Initial model upload

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: train_2024-09-20-07-59-22
+  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. -->
+
+# train_2024-09-20-07-59-22
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) on the mllm_demo 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.45.0.dev0
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual).*(?:q_proj|up_proj|k_proj|down_proj|v_proj|o_proj|gate_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbe742ab1fff08cca8e1920428f0bce4ae35e374f37d9cf77c0c9282684d3e85
+size 36981072

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 +1,9 @@
+{
+    "epoch": 2.9936575052854124,
+    "num_input_tokens_seen": 4597544,
+    "total_flos": 5.475245368337203e+16,
+    "train_loss": 2.9544576898133013,
+    "train_runtime": 3114.1126,
+    "train_samples_per_second": 1.822,
+    "train_steps_per_second": 0.114
+}

checkpoint-100/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-100/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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual).*(?:q_proj|up_proj|k_proj|down_proj|v_proj|o_proj|gate_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6531152952d0b28f958fa340d31da691089a8e27291a917d5f61610efe069aad
+size 36981072

checkpoint-100/added_tokens.json

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

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f95f20c81cd51f1dfc6095c11bcccfa9eb8c3092c253702591f9ad516d075f
+size 74188650

checkpoint-100/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-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04dd9dcd59991cca937944d88165fb0151aa24efcec26f3d7e0c4328a22a9a34
+size 1064

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8456659619450317,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.042283298097251586,
+      "grad_norm": 1.2008394002914429,
+      "learning_rate": 4.9975392245612254e-05,
+      "loss": 4.1473,
+      "num_input_tokens_seen": 68384,
+      "step": 5
+    },
+    {
+      "epoch": 0.08456659619450317,
+      "grad_norm": 1.1565380096435547,
+      "learning_rate": 4.9901617425775067e-05,
+      "loss": 4.021,
+      "num_input_tokens_seen": 128224,
+      "step": 10
+    },
+    {
+      "epoch": 0.12684989429175475,
+      "grad_norm": 0.972896158695221,
+      "learning_rate": 4.9778820775100185e-05,
+      "loss": 3.8212,
+      "num_input_tokens_seen": 197760,
+      "step": 15
+    },
+    {
+      "epoch": 0.16913319238900634,
+      "grad_norm": 1.0641047954559326,
+      "learning_rate": 4.9607244033573156e-05,
+      "loss": 3.7653,
+      "num_input_tokens_seen": 262832,
+      "step": 20
+    },
+    {
+      "epoch": 0.21141649048625794,
+      "grad_norm": 1.0994701385498047,
+      "learning_rate": 4.93872249706591e-05,
+      "loss": 3.7434,
+      "num_input_tokens_seen": 333472,
+      "step": 25
+    },
+    {
+      "epoch": 0.2536997885835095,
+      "grad_norm": 1.193864107131958,
+      "learning_rate": 4.91191967203629e-05,
+      "loss": 3.5488,
+      "num_input_tokens_seen": 393616,
+      "step": 30
+    },
+    {
+      "epoch": 0.2959830866807611,
+      "grad_norm": 1.0215297937393188,
+      "learning_rate": 4.8803686928552736e-05,
+      "loss": 3.5732,
+      "num_input_tokens_seen": 458240,
+      "step": 35
+    },
+    {
+      "epoch": 0.3382663847780127,
+      "grad_norm": 1.312198519706726,
+      "learning_rate": 4.84413167142257e-05,
+      "loss": 3.7108,
+      "num_input_tokens_seen": 524576,
+      "step": 40
+    },
+    {
+      "epoch": 0.38054968287526425,
+      "grad_norm": 1.3579617738723755,
+      "learning_rate": 4.803279944676032e-05,
+      "loss": 3.6871,
+      "num_input_tokens_seen": 591856,
+      "step": 45
+    },
+    {
+      "epoch": 0.42283298097251587,
+      "grad_norm": 1.4524191617965698,
+      "learning_rate": 4.7578939341563095e-05,
+      "loss": 3.286,
+      "num_input_tokens_seen": 655648,
+      "step": 50
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 1.248831033706665,
+      "learning_rate": 4.70806298768736e-05,
+      "loss": 3.5377,
+      "num_input_tokens_seen": 721280,
+      "step": 55
+    },
+    {
+      "epoch": 0.507399577167019,
+      "grad_norm": 1.2427473068237305,
+      "learning_rate": 4.653885203484515e-05,
+      "loss": 3.56,
+      "num_input_tokens_seen": 784688,
+      "step": 60
+    },
+    {
+      "epoch": 0.5496828752642706,
+      "grad_norm": 1.323653221130371,
+      "learning_rate": 4.595467237036329e-05,
+      "loss": 3.4937,
+      "num_input_tokens_seen": 850848,
+      "step": 65
+    },
+    {
+      "epoch": 0.5919661733615222,
+      "grad_norm": 1.3730229139328003,
+      "learning_rate": 4.532924091140417e-05,
+      "loss": 3.3823,
+      "num_input_tokens_seen": 912480,
+      "step": 70
+    },
+    {
+      "epoch": 0.6342494714587738,
+      "grad_norm": 1.5328903198242188,
+      "learning_rate": 4.466378889506607e-05,
+      "loss": 3.3798,
+      "num_input_tokens_seen": 978448,
+      "step": 75
+    },
+    {
+      "epoch": 0.6765327695560254,
+      "grad_norm": 1.4153543710708618,
+      "learning_rate": 4.395962634373097e-05,
+      "loss": 3.3044,
+      "num_input_tokens_seen": 1041280,
+      "step": 80
+    },
+    {
+      "epoch": 0.718816067653277,
+      "grad_norm": 1.6301600933074951,
+      "learning_rate": 4.3218139486127854e-05,
+      "loss": 3.3661,
+      "num_input_tokens_seen": 1102224,
+      "step": 85
+    },
+    {
+      "epoch": 0.7610993657505285,
+      "grad_norm": 1.6634522676467896,
+      "learning_rate": 4.2440788028374624e-05,
+      "loss": 3.3829,
+      "num_input_tokens_seen": 1166576,
+      "step": 90
+    },
+    {
+      "epoch": 0.8033826638477801,
+      "grad_norm": 1.4539167881011963,
+      "learning_rate": 4.1629102280370904e-05,
+      "loss": 3.2241,
+      "num_input_tokens_seen": 1230096,
+      "step": 95
+    },
+    {
+      "epoch": 0.8456659619450317,
+      "grad_norm": 1.453364372253418,
+      "learning_rate": 4.0784680143198836e-05,
+      "loss": 3.0931,
+      "num_input_tokens_seen": 1297968,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 354,
+  "num_input_tokens_seen": 1297968,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5457586224840704e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ffc1f66e5aa3de4b714f2b3822cf0f4055bcd46a4096c6e5c3e47b3d4540a1
+size 5432

