second model upload

.gitattributes

@@ -33,3 +33,9 @@ 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-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/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: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 2
+- 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: 100.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.46.1
+- Pytorch 2.4.0
+- Datasets 3.1.0
+- Tokenizers 0.20.3

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).*(?:up_proj|k_proj|gate_proj|o_proj|down_proj|q_proj|v_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:f2d8f2d7a0cd1eb16ffe2194563af3d428fde0c48dcd1cf8f6350451d30a184d
+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": 100.0,
+    "total_flos": 5.03081615753216e+16,
+    "train_loss": 0.057032368842141294,
+    "train_runtime": 3711.3142,
+    "train_samples_per_second": 2.694,
+    "train_steps_per_second": 1.347
+}

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).*(?:up_proj|k_proj|gate_proj|o_proj|down_proj|q_proj|v_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 sha256:032f76d4a06194757a6dffebde8b3ca9e4b47f0c9780c1ff1b87f07a55e96c56
+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:a8b425feecb648aa2613191cfb63336f2aac2737a73ddf72a20709c3c0c35f05
+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 sha256:33051b9eb3114c963021f9df60752af83921fd52e5809bd85ce27e94f9d0d9ad
+size 14512

checkpoint-1000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bccd7c24723c07f97d24e82405612113d129d077233ca61366b6299d4233c2d
+size 14512

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a04a4b89c1f6d532e91e51c94dbf6655bf22841225941d9103f7734956476d
+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 +1,144 @@
+{
+  "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",
+  "model_max_length": 32768,
+  "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": 20.0,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.939609527587891,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.4893,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.7112133502960205,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.2055,
+      "step": 20
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.128227710723877,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.0467,
+      "step": 30
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.812015175819397,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.959,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.001788854598999,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.8838,
+      "step": 50
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.275044322013855,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.8455,
+      "step": 60
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.9736475348472595,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.8018,
+      "step": 70
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.2415788173675537,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.7934,
+      "step": 80
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 2.08917236328125,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.7508,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7156405448913574,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6881,
+      "step": 100
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.8509552478790283,
+      "learning_rate": 4.4e-06,
+      "loss": 0.6296,
+      "step": 110
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.1180299520492554,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.599,
+      "step": 120
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.9558420181274414,
+      "learning_rate": 5.2e-06,
+      "loss": 0.6189,
+      "step": 130
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.513689637184143,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.6507,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.101956844329834,
+      "learning_rate": 6e-06,
+      "loss": 0.6767,
+      "step": 150
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 1.2160413265228271,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.5263,
+      "step": 160
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 2.2328133583068848,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 0.5254,
+      "step": 170
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 1.8659697771072388,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.526,
+      "step": 180
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 3.3415005207061768,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 0.5359,
+      "step": 190
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.0912972688674927,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.5413,
+      "step": 200
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 3.15617299079895,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 0.5434,
+      "step": 210
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 2.088568687438965,
+      "learning_rate": 8.8e-06,
+      "loss": 0.4533,
+      "step": 220
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 5.438419342041016,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 0.4051,
+      "step": 230
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 1.167334794998169,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.5039,
+      "step": 240
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.4560151100158691,
+      "learning_rate": 1e-05,
+      "loss": 0.4845,
+      "step": 250
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 2.4988670349121094,
+      "learning_rate": 1.04e-05,
+      "loss": 0.4003,
+      "step": 260
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": Infinity,
+      "learning_rate": 1.0760000000000002e-05,
+      "loss": 0.358,
+      "step": 270
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 1.568748950958252,
+      "learning_rate": 1.1160000000000002e-05,
+      "loss": 0.438,
+      "step": 280
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 2.2470250129699707,
+      "learning_rate": 1.156e-05,
+      "loss": 0.4482,
+      "step": 290
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.1772513389587402,
+      "learning_rate": 1.196e-05,
+      "loss": 0.4083,
+      "step": 300
+    },
+    {
+      "epoch": 6.2,
+      "grad_norm": 2.48183536529541,
+      "learning_rate": 1.236e-05,
+      "loss": 0.3352,
+      "step": 310
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 2.4329469203948975,
