vision_on

.gitattributes

@@ -33,3 +33,8 @@ 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-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2-VL-2B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: qwen2vl_lora_16lr_7b
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen2vl_lora_16lr_7b
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) on the talk2car dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 3
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 6
+- total_eval_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 40.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.48.2
+- Pytorch 2.4.0
+- Datasets 3.1.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+  "bias": "none",
+  "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_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual.patch_embed|visual.blocks).*(?:o_proj|v_proj|down_proj|k_proj|q_proj|up_proj|gate_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788ec8b5da707abf6948e70f786bef2295da243d71c6e22f81ad1a15d216c6d4
+size 73911112

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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 40.0,
+    "total_flos": 2.004550530755461e+17,
+    "train_loss": 0.09495920253196216,
+    "train_runtime": 28025.0795,
+    "train_samples_per_second": 0.714,
+    "train_steps_per_second": 0.12
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-1000/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+  "bias": "none",
+  "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_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual.patch_embed|visual.blocks).*(?:o_proj|v_proj|down_proj|k_proj|q_proj|up_proj|gate_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3deb2c723ca194b1a5a0be565dc2099d36a5628ab4101146cefaf66983f7615
+size 73911112

checkpoint-1000/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-1000/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb228cd06b4526571fbb9a3a19a1bc7cb1dca378bc66a296104de67254345af
+size 148047978

checkpoint-1000/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 12845056,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 2
+}

checkpoint-1000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f3803bff3f596c03b55881de967a825b5734e4a581739164f9cb9e7fd1aee89
+size 14512

checkpoint-1000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d768a04b798e2ca42effbe096b8e4481f32a402a9125a2ced390586dab8eb29e
+size 14512

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f08df4df4cc87960e1f920262b834a1d27f67a7cbdd32431fe0bca63620d0ec0
+size 1064

