Upload Qwen2-VL weather satellite DoRA adapter

.gitattributes

@@ -33,3 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-294/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+base_model: Qwen/Qwen2-VL-7B-Instruct
+library_name: peft
+model_name: dora_weather_model
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for dora_weather_model
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-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
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/azdinsahir11-university-mohamed-v/qwen2vl-dora-weather/runs/4jvr2049) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.16.0
+- TRL: 0.19.1
+- Transformers: 4.53.2
+- Pytorch: 2.6.0+cu124
+- Datasets: 4.0.0
+- Tokenizers: 0.21.2
+
+## 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}}
+}
+```

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "use_qalora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ae0566adc584bf3f8101d856bbc3bbcdb391abb4e9b4971879f6fee926e0b2a
+size 41338272

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

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 %}

checkpoint-100/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2-VL-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.16.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:890f4369a570b5bd11475b67c9d19ea464f8c393e2484aa8608f99a95abed036
+size 41338272

checkpoint-100/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-100/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 %}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d35e69e91b29c6193390436df653aedbea546e0ffed119da353ac344163f696
+size 82856258

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb249db3ae450805114647bca32d2fe321ec7bb09f3a40ea4e26478fff9cfc7d
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9721d5ba1fb05d41f214a5bebb8206b88b746e805209d13e654bce65e0ffa08
+size 1064

checkpoint-100/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "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
+    }
+  },
+  "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": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_global_step": 100,
+  "best_metric": 0.22464126348495483,
+  "best_model_checkpoint": "./dora_weather_model/checkpoint-100",
+  "epoch": 1.0205655526992288,
+  "eval_steps": 25,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 18.158021926879883,
+      "learning_rate": 0.0001,
+      "loss": 12.1979,
+      "mean_token_accuracy": 0.615905399620533,
+      "num_tokens": 171254.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 7.034078598022461,
+      "learning_rate": 0.0001,
+      "loss": 4.2501,
+      "mean_token_accuracy": 0.8467875950038433,
+      "num_tokens": 342816.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "eval_loss": 0.3218275308609009,
+      "eval_mean_token_accuracy": 0.9006080529628656,
+      "eval_num_tokens": 428469.0,
+      "eval_runtime": 133.9929,
+      "eval_samples_per_second": 1.455,
+      "eval_steps_per_second": 1.455,
+      "step": 25
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 7.133749008178711,
+      "learning_rate": 0.0001,
+      "loss": 2.5798,
+      "mean_token_accuracy": 0.8995884403586387,
+      "num_tokens": 514067.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 5.986148834228516,
+      "learning_rate": 0.0001,
+      "loss": 2.2895,
+      "mean_token_accuracy": 0.9077658534049988,
+      "num_tokens": 685570.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 5.834242343902588,
+      "learning_rate": 0.0001,
+      "loss": 2.0929,
+      "mean_token_accuracy": 0.9145211182534695,
+      "num_tokens": 856740.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "eval_loss": 0.25579357147216797,
+      "eval_mean_token_accuracy": 0.9177517074805039,
+      "eval_num_tokens": 856740.0,
+      "eval_runtime": 133.8597,
+      "eval_samples_per_second": 1.457,
+      "eval_steps_per_second": 1.457,
+      "step": 50
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 5.7353739738464355,
+      "learning_rate": 0.0001,
+      "loss": 2.1152,
+      "mean_token_accuracy": 0.9142912536859512,
+      "num_tokens": 1028000.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 5.386626720428467,
+      "learning_rate": 0.0001,
+      "loss": 1.9346,
+      "mean_token_accuracy": 0.9206269770860672,
+      "num_tokens": 1199650.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "eval_loss": 0.23230257630348206,
+      "eval_mean_token_accuracy": 0.9229834336500902,
+      "eval_num_tokens": 1285076.0,
+      "eval_runtime": 133.8858,
+      "eval_samples_per_second": 1.456,
+      "eval_steps_per_second": 1.456,
+      "step": 75
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 5.34901237487793,
+      "learning_rate": 0.0001,
+      "loss": 1.8041,
+      "mean_token_accuracy": 0.9239558480679989,
+      "num_tokens": 1370524.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 5.087592601776123,
+      "learning_rate": 0.0001,
+      "loss": 1.8039,
+      "mean_token_accuracy": 0.9247349828481675,
+      "num_tokens": 1542159.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 5.261311054229736,
+      "learning_rate": 0.0001,
+      "loss": 1.6074,
+      "mean_token_accuracy": 0.9265569303486798,
+      "num_tokens": 1700574.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "eval_loss": 0.22464126348495483,
+      "eval_mean_token_accuracy": 0.9246747863598359,
+      "eval_num_tokens": 1700574.0,
+      "eval_runtime": 133.7804,
+      "eval_samples_per_second": 1.458,
+      "eval_steps_per_second": 1.458,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 294,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.914505570735104e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e3dc8a742175f8c36087d59cc03fe76f544e4a592cf9bbf2020761587cf8e8
+size 5752

checkpoint-150/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2-VL-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.16.0

checkpoint-150/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa6f62cc9b62b0d620a283bea8f19a37252b0c595824057503bb1baf3f0d0fa
+size 41338272

checkpoint-150/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-150/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 %}

