Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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-18/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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_2024-10-08-07-24-35
+  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_2024-10-08-07-24-35
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) on the my_chartQA 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
+- Pytorch 2.4.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 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).*(?:down_proj|v_proj|k_proj|gate_proj|q_proj|o_proj|up_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 sha256:89558bbbfeff0f196d771ea3401fd2928ee3046d49a4583b664d903d8d4d146a
+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": 2.88,
+    "num_input_tokens_seen": 90320,
+    "total_flos": 1075626816552960.0,
+    "train_loss": 2.124886062410143,
+    "train_runtime": 88.8196,
+    "train_samples_per_second": 3.378,
+    "train_steps_per_second": 0.203
+}

checkpoint-18/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-18/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).*(?:down_proj|v_proj|k_proj|gate_proj|q_proj|o_proj|up_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-18/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89558bbbfeff0f196d771ea3401fd2928ee3046d49a4583b664d903d8d4d146a
+size 36981072

checkpoint-18/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-18/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b9615747de0ec0d1e12cb6d596d11d38460105f2b2bfbeb6bcdcaeeb581014e
+size 74188650

checkpoint-18/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-18/rng_state.pth

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

checkpoint-18/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ba1e4effc421166914f0f22734677942b1ec5fd39f9ce3e71e50dcdc92a2b0
+size 1064

checkpoint-18/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-18/tokenizer.json

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

checkpoint-18/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 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",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-18/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.88,
+  "eval_steps": 500,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.393312454223633,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 2.9277,
+      "num_input_tokens_seen": 24896,
+      "step": 5
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 4.3577046394348145,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 2.0351,
+      "num_input_tokens_seen": 50000,
+      "step": 10
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 3.4381613731384277,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 1.731,
+      "num_input_tokens_seen": 74784,
+      "step": 15
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 18,
+  "num_input_tokens_seen": 90320,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1075626816552960.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-18/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db089b3a417d8fcdedd0b43510f5de06917cb4d26e14d6b4f9c3a5e2a9cb7cc3
+size 5432

llamaboard_config.yaml

@@ -0,0 +1,66 @@
+top.booster: auto
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Qwen2-VL-2B-Instruct
+top.quantization_bit: none
+top.quantization_method: bitsandbytes
+top.rope_scaling: none
+top.template: qwen2_vl
+train.additional_target: ''
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 2
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 1024
+train.dataset:
+- my_chartQA
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 0.25
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 8
+train.learning_rate: 5e-5
+train.logging_steps: 5
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '100000'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '3.0'
+train.optim: adamw_torch
+train.packing: false
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to: false
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 100
+train.shift_attn: false
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.val_size: 0
+train.warmup_steps: 0