checkpoint-200/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-200/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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual).*(?:q_proj|up_proj|k_proj|down_proj|v_proj|o_proj|gate_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa4d40e33e11107719ab5bf9501376ee613320df6a77255b90a0c6c0a0d0c9e
+size 36981072

checkpoint-200/added_tokens.json

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

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08e6b9fcbb722812a26827515001fb3b132631d15e5597f61fcd8df6fe9fb67a
+size 74188650

checkpoint-200/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-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38fcdee1f6f088caee5d91891180bcd8066f8dc1f962727fbfed0a1194bbedb
+size 1064

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,353 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6913319238900635,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.042283298097251586,
+      "grad_norm": 1.2008394002914429,
+      "learning_rate": 4.9975392245612254e-05,
+      "loss": 4.1473,
+      "num_input_tokens_seen": 68384,
+      "step": 5
+    },
+    {
+      "epoch": 0.08456659619450317,
+      "grad_norm": 1.1565380096435547,
+      "learning_rate": 4.9901617425775067e-05,
+      "loss": 4.021,
+      "num_input_tokens_seen": 128224,
+      "step": 10
+    },
+    {
+      "epoch": 0.12684989429175475,
+      "grad_norm": 0.972896158695221,
+      "learning_rate": 4.9778820775100185e-05,
+      "loss": 3.8212,
+      "num_input_tokens_seen": 197760,
+      "step": 15
+    },
+    {
+      "epoch": 0.16913319238900634,
+      "grad_norm": 1.0641047954559326,
+      "learning_rate": 4.9607244033573156e-05,
+      "loss": 3.7653,
+      "num_input_tokens_seen": 262832,
+      "step": 20
+    },
+    {
+      "epoch": 0.21141649048625794,
+      "grad_norm": 1.0994701385498047,
+      "learning_rate": 4.93872249706591e-05,
+      "loss": 3.7434,
+      "num_input_tokens_seen": 333472,
+      "step": 25
+    },
+    {
+      "epoch": 0.2536997885835095,
+      "grad_norm": 1.193864107131958,
+      "learning_rate": 4.91191967203629e-05,
+      "loss": 3.5488,
+      "num_input_tokens_seen": 393616,
+      "step": 30
+    },
+    {
+      "epoch": 0.2959830866807611,
+      "grad_norm": 1.0215297937393188,
+      "learning_rate": 4.8803686928552736e-05,
+      "loss": 3.5732,
+      "num_input_tokens_seen": 458240,
+      "step": 35
+    },
+    {
+      "epoch": 0.3382663847780127,
+      "grad_norm": 1.312198519706726,
+      "learning_rate": 4.84413167142257e-05,
+      "loss": 3.7108,
+      "num_input_tokens_seen": 524576,
+      "step": 40
+    },
+    {
+      "epoch": 0.38054968287526425,
+      "grad_norm": 1.3579617738723755,
+      "learning_rate": 4.803279944676032e-05,
+      "loss": 3.6871,
+      "num_input_tokens_seen": 591856,
+      "step": 45
+    },
+    {
+      "epoch": 0.42283298097251587,
+      "grad_norm": 1.4524191617965698,
+      "learning_rate": 4.7578939341563095e-05,
+      "loss": 3.286,
+      "num_input_tokens_seen": 655648,
+      "step": 50
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 1.248831033706665,
+      "learning_rate": 4.70806298768736e-05,
+      "loss": 3.5377,
+      "num_input_tokens_seen": 721280,
