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-186/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: qwen2vl_lora
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen2vl_lora
+
+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: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.45.2
+- 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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual).*(?:up_proj|gate_proj|k_proj|down_proj|q_proj|o_proj|v_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a5f402b4795e794d7b5a419ae8141c661c9668bf868c5208aa4931b5362085
+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 +1,8 @@
+{
+    "epoch": 2.976,
+    "total_flos": 4302697811263488.0,
+    "train_loss": 0.3938655372588865,
+    "train_runtime": 377.5359,
+    "train_samples_per_second": 3.973,
+    "train_steps_per_second": 0.493
+}

checkpoint-186/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-186/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).*(?:up_proj|gate_proj|k_proj|down_proj|q_proj|o_proj|v_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-186/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a5f402b4795e794d7b5a419ae8141c661c9668bf868c5208aa4931b5362085
+size 36981072

checkpoint-186/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-186/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca54ee6842b49148257209293d96038f00ba7d58977b35832571e351b9ea36e
+size 74188906

checkpoint-186/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-186/rng_state.pth

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

checkpoint-186/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa30210e581fe5599d3edf74009fbbfbb1528a3358541235c0da5bbec9636599
+size 1064

checkpoint-186/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-186/tokenizer.json

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

checkpoint-186/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-186/trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.976,
+  "eval_steps": 500,
+  "global_step": 186,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.315385580062866,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 1.1346,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.9955989122390747,
+      "learning_rate": 9.999115304121459e-06,
+      "loss": 0.6167,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.6150994300842285,
+      "learning_rate": 9.893330096656576e-06,
+      "loss": 0.6992,
+      "step": 30
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.5031245946884155,
+      "learning_rate": 9.614885510995047e-06,
+      "loss": 0.5127,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.037620782852173,
+      "learning_rate": 9.173606363381218e-06,
+      "loss": 0.6019,
+      "step": 50
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.4414268732070923,
+      "learning_rate": 8.585063028536015e-06,
+      "loss": 0.5458,
+      "step": 60
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.4928420782089233,
+      "learning_rate": 7.870022044630569e-06,
+      "loss": 0.4214,
+      "step": 70
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 3.09617280960083,
+      "learning_rate": 7.053713373516538e-06,
+      "loss": 0.3165,
+      "step": 80
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.9061471819877625,
+      "learning_rate": 6.164940170670266e-06,
+      "loss": 0.2753,
+      "step": 90
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.7724579572677612,
+      "learning_rate": 5.235062476295488e-06,
+      "loss": 0.2277,
+      "step": 100
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.286865711212158,
+      "learning_rate": 4.29689068767551e-06,
+      "loss": 0.364,
+      "step": 110
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.2703816890716553,
+      "learning_rate": 3.3835278562017405e-06,
+      "loss": 0.2258,
+      "step": 120
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 3.2891488075256348,
+      "learning_rate": 2.5272016582081236e-06,
+      "loss": 0.3729,
+      "step": 130
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 1.9059756994247437,
+      "learning_rate": 1.7581272530970666e-06,
+      "loss": 0.2026,
+      "step": 140
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.4624115228652954,
+      "learning_rate": 1.103441152395588e-06,
+      "loss": 0.1538,
+      "step": 150
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.4256014823913574,
+      "learning_rate": 5.862437177854629e-07,
+      "loss": 0.2309,
+      "step": 160
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.27677008509635925,
+      "learning_rate": 2.2478407321721295e-07,
+      "loss": 0.1604,
+      "step": 170
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.8201978206634521,
+      "learning_rate": 3.181619118841517e-08,
+      "loss": 0.1571,
+      "step": 180
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 186,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4302697811263488.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-186/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ddc27e59906876e1f7274dbef924fef40cd0e15efb47e1b21ef1e9812c47bcb
+size 5368

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/Oct10_07-49-58_88d39722dab7/events.out.tfevents.1728546628.88d39722dab7.2873.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25231921839fab0ab45a3c351f9dbdaa021d5ad1174afef101074e3faafad98d
+size 9674