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
+}

running_log.txt

@@ -0,0 +1,407 @@
+[INFO|configuration_utils.py:672] 2024-10-08 07:24:54,054 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json
+
+[WARNING|modeling_rope_utils.py:379] 2024-10-08 07:24:54,055 >> Unrecognized keys in `rope_scaling` for 'rope_type'='default': {'mrope_section'}
+
+[INFO|configuration_utils.py:739] 2024-10-08 07:24:54,057 >> Model config Qwen2VLConfig {
+  "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1536,
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}
+
+
+[INFO|tokenization_utils_base.py:2214] 2024-10-08 07:24:54,290 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/vocab.json
+
+[INFO|tokenization_utils_base.py:2214] 2024-10-08 07:24:54,290 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/merges.txt
+
+[INFO|tokenization_utils_base.py:2214] 2024-10-08 07:24:54,290 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/tokenizer.json
+
+[INFO|tokenization_utils_base.py:2214] 2024-10-08 07:24:54,290 >> loading file added_tokens.json from cache at None
+
+[INFO|tokenization_utils_base.py:2214] 2024-10-08 07:24:54,290 >> loading file special_tokens_map.json from cache at None
+
+[INFO|tokenization_utils_base.py:2214] 2024-10-08 07:24:54,290 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/tokenizer_config.json
+
+[INFO|tokenization_utils_base.py:2478] 2024-10-08 07:24:54,670 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|image_processing_base.py:375] 2024-10-08 07:24:55,378 >> loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/preprocessor_config.json
+
+[INFO|image_processing_base.py:375] 2024-10-08 07:24:55,609 >> loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/preprocessor_config.json
+
+[INFO|image_processing_base.py:429] 2024-10-08 07:24:55,609 >> Image processor Qwen2VLImageProcessor {
+  "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
+}
+
+
+[INFO|tokenization_utils_base.py:2214] 2024-10-08 07:24:55,836 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/vocab.json
+
+[INFO|tokenization_utils_base.py:2214] 2024-10-08 07:24:55,836 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/merges.txt
+
+[INFO|tokenization_utils_base.py:2214] 2024-10-08 07:24:55,836 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/tokenizer.json
+
+[INFO|tokenization_utils_base.py:2214] 2024-10-08 07:24:55,836 >> loading file added_tokens.json from cache at None
+
+[INFO|tokenization_utils_base.py:2214] 2024-10-08 07:24:55,836 >> loading file special_tokens_map.json from cache at None
+
+[INFO|tokenization_utils_base.py:2214] 2024-10-08 07:24:55,836 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/tokenizer_config.json
+
+[INFO|tokenization_utils_base.py:2478] 2024-10-08 07:24:56,214 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|processing_utils.py:744] 2024-10-08 07:24:57,333 >> Processor Qwen2VLProcessor:
+- image_processor: Qwen2VLImageProcessor {
+  "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
+}
+
+- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2-VL-2B-Instruct', vocab_size=151643, model_max_length=32768, is_fast=True, padding_side='left', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', '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|>']}, clean_up_tokenization_spaces=False),  added_tokens_decoder={
+	151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+}
+
+{
+  "processor_class": "Qwen2VLProcessor"
+}
+
+
+[INFO|configuration_utils.py:672] 2024-10-08 07:25:02,808 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json
+
+[WARNING|modeling_rope_utils.py:379] 2024-10-08 07:25:02,809 >> Unrecognized keys in `rope_scaling` for 'rope_type'='default': {'mrope_section'}
+
+[INFO|configuration_utils.py:739] 2024-10-08 07:25:02,810 >> Model config Qwen2VLConfig {
+  "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1536,
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}
+
+
+[INFO|modeling_utils.py:3726] 2024-10-08 07:25:02,826 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/model.safetensors.index.json
+
+[INFO|modeling_utils.py:1622] 2024-10-08 07:25:02,828 >> Instantiating Qwen2VLForConditionalGeneration model under default dtype torch.bfloat16.
+
+[INFO|configuration_utils.py:1099] 2024-10-08 07:25:02,829 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151645
+}
+
+
+[WARNING|logging.py:328] 2024-10-08 07:25:02,855 >> `Qwen2VLRotaryEmbedding` can now be fully parameterized by passing the model config through the `config` argument. All other arguments will be removed in v4.46
+
+[INFO|modeling_utils.py:4568] 2024-10-08 07:25:05,453 >> All model checkpoint weights were used when initializing Qwen2VLForConditionalGeneration.
+
+
+[INFO|modeling_utils.py:4576] 2024-10-08 07:25:05,453 >> All the weights of Qwen2VLForConditionalGeneration were initialized from the model checkpoint at Qwen/Qwen2-VL-2B-Instruct.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2VLForConditionalGeneration for predictions without further training.
+
+[INFO|configuration_utils.py:1054] 2024-10-08 07:25:05,690 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/generation_config.json
+
+[INFO|configuration_utils.py:1099] 2024-10-08 07:25:05,690 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.01,
+  "top_k": 1,
+  "top_p": 0.001
+}
+
+
+[INFO|trainer.py:667] 2024-10-08 07:25:06,169 >> Using auto half precision backend
+
+[INFO|trainer.py:2243] 2024-10-08 07:25:06,740 >> ***** Running training *****
+
+[INFO|trainer.py:2244] 2024-10-08 07:25:06,740 >>   Num examples = 100
+
+[INFO|trainer.py:2245] 2024-10-08 07:25:06,740 >>   Num Epochs = 3
+
+[INFO|trainer.py:2246] 2024-10-08 07:25:06,740 >>   Instantaneous batch size per device = 2
+
+[INFO|trainer.py:2249] 2024-10-08 07:25:06,740 >>   Total train batch size (w. parallel, distributed & accumulation) = 16
+
+[INFO|trainer.py:2250] 2024-10-08 07:25:06,740 >>   Gradient Accumulation steps = 8
+
+[INFO|trainer.py:2251] 2024-10-08 07:25:06,740 >>   Total optimization steps = 18
+
+[INFO|trainer.py:2252] 2024-10-08 07:25:06,746 >>   Number of trainable parameters = 9,232,384
+
+[INFO|trainer.py:3705] 2024-10-08 07:26:34,621 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-07-24-35/checkpoint-18
+
+[INFO|configuration_utils.py:672] 2024-10-08 07:26:35,108 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json
+
+[WARNING|modeling_rope_utils.py:379] 2024-10-08 07:26:35,108 >> Unrecognized keys in `rope_scaling` for 'rope_type'='default': {'mrope_section'}
+
+[INFO|configuration_utils.py:739] 2024-10-08 07:26:35,110 >> Model config Qwen2VLConfig {
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1536,
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}
+
+
+[INFO|tokenization_utils_base.py:2649] 2024-10-08 07:26:35,193 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-07-24-35/checkpoint-18/tokenizer_config.json
+
+[INFO|tokenization_utils_base.py:2658] 2024-10-08 07:26:35,193 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-07-24-35/checkpoint-18/special_tokens_map.json
+
+[INFO|image_processing_base.py:258] 2024-10-08 07:26:35,565 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-07-24-35/checkpoint-18/preprocessor_config.json
+
+[INFO|trainer.py:2505] 2024-10-08 07:26:35,566 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|image_processing_base.py:258] 2024-10-08 07:26:35,568 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-07-24-35/preprocessor_config.json
+
+[INFO|trainer.py:3705] 2024-10-08 07:26:35,568 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-07-24-35
+
+[INFO|configuration_utils.py:672] 2024-10-08 07:26:36,065 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json
+
+[WARNING|modeling_rope_utils.py:379] 2024-10-08 07:26:36,065 >> Unrecognized keys in `rope_scaling` for 'rope_type'='default': {'mrope_section'}
+
+[INFO|configuration_utils.py:739] 2024-10-08 07:26:36,067 >> Model config Qwen2VLConfig {
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1536,
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}
+
+
+[INFO|tokenization_utils_base.py:2649] 2024-10-08 07:26:36,146 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-07-24-35/tokenizer_config.json
+
+[INFO|tokenization_utils_base.py:2658] 2024-10-08 07:26:36,147 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-07-24-35/special_tokens_map.json
+
+[INFO|modelcard.py:449] 2024-10-08 07:26:36,523 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

