Upload 33 files

README.md

@@ -1,3 +1,61 @@
----
-license: mit
----
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: sft
+  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. -->
+
+# sft
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) on the dora_demo_31 and the identity datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.5046
+
+## 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: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 16
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.0+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": 0.0,
+  "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|k_proj|o_proj|up_proj|gate_proj|v_proj|q_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 sha256:003d7fea1b63ba5ccc728d83cbc41b2ffd675f9d850f3932206e753ad980e55c
+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 +1,12 @@
+{
+    "epoch": 16.0,
+    "eval_loss": 0.5046026110649109,
+    "eval_runtime": 20.0388,
+    "eval_samples_per_second": 2.345,
+    "eval_steps_per_second": 2.345,
+    "total_flos": 3.485945501879501e+16,
+    "train_loss": 0.457215073876656,
+    "train_runtime": 4064.4346,
+    "train_samples_per_second": 1.638,
+    "train_steps_per_second": 0.051
+}

checkpoint-208/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-208/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": 0.0,
+  "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|k_proj|o_proj|up_proj|gate_proj|v_proj|q_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-208/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:003d7fea1b63ba5ccc728d83cbc41b2ffd675f9d850f3932206e753ad980e55c
+size 36981072

checkpoint-208/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-208/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a729ca72aa79ef785f7ab3a36b46f357c6449e6db061230aa8b9f096a9e1a7
+size 74188650

checkpoint-208/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52cca5856c568bc52c683b690919168fa27bfbdfefc6e0a62355afa6011157c3
+size 14244

checkpoint-208/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e84653c32772b6ebe38bc1fa88233f076b0acccd83473b0e19c56f7f06105d5
+size 1064

checkpoint-208/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-208/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-208/trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 16.0,
+  "eval_steps": 500,
+  "global_step": 208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.4849790334701538,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.4899,
+      "step": 10
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 1.4494893550872803,
+      "learning_rate": 9.523809523809524e-05,
+      "loss": 1.4047,
+      "step": 20
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 1.1887791156768799,
+      "learning_rate": 9.94295546780682e-05,
+      "loss": 1.1335,
+      "step": 30
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 2.6606452465057373,
+      "learning_rate": 9.747435008912438e-05,
+      "loss": 0.758,
+      "step": 40
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "grad_norm": 2.238654136657715,
+      "learning_rate": 9.418238419956484e-05,
+      "loss": 0.6976,
+      "step": 50
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 2.202763080596924,
+      "learning_rate": 8.964635069757802e-05,
+      "loss": 0.5176,
+      "step": 60
+    },
+    {
+      "epoch": 5.384615384615385,
+      "grad_norm": 1.5672999620437622,
+      "learning_rate": 8.399397316510596e-05,
+      "loss": 0.5374,
+      "step": 70
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 1.7563928365707397,
+      "learning_rate": 7.738440869493018e-05,
+      "loss": 0.4344,
+      "step": 80
+    },
+    {
+      "epoch": 6.923076923076923,
+      "grad_norm": 1.8594719171524048,
+      "learning_rate": 7.000376641716133e-05,
+      "loss": 0.3991,
+      "step": 90
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 1.8146908283233643,
+      "learning_rate": 6.205986712243875e-05,
+      "loss": 0.3497,
+      "step": 100
+    },
+    {
+      "epoch": 8.461538461538462,
+      "grad_norm": 1.8267848491668701,
+      "learning_rate": 5.377639153800229e-05,
+      "loss": 0.3176,
+      "step": 110
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 1.6012214422225952,
+      "learning_rate": 4.5386582026834906e-05,
+      "loss": 0.2394,
+      "step": 120
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.043828010559082,
+      "learning_rate": 3.712667505458622e-05,
+      "loss": 0.2328,
+      "step": 130
+    },
+    {
+      "epoch": 10.76923076923077,
+      "grad_norm": 2.1970419883728027,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.1849,
+      "step": 140
+    },
+    {
+      "epoch": 11.538461538461538,
+      "grad_norm": 1.2817729711532593,
+      "learning_rate": 2.1916677057681785e-05,
+      "loss": 0.1416,
+      "step": 150
+    },
+    {
+      "epoch": 12.307692307692308,
+      "grad_norm": 1.8149962425231934,
+      "learning_rate": 1.5394862284655264e-05,
+      "loss": 0.1323,
+      "step": 160
+    },
+    {
+      "epoch": 13.076923076923077,
+      "grad_norm": 2.4009556770324707,
+      "learning_rate": 9.847443344610297e-06,
+      "loss": 0.1315,
+      "step": 170
+    },
+    {
+      "epoch": 13.846153846153847,
+      "grad_norm": 1.9544780254364014,
+      "learning_rate": 5.430621953703785e-06,
+      "loss": 0.1065,
+      "step": 180
+    },
+    {
+      "epoch": 14.615384615384615,
+      "grad_norm": 1.0407898426055908,
+      "learning_rate": 2.268764973114684e-06,
+      "loss": 0.1174,
+      "step": 190
+    },
+    {
+      "epoch": 15.384615384615385,
+      "grad_norm": 3.4905996322631836,
+      "learning_rate": 4.5090254315662826e-07,
+      "loss": 0.0959,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 208,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 16,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.485945501879501e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-208/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d984b13dc94c2c552d631f900dbb389ec8e262db2b9e4dbd2e77e110776602dc
+size 5368