+      "step": 55
+    },
+    {
+      "epoch": 0.507399577167019,
+      "grad_norm": 1.2427473068237305,
+      "learning_rate": 4.653885203484515e-05,
+      "loss": 3.56,
+      "num_input_tokens_seen": 784688,
+      "step": 60
+    },
+    {
+      "epoch": 0.5496828752642706,
+      "grad_norm": 1.323653221130371,
+      "learning_rate": 4.595467237036329e-05,
+      "loss": 3.4937,
+      "num_input_tokens_seen": 850848,
+      "step": 65
+    },
+    {
+      "epoch": 0.5919661733615222,
+      "grad_norm": 1.3730229139328003,
+      "learning_rate": 4.532924091140417e-05,
+      "loss": 3.3823,
+      "num_input_tokens_seen": 912480,
+      "step": 70
+    },
+    {
+      "epoch": 0.6342494714587738,
+      "grad_norm": 1.5328903198242188,
+      "learning_rate": 4.466378889506607e-05,
+      "loss": 3.3798,
+      "num_input_tokens_seen": 978448,
+      "step": 75
+    },
+    {
+      "epoch": 0.6765327695560254,
+      "grad_norm": 1.4153543710708618,
+      "learning_rate": 4.395962634373097e-05,
+      "loss": 3.3044,
+      "num_input_tokens_seen": 1041280,
+      "step": 80
+    },
+    {
+      "epoch": 0.718816067653277,
+      "grad_norm": 1.6301600933074951,
+      "learning_rate": 4.3218139486127854e-05,
+      "loss": 3.3661,
+      "num_input_tokens_seen": 1102224,
+      "step": 85
+    },
+    {
+      "epoch": 0.7610993657505285,
+      "grad_norm": 1.6634522676467896,
+      "learning_rate": 4.2440788028374624e-05,
+      "loss": 3.3829,
+      "num_input_tokens_seen": 1166576,
+      "step": 90
+    },
+    {
+      "epoch": 0.8033826638477801,
+      "grad_norm": 1.4539167881011963,
+      "learning_rate": 4.1629102280370904e-05,
+      "loss": 3.2241,
+      "num_input_tokens_seen": 1230096,
+      "step": 95
+    },
+    {
+      "epoch": 0.8456659619450317,
+      "grad_norm": 1.453364372253418,
+      "learning_rate": 4.0784680143198836e-05,
+      "loss": 3.0931,
+      "num_input_tokens_seen": 1297968,
+      "step": 100
+    },
+    {
+      "epoch": 0.8879492600422833,
+      "grad_norm": 2.0559964179992676,
+      "learning_rate": 3.990918396346254e-05,
+      "loss": 3.3581,
+      "num_input_tokens_seen": 1361760,
+      "step": 105
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 2.0426218509674072,
+      "learning_rate": 3.900433726075865e-05,
+      "loss": 3.2308,
+      "num_input_tokens_seen": 1422096,
+      "step": 110
+    },
+    {
+      "epoch": 0.9725158562367865,
+      "grad_norm": 1.7696195840835571,
+      "learning_rate": 3.8071921334720696e-05,
+      "loss": 3.1427,
+      "num_input_tokens_seen": 1491120,
+      "step": 115
+    },
+    {
+      "epoch": 1.014799154334038,
+      "grad_norm": 2.3205981254577637,
+      "learning_rate": 3.711377175831626e-05,
+      "loss": 3.0988,
+      "num_input_tokens_seen": 1556440,
+      "step": 120
+    },
+    {
+      "epoch": 1.0570824524312896,
+      "grad_norm": 1.7631757259368896,
+      "learning_rate": 3.613177476430079e-05,
+      "loss": 3.0695,
+      "num_input_tokens_seen": 1624200,
+      "step": 125
+    },
+    {
+      "epoch": 1.0993657505285412,
+      "grad_norm": 2.32861328125,
+      "learning_rate": 3.512786353194134e-05,
+      "loss": 3.1109,
+      "num_input_tokens_seen": 1686600,
+      "step": 130
+    },
+    {
