Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,6 @@ 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
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+v5_dagger_model/checkpoint-180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+v5_dagger_model/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+v5_dagger_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text

v5_dagger_model/README.md

@@ -0,0 +1,63 @@
+---
+base_model: unsloth/qwen2.5-vl-7b-instruct
+library_name: peft
+model_name: lora_model_v5_dagger
+tags:
+- base_model:adapter:unsloth/qwen2.5-vl-7b-instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for lora_model_v5_dagger
+
+This model is a fine-tuned version of [unsloth/qwen2.5-vl-7b-instruct](https://huggingface.co/unsloth/qwen2.5-vl-7b-instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 0.24.0
+- Transformers: 4.57.6
+- Pytorch: 2.5.1+rocm6.2
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

v5_dagger_model/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2_5_VLForConditionalGeneration",
+    "parent_library": "transformers.models.qwen2_5_vl.modeling_qwen2_5_vl",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-vl-7b-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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:qkv|proj|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:qkv|proj|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

v5_dagger_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b8c8d6d82ce21ed20fb5412ef5d433408a355615435f2800946c1b12d44ed5
+size 161539072

v5_dagger_model/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

v5_dagger_model/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 %}

v5_dagger_model/checkpoint-180/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen2.5-vl-7b-instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen2.5-vl-7b-instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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

v5_dagger_model/checkpoint-180/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2_5_VLForConditionalGeneration",
+    "parent_library": "transformers.models.qwen2_5_vl.modeling_qwen2_5_vl",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-vl-7b-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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:qkv|proj|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:qkv|proj|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

v5_dagger_model/checkpoint-180/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67941e66c2f9225aa6933c55078fe365a14f8342476dc78fbf1ee0c4f42cf0f3
+size 161539072

v5_dagger_model/checkpoint-180/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

v5_dagger_model/checkpoint-180/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 %}

v5_dagger_model/checkpoint-180/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9aff8b19c14d674b647d46355b11afee92d3fc6ad1272b99f2dee268ddbfd1b
+size 82464628

v5_dagger_model/checkpoint-180/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "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
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "_Unsloth_Patched_Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

v5_dagger_model/checkpoint-180/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc969112b1f0893268b67300da6d4435cd3fc222db3a89dedc3eb14ba7beab8
+size 14244

v5_dagger_model/checkpoint-180/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db10a462ddd938463497e09c4cc90b5fc5aae3e3f95255defedc7750b4e90de7
+size 1064

v5_dagger_model/checkpoint-180/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": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

v5_dagger_model/checkpoint-180/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741c85ffe434aad73e934a73ef380c85e94cd863b8f55e1a1ad66cacb5a93dfd
+size 11422164

v5_dagger_model/checkpoint-180/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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
+    }
+  },
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "processor_class": "_Unsloth_Patched_Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