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 +1,8 @@
+{
+    "epoch": 2.976,
+    "total_flos": 4302697811263488.0,
+    "train_loss": 0.3938655372588865,
+    "train_runtime": 377.5359,
+    "train_samples_per_second": 3.973,
+    "train_steps_per_second": 0.493
+}

trainer_log.jsonl

@@ -0,0 +1,19 @@
+{"current_steps": 10, "total_steps": 186, "loss": 1.1346, "learning_rate": 5.263157894736842e-06, "epoch": 0.16, "percentage": 5.38, "elapsed_time": "0:00:22", "remaining_time": "0:06:28"}
+{"current_steps": 20, "total_steps": 186, "loss": 0.6167, "learning_rate": 9.999115304121459e-06, "epoch": 0.32, "percentage": 10.75, "elapsed_time": "0:00:41", "remaining_time": "0:05:47"}
+{"current_steps": 30, "total_steps": 186, "loss": 0.6992, "learning_rate": 9.893330096656576e-06, "epoch": 0.48, "percentage": 16.13, "elapsed_time": "0:01:01", "remaining_time": "0:05:21"}
+{"current_steps": 40, "total_steps": 186, "loss": 0.5127, "learning_rate": 9.614885510995047e-06, "epoch": 0.64, "percentage": 21.51, "elapsed_time": "0:01:21", "remaining_time": "0:04:58"}
+{"current_steps": 50, "total_steps": 186, "loss": 0.6019, "learning_rate": 9.173606363381218e-06, "epoch": 0.8, "percentage": 26.88, "elapsed_time": "0:01:42", "remaining_time": "0:04:37"}
+{"current_steps": 60, "total_steps": 186, "loss": 0.5458, "learning_rate": 8.585063028536015e-06, "epoch": 0.96, "percentage": 32.26, "elapsed_time": "0:02:02", "remaining_time": "0:04:16"}
+{"current_steps": 70, "total_steps": 186, "loss": 0.4214, "learning_rate": 7.870022044630569e-06, "epoch": 1.12, "percentage": 37.63, "elapsed_time": "0:02:22", "remaining_time": "0:03:56"}
+{"current_steps": 80, "total_steps": 186, "loss": 0.3165, "learning_rate": 7.053713373516538e-06, "epoch": 1.28, "percentage": 43.01, "elapsed_time": "0:02:43", "remaining_time": "0:03:36"}
+{"current_steps": 90, "total_steps": 186, "loss": 0.2753, "learning_rate": 6.164940170670266e-06, "epoch": 1.44, "percentage": 48.39, "elapsed_time": "0:03:03", "remaining_time": "0:03:15"}
+{"current_steps": 100, "total_steps": 186, "loss": 0.2277, "learning_rate": 5.235062476295488e-06, "epoch": 1.6, "percentage": 53.76, "elapsed_time": "0:03:23", "remaining_time": "0:02:54"}
+{"current_steps": 110, "total_steps": 186, "loss": 0.364, "learning_rate": 4.29689068767551e-06, "epoch": 1.76, "percentage": 59.14, "elapsed_time": "0:03:43", "remaining_time": "0:02:34"}
+{"current_steps": 120, "total_steps": 186, "loss": 0.2258, "learning_rate": 3.3835278562017405e-06, "epoch": 1.92, "percentage": 64.52, "elapsed_time": "0:04:03", "remaining_time": "0:02:14"}
+{"current_steps": 130, "total_steps": 186, "loss": 0.3729, "learning_rate": 2.5272016582081236e-06, "epoch": 2.08, "percentage": 69.89, "elapsed_time": "0:04:23", "remaining_time": "0:01:53"}
+{"current_steps": 140, "total_steps": 186, "loss": 0.2026, "learning_rate": 1.7581272530970666e-06, "epoch": 2.24, "percentage": 75.27, "elapsed_time": "0:04:44", "remaining_time": "0:01:33"}
+{"current_steps": 150, "total_steps": 186, "loss": 0.1538, "learning_rate": 1.103441152395588e-06, "epoch": 2.4, "percentage": 80.65, "elapsed_time": "0:05:04", "remaining_time": "0:01:13"}
+{"current_steps": 160, "total_steps": 186, "loss": 0.2309, "learning_rate": 5.862437177854629e-07, "epoch": 2.56, "percentage": 86.02, "elapsed_time": "0:05:24", "remaining_time": "0:00:52"}
+{"current_steps": 170, "total_steps": 186, "loss": 0.1604, "learning_rate": 2.2478407321721295e-07, "epoch": 2.7199999999999998, "percentage": 91.4, "elapsed_time": "0:05:44", "remaining_time": "0:00:32"}
+{"current_steps": 180, "total_steps": 186, "loss": 0.1571, "learning_rate": 3.181619118841517e-08, "epoch": 2.88, "percentage": 96.77, "elapsed_time": "0:06:04", "remaining_time": "0:00:12"}