+      "learning_rate": 1.2760000000000001e-05,
+      "loss": 0.3115,
+      "step": 320
+    },
+    {
+      "epoch": 6.6,
+      "grad_norm": 3.1733779907226562,
+      "learning_rate": 1.3160000000000001e-05,
+      "loss": 0.3295,
+      "step": 330
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 1.5031541585922241,
+      "learning_rate": 1.3560000000000002e-05,
+      "loss": 0.3617,
+      "step": 340
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.4660649299621582,
+      "learning_rate": 1.396e-05,
+      "loss": 0.3997,
+      "step": 350
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 2.0959041118621826,
+      "learning_rate": 1.4360000000000001e-05,
+      "loss": 0.2882,
+      "step": 360
+    },
+    {
+      "epoch": 7.4,
+      "grad_norm": 2.1866960525512695,
+      "learning_rate": 1.4760000000000001e-05,
+      "loss": 0.1761,
+      "step": 370
+    },
+    {
+      "epoch": 7.6,
+      "grad_norm": 3.808837652206421,
+      "learning_rate": 1.516e-05,
+      "loss": 0.3476,
+      "step": 380
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 2.1240618228912354,
+      "learning_rate": 1.556e-05,
+      "loss": 0.2462,
+      "step": 390
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 4.748623847961426,
+      "learning_rate": 1.5960000000000003e-05,
+      "loss": 0.2915,
+      "step": 400
+    },
+    {
+      "epoch": 8.2,
+      "grad_norm": 1.3342574834823608,
+      "learning_rate": 1.636e-05,
+      "loss": 0.2063,
+      "step": 410
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 4.858347415924072,
+      "learning_rate": 1.6760000000000002e-05,
+      "loss": 0.1655,
+      "step": 420
+    },
+    {
+      "epoch": 8.6,
+      "grad_norm": 7.156524658203125,
+      "learning_rate": 1.7160000000000002e-05,
+      "loss": 0.3072,
+      "step": 430
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 1.796271562576294,
+      "learning_rate": 1.756e-05,
+      "loss": 0.2161,
+      "step": 440
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.3102816641330719,
+      "learning_rate": 1.796e-05,
+      "loss": 0.1655,
+      "step": 450
+    },
+    {
+      "epoch": 9.2,
+      "grad_norm": 2.9082212448120117,
+      "learning_rate": 1.8360000000000004e-05,
+      "loss": 0.1096,
+      "step": 460
+    },
+    {
+      "epoch": 9.4,
+      "grad_norm": 2.176609754562378,
+      "learning_rate": 1.876e-05,
+      "loss": 0.1441,
+      "step": 470
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 4.31577205657959,
+      "learning_rate": 1.916e-05,
+      "loss": 0.1766,
+      "step": 480
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 3.6560301780700684,
+      "learning_rate": 1.9560000000000002e-05,
+      "loss": 0.2017,
+      "step": 490
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.5466725826263428,
+      "learning_rate": 1.9960000000000002e-05,
+      "loss": 0.2644,
+      "step": 500
+    },
+    {
+      "epoch": 10.2,
+      "grad_norm": 1.722813606262207,
+      "learning_rate": 1.9999844036286483e-05,
+      "loss": 0.1303,
+      "step": 510
+    },
+    {
+      "epoch": 10.4,
+      "grad_norm": 1.9171879291534424,
+      "learning_rate": 1.9999210442038164e-05,
+      "loss": 0.1545,
+      "step": 520
+    },
+    {
+      "epoch": 10.6,
+      "grad_norm": 5.039783477783203,
+      "learning_rate": 1.999808950037968e-05,
+      "loss": 0.1664,
+      "step": 530
+    },
+    {
+      "epoch": 10.8,
+      "grad_norm": 1.7670263051986694,
+      "learning_rate": 1.9996481265944146e-05,
+      "loss": 0.1468,
+      "step": 540
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 2.348796844482422,
+      "learning_rate": 1.9994385817114644e-05,
+      "loss": 0.1501,
+      "step": 550
+    },
+    {
+      "epoch": 11.2,
+      "grad_norm": 0.6991663575172424,
+      "learning_rate": 1.9991803256020393e-05,
+      "loss": 0.0598,
+      "step": 560
+    },
+    {
+      "epoch": 11.4,
+      "grad_norm": 0.9841463565826416,
+      "learning_rate": 1.9988733708531772e-05,
+      "loss": 0.0975,
+      "step": 570
+    },
+    {
+      "epoch": 11.6,
+      "grad_norm": 0.5151156783103943,
+      "learning_rate": 1.99851773242542e-05,
+      "loss": 0.1535,
+      "step": 580
+    },
+    {
+      "epoch": 11.8,
+      "grad_norm": 0.2328900247812271,
+      "learning_rate": 1.9981134276520828e-05,
+      "loss": 0.1044,
+      "step": 590
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 6.50738525390625,
+      "learning_rate": 1.99766047623841e-05,
+      "loss": 0.1007,
+      "step": 600
+    },
+    {
+      "epoch": 12.2,
+      "grad_norm": 1.2217416763305664,
+      "learning_rate": 1.997158900260614e-05,
+      "loss": 0.0586,
+      "step": 610
+    },
+    {
+      "epoch": 12.4,
+      "grad_norm": 0.12162764370441437,
+      "learning_rate": 1.996608724164801e-05,
+      "loss": 0.0689,
+      "step": 620
+    },
+    {
+      "epoch": 12.6,
+      "grad_norm": 3.3592309951782227,
+      "learning_rate": 1.9960099747657774e-05,
+      "loss": 0.0902,
+      "step": 630
+    },
+    {
+      "epoch": 12.8,
+      "grad_norm": 1.7452058792114258,
+      "learning_rate": 1.995362681245744e-05,
+      "loss": 0.1005,
+      "step": 640
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 4.02609920501709,
+      "learning_rate": 1.9946668751528745e-05,
+      "loss": 0.0921,
+      "step": 650
+    },
+    {
+      "epoch": 13.2,
+      "grad_norm": 0.6409686207771301,
+      "learning_rate": 1.9939225903997748e-05,
+      "loss": 0.0846,
+      "step": 660
+    },
+    {
+      "epoch": 13.4,
+      "grad_norm": 0.5872007608413696,
+      "learning_rate": 1.9931298632618355e-05,
+      "loss": 0.0758,
+      "step": 670
+    },
+    {
+      "epoch": 13.6,
+      "grad_norm": 0.45962050557136536,
+      "learning_rate": 1.992288732375458e-05,
+      "loss": 0.0706,
+      "step": 680
+    },
+    {
+      "epoch": 13.8,
+      "grad_norm": 0.5623728632926941,
+      "learning_rate": 1.9913992387361747e-05,
+      "loss": 0.0872,
+      "step": 690
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 1.1793012619018555,
+      "learning_rate": 1.9904614256966514e-05,
+      "loss": 0.0889,
+      "step": 700
+    },
+    {
+      "epoch": 14.2,
+      "grad_norm": 1.6852632761001587,
+      "learning_rate": 1.9894753389645723e-05,
+      "loss": 0.0352,
+      "step": 710
+    },
+    {
+      "epoch": 14.4,
+      "grad_norm": 0.9700791835784912,
+      "learning_rate": 1.9884410266004134e-05,
+      "loss": 0.0595,
+      "step": 720