v5_dagger_model/checkpoint-180/trainer_state.json

@@ -0,0 +1,1294 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05755395683453238,
+      "grad_norm": 2.2564826011657715,
+      "learning_rate": 0.0,
+      "loss": 4.8786,
+      "step": 1
+    },
+    {
+      "epoch": 0.11510791366906475,
+      "grad_norm": 2.6304173469543457,
+      "learning_rate": 2e-05,
+      "loss": 5.4851,
+      "step": 2
+    },
+    {
+      "epoch": 0.17266187050359713,
+      "grad_norm": 2.5263326168060303,
+      "learning_rate": 4e-05,
+      "loss": 4.7033,
+      "step": 3
+    },
+    {
+      "epoch": 0.2302158273381295,
+      "grad_norm": 2.3896210193634033,
+      "learning_rate": 6e-05,
+      "loss": 4.6046,
+      "step": 4
+    },
+    {
+      "epoch": 0.28776978417266186,
+      "grad_norm": 2.7547967433929443,
+      "learning_rate": 8e-05,
+      "loss": 4.9866,
+      "step": 5
+    },
+    {
+      "epoch": 0.34532374100719426,
+      "grad_norm": 3.2151615619659424,
+      "learning_rate": 0.0001,
+      "loss": 5.0008,
+      "step": 6
+    },
+    {
+      "epoch": 0.4028776978417266,
+      "grad_norm": 2.4654593467712402,
+      "learning_rate": 0.00012,
+      "loss": 3.7805,
+      "step": 7
+    },
+    {
+      "epoch": 0.460431654676259,
+      "grad_norm": 2.3590445518493652,
+      "learning_rate": 0.00014,
+      "loss": 3.5862,
+      "step": 8
+    },
+    {
+      "epoch": 0.5179856115107914,
+      "grad_norm": 1.6592985391616821,
+      "learning_rate": 0.00016,
+      "loss": 2.8476,
+      "step": 9
+    },
+    {
+      "epoch": 0.5755395683453237,
+      "grad_norm": 1.1599284410476685,
+      "learning_rate": 0.00018,
+      "loss": 2.1064,
+      "step": 10
+    },
+    {
+      "epoch": 0.6330935251798561,
+      "grad_norm": 1.802690029144287,
+      "learning_rate": 0.0002,
+      "loss": 2.4239,
+      "step": 11
+    },
+    {
+      "epoch": 0.6906474820143885,
+      "grad_norm": 1.470718502998352,
+      "learning_rate": 0.00019894736842105264,
+      "loss": 2.1704,
+      "step": 12
+    },
+    {
+      "epoch": 0.7482014388489209,
+      "grad_norm": 2.7104134559631348,
+      "learning_rate": 0.00019789473684210526,
+      "loss": 1.9153,
+      "step": 13
+    },
+    {
+      "epoch": 0.8057553956834532,
+      "grad_norm": 1.823458194732666,
+      "learning_rate": 0.0001968421052631579,
+      "loss": 1.5356,
+      "step": 14
+    },
+    {
+      "epoch": 0.8633093525179856,
+      "grad_norm": 1.5308654308319092,
+      "learning_rate": 0.00019578947368421054,
+      "loss": 1.6719,
+      "step": 15
+    },
+    {
+      "epoch": 0.920863309352518,
+      "grad_norm": 1.1720850467681885,
+      "learning_rate": 0.00019473684210526317,
+      "loss": 1.4082,
+      "step": 16
+    },
+    {
+      "epoch": 0.9784172661870504,
+      "grad_norm": 0.921774685382843,
+      "learning_rate": 0.0001936842105263158,
+      "loss": 1.3164,
+      "step": 17
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0646902322769165,
+      "learning_rate": 0.00019263157894736842,
+      "loss": 1.3508,
+      "step": 18
+    },
+    {
+      "epoch": 1.0575539568345325,
+      "grad_norm": 0.7060080170631409,
+      "learning_rate": 0.00019157894736842104,
+      "loss": 1.1843,
+      "step": 19
+    },
+    {
+      "epoch": 1.1151079136690647,
+      "grad_norm": 0.6636799573898315,
+      "learning_rate": 0.0001905263157894737,
+      "loss": 1.013,
+      "step": 20
+    },
+    {
+      "epoch": 1.1726618705035972,
+      "grad_norm": 0.6766036748886108,
+      "learning_rate": 0.00018947368421052632,
+      "loss": 0.8595,
+      "step": 21
+    },
+    {
+      "epoch": 1.2302158273381294,
+      "grad_norm": 0.5309479832649231,
+      "learning_rate": 0.00018842105263157898,
+      "loss": 0.8741,
+      "step": 22
+    },
+    {
+      "epoch": 1.2877697841726619,
+      "grad_norm": 0.7695677876472473,
+      "learning_rate": 0.0001873684210526316,
+      "loss": 0.9812,
+      "step": 23
+    },
+    {
+      "epoch": 1.3453237410071943,
+      "grad_norm": 0.8244631290435791,
+      "learning_rate": 0.00018631578947368423,
+      "loss": 0.7284,
+      "step": 24
+    },
+    {
+      "epoch": 1.4028776978417266,
+      "grad_norm": 0.7941868305206299,
+      "learning_rate": 0.00018526315789473685,
+      "loss": 0.7796,
+      "step": 25
+    },
+    {
+      "epoch": 1.460431654676259,
+      "grad_norm": 0.5958636999130249,
+      "learning_rate": 0.00018421052631578948,
+      "loss": 0.8259,
+      "step": 26
+    },
+    {
+      "epoch": 1.5179856115107913,
+      "grad_norm": 0.8691028952598572,
+      "learning_rate": 0.0001831578947368421,
+      "loss": 0.6653,
+      "step": 27
+    },
+    {
+      "epoch": 1.5755395683453237,
+      "grad_norm": 0.646342396736145,
+      "learning_rate": 0.00018210526315789476,
+      "loss": 0.6347,
+      "step": 28
+    },
+    {
+      "epoch": 1.6330935251798562,
+      "grad_norm": 0.6964317560195923,
+      "learning_rate": 0.00018105263157894739,
+      "loss": 0.6772,
+      "step": 29
+    },
+    {
+      "epoch": 1.6906474820143886,
+      "grad_norm": 0.6086808443069458,
+      "learning_rate": 0.00018,
+      "loss": 0.6906,
+      "step": 30
+    },
+    {
+      "epoch": 1.7482014388489209,
+      "grad_norm": 0.6074932217597961,
+      "learning_rate": 0.00017894736842105264,
+      "loss": 0.6537,
+      "step": 31
+    },
+    {
+      "epoch": 1.8057553956834531,
+      "grad_norm": 0.539799690246582,
+      "learning_rate": 0.00017789473684210526,
+      "loss": 0.5003,
+      "step": 32
+    },
+    {
+      "epoch": 1.8633093525179856,
+      "grad_norm": 0.5748394727706909,
+      "learning_rate": 0.0001768421052631579,
+      "loss": 0.3782,
+      "step": 33
+    },
+    {
+      "epoch": 1.920863309352518,
+      "grad_norm": 0.5975272059440613,
+      "learning_rate": 0.00017578947368421052,
+      "loss": 0.4689,
+      "step": 34
+    },
+    {
+      "epoch": 1.9784172661870505,
+      "grad_norm": 0.6873601078987122,
+      "learning_rate": 0.00017473684210526317,
+      "loss": 0.5143,
+      "step": 35
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7587007880210876,
+      "learning_rate": 0.0001736842105263158,
+      "loss": 0.3664,
+      "step": 36
+    },
+    {
+      "epoch": 2.0575539568345325,
+      "grad_norm": 0.5641581416130066,
+      "learning_rate": 0.00017263157894736842,
+      "loss": 0.3186,
+      "step": 37
+    },
+    {
+      "epoch": 2.115107913669065,
+      "grad_norm": 0.6975970268249512,
+      "learning_rate": 0.00017157894736842107,
+      "loss": 0.4577,
+      "step": 38
+    },
+    {
+      "epoch": 2.172661870503597,
+      "grad_norm": 0.5590388774871826,
+      "learning_rate": 0.0001705263157894737,
+      "loss": 0.2734,
+      "step": 39
+    },
+    {
+      "epoch": 2.2302158273381294,
+      "grad_norm": 0.5296897292137146,
+      "learning_rate": 0.00016947368421052633,
+      "loss": 0.3938,
+      "step": 40
+    },
+    {
+      "epoch": 2.287769784172662,
+      "grad_norm": 0.44214928150177,
+      "learning_rate": 0.00016842105263157895,
+      "loss": 0.4129,
+      "step": 41
+    },
+    {
+      "epoch": 2.3453237410071943,
+      "grad_norm": 0.5920043587684631,
+      "learning_rate": 0.0001673684210526316,
+      "loss": 0.2301,
+      "step": 42
+    },
+    {
+      "epoch": 2.402877697841727,
+      "grad_norm": 0.5350307822227478,
+      "learning_rate": 0.00016631578947368423,
+      "loss": 0.3897,
+      "step": 43
+    },
+    {
+      "epoch": 2.460431654676259,
+      "grad_norm": 0.5216901898384094,
+      "learning_rate": 0.00016526315789473686,
+      "loss": 0.3855,
+      "step": 44
+    },
+    {
+      "epoch": 2.5179856115107913,
+      "grad_norm": 0.6011196374893188,
+      "learning_rate": 0.00016421052631578948,
+      "loss": 0.3711,
+      "step": 45
+    },
+    {
+      "epoch": 2.5755395683453237,
+      "grad_norm": 0.5409759283065796,
+      "learning_rate": 0.0001631578947368421,
+      "loss": 0.2035,
+      "step": 46
+    },
+    {
+      "epoch": 2.633093525179856,
+      "grad_norm": 0.5009431838989258,
+      "learning_rate": 0.00016210526315789473,
+      "loss": 0.1684,
+      "step": 47
+    },
+    {
+      "epoch": 2.6906474820143886,
+      "grad_norm": 0.6343453526496887,
+      "learning_rate": 0.00016105263157894736,
+      "loss": 0.4425,
+      "step": 48
+    },
+    {
+      "epoch": 2.7482014388489207,
+      "grad_norm": 0.5234959721565247,
+      "learning_rate": 0.00016,
+      "loss": 0.2177,
+      "step": 49
+    },
+    {
+      "epoch": 2.805755395683453,
+      "grad_norm": 0.47029346227645874,
+      "learning_rate": 0.00015894736842105264,
+      "loss": 0.2741,
+      "step": 50
+    },
+    {
+      "epoch": 2.8633093525179856,
+      "grad_norm": 0.5409159064292908,
+      "learning_rate": 0.00015789473684210527,
+      "loss": 0.3455,
+      "step": 51
+    },
+    {
+      "epoch": 2.920863309352518,
+      "grad_norm": 0.5376619696617126,
+      "learning_rate": 0.0001568421052631579,
+      "loss": 0.3439,
+      "step": 52
+    },
+    {
+      "epoch": 2.9784172661870505,
+      "grad_norm": 0.6080886721611023,
+      "learning_rate": 0.00015578947368421052,
+      "loss": 0.3303,
+      "step": 53
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7982627153396606,
+      "learning_rate": 0.00015473684210526317,
+      "loss": 0.3354,
+      "step": 54
+    },
+    {
+      "epoch": 3.0575539568345325,
+      "grad_norm": 0.5055177211761475,
+      "learning_rate": 0.0001536842105263158,
+      "loss": 0.2868,
+      "step": 55
+    },
+    {
+      "epoch": 3.115107913669065,
+      "grad_norm": 0.4262123107910156,
+      "learning_rate": 0.00015263157894736845,
+      "loss": 0.2097,
+      "step": 56
+    },
+    {
+      "epoch": 3.172661870503597,
+      "grad_norm": 0.3976552486419678,
+      "learning_rate": 0.00015157894736842108,
+      "loss": 0.3558,
+      "step": 57
+    },
+    {
+      "epoch": 3.2302158273381294,
+      "grad_norm": 0.46125659346580505,
+      "learning_rate": 0.0001505263157894737,
+      "loss": 0.2219,
+      "step": 58
+    },
+    {
+      "epoch": 3.287769784172662,
+      "grad_norm": 0.4844948649406433,
+      "learning_rate": 0.00014947368421052633,
+      "loss": 0.2234,
+      "step": 59
+    },
+    {
+      "epoch": 3.3453237410071943,
+      "grad_norm": 0.6512012481689453,
+      "learning_rate": 0.00014842105263157895,
+      "loss": 0.274,
+      "step": 60
+    },
+    {
+      "epoch": 3.402877697841727,