checkpoint-1000/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-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,145 @@
+{
+  "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,
+  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,733 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.904761904761905,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11904761904761904,
+      "grad_norm": 5.44253396987915,
+      "learning_rate": 5.952380952380953e-07,
+      "loss": 1.5321,
+      "step": 10
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 2.2140841484069824,
+      "learning_rate": 1.1904761904761906e-06,
+      "loss": 1.1934,
+      "step": 20
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 1.413270115852356,
+      "learning_rate": 1.7857142857142859e-06,
+      "loss": 0.9128,
+      "step": 30
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.0657840967178345,
+      "learning_rate": 2.380952380952381e-06,
+      "loss": 0.7772,
+      "step": 40
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "grad_norm": 0.9593137502670288,
+      "learning_rate": 2.9761904761904763e-06,
+      "loss": 0.7849,
+      "step": 50
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 1.134382724761963,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.716,
+      "step": 60
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.618364691734314,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.6678,
+      "step": 70
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.7465847134590149,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 0.671,
+      "step": 80
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.6726512908935547,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.6186,
+      "step": 90
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.6353351473808289,
+      "learning_rate": 5.9523809523809525e-06,
+      "loss": 0.5818,
+      "step": 100
+    },
+    {
+      "epoch": 1.3095238095238095,
+      "grad_norm": 0.7020516991615295,
+      "learning_rate": 6.547619047619048e-06,
+      "loss": 0.6056,
+      "step": 110
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.1165708303451538,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.6225,
+      "step": 120
+    },
+    {
+      "epoch": 1.5476190476190477,
+      "grad_norm": 1.7502918243408203,
+      "learning_rate": 7.738095238095238e-06,
+      "loss": 0.6321,
+      "step": 130
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.6962683796882629,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.5751,
+      "step": 140
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.876686155796051,
+      "learning_rate": 8.92857142857143e-06,
+      "loss": 0.5974,
+      "step": 150
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.5832173228263855,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.6085,
+      "step": 160
+    },
+    {
+      "epoch": 2.0238095238095237,
+      "grad_norm": 0.44337984919548035,
+      "learning_rate": 1.011904761904762e-05,
+      "loss": 0.5713,
+      "step": 170
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 1.2403652667999268,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.5165,
+      "step": 180
+    },
+    {
+      "epoch": 2.261904761904762,
+      "grad_norm": 0.7495181560516357,
+      "learning_rate": 1.130952380952381e-05,
+      "loss": 0.5448,
+      "step": 190
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.8501800298690796,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 0.5122,
+      "step": 200
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.8133195638656616,
+      "learning_rate": 1.25e-05,
+      "loss": 0.5337,
+      "step": 210
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 1.3526533842086792,
+      "learning_rate": 1.3095238095238096e-05,
+      "loss": 0.4943,
+      "step": 220
+    },
+    {
+      "epoch": 2.738095238095238,
+      "grad_norm": 1.0535343885421753,
+      "learning_rate": 1.3690476190476192e-05,
+      "loss": 0.521,
+      "step": 230
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 1.2215440273284912,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.5461,
+      "step": 240
+    },
+    {
+      "epoch": 2.9761904761904763,
+      "grad_norm": 1.1781115531921387,
+      "learning_rate": 1.4880952380952383e-05,
+      "loss": 0.5346,
+      "step": 250
+    },
+    {
+      "epoch": 3.0952380952380953,
+      "grad_norm": 0.762434184551239,
+      "learning_rate": 1.5476190476190476e-05,
+      "loss": 0.4855,
+      "step": 260
+    },
+    {
+      "epoch": 3.2142857142857144,
+      "grad_norm": 1.287593126296997,
+      "learning_rate": 1.6071428571428572e-05,
+      "loss": 0.473,
+      "step": 270
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.9310547113418579,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.4201,
+      "step": 280
+    },
+    {
+      "epoch": 3.4523809523809526,
+      "grad_norm": 1.1341677904129028,
+      "learning_rate": 1.7261904761904763e-05,
+      "loss": 0.3884,
+      "step": 290
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 1.483049750328064,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 0.4662,
+      "step": 300
+    },
+    {
+      "epoch": 3.6904761904761907,
+      "grad_norm": 0.9312372803688049,
+      "learning_rate": 1.8452380952380954e-05,
+      "loss": 0.4688,
+      "step": 310
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "grad_norm": 1.0440223217010498,
+      "learning_rate": 1.904761904761905e-05,
+      "loss": 0.4727,
+      "step": 320
+    },
+    {
+      "epoch": 3.928571428571429,
+      "grad_norm": 1.20750892162323,
+      "learning_rate": 1.9642857142857145e-05,
+      "loss": 0.4062,
+      "step": 330
+    },
+    {
+      "epoch": 4.0476190476190474,
+      "grad_norm": 1.5511012077331543,
+      "learning_rate": 1.999991365731819e-05,
+      "loss": 0.4459,
+      "step": 340
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 1.3020656108856201,
+      "learning_rate": 1.9998942319271076e-05,
+      "loss": 0.3667,
+      "step": 350
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.9357143640518188,
+      "learning_rate": 1.9996891820008165e-05,
+      "loss": 0.3703,
+      "step": 360
+    },
+    {
+      "epoch": 4.404761904761905,
+      "grad_norm": 1.120471477508545,
+      "learning_rate": 1.9993762380834786e-05,
+      "loss": 0.3797,
+      "step": 370
+    },
+    {
+      "epoch": 4.523809523809524,
+      "grad_norm": 1.4476983547210693,
+      "learning_rate": 1.9989554339503612e-05,
+      "loss": 0.366,
+      "step": 380
+    },
+    {
+      "epoch": 4.642857142857143,
+      "grad_norm": 0.8721790313720703,
+      "learning_rate": 1.998426815017817e-05,
+      "loss": 0.3914,
+      "step": 390
+    },
+    {
+      "epoch": 4.761904761904762,
+      "grad_norm": 1.4711418151855469,
+      "learning_rate": 1.997790438338385e-05,
+      "loss": 0.3665,
+      "step": 400
+    },
+    {
+      "epoch": 4.880952380952381,
+      "grad_norm": 1.216174840927124,
+      "learning_rate": 1.9970463725946335e-05,
+      "loss": 0.345,
+      "step": 410
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.8730125427246094,
+      "learning_rate": 1.9962847054074817e-05,
+      "loss": 0.3732,
+      "step": 420
+    },
+    {
+      "epoch": 5.119047619047619,
+      "grad_norm": 1.7755807638168335,
+      "learning_rate": 1.9953362612814294e-05,
+      "loss": 0.2578,
+      "step": 430
+    },
+    {
+      "epoch": 5.238095238095238,
+      "grad_norm": 1.7037990093231201,
+      "learning_rate": 1.9942803929643423e-05,
+      "loss": 0.2561,
+      "step": 440
+    },
+    {
+      "epoch": 5.357142857142857,
+      "grad_norm": 1.140688180923462,
+      "learning_rate": 1.9931172144134874e-05,
+      "loss": 0.2525,
+      "step": 450
+    },
+    {
+      "epoch": 5.476190476190476,
+      "grad_norm": 1.492291808128357,
+      "learning_rate": 1.99184685116786e-05,
+      "loss": 0.2727,
+      "step": 460
+    },
+    {
+      "epoch": 5.595238095238095,
+      "grad_norm": 1.1798468828201294,
+      "learning_rate": 1.9904694403346362e-05,
+      "loss": 0.291,
+      "step": 470
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 1.1415112018585205,
+      "learning_rate": 1.9889851305743742e-05,
+      "loss": 0.2845,
+      "step": 480
+    },
+    {
+      "epoch": 5.833333333333333,
+      "grad_norm": 1.8219681978225708,
+      "learning_rate": 1.9873940820849714e-05,
+      "loss": 0.2746,
+      "step": 490
+    },
+    {
+      "epoch": 5.9523809523809526,
+      "grad_norm": 1.3858968019485474,
+      "learning_rate": 1.9856964665843717e-05,
+      "loss": 0.2861,
+      "step": 500
+    },
+    {
+      "epoch": 6.071428571428571,
+      "grad_norm": 1.2878497838974,
+      "learning_rate": 1.9838924672920344e-05,
+      "loss": 0.239,
+      "step": 510
+    },
+    {
