Upload 54 files

README.md

@@ -0,0 +1,61 @@
+---
+library_name: peft
+license: other
+base_model: llava-hf/llava-1.5-7b-hf
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: train_k_folds_4_4_epochs
+  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_k_folds_4_4_epochs
+
+This model is a fine-tuned version of [llava-hf/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf) on the sticker_labels_kfolds_train_4 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
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 4.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.1
+- Pytorch 2.7.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,132 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "llava-hf/llava-1.5-7b-hf",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "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": [
+    "27.self_attn.v_proj",
+    "language_model.layers.20.self_attn.k_proj",
+    "24.self_attn.q_proj",
+    "language_model.layers.13.self_attn.v_proj",
+    "language_model.layers.17.self_attn.v_proj",
+    "language_model.layers.7.self_attn.v_proj",
+    "language_model.layers.17.self_attn.q_proj",
+    "language_model.layers.0.self_attn.v_proj",
+    "language_model.layers.22.self_attn.q_proj",
+    "31.self_attn.v_proj",
+    "language_model.layers.3.self_attn.k_proj",
+    "language_model.layers.15.self_attn.q_proj",
+    "language_model.layers.19.self_attn.k_proj",
+    "language_model.layers.1.self_attn.k_proj",
+    "language_model.layers.4.self_attn.q_proj",
+    "24.self_attn.v_proj",
+    "30.self_attn.v_proj",
+    "language_model.layers.18.self_attn.q_proj",
+    "language_model.layers.17.self_attn.k_proj",
+    "25.self_attn.k_proj",
+    "language_model.layers.8.self_attn.q_proj",
+    "language_model.layers.2.self_attn.q_proj",
+    "down_proj",
+    "language_model.layers.23.self_attn.v_proj",
+    "o_proj",
+    "language_model.layers.19.self_attn.q_proj",
+    "language_model.layers.15.self_attn.k_proj",
+    "language_model.layers.6.self_attn.v_proj",
+    "28.self_attn.k_proj",
+    "language_model.layers.21.self_attn.q_proj",
+    "24.self_attn.k_proj",
+    "language_model.layers.7.self_attn.q_proj",
+    "language_model.layers.12.self_attn.q_proj",
+    "language_model.layers.9.self_attn.v_proj",
+    "language_model.layers.23.self_attn.k_proj",
+    "language_model.layers.1.self_attn.v_proj",
+    "language_model.layers.18.self_attn.k_proj",
+    "30.self_attn.k_proj",
+    "language_model.layers.11.self_attn.v_proj",
+    "language_model.layers.7.self_attn.k_proj",
+    "language_model.layers.22.self_attn.k_proj",
+    "language_model.layers.5.self_attn.v_proj",
+    "language_model.layers.10.self_attn.v_proj",
+    "language_model.layers.8.self_attn.v_proj",
+    "language_model.layers.3.self_attn.q_proj",
+    "language_model.layers.15.self_attn.v_proj",
+    "27.self_attn.k_proj",
+    "language_model.layers.22.self_attn.v_proj",
+    "language_model.layers.13.self_attn.q_proj",
+    "language_model.layers.16.self_attn.v_proj",
+    "language_model.layers.0.self_attn.q_proj",
+    "language_model.layers.5.self_attn.k_proj",
+    "language_model.layers.9.self_attn.k_proj",
+    "language_model.layers.3.self_attn.v_proj",
+    "language_model.layers.12.self_attn.k_proj",
+    "language_model.layers.11.self_attn.q_proj",
+    "28.self_attn.q_proj",
+    "29.self_attn.q_proj",
+    "25.self_attn.q_proj",
+    "language_model.layers.21.self_attn.k_proj",
+    "language_model.layers.9.self_attn.q_proj",
+    "26.self_attn.v_proj",
+    "language_model.layers.2.self_attn.v_proj",
+    "29.self_attn.k_proj",
+    "gate_proj",
+    "25.self_attn.v_proj",
+    "language_model.layers.2.self_attn.k_proj",
+    "26.self_attn.k_proj",
+    "language_model.layers.4.self_attn.v_proj",
+    "language_model.layers.11.self_attn.k_proj",
+    "language_model.layers.23.self_attn.q_proj",
+    "language_model.layers.16.self_attn.k_proj",
+    "language_model.layers.14.self_attn.v_proj",
+    "language_model.layers.10.self_attn.q_proj",
+    "language_model.layers.20.self_attn.q_proj",
+    "language_model.layers.20.self_attn.v_proj",
+    "language_model.layers.21.self_attn.v_proj",
+    "language_model.layers.16.self_attn.q_proj",
+    "language_model.layers.13.self_attn.k_proj",
+    "26.self_attn.q_proj",
+    "31.self_attn.k_proj",
+    "language_model.layers.14.self_attn.q_proj",
+    "language_model.layers.4.self_attn.k_proj",
+    "27.self_attn.q_proj",
+    "language_model.layers.1.self_attn.q_proj",
+    "language_model.layers.8.self_attn.k_proj",
+    "language_model.layers.14.self_attn.k_proj",
+    "29.self_attn.v_proj",
+    "language_model.layers.12.self_attn.v_proj",
+    "30.self_attn.q_proj",
+    "language_model.layers.0.self_attn.k_proj",
+    "language_model.layers.19.self_attn.v_proj",
+    "up_proj",
+    "31.self_attn.q_proj",
+    "language_model.layers.18.self_attn.v_proj",
+    "language_model.layers.10.self_attn.k_proj",
+    "language_model.layers.6.self_attn.q_proj",
+    "language_model.layers.5.self_attn.q_proj",
+    "28.self_attn.v_proj",
+    "language_model.layers.6.self_attn.k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc553793ac8a8002149a9657652e8b249f93295395e40dba89d7a0033668823a
+size 80019840