+      "epoch": 1.1416490486257929,
+      "grad_norm": 2.1291067600250244,
+      "learning_rate": 3.410401438132056e-05,
+      "loss": 3.116,
+      "num_input_tokens_seen": 1755144,
+      "step": 135
+    },
+    {
+      "epoch": 1.1839323467230445,
+      "grad_norm": 1.8158444166183472,
+      "learning_rate": 3.3062242882712724e-05,
+      "loss": 2.9528,
+      "num_input_tokens_seen": 1819672,
+      "step": 140
+    },
+    {
+      "epoch": 1.226215644820296,
+      "grad_norm": 2.161515951156616,
+      "learning_rate": 3.200459988869111e-05,
+      "loss": 2.8494,
+      "num_input_tokens_seen": 1886136,
+      "step": 145
+    },
+    {
+      "epoch": 1.2684989429175475,
+      "grad_norm": 2.321112632751465,
+      "learning_rate": 3.093316749677788e-05,
+      "loss": 3.1525,
+      "num_input_tokens_seen": 1947656,
+      "step": 150
+    },
+    {
+      "epoch": 1.3107822410147991,
+      "grad_norm": 2.4329445362091064,
+      "learning_rate": 2.985005495058446e-05,
+      "loss": 2.8991,
+      "num_input_tokens_seen": 2013272,
+      "step": 155
+    },
+    {
+      "epoch": 1.3530655391120507,
+      "grad_norm": 2.7929720878601074,
+      "learning_rate": 2.875739448751176e-05,
+      "loss": 3.026,
+      "num_input_tokens_seen": 2079816,
+      "step": 160
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 2.6059908866882324,
+      "learning_rate": 2.7657337141184138e-05,
+      "loss": 2.8813,
+      "num_input_tokens_seen": 2146008,
+      "step": 165
+    },
+    {
+      "epoch": 1.437632135306554,
+      "grad_norm": 2.831233501434326,
+      "learning_rate": 2.655204850688085e-05,
+      "loss": 2.7721,
+      "num_input_tokens_seen": 2212840,
+      "step": 170
+    },
+    {
+      "epoch": 1.4799154334038054,
+      "grad_norm": 2.757953643798828,
+      "learning_rate": 2.5443704478301154e-05,
+      "loss": 2.737,
+      "num_input_tokens_seen": 2278824,
+      "step": 175
+    },
+    {
+      "epoch": 1.522198731501057,
+      "grad_norm": 2.8655178546905518,
+      "learning_rate": 2.433448696405563e-05,
+      "loss": 2.6645,
+      "num_input_tokens_seen": 2339768,
+      "step": 180
+    },
+    {
+      "epoch": 1.5644820295983086,
+      "grad_norm": 2.8346216678619385,
+      "learning_rate": 2.3226579592316538e-05,
+      "loss": 2.7233,
+      "num_input_tokens_seen": 2407976,
+      "step": 185
+    },
+    {
+      "epoch": 1.6067653276955602,
+      "grad_norm": 2.432692766189575,
+      "learning_rate": 2.2122163412082927e-05,
+      "loss": 2.7463,
+      "num_input_tokens_seen": 2469176,
+      "step": 190
+    },
+    {
+      "epoch": 1.6490486257928119,
+      "grad_norm": 3.0815346240997314,
+      "learning_rate": 2.1023412599523204e-05,
+      "loss": 2.8348,
+      "num_input_tokens_seen": 2528152,
+      "step": 195
+    },
+    {
+      "epoch": 1.6913319238900635,
+      "grad_norm": 3.362581968307495,
+      "learning_rate": 1.993249017784766e-05,
+      "loss": 2.7732,
+      "num_input_tokens_seen": 2588984,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 354,
+  "num_input_tokens_seen": 2588984,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.083238062474035e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ffc1f66e5aa3de4b714f2b3822cf0f4055bcd46a4096c6e5c3e47b3d4540a1
+size 5432