+    },
+    {
+      "epoch": 14.6,
+      "grad_norm": 1.602258324623108,
+      "learning_rate": 1.9873585390151003e-05,
+      "loss": 0.1022,
+      "step": 730
+    },
+    {
+      "epoch": 14.8,
+      "grad_norm": 1.9688293933868408,
+      "learning_rate": 1.986227928967551e-05,
+      "loss": 0.0556,
+      "step": 740
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.102990746498108,
+      "learning_rate": 1.9850492515621038e-05,
+      "loss": 0.0393,
+      "step": 750
+    },
+    {
+      "epoch": 15.2,
+      "grad_norm": 0.3437381684780121,
+      "learning_rate": 1.983822564245833e-05,
+      "loss": 0.0701,
+      "step": 760
+    },
+    {
+      "epoch": 15.4,
+      "grad_norm": 1.0362671613693237,
+      "learning_rate": 1.982547926805747e-05,
+      "loss": 0.0564,
+      "step": 770
+    },
+    {
+      "epoch": 15.6,
+      "grad_norm": 0.20574238896369934,
+      "learning_rate": 1.981225401365877e-05,
+      "loss": 0.0525,
+      "step": 780
+    },
+    {
+      "epoch": 15.8,
+      "grad_norm": 2.8671562671661377,
+      "learning_rate": 1.979855052384247e-05,
+      "loss": 0.0604,
+      "step": 790
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 1.1551826000213623,
+      "learning_rate": 1.9784369466497333e-05,
+      "loss": 0.1029,
+      "step": 800
+    },
+    {
+      "epoch": 16.2,
+      "grad_norm": 1.6653599739074707,
+      "learning_rate": 1.9769711532788083e-05,
+      "loss": 0.0592,
+      "step": 810
+    },
+    {
+      "epoch": 16.4,
+      "grad_norm": 0.7432021498680115,
+      "learning_rate": 1.9754577437121733e-05,
+      "loss": 0.0465,
+      "step": 820
+    },
+    {
+      "epoch": 16.6,
+      "grad_norm": 0.7289913892745972,
+      "learning_rate": 1.9738967917112752e-05,
+      "loss": 0.0338,
+      "step": 830
+    },
+    {
+      "epoch": 16.8,
+      "grad_norm": 0.05203216150403023,
+      "learning_rate": 1.9722883733547128e-05,
+      "loss": 0.1039,
+      "step": 840
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 0.6313950419425964,
+      "learning_rate": 1.9706325670345276e-05,
+      "loss": 0.0514,
+      "step": 850
+    },
+    {
+      "epoch": 17.2,
+      "grad_norm": 0.6369919180870056,
+      "learning_rate": 1.968929453452383e-05,
+      "loss": 0.0358,
+      "step": 860
+    },
+    {
+      "epoch": 17.4,
+      "grad_norm": 1.4422746896743774,
+      "learning_rate": 1.967179115615633e-05,
+      "loss": 0.0274,
+      "step": 870
+    },
+    {
+      "epoch": 17.6,
+      "grad_norm": 0.514399528503418,
+      "learning_rate": 1.965381638833274e-05,
+      "loss": 0.0279,
+      "step": 880
+    },
+    {
+      "epoch": 17.8,
+      "grad_norm": 0.05869906023144722,
+      "learning_rate": 1.963537110711789e-05,
+      "loss": 0.0477,
+      "step": 890
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.21828149259090424,
+      "learning_rate": 1.9616456211508756e-05,
+      "loss": 0.0343,
+      "step": 900
+    },
+    {
+      "epoch": 18.2,
+      "grad_norm": 0.0298184622079134,
+      "learning_rate": 1.9597072623390668e-05,
+      "loss": 0.0167,
+      "step": 910
+    },
+    {
+      "epoch": 18.4,
+      "grad_norm": 0.378787100315094,
+      "learning_rate": 1.9577221287492368e-05,
+      "loss": 0.0215,
+      "step": 920
+    },
+    {
+      "epoch": 18.6,
+      "grad_norm": 4.263318061828613,
+      "learning_rate": 1.9556903171339963e-05,
+      "loss": 0.0161,
+      "step": 930
+    },
+    {
+      "epoch": 18.8,
+      "grad_norm": 2.174684524536133,
+      "learning_rate": 1.9536119265209763e-05,
+      "loss": 0.0134,
+      "step": 940
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.03400244563817978,
+      "learning_rate": 1.951487058208003e-05,
+      "loss": 0.015,
+      "step": 950
+    },
+    {
+      "epoch": 19.2,
+      "grad_norm": 0.05419604852795601,
+      "learning_rate": 1.9493158157581617e-05,
+      "loss": 0.0112,
+      "step": 960
+    },
+    {
+      "epoch": 19.4,
+      "grad_norm": 0.058521125465631485,
+      "learning_rate": 1.9470983049947446e-05,
+      "loss": 0.0033,
+      "step": 970
+    },
+    {
+      "epoch": 19.6,
+      "grad_norm": 0.016082677990198135,
+      "learning_rate": 1.9448346339960984e-05,
+      "loss": 0.0192,
+      "step": 980
+    },
+    {
+      "epoch": 19.8,
+      "grad_norm": 6.2492570877075195,
+      "learning_rate": 1.9425249130903544e-05,
+      "loss": 0.0519,
+      "step": 990
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.238447666168213,
+      "learning_rate": 1.9401692548500504e-05,
+      "loss": 0.0251,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 100,
+  "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": 1.0061632348618752e+16,
+  "train_batch_size": 1,
+  "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:fa4e3872264c5ddee20fc06b01d4df10a537eb79ade4211e1c938063f5ceeae0
+size 5432

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).*(?:up_proj|k_proj|gate_proj|o_proj|down_proj|q_proj|v_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 sha256:4a28c80ef67071e304d78db2f5d96f486b1359515435e96173cefd85ee18bce6
+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 sha256:74e384e64729626e9495c7049318b6399822453adfee4f794109dd96a74f7c26
+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 sha256:2c68e52fd4325078bf8c6ba8d79859d6361cebcb355320ae2f7795f343d59474
+size 14512

checkpoint-2000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d45c5a7264eeca55ff22188c25c7d224c91ba109a345f56904c65dda7f1c3be
+size 14512

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2af837b3a9fca31994e69f44440e1bc2335bb3ce5849333903e6a471eef8bcc
+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 +1,144 @@
+{
+  "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",
+  "model_max_length": 32768,
+  "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": 40.0,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.939609527587891,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.4893,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.7112133502960205,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.2055,
+      "step": 20
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.128227710723877,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.0467,
+      "step": 30
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.812015175819397,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.959,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.001788854598999,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.8838,