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 16.0,
+    "eval_loss": 0.5046026110649109,
+    "eval_runtime": 20.0388,
+    "eval_samples_per_second": 2.345,
+    "eval_steps_per_second": 2.345
+}

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
+}

runs/Sep03_06-03-57_peter-rog/events.out.tfevents.1725336255.peter-rog.178069.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0cbaf214aceff41f8b37d89f1cb46e41fd8be13470fe95f0ff6665625b43896
+size 10153

runs/Sep03_06-03-57_peter-rog/events.out.tfevents.1725340350.peter-rog.178069.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daf6bb8783e88a65400bae27d2e74806018f2aa63beed359bf17c69c5534fcb5
+size 359

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_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
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 16.0,
+    "total_flos": 3.485945501879501e+16,
+    "train_loss": 0.457215073876656,
+    "train_runtime": 4064.4346,
+    "train_samples_per_second": 1.638,
+    "train_steps_per_second": 0.051
+}

trainer_log.jsonl

@@ -0,0 +1,21 @@
+{"current_steps": 10, "total_steps": 208, "loss": 1.4899, "learning_rate": 4.761904761904762e-05, "epoch": 0.7692307692307693, "percentage": 4.81, "elapsed_time": "0:03:14", "remaining_time": "1:04:02"}
+{"current_steps": 20, "total_steps": 208, "loss": 1.4047, "learning_rate": 9.523809523809524e-05, "epoch": 1.5384615384615383, "percentage": 9.62, "elapsed_time": "0:06:32", "remaining_time": "1:01:27"}
+{"current_steps": 30, "total_steps": 208, "loss": 1.1335, "learning_rate": 9.94295546780682e-05, "epoch": 2.3076923076923075, "percentage": 14.42, "elapsed_time": "0:09:43", "remaining_time": "0:57:44"}
+{"current_steps": 40, "total_steps": 208, "loss": 0.758, "learning_rate": 9.747435008912438e-05, "epoch": 3.076923076923077, "percentage": 19.23, "elapsed_time": "0:13:03", "remaining_time": "0:54:48"}
+{"current_steps": 50, "total_steps": 208, "loss": 0.6976, "learning_rate": 9.418238419956484e-05, "epoch": 3.8461538461538463, "percentage": 24.04, "elapsed_time": "0:16:18", "remaining_time": "0:51:30"}
+{"current_steps": 60, "total_steps": 208, "loss": 0.5176, "learning_rate": 8.964635069757802e-05, "epoch": 4.615384615384615, "percentage": 28.85, "elapsed_time": "0:19:39", "remaining_time": "0:48:29"}
+{"current_steps": 70, "total_steps": 208, "loss": 0.5374, "learning_rate": 8.399397316510596e-05, "epoch": 5.384615384615385, "percentage": 33.65, "elapsed_time": "0:22:51", "remaining_time": "0:45:04"}
+{"current_steps": 80, "total_steps": 208, "loss": 0.4344, "learning_rate": 7.738440869493018e-05, "epoch": 6.153846153846154, "percentage": 38.46, "elapsed_time": "0:26:05", "remaining_time": "0:41:44"}
+{"current_steps": 90, "total_steps": 208, "loss": 0.3991, "learning_rate": 7.000376641716133e-05, "epoch": 6.923076923076923, "percentage": 43.27, "elapsed_time": "0:29:22", "remaining_time": "0:38:30"}
+{"current_steps": 100, "total_steps": 208, "loss": 0.3497, "learning_rate": 6.205986712243875e-05, "epoch": 7.6923076923076925, "percentage": 48.08, "elapsed_time": "0:32:31", "remaining_time": "0:35:07"}