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd1efdea984301a883e57924aca93d0f5c615f9cb303bf64a677ccfae43e49e
+size 82856258

checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a678c19a8a3d1225523b7256cf228029f9576bce9458a5f8635efdce9a4768c5
+size 14244

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa625c3d289d110f65fab1387b954cea711ff0d79423e66f88e963a9e2a838b7
+size 1064

checkpoint-150/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-150/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

checkpoint-150/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "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
+    }
+  },
+  "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": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-150/trainer_state.json

@@ -0,0 +1,229 @@
+{
+  "best_global_step": 150,
+  "best_metric": 0.21437418460845947,
+  "best_model_checkpoint": "./dora_weather_model/checkpoint-150",
+  "epoch": 1.5347043701799485,
+  "eval_steps": 25,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 18.158021926879883,
+      "learning_rate": 0.0001,
+      "loss": 12.1979,
+      "mean_token_accuracy": 0.615905399620533,
+      "num_tokens": 171254.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 7.034078598022461,
+      "learning_rate": 0.0001,
+      "loss": 4.2501,
+      "mean_token_accuracy": 0.8467875950038433,
+      "num_tokens": 342816.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "eval_loss": 0.3218275308609009,
+      "eval_mean_token_accuracy": 0.9006080529628656,
+      "eval_num_tokens": 428469.0,
+      "eval_runtime": 133.9929,
+      "eval_samples_per_second": 1.455,
+      "eval_steps_per_second": 1.455,
+      "step": 25
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 7.133749008178711,
+      "learning_rate": 0.0001,
+      "loss": 2.5798,
+      "mean_token_accuracy": 0.8995884403586387,
+      "num_tokens": 514067.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 5.986148834228516,
+      "learning_rate": 0.0001,
+      "loss": 2.2895,
+      "mean_token_accuracy": 0.9077658534049988,
+      "num_tokens": 685570.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 5.834242343902588,
+      "learning_rate": 0.0001,
+      "loss": 2.0929,
+      "mean_token_accuracy": 0.9145211182534695,
+      "num_tokens": 856740.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "eval_loss": 0.25579357147216797,
+      "eval_mean_token_accuracy": 0.9177517074805039,
+      "eval_num_tokens": 856740.0,
+      "eval_runtime": 133.8597,
+      "eval_samples_per_second": 1.457,
+      "eval_steps_per_second": 1.457,
+      "step": 50
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 5.7353739738464355,
+      "learning_rate": 0.0001,
+      "loss": 2.1152,
+      "mean_token_accuracy": 0.9142912536859512,
+      "num_tokens": 1028000.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 5.386626720428467,
+      "learning_rate": 0.0001,
+      "loss": 1.9346,
+      "mean_token_accuracy": 0.9206269770860672,
+      "num_tokens": 1199650.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "eval_loss": 0.23230257630348206,
+      "eval_mean_token_accuracy": 0.9229834336500902,
+      "eval_num_tokens": 1285076.0,
+      "eval_runtime": 133.8858,
+      "eval_samples_per_second": 1.456,
+      "eval_steps_per_second": 1.456,
+      "step": 75
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 5.34901237487793,
+      "learning_rate": 0.0001,
+      "loss": 1.8041,
+      "mean_token_accuracy": 0.9239558480679989,
+      "num_tokens": 1370524.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 5.087592601776123,
+      "learning_rate": 0.0001,
+      "loss": 1.8039,
+      "mean_token_accuracy": 0.9247349828481675,
+      "num_tokens": 1542159.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 5.261311054229736,
+      "learning_rate": 0.0001,
+      "loss": 1.6074,
+      "mean_token_accuracy": 0.9265569303486798,
+      "num_tokens": 1700574.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "eval_loss": 0.22464126348495483,
+      "eval_mean_token_accuracy": 0.9246747863598359,
+      "eval_num_tokens": 1700574.0,
+      "eval_runtime": 133.7804,
+      "eval_samples_per_second": 1.458,
+      "eval_steps_per_second": 1.458,
+      "step": 100
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 5.311674118041992,
+      "learning_rate": 0.0001,
+      "loss": 1.6489,
+      "mean_token_accuracy": 0.9300300016999244,
+      "num_tokens": 1871783.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 5.830325126647949,
+      "learning_rate": 0.0001,
+      "loss": 1.649,
+      "mean_token_accuracy": 0.9298087596893311,
+      "num_tokens": 2043203.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.2776349614395888,
+      "eval_loss": 0.21555578708648682,
+      "eval_mean_token_accuracy": 0.9271895112135471,
+      "eval_num_tokens": 2128963.0,
+      "eval_runtime": 134.043,
+      "eval_samples_per_second": 1.455,
+      "eval_steps_per_second": 1.455,
+      "step": 125
+    },
+    {
+      "epoch": 1.3290488431876606,
+      "grad_norm": 5.271592140197754,
+      "learning_rate": 0.0001,
+      "loss": 1.6119,
+      "mean_token_accuracy": 0.9305527195334434,
+      "num_tokens": 2214867.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 5.680342197418213,
+      "learning_rate": 0.0001,
+      "loss": 1.5448,
+      "mean_token_accuracy": 0.9328176341950893,
+      "num_tokens": 2385981.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "grad_norm": 5.75166654586792,
+      "learning_rate": 0.0001,
+      "loss": 1.5601,
+      "mean_token_accuracy": 0.9319623775780201,
+      "num_tokens": 2557432.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "eval_loss": 0.21437418460845947,
+      "eval_mean_token_accuracy": 0.9275352300741734,
+      "eval_num_tokens": 2557432.0,
+      "eval_runtime": 133.9121,
+      "eval_samples_per_second": 1.456,
+      "eval_steps_per_second": 1.456,
+      "step": 150
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 294,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1902339922153472e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e3dc8a742175f8c36087d59cc03fe76f544e4a592cf9bbf2020761587cf8e8
+size 5752