+      "epoch": 6.190476190476191,
+      "grad_norm": 2.5550217628479004,
+      "learning_rate": 1.9819822789091597e-05,
+      "loss": 0.1605,
+      "step": 520
+    },
+    {
+      "epoch": 6.309523809523809,
+      "grad_norm": 2.016493082046509,
+      "learning_rate": 1.9799661075976754e-05,
+      "loss": 0.2069,
+      "step": 530
+    },
+    {
+      "epoch": 6.428571428571429,
+      "grad_norm": 1.8905669450759888,
+      "learning_rate": 1.977844170957984e-05,
+      "loss": 0.1953,
+      "step": 540
+    },
+    {
+      "epoch": 6.5476190476190474,
+      "grad_norm": 1.6992967128753662,
+      "learning_rate": 1.9756166980054812e-05,
+      "loss": 0.1837,
+      "step": 550
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 1.893633246421814,
+      "learning_rate": 1.973283929145836e-05,
+      "loss": 0.1947,
+      "step": 560
+    },
+    {
+      "epoch": 6.785714285714286,
+      "grad_norm": 1.6204354763031006,
+      "learning_rate": 1.9708461161490456e-05,
+      "loss": 0.1836,
+      "step": 570
+    },
+    {
+      "epoch": 6.904761904761905,
+      "grad_norm": 2.0902771949768066,
+      "learning_rate": 1.9683035221222617e-05,
+      "loss": 0.1971,
+      "step": 580
+    },
+    {
+      "epoch": 7.023809523809524,
+      "grad_norm": 2.2528581619262695,
+      "learning_rate": 1.9656564214813948e-05,
+      "loss": 0.1864,
+      "step": 590
+    },
+    {
+      "epoch": 7.142857142857143,
+      "grad_norm": 0.9720670580863953,
+      "learning_rate": 1.9629050999214977e-05,
+      "loss": 0.114,
+      "step": 600
+    },
+    {
+      "epoch": 7.261904761904762,
+      "grad_norm": 1.1338551044464111,
+      "learning_rate": 1.960049854385929e-05,
+      "loss": 0.1331,
+      "step": 610
+    },
+    {
+      "epoch": 7.380952380952381,
+      "grad_norm": 1.8178822994232178,
+      "learning_rate": 1.957090993034306e-05,
+      "loss": 0.1144,
+      "step": 620
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 2.2525339126586914,
+      "learning_rate": 1.9540288352092474e-05,
+      "loss": 0.1298,
+      "step": 630
+    },
+    {
+      "epoch": 7.619047619047619,
+      "grad_norm": 2.6778416633605957,
+      "learning_rate": 1.9508637114019037e-05,
+      "loss": 0.131,
+      "step": 640
+    },
+    {
+      "epoch": 7.738095238095238,
+      "grad_norm": 1.2893160581588745,
+      "learning_rate": 1.947595963216292e-05,
+      "loss": 0.1332,
+      "step": 650
+    },
+    {
+      "epoch": 7.857142857142857,
+      "grad_norm": 2.0039525032043457,
+      "learning_rate": 1.9442259433324247e-05,
+      "loss": 0.1385,
+      "step": 660
+    },
+    {
+      "epoch": 7.976190476190476,
+      "grad_norm": 1.5008896589279175,
+      "learning_rate": 1.9407540154682473e-05,
+      "loss": 0.1564,
+      "step": 670
+    },
+    {
+      "epoch": 8.095238095238095,
+      "grad_norm": 1.5358928442001343,
+      "learning_rate": 1.9371805543403826e-05,
+      "loss": 0.0916,
+      "step": 680
+    },
+    {
+      "epoch": 8.214285714285714,
+      "grad_norm": 1.3121554851531982,
+      "learning_rate": 1.9335059456236877e-05,
+      "loss": 0.0928,
+      "step": 690
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 1.5265170335769653,
+      "learning_rate": 1.9297305859096305e-05,
+      "loss": 0.0858,
+      "step": 700
+    },
+    {
+      "epoch": 8.452380952380953,
+      "grad_norm": 2.1085143089294434,
+      "learning_rate": 1.925854882663486e-05,
+      "loss": 0.0821,
+      "step": 710
+    },
+    {
+      "epoch": 8.571428571428571,
+      "grad_norm": 1.8447340726852417,
+      "learning_rate": 1.9218792541803582e-05,
+      "loss": 0.1064,
+      "step": 720
+    },
+    {
+      "epoch": 8.69047619047619,
+      "grad_norm": 1.8958710432052612,
+      "learning_rate": 1.9178041295400383e-05,
+      "loss": 0.082,
+      "step": 730
+    },
+    {
+      "epoch": 8.80952380952381,
+      "grad_norm": 1.9607478380203247,
+      "learning_rate": 1.9136299485606898e-05,
+      "loss": 0.0901,
+      "step": 740
+    },
+    {
+      "epoch": 8.928571428571429,
+      "grad_norm": 2.034801959991455,
+      "learning_rate": 1.9093571617513853e-05,
+      "loss": 0.1067,
+      "step": 750
+    },
+    {
+      "epoch": 9.047619047619047,
+      "grad_norm": 1.1250438690185547,
+      "learning_rate": 1.90498623026348e-05,
+      "loss": 0.0558,
+      "step": 760
+    },
+    {
+      "epoch": 9.166666666666666,
+      "grad_norm": 3.2768161296844482,
+      "learning_rate": 1.9005176258408434e-05,
+      "loss": 0.0464,
+      "step": 770
+    },
+    {
+      "epoch": 9.285714285714286,
+      "grad_norm": 1.0632288455963135,
+      "learning_rate": 1.8959518307689444e-05,
+      "loss": 0.0499,
+      "step": 780
+    },
+    {
+      "epoch": 9.404761904761905,
+      "grad_norm": 1.1634855270385742,
+      "learning_rate": 1.8912893378227984e-05,
+      "loss": 0.0665,
+      "step": 790
+    },
+    {
+      "epoch": 9.523809523809524,
+      "grad_norm": 2.089411497116089,
+      "learning_rate": 1.8865306502137852e-05,
+      "loss": 0.0715,
+      "step": 800
+    },
+    {
+      "epoch": 9.642857142857142,
+      "grad_norm": 0.46574532985687256,
+      "learning_rate": 1.8816762815353368e-05,
+      "loss": 0.0453,
+      "step": 810
+    },
+    {
+      "epoch": 9.761904761904763,
+      "grad_norm": 2.3916738033294678,
+      "learning_rate": 1.876726755707508e-05,
+      "loss": 0.1086,
+      "step": 820
+    },
+    {
+      "epoch": 9.880952380952381,
+      "grad_norm": 1.7373374700546265,
+      "learning_rate": 1.8716826069204297e-05,
+      "loss": 0.1003,
+      "step": 830
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.2700127363204956,
+      "learning_rate": 1.8665443795766566e-05,
+      "loss": 0.054,
+      "step": 840
+    },
+    {
+      "epoch": 10.119047619047619,
+      "grad_norm": 0.9935422539710999,
+      "learning_rate": 1.8613126282324092e-05,
+      "loss": 0.0403,
+      "step": 850
+    },
+    {
+      "epoch": 10.238095238095237,
+      "grad_norm": 1.3984347581863403,
+      "learning_rate": 1.855987917537724e-05,
+      "loss": 0.0584,
+      "step": 860
+    },
+    {
+      "epoch": 10.357142857142858,
+      "grad_norm": 2.4390032291412354,
+      "learning_rate": 1.8505708221755106e-05,
+      "loss": 0.0672,
+      "step": 870
+    },
+    {
+      "epoch": 10.476190476190476,
+      "grad_norm": 0.9531667828559875,
+      "learning_rate": 1.8450619267995283e-05,
+      "loss": 0.0425,
+      "step": 880
+    },
+    {
+      "epoch": 10.595238095238095,
+      "grad_norm": 0.42088013887405396,
+      "learning_rate": 1.8394618259712866e-05,
+      "loss": 0.0399,
+      "step": 890
+    },
+    {
+      "epoch": 10.714285714285714,
+      "grad_norm": 0.8044432997703552,
+      "learning_rate": 1.8337711240958734e-05,
+      "loss": 0.0516,
+      "step": 900
+    },
+    {
+      "epoch": 10.833333333333334,
+      "grad_norm": 1.7414997816085815,
+      "learning_rate": 1.827990435356725e-05,
+      "loss": 0.043,
+      "step": 910
+    },
+    {
+      "epoch": 10.952380952380953,
+      "grad_norm": 0.6912918090820312,
+      "learning_rate": 1.822120383649339e-05,
+      "loss": 0.0444,
+      "step": 920
+    },
+    {
+      "epoch": 11.071428571428571,
+      "grad_norm": 1.3013064861297607,
+      "learning_rate": 1.8161616025139375e-05,
+      "loss": 0.0436,
+      "step": 930
+    },
+    {
+      "epoch": 11.19047619047619,
+      "grad_norm": 1.2811461687088013,
+      "learning_rate": 1.8101147350670905e-05,
+      "loss": 0.039,
+      "step": 940
+    },
+    {
+      "epoch": 11.30952380952381,
+      "grad_norm": 6.565953254699707,
+      "learning_rate": 1.8039804339323083e-05,
+      "loss": 0.0411,
+      "step": 950
+    },
+    {
+      "epoch": 11.428571428571429,
+      "grad_norm": 1.2721556425094604,
+      "learning_rate": 1.7977593611696017e-05,
+      "loss": 0.0242,
+      "step": 960
+    },
+    {
+      "epoch": 11.547619047619047,
+      "grad_norm": 1.6954939365386963,
+      "learning_rate": 1.791452188204031e-05,
+      "loss": 0.0421,
+      "step": 970
+    },
+    {
+      "epoch": 11.666666666666666,
+      "grad_norm": 1.3118443489074707,
+      "learning_rate": 1.7850595957532394e-05,
+      "loss": 0.0524,
+      "step": 980
+    },
+    {
+      "epoch": 11.785714285714286,
+      "grad_norm": 0.5428506731987,
+      "learning_rate": 1.778582273753984e-05,
+      "loss": 0.0484,
+      "step": 990
+    },
+    {
+      "epoch": 11.904761904761905,
+      "grad_norm": 0.4753515124320984,
+      "learning_rate": 1.772020921287674e-05,
+      "loss": 0.0347,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3360,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.965853086449664e+16,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe16ad85cf67a1d616e8a664749a043a7e42845bd6dfe8881e3e3c947d23497a
+size 5624