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "num_input_tokens_seen": 2494624,
+    "total_flos": 1.0404813073494835e+17,
+    "train_loss": 2.765545678990228,
+    "train_runtime": 591.3728,
+    "train_samples_per_second": 6.02,
+    "train_steps_per_second": 0.189
+}

chat_template.jinja

@@ -0,0 +1 @@
+{% set system_message = 'A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user\'s questions.' %}{% 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 %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'USER: ' + content + ' ASSISTANT:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+base_model: llava-hf/llava-1.5-7b-hf
+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 0.15.2

checkpoint-100/adapter_config.json

@@ -0,0 +1,132 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "llava-hf/llava-1.5-7b-hf",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "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": [
+    "27.self_attn.v_proj",
+    "language_model.layers.20.self_attn.k_proj",
+    "24.self_attn.q_proj",
+    "language_model.layers.13.self_attn.v_proj",
+    "language_model.layers.17.self_attn.v_proj",
+    "language_model.layers.7.self_attn.v_proj",
+    "language_model.layers.17.self_attn.q_proj",
+    "language_model.layers.0.self_attn.v_proj",
+    "language_model.layers.22.self_attn.q_proj",
+    "31.self_attn.v_proj",
+    "language_model.layers.3.self_attn.k_proj",
+    "language_model.layers.15.self_attn.q_proj",
+    "language_model.layers.19.self_attn.k_proj",
+    "language_model.layers.1.self_attn.k_proj",
+    "language_model.layers.4.self_attn.q_proj",
+    "24.self_attn.v_proj",
+    "30.self_attn.v_proj",
+    "language_model.layers.18.self_attn.q_proj",
+    "language_model.layers.17.self_attn.k_proj",
+    "25.self_attn.k_proj",
+    "language_model.layers.8.self_attn.q_proj",
+    "language_model.layers.2.self_attn.q_proj",
+    "down_proj",
+    "language_model.layers.23.self_attn.v_proj",
+    "o_proj",
+    "language_model.layers.19.self_attn.q_proj",
+    "language_model.layers.15.self_attn.k_proj",
+    "language_model.layers.6.self_attn.v_proj",
+    "28.self_attn.k_proj",
+    "language_model.layers.21.self_attn.q_proj",
+    "24.self_attn.k_proj",
+    "language_model.layers.7.self_attn.q_proj",
+    "language_model.layers.12.self_attn.q_proj",
+    "language_model.layers.9.self_attn.v_proj",
+    "language_model.layers.23.self_attn.k_proj",
+    "language_model.layers.1.self_attn.v_proj",
+    "language_model.layers.18.self_attn.k_proj",
+    "30.self_attn.k_proj",
+    "language_model.layers.11.self_attn.v_proj",
+    "language_model.layers.7.self_attn.k_proj",
+    "language_model.layers.22.self_attn.k_proj",
+    "language_model.layers.5.self_attn.v_proj",
+    "language_model.layers.10.self_attn.v_proj",
+    "language_model.layers.8.self_attn.v_proj",
+    "language_model.layers.3.self_attn.q_proj",
+    "language_model.layers.15.self_attn.v_proj",
+    "27.self_attn.k_proj",
+    "language_model.layers.22.self_attn.v_proj",
+    "language_model.layers.13.self_attn.q_proj",
+    "language_model.layers.16.self_attn.v_proj",
+    "language_model.layers.0.self_attn.q_proj",
+    "language_model.layers.5.self_attn.k_proj",
+    "language_model.layers.9.self_attn.k_proj",
+    "language_model.layers.3.self_attn.v_proj",