+      "step": 50
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.275044322013855,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.8455,
+      "step": 60
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.9736475348472595,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.8018,
+      "step": 70
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.2415788173675537,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.7934,
+      "step": 80
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 2.08917236328125,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.7508,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7156405448913574,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6881,
+      "step": 100
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.8509552478790283,
+      "learning_rate": 4.4e-06,
+      "loss": 0.6296,
+      "step": 110
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.1180299520492554,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.599,
+      "step": 120
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.9558420181274414,
+      "learning_rate": 5.2e-06,
+      "loss": 0.6189,
+      "step": 130
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.513689637184143,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.6507,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.101956844329834,
+      "learning_rate": 6e-06,
+      "loss": 0.6767,
+      "step": 150
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 1.2160413265228271,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.5263,
+      "step": 160
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 2.2328133583068848,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 0.5254,
+      "step": 170
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 1.8659697771072388,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.526,
+      "step": 180
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 3.3415005207061768,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 0.5359,
+      "step": 190
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.0912972688674927,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.5413,
+      "step": 200
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 3.15617299079895,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 0.5434,
+      "step": 210
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 2.088568687438965,
+      "learning_rate": 8.8e-06,
+      "loss": 0.4533,
+      "step": 220
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 5.438419342041016,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 0.4051,
+      "step": 230
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 1.167334794998169,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.5039,
+      "step": 240
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.4560151100158691,
+      "learning_rate": 1e-05,
+      "loss": 0.4845,
+      "step": 250
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 2.4988670349121094,
+      "learning_rate": 1.04e-05,
+      "loss": 0.4003,
+      "step": 260
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": Infinity,
+      "learning_rate": 1.0760000000000002e-05,
+      "loss": 0.358,
+      "step": 270
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 1.568748950958252,
+      "learning_rate": 1.1160000000000002e-05,
+      "loss": 0.438,
+      "step": 280
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 2.2470250129699707,
+      "learning_rate": 1.156e-05,
+      "loss": 0.4482,
+      "step": 290
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.1772513389587402,
+      "learning_rate": 1.196e-05,
+      "loss": 0.4083,
+      "step": 300
+    },
+    {
+      "epoch": 6.2,
+      "grad_norm": 2.48183536529541,
+      "learning_rate": 1.236e-05,
+      "loss": 0.3352,
+      "step": 310
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 2.4329469203948975,
+      "learning_rate": 1.2760000000000001e-05,
+      "loss": 0.3115,
+      "step": 320
+    },
+    {
+      "epoch": 6.6,
+      "grad_norm": 3.1733779907226562,
+      "learning_rate": 1.3160000000000001e-05,
+      "loss": 0.3295,
+      "step": 330
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 1.5031541585922241,
+      "learning_rate": 1.3560000000000002e-05,
+      "loss": 0.3617,
+      "step": 340
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.4660649299621582,
+      "learning_rate": 1.396e-05,
+      "loss": 0.3997,
+      "step": 350
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 2.0959041118621826,
+      "learning_rate": 1.4360000000000001e-05,
+      "loss": 0.2882,
+      "step": 360
+    },
+    {
+      "epoch": 7.4,
+      "grad_norm": 2.1866960525512695,
+      "learning_rate": 1.4760000000000001e-05,
+      "loss": 0.1761,
+      "step": 370
+    },
+    {
+      "epoch": 7.6,
+      "grad_norm": 3.808837652206421,
+      "learning_rate": 1.516e-05,
+      "loss": 0.3476,
+      "step": 380
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 2.1240618228912354,
+      "learning_rate": 1.556e-05,
+      "loss": 0.2462,
+      "step": 390
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 4.748623847961426,
+      "learning_rate": 1.5960000000000003e-05,
+      "loss": 0.2915,
+      "step": 400
+    },
+    {
+      "epoch": 8.2,
+      "grad_norm": 1.3342574834823608,
+      "learning_rate": 1.636e-05,
+      "loss": 0.2063,
+      "step": 410
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 4.858347415924072,
+      "learning_rate": 1.6760000000000002e-05,
+      "loss": 0.1655,
+      "step": 420
+    },
+    {
+      "epoch": 8.6,
+      "grad_norm": 7.156524658203125,
+      "learning_rate": 1.7160000000000002e-05,
+      "loss": 0.3072,
+      "step": 430
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 1.796271562576294,
+      "learning_rate": 1.756e-05,
+      "loss": 0.2161,
+      "step": 440
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.3102816641330719,
+      "learning_rate": 1.796e-05,
+      "loss": 0.1655,
+      "step": 450
+    },
+    {
+      "epoch": 9.2,
+      "grad_norm": 2.9082212448120117,
+      "learning_rate": 1.8360000000000004e-05,
+      "loss": 0.1096,
+      "step": 460
+    },
+    {
+      "epoch": 9.4,
+      "grad_norm": 2.176609754562378,
+      "learning_rate": 1.876e-05,
+      "loss": 0.1441,
+      "step": 470
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 4.31577205657959,
+      "learning_rate": 1.916e-05,
+      "loss": 0.1766,