+      "grad_norm": 0.5738747715950012,
+      "learning_rate": 0.00014736842105263158,
+      "loss": 0.2676,
+      "step": 61
+    },
+    {
+      "epoch": 3.460431654676259,
+      "grad_norm": 0.5202072858810425,
+      "learning_rate": 0.00014631578947368423,
+      "loss": 0.2553,
+      "step": 62
+    },
+    {
+      "epoch": 3.5179856115107913,
+      "grad_norm": 0.5690760612487793,
+      "learning_rate": 0.00014526315789473686,
+      "loss": 0.1784,
+      "step": 63
+    },
+    {
+      "epoch": 3.5755395683453237,
+      "grad_norm": 0.6203038096427917,
+      "learning_rate": 0.00014421052631578948,
+      "loss": 0.1628,
+      "step": 64
+    },
+    {
+      "epoch": 3.633093525179856,
+      "grad_norm": 0.31157344579696655,
+      "learning_rate": 0.0001431578947368421,
+      "loss": 0.0833,
+      "step": 65
+    },
+    {
+      "epoch": 3.6906474820143886,
+      "grad_norm": 0.34490475058555603,
+      "learning_rate": 0.00014210526315789474,
+      "loss": 0.0886,
+      "step": 66
+    },
+    {
+      "epoch": 3.7482014388489207,
+      "grad_norm": 0.7103127241134644,
+      "learning_rate": 0.00014105263157894736,
+      "loss": 0.2206,
+      "step": 67
+    },
+    {
+      "epoch": 3.805755395683453,
+      "grad_norm": 0.5580653548240662,
+      "learning_rate": 0.00014,
+      "loss": 0.2825,
+      "step": 68
+    },
+    {
+      "epoch": 3.8633093525179856,
+      "grad_norm": 0.5951279401779175,
+      "learning_rate": 0.00013894736842105264,
+      "loss": 0.2963,
+      "step": 69
+    },
+    {
+      "epoch": 3.920863309352518,
+      "grad_norm": 0.3637178838253021,
+      "learning_rate": 0.00013789473684210527,
+      "loss": 0.1536,
+      "step": 70
+    },
+    {
+      "epoch": 3.9784172661870505,
+      "grad_norm": 0.5208351016044617,
+      "learning_rate": 0.0001368421052631579,
+      "loss": 0.197,
+      "step": 71
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6591724753379822,
+      "learning_rate": 0.00013578947368421055,
+      "loss": 0.2031,
+      "step": 72
+    },
+    {
+      "epoch": 4.057553956834532,
+      "grad_norm": 0.5273791551589966,
+      "learning_rate": 0.00013473684210526317,
+      "loss": 0.1916,
+      "step": 73
+    },
+    {
+      "epoch": 4.115107913669065,
+      "grad_norm": 0.49362239241600037,
+      "learning_rate": 0.0001336842105263158,
+      "loss": 0.1308,
+      "step": 74
+    },
+    {
+      "epoch": 4.172661870503597,
+      "grad_norm": 0.39194148778915405,
+      "learning_rate": 0.00013263157894736842,
+      "loss": 0.1079,
+      "step": 75
+    },
+    {
+      "epoch": 4.23021582733813,
+      "grad_norm": 0.6204246878623962,
+      "learning_rate": 0.00013157894736842108,
+      "loss": 0.1913,
+      "step": 76
+    },
+    {
+      "epoch": 4.287769784172662,
+      "grad_norm": 0.3720596432685852,
+      "learning_rate": 0.0001305263157894737,
+      "loss": 0.12,
+      "step": 77
+    },
+    {
+      "epoch": 4.345323741007194,
+      "grad_norm": 0.5735775828361511,
+      "learning_rate": 0.00012947368421052633,
+      "loss": 0.1184,
+      "step": 78
+    },
+    {
+      "epoch": 4.402877697841727,
+      "grad_norm": 0.6928539872169495,
+      "learning_rate": 0.00012842105263157895,
+      "loss": 0.1654,
+      "step": 79
+    },
+    {
+      "epoch": 4.460431654676259,
+      "grad_norm": 0.7389291524887085,
+      "learning_rate": 0.00012736842105263158,
+      "loss": 0.1942,
+      "step": 80
+    },
+    {
+      "epoch": 4.517985611510792,
+      "grad_norm": 0.4916699528694153,
+      "learning_rate": 0.0001263157894736842,
+      "loss": 0.102,
+      "step": 81
+    },
+    {
+      "epoch": 4.575539568345324,
+      "grad_norm": 0.6677173376083374,
+      "learning_rate": 0.00012526315789473683,
+      "loss": 0.2271,
+      "step": 82
+    },
+    {
+      "epoch": 4.633093525179856,
+      "grad_norm": 0.4940044581890106,
+      "learning_rate": 0.00012421052631578949,
+      "loss": 0.1163,
+      "step": 83
+    },
+    {
+      "epoch": 4.690647482014389,
+      "grad_norm": 0.5350868701934814,
+      "learning_rate": 0.0001231578947368421,
+      "loss": 0.1427,
+      "step": 84
+    },
+    {
+      "epoch": 4.748201438848921,
+      "grad_norm": 0.6581408977508545,
+      "learning_rate": 0.00012210526315789474,
+      "loss": 0.1343,
+      "step": 85
+    },
+    {
+      "epoch": 4.805755395683454,
+      "grad_norm": 0.45714738965034485,
+      "learning_rate": 0.00012105263157894738,
+      "loss": 0.1206,
+      "step": 86
+    },
+    {
+      "epoch": 4.863309352517986,
+      "grad_norm": 0.5649847388267517,
+      "learning_rate": 0.00012,
+      "loss": 0.1647,
+      "step": 87
+    },
+    {
+      "epoch": 4.920863309352518,
+      "grad_norm": 0.7216070294380188,
+      "learning_rate": 0.00011894736842105263,
+      "loss": 0.1509,
+      "step": 88
+    },
+    {
+      "epoch": 4.9784172661870505,
+      "grad_norm": 0.8254823684692383,
+      "learning_rate": 0.00011789473684210525,
+      "loss": 0.2195,
+      "step": 89
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.6784593462944031,
+      "learning_rate": 0.00011684210526315791,
+      "loss": 0.0999,
+      "step": 90
+    },
+    {
+      "epoch": 5.057553956834532,
+      "grad_norm": 0.45816510915756226,
+      "learning_rate": 0.00011578947368421053,
+      "loss": 0.106,
+      "step": 91
+    },
+    {
+      "epoch": 5.115107913669065,
+      "grad_norm": 0.28045934438705444,
+      "learning_rate": 0.00011473684210526316,
+      "loss": 0.0898,
+      "step": 92
+    },
+    {
+      "epoch": 5.172661870503597,
+      "grad_norm": 0.5236830711364746,
+      "learning_rate": 0.0001136842105263158,
+      "loss": 0.1103,
+      "step": 93
+    },
+    {
+      "epoch": 5.23021582733813,
+      "grad_norm": 0.4514773488044739,
+      "learning_rate": 0.00011263157894736843,
+      "loss": 0.0513,
+      "step": 94
+    },
+    {
+      "epoch": 5.287769784172662,
+      "grad_norm": 0.47659534215927124,
+      "learning_rate": 0.00011157894736842105,
+      "loss": 0.1132,
+      "step": 95
+    },
+    {
+      "epoch": 5.345323741007194,
+      "grad_norm": 0.4033092260360718,
+      "learning_rate": 0.0001105263157894737,
+      "loss": 0.0819,
+      "step": 96
+    },
+    {
+      "epoch": 5.402877697841727,
+      "grad_norm": 0.44451287388801575,
+      "learning_rate": 0.00010947368421052633,
+      "loss": 0.094,
+      "step": 97
+    },
+    {
+      "epoch": 5.460431654676259,
+      "grad_norm": 0.5565096735954285,
+      "learning_rate": 0.00010842105263157896,
+      "loss": 0.0954,
+      "step": 98
+    },
+    {
+      "epoch": 5.517985611510792,
+      "grad_norm": 0.6061581969261169,
+      "learning_rate": 0.00010736842105263158,
+      "loss": 0.1524,
+      "step": 99
+    },
+    {
+      "epoch": 5.575539568345324,
+      "grad_norm": 0.6519442796707153,
+      "learning_rate": 0.00010631578947368421,
+      "loss": 0.0963,
+      "step": 100
+    },
+    {
+      "epoch": 5.633093525179856,
+      "grad_norm": 0.6096929907798767,
+      "learning_rate": 0.00010526315789473685,
+      "loss": 0.0947,
+      "step": 101
+    },
+    {
+      "epoch": 5.690647482014389,
+      "grad_norm": 0.5992321372032166,
+      "learning_rate": 0.00010421052631578947,
+      "loss": 0.0849,
+      "step": 102
+    },
+    {
+      "epoch": 5.748201438848921,
+      "grad_norm": 0.6278153657913208,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 0.0771,
+      "step": 103
+    },
+    {
+      "epoch": 5.805755395683454,
+      "grad_norm": 0.8151980042457581,
+      "learning_rate": 0.00010210526315789475,
+      "loss": 0.1253,
+      "step": 104
+    },
+    {
+      "epoch": 5.863309352517986,
+      "grad_norm": 0.3898473381996155,
+      "learning_rate": 0.00010105263157894738,
+      "loss": 0.0488,
+      "step": 105
+    },
+    {
+      "epoch": 5.920863309352518,
+      "grad_norm": 0.4772569537162781,
+      "learning_rate": 0.0001,
+      "loss": 0.0964,
+      "step": 106
+    },
+    {
+      "epoch": 5.9784172661870505,
+      "grad_norm": 0.6889118552207947,
+      "learning_rate": 9.894736842105263e-05,
+      "loss": 0.1749,
+      "step": 107
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.813023030757904,
+      "learning_rate": 9.789473684210527e-05,
+      "loss": 0.0617,
+      "step": 108
+    },
+    {
+      "epoch": 6.057553956834532,
+      "grad_norm": 0.6126425266265869,
+      "learning_rate": 9.68421052631579e-05,
+      "loss": 0.116,
+      "step": 109
+    },
+    {
+      "epoch": 6.115107913669065,
+      "grad_norm": 0.36758872866630554,
+      "learning_rate": 9.578947368421052e-05,
+      "loss": 0.0589,
+      "step": 110
+    },
+    {
+      "epoch": 6.172661870503597,
+      "grad_norm": 0.38784849643707275,
+      "learning_rate": 9.473684210526316e-05,
+      "loss": 0.0833,
+      "step": 111
+    },
+    {
+      "epoch": 6.23021582733813,
+      "grad_norm": 0.3257942795753479,
+      "learning_rate": 9.36842105263158e-05,
+      "loss": 0.0418,
+      "step": 112
+    },
+    {
+      "epoch": 6.287769784172662,
+      "grad_norm": 0.5511656403541565,
+      "learning_rate": 9.263157894736843e-05,
+      "loss": 0.0843,
+      "step": 113
+    },
+    {
+      "epoch": 6.345323741007194,
+      "grad_norm": 0.3442849814891815,
+      "learning_rate": 9.157894736842105e-05,
+      "loss": 0.054,
+      "step": 114
+    },
+    {
+      "epoch": 6.402877697841727,
+      "grad_norm": 0.536539614200592,
+      "learning_rate": 9.052631578947369e-05,
+      "loss": 0.0413,
+      "step": 115
+    },
+    {
+      "epoch": 6.460431654676259,
+      "grad_norm": 0.524313747882843,
+      "learning_rate": 8.947368421052632e-05,
+      "loss": 0.0874,
+      "step": 116
+    },
+    {
+      "epoch": 6.517985611510792,
+      "grad_norm": 0.4178919494152069,
+      "learning_rate": 8.842105263157894e-05,
+      "loss": 0.0542,
+      "step": 117
+    },
+    {
+      "epoch": 6.575539568345324,
+      "grad_norm": 0.6238830089569092,
+      "learning_rate": 8.736842105263158e-05,
+      "loss": 0.1018,
+      "step": 118
+    },
+    {
+      "epoch": 6.633093525179856,
+      "grad_norm": 0.5132068991661072,
+      "learning_rate": 8.631578947368421e-05,
+      "loss": 0.0759,
+      "step": 119
+    },
+    {
+      "epoch": 6.690647482014389,
+      "grad_norm": 0.6828580498695374,
+      "learning_rate": 8.526315789473685e-05,
+      "loss": 0.06,
+      "step": 120
+    },
+    {
+      "epoch": 6.748201438848921,
+      "grad_norm": 0.863381028175354,