+    "language_model.layers.12.self_attn.k_proj",
+    "language_model.layers.11.self_attn.q_proj",
+    "28.self_attn.q_proj",
+    "29.self_attn.q_proj",
+    "25.self_attn.q_proj",
+    "language_model.layers.21.self_attn.k_proj",
+    "language_model.layers.9.self_attn.q_proj",
+    "26.self_attn.v_proj",
+    "language_model.layers.2.self_attn.v_proj",
+    "29.self_attn.k_proj",
+    "gate_proj",
+    "25.self_attn.v_proj",
+    "language_model.layers.2.self_attn.k_proj",
+    "26.self_attn.k_proj",
+    "language_model.layers.4.self_attn.v_proj",
+    "language_model.layers.11.self_attn.k_proj",
+    "language_model.layers.23.self_attn.q_proj",
+    "language_model.layers.16.self_attn.k_proj",
+    "language_model.layers.14.self_attn.v_proj",
+    "language_model.layers.10.self_attn.q_proj",
+    "language_model.layers.20.self_attn.q_proj",
+    "language_model.layers.20.self_attn.v_proj",
+    "language_model.layers.21.self_attn.v_proj",
+    "language_model.layers.16.self_attn.q_proj",
+    "language_model.layers.13.self_attn.k_proj",
+    "26.self_attn.q_proj",
+    "31.self_attn.k_proj",
+    "language_model.layers.14.self_attn.q_proj",
+    "language_model.layers.4.self_attn.k_proj",
+    "27.self_attn.q_proj",
+    "language_model.layers.1.self_attn.q_proj",
+    "language_model.layers.8.self_attn.k_proj",
+    "language_model.layers.14.self_attn.k_proj",
+    "29.self_attn.v_proj",
+    "language_model.layers.12.self_attn.v_proj",
+    "30.self_attn.q_proj",
+    "language_model.layers.0.self_attn.k_proj",
+    "language_model.layers.19.self_attn.v_proj",
+    "up_proj",
+    "31.self_attn.q_proj",
+    "language_model.layers.18.self_attn.v_proj",
+    "language_model.layers.10.self_attn.k_proj",
+    "language_model.layers.6.self_attn.q_proj",
+    "language_model.layers.5.self_attn.q_proj",
+    "28.self_attn.v_proj",
+    "language_model.layers.6.self_attn.k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f85c0a2f58dfb3fce36cd80902d5079cc15d7149df412b5d9c3d122c5983c14
+size 80019840

checkpoint-100/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

checkpoint-100/chat_template.jinja

@@ -0,0 +1,2 @@
+{% for message in messages %}{% if message['role'] != 'system' %}{{ message['role'].upper() + ': '}}{% endif %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>
+' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] + ' '}}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] + ' '}}{% endgeneration %}{% endfor %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTANT:' }}{% endif %}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e358ea9cb61168fb8da798fce3f24507e383ee248b1193df1d4455a088cb836d
+size 160285219

checkpoint-100/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

checkpoint-100/processor_config.json

@@ -0,0 +1,7 @@
+{
+  "image_token": "<image>",
+  "num_additional_image_tokens": 1,
+  "patch_size": 14,
+  "processor_class": "LlavaProcessor",
+  "vision_feature_select_strategy": "default"
+}

checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ea5dcfd1b4a49b41b4fa01a8b24bba6186957162c3fd555ebff28620c7268b
+size 14917

checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2a5af18bb5eae8b7fd6bdef66259014d98ba87ffb16d614bba38f2c32030798
+size 14917

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6be21f9eb4e7865940e344f20ebbbfc9faab9771df177dc7b0a881e3946855d0
+size 1465