checkpoint-200/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2-VL-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.16.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2820e3d2e8426494323ad2ca002dca9a6525d5c8453232fb905f393d1fc2f225
+size 41338272

checkpoint-200/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

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 %}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d987f463c742c04748d62de9a1aab0988ffb3924328b06aaa4112e414d8779e8
+size 82856258

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c68b393cd56ef764139125d36928914f60a246189bb4929d3055c49ae1cfc97
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da963d3b7106f3b4c395d03ef6897e64220165c23480563310345c76ab7b120d
+size 1064

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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "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
+    }
+  },
+  "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": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,294 @@
+{
+  "best_global_step": 200,
+  "best_metric": 0.2047508805990219,
+  "best_model_checkpoint": "./dora_weather_model/checkpoint-200",
+  "epoch": 2.0411311053984575,
+  "eval_steps": 25,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 18.158021926879883,
+      "learning_rate": 0.0001,
+      "loss": 12.1979,
+      "mean_token_accuracy": 0.615905399620533,
+      "num_tokens": 171254.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 7.034078598022461,
+      "learning_rate": 0.0001,
+      "loss": 4.2501,
+      "mean_token_accuracy": 0.8467875950038433,
+      "num_tokens": 342816.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "eval_loss": 0.3218275308609009,
+      "eval_mean_token_accuracy": 0.9006080529628656,
+      "eval_num_tokens": 428469.0,
+      "eval_runtime": 133.9929,
+      "eval_samples_per_second": 1.455,
+      "eval_steps_per_second": 1.455,
+      "step": 25
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 7.133749008178711,
+      "learning_rate": 0.0001,
+      "loss": 2.5798,
+      "mean_token_accuracy": 0.8995884403586387,
+      "num_tokens": 514067.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 5.986148834228516,
+      "learning_rate": 0.0001,
+      "loss": 2.2895,
+      "mean_token_accuracy": 0.9077658534049988,
+      "num_tokens": 685570.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 5.834242343902588,
+      "learning_rate": 0.0001,
+      "loss": 2.0929,
+      "mean_token_accuracy": 0.9145211182534695,
+      "num_tokens": 856740.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "eval_loss": 0.25579357147216797,
+      "eval_mean_token_accuracy": 0.9177517074805039,
+      "eval_num_tokens": 856740.0,
+      "eval_runtime": 133.8597,
+      "eval_samples_per_second": 1.457,
+      "eval_steps_per_second": 1.457,
+      "step": 50
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 5.7353739738464355,
+      "learning_rate": 0.0001,
+      "loss": 2.1152,
+      "mean_token_accuracy": 0.9142912536859512,
+      "num_tokens": 1028000.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 5.386626720428467,
+      "learning_rate": 0.0001,
+      "loss": 1.9346,
+      "mean_token_accuracy": 0.9206269770860672,
+      "num_tokens": 1199650.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "eval_loss": 0.23230257630348206,
+      "eval_mean_token_accuracy": 0.9229834336500902,
+      "eval_num_tokens": 1285076.0,
+      "eval_runtime": 133.8858,
+      "eval_samples_per_second": 1.456,
+      "eval_steps_per_second": 1.456,
+      "step": 75
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 5.34901237487793,
+      "learning_rate": 0.0001,
+      "loss": 1.8041,
+      "mean_token_accuracy": 0.9239558480679989,
+      "num_tokens": 1370524.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 5.087592601776123,
+      "learning_rate": 0.0001,
+      "loss": 1.8039,
+      "mean_token_accuracy": 0.9247349828481675,
+      "num_tokens": 1542159.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 5.261311054229736,
+      "learning_rate": 0.0001,
+      "loss": 1.6074,