+      "learning_rate": 8.421052631578948e-05,
+      "loss": 0.1235,
+      "step": 121
+    },
+    {
+      "epoch": 6.805755395683454,
+      "grad_norm": 0.7518329620361328,
+      "learning_rate": 8.315789473684212e-05,
+      "loss": 0.0487,
+      "step": 122
+    },
+    {
+      "epoch": 6.863309352517986,
+      "grad_norm": 0.7018346190452576,
+      "learning_rate": 8.210526315789474e-05,
+      "loss": 0.0631,
+      "step": 123
+    },
+    {
+      "epoch": 6.920863309352518,
+      "grad_norm": 0.4782824218273163,
+      "learning_rate": 8.105263157894737e-05,
+      "loss": 0.074,
+      "step": 124
+    },
+    {
+      "epoch": 6.9784172661870505,
+      "grad_norm": 0.3680833578109741,
+      "learning_rate": 8e-05,
+      "loss": 0.0397,
+      "step": 125
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.09224724024534225,
+      "learning_rate": 7.894736842105263e-05,
+      "loss": 0.0011,
+      "step": 126
+    },
+    {
+      "epoch": 7.057553956834532,
+      "grad_norm": 0.6668319702148438,
+      "learning_rate": 7.789473684210526e-05,
+      "loss": 0.0708,
+      "step": 127
+    },
+    {
+      "epoch": 7.115107913669065,
+      "grad_norm": 0.28305375576019287,
+      "learning_rate": 7.68421052631579e-05,
+      "loss": 0.0255,
+      "step": 128
+    },
+    {
+      "epoch": 7.172661870503597,
+      "grad_norm": 0.3016341030597687,
+      "learning_rate": 7.578947368421054e-05,
+      "loss": 0.0288,
+      "step": 129
+    },
+    {
+      "epoch": 7.23021582733813,
+      "grad_norm": 0.3837669789791107,
+      "learning_rate": 7.473684210526316e-05,
+      "loss": 0.0434,
+      "step": 130
+    },
+    {
+      "epoch": 7.287769784172662,
+      "grad_norm": 0.37557587027549744,
+      "learning_rate": 7.368421052631579e-05,
+      "loss": 0.0394,
+      "step": 131
+    },
+    {
+      "epoch": 7.345323741007194,
+      "grad_norm": 0.43611082434654236,
+      "learning_rate": 7.263157894736843e-05,
+      "loss": 0.063,
+      "step": 132
+    },
+    {
+      "epoch": 7.402877697841727,
+      "grad_norm": 0.41498398780822754,
+      "learning_rate": 7.157894736842105e-05,
+      "loss": 0.0419,
+      "step": 133
+    },
+    {
+      "epoch": 7.460431654676259,
+      "grad_norm": 0.39031943678855896,
+      "learning_rate": 7.052631578947368e-05,
+      "loss": 0.0507,
+      "step": 134
+    },
+    {
+      "epoch": 7.517985611510792,
+      "grad_norm": 0.371528297662735,
+      "learning_rate": 6.947368421052632e-05,
+      "loss": 0.0805,
+      "step": 135
+    },
+    {
+      "epoch": 7.575539568345324,
+      "grad_norm": 0.4692123532295227,
+      "learning_rate": 6.842105263157895e-05,
+      "loss": 0.0519,
+      "step": 136
+    },
+    {
+      "epoch": 7.633093525179856,
+      "grad_norm": 0.41735348105430603,
+      "learning_rate": 6.736842105263159e-05,
+      "loss": 0.0551,
+      "step": 137
+    },
+    {
+      "epoch": 7.690647482014389,
+      "grad_norm": 0.3480510115623474,
+      "learning_rate": 6.631578947368421e-05,
+      "loss": 0.0215,
+      "step": 138
+    },
+    {
+      "epoch": 7.748201438848921,
+      "grad_norm": 0.6142042875289917,
+      "learning_rate": 6.526315789473685e-05,
+      "loss": 0.059,
+      "step": 139
+    },
+    {
+      "epoch": 7.805755395683454,
+      "grad_norm": 0.5081954598426819,
+      "learning_rate": 6.421052631578948e-05,
+      "loss": 0.0495,
+      "step": 140
+    },
+    {
+      "epoch": 7.863309352517986,
+      "grad_norm": 0.501690685749054,
+      "learning_rate": 6.31578947368421e-05,
+      "loss": 0.07,
+      "step": 141
+    },
+    {
+      "epoch": 7.920863309352518,
+      "grad_norm": 0.4325466454029083,
+      "learning_rate": 6.210526315789474e-05,
+      "loss": 0.0586,
+      "step": 142
+    },
+    {
+      "epoch": 7.9784172661870505,
+      "grad_norm": 0.3772739768028259,
+      "learning_rate": 6.105263157894737e-05,
+      "loss": 0.0344,
+      "step": 143
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.5539509057998657,
+      "learning_rate": 6e-05,
+      "loss": 0.0224,
+      "step": 144
+    },
+    {
+      "epoch": 8.057553956834532,
+      "grad_norm": 0.27673545479774475,
+      "learning_rate": 5.894736842105263e-05,
+      "loss": 0.0302,
+      "step": 145
+    },
+    {
+      "epoch": 8.115107913669064,
+      "grad_norm": 0.2896704375743866,
+      "learning_rate": 5.789473684210527e-05,
+      "loss": 0.0376,
+      "step": 146
+    },
+    {
+      "epoch": 8.172661870503598,
+      "grad_norm": 0.30631378293037415,
+      "learning_rate": 5.68421052631579e-05,
+      "loss": 0.0504,
+      "step": 147
+    },
+    {
+      "epoch": 8.23021582733813,
+      "grad_norm": 0.37479743361473083,
+      "learning_rate": 5.5789473684210526e-05,
+      "loss": 0.042,
+      "step": 148
+    },
+    {
+      "epoch": 8.287769784172662,
+      "grad_norm": 0.2734068036079407,
+      "learning_rate": 5.4736842105263165e-05,
+      "loss": 0.035,
+      "step": 149
+    },
+    {
+      "epoch": 8.345323741007194,
+      "grad_norm": 0.347070574760437,
+      "learning_rate": 5.368421052631579e-05,
+      "loss": 0.0229,
+      "step": 150
+    },
+    {
+      "epoch": 8.402877697841726,
+      "grad_norm": 0.4153132736682892,
+      "learning_rate": 5.2631578947368424e-05,
+      "loss": 0.0314,
+      "step": 151
+    },
+    {
+      "epoch": 8.46043165467626,
+      "grad_norm": 0.40641433000564575,
+      "learning_rate": 5.157894736842106e-05,
+      "loss": 0.0378,
+      "step": 152
+    },
+    {
+      "epoch": 8.517985611510792,
+      "grad_norm": 0.13249178230762482,
+      "learning_rate": 5.052631578947369e-05,
+      "loss": 0.0117,
+      "step": 153
+    },
+    {
+      "epoch": 8.575539568345324,
+      "grad_norm": 0.3464171886444092,
+      "learning_rate": 4.9473684210526315e-05,
+      "loss": 0.0242,
+      "step": 154
+    },
+    {
+      "epoch": 8.633093525179856,
+      "grad_norm": 0.25235357880592346,
+      "learning_rate": 4.842105263157895e-05,
+      "loss": 0.018,
+      "step": 155
+    },
+    {
+      "epoch": 8.690647482014388,
+      "grad_norm": 0.284230500459671,
+      "learning_rate": 4.736842105263158e-05,
+      "loss": 0.0204,
+      "step": 156
+    },
+    {
+      "epoch": 8.748201438848922,
+      "grad_norm": 0.45346125960350037,
+      "learning_rate": 4.6315789473684214e-05,
+      "loss": 0.0324,
+      "step": 157
+    },
+    {
+      "epoch": 8.805755395683454,
+      "grad_norm": 0.4248915910720825,
+      "learning_rate": 4.5263157894736846e-05,
+      "loss": 0.0473,
+      "step": 158
+    },
+    {
+      "epoch": 8.863309352517986,
+      "grad_norm": 0.3843662142753601,
+      "learning_rate": 4.421052631578947e-05,
+      "loss": 0.0338,
+      "step": 159
+    },
+    {
+      "epoch": 8.920863309352518,
+      "grad_norm": 0.31479740142822266,
+      "learning_rate": 4.3157894736842105e-05,
+      "loss": 0.0196,
+      "step": 160
+    },
+    {
+      "epoch": 8.97841726618705,
+      "grad_norm": 0.44000598788261414,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 0.0631,
+      "step": 161
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.6475702524185181,
+      "learning_rate": 4.105263157894737e-05,
+      "loss": 0.0274,
+      "step": 162
+    },
+    {
+      "epoch": 9.057553956834532,
+      "grad_norm": 0.22291642427444458,
+      "learning_rate": 4e-05,
+      "loss": 0.023,
+      "step": 163
+    },
+    {
+      "epoch": 9.115107913669064,
+      "grad_norm": 0.21420802175998688,
+      "learning_rate": 3.894736842105263e-05,
+      "loss": 0.0471,
+      "step": 164
+    },
+    {
+      "epoch": 9.172661870503598,
+      "grad_norm": 0.13398566842079163,
+      "learning_rate": 3.789473684210527e-05,
+      "loss": 0.006,
+      "step": 165
+    },
+    {
+      "epoch": 9.23021582733813,
+      "grad_norm": 0.3127495348453522,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 0.0246,
+      "step": 166
+    },
+    {
+      "epoch": 9.287769784172662,
+      "grad_norm": 0.20528411865234375,
+      "learning_rate": 3.578947368421053e-05,
+      "loss": 0.0155,
+      "step": 167
+    },
+    {
+      "epoch": 9.345323741007194,
+      "grad_norm": 0.36064884066581726,
+      "learning_rate": 3.473684210526316e-05,
+      "loss": 0.0311,
+      "step": 168
+    },
+    {
+      "epoch": 9.402877697841726,
+      "grad_norm": 0.30914369225502014,
+      "learning_rate": 3.368421052631579e-05,
+      "loss": 0.0194,
+      "step": 169
+    },
+    {
+      "epoch": 9.46043165467626,
+      "grad_norm": 0.35021311044692993,
+      "learning_rate": 3.2631578947368426e-05,
+      "loss": 0.0236,
+      "step": 170
+    },
+    {
+      "epoch": 9.517985611510792,
+      "grad_norm": 0.2852305471897125,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 0.0157,
+      "step": 171
+    },
+    {
+      "epoch": 9.575539568345324,
+      "grad_norm": 0.40218594670295715,
+      "learning_rate": 3.0526315789473684e-05,
+      "loss": 0.0205,
+      "step": 172
+    },
+    {
+      "epoch": 9.633093525179856,
+      "grad_norm": 0.2896270751953125,
+      "learning_rate": 2.9473684210526314e-05,
+      "loss": 0.0208,
+      "step": 173
+    },
+    {
+      "epoch": 9.690647482014388,
+      "grad_norm": 0.34825772047042847,
+      "learning_rate": 2.842105263157895e-05,
+      "loss": 0.0264,
+      "step": 174
+    },
+    {
+      "epoch": 9.748201438848922,
+      "grad_norm": 0.3722160756587982,
+      "learning_rate": 2.7368421052631583e-05,
+      "loss": 0.0301,
+      "step": 175
+    },
+    {
+      "epoch": 9.805755395683454,
+      "grad_norm": 0.37555378675460815,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 0.0229,
+      "step": 176
+    },
+    {
+      "epoch": 9.863309352517986,
+      "grad_norm": 0.27715688943862915,
+      "learning_rate": 2.5263157894736845e-05,
+      "loss": 0.0187,
+      "step": 177
+    },
+    {
+      "epoch": 9.920863309352518,
+      "grad_norm": 0.23289476335048676,
+      "learning_rate": 2.4210526315789474e-05,
+      "loss": 0.0149,
+      "step": 178
+    },
+    {
+      "epoch": 9.97841726618705,
+      "grad_norm": 0.36138466000556946,
+      "learning_rate": 2.3157894736842107e-05,
+      "loss": 0.0198,
+      "step": 179
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.3544670045375824,
+      "learning_rate": 2.2105263157894736e-05,
+      "loss": 0.0101,
+      "step": 180
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.365885636890624e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