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {
+    "image_token": "<image>"
+  },
+  "image_token": "<image>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "LlavaProcessor",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,234 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.5739910313901344,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17937219730941703,
+      "grad_norm": 1.5203849077224731,
+      "learning_rate": 4.984280524733107e-05,
+      "loss": 3.5214,
+      "num_input_tokens_seen": 111952,
+      "step": 5,
+      "train_runtime": 27.5462,
+      "train_tokens_per_second": 4064.161
+    },
+    {
+      "epoch": 0.35874439461883406,
+      "grad_norm": 0.9002476334571838,
+      "learning_rate": 4.9207588053056545e-05,
+      "loss": 3.3636,
+      "num_input_tokens_seen": 223776,
+      "step": 10,
+      "train_runtime": 53.4438,
+      "train_tokens_per_second": 4187.127
+    },
+    {
+      "epoch": 0.5381165919282511,
+      "grad_norm": 0.6985305547714233,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 3.0641,
+      "num_input_tokens_seen": 335600,
+      "step": 15,
+      "train_runtime": 79.4605,
+      "train_tokens_per_second": 4223.48
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "grad_norm": 0.5677102208137512,
+      "learning_rate": 4.653281570581023e-05,
+      "loss": 2.9922,
+      "num_input_tokens_seen": 447424,
+      "step": 20,
+      "train_runtime": 105.6383,
+      "train_tokens_per_second": 4235.433
+    },
+    {
+      "epoch": 0.8968609865470852,
+      "grad_norm": 0.6143746376037598,
+      "learning_rate": 4.454578706170075e-05,
+      "loss": 3.0359,
+      "num_input_tokens_seen": 559328,
+      "step": 25,
+      "train_runtime": 131.8723,
+      "train_tokens_per_second": 4241.437
+    },
+    {
+      "epoch": 1.0717488789237668,
+      "grad_norm": 0.5885606408119202,
+      "learning_rate": 4.2174923150872544e-05,
+      "loss": 2.825,
+      "num_input_tokens_seen": 668544,
+      "step": 30,
+      "train_runtime": 157.5044,
+      "train_tokens_per_second": 4244.606
+    },
+    {
+      "epoch": 1.251121076233184,
+      "grad_norm": 0.5807215571403503,
+      "learning_rate": 3.946678240449515e-05,
+      "loss": 2.8427,
+      "num_input_tokens_seen": 780496,
+      "step": 35,
+      "train_runtime": 183.817,
+      "train_tokens_per_second": 4246.05
+    },
+    {
+      "epoch": 1.4304932735426008,
+      "grad_norm": 0.6312059164047241,
+      "learning_rate": 3.6474546611688445e-05,
+      "loss": 2.7976,
+      "num_input_tokens_seen": 892128,
+      "step": 40,
+      "train_runtime": 210.129,
+      "train_tokens_per_second": 4245.62
+    },
+    {
+      "epoch": 1.609865470852018,
+      "grad_norm": 0.6633515357971191,
+      "learning_rate": 3.3256976548879184e-05,
+      "loss": 2.6764,
+      "num_input_tokens_seen": 1004112,
+      "step": 45,
+      "train_runtime": 236.4964,
+      "train_tokens_per_second": 4245.781
+    },
+    {
+      "epoch": 1.789237668161435,
+      "grad_norm": 0.7430306077003479,
+      "learning_rate": 2.9877258050403212e-05,
+      "loss": 2.7217,
+      "num_input_tokens_seen": 1116064,
+      "step": 50,
+      "train_runtime": 262.8011,
+      "train_tokens_per_second": 4246.801