checkpoint-300/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-300/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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual).*(?:q_proj|up_proj|k_proj|down_proj|v_proj|o_proj|gate_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bc6b3d730c2d3f46f7683df010eb128bc39338ebd58ef6ac0a012f0e3292f42
+size 36981072

checkpoint-300/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-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da7125dc0295b65e9c1567b237eb0f6fe7f7ea14ed978261f30c820248b2db51
+size 74188650

checkpoint-300/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-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b536bbd5401df732c4ca4af58f86f6646b737fee8a39cc0d33f379aeb951bbc1
+size 1064

checkpoint-300/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-300/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,513 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.536997885835095,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.042283298097251586,
+      "grad_norm": 1.2008394002914429,
+      "learning_rate": 4.9975392245612254e-05,
+      "loss": 4.1473,
+      "num_input_tokens_seen": 68384,
+      "step": 5
+    },
+    {
+      "epoch": 0.08456659619450317,
+      "grad_norm": 1.1565380096435547,
+      "learning_rate": 4.9901617425775067e-05,
+      "loss": 4.021,
+      "num_input_tokens_seen": 128224,
+      "step": 10
+    },
+    {
+      "epoch": 0.12684989429175475,
+      "grad_norm": 0.972896158695221,
+      "learning_rate": 4.9778820775100185e-05,
+      "loss": 3.8212,
+      "num_input_tokens_seen": 197760,
+      "step": 15
+    },
+    {
+      "epoch": 0.16913319238900634,
+      "grad_norm": 1.0641047954559326,
+      "learning_rate": 4.9607244033573156e-05,
+      "loss": 3.7653,
+      "num_input_tokens_seen": 262832,
+      "step": 20
+    },
+    {
+      "epoch": 0.21141649048625794,
+      "grad_norm": 1.0994701385498047,
+      "learning_rate": 4.93872249706591e-05,
+      "loss": 3.7434,
+      "num_input_tokens_seen": 333472,
+      "step": 25
+    },
+    {
+      "epoch": 0.2536997885835095,
+      "grad_norm": 1.193864107131958,
+      "learning_rate": 4.91191967203629e-05,
+      "loss": 3.5488,
+      "num_input_tokens_seen": 393616,
+      "step": 30
+    },
+    {
+      "epoch": 0.2959830866807611,
+      "grad_norm": 1.0215297937393188,
+      "learning_rate": 4.8803686928552736e-05,
+      "loss": 3.5732,
+      "num_input_tokens_seen": 458240,
+      "step": 35
+    },
+    {
+      "epoch": 0.3382663847780127,
+      "grad_norm": 1.312198519706726,
+      "learning_rate": 4.84413167142257e-05,
+      "loss": 3.7108,
+      "num_input_tokens_seen": 524576,
+      "step": 40
+    },
+    {
+      "epoch": 0.38054968287526425,
+      "grad_norm": 1.3579617738723755,
+      "learning_rate": 4.803279944676032e-05,
+      "loss": 3.6871,
+      "num_input_tokens_seen": 591856,
+      "step": 45
+    },
+    {
+      "epoch": 0.42283298097251587,
+      "grad_norm": 1.4524191617965698,
+      "learning_rate": 4.7578939341563095e-05,
+      "loss": 3.286,
+      "num_input_tokens_seen": 655648,
+      "step": 50
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 1.248831033706665,
+      "learning_rate": 4.70806298768736e-05,
+      "loss": 3.5377,
+      "num_input_tokens_seen": 721280,
+      "step": 55
+    },
+    {
+      "epoch": 0.507399577167019,
+      "grad_norm": 1.2427473068237305,
+      "learning_rate": 4.653885203484515e-05,
+      "loss": 3.56,
+      "num_input_tokens_seen": 784688,