v5_dagger_model/checkpoint-180/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:969e56a7eae06893debed56d183f82653536b35bc145e8a7e175ba60a2cce302
+size 5944

v5_dagger_model/checkpoint-180/video_preprocessor_config.json

@@ -0,0 +1,45 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "_Unsloth_Patched_Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}

v5_dagger_model/checkpoint-200/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen2.5-vl-7b-instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen2.5-vl-7b-instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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

v5_dagger_model/checkpoint-200/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2_5_VLForConditionalGeneration",
+    "parent_library": "transformers.models.qwen2_5_vl.modeling_qwen2_5_vl",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-vl-7b-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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:qkv|proj|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:qkv|proj|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

v5_dagger_model/checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b8c8d6d82ce21ed20fb5412ef5d433408a355615435f2800946c1b12d44ed5
+size 161539072

v5_dagger_model/checkpoint-200/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

v5_dagger_model/checkpoint-200/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 %}

v5_dagger_model/checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f38b18b87b3cec636b40dec5107691df1d9afe63a533ad176768c5b0bf82e146
+size 82464628

v5_dagger_model/checkpoint-200/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "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
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "_Unsloth_Patched_Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

v5_dagger_model/checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004e07e622390b3ef93cd3c314e8250117d865d4c97d71719da5ef24b150050b
+size 14244

v5_dagger_model/checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
+size 1064

v5_dagger_model/checkpoint-200/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": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

v5_dagger_model/checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741c85ffe434aad73e934a73ef380c85e94cd863b8f55e1a1ad66cacb5a93dfd
+size 11422164

v5_dagger_model/checkpoint-200/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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
+    }
+  },
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "processor_class": "_Unsloth_Patched_Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