+    },
+    {
+      "epoch": 1.9686098654708521,
+      "grad_norm": 0.7268422245979309,
+      "learning_rate": 2.6401761180929797e-05,
+      "loss": 2.7066,
+      "num_input_tokens_seen": 1227808,
+      "step": 55,
+      "train_runtime": 289.1347,
+      "train_tokens_per_second": 4246.491
+    },
+    {
+      "epoch": 2.1434977578475336,
+      "grad_norm": 0.7635470032691956,
+      "learning_rate": 2.2898736876768815e-05,
+      "loss": 2.6038,
+      "num_input_tokens_seen": 1337104,
+      "step": 60,
+      "train_runtime": 314.8221,
+      "train_tokens_per_second": 4247.173
+    },
+    {
+      "epoch": 2.3228699551569507,
+      "grad_norm": 0.8516287207603455,
+      "learning_rate": 1.9436976651092144e-05,
+      "loss": 2.5954,
+      "num_input_tokens_seen": 1448976,
+      "step": 65,
+      "train_runtime": 341.1436,
+      "train_tokens_per_second": 4247.407
+    },
+    {
+      "epoch": 2.502242152466368,
+      "grad_norm": 0.8331743478775024,
+      "learning_rate": 1.6084461683442176e-05,
+      "loss": 2.6679,
+      "num_input_tokens_seen": 1560352,
+      "step": 70,
+      "train_runtime": 367.4136,
+      "train_tokens_per_second": 4246.854
+    },
+    {
+      "epoch": 2.681614349775785,
+      "grad_norm": 0.8733316659927368,
+      "learning_rate": 1.2907027822369005e-05,
+      "loss": 2.5975,
+      "num_input_tokens_seen": 1672176,
+      "step": 75,
+      "train_runtime": 393.7208,
+      "train_tokens_per_second": 4247.111
+    },
+    {
+      "epoch": 2.8609865470852016,
+      "grad_norm": 0.927335798740387,
+      "learning_rate": 9.967072717539851e-06,
+      "loss": 2.6389,
+      "num_input_tokens_seen": 1784448,
+      "step": 80,
+      "train_runtime": 420.1259,
+      "train_tokens_per_second": 4247.412
+    },
+    {
+      "epoch": 3.0358744394618835,
+      "grad_norm": 0.821441650390625,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 2.4908,
+      "num_input_tokens_seen": 1893216,
+      "step": 85,
+      "train_runtime": 445.7557,
+      "train_tokens_per_second": 4247.205
+    },
+    {
+      "epoch": 3.2152466367713006,
+      "grad_norm": 0.8318443894386292,
+      "learning_rate": 5.02473786604378e-06,
+      "loss": 2.6384,
+      "num_input_tokens_seen": 2005392,
+      "step": 90,
+      "train_runtime": 472.0937,
+      "train_tokens_per_second": 4247.869
+    },
+    {
+      "epoch": 3.3946188340807173,
+      "grad_norm": 0.8994652628898621,
+      "learning_rate": 3.119414452281158e-06,
+      "loss": 2.5131,
+      "num_input_tokens_seen": 2117168,
+      "step": 95,
+      "train_runtime": 498.4113,
+      "train_tokens_per_second": 4247.833
+    },
+    {
+      "epoch": 3.5739910313901344,
+      "grad_norm": 0.9667345881462097,
+      "learning_rate": 1.6437764926350074e-06,
+      "loss": 2.5565,
+      "num_input_tokens_seen": 2229024,
+      "step": 100,
+      "train_runtime": 524.7221,
+      "train_tokens_per_second": 4248.009
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 112,
+  "num_input_tokens_seen": 2229024,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.29702354050089e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c43db658eaa1d450fd25da35350814f9c84e2c2f8aed15977213a4dd95ff5d
+size 6161