+      "step": 480
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 3.6560301780700684,
+      "learning_rate": 1.9560000000000002e-05,
+      "loss": 0.2017,
+      "step": 490
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.5466725826263428,
+      "learning_rate": 1.9960000000000002e-05,
+      "loss": 0.2644,
+      "step": 500
+    },
+    {
+      "epoch": 10.2,
+      "grad_norm": 1.722813606262207,
+      "learning_rate": 1.9999844036286483e-05,
+      "loss": 0.1303,
+      "step": 510
+    },
+    {
+      "epoch": 10.4,
+      "grad_norm": 1.9171879291534424,
+      "learning_rate": 1.9999210442038164e-05,
+      "loss": 0.1545,
+      "step": 520
+    },
+    {
+      "epoch": 10.6,
+      "grad_norm": 5.039783477783203,
+      "learning_rate": 1.999808950037968e-05,
+      "loss": 0.1664,
+      "step": 530
+    },
+    {
+      "epoch": 10.8,
+      "grad_norm": 1.7670263051986694,
+      "learning_rate": 1.9996481265944146e-05,
+      "loss": 0.1468,
+      "step": 540
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 2.348796844482422,
+      "learning_rate": 1.9994385817114644e-05,
+      "loss": 0.1501,
+      "step": 550
+    },
+    {
+      "epoch": 11.2,
+      "grad_norm": 0.6991663575172424,
+      "learning_rate": 1.9991803256020393e-05,
+      "loss": 0.0598,
+      "step": 560
+    },
+    {
+      "epoch": 11.4,
+      "grad_norm": 0.9841463565826416,
+      "learning_rate": 1.9988733708531772e-05,
+      "loss": 0.0975,
+      "step": 570
+    },
+    {
+      "epoch": 11.6,
+      "grad_norm": 0.5151156783103943,
+      "learning_rate": 1.99851773242542e-05,
+      "loss": 0.1535,
+      "step": 580
+    },
+    {
+      "epoch": 11.8,
+      "grad_norm": 0.2328900247812271,
+      "learning_rate": 1.9981134276520828e-05,
+      "loss": 0.1044,
+      "step": 590
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 6.50738525390625,
+      "learning_rate": 1.99766047623841e-05,
+      "loss": 0.1007,
+      "step": 600
+    },
+    {
+      "epoch": 12.2,
+      "grad_norm": 1.2217416763305664,
+      "learning_rate": 1.997158900260614e-05,
+      "loss": 0.0586,
+      "step": 610
+    },
+    {
+      "epoch": 12.4,
+      "grad_norm": 0.12162764370441437,
+      "learning_rate": 1.996608724164801e-05,
+      "loss": 0.0689,
+      "step": 620
+    },
+    {
+      "epoch": 12.6,
+      "grad_norm": 3.3592309951782227,
+      "learning_rate": 1.9960099747657774e-05,
+      "loss": 0.0902,
+      "step": 630
+    },
+    {
+      "epoch": 12.8,
+      "grad_norm": 1.7452058792114258,
+      "learning_rate": 1.995362681245744e-05,
+      "loss": 0.1005,
+      "step": 640
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 4.02609920501709,
+      "learning_rate": 1.9946668751528745e-05,
+      "loss": 0.0921,
+      "step": 650
+    },
+    {
+      "epoch": 13.2,
+      "grad_norm": 0.6409686207771301,
+      "learning_rate": 1.9939225903997748e-05,
+      "loss": 0.0846,
+      "step": 660
+    },
+    {
+      "epoch": 13.4,
+      "grad_norm": 0.5872007608413696,
+      "learning_rate": 1.9931298632618355e-05,
+      "loss": 0.0758,
+      "step": 670
+    },
+    {
+      "epoch": 13.6,
+      "grad_norm": 0.45962050557136536,
+      "learning_rate": 1.992288732375458e-05,
+      "loss": 0.0706,
+      "step": 680
+    },
+    {
+      "epoch": 13.8,
+      "grad_norm": 0.5623728632926941,
+      "learning_rate": 1.9913992387361747e-05,
+      "loss": 0.0872,
+      "step": 690
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 1.1793012619018555,
+      "learning_rate": 1.9904614256966514e-05,
+      "loss": 0.0889,
+      "step": 700
+    },
+    {
+      "epoch": 14.2,
+      "grad_norm": 1.6852632761001587,
+      "learning_rate": 1.9894753389645723e-05,
+      "loss": 0.0352,
+      "step": 710
+    },
+    {
+      "epoch": 14.4,
+      "grad_norm": 0.9700791835784912,
+      "learning_rate": 1.9884410266004134e-05,
+      "loss": 0.0595,
+      "step": 720
+    },
+    {
+      "epoch": 14.6,
+      "grad_norm": 1.602258324623108,
+      "learning_rate": 1.9873585390151003e-05,
+      "loss": 0.1022,
+      "step": 730
+    },
+    {
+      "epoch": 14.8,
+      "grad_norm": 1.9688293933868408,
+      "learning_rate": 1.986227928967551e-05,
+      "loss": 0.0556,
+      "step": 740
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.102990746498108,
+      "learning_rate": 1.9850492515621038e-05,
+      "loss": 0.0393,
+      "step": 750
+    },
+    {
+      "epoch": 15.2,
+      "grad_norm": 0.3437381684780121,
+      "learning_rate": 1.983822564245833e-05,
+      "loss": 0.0701,
+      "step": 760
+    },
+    {
+      "epoch": 15.4,
+      "grad_norm": 1.0362671613693237,
+      "learning_rate": 1.982547926805747e-05,
+      "loss": 0.0564,
+      "step": 770
+    },
+    {
+      "epoch": 15.6,
+      "grad_norm": 0.20574238896369934,
+      "learning_rate": 1.981225401365877e-05,
+      "loss": 0.0525,
+      "step": 780
+    },
+    {
+      "epoch": 15.8,
+      "grad_norm": 2.8671562671661377,
+      "learning_rate": 1.979855052384247e-05,
+      "loss": 0.0604,
+      "step": 790
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 1.1551826000213623,
+      "learning_rate": 1.9784369466497333e-05,
+      "loss": 0.1029,
+      "step": 800
+    },
+    {
+      "epoch": 16.2,
+      "grad_norm": 1.6653599739074707,
+      "learning_rate": 1.9769711532788083e-05,
+      "loss": 0.0592,
+      "step": 810
+    },
+    {
+      "epoch": 16.4,
+      "grad_norm": 0.7432021498680115,
+      "learning_rate": 1.9754577437121733e-05,
+      "loss": 0.0465,
+      "step": 820
+    },
+    {
+      "epoch": 16.6,
+      "grad_norm": 0.7289913892745972,
+      "learning_rate": 1.9738967917112752e-05,
+      "loss": 0.0338,
+      "step": 830
+    },
+    {
+      "epoch": 16.8,
+      "grad_norm": 0.05203216150403023,
+      "learning_rate": 1.9722883733547128e-05,
+      "loss": 0.1039,
+      "step": 840
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 0.6313950419425964,
+      "learning_rate": 1.9706325670345276e-05,
+      "loss": 0.0514,
+      "step": 850
+    },
+    {
+      "epoch": 17.2,
+      "grad_norm": 0.6369919180870056,
+      "learning_rate": 1.968929453452383e-05,
+      "loss": 0.0358,
+      "step": 860
+    },
+    {
+      "epoch": 17.4,
+      "grad_norm": 1.4422746896743774,
+      "learning_rate": 1.967179115615633e-05,
+      "loss": 0.0274,
+      "step": 870
+    },
+    {
+      "epoch": 17.6,
+      "grad_norm": 0.514399528503418,