v5_dagger_model/checkpoint-200/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.115107913669064,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05755395683453238,
+      "grad_norm": 2.2564826011657715,
+      "learning_rate": 0.0,
+      "loss": 4.8786,
+      "step": 1
+    },
+    {
+      "epoch": 0.11510791366906475,
+      "grad_norm": 2.6304173469543457,
+      "learning_rate": 2e-05,
+      "loss": 5.4851,
+      "step": 2
+    },
+    {
+      "epoch": 0.17266187050359713,
+      "grad_norm": 2.5263326168060303,
+      "learning_rate": 4e-05,
+      "loss": 4.7033,
+      "step": 3
+    },
+    {
+      "epoch": 0.2302158273381295,
+      "grad_norm": 2.3896210193634033,
+      "learning_rate": 6e-05,
+      "loss": 4.6046,
+      "step": 4
+    },
+    {
+      "epoch": 0.28776978417266186,
+      "grad_norm": 2.7547967433929443,
+      "learning_rate": 8e-05,
+      "loss": 4.9866,
+      "step": 5
+    },
+    {
+      "epoch": 0.34532374100719426,
+      "grad_norm": 3.2151615619659424,
+      "learning_rate": 0.0001,
+      "loss": 5.0008,
+      "step": 6
+    },
+    {
+      "epoch": 0.4028776978417266,
+      "grad_norm": 2.4654593467712402,
+      "learning_rate": 0.00012,
+      "loss": 3.7805,
+      "step": 7
+    },
+    {
+      "epoch": 0.460431654676259,
+      "grad_norm": 2.3590445518493652,
+      "learning_rate": 0.00014,
+      "loss": 3.5862,
+      "step": 8
+    },
+    {
+      "epoch": 0.5179856115107914,
+      "grad_norm": 1.6592985391616821,
+      "learning_rate": 0.00016,
+      "loss": 2.8476,
+      "step": 9
+    },
+    {
+      "epoch": 0.5755395683453237,
+      "grad_norm": 1.1599284410476685,
+      "learning_rate": 0.00018,
+      "loss": 2.1064,
+      "step": 10
+    },
+    {
+      "epoch": 0.6330935251798561,
+      "grad_norm": 1.802690029144287,
+      "learning_rate": 0.0002,
+      "loss": 2.4239,
+      "step": 11
+    },
+    {
+      "epoch": 0.6906474820143885,
+      "grad_norm": 1.470718502998352,
+      "learning_rate": 0.00019894736842105264,
+      "loss": 2.1704,
+      "step": 12
+    },
+    {
+      "epoch": 0.7482014388489209,
+      "grad_norm": 2.7104134559631348,
+      "learning_rate": 0.00019789473684210526,
+      "loss": 1.9153,
+      "step": 13
+    },
+    {
+      "epoch": 0.8057553956834532,
+      "grad_norm": 1.823458194732666,
+      "learning_rate": 0.0001968421052631579,
+      "loss": 1.5356,
+      "step": 14
+    },
+    {
+      "epoch": 0.8633093525179856,
+      "grad_norm": 1.5308654308319092,
+      "learning_rate": 0.00019578947368421054,
+      "loss": 1.6719,
+      "step": 15
+    },
+    {
+      "epoch": 0.920863309352518,
+      "grad_norm": 1.1720850467681885,
+      "learning_rate": 0.00019473684210526317,
+      "loss": 1.4082,
+      "step": 16
+    },
+    {
+      "epoch": 0.9784172661870504,
+      "grad_norm": 0.921774685382843,
+      "learning_rate": 0.0001936842105263158,
+      "loss": 1.3164,
+      "step": 17
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0646902322769165,
+      "learning_rate": 0.00019263157894736842,
+      "loss": 1.3508,
+      "step": 18
+    },
+    {
+      "epoch": 1.0575539568345325,
+      "grad_norm": 0.7060080170631409,
+      "learning_rate": 0.00019157894736842104,
+      "loss": 1.1843,
+      "step": 19
+    },
+    {
+      "epoch": 1.1151079136690647,
+      "grad_norm": 0.6636799573898315,
+      "learning_rate": 0.0001905263157894737,
+      "loss": 1.013,
+      "step": 20
+    },
+    {
+      "epoch": 1.1726618705035972,
+      "grad_norm": 0.6766036748886108,
+      "learning_rate": 0.00018947368421052632,
+      "loss": 0.8595,
+      "step": 21
+    },
+    {
+      "epoch": 1.2302158273381294,
+      "grad_norm": 0.5309479832649231,
+      "learning_rate": 0.00018842105263157898,
+      "loss": 0.8741,
+      "step": 22
+    },
+    {
+      "epoch": 1.2877697841726619,
+      "grad_norm": 0.7695677876472473,
+      "learning_rate": 0.0001873684210526316,
+      "loss": 0.9812,
+      "step": 23
+    },
+    {
+      "epoch": 1.3453237410071943,
+      "grad_norm": 0.8244631290435791,
+      "learning_rate": 0.00018631578947368423,
+      "loss": 0.7284,
+      "step": 24
+    },
+    {
+      "epoch": 1.4028776978417266,
+      "grad_norm": 0.7941868305206299,
+      "learning_rate": 0.00018526315789473685,
+      "loss": 0.7796,
+      "step": 25
+    },
+    {
+      "epoch": 1.460431654676259,
+      "grad_norm": 0.5958636999130249,
+      "learning_rate": 0.00018421052631578948,
+      "loss": 0.8259,
+      "step": 26
+    },
+    {
+      "epoch": 1.5179856115107913,
+      "grad_norm": 0.8691028952598572,
+      "learning_rate": 0.0001831578947368421,
+      "loss": 0.6653,
+      "step": 27
+    },
+    {
+      "epoch": 1.5755395683453237,
+      "grad_norm": 0.646342396736145,
+      "learning_rate": 0.00018210526315789476,
+      "loss": 0.6347,
+      "step": 28
+    },
+    {
+      "epoch": 1.6330935251798562,
+      "grad_norm": 0.6964317560195923,
+      "learning_rate": 0.00018105263157894739,
+      "loss": 0.6772,
+      "step": 29
+    },
+    {
+      "epoch": 1.6906474820143886,
+      "grad_norm": 0.6086808443069458,
+      "learning_rate": 0.00018,
+      "loss": 0.6906,
+      "step": 30
+    },
+    {
+      "epoch": 1.7482014388489209,
+      "grad_norm": 0.6074932217597961,
+      "learning_rate": 0.00017894736842105264,
+      "loss": 0.6537,
+      "step": 31
+    },
+    {
+      "epoch": 1.8057553956834531,
+      "grad_norm": 0.539799690246582,
+      "learning_rate": 0.00017789473684210526,
+      "loss": 0.5003,
+      "step": 32
+    },
+    {
+      "epoch": 1.8633093525179856,
+      "grad_norm": 0.5748394727706909,
+      "learning_rate": 0.0001768421052631579,
+      "loss": 0.3782,
+      "step": 33
+    },
+    {
+      "epoch": 1.920863309352518,
+      "grad_norm": 0.5975272059440613,
+      "learning_rate": 0.00017578947368421052,
+      "loss": 0.4689,
+      "step": 34
+    },
+    {
+      "epoch": 1.9784172661870505,
+      "grad_norm": 0.6873601078987122,
+      "learning_rate": 0.00017473684210526317,
+      "loss": 0.5143,
+      "step": 35
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7587007880210876,
+      "learning_rate": 0.0001736842105263158,
+      "loss": 0.3664,
+      "step": 36
+    },
+    {
+      "epoch": 2.0575539568345325,
+      "grad_norm": 0.5641581416130066,
+      "learning_rate": 0.00017263157894736842,
+      "loss": 0.3186,
+      "step": 37
+    },
+    {
+      "epoch": 2.115107913669065,
+      "grad_norm": 0.6975970268249512,
+      "learning_rate": 0.00017157894736842107,
+      "loss": 0.4577,
+      "step": 38
+    },
+    {
+      "epoch": 2.172661870503597,
+      "grad_norm": 0.5590388774871826,
+      "learning_rate": 0.0001705263157894737,
+      "loss": 0.2734,
+      "step": 39
+    },
+    {
+      "epoch": 2.2302158273381294,
+      "grad_norm": 0.5296897292137146,
+      "learning_rate": 0.00016947368421052633,
+      "loss": 0.3938,
+      "step": 40
+    },
+    {
+      "epoch": 2.287769784172662,
+      "grad_norm": 0.44214928150177,
+      "learning_rate": 0.00016842105263157895,
+      "loss": 0.4129,
+      "step": 41
+    },
+    {
+      "epoch": 2.3453237410071943,
+      "grad_norm": 0.5920043587684631,
+      "learning_rate": 0.0001673684210526316,
+      "loss": 0.2301,
+      "step": 42
+    },
+    {
+      "epoch": 2.402877697841727,
+      "grad_norm": 0.5350307822227478,
+      "learning_rate": 0.00016631578947368423,
+      "loss": 0.3897,
+      "step": 43
+    },
+    {
+      "epoch": 2.460431654676259,
+      "grad_norm": 0.5216901898384094,
+      "learning_rate": 0.00016526315789473686,
+      "loss": 0.3855,
+      "step": 44
+    },
+    {
+      "epoch": 2.5179856115107913,
+      "grad_norm": 0.6011196374893188,
+      "learning_rate": 0.00016421052631578948,
+      "loss": 0.3711,
+      "step": 45
+    },
+    {
+      "epoch": 2.5755395683453237,
+      "grad_norm": 0.5409759283065796,
+      "learning_rate": 0.0001631578947368421,
+      "loss": 0.2035,
+      "step": 46
+    },
+    {
+      "epoch": 2.633093525179856,
+      "grad_norm": 0.5009431838989258,
+      "learning_rate": 0.00016210526315789473,
+      "loss": 0.1684,
+      "step": 47
+    },
+    {
+      "epoch": 2.6906474820143886,
+      "grad_norm": 0.6343453526496887,
+      "learning_rate": 0.00016105263157894736,
+      "loss": 0.4425,
+      "step": 48
+    },
+    {
+      "epoch": 2.7482014388489207,
+      "grad_norm": 0.5234959721565247,
+      "learning_rate": 0.00016,
+      "loss": 0.2177,
+      "step": 49
+    },
+    {
+      "epoch": 2.805755395683453,
+      "grad_norm": 0.47029346227645874,
+      "learning_rate": 0.00015894736842105264,
+      "loss": 0.2741,
+      "step": 50
+    },
+    {
+      "epoch": 2.8633093525179856,
+      "grad_norm": 0.5409159064292908,
+      "learning_rate": 0.00015789473684210527,
+      "loss": 0.3455,
+      "step": 51
+    },
+    {
+      "epoch": 2.920863309352518,
+      "grad_norm": 0.5376619696617126,
+      "learning_rate": 0.0001568421052631579,
+      "loss": 0.3439,
+      "step": 52
+    },
+    {
+      "epoch": 2.9784172661870505,
+      "grad_norm": 0.6080886721611023,
+      "learning_rate": 0.00015578947368421052,
+      "loss": 0.3303,
+      "step": 53
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7982627153396606,
+      "learning_rate": 0.00015473684210526317,
+      "loss": 0.3354,
+      "step": 54
+    },
+    {
+      "epoch": 3.0575539568345325,
+      "grad_norm": 0.5055177211761475,
+      "learning_rate": 0.0001536842105263158,
+      "loss": 0.2868,
+      "step": 55
+    },
+    {
+      "epoch": 3.115107913669065,
+      "grad_norm": 0.4262123107910156,
+      "learning_rate": 0.00015263157894736845,
+      "loss": 0.2097,
+      "step": 56
+    },
+    {
+      "epoch": 3.172661870503597,
+      "grad_norm": 0.3976552486419678,
+      "learning_rate": 0.00015157894736842108,
+      "loss": 0.3558,
+      "step": 57
+    },
+    {
+      "epoch": 3.2302158273381294,
+      "grad_norm": 0.46125659346580505,
+      "learning_rate": 0.0001505263157894737,
+      "loss": 0.2219,
+      "step": 58
+    },
+    {
+      "epoch": 3.287769784172662,
+      "grad_norm": 0.4844948649406433,
+      "learning_rate": 0.00014947368421052633,
+      "loss": 0.2234,
+      "step": 59
+    },
+    {
+      "epoch": 3.3453237410071943,
+      "grad_norm": 0.6512012481689453,
+      "learning_rate": 0.00014842105263157895,
+      "loss": 0.274,
+      "step": 60
+    },
+    {
+      "epoch": 3.402877697841727,
+      "grad_norm": 0.5738747715950012,
+      "learning_rate": 0.00014736842105263158,
+      "loss": 0.2676,
+      "step": 61
+    },
+    {
+      "epoch": 3.460431654676259,
+      "grad_norm": 0.5202072858810425,
+      "learning_rate": 0.00014631578947368423,
+      "loss": 0.2553,
+      "step": 62
+    },
+    {
+      "epoch": 3.5179856115107913,
+      "grad_norm": 0.5690760612487793,
+      "learning_rate": 0.00014526315789473686,
+      "loss": 0.1784,
+      "step": 63
+    },
+    {
+      "epoch": 3.5755395683453237,
+      "grad_norm": 0.6203038096427917,
+      "learning_rate": 0.00014421052631578948,
+      "loss": 0.1628,
+      "step": 64
+    },
+    {
+      "epoch": 3.633093525179856,
+      "grad_norm": 0.31157344579696655,
+      "learning_rate": 0.0001431578947368421,
+      "loss": 0.0833,
+      "step": 65
+    },
+    {
+      "epoch": 3.6906474820143886,
+      "grad_norm": 0.34490475058555603,
+      "learning_rate": 0.00014210526315789474,
+      "loss": 0.0886,
+      "step": 66
+    },
+    {
+      "epoch": 3.7482014388489207,
+      "grad_norm": 0.7103127241134644,
+      "learning_rate": 0.00014105263157894736,
+      "loss": 0.2206,
+      "step": 67
+    },
+    {
+      "epoch": 3.805755395683453,
+      "grad_norm": 0.5580653548240662,
+      "learning_rate": 0.00014,
+      "loss": 0.2825,
+      "step": 68
+    },
+    {
+      "epoch": 3.8633093525179856,
+      "grad_norm": 0.5951279401779175,
+      "learning_rate": 0.00013894736842105264,
+      "loss": 0.2963,
+      "step": 69
+    },
+    {
+      "epoch": 3.920863309352518,