checkpoint-2000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-2000/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+  "bias": "none",
+  "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_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual.patch_embed|visual.blocks).*(?:o_proj|v_proj|down_proj|k_proj|q_proj|up_proj|gate_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03928b0ecd6b0549b45181cc9efb4fbf4040792fdf1f257edf0b7c21fbc2ee40
+size 73911112

checkpoint-2000/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-2000/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95a36ccd6117677e5f04e807f62ecb626c9dca12a1beaf724fa9f43cc788efac
+size 148047978

checkpoint-2000/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 12845056,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 2
+}

checkpoint-2000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23c5c1a139c10fe0906308288b9990e59b0830f85f1180b142012af4957b1ba2
+size 14512

checkpoint-2000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e02bd5e21ab993cf26deb90360061cfc27b8440d255a29134ff03a42f4f9abff
+size 14512

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:849e569d25a585ac5f4565034971d52ce26f78183bf5984dd969f75ddb21fb9b
+size 1064

checkpoint-2000/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-2000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,145 @@
+{
+  "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,
+  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,1433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 23.80952380952381,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11904761904761904,
+      "grad_norm": 5.44253396987915,
+      "learning_rate": 5.952380952380953e-07,
+      "loss": 1.5321,
+      "step": 10
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 2.2140841484069824,
+      "learning_rate": 1.1904761904761906e-06,
+      "loss": 1.1934,
+      "step": 20
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 1.413270115852356,
+      "learning_rate": 1.7857142857142859e-06,
+      "loss": 0.9128,
+      "step": 30
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.0657840967178345,
+      "learning_rate": 2.380952380952381e-06,
+      "loss": 0.7772,
+      "step": 40
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "grad_norm": 0.9593137502670288,
+      "learning_rate": 2.9761904761904763e-06,
+      "loss": 0.7849,
+      "step": 50
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 1.134382724761963,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.716,
+      "step": 60
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.618364691734314,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.6678,
+      "step": 70
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.7465847134590149,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 0.671,
+      "step": 80
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.6726512908935547,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.6186,
+      "step": 90
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.6353351473808289,
+      "learning_rate": 5.9523809523809525e-06,
+      "loss": 0.5818,
+      "step": 100
+    },
+    {
+      "epoch": 1.3095238095238095,
+      "grad_norm": 0.7020516991615295,
+      "learning_rate": 6.547619047619048e-06,
+      "loss": 0.6056,
+      "step": 110
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.1165708303451538,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.6225,
+      "step": 120
+    },
+    {
+      "epoch": 1.5476190476190477,
+      "grad_norm": 1.7502918243408203,
+      "learning_rate": 7.738095238095238e-06,
+      "loss": 0.6321,
+      "step": 130
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.6962683796882629,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.5751,
+      "step": 140
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.876686155796051,
+      "learning_rate": 8.92857142857143e-06,
+      "loss": 0.5974,
+      "step": 150
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.5832173228263855,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.6085,
+      "step": 160
+    },
+    {
+      "epoch": 2.0238095238095237,
+      "grad_norm": 0.44337984919548035,
+      "learning_rate": 1.011904761904762e-05,
+      "loss": 0.5713,
+      "step": 170
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 1.2403652667999268,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.5165,
+      "step": 180
+    },
+    {
+      "epoch": 2.261904761904762,
+      "grad_norm": 0.7495181560516357,
+      "learning_rate": 1.130952380952381e-05,
+      "loss": 0.5448,
+      "step": 190
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.8501800298690796,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 0.5122,
+      "step": 200
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.8133195638656616,
+      "learning_rate": 1.25e-05,
+      "loss": 0.5337,
+      "step": 210
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 1.3526533842086792,
+      "learning_rate": 1.3095238095238096e-05,
+      "loss": 0.4943,
+      "step": 220
+    },
+    {
+      "epoch": 2.738095238095238,
+      "grad_norm": 1.0535343885421753,
+      "learning_rate": 1.3690476190476192e-05,
+      "loss": 0.521,
+      "step": 230
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 1.2215440273284912,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.5461,
+      "step": 240
+    },
+    {
+      "epoch": 2.9761904761904763,
+      "grad_norm": 1.1781115531921387,
+      "learning_rate": 1.4880952380952383e-05,
+      "loss": 0.5346,
+      "step": 250
+    },
+    {
+      "epoch": 3.0952380952380953,
+      "grad_norm": 0.762434184551239,
+      "learning_rate": 1.5476190476190476e-05,
+      "loss": 0.4855,
+      "step": 260
+    },
+    {
+      "epoch": 3.2142857142857144,
+      "grad_norm": 1.287593126296997,
+      "learning_rate": 1.6071428571428572e-05,
+      "loss": 0.473,
+      "step": 270
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.9310547113418579,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.4201,
+      "step": 280
+    },
+    {
+      "epoch": 3.4523809523809526,
+      "grad_norm": 1.1341677904129028,
+      "learning_rate": 1.7261904761904763e-05,
+      "loss": 0.3884,
+      "step": 290
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 1.483049750328064,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 0.4662,
+      "step": 300
+    },
+    {
+      "epoch": 3.6904761904761907,
+      "grad_norm": 0.9312372803688049,
+      "learning_rate": 1.8452380952380954e-05,
+      "loss": 0.4688,
+      "step": 310
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "grad_norm": 1.0440223217010498,
+      "learning_rate": 1.904761904761905e-05,
+      "loss": 0.4727,
+      "step": 320
+    },
+    {
+      "epoch": 3.928571428571429,
+      "grad_norm": 1.20750892162323,
+      "learning_rate": 1.9642857142857145e-05,
+      "loss": 0.4062,
+      "step": 330
+    },
+    {
+      "epoch": 4.0476190476190474,
+      "grad_norm": 1.5511012077331543,
+      "learning_rate": 1.999991365731819e-05,
+      "loss": 0.4459,
+      "step": 340
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 1.3020656108856201,
+      "learning_rate": 1.9998942319271076e-05,
+      "loss": 0.3667,
+      "step": 350
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.9357143640518188,
+      "learning_rate": 1.9996891820008165e-05,
+      "loss": 0.3703,
+      "step": 360
+    },
+    {
+      "epoch": 4.404761904761905,
+      "grad_norm": 1.120471477508545,
+      "learning_rate": 1.9993762380834786e-05,