+      "learning_rate": 1.965381638833274e-05,
+      "loss": 0.0279,
+      "step": 880
+    },
+    {
+      "epoch": 17.8,
+      "grad_norm": 0.05869906023144722,
+      "learning_rate": 1.963537110711789e-05,
+      "loss": 0.0477,
+      "step": 890
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.21828149259090424,
+      "learning_rate": 1.9616456211508756e-05,
+      "loss": 0.0343,
+      "step": 900
+    },
+    {
+      "epoch": 18.2,
+      "grad_norm": 0.0298184622079134,
+      "learning_rate": 1.9597072623390668e-05,
+      "loss": 0.0167,
+      "step": 910
+    },
+    {
+      "epoch": 18.4,
+      "grad_norm": 0.378787100315094,
+      "learning_rate": 1.9577221287492368e-05,
+      "loss": 0.0215,
+      "step": 920
+    },
+    {
+      "epoch": 18.6,
+      "grad_norm": 4.263318061828613,
+      "learning_rate": 1.9556903171339963e-05,
+      "loss": 0.0161,
+      "step": 930
+    },
+    {
+      "epoch": 18.8,
+      "grad_norm": 2.174684524536133,
+      "learning_rate": 1.9536119265209763e-05,
+      "loss": 0.0134,
+      "step": 940
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.03400244563817978,
+      "learning_rate": 1.951487058208003e-05,
+      "loss": 0.015,
+      "step": 950
+    },
+    {
+      "epoch": 19.2,
+      "grad_norm": 0.05419604852795601,
+      "learning_rate": 1.9493158157581617e-05,
+      "loss": 0.0112,
+      "step": 960
+    },
+    {
+      "epoch": 19.4,
+      "grad_norm": 0.058521125465631485,
+      "learning_rate": 1.9470983049947446e-05,
+      "loss": 0.0033,
+      "step": 970
+    },
+    {
+      "epoch": 19.6,
+      "grad_norm": 0.016082677990198135,
+      "learning_rate": 1.9448346339960984e-05,
+      "loss": 0.0192,
+      "step": 980
+    },
+    {
+      "epoch": 19.8,
+      "grad_norm": 6.2492570877075195,
+      "learning_rate": 1.9425249130903544e-05,
+      "loss": 0.0519,
+      "step": 990
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.238447666168213,
+      "learning_rate": 1.9401692548500504e-05,
+      "loss": 0.0251,
+      "step": 1000
+    },
+    {
+      "epoch": 20.2,
+      "grad_norm": 0.035032495856285095,
+      "learning_rate": 1.937767774086646e-05,
+      "loss": 0.0127,
+      "step": 1010
+    },
+    {
+      "epoch": 20.4,
+      "grad_norm": 0.01225972082465887,
+      "learning_rate": 1.935320587844926e-05,
+      "loss": 0.004,
+      "step": 1020
+    },
+    {
+      "epoch": 20.6,
+      "grad_norm": 0.004545880481600761,
+      "learning_rate": 1.9328278153972947e-05,
+      "loss": 0.0356,
+      "step": 1030
+    },
+    {
+      "epoch": 20.8,
+      "grad_norm": 3.91441011428833,
+      "learning_rate": 1.9302895782379648e-05,
+      "loss": 0.0355,
+      "step": 1040
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 0.48417937755584717,
+      "learning_rate": 1.9277060000770342e-05,
+      "loss": 0.0043,
+      "step": 1050
+    },
+    {
+      "epoch": 21.2,
+      "grad_norm": 3.8912832736968994,
+      "learning_rate": 1.925077206834458e-05,
+      "loss": 0.0242,
+      "step": 1060
+    },
+    {
+      "epoch": 21.4,
+      "grad_norm": 0.013348647393286228,
+      "learning_rate": 1.9224033266339103e-05,
+      "loss": 0.0076,
+      "step": 1070
+    },
+    {
+      "epoch": 21.6,
+      "grad_norm": 0.11039220541715622,
+      "learning_rate": 1.9196844897965393e-05,
+      "loss": 0.0145,
+      "step": 1080
+    },
+    {
+      "epoch": 21.8,
+      "grad_norm": 3.4672281742095947,
+      "learning_rate": 1.9169208288346168e-05,
+      "loss": 0.0033,
+      "step": 1090
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 0.006285279057919979,
+      "learning_rate": 1.914112478445079e-05,
+      "loss": 0.0107,
+      "step": 1100
+    },
+    {
+      "epoch": 22.2,
+      "grad_norm": 0.04273529723286629,
+      "learning_rate": 1.9112595755029625e-05,
+      "loss": 0.0483,
+      "step": 1110
+    },
+    {
+      "epoch": 22.4,
+      "grad_norm": 0.007396802771836519,
+      "learning_rate": 1.9083622590547313e-05,
+      "loss": 0.0021,
+      "step": 1120
+    },
+    {
+      "epoch": 22.6,
+      "grad_norm": 0.2701977491378784,
+      "learning_rate": 1.905420670311502e-05,
+      "loss": 0.0027,
+      "step": 1130
+    },
+    {
+      "epoch": 22.8,
+      "grad_norm": 0.016060367226600647,
+      "learning_rate": 1.9024349526421596e-05,
+      "loss": 0.0217,
+      "step": 1140
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 0.017666257917881012,
+      "learning_rate": 1.899405251566371e-05,
+      "loss": 0.0458,
+      "step": 1150
+    },
+    {
+      "epoch": 23.2,
+      "grad_norm": 0.043862633407115936,
+      "learning_rate": 1.896331714747493e-05,
+      "loss": 0.0011,
+      "step": 1160
+    },
+    {
+      "epoch": 23.4,
+      "grad_norm": 0.031046241521835327,
+      "learning_rate": 1.893214491985374e-05,
+      "loss": 0.0128,
+      "step": 1170
+    },
+    {
+      "epoch": 23.6,
+      "grad_norm": 0.005483916029334068,
+      "learning_rate": 1.8900537352090523e-05,
+      "loss": 0.0108,
+      "step": 1180
+    },
+    {
+      "epoch": 23.8,
+      "grad_norm": 0.03962108865380287,
+      "learning_rate": 1.886849598469356e-05,
+      "loss": 0.0007,
+      "step": 1190
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.06565005332231522,
+      "learning_rate": 1.8836022379313884e-05,
+      "loss": 0.0173,
+      "step": 1200
+    },
+    {
+      "epoch": 24.2,
+      "grad_norm": 0.006141431163996458,
+      "learning_rate": 1.8803118118669203e-05,
+      "loss": 0.001,
+      "step": 1210
+    },
+    {
+      "epoch": 24.4,
+      "grad_norm": 0.008573741652071476,
+      "learning_rate": 1.8769784806466768e-05,
+      "loss": 0.0003,
+      "step": 1220
+    },
+    {
+      "epoch": 24.6,
+      "grad_norm": 0.016578705981373787,
+      "learning_rate": 1.8736024067325188e-05,
+      "loss": 0.0043,
+      "step": 1230
+    },
+    {
+      "epoch": 24.8,
+      "grad_norm": 0.006640794221311808,
+      "learning_rate": 1.870183754669526e-05,
+      "loss": 0.0002,
+      "step": 1240
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.8556722402572632,
+      "learning_rate": 1.8667226910779767e-05,
+      "loss": 0.0041,
+      "step": 1250
+    },
+    {
+      "epoch": 25.2,
+      "grad_norm": 0.0022739043924957514,
+      "learning_rate": 1.863219384645227e-05,
+      "loss": 0.0003,
+      "step": 1260
+    },
+    {
+      "epoch": 25.4,
+      "grad_norm": 0.012654612772166729,
+      "learning_rate": 1.8596740061174912e-05,
+      "loss": 0.0005,