+      "grad_norm": 0.3637178838253021,
+      "learning_rate": 0.00013789473684210527,
+      "loss": 0.1536,
+      "step": 70
+    },
+    {
+      "epoch": 3.9784172661870505,
+      "grad_norm": 0.5208351016044617,
+      "learning_rate": 0.0001368421052631579,
+      "loss": 0.197,
+      "step": 71
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6591724753379822,
+      "learning_rate": 0.00013578947368421055,
+      "loss": 0.2031,
+      "step": 72
+    },
+    {
+      "epoch": 4.057553956834532,
+      "grad_norm": 0.5273791551589966,
+      "learning_rate": 0.00013473684210526317,
+      "loss": 0.1916,
+      "step": 73
+    },
+    {
+      "epoch": 4.115107913669065,
+      "grad_norm": 0.49362239241600037,
+      "learning_rate": 0.0001336842105263158,
+      "loss": 0.1308,
+      "step": 74
+    },
+    {
+      "epoch": 4.172661870503597,
+      "grad_norm": 0.39194148778915405,
+      "learning_rate": 0.00013263157894736842,
+      "loss": 0.1079,
+      "step": 75
+    },
+    {
+      "epoch": 4.23021582733813,
+      "grad_norm": 0.6204246878623962,
+      "learning_rate": 0.00013157894736842108,
+      "loss": 0.1913,
+      "step": 76
+    },
+    {
+      "epoch": 4.287769784172662,
+      "grad_norm": 0.3720596432685852,
+      "learning_rate": 0.0001305263157894737,
+      "loss": 0.12,
+      "step": 77
+    },
+    {
+      "epoch": 4.345323741007194,
+      "grad_norm": 0.5735775828361511,
+      "learning_rate": 0.00012947368421052633,
+      "loss": 0.1184,
+      "step": 78
+    },
+    {
+      "epoch": 4.402877697841727,
+      "grad_norm": 0.6928539872169495,
+      "learning_rate": 0.00012842105263157895,
+      "loss": 0.1654,
+      "step": 79
+    },
+    {
+      "epoch": 4.460431654676259,
+      "grad_norm": 0.7389291524887085,
+      "learning_rate": 0.00012736842105263158,
+      "loss": 0.1942,
+      "step": 80
+    },
+    {
+      "epoch": 4.517985611510792,
+      "grad_norm": 0.4916699528694153,
+      "learning_rate": 0.0001263157894736842,
+      "loss": 0.102,
+      "step": 81
+    },
+    {
+      "epoch": 4.575539568345324,
+      "grad_norm": 0.6677173376083374,
+      "learning_rate": 0.00012526315789473683,
+      "loss": 0.2271,
+      "step": 82
+    },
+    {
+      "epoch": 4.633093525179856,
+      "grad_norm": 0.4940044581890106,
+      "learning_rate": 0.00012421052631578949,
+      "loss": 0.1163,
+      "step": 83
+    },
+    {
+      "epoch": 4.690647482014389,
+      "grad_norm": 0.5350868701934814,
+      "learning_rate": 0.0001231578947368421,
+      "loss": 0.1427,
+      "step": 84
+    },
+    {
+      "epoch": 4.748201438848921,
+      "grad_norm": 0.6581408977508545,
+      "learning_rate": 0.00012210526315789474,
+      "loss": 0.1343,
+      "step": 85
+    },
+    {
+      "epoch": 4.805755395683454,
+      "grad_norm": 0.45714738965034485,
+      "learning_rate": 0.00012105263157894738,
+      "loss": 0.1206,
+      "step": 86
+    },
+    {
+      "epoch": 4.863309352517986,
+      "grad_norm": 0.5649847388267517,
+      "learning_rate": 0.00012,
+      "loss": 0.1647,
+      "step": 87
+    },
+    {
+      "epoch": 4.920863309352518,
+      "grad_norm": 0.7216070294380188,
+      "learning_rate": 0.00011894736842105263,
+      "loss": 0.1509,
+      "step": 88
+    },
+    {
+      "epoch": 4.9784172661870505,
+      "grad_norm": 0.8254823684692383,
+      "learning_rate": 0.00011789473684210525,
+      "loss": 0.2195,
+      "step": 89
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.6784593462944031,
+      "learning_rate": 0.00011684210526315791,
+      "loss": 0.0999,
+      "step": 90
+    },
+    {
+      "epoch": 5.057553956834532,
+      "grad_norm": 0.45816510915756226,
+      "learning_rate": 0.00011578947368421053,
+      "loss": 0.106,
+      "step": 91
+    },
+    {
+      "epoch": 5.115107913669065,
+      "grad_norm": 0.28045934438705444,
+      "learning_rate": 0.00011473684210526316,
+      "loss": 0.0898,
+      "step": 92
+    },
+    {
+      "epoch": 5.172661870503597,
+      "grad_norm": 0.5236830711364746,
+      "learning_rate": 0.0001136842105263158,
+      "loss": 0.1103,
+      "step": 93
+    },
+    {
+      "epoch": 5.23021582733813,
+      "grad_norm": 0.4514773488044739,
+      "learning_rate": 0.00011263157894736843,
+      "loss": 0.0513,
+      "step": 94
+    },
+    {
+      "epoch": 5.287769784172662,
+      "grad_norm": 0.47659534215927124,
+      "learning_rate": 0.00011157894736842105,
+      "loss": 0.1132,
+      "step": 95
+    },
+    {
+      "epoch": 5.345323741007194,
+      "grad_norm": 0.4033092260360718,
+      "learning_rate": 0.0001105263157894737,
+      "loss": 0.0819,
+      "step": 96
+    },
+    {
+      "epoch": 5.402877697841727,
+      "grad_norm": 0.44451287388801575,
+      "learning_rate": 0.00010947368421052633,
+      "loss": 0.094,
+      "step": 97
+    },
+    {
+      "epoch": 5.460431654676259,
+      "grad_norm": 0.5565096735954285,
+      "learning_rate": 0.00010842105263157896,
+      "loss": 0.0954,
+      "step": 98
+    },
+    {
+      "epoch": 5.517985611510792,
+      "grad_norm": 0.6061581969261169,
+      "learning_rate": 0.00010736842105263158,
+      "loss": 0.1524,
+      "step": 99
+    },
+    {
+      "epoch": 5.575539568345324,
+      "grad_norm": 0.6519442796707153,
+      "learning_rate": 0.00010631578947368421,
+      "loss": 0.0963,
+      "step": 100
+    },
+    {
+      "epoch": 5.633093525179856,
+      "grad_norm": 0.6096929907798767,
+      "learning_rate": 0.00010526315789473685,
+      "loss": 0.0947,
+      "step": 101
+    },
+    {
+      "epoch": 5.690647482014389,
+      "grad_norm": 0.5992321372032166,
+      "learning_rate": 0.00010421052631578947,
+      "loss": 0.0849,
+      "step": 102
+    },
+    {
+      "epoch": 5.748201438848921,
+      "grad_norm": 0.6278153657913208,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 0.0771,
+      "step": 103
+    },
+    {
+      "epoch": 5.805755395683454,
+      "grad_norm": 0.8151980042457581,
+      "learning_rate": 0.00010210526315789475,
+      "loss": 0.1253,
+      "step": 104
+    },
+    {
+      "epoch": 5.863309352517986,
+      "grad_norm": 0.3898473381996155,
+      "learning_rate": 0.00010105263157894738,
+      "loss": 0.0488,
+      "step": 105
+    },
+    {
+      "epoch": 5.920863309352518,
+      "grad_norm": 0.4772569537162781,
+      "learning_rate": 0.0001,
+      "loss": 0.0964,
+      "step": 106
+    },
+    {
+      "epoch": 5.9784172661870505,
+      "grad_norm": 0.6889118552207947,
+      "learning_rate": 9.894736842105263e-05,
+      "loss": 0.1749,
+      "step": 107
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.813023030757904,
+      "learning_rate": 9.789473684210527e-05,
+      "loss": 0.0617,
+      "step": 108
+    },
+    {
+      "epoch": 6.057553956834532,
+      "grad_norm": 0.6126425266265869,
+      "learning_rate": 9.68421052631579e-05,
+      "loss": 0.116,
+      "step": 109
+    },
+    {
+      "epoch": 6.115107913669065,
+      "grad_norm": 0.36758872866630554,
+      "learning_rate": 9.578947368421052e-05,
+      "loss": 0.0589,
+      "step": 110
+    },
+    {
+      "epoch": 6.172661870503597,
+      "grad_norm": 0.38784849643707275,
+      "learning_rate": 9.473684210526316e-05,
+      "loss": 0.0833,
+      "step": 111
+    },
+    {
+      "epoch": 6.23021582733813,
+      "grad_norm": 0.3257942795753479,
+      "learning_rate": 9.36842105263158e-05,
+      "loss": 0.0418,
+      "step": 112
+    },
+    {
+      "epoch": 6.287769784172662,
+      "grad_norm": 0.5511656403541565,
+      "learning_rate": 9.263157894736843e-05,
+      "loss": 0.0843,
+      "step": 113
+    },
+    {
+      "epoch": 6.345323741007194,
+      "grad_norm": 0.3442849814891815,
+      "learning_rate": 9.157894736842105e-05,
+      "loss": 0.054,
+      "step": 114
+    },
+    {
+      "epoch": 6.402877697841727,
+      "grad_norm": 0.536539614200592,
+      "learning_rate": 9.052631578947369e-05,
+      "loss": 0.0413,
+      "step": 115
+    },
+    {
+      "epoch": 6.460431654676259,
+      "grad_norm": 0.524313747882843,
+      "learning_rate": 8.947368421052632e-05,
+      "loss": 0.0874,
+      "step": 116
+    },
+    {
+      "epoch": 6.517985611510792,
+      "grad_norm": 0.4178919494152069,
+      "learning_rate": 8.842105263157894e-05,
+      "loss": 0.0542,
+      "step": 117
+    },
+    {
+      "epoch": 6.575539568345324,
+      "grad_norm": 0.6238830089569092,
+      "learning_rate": 8.736842105263158e-05,
+      "loss": 0.1018,
+      "step": 118
+    },
+    {
+      "epoch": 6.633093525179856,
+      "grad_norm": 0.5132068991661072,
+      "learning_rate": 8.631578947368421e-05,
+      "loss": 0.0759,
+      "step": 119
+    },
+    {
+      "epoch": 6.690647482014389,
+      "grad_norm": 0.6828580498695374,
+      "learning_rate": 8.526315789473685e-05,
+      "loss": 0.06,
+      "step": 120
+    },
+    {
+      "epoch": 6.748201438848921,
+      "grad_norm": 0.863381028175354,
+      "learning_rate": 8.421052631578948e-05,
+      "loss": 0.1235,
+      "step": 121
+    },
+    {
+      "epoch": 6.805755395683454,
+      "grad_norm": 0.7518329620361328,
+      "learning_rate": 8.315789473684212e-05,
+      "loss": 0.0487,
+      "step": 122
+    },
+    {
+      "epoch": 6.863309352517986,
+      "grad_norm": 0.7018346190452576,
+      "learning_rate": 8.210526315789474e-05,
+      "loss": 0.0631,
+      "step": 123
+    },
+    {
+      "epoch": 6.920863309352518,
+      "grad_norm": 0.4782824218273163,
+      "learning_rate": 8.105263157894737e-05,
+      "loss": 0.074,
+      "step": 124
+    },
+    {
+      "epoch": 6.9784172661870505,
+      "grad_norm": 0.3680833578109741,
+      "learning_rate": 8e-05,
+      "loss": 0.0397,
+      "step": 125
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.09224724024534225,
+      "learning_rate": 7.894736842105263e-05,
+      "loss": 0.0011,
+      "step": 126
+    },
+    {
+      "epoch": 7.057553956834532,
+      "grad_norm": 0.6668319702148438,
+      "learning_rate": 7.789473684210526e-05,
+      "loss": 0.0708,
+      "step": 127
+    },
+    {
+      "epoch": 7.115107913669065,
+      "grad_norm": 0.28305375576019287,
+      "learning_rate": 7.68421052631579e-05,
+      "loss": 0.0255,
+      "step": 128
+    },
+    {
+      "epoch": 7.172661870503597,
+      "grad_norm": 0.3016341030597687,
+      "learning_rate": 7.578947368421054e-05,
+      "loss": 0.0288,
+      "step": 129
+    },
+    {
+      "epoch": 7.23021582733813,
+      "grad_norm": 0.3837669789791107,
+      "learning_rate": 7.473684210526316e-05,
+      "loss": 0.0434,
+      "step": 130
+    },
+    {
+      "epoch": 7.287769784172662,
+      "grad_norm": 0.37557587027549744,
+      "learning_rate": 7.368421052631579e-05,
+      "loss": 0.0394,
+      "step": 131
+    },
+    {
+      "epoch": 7.345323741007194,
+      "grad_norm": 0.43611082434654236,
+      "learning_rate": 7.263157894736843e-05,
+      "loss": 0.063,
+      "step": 132
+    },
+    {
+      "epoch": 7.402877697841727,
+      "grad_norm": 0.41498398780822754,
+      "learning_rate": 7.157894736842105e-05,
+      "loss": 0.0419,
+      "step": 133
+    },
+    {
+      "epoch": 7.460431654676259,
+      "grad_norm": 0.39031943678855896,
+      "learning_rate": 7.052631578947368e-05,
+      "loss": 0.0507,
+      "step": 134
+    },
+    {
+      "epoch": 7.517985611510792,
+      "grad_norm": 0.371528297662735,
+      "learning_rate": 6.947368421052632e-05,
+      "loss": 0.0805,
+      "step": 135
+    },
+    {
+      "epoch": 7.575539568345324,
+      "grad_norm": 0.4692123532295227,
+      "learning_rate": 6.842105263157895e-05,
+      "loss": 0.0519,
+      "step": 136
+    },
+    {
+      "epoch": 7.633093525179856,
+      "grad_norm": 0.41735348105430603,
+      "learning_rate": 6.736842105263159e-05,
+      "loss": 0.0551,
+      "step": 137
+    },
+    {
+      "epoch": 7.690647482014389,
+      "grad_norm": 0.3480510115623474,
+      "learning_rate": 6.631578947368421e-05,
+      "loss": 0.0215,
+      "step": 138
+    },
+    {
+      "epoch": 7.748201438848921,
+      "grad_norm": 0.6142042875289917,
+      "learning_rate": 6.526315789473685e-05,