+      "loss": 0.3797,
+      "step": 370
+    },
+    {
+      "epoch": 4.523809523809524,
+      "grad_norm": 1.4476983547210693,
+      "learning_rate": 1.9989554339503612e-05,
+      "loss": 0.366,
+      "step": 380
+    },
+    {
+      "epoch": 4.642857142857143,
+      "grad_norm": 0.8721790313720703,
+      "learning_rate": 1.998426815017817e-05,
+      "loss": 0.3914,
+      "step": 390
+    },
+    {
+      "epoch": 4.761904761904762,
+      "grad_norm": 1.4711418151855469,
+      "learning_rate": 1.997790438338385e-05,
+      "loss": 0.3665,
+      "step": 400
+    },
+    {
+      "epoch": 4.880952380952381,
+      "grad_norm": 1.216174840927124,
+      "learning_rate": 1.9970463725946335e-05,
+      "loss": 0.345,
+      "step": 410
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.8730125427246094,
+      "learning_rate": 1.9962847054074817e-05,
+      "loss": 0.3732,
+      "step": 420
+    },
+    {
+      "epoch": 5.119047619047619,
+      "grad_norm": 1.7755807638168335,
+      "learning_rate": 1.9953362612814294e-05,
+      "loss": 0.2578,
+      "step": 430
+    },
+    {
+      "epoch": 5.238095238095238,
+      "grad_norm": 1.7037990093231201,
+      "learning_rate": 1.9942803929643423e-05,
+      "loss": 0.2561,
+      "step": 440
+    },
+    {
+      "epoch": 5.357142857142857,
+      "grad_norm": 1.140688180923462,
+      "learning_rate": 1.9931172144134874e-05,
+      "loss": 0.2525,
+      "step": 450
+    },
+    {
+      "epoch": 5.476190476190476,
+      "grad_norm": 1.492291808128357,
+      "learning_rate": 1.99184685116786e-05,
+      "loss": 0.2727,
+      "step": 460
+    },
+    {
+      "epoch": 5.595238095238095,
+      "grad_norm": 1.1798468828201294,
+      "learning_rate": 1.9904694403346362e-05,
+      "loss": 0.291,
+      "step": 470
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 1.1415112018585205,
+      "learning_rate": 1.9889851305743742e-05,
+      "loss": 0.2845,
+      "step": 480
+    },
+    {
+      "epoch": 5.833333333333333,
+      "grad_norm": 1.8219681978225708,
+      "learning_rate": 1.9873940820849714e-05,
+      "loss": 0.2746,
+      "step": 490
+    },
+    {
+      "epoch": 5.9523809523809526,
+      "grad_norm": 1.3858968019485474,
+      "learning_rate": 1.9856964665843717e-05,
+      "loss": 0.2861,
+      "step": 500
+    },
+    {
+      "epoch": 6.071428571428571,
+      "grad_norm": 1.2878497838974,
+      "learning_rate": 1.9838924672920344e-05,
+      "loss": 0.239,
+      "step": 510
+    },
+    {
+      "epoch": 6.190476190476191,
+      "grad_norm": 2.5550217628479004,
+      "learning_rate": 1.9819822789091597e-05,
+      "loss": 0.1605,
+      "step": 520
+    },
+    {
+      "epoch": 6.309523809523809,
+      "grad_norm": 2.016493082046509,
+      "learning_rate": 1.9799661075976754e-05,
+      "loss": 0.2069,
+      "step": 530
+    },
+    {
+      "epoch": 6.428571428571429,
+      "grad_norm": 1.8905669450759888,
+      "learning_rate": 1.977844170957984e-05,
+      "loss": 0.1953,
+      "step": 540
+    },
+    {
+      "epoch": 6.5476190476190474,
+      "grad_norm": 1.6992967128753662,
+      "learning_rate": 1.9756166980054812e-05,
+      "loss": 0.1837,
+      "step": 550
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 1.893633246421814,
+      "learning_rate": 1.973283929145836e-05,
+      "loss": 0.1947,
+      "step": 560
+    },
+    {
+      "epoch": 6.785714285714286,
+      "grad_norm": 1.6204354763031006,
+      "learning_rate": 1.9708461161490456e-05,
+      "loss": 0.1836,
+      "step": 570
+    },
+    {
+      "epoch": 6.904761904761905,
+      "grad_norm": 2.0902771949768066,
+      "learning_rate": 1.9683035221222617e-05,
+      "loss": 0.1971,
+      "step": 580
+    },
+    {
+      "epoch": 7.023809523809524,
+      "grad_norm": 2.2528581619262695,
+      "learning_rate": 1.9656564214813948e-05,
+      "loss": 0.1864,
+      "step": 590
+    },
+    {
+      "epoch": 7.142857142857143,
+      "grad_norm": 0.9720670580863953,
+      "learning_rate": 1.9629050999214977e-05,
+      "loss": 0.114,
+      "step": 600
+    },
+    {
+      "epoch": 7.261904761904762,
+      "grad_norm": 1.1338551044464111,
+      "learning_rate": 1.960049854385929e-05,
+      "loss": 0.1331,
+      "step": 610
+    },
+    {
+      "epoch": 7.380952380952381,
+      "grad_norm": 1.8178822994232178,
+      "learning_rate": 1.957090993034306e-05,
+      "loss": 0.1144,
+      "step": 620
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 2.2525339126586914,
+      "learning_rate": 1.9540288352092474e-05,
+      "loss": 0.1298,
+      "step": 630
+    },
+    {
+      "epoch": 7.619047619047619,
+      "grad_norm": 2.6778416633605957,
+      "learning_rate": 1.9508637114019037e-05,
+      "loss": 0.131,
+      "step": 640
+    },
+    {
+      "epoch": 7.738095238095238,
+      "grad_norm": 1.2893160581588745,
+      "learning_rate": 1.947595963216292e-05,
+      "loss": 0.1332,
+      "step": 650
+    },
+    {
+      "epoch": 7.857142857142857,
+      "grad_norm": 2.0039525032043457,
+      "learning_rate": 1.9442259433324247e-05,
+      "loss": 0.1385,
+      "step": 660
+    },
+    {
+      "epoch": 7.976190476190476,
+      "grad_norm": 1.5008896589279175,
+      "learning_rate": 1.9407540154682473e-05,
+      "loss": 0.1564,
+      "step": 670
+    },
+    {
+      "epoch": 8.095238095238095,
+      "grad_norm": 1.5358928442001343,
+      "learning_rate": 1.9371805543403826e-05,
+      "loss": 0.0916,
+      "step": 680
+    },
+    {
+      "epoch": 8.214285714285714,
+      "grad_norm": 1.3121554851531982,
+      "learning_rate": 1.9335059456236877e-05,
+      "loss": 0.0928,
+      "step": 690
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 1.5265170335769653,
+      "learning_rate": 1.9297305859096305e-05,
+      "loss": 0.0858,
+      "step": 700
+    },
+    {
+      "epoch": 8.452380952380953,
+      "grad_norm": 2.1085143089294434,
+      "learning_rate": 1.925854882663486e-05,
+      "loss": 0.0821,
+      "step": 710
+    },
+    {
+      "epoch": 8.571428571428571,
+      "grad_norm": 1.8447340726852417,
+      "learning_rate": 1.9218792541803582e-05,
+      "loss": 0.1064,
+      "step": 720
+    },
+    {
+      "epoch": 8.69047619047619,
+      "grad_norm": 1.8958710432052612,
+      "learning_rate": 1.9178041295400383e-05,
+      "loss": 0.082,
+      "step": 730
+    },
+    {
+      "epoch": 8.80952380952381,
+      "grad_norm": 1.9607478380203247,
+      "learning_rate": 1.9136299485606898e-05,
+      "loss": 0.0901,
+      "step": 740
+    },
+    {
+      "epoch": 8.928571428571429,
+      "grad_norm": 2.034801959991455,
+      "learning_rate": 1.9093571617513853e-05,
+      "loss": 0.1067,
+      "step": 750
+    },
+    {
+      "epoch": 9.047619047619047,
+      "grad_norm": 1.1250438690185547,
+      "learning_rate": 1.90498623026348e-05,
+      "loss": 0.0558,
+      "step": 760
+    },
+    {
+      "epoch": 9.166666666666666,
+      "grad_norm": 3.2768161296844482,
+      "learning_rate": 1.9005176258408434e-05,
+      "loss": 0.0464,
+      "step": 770
+    },
+    {
+      "epoch": 9.285714285714286,
+      "grad_norm": 1.0632288455963135,
+      "learning_rate": 1.8959518307689444e-05,
+      "loss": 0.0499,
+      "step": 780
+    },
+    {
+      "epoch": 9.404761904761905,
+      "grad_norm": 1.1634855270385742,
+      "learning_rate": 1.8912893378227984e-05,
+      "loss": 0.0665,
+      "step": 790
+    },
+    {
+      "epoch": 9.523809523809524,
+      "grad_norm": 2.089411497116089,
+      "learning_rate": 1.8865306502137852e-05,
+      "loss": 0.0715,