+      "step": 1270
+    },
+    {
+      "epoch": 25.6,
+      "grad_norm": 0.004489220213145018,
+      "learning_rate": 1.8560867282915164e-05,
+      "loss": 0.0041,
+      "step": 1280
+    },
+    {
+      "epoch": 25.8,
+      "grad_norm": 0.006669621914625168,
+      "learning_rate": 1.8524577260061628e-05,
+      "loss": 0.0044,
+      "step": 1290
+    },
+    {
+      "epoch": 26.0,
+      "grad_norm": 0.12849736213684082,
+      "learning_rate": 1.848787176133882e-05,
+      "loss": 0.0006,
+      "step": 1300
+    },
+    {
+      "epoch": 26.2,
+      "grad_norm": 0.003363212803378701,
+      "learning_rate": 1.8450752575720967e-05,
+      "loss": 0.0002,
+      "step": 1310
+    },
+    {
+      "epoch": 26.4,
+      "grad_norm": 0.005168403964489698,
+      "learning_rate": 1.8413221512344805e-05,
+      "loss": 0.0001,
+      "step": 1320
+    },
+    {
+      "epoch": 26.6,
+      "grad_norm": 0.006153238005936146,
+      "learning_rate": 1.837528040042142e-05,
+      "loss": 0.0005,
+      "step": 1330
+    },
+    {
+      "epoch": 26.8,
+      "grad_norm": 0.005247591994702816,
+      "learning_rate": 1.8336931089147076e-05,
+      "loss": 0.0002,
+      "step": 1340
+    },
+    {
+      "epoch": 27.0,
+      "grad_norm": 0.008389480412006378,
+      "learning_rate": 1.82981754476131e-05,
+      "loss": 0.0061,
+      "step": 1350
+    },
+    {
+      "epoch": 27.2,
+      "grad_norm": 0.001621560426428914,
+      "learning_rate": 1.8259015364714786e-05,
+      "loss": 0.0002,
+      "step": 1360
+    },
+    {
+      "epoch": 27.4,
+      "grad_norm": 0.012759492732584476,
+      "learning_rate": 1.8219452749059332e-05,
+      "loss": 0.0009,
+      "step": 1370
+    },
+    {
+      "epoch": 27.6,
+      "grad_norm": 0.0008200361044146121,
+      "learning_rate": 1.8179489528872808e-05,
+      "loss": 0.0002,
+      "step": 1380
+    },
+    {
+      "epoch": 27.8,
+      "grad_norm": 0.010921397246420383,
+      "learning_rate": 1.8139127651906183e-05,
+      "loss": 0.0001,
+      "step": 1390
+    },
+    {
+      "epoch": 28.0,
+      "grad_norm": 0.009295720607042313,
+      "learning_rate": 1.80983690853404e-05,
+      "loss": 0.0001,
+      "step": 1400
+    },
+    {
+      "epoch": 28.2,
+      "grad_norm": 0.003324209712445736,
+      "learning_rate": 1.8057215815690494e-05,
+      "loss": 0.0001,
+      "step": 1410
+    },
+    {
+      "epoch": 28.4,
+      "grad_norm": 0.19921115040779114,
+      "learning_rate": 1.8015669848708768e-05,
+      "loss": 0.0003,
+      "step": 1420
+    },
+    {
+      "epoch": 28.6,
+      "grad_norm": 0.005366879981011152,
+      "learning_rate": 1.7973733209287036e-05,
+      "loss": 0.0001,
+      "step": 1430
+    },
+    {
+      "epoch": 28.8,
+      "grad_norm": 0.0017453564796596766,
+      "learning_rate": 1.793140794135795e-05,
+      "loss": 0.0029,
+      "step": 1440
+    },
+    {
+      "epoch": 29.0,
+      "grad_norm": 0.013708272948861122,
+      "learning_rate": 1.7888696107795343e-05,
+      "loss": 0.0001,
+      "step": 1450
+    },
+    {
+      "epoch": 29.2,
+      "grad_norm": 0.0043100654147565365,
+      "learning_rate": 1.7845599790313735e-05,
+      "loss": 0.0003,
+      "step": 1460
+    },
+    {
+      "epoch": 29.4,
+      "grad_norm": 0.02302490547299385,
+      "learning_rate": 1.780212108936684e-05,
+      "loss": 0.0011,
+      "step": 1470
+    },
+    {
+      "epoch": 29.6,
+      "grad_norm": 0.004419188946485519,
+      "learning_rate": 1.7758262124045195e-05,
+      "loss": 0.0001,
+      "step": 1480
+    },
+    {
+      "epoch": 29.8,
+      "grad_norm": 0.0013392951805144548,
+      "learning_rate": 1.7714025031972904e-05,
+      "loss": 0.0003,
+      "step": 1490
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.0014274229761213064,
+      "learning_rate": 1.7669411969203417e-05,
+      "loss": 0.0002,
+      "step": 1500
+    },
+    {
+      "epoch": 30.2,
+      "grad_norm": 0.001878496608696878,
+      "learning_rate": 1.762442511011448e-05,
+      "loss": 0.0001,
+      "step": 1510
+    },
+    {
+      "epoch": 30.4,
+      "grad_norm": 0.005069437436759472,
+      "learning_rate": 1.7579066647302134e-05,
+      "loss": 0.0001,
+      "step": 1520
+    },
+    {
+      "epoch": 30.6,
+      "grad_norm": 0.0014868683647364378,
+      "learning_rate": 1.7533338791473872e-05,
+      "loss": 0.0001,
+      "step": 1530
+    },
+    {
+      "epoch": 30.8,
+      "grad_norm": 0.003168011549860239,
+      "learning_rate": 1.7487243771340862e-05,
+      "loss": 0.0001,
+      "step": 1540
+    },
+    {
+      "epoch": 31.0,
+      "grad_norm": 0.004825201351195574,
+      "learning_rate": 1.7440783833509366e-05,
+      "loss": 0.0001,
+      "step": 1550
+    },
+    {
+      "epoch": 31.2,
+      "grad_norm": 0.006287866272032261,
+      "learning_rate": 1.7393961242371203e-05,
+      "loss": 0.0001,
+      "step": 1560
+    },
+    {
+      "epoch": 31.4,
+      "grad_norm": 0.005126502364873886,
+      "learning_rate": 1.7346778279993417e-05,
+      "loss": 0.0001,
+      "step": 1570
+    },
+    {
+      "epoch": 31.6,
+      "grad_norm": 0.0005843121325597167,
+      "learning_rate": 1.7299237246007018e-05,
+      "loss": 0.0001,
+      "step": 1580
+    },
+    {
+      "epoch": 31.8,
+      "grad_norm": 0.0023757207673043013,
+      "learning_rate": 1.7251340457494934e-05,
+      "loss": 0.0001,
+      "step": 1590
+    },
+    {
+      "epoch": 32.0,
+      "grad_norm": 0.004019857384264469,
+      "learning_rate": 1.720309024887907e-05,
+      "loss": 0.0001,
+      "step": 1600
+    },
+    {
+      "epoch": 32.2,
+      "grad_norm": 0.006111355032771826,
+      "learning_rate": 1.715448897180652e-05,
+      "loss": 0.0001,
+      "step": 1610
+    },
+    {
+      "epoch": 32.4,
+      "grad_norm": 0.000667453627102077,
+      "learning_rate": 1.710553899503496e-05,
+      "loss": 0.0001,
+      "step": 1620
+    },
+    {
+      "epoch": 32.6,
+      "grad_norm": 0.0010104542598128319,
+      "learning_rate": 1.705624270431721e-05,
+      "loss": 0.0001,
+      "step": 1630
+    },
+    {
+      "epoch": 32.8,
+      "grad_norm": 0.004804989788681269,
+      "learning_rate": 1.700660250228492e-05,
+      "loss": 0.0001,
+      "step": 1640
+    },
+    {
+      "epoch": 33.0,
+      "grad_norm": 0.004056953825056553,
+      "learning_rate": 1.695662080833151e-05,
+      "loss": 0.0001,
+      "step": 1650
+    },
+    {
+      "epoch": 33.2,
+      "grad_norm": 0.0015452856896445155,