+      "step": 60
+    },
+    {
+      "epoch": 0.5496828752642706,
+      "grad_norm": 1.323653221130371,
+      "learning_rate": 4.595467237036329e-05,
+      "loss": 3.4937,
+      "num_input_tokens_seen": 850848,
+      "step": 65
+    },
+    {
+      "epoch": 0.5919661733615222,
+      "grad_norm": 1.3730229139328003,
+      "learning_rate": 4.532924091140417e-05,
+      "loss": 3.3823,
+      "num_input_tokens_seen": 912480,
+      "step": 70
+    },
+    {
+      "epoch": 0.6342494714587738,
+      "grad_norm": 1.5328903198242188,
+      "learning_rate": 4.466378889506607e-05,
+      "loss": 3.3798,
+      "num_input_tokens_seen": 978448,
+      "step": 75
+    },
+    {
+      "epoch": 0.6765327695560254,
+      "grad_norm": 1.4153543710708618,
+      "learning_rate": 4.395962634373097e-05,
+      "loss": 3.3044,
+      "num_input_tokens_seen": 1041280,
+      "step": 80
+    },
+    {
+      "epoch": 0.718816067653277,
+      "grad_norm": 1.6301600933074951,
+      "learning_rate": 4.3218139486127854e-05,
+      "loss": 3.3661,
+      "num_input_tokens_seen": 1102224,
+      "step": 85
+    },
+    {
+      "epoch": 0.7610993657505285,
+      "grad_norm": 1.6634522676467896,
+      "learning_rate": 4.2440788028374624e-05,
+      "loss": 3.3829,
+      "num_input_tokens_seen": 1166576,
+      "step": 90
+    },
+    {
+      "epoch": 0.8033826638477801,
+      "grad_norm": 1.4539167881011963,
+      "learning_rate": 4.1629102280370904e-05,
+      "loss": 3.2241,
+      "num_input_tokens_seen": 1230096,
+      "step": 95
+    },
+    {
+      "epoch": 0.8456659619450317,
+      "grad_norm": 1.453364372253418,
+      "learning_rate": 4.0784680143198836e-05,
+      "loss": 3.0931,
+      "num_input_tokens_seen": 1297968,
+      "step": 100
+    },
+    {
+      "epoch": 0.8879492600422833,
+      "grad_norm": 2.0559964179992676,
+      "learning_rate": 3.990918396346254e-05,
+      "loss": 3.3581,
+      "num_input_tokens_seen": 1361760,
+      "step": 105
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 2.0426218509674072,
+      "learning_rate": 3.900433726075865e-05,
+      "loss": 3.2308,
+      "num_input_tokens_seen": 1422096,
+      "step": 110
+    },
+    {
+      "epoch": 0.9725158562367865,
+      "grad_norm": 1.7696195840835571,
+      "learning_rate": 3.8071921334720696e-05,
+      "loss": 3.1427,
+      "num_input_tokens_seen": 1491120,
+      "step": 115
+    },
+    {
+      "epoch": 1.014799154334038,
+      "grad_norm": 2.3205981254577637,
+      "learning_rate": 3.711377175831626e-05,
+      "loss": 3.0988,
+      "num_input_tokens_seen": 1556440,
+      "step": 120
+    },
+    {
+      "epoch": 1.0570824524312896,
+      "grad_norm": 1.7631757259368896,
+      "learning_rate": 3.613177476430079e-05,
+      "loss": 3.0695,
+      "num_input_tokens_seen": 1624200,
+      "step": 125
+    },
+    {
+      "epoch": 1.0993657505285412,
+      "grad_norm": 2.32861328125,
+      "learning_rate": 3.512786353194134e-05,
+      "loss": 3.1109,
+      "num_input_tokens_seen": 1686600,
+      "step": 130
+    },
+    {
+      "epoch": 1.1416490486257929,
+      "grad_norm": 2.1291067600250244,
+      "learning_rate": 3.410401438132056e-05,
+      "loss": 3.116,
+      "num_input_tokens_seen": 1755144,
+      "step": 135
+    },
+    {
+      "epoch": 1.1839323467230445,
+      "grad_norm": 1.8158444166183472,
+      "learning_rate": 3.3062242882712724e-05,
+      "loss": 2.9528,
+      "num_input_tokens_seen": 1819672,
+      "step": 140
+    },
+    {
+      "epoch": 1.226215644820296,