+      "step": 800
+    },
+    {
+      "epoch": 9.642857142857142,
+      "grad_norm": 0.46574532985687256,
+      "learning_rate": 1.8816762815353368e-05,
+      "loss": 0.0453,
+      "step": 810
+    },
+    {
+      "epoch": 9.761904761904763,
+      "grad_norm": 2.3916738033294678,
+      "learning_rate": 1.876726755707508e-05,
+      "loss": 0.1086,
+      "step": 820
+    },
+    {
+      "epoch": 9.880952380952381,
+      "grad_norm": 1.7373374700546265,
+      "learning_rate": 1.8716826069204297e-05,
+      "loss": 0.1003,
+      "step": 830
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.2700127363204956,
+      "learning_rate": 1.8665443795766566e-05,
+      "loss": 0.054,
+      "step": 840
+    },
+    {
+      "epoch": 10.119047619047619,
+      "grad_norm": 0.9935422539710999,
+      "learning_rate": 1.8613126282324092e-05,
+      "loss": 0.0403,
+      "step": 850
+    },
+    {
+      "epoch": 10.238095238095237,
+      "grad_norm": 1.3984347581863403,
+      "learning_rate": 1.855987917537724e-05,
+      "loss": 0.0584,
+      "step": 860
+    },
+    {
+      "epoch": 10.357142857142858,
+      "grad_norm": 2.4390032291412354,
+      "learning_rate": 1.8505708221755106e-05,
+      "loss": 0.0672,
+      "step": 870
+    },
+    {
+      "epoch": 10.476190476190476,
+      "grad_norm": 0.9531667828559875,
+      "learning_rate": 1.8450619267995283e-05,
+      "loss": 0.0425,
+      "step": 880
+    },
+    {
+      "epoch": 10.595238095238095,
+      "grad_norm": 0.42088013887405396,
+      "learning_rate": 1.8394618259712866e-05,
+      "loss": 0.0399,
+      "step": 890
+    },
+    {
+      "epoch": 10.714285714285714,
+      "grad_norm": 0.8044432997703552,
+      "learning_rate": 1.8337711240958734e-05,
+      "loss": 0.0516,
+      "step": 900
+    },
+    {
+      "epoch": 10.833333333333334,
+      "grad_norm": 1.7414997816085815,
+      "learning_rate": 1.827990435356725e-05,
+      "loss": 0.043,
+      "step": 910
+    },
+    {
+      "epoch": 10.952380952380953,
+      "grad_norm": 0.6912918090820312,
+      "learning_rate": 1.822120383649339e-05,
+      "loss": 0.0444,
+      "step": 920
+    },
+    {
+      "epoch": 11.071428571428571,
+      "grad_norm": 1.3013064861297607,
+      "learning_rate": 1.8161616025139375e-05,
+      "loss": 0.0436,
+      "step": 930
+    },
+    {
+      "epoch": 11.19047619047619,
+      "grad_norm": 1.2811461687088013,
+      "learning_rate": 1.8101147350670905e-05,
+      "loss": 0.039,
+      "step": 940
+    },
+    {
+      "epoch": 11.30952380952381,
+      "grad_norm": 6.565953254699707,
+      "learning_rate": 1.8039804339323083e-05,
+      "loss": 0.0411,
+      "step": 950
+    },
+    {
+      "epoch": 11.428571428571429,
+      "grad_norm": 1.2721556425094604,
+      "learning_rate": 1.7977593611696017e-05,
+      "loss": 0.0242,
+      "step": 960
+    },
+    {
+      "epoch": 11.547619047619047,
+      "grad_norm": 1.6954939365386963,
+      "learning_rate": 1.791452188204031e-05,
+      "loss": 0.0421,
+      "step": 970
+    },
+    {
+      "epoch": 11.666666666666666,
+      "grad_norm": 1.3118443489074707,
+      "learning_rate": 1.7850595957532394e-05,
+      "loss": 0.0524,
+      "step": 980
+    },
+    {
+      "epoch": 11.785714285714286,
+      "grad_norm": 0.5428506731987,
+      "learning_rate": 1.778582273753984e-05,
+      "loss": 0.0484,
+      "step": 990
+    },
+    {
+      "epoch": 11.904761904761905,
+      "grad_norm": 0.4753515124320984,
+      "learning_rate": 1.772020921287674e-05,
+      "loss": 0.0347,
+      "step": 1000
+    },
+    {
+      "epoch": 12.023809523809524,
+      "grad_norm": 1.2880959510803223,
+      "learning_rate": 1.7653762465049185e-05,
+      "loss": 0.0408,
+      "step": 1010
+    },
+    {
+      "epoch": 12.142857142857142,
+      "grad_norm": 2.5490682125091553,
+      "learning_rate": 1.7586489665491013e-05,
+      "loss": 0.0461,
+      "step": 1020
+    },
+    {
+      "epoch": 12.261904761904763,
+      "grad_norm": 0.1983003169298172,
+      "learning_rate": 1.7518398074789776e-05,
+      "loss": 0.0391,
+      "step": 1030
+    },
+    {
+      "epoch": 12.380952380952381,
+      "grad_norm": 1.2978509664535522,
+      "learning_rate": 1.7449495041903136e-05,
+      "loss": 0.0272,
+      "step": 1040
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 0.3622434437274933,
+      "learning_rate": 1.737978800336572e-05,
+      "loss": 0.0431,
+      "step": 1050
+    },
+    {
+      "epoch": 12.619047619047619,
+      "grad_norm": 2.1278223991394043,
+      "learning_rate": 1.7309284482486494e-05,
+      "loss": 0.0241,
+      "step": 1060
+    },
+    {
+      "epoch": 12.738095238095237,
+      "grad_norm": 2.409932851791382,
+      "learning_rate": 1.723799208853681e-05,
+      "loss": 0.0247,
+      "step": 1070
+    },
+    {
+      "epoch": 12.857142857142858,
+      "grad_norm": 0.8543738126754761,
+      "learning_rate": 1.7165918515929147e-05,
+      "loss": 0.0385,
+      "step": 1080
+    },
+    {
+      "epoch": 12.976190476190476,
+      "grad_norm": 0.301162451505661,
+      "learning_rate": 1.7093071543386667e-05,
+      "loss": 0.0362,
+      "step": 1090
+    },
+    {
+      "epoch": 13.095238095238095,
+      "grad_norm": 0.9338281750679016,
+      "learning_rate": 1.7019459033103684e-05,
+      "loss": 0.0297,
+      "step": 1100
+    },
+    {
+      "epoch": 13.214285714285714,
+      "grad_norm": 1.0773793458938599,
+      "learning_rate": 1.6945088929897115e-05,
+      "loss": 0.0312,
+      "step": 1110
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 0.34426188468933105,
+      "learning_rate": 1.686996926034902e-05,
+      "loss": 0.0146,
+      "step": 1120
+    },
+    {
+      "epoch": 13.452380952380953,
+      "grad_norm": 0.22328321635723114,
+      "learning_rate": 1.67941081319403e-05,
+      "loss": 0.0195,
+      "step": 1130
+    },
+    {
+      "epoch": 13.571428571428571,
+      "grad_norm": 0.5331404805183411,
+      "learning_rate": 1.6717513732175686e-05,
+      "loss": 0.025,
+      "step": 1140
+    },
+    {
+      "epoch": 13.69047619047619,
+      "grad_norm": 2.170349359512329,
+      "learning_rate": 1.6640194327700087e-05,
+      "loss": 0.0132,
+      "step": 1150
+    },
+    {
+      "epoch": 13.80952380952381,
+      "grad_norm": 1.2327094078063965,
+      "learning_rate": 1.6562158263406376e-05,
+      "loss": 0.0175,
+      "step": 1160
+    },
+    {
+      "epoch": 13.928571428571429,
+      "grad_norm": 0.2306894212961197,
+      "learning_rate": 1.6483413961534764e-05,
+      "loss": 0.0195,
+      "step": 1170
+    },
+    {
+      "epoch": 14.047619047619047,
+      "grad_norm": 0.8987044095993042,
+      "learning_rate": 1.640396992076379e-05,
+      "loss": 0.0186,
+      "step": 1180
+    },
+    {
+      "epoch": 14.166666666666666,
+      "grad_norm": 1.013019323348999,
+      "learning_rate": 1.6323834715293094e-05,
+      "loss": 0.0259,
+      "step": 1190
+    },
+    {
+      "epoch": 14.285714285714286,
+      "grad_norm": 0.14262178540229797,
+      "learning_rate": 1.6243016993918022e-05,
+      "loss": 0.0158,
+      "step": 1200
+    },
+    {
+      "epoch": 14.404761904761905,
+      "grad_norm": 0.7596869468688965,
+      "learning_rate": 1.616152547909618e-05,
+      "loss": 0.0265,
+      "step": 1210
+    },
+    {
+      "epoch": 14.523809523809524,
+      "grad_norm": 0.2511692941188812,
+      "learning_rate": 1.6079368966006022e-05,
+      "loss": 0.022,
+      "step": 1220
+    },
+    {
+      "epoch": 14.642857142857142,
+      "grad_norm": 0.16154764592647552,