+{"current_steps": 110, "total_steps": 208, "loss": 0.3176, "learning_rate": 5.377639153800229e-05, "epoch": 8.461538461538462, "percentage": 52.88, "elapsed_time": "0:35:43", "remaining_time": "0:31:49"}
+{"current_steps": 120, "total_steps": 208, "loss": 0.2394, "learning_rate": 4.5386582026834906e-05, "epoch": 9.23076923076923, "percentage": 57.69, "elapsed_time": "0:38:57", "remaining_time": "0:28:34"}
+{"current_steps": 130, "total_steps": 208, "loss": 0.2328, "learning_rate": 3.712667505458622e-05, "epoch": 10.0, "percentage": 62.5, "elapsed_time": "0:42:11", "remaining_time": "0:25:19"}
+{"current_steps": 140, "total_steps": 208, "loss": 0.1849, "learning_rate": 2.9229249349905684e-05, "epoch": 10.76923076923077, "percentage": 67.31, "elapsed_time": "0:45:27", "remaining_time": "0:22:04"}
+{"current_steps": 150, "total_steps": 208, "loss": 0.1416, "learning_rate": 2.1916677057681785e-05, "epoch": 11.538461538461538, "percentage": 72.12, "elapsed_time": "0:48:40", "remaining_time": "0:18:49"}
+{"current_steps": 160, "total_steps": 208, "loss": 0.1323, "learning_rate": 1.5394862284655264e-05, "epoch": 12.307692307692308, "percentage": 76.92, "elapsed_time": "0:51:59", "remaining_time": "0:15:35"}
+{"current_steps": 170, "total_steps": 208, "loss": 0.1315, "learning_rate": 9.847443344610297e-06, "epoch": 13.076923076923077, "percentage": 81.73, "elapsed_time": "0:55:13", "remaining_time": "0:12:20"}
+{"current_steps": 180, "total_steps": 208, "loss": 0.1065, "learning_rate": 5.430621953703785e-06, "epoch": 13.846153846153847, "percentage": 86.54, "elapsed_time": "0:58:29", "remaining_time": "0:09:05"}
+{"current_steps": 190, "total_steps": 208, "loss": 0.1174, "learning_rate": 2.268764973114684e-06, "epoch": 14.615384615384615, "percentage": 91.35, "elapsed_time": "1:01:43", "remaining_time": "0:05:50"}
+{"current_steps": 200, "total_steps": 208, "loss": 0.0959, "learning_rate": 4.5090254315662826e-07, "epoch": 15.384615384615385, "percentage": 96.15, "elapsed_time": "1:05:00", "remaining_time": "0:02:36"}
+{"current_steps": 208, "total_steps": 208, "epoch": 16.0, "percentage": 100.0, "elapsed_time": "1:07:44", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 16.0,
+  "eval_steps": 500,
+  "global_step": 208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.4849790334701538,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.4899,
+      "step": 10
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 1.4494893550872803,
+      "learning_rate": 9.523809523809524e-05,
+      "loss": 1.4047,
+      "step": 20
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 1.1887791156768799,
+      "learning_rate": 9.94295546780682e-05,
+      "loss": 1.1335,
+      "step": 30
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 2.6606452465057373,
+      "learning_rate": 9.747435008912438e-05,
+      "loss": 0.758,
+      "step": 40
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "grad_norm": 2.238654136657715,
+      "learning_rate": 9.418238419956484e-05,
+      "loss": 0.6976,
+      "step": 50
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 2.202763080596924,