checkpoint-112/README.md

@@ -0,0 +1,202 @@
+---
+base_model: llava-hf/llava-1.5-7b-hf
+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 0.15.2

checkpoint-112/adapter_config.json

@@ -0,0 +1,132 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "llava-hf/llava-1.5-7b-hf",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "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": [
+    "27.self_attn.v_proj",
+    "language_model.layers.20.self_attn.k_proj",
+    "24.self_attn.q_proj",
+    "language_model.layers.13.self_attn.v_proj",
+    "language_model.layers.17.self_attn.v_proj",
+    "language_model.layers.7.self_attn.v_proj",
+    "language_model.layers.17.self_attn.q_proj",
+    "language_model.layers.0.self_attn.v_proj",
+    "language_model.layers.22.self_attn.q_proj",
+    "31.self_attn.v_proj",
+    "language_model.layers.3.self_attn.k_proj",
+    "language_model.layers.15.self_attn.q_proj",
+    "language_model.layers.19.self_attn.k_proj",
+    "language_model.layers.1.self_attn.k_proj",
+    "language_model.layers.4.self_attn.q_proj",
+    "24.self_attn.v_proj",
+    "30.self_attn.v_proj",
+    "language_model.layers.18.self_attn.q_proj",
+    "language_model.layers.17.self_attn.k_proj",
+    "25.self_attn.k_proj",
+    "language_model.layers.8.self_attn.q_proj",
+    "language_model.layers.2.self_attn.q_proj",
+    "down_proj",
+    "language_model.layers.23.self_attn.v_proj",
+    "o_proj",
+    "language_model.layers.19.self_attn.q_proj",
+    "language_model.layers.15.self_attn.k_proj",
+    "language_model.layers.6.self_attn.v_proj",
+    "28.self_attn.k_proj",
+    "language_model.layers.21.self_attn.q_proj",
+    "24.self_attn.k_proj",
+    "language_model.layers.7.self_attn.q_proj",
+    "language_model.layers.12.self_attn.q_proj",
+    "language_model.layers.9.self_attn.v_proj",
+    "language_model.layers.23.self_attn.k_proj",
+    "language_model.layers.1.self_attn.v_proj",
+    "language_model.layers.18.self_attn.k_proj",
+    "30.self_attn.k_proj",
+    "language_model.layers.11.self_attn.v_proj",
+    "language_model.layers.7.self_attn.k_proj",
+    "language_model.layers.22.self_attn.k_proj",
+    "language_model.layers.5.self_attn.v_proj",
+    "language_model.layers.10.self_attn.v_proj",
+    "language_model.layers.8.self_attn.v_proj",
+    "language_model.layers.3.self_attn.q_proj",
+    "language_model.layers.15.self_attn.v_proj",
+    "27.self_attn.k_proj",
+    "language_model.layers.22.self_attn.v_proj",
+    "language_model.layers.13.self_attn.q_proj",
+    "language_model.layers.16.self_attn.v_proj",
+    "language_model.layers.0.self_attn.q_proj",
+    "language_model.layers.5.self_attn.k_proj",
+    "language_model.layers.9.self_attn.k_proj",
+    "language_model.layers.3.self_attn.v_proj",
+    "language_model.layers.12.self_attn.k_proj",
+    "language_model.layers.11.self_attn.q_proj",
+    "28.self_attn.q_proj",
+    "29.self_attn.q_proj",
+    "25.self_attn.q_proj",
+    "language_model.layers.21.self_attn.k_proj",
+    "language_model.layers.9.self_attn.q_proj",
+    "26.self_attn.v_proj",
+    "language_model.layers.2.self_attn.v_proj",
+    "29.self_attn.k_proj",
+    "gate_proj",
+    "25.self_attn.v_proj",
+    "language_model.layers.2.self_attn.k_proj",
+    "26.self_attn.k_proj",
+    "language_model.layers.4.self_attn.v_proj",
+    "language_model.layers.11.self_attn.k_proj",
+    "language_model.layers.23.self_attn.q_proj",
+    "language_model.layers.16.self_attn.k_proj",
+    "language_model.layers.14.self_attn.v_proj",
+    "language_model.layers.10.self_attn.q_proj",
+    "language_model.layers.20.self_attn.q_proj",
+    "language_model.layers.20.self_attn.v_proj",
+    "language_model.layers.21.self_attn.v_proj",
+    "language_model.layers.16.self_attn.q_proj",
+    "language_model.layers.13.self_attn.k_proj",
+    "26.self_attn.q_proj",
+    "31.self_attn.k_proj",
+    "language_model.layers.14.self_attn.q_proj",
+    "language_model.layers.4.self_attn.k_proj",
+    "27.self_attn.q_proj",
+    "language_model.layers.1.self_attn.q_proj",
+    "language_model.layers.8.self_attn.k_proj",
+    "language_model.layers.14.self_attn.k_proj",
+    "29.self_attn.v_proj",
+    "language_model.layers.12.self_attn.v_proj",
+    "30.self_attn.q_proj",
+    "language_model.layers.0.self_attn.k_proj",
+    "language_model.layers.19.self_attn.v_proj",
+    "up_proj",
+    "31.self_attn.q_proj",
+    "language_model.layers.18.self_attn.v_proj",
+    "language_model.layers.10.self_attn.k_proj",
+    "language_model.layers.6.self_attn.q_proj",
+    "language_model.layers.5.self_attn.q_proj",
+    "28.self_attn.v_proj",
+    "language_model.layers.6.self_attn.k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-112/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc553793ac8a8002149a9657652e8b249f93295395e40dba89d7a0033668823a
+size 80019840

checkpoint-112/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

checkpoint-112/chat_template.jinja

@@ -0,0 +1,2 @@
+{% for message in messages %}{% if message['role'] != 'system' %}{{ message['role'].upper() + ': '}}{% endif %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>
+' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] + ' '}}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] + ' '}}{% endgeneration %}{% endfor %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTANT:' }}{% endif %}

checkpoint-112/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2a813c2e7e057c97caec59ee87293d494de7436557ff9f6b1b4e01e79a7287
+size 160285219

checkpoint-112/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

checkpoint-112/processor_config.json

@@ -0,0 +1,7 @@
+{
+  "image_token": "<image>",
+  "num_additional_image_tokens": 1,
+  "patch_size": 14,
+  "processor_class": "LlavaProcessor",
+