+      "learning_rate": 1.5996556321597663e-05,
+      "loss": 0.0222,
+      "step": 1230
+    },
+    {
+      "epoch": 14.761904761904763,
+      "grad_norm": 0.6887322664260864,
+      "learning_rate": 1.5913096483635827e-05,
+      "loss": 0.008,
+      "step": 1240
+    },
+    {
+      "epoch": 14.880952380952381,
+      "grad_norm": 0.07254794239997864,
+      "learning_rate": 1.582899845973525e-05,
+      "loss": 0.0034,
+      "step": 1250
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.4768582284450531,
+      "learning_rate": 1.574427132638851e-05,
+      "loss": 0.0083,
+      "step": 1260
+    },
+    {
+      "epoch": 15.119047619047619,
+      "grad_norm": 0.04978374391794205,
+      "learning_rate": 1.5658924227986415e-05,
+      "loss": 0.0102,
+      "step": 1270
+    },
+    {
+      "epoch": 15.238095238095237,
+      "grad_norm": 1.5553603172302246,
+      "learning_rate": 1.5572966375831072e-05,
+      "loss": 0.0082,
+      "step": 1280
+    },
+    {
+      "epoch": 15.357142857142858,
+      "grad_norm": 0.1932092010974884,
+      "learning_rate": 1.5486407047141745e-05,
+      "loss": 0.0191,
+      "step": 1290
+    },
+    {
+      "epoch": 15.476190476190476,
+      "grad_norm": 0.12488748133182526,
+      "learning_rate": 1.5399255584053568e-05,
+      "loss": 0.0068,
+      "step": 1300
+    },
+    {
+      "epoch": 15.595238095238095,
+      "grad_norm": 0.04466537758708,
+      "learning_rate": 1.5311521392609283e-05,
+      "loss": 0.0067,
+      "step": 1310
+    },
+    {
+      "epoch": 15.714285714285714,
+      "grad_norm": 0.1408109813928604,
+      "learning_rate": 1.5223213941744078e-05,
+      "loss": 0.0076,
+      "step": 1320
+    },
+    {
+      "epoch": 15.833333333333334,
+      "grad_norm": 0.4874057471752167,
+      "learning_rate": 1.5134342762263606e-05,
+      "loss": 0.0109,
+      "step": 1330
+    },
+    {
+      "epoch": 15.952380952380953,
+      "grad_norm": 0.15269064903259277,
+      "learning_rate": 1.504491744581537e-05,
+      "loss": 0.0073,
+      "step": 1340
+    },
+    {
+      "epoch": 16.071428571428573,
+      "grad_norm": 0.192997545003891,
+      "learning_rate": 1.4954947643853508e-05,
+      "loss": 0.0223,
+      "step": 1350
+    },
+    {
+      "epoch": 16.19047619047619,
+      "grad_norm": 0.9681908488273621,
+      "learning_rate": 1.486444306659714e-05,
+      "loss": 0.0037,
+      "step": 1360
+    },
+    {
+      "epoch": 16.30952380952381,
+      "grad_norm": 1.2680203914642334,
+      "learning_rate": 1.4773413481982359e-05,
+      "loss": 0.008,
+      "step": 1370
+    },
+    {
+      "epoch": 16.428571428571427,
+      "grad_norm": 0.07117388397455215,
+      "learning_rate": 1.4681868714608021e-05,
+      "loss": 0.0046,
+      "step": 1380
+    },
+    {
+      "epoch": 16.547619047619047,
+      "grad_norm": 0.031909532845020294,
+      "learning_rate": 1.4589818644675378e-05,
+      "loss": 0.0101,
+      "step": 1390
+    },
+    {
+      "epoch": 16.666666666666668,
+      "grad_norm": 1.234426498413086,
+      "learning_rate": 1.4497273206921747e-05,
+      "loss": 0.0051,
+      "step": 1400
+    },
+    {
+      "epoch": 16.785714285714285,
+      "grad_norm": 0.43718039989471436,
+      "learning_rate": 1.4404242389548274e-05,
+      "loss": 0.0063,
+      "step": 1410
+    },
+    {
+      "epoch": 16.904761904761905,
+      "grad_norm": 3.5411911010742188,
+      "learning_rate": 1.4310736233141926e-05,
+      "loss": 0.0177,
+      "step": 1420
+    },
+    {
+      "epoch": 17.023809523809526,
+      "grad_norm": 0.09840346872806549,
+      "learning_rate": 1.4216764829591853e-05,
+      "loss": 0.0071,
+      "step": 1430
+    },
+    {
+      "epoch": 17.142857142857142,
+      "grad_norm": 0.09478545933961868,
+      "learning_rate": 1.4122338321000175e-05,
+      "loss": 0.0032,
+      "step": 1440
+    },
+    {
+      "epoch": 17.261904761904763,
+      "grad_norm": 0.040692731738090515,
+      "learning_rate": 1.4027466898587375e-05,
+      "loss": 0.0036,
+      "step": 1450
+    },
+    {
+      "epoch": 17.38095238095238,
+      "grad_norm": 0.6164568066596985,
+      "learning_rate": 1.3932160801592395e-05,
+      "loss": 0.0066,
+      "step": 1460
+    },
+    {
+      "epoch": 17.5,
+      "grad_norm": 0.2039034515619278,
+      "learning_rate": 1.3836430316167533e-05,
+      "loss": 0.008,
+      "step": 1470
+    },
+    {
+      "epoch": 17.61904761904762,
+      "grad_norm": 0.06619343906641006,
+      "learning_rate": 1.3740285774268282e-05,
+      "loss": 0.0068,
+      "step": 1480
+    },
+    {
+      "epoch": 17.738095238095237,
+      "grad_norm": 0.050607554614543915,
+      "learning_rate": 1.3643737552538237e-05,
+      "loss": 0.0058,
+      "step": 1490
+    },
+    {
+      "epoch": 17.857142857142858,
+      "grad_norm": 0.6153551340103149,
+      "learning_rate": 1.3546796071189153e-05,
+      "loss": 0.0089,
+      "step": 1500
+    },
+    {
+      "epoch": 17.976190476190474,
+      "grad_norm": 0.07599499821662903,
+      "learning_rate": 1.3449471792876333e-05,
+      "loss": 0.0063,
+      "step": 1510
+    },
+    {
+      "epoch": 18.095238095238095,
+      "grad_norm": 0.0883430764079094,
+      "learning_rate": 1.3351775221569416e-05,
+      "loss": 0.0054,
+      "step": 1520
+    },
+    {
+      "epoch": 18.214285714285715,
+      "grad_norm": 0.02305910363793373,
+      "learning_rate": 1.3253716901418702e-05,
+      "loss": 0.0028,
+      "step": 1530
+    },
+    {
+      "epoch": 18.333333333333332,
+      "grad_norm": 0.6192808151245117,
+      "learning_rate": 1.3155307415617156e-05,
+      "loss": 0.002,
+      "step": 1540
+    },
+    {
+      "epoch": 18.452380952380953,
+      "grad_norm": 0.23332145810127258,
+      "learning_rate": 1.3056557385258181e-05,
+      "loss": 0.0066,
+      "step": 1550
+    },
+    {
+      "epoch": 18.571428571428573,
+      "grad_norm": 0.045441482216119766,
+      "learning_rate": 1.2957477468189321e-05,
+      "loss": 0.0015,
+      "step": 1560
+    },
+    {
+      "epoch": 18.69047619047619,
+      "grad_norm": 0.009192162193357944,
+      "learning_rate": 1.2858078357861979e-05,
+      "loss": 0.0128,
+      "step": 1570
+    },
+    {
+      "epoch": 18.80952380952381,
+      "grad_norm": 0.05836764723062515,
+      "learning_rate": 1.2758370782177296e-05,
+      "loss": 0.0048,
+      "step": 1580
+    },
+    {
+      "epoch": 18.928571428571427,
+      "grad_norm": 1.0975781679153442,
+      "learning_rate": 1.2658365502328329e-05,
+      "loss": 0.007,
+      "step": 1590
+    },
+    {
+      "epoch": 19.047619047619047,
+      "grad_norm": 1.1575758457183838,
+      "learning_rate": 1.2558073311638604e-05,
+      "loss": 0.018,
+      "step": 1600
+    },
+    {
+      "epoch": 19.166666666666668,
+      "grad_norm": 0.1114954873919487,
+      "learning_rate": 1.2457505034397223e-05,
+      "loss": 0.0023,
+      "step": 1610
+    },
+    {
+      "epoch": 19.285714285714285,
+      "grad_norm": 0.07574819773435593,
+      "learning_rate": 1.2356671524690645e-05,
+      "loss": 0.0019,
+      "step": 1620
+    },
+    {
+      "epoch": 19.404761904761905,
+      "grad_norm": 0.009654861874878407,
+      "learning_rate": 1.2255583665231196e-05,
+      "loss": 0.0026,
+      "step": 1630
+    },
+    {
+      "epoch": 19.523809523809526,
+      "grad_norm": 0.02393646165728569,
+      "learning_rate": 1.2154252366182564e-05,
+      "loss": 0.0014,
+      "step": 1640
+    },
+    {
+      "epoch": 19.642857142857142,
+      "grad_norm": 0.020082678645849228,
+      "learning_rate": 1.2052688563982257e-05,
