": 4.363500074586795e-05,
+      "loss": 0.00015302015468478204,
+      "step": 10700
+    },
+    {
+      "epoch": 11.84256719692814,
+      "grad_norm": 0.00041609694017097354,
+      "learning_rate": 4.268713992709801e-05,
+      "loss": 0.0001718943752348423,
+      "step": 10800
+    },
+    {
+      "epoch": 11.952276467361493,
+      "grad_norm": 0.001313285669311881,
+      "learning_rate": 4.1741957284041396e-05,
+      "loss": 0.0002560199424624443,
+      "step": 10900
+    },
+    {
+      "epoch": 12.061437191442677,
+      "grad_norm": 0.20023229718208313,
+      "learning_rate": 4.079979896925319e-05,
+      "loss": 0.001909550279378891,
+      "step": 11000
+    },
+    {
+      "epoch": 12.17114646187603,
+      "grad_norm": 0.017514726147055626,
+      "learning_rate": 3.986101002769419e-05,
+      "loss": 0.00020196065306663514,
+      "step": 11100
+    },
+    {
+      "epoch": 12.28085573230938,
+      "grad_norm": 9.268768189940602e-05,
+      "learning_rate": 3.89259342703655e-05,
+      "loss": 0.0002678022161126137,
+      "step": 11200
+    },
+    {
+      "epoch": 12.390565002742731,
+      "grad_norm": 0.00034697377122938633,
+      "learning_rate": 3.799491414839556e-05,
+      "loss": 0.00046276580542325974,
+      "step": 11300
+    },
+    {
+      "epoch": 12.500274273176084,
+      "grad_norm": 0.0007233850774355233,
+      "learning_rate": 3.7068290627624544e-05,
+      "loss": 0.0004483434557914734,
+      "step": 11400
+    },
+    {
+      "epoch": 12.609983543609435,
+      "grad_norm": 0.00960569642484188,
+      "learning_rate": 3.614640306373329e-05,
+      "loss": 0.00046372778713703154,
+      "step": 11500
+    },
+    {
+      "epoch": 12.719692814042787,
+      "grad_norm": 8.914520003600046e-05,
+      "learning_rate": 3.522958907796155e-05,
+      "loss": 0.0001941412128508091,
+      "step": 11600
+    },
+    {
+      "epoch": 12.829402084476138,
+      "grad_norm": 0.00025227374862879515,
+      "learning_rate": 3.431818443346164e-05,
+      "loss": 7.15433107689023e-05,
+      "step": 11700
+    },
+    {
+      "epoch": 12.939111354909489,
+      "grad_norm": 7.685183663852513e-05,
+      "learning_rate": 3.341252291233241e-05,
+      "loss": 0.0002717839926481247,
+      "step": 11800
+    },
+    {
+      "epoch": 13.048272078990674,
+      "grad_norm": 2.5767532861209475e-05,
+      "learning_rate": 3.251293619337889e-05,
+      "loss": 5.591163411736489e-05,
+      "step": 11900
+    },
+    {
+      "epoch": 13.157981349424027,
+      "grad_norm": 7.815273420419544e-05,
+      "learning_rate": 3.161975373064217e-05,
+      "loss": 1.8522043246775867e-05,
+      "step": 12000
+    },
+    {
+      "epoch": 13.157981349424027,
+      "eval_loss": 0.15513338148593903,
+      "eval_runtime": 107.1852,
+      "eval_samples_per_second": 30.032,
+      "eval_steps_per_second": 7.51,
+      "step": 12000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 18240,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 3000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.758640217053987e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

RuleMaze/regular/checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d227f27eaab049d18fc25bf8cd8a37399cee0dfc72fb22dff279a0b1bcd79f62
+size 5585