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
+  }
+}

tokenizer.json

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

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 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",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.88,
+    "num_input_tokens_seen": 90320,
+    "total_flos": 1075626816552960.0,
+    "train_loss": 2.124886062410143,
+    "train_runtime": 88.8196,
+    "train_samples_per_second": 3.378,
+    "train_steps_per_second": 0.203
+}

trainer_log.jsonl

@@ -0,0 +1,4 @@
+{"current_steps": 5, "total_steps": 18, "loss": 2.9277, "learning_rate": 4.1069690242163484e-05, "epoch": 0.8, "percentage": 27.78, "elapsed_time": "0:00:25", "remaining_time": "0:01:05", "throughput": 989.42, "total_tokens": 24896}
+{"current_steps": 10, "total_steps": 18, "loss": 2.0351, "learning_rate": 2.0658795558326743e-05, "epoch": 1.6, "percentage": 55.56, "elapsed_time": "0:00:49", "remaining_time": "0:00:39", "throughput": 1014.57, "total_tokens": 50000}
+{"current_steps": 15, "total_steps": 18, "loss": 1.731, "learning_rate": 3.3493649053890326e-06, "epoch": 2.4, "percentage": 83.33, "elapsed_time": "0:01:13", "remaining_time": "0:00:14", "throughput": 1019.0, "total_tokens": 74784}
+{"current_steps": 18, "total_steps": 18, "epoch": 2.88, "percentage": 100.0, "elapsed_time": "0:01:28", "remaining_time": "0:00:00", "throughput": 1016.96, "total_tokens": 90320}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.88,
+  "eval_steps": 500,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.393312454223633,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 2.9277,
+      "num_input_tokens_seen": 24896,
+      "step": 5
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 4.3577046394348145,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 2.0351,
+      "num_input_tokens_seen": 50000,
+      "step": 10
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 3.4381613731384277,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 1.731,
+      "num_input_tokens_seen": 74784,
+      "step": 15
+    },
+    {
+      "epoch": 2.88,
+      "num_input_tokens_seen": 90320,
+      "step": 18,
+      "total_flos": 1075626816552960.0,
+      "train_loss": 2.124886062410143,
+      "train_runtime": 88.8196,
+      "train_samples_per_second": 3.378,
+      "train_steps_per_second": 0.203
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 18,
+  "num_input_tokens_seen": 90320,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1075626816552960.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db089b3a417d8fcdedd0b43510f5de06917cb4d26e14d6b4f9c3a5e2a9cb7cc3
+size 5432

training_args.yaml

@@ -0,0 +1,32 @@
+bf16: true
+cutoff_len: 1024
+dataset: my_chartQA
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+gradient_accumulation_steps: 8
+include_num_input_tokens_seen: true
+learning_rate: 5.0e-05
+logging_steps: 5
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: all
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 100000
+model_name_or_path: Qwen/Qwen2-VL-2B-Instruct
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-07-24-35
+packing: false
+per_device_train_batch_size: 2
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+save_steps: 100
+stage: sft
+template: qwen2_vl
+warmup_steps: 0