+      "loss": 0.0012,
+      "step": 1650
+    },
+    {
+      "epoch": 19.761904761904763,
+      "grad_norm": 0.9789303541183472,
+      "learning_rate": 1.1950903220161286e-05,
+      "loss": 0.0063,
+      "step": 1660
+    },
+    {
+      "epoch": 19.88095238095238,
+      "grad_norm": 0.2839144766330719,
+      "learning_rate": 1.1848907320161092e-05,
+      "loss": 0.0034,
+      "step": 1670
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.010598956607282162,
+      "learning_rate": 1.174671187214794e-05,
+      "loss": 0.0054,
+      "step": 1680
+    },
+    {
+      "epoch": 20.11904761904762,
+      "grad_norm": 0.07026033848524094,
+      "learning_rate": 1.1644327905824808e-05,
+      "loss": 0.0084,
+      "step": 1690
+    },
+    {
+      "epoch": 20.238095238095237,
+      "grad_norm": 0.2679937779903412,
+      "learning_rate": 1.1541766471241e-05,
+      "loss": 0.0022,
+      "step": 1700
+    },
+    {
+      "epoch": 20.357142857142858,
+      "grad_norm": 0.10295789688825607,
+      "learning_rate": 1.1439038637599529e-05,
+      "loss": 0.0008,
+      "step": 1710
+    },
+    {
+      "epoch": 20.476190476190474,
+      "grad_norm": 0.4343288242816925,
+      "learning_rate": 1.1336155492062439e-05,
+      "loss": 0.0021,
+      "step": 1720
+    },
+    {
+      "epoch": 20.595238095238095,
+      "grad_norm": 0.018273649737238884,
+      "learning_rate": 1.1233128138554222e-05,
+      "loss": 0.0006,
+      "step": 1730
+    },
+    {
+      "epoch": 20.714285714285715,
+      "grad_norm": 0.008875339291989803,
+      "learning_rate": 1.112996769656337e-05,
+      "loss": 0.0003,
+      "step": 1740
+    },
+    {
+      "epoch": 20.833333333333332,
+      "grad_norm": 0.21868984401226044,
+      "learning_rate": 1.1026685299942286e-05,
+      "loss": 0.0022,
+      "step": 1750
+    },
+    {
+      "epoch": 20.952380952380953,
+      "grad_norm": 0.024242576211690903,
+      "learning_rate": 1.0923292095705642e-05,
+      "loss": 0.003,
+      "step": 1760
+    },
+    {
+      "epoch": 21.071428571428573,
+      "grad_norm": 0.008948619477450848,
+      "learning_rate": 1.0819799242827299e-05,
+      "loss": 0.0046,
+      "step": 1770
+    },
+    {
+      "epoch": 21.19047619047619,
+      "grad_norm": 0.01921582594513893,
+      "learning_rate": 1.0716217911035952e-05,
+      "loss": 0.002,
+      "step": 1780
+    },
+    {
+      "epoch": 21.30952380952381,
+      "grad_norm": 0.015329894609749317,
+      "learning_rate": 1.0612559279609606e-05,
+      "loss": 0.0004,
+      "step": 1790
+    },
+    {
+      "epoch": 21.428571428571427,
+      "grad_norm": 0.03253422677516937,
+      "learning_rate": 1.0508834536169028e-05,
+      "loss": 0.0032,
+      "step": 1800
+    },
+    {
+      "epoch": 21.547619047619047,
+      "grad_norm": 0.007767899427562952,
+      "learning_rate": 1.0405054875470287e-05,
+      "loss": 0.0003,
+      "step": 1810
+    },
+    {
+      "epoch": 21.666666666666668,
+      "grad_norm": 0.014929098077118397,
+      "learning_rate": 1.030123149819654e-05,
+      "loss": 0.0052,
+      "step": 1820
+    },
+    {
+      "epoch": 21.785714285714285,
+      "grad_norm": 0.020312979817390442,
+      "learning_rate": 1.0197375609749164e-05,
+      "loss": 0.0006,
+      "step": 1830
+    },
+    {
+      "epoch": 21.904761904761905,
+      "grad_norm": 0.04301303252577782,
+      "learning_rate": 1.0093498419038394e-05,
+      "loss": 0.002,
+      "step": 1840
+    },
+    {
+      "epoch": 22.023809523809526,
+      "grad_norm": 0.011388319544494152,
+      "learning_rate": 9.989611137273556e-06,
+      "loss": 0.004,
+      "step": 1850
+    },
+    {
+      "epoch": 22.142857142857142,
+      "grad_norm": 0.02648976631462574,
+      "learning_rate": 9.885724976753078e-06,
+      "loss": 0.0005,
+      "step": 1860
+    },
+    {
+      "epoch": 22.261904761904763,
+      "grad_norm": 0.016934091225266457,
+      "learning_rate": 9.78185114965439e-06,
+      "loss": 0.0007,
+      "step": 1870
+    },
+    {
+      "epoch": 22.38095238095238,
+      "grad_norm": 0.008141864091157913,
+      "learning_rate": 9.678000866823789e-06,
+      "loss": 0.0031,
+      "step": 1880
+    },
+    {
+      "epoch": 22.5,
+      "grad_norm": 0.015341422520577908,
+      "learning_rate": 9.574185336566503e-06,
+      "loss": 0.0007,
+      "step": 1890
+    },
+    {
+      "epoch": 22.61904761904762,
+      "grad_norm": 0.013799485750496387,
+      "learning_rate": 9.470415763437003e-06,
+      "loss": 0.0033,
+      "step": 1900
+    },
+    {
+      "epoch": 22.738095238095237,
+      "grad_norm": 0.032908592373132706,
+      "learning_rate": 9.366703347029725e-06,
+      "loss": 0.001,
+      "step": 1910
+    },
+    {
+      "epoch": 22.857142857142858,
+      "grad_norm": 0.06811460107564926,
+      "learning_rate": 9.263059280770303e-06,
+      "loss": 0.0024,
+      "step": 1920
+    },
+    {
+      "epoch": 22.976190476190474,
+      "grad_norm": 0.045220863074064255,
+      "learning_rate": 9.159494750707527e-06,
+      "loss": 0.0004,
+      "step": 1930
+    },
+    {
+      "epoch": 23.095238095238095,
+      "grad_norm": 0.003873666515573859,
+      "learning_rate": 9.05602093430603e-06,
+      "loss": 0.0003,
+      "step": 1940
+    },
+    {
+      "epoch": 23.214285714285715,
+      "grad_norm": 0.013574629090726376,
+      "learning_rate": 8.952648999239948e-06,
+      "loss": 0.0035,
+      "step": 1950
+    },
+    {
+      "epoch": 23.333333333333332,
+      "grad_norm": 0.009078383445739746,
+      "learning_rate": 8.849390102187615e-06,
+      "loss": 0.0002,
+      "step": 1960
+    },
+    {
+      "epoch": 23.452380952380953,
+      "grad_norm": 0.0057939100079238415,
+      "learning_rate": 8.746255387627444e-06,
+      "loss": 0.0004,
+      "step": 1970
+    },
+    {
+      "epoch": 23.571428571428573,
+      "grad_norm": 0.019538553431630135,
+      "learning_rate": 8.643255986635152e-06,
+      "loss": 0.0002,
+      "step": 1980
+    },
+    {
+      "epoch": 23.69047619047619,
+      "grad_norm": 0.007959152571856976,
+      "learning_rate": 8.540403015682382e-06,
+      "loss": 0.0009,
+      "step": 1990
+    },
+    {
+      "epoch": 23.80952380952381,
+      "grad_norm": 0.009719247929751873,
+      "learning_rate": 8.437707575436943e-06,
+      "loss": 0.0078,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3360,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1931390331741798e+17,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe16ad85cf67a1d616e8a664749a043a7e42845bd6dfe8881e3e3c947d23497a
+size 5624

checkpoint-3000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-3000/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+  "bias": "none",
+  "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_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual.patch_embed|visual.blocks).*(?:o_proj|v_proj|down_proj|k_proj|q_proj|up_proj|gate_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-3000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9125f43477e44442eeeb0a5636962102d5fa86da13422a8be4b72a35cab5fd60
+size 73911112

checkpoint-3000/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-3000/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f287e8823b2411b8fb6a85cc5745d8b1b02be79332d47db6aa61959714c480e
+size 148047978

checkpoint-3000/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 12845056,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 2
+}

checkpoint-3000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f55565ad4212d927304dc332f26c49b3f14337c859de7f43c26f8335e8cce96
+size 14512