+      "learning_rate": 8.964635069757802e-05,
+      "loss": 0.5176,
+      "step": 60
+    },
+    {
+      "epoch": 5.384615384615385,
+      "grad_norm": 1.5672999620437622,
+      "learning_rate": 8.399397316510596e-05,
+      "loss": 0.5374,
+      "step": 70
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 1.7563928365707397,
+      "learning_rate": 7.738440869493018e-05,
+      "loss": 0.4344,
+      "step": 80
+    },
+    {
+      "epoch": 6.923076923076923,
+      "grad_norm": 1.8594719171524048,
+      "learning_rate": 7.000376641716133e-05,
+      "loss": 0.3991,
+      "step": 90
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 1.8146908283233643,
+      "learning_rate": 6.205986712243875e-05,
+      "loss": 0.3497,
+      "step": 100
+    },
+    {
+      "epoch": 8.461538461538462,
+      "grad_norm": 1.8267848491668701,
+      "learning_rate": 5.377639153800229e-05,
+      "loss": 0.3176,
+      "step": 110
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 1.6012214422225952,
+      "learning_rate": 4.5386582026834906e-05,
+      "loss": 0.2394,
+      "step": 120
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.043828010559082,
+      "learning_rate": 3.712667505458622e-05,
+      "loss": 0.2328,
+      "step": 130
+    },
+    {
+      "epoch": 10.76923076923077,
+      "grad_norm": 2.1970419883728027,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.1849,
+      "step": 140
+    },
+    {
+      "epoch": 11.538461538461538,
+      "grad_norm": 1.2817729711532593,
+      "learning_rate": 2.1916677057681785e-05,
+      "loss": 0.1416,
+      "step": 150
+    },
+    {
+      "epoch": 12.307692307692308,
+      "grad_norm": 1.8149962425231934,
+      "learning_rate": 1.5394862284655264e-05,
+      "loss": 0.1323,
+      "step": 160
+    },
+    {
+      "epoch": 13.076923076923077,
+      "grad_norm": 2.4009556770324707,
+      "learning_rate": 9.847443344610297e-06,
+      "loss": 0.1315,
+      "step": 170
+    },
+    {
+      "epoch": 13.846153846153847,
+      "grad_norm": 1.9544780254364014,
+      "learning_rate": 5.430621953703785e-06,
+      "loss": 0.1065,
+      "step": 180
+    },
+    {
+      "epoch": 14.615384615384615,
+      "grad_norm": 1.0407898426055908,
+      "learning_rate": 2.268764973114684e-06,
+      "loss": 0.1174,
+      "step": 190
+    },
+    {
+      "epoch": 15.384615384615385,
+      "grad_norm": 3.4905996322631836,
+      "learning_rate": 4.5090254315662826e-07,
+      "loss": 0.0959,
+      "step": 200
+    },
+    {
+      "epoch": 16.0,
+      "step": 208,
+      "total_flos": 3.485945501879501e+16,
+      "train_loss": 0.457215073876656,
+      "train_runtime": 4064.4346,
+      "train_samples_per_second": 1.638,
+      "train_steps_per_second": 0.051
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 208,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 16,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.485945501879501e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d984b13dc94c2c552d631f900dbb389ec8e262db2b9e4dbd2e77e110776602dc
+size 5368