+{"current_steps": 186, "total_steps": 186, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "0:06:17", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,168 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.976,
+  "eval_steps": 500,
+  "global_step": 186,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.315385580062866,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 1.1346,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.9955989122390747,
+      "learning_rate": 9.999115304121459e-06,
+      "loss": 0.6167,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.6150994300842285,
+      "learning_rate": 9.893330096656576e-06,
+      "loss": 0.6992,
+      "step": 30
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.5031245946884155,
+      "learning_rate": 9.614885510995047e-06,
+      "loss": 0.5127,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.037620782852173,
+      "learning_rate": 9.173606363381218e-06,
+      "loss": 0.6019,
+      "step": 50
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.4414268732070923,
+      "learning_rate": 8.585063028536015e-06,
+      "loss": 0.5458,
+      "step": 60
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.4928420782089233,
+      "learning_rate": 7.870022044630569e-06,
+      "loss": 0.4214,
+      "step": 70
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 3.09617280960083,
+      "learning_rate": 7.053713373516538e-06,
+      "loss": 0.3165,
+      "step": 80
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.9061471819877625,
+      "learning_rate": 6.164940170670266e-06,
+      "loss": 0.2753,
+      "step": 90
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.7724579572677612,
+      "learning_rate": 5.235062476295488e-06,
+      "loss": 0.2277,
+      "step": 100
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.286865711212158,
+      "learning_rate": 4.29689068767551e-06,
+      "loss": 0.364,
+      "step": 110
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.2703816890716553,
+      "learning_rate": 3.3835278562017405e-06,
+      "loss": 0.2258,
+      "step": 120
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 3.2891488075256348,
+      "learning_rate": 2.5272016582081236e-06,
+      "loss": 0.3729,
+      "step": 130
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 1.9059756994247437,
+      "learning_rate": 1.7581272530970666e-06,
+      "loss": 0.2026,
+      "step": 140
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.4624115228652954,
+      "learning_rate": 1.103441152395588e-06,
+      "loss": 0.1538,
+      "step": 150
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.4256014823913574,
+      "learning_rate": 5.862437177854629e-07,
+      "loss": 0.2309,
+      "step": 160
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.27677008509635925,
+      "learning_rate": 2.2478407321721295e-07,
+      "loss": 0.1604,
+      "step": 170
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.8201978206634521,
+      "learning_rate": 3.181619118841517e-08,
+      "loss": 0.1571,
+      "step": 180
+    },
+    {
+      "epoch": 2.976,
+      "step": 186,
+      "total_flos": 4302697811263488.0,
+      "train_loss": 0.3938655372588865,
+      "train_runtime": 377.5359,
+      "train_samples_per_second": 3.973,
+      "train_steps_per_second": 0.493
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 186,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4302697811263488.0,
+  "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 sha256:2ddc27e59906876e1f7274dbef924fef40cd0e15efb47e1b21ef1e9812c47bcb
+size 5368