+      "mean_token_accuracy": 0.9265569303486798,
+      "num_tokens": 1700574.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "eval_loss": 0.22464126348495483,
+      "eval_mean_token_accuracy": 0.9246747863598359,
+      "eval_num_tokens": 1700574.0,
+      "eval_runtime": 133.7804,
+      "eval_samples_per_second": 1.458,
+      "eval_steps_per_second": 1.458,
+      "step": 100
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 5.311674118041992,
+      "learning_rate": 0.0001,
+      "loss": 1.6489,
+      "mean_token_accuracy": 0.9300300016999244,
+      "num_tokens": 1871783.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 5.830325126647949,
+      "learning_rate": 0.0001,
+      "loss": 1.649,
+      "mean_token_accuracy": 0.9298087596893311,
+      "num_tokens": 2043203.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.2776349614395888,
+      "eval_loss": 0.21555578708648682,
+      "eval_mean_token_accuracy": 0.9271895112135471,
+      "eval_num_tokens": 2128963.0,
+      "eval_runtime": 134.043,
+      "eval_samples_per_second": 1.455,
+      "eval_steps_per_second": 1.455,
+      "step": 125
+    },
+    {
+      "epoch": 1.3290488431876606,
+      "grad_norm": 5.271592140197754,
+      "learning_rate": 0.0001,
+      "loss": 1.6119,
+      "mean_token_accuracy": 0.9305527195334434,
+      "num_tokens": 2214867.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 5.680342197418213,
+      "learning_rate": 0.0001,
+      "loss": 1.5448,
+      "mean_token_accuracy": 0.9328176341950893,
+      "num_tokens": 2385981.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "grad_norm": 5.75166654586792,
+      "learning_rate": 0.0001,
+      "loss": 1.5601,
+      "mean_token_accuracy": 0.9319623775780201,
+      "num_tokens": 2557432.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "eval_loss": 0.21437418460845947,
+      "eval_mean_token_accuracy": 0.9275352300741734,
+      "eval_num_tokens": 2557432.0,
+      "eval_runtime": 133.9121,
+      "eval_samples_per_second": 1.456,
+      "eval_steps_per_second": 1.456,
+      "step": 150
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "grad_norm": 5.1881279945373535,
+      "learning_rate": 0.0001,
+      "loss": 1.5801,
+      "mean_token_accuracy": 0.9312322027981281,
+      "num_tokens": 2729083.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.7403598971722365,
+      "grad_norm": 4.914985179901123,
+      "learning_rate": 0.0001,
+      "loss": 1.618,
+      "mean_token_accuracy": 0.9298858948051929,
+      "num_tokens": 2900445.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.7917737789203085,
+      "eval_loss": 0.20662951469421387,
+      "eval_mean_token_accuracy": 0.9307488389504261,
+      "eval_num_tokens": 2986280.0,
+      "eval_runtime": 134.1279,
+      "eval_samples_per_second": 1.454,
+      "eval_steps_per_second": 1.454,
+      "step": 175
+    },
+    {
+      "epoch": 1.8431876606683804,
+      "grad_norm": 4.635578155517578,
+      "learning_rate": 0.0001,
+      "loss": 1.5242,
+      "mean_token_accuracy": 0.9346732541918754,
+      "num_tokens": 3072258.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.9460154241645244,
+      "grad_norm": 4.892042636871338,
+      "learning_rate": 0.0001,
+      "loss": 1.5347,
+      "mean_token_accuracy": 0.9339244142174721,
+      "num_tokens": 3242706.0,
+      "step": 190
+    },
+    {
+      "epoch": 2.0411311053984575,
+      "grad_norm": 4.989599704742432,
+      "learning_rate": 0.0001,
+      "loss": 1.4122,
+      "mean_token_accuracy": 0.9334916754348858,
+      "num_tokens": 3401061.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.0411311053984575,
+      "eval_loss": 0.2047508805990219,
+      "eval_mean_token_accuracy": 0.9310440222422282,
+      "eval_num_tokens": 3401061.0,
+      "eval_runtime": 134.0638,
+      "eval_samples_per_second": 1.455,
+      "eval_steps_per_second": 1.455,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 294,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5828606241721856e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e3dc8a742175f8c36087d59cc03fe76f544e4a592cf9bbf2020761587cf8e8
+size 5752