+      "grad_norm": 2.161515951156616,
+      "learning_rate": 3.200459988869111e-05,
+      "loss": 2.8494,
+      "num_input_tokens_seen": 1886136,
+      "step": 145
+    },
+    {
+      "epoch": 1.2684989429175475,
+      "grad_norm": 2.321112632751465,
+      "learning_rate": 3.093316749677788e-05,
+      "loss": 3.1525,
+      "num_input_tokens_seen": 1947656,
+      "step": 150
+    },
+    {
+      "epoch": 1.3107822410147991,
+      "grad_norm": 2.4329445362091064,
+      "learning_rate": 2.985005495058446e-05,
+      "loss": 2.8991,
+      "num_input_tokens_seen": 2013272,
+      "step": 155
+    },
+    {
+      "epoch": 1.3530655391120507,
+      "grad_norm": 2.7929720878601074,
+      "learning_rate": 2.875739448751176e-05,
+      "loss": 3.026,
+      "num_input_tokens_seen": 2079816,
+      "step": 160
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 2.6059908866882324,
+      "learning_rate": 2.7657337141184138e-05,
+      "loss": 2.8813,
+      "num_input_tokens_seen": 2146008,
+      "step": 165
+    },
+    {
+      "epoch": 1.437632135306554,
+      "grad_norm": 2.831233501434326,
+      "learning_rate": 2.655204850688085e-05,
+      "loss": 2.7721,
+      "num_input_tokens_seen": 2212840,
+      "step": 170
+    },
+    {
+      "epoch": 1.4799154334038054,
+      "grad_norm": 2.757953643798828,
+      "learning_rate": 2.5443704478301154e-05,
+      "loss": 2.737,
+      "num_input_tokens_seen": 2278824,
+      "step": 175
+    },
+    {
+      "epoch": 1.522198731501057,
+      "grad_norm": 2.8655178546905518,
+      "learning_rate": 2.433448696405563e-05,
+      "loss": 2.6645,
+      "num_input_tokens_seen": 2339768,
+      "step": 180
+    },
+    {
+      "epoch": 1.5644820295983086,
+      "grad_norm": 2.8346216678619385,
+      "learning_rate": 2.3226579592316538e-05,
+      "loss": 2.7233,
+      "num_input_tokens_seen": 2407976,
+      "step": 185
+    },
+    {
+      "epoch": 1.6067653276955602,
+      "grad_norm": 2.432692766189575,
+      "learning_rate": 2.2122163412082927e-05,
+      "loss": 2.7463,
+      "num_input_tokens_seen": 2469176,
+      "step": 190
+    },
+    {
+      "epoch": 1.6490486257928119,
+      "grad_norm": 3.0815346240997314,
+      "learning_rate": 2.1023412599523204e-05,
+      "loss": 2.8348,
+      "num_input_tokens_seen": 2528152,
+      "step": 195
+    },
+    {
+      "epoch": 1.6913319238900635,
+      "grad_norm": 3.362581968307495,
+      "learning_rate": 1.993249017784766e-05,
+      "loss": 2.7732,
+      "num_input_tokens_seen": 2588984,
+      "step": 200
+    },
+    {
+      "epoch": 1.733615221987315,
+      "grad_norm": 3.2196719646453857,
+      "learning_rate": 1.8851543759137007e-05,
+      "loss": 2.7693,
+      "num_input_tokens_seen": 2657016,
+      "step": 205
+    },
+    {
+      "epoch": 1.7758985200845667,
+      "grad_norm": 2.6926162242889404,
+      "learning_rate": 1.778270131650948e-05,
+      "loss": 2.6524,
+      "num_input_tokens_seen": 2719656,
+      "step": 210
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 2.9597244262695312,
+      "learning_rate": 1.672806699494966e-05,
+      "loss": 2.7338,
+      "num_input_tokens_seen": 2786168,
+      "step": 215
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 3.4195263385772705,
+      "learning_rate": 1.5689716969045848e-05,
+      "loss": 2.7467,
+      "num_input_tokens_seen": 2849400,
+      "step": 220
+    },
+    {
+      "epoch": 1.9027484143763214,
+      "grad_norm": 2.8715097904205322,
+      "learning_rate": 1.4669695355790552e-05,
+      "loss": 2.5769,