+      "loss": 0.059,
+      "step": 139
+    },
+    {
+      "epoch": 7.805755395683454,
+      "grad_norm": 0.5081954598426819,
+      "learning_rate": 6.421052631578948e-05,
+      "loss": 0.0495,
+      "step": 140
+    },
+    {
+      "epoch": 7.863309352517986,
+      "grad_norm": 0.501690685749054,
+      "learning_rate": 6.31578947368421e-05,
+      "loss": 0.07,
+      "step": 141
+    },
+    {
+      "epoch": 7.920863309352518,
+      "grad_norm": 0.4325466454029083,
+      "learning_rate": 6.210526315789474e-05,
+      "loss": 0.0586,
+      "step": 142
+    },
+    {
+      "epoch": 7.9784172661870505,
+      "grad_norm": 0.3772739768028259,
+      "learning_rate": 6.105263157894737e-05,
+      "loss": 0.0344,
+      "step": 143
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.5539509057998657,
+      "learning_rate": 6e-05,
+      "loss": 0.0224,
+      "step": 144
+    },
+    {
+      "epoch": 8.057553956834532,
+      "grad_norm": 0.27673545479774475,
+      "learning_rate": 5.894736842105263e-05,
+      "loss": 0.0302,
+      "step": 145
+    },
+    {
+      "epoch": 8.115107913669064,
+      "grad_norm": 0.2896704375743866,
+      "learning_rate": 5.789473684210527e-05,
+      "loss": 0.0376,
+      "step": 146
+    },
+    {
+      "epoch": 8.172661870503598,
+      "grad_norm": 0.30631378293037415,
+      "learning_rate": 5.68421052631579e-05,
+      "loss": 0.0504,
+      "step": 147
+    },
+    {
+      "epoch": 8.23021582733813,
+      "grad_norm": 0.37479743361473083,
+      "learning_rate": 5.5789473684210526e-05,
+      "loss": 0.042,
+      "step": 148
+    },
+    {
+      "epoch": 8.287769784172662,
+      "grad_norm": 0.2734068036079407,
+      "learning_rate": 5.4736842105263165e-05,
+      "loss": 0.035,
+      "step": 149
+    },
+    {
+      "epoch": 8.345323741007194,
+      "grad_norm": 0.347070574760437,
+      "learning_rate": 5.368421052631579e-05,
+      "loss": 0.0229,
+      "step": 150
+    },
+    {
+      "epoch": 8.402877697841726,
+      "grad_norm": 0.4153132736682892,
+      "learning_rate": 5.2631578947368424e-05,
+      "loss": 0.0314,
+      "step": 151
+    },
+    {
+      "epoch": 8.46043165467626,
+      "grad_norm": 0.40641433000564575,
+      "learning_rate": 5.157894736842106e-05,
+      "loss": 0.0378,
+      "step": 152
+    },
+    {
+      "epoch": 8.517985611510792,
+      "grad_norm": 0.13249178230762482,
+      "learning_rate": 5.052631578947369e-05,
+      "loss": 0.0117,
+      "step": 153
+    },
+    {
+      "epoch": 8.575539568345324,
+      "grad_norm": 0.3464171886444092,
+      "learning_rate": 4.9473684210526315e-05,
+      "loss": 0.0242,
+      "step": 154
+    },
+    {
+      "epoch": 8.633093525179856,
+      "grad_norm": 0.25235357880592346,
+      "learning_rate": 4.842105263157895e-05,
+      "loss": 0.018,
+      "step": 155
+    },
+    {
+      "epoch": 8.690647482014388,
+      "grad_norm": 0.284230500459671,
+      "learning_rate": 4.736842105263158e-05,
+      "loss": 0.0204,
+      "step": 156
+    },
+    {
+      "epoch": 8.748201438848922,
+      "grad_norm": 0.45346125960350037,
+      "learning_rate": 4.6315789473684214e-05,
+      "loss": 0.0324,
+      "step": 157
+    },
+    {
+      "epoch": 8.805755395683454,
+      "grad_norm": 0.4248915910720825,
+      "learning_rate": 4.5263157894736846e-05,
+      "loss": 0.0473,
+      "step": 158
+    },
+    {
+      "epoch": 8.863309352517986,
+      "grad_norm": 0.3843662142753601,
+      "learning_rate": 4.421052631578947e-05,
+      "loss": 0.0338,
+      "step": 159
+    },
+    {
+      "epoch": 8.920863309352518,
+      "grad_norm": 0.31479740142822266,
+      "learning_rate": 4.3157894736842105e-05,
+      "loss": 0.0196,
+      "step": 160
+    },
+    {
+      "epoch": 8.97841726618705,
+      "grad_norm": 0.44000598788261414,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 0.0631,
+      "step": 161
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.6475702524185181,
+      "learning_rate": 4.105263157894737e-05,
+      "loss": 0.0274,
+      "step": 162
+    },
+    {
+      "epoch": 9.057553956834532,
+      "grad_norm": 0.22291642427444458,
+      "learning_rate": 4e-05,
+      "loss": 0.023,
+      "step": 163
+    },
+    {
+      "epoch": 9.115107913669064,
+      "grad_norm": 0.21420802175998688,
+      "learning_rate": 3.894736842105263e-05,
+      "loss": 0.0471,
+      "step": 164
+    },
+    {
+      "epoch": 9.172661870503598,
+      "grad_norm": 0.13398566842079163,
+      "learning_rate": 3.789473684210527e-05,
+      "loss": 0.006,
+      "step": 165
+    },
+    {
+      "epoch": 9.23021582733813,
+      "grad_norm": 0.3127495348453522,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 0.0246,
+      "step": 166
+    },
+    {
+      "epoch": 9.287769784172662,
+      "grad_norm": 0.20528411865234375,
+      "learning_rate": 3.578947368421053e-05,
+      "loss": 0.0155,
+      "step": 167
+    },
+    {
+      "epoch": 9.345323741007194,
+      "grad_norm": 0.36064884066581726,
+      "learning_rate": 3.473684210526316e-05,
+      "loss": 0.0311,
+      "step": 168
+    },
+    {
+      "epoch": 9.402877697841726,
+      "grad_norm": 0.30914369225502014,
+      "learning_rate": 3.368421052631579e-05,
+      "loss": 0.0194,
+      "step": 169
+    },
+    {
+      "epoch": 9.46043165467626,
+      "grad_norm": 0.35021311044692993,
+      "learning_rate": 3.2631578947368426e-05,
+      "loss": 0.0236,
+      "step": 170
+    },
+    {
+      "epoch": 9.517985611510792,
+      "grad_norm": 0.2852305471897125,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 0.0157,
+      "step": 171
+    },
+    {
+      "epoch": 9.575539568345324,
+      "grad_norm": 0.40218594670295715,
+      "learning_rate": 3.0526315789473684e-05,
+      "loss": 0.0205,
+      "step": 172
+    },
+    {
+      "epoch": 9.633093525179856,
+      "grad_norm": 0.2896270751953125,
+      "learning_rate": 2.9473684210526314e-05,
+      "loss": 0.0208,
+      "step": 173
+    },
+    {
+      "epoch": 9.690647482014388,
+      "grad_norm": 0.34825772047042847,
+      "learning_rate": 2.842105263157895e-05,
+      "loss": 0.0264,
+      "step": 174
+    },
+    {
+      "epoch": 9.748201438848922,
+      "grad_norm": 0.3722160756587982,
+      "learning_rate": 2.7368421052631583e-05,
+      "loss": 0.0301,
+      "step": 175
+    },
+    {
+      "epoch": 9.805755395683454,
+      "grad_norm": 0.37555378675460815,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 0.0229,
+      "step": 176
+    },
+    {
+      "epoch": 9.863309352517986,
+      "grad_norm": 0.27715688943862915,
+      "learning_rate": 2.5263157894736845e-05,
+      "loss": 0.0187,
+      "step": 177
+    },
+    {
+      "epoch": 9.920863309352518,
+      "grad_norm": 0.23289476335048676,
+      "learning_rate": 2.4210526315789474e-05,
+      "loss": 0.0149,
+      "step": 178
+    },
+    {
+      "epoch": 9.97841726618705,
+      "grad_norm": 0.36138466000556946,
+      "learning_rate": 2.3157894736842107e-05,
+      "loss": 0.0198,
+      "step": 179
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.3544670045375824,
+      "learning_rate": 2.2105263157894736e-05,
+      "loss": 0.0101,
+      "step": 180
+    },
+    {
+      "epoch": 10.057553956834532,
+      "grad_norm": 0.262861967086792,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 0.0224,
+      "step": 181
+    },
+    {
+      "epoch": 10.115107913669064,
+      "grad_norm": 0.2020009309053421,
+      "learning_rate": 2e-05,
+      "loss": 0.0069,
+      "step": 182
+    },
+    {
+      "epoch": 10.172661870503598,
+      "grad_norm": 0.1618271917104721,
+      "learning_rate": 1.8947368421052634e-05,
+      "loss": 0.0089,
+      "step": 183
+    },
+    {
+      "epoch": 10.23021582733813,
+      "grad_norm": 0.27916064858436584,
+      "learning_rate": 1.7894736842105264e-05,
+      "loss": 0.0396,
+      "step": 184
+    },
+    {
+      "epoch": 10.287769784172662,
+      "grad_norm": 0.3328520953655243,
+      "learning_rate": 1.6842105263157896e-05,
+      "loss": 0.0145,
+      "step": 185
+    },
+    {
+      "epoch": 10.345323741007194,
+      "grad_norm": 0.283782035112381,
+      "learning_rate": 1.5789473684210526e-05,
+      "loss": 0.0191,
+      "step": 186
+    },
+    {
+      "epoch": 10.402877697841726,
+      "grad_norm": 0.26925837993621826,
+      "learning_rate": 1.4736842105263157e-05,
+      "loss": 0.025,
+      "step": 187
+    },
+    {
+      "epoch": 10.46043165467626,
+      "grad_norm": 0.17918215692043304,
+      "learning_rate": 1.3684210526315791e-05,
+      "loss": 0.0087,
+      "step": 188
+    },
+    {
+      "epoch": 10.517985611510792,
+      "grad_norm": 0.18995825946331024,
+      "learning_rate": 1.2631578947368422e-05,
+      "loss": 0.0121,
+      "step": 189
+    },
+    {
+      "epoch": 10.575539568345324,
+      "grad_norm": 0.21823520958423615,
+      "learning_rate": 1.1578947368421053e-05,
+      "loss": 0.0085,
+      "step": 190
+    },
+    {
+      "epoch": 10.633093525179856,
+      "grad_norm": 0.1712862104177475,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.0073,
+      "step": 191
+    },
+    {
+      "epoch": 10.690647482014388,
+      "grad_norm": 0.37750497460365295,
+      "learning_rate": 9.473684210526317e-06,
+      "loss": 0.0261,
+      "step": 192
+    },
+    {
+      "epoch": 10.748201438848922,
+      "grad_norm": 0.1838180422782898,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 0.009,
+      "step": 193
+    },
+    {
+      "epoch": 10.805755395683454,
+      "grad_norm": 0.2149781882762909,
+      "learning_rate": 7.3684210526315784e-06,
+      "loss": 0.0157,
+      "step": 194
+    },
+    {
+      "epoch": 10.863309352517986,
+      "grad_norm": 0.2131088376045227,
+      "learning_rate": 6.315789473684211e-06,
+      "loss": 0.0162,
+      "step": 195
+    },
+    {
+      "epoch": 10.920863309352518,
+      "grad_norm": 0.19945627450942993,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 0.0108,
+      "step": 196
+    },
+    {
+      "epoch": 10.97841726618705,
+      "grad_norm": 0.19360119104385376,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 0.0074,
+      "step": 197
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.4595318138599396,
+      "learning_rate": 3.1578947368421056e-06,
+      "loss": 0.0166,
+      "step": 198
+    },
+    {
+      "epoch": 11.057553956834532,
+      "grad_norm": 0.141096830368042,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 0.0084,
+      "step": 199
+    },
+    {
+      "epoch": 11.115107913669064,
+      "grad_norm": 0.16863495111465454,
+      "learning_rate": 1.0526315789473685e-06,
+      "loss": 0.0067,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.632696083700531e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

v5_dagger_model/checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:969e56a7eae06893debed56d183f82653536b35bc145e8a7e175ba60a2cce302
+size 5944

v5_dagger_model/checkpoint-200/video_preprocessor_config.json

@@ -0,0 +1,45 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "_Unsloth_Patched_Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}

v5_dagger_model/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "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
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "_Unsloth_Patched_Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

v5_dagger_model/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": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

v5_dagger_model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741c85ffe434aad73e934a73ef380c85e94cd863b8f55e1a1ad66cacb5a93dfd
+size 11422164

v5_dagger_model/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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
+    }
+  },
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "processor_class": "_Unsloth_Patched_Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

v5_dagger_model/video_preprocessor_config.json

@@ -0,0 +1,45 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "_Unsloth_Patched_Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}