+      "learning_rate": 1.690630005849423e-05,
+      "loss": 0.0001,
+      "step": 1660
+    },
+    {
+      "epoch": 33.4,
+      "grad_norm": 0.0012899715220555663,
+      "learning_rate": 1.6855642705335438e-05,
+      "loss": 0.0001,
+      "step": 1670
+    },
+    {
+      "epoch": 33.6,
+      "grad_norm": 0.0010839162860065699,
+      "learning_rate": 1.6804651217823055e-05,
+      "loss": 0.0001,
+      "step": 1680
+    },
+    {
+      "epoch": 33.8,
+      "grad_norm": 0.0011267494410276413,
+      "learning_rate": 1.6753328081210244e-05,
+      "loss": 0.0001,
+      "step": 1690
+    },
+    {
+      "epoch": 34.0,
+      "grad_norm": 0.0027927302289754152,
+      "learning_rate": 1.6701675796914284e-05,
+      "loss": 0.0,
+      "step": 1700
+    },
+    {
+      "epoch": 34.2,
+      "grad_norm": 0.0011741920607164502,
+      "learning_rate": 1.6649696882394635e-05,
+      "loss": 0.0001,
+      "step": 1710
+    },
+    {
+      "epoch": 34.4,
+      "grad_norm": 0.0019491278799250722,
+      "learning_rate": 1.6597393871030264e-05,
+      "loss": 0.0,
+      "step": 1720
+    },
+    {
+      "epoch": 34.6,
+      "grad_norm": 0.0015785045688971877,
+      "learning_rate": 1.654476931199615e-05,
+      "loss": 0.0,
+      "step": 1730
+    },
+    {
+      "epoch": 34.8,
+      "grad_norm": 0.0008629497606307268,
+      "learning_rate": 1.649182577013906e-05,
+      "loss": 0.0001,
+      "step": 1740
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.003077285597100854,
+      "learning_rate": 1.643856582585254e-05,
+      "loss": 0.0001,
+      "step": 1750
+    },
+    {
+      "epoch": 35.2,
+      "grad_norm": 0.0013041843194514513,
+      "learning_rate": 1.6384992074951124e-05,
+      "loss": 0.0,
+      "step": 1760
+    },
+    {
+      "epoch": 35.4,
+      "grad_norm": 0.0008168126805685461,
+      "learning_rate": 1.6331107128543856e-05,
+      "loss": 0.0001,
+      "step": 1770
+    },
+    {
+      "epoch": 35.6,
+      "grad_norm": 0.0013320008292794228,
+      "learning_rate": 1.6276913612907005e-05,
+      "loss": 0.0001,
+      "step": 1780
+    },
+    {
+      "epoch": 35.8,
+      "grad_norm": 0.0011947667226195335,
+      "learning_rate": 1.6222414169356066e-05,
+      "loss": 0.0001,
+      "step": 1790
+    },
+    {
+      "epoch": 36.0,
+      "grad_norm": 0.0013605114072561264,
+      "learning_rate": 1.6167611454117027e-05,
+      "loss": 0.0001,
+      "step": 1800
+    },
+    {
+      "epoch": 36.2,
+      "grad_norm": 0.00024013180518522859,
+      "learning_rate": 1.611250813819692e-05,
+      "loss": 0.0,
+      "step": 1810
+    },
+    {
+      "epoch": 36.4,
+      "grad_norm": 0.002005120040848851,
+      "learning_rate": 1.6057106907253617e-05,
+      "loss": 0.0,
+      "step": 1820
+    },
+    {
+      "epoch": 36.6,
+      "grad_norm": 0.0015634404262527823,
+      "learning_rate": 1.6001410461464955e-05,
+      "loss": 0.0001,
+      "step": 1830
+    },
+    {
+      "epoch": 36.8,
+      "grad_norm": 0.0009015756659209728,
+      "learning_rate": 1.5945421515397135e-05,
+      "loss": 0.0,
+      "step": 1840
+    },
+    {
+      "epoch": 37.0,
+      "grad_norm": 0.001351571292616427,
+      "learning_rate": 1.5889142797872387e-05,
+      "loss": 0.0,
+      "step": 1850
+    },
+    {
+      "epoch": 37.2,
+      "grad_norm": 0.0014051242033019662,
+      "learning_rate": 1.5832577051836016e-05,
+      "loss": 0.0,
+      "step": 1860
+    },
+    {
+      "epoch": 37.4,
+      "grad_norm": 0.0011573507217690349,
+      "learning_rate": 1.5775727034222675e-05,
+      "loss": 0.0,
+      "step": 1870
+    },
+    {
+      "epoch": 37.6,
+      "grad_norm": 0.0010998898651450872,
+      "learning_rate": 1.5718595515822027e-05,
+      "loss": 0.0,
+      "step": 1880
+    },
+    {
+      "epoch": 37.8,
+      "grad_norm": 0.001832842011936009,
+      "learning_rate": 1.5661185281143666e-05,
+      "loss": 0.0001,
+      "step": 1890
+    },
+    {
+      "epoch": 38.0,
+      "grad_norm": 0.0008399503421969712,
+      "learning_rate": 1.5603499128281447e-05,
+      "loss": 0.0,
+      "step": 1900
+    },
+    {
+      "epoch": 38.2,
+      "grad_norm": 0.0016098183114081621,
+      "learning_rate": 1.5545539868777075e-05,
+      "loss": 0.0,
+      "step": 1910
+    },
+    {
+      "epoch": 38.4,
+      "grad_norm": 0.0031196950003504753,
+      "learning_rate": 1.5487310327483087e-05,
+      "loss": 0.0,
+      "step": 1920
+    },
+    {
+      "epoch": 38.6,
+      "grad_norm": 0.0025677145458757877,
+      "learning_rate": 1.5428813342425177e-05,
+      "loss": 0.0,
+      "step": 1930
+    },
+    {
+      "epoch": 38.8,
+      "grad_norm": 0.00022408693621400744,
+      "learning_rate": 1.5370051764663872e-05,
+      "loss": 0.0,
+      "step": 1940
+    },
+    {
+      "epoch": 39.0,
+      "grad_norm": 0.001144173787906766,
+      "learning_rate": 1.5311028458155567e-05,
+      "loss": 0.0,
+      "step": 1950
+    },
+    {
+      "epoch": 39.2,
+      "grad_norm": 0.0006699798977933824,
+      "learning_rate": 1.5251746299612959e-05,
+      "loss": 0.0,
+      "step": 1960
+    },
+    {
+      "epoch": 39.4,
+      "grad_norm": 0.0007150991004891694,
+      "learning_rate": 1.5192208178364815e-05,
+      "loss": 0.0,
+      "step": 1970
+    },
+    {
+      "epoch": 39.6,
+      "grad_norm": 0.0018977021099999547,
+      "learning_rate": 1.5132416996215171e-05,
+      "loss": 0.0,
+      "step": 1980
+    },
+    {
+      "epoch": 39.8,
+      "grad_norm": 0.0005208357470110059,
+      "learning_rate": 1.5072375667301893e-05,
+      "loss": 0.0,
+      "step": 1990
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.0018139018211513758,
+      "learning_rate": 1.5012087117954643e-05,
+      "loss": 0.0,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 100,
+  "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": 2.0123264688848896e+16,
+  "train_batch_size": 1,
+  "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:fa4e3872264c5ddee20fc06b01d4df10a537eb79ade4211e1c938063f5ceeae0
+size 5432

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).*(?:up_proj|k_proj|gate_proj|o_proj|down_proj|q_proj|v_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:ad775057166bc5fd187e9266c268170e91e2e2d499e0ba5df3fd3b1c197cda94
+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 sha256:24763c79fa39c5f39bcde9e05d5defc0d1d0703a75df050260a9de693954f9e6
+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 sha256:634e4dc0c63d6e5a5b9bc55f0e9f3b8ffffa8f13bfb95ee9b78a01a73dc7eb63
+size 14512