+      "num_input_tokens_seen": 2917000,
+      "step": 225
+    },
+    {
+      "epoch": 1.945031712473573,
+      "grad_norm": 3.514866352081299,
+      "learning_rate": 1.3670010190490073e-05,
+      "loss": 2.784,
+      "num_input_tokens_seen": 2980712,
+      "step": 230
+    },
+    {
+      "epoch": 1.9873150105708244,
+      "grad_norm": 3.751493215560913,
+      "learning_rate": 1.2692629473705453e-05,
+      "loss": 2.7729,
+      "num_input_tokens_seen": 3045848,
+      "step": 235
+    },
+    {
+      "epoch": 2.029598308668076,
+      "grad_norm": 2.950978994369507,
+      "learning_rate": 1.173947729700644e-05,
+      "loss": 2.8171,
+      "num_input_tokens_seen": 3105128,
+      "step": 240
+    },
+    {
+      "epoch": 2.0718816067653276,
+      "grad_norm": 3.061615467071533,
+      "learning_rate": 1.081243005516571e-05,
+      "loss": 2.5436,
+      "num_input_tokens_seen": 3175016,
+      "step": 245
+    },
+    {
+      "epoch": 2.1141649048625792,
+      "grad_norm": 3.8741908073425293,
+      "learning_rate": 9.913312752249903e-06,
+      "loss": 2.4681,
+      "num_input_tokens_seen": 3245608,
+      "step": 250
+    },
+    {
+      "epoch": 2.156448202959831,
+      "grad_norm": 4.65464448928833,
+      "learning_rate": 9.043895408879505e-06,
+      "loss": 2.4036,
+      "num_input_tokens_seen": 3308040,
+      "step": 255
+    },
+    {
+      "epoch": 2.1987315010570825,
+      "grad_norm": 3.1693899631500244,
+      "learning_rate": 8.20588957773018e-06,
+      "loss": 2.4283,
+      "num_input_tokens_seen": 3376152,
+      "step": 260
+    },
+    {
+      "epoch": 2.241014799154334,
+      "grad_norm": 3.5537617206573486,
+      "learning_rate": 7.400944974135427e-06,
+      "loss": 2.6161,
+      "num_input_tokens_seen": 3438504,
+      "step": 265
+    },
+    {
+      "epoch": 2.2832980972515857,
+      "grad_norm": 3.5316078662872314,
+      "learning_rate": 6.6306462284233234e-06,
+      "loss": 2.6151,
+      "num_input_tokens_seen": 3508488,
+      "step": 270
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 3.0121572017669678,
+      "learning_rate": 5.896509766381028e-06,
+      "loss": 2.5051,
+      "num_input_tokens_seen": 3572248,
+      "step": 275
+    },
+    {
+      "epoch": 2.367864693446089,
+      "grad_norm": 3.4623148441314697,
+      "learning_rate": 5.199980823988157e-06,
+      "loss": 2.535,
+      "num_input_tokens_seen": 3627304,
+      "step": 280
+    },
+    {
+      "epoch": 2.41014799154334,
+      "grad_norm": 2.7531158924102783,
+      "learning_rate": 4.542430602295774e-06,
+      "loss": 2.4052,
+      "num_input_tokens_seen": 3696504,
+      "step": 285
+    },
+    {
+      "epoch": 2.452431289640592,
+      "grad_norm": 3.238701105117798,
+      "learning_rate": 3.925153568052123e-06,
+      "loss": 2.6136,
+      "num_input_tokens_seen": 3757976,
+      "step": 290
+    },
+    {
+      "epoch": 2.4947145877378434,
+      "grad_norm": 3.5991199016571045,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 2.2962,
+      "num_input_tokens_seen": 3829192,
+      "step": 295
+    },
+    {
+      "epoch": 2.536997885835095,
+      "grad_norm": 3.9785468578338623,
+      "learning_rate": 2.8161981235857143e-06,
+      "loss": 2.6799,
+      "num_input_tokens_seen": 3900648,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 354,
+  "num_input_tokens_seen": 3900648,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.645307341379174e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ffc1f66e5aa3de4b714f2b3822cf0f4055bcd46a4096c6e5c3e47b3d4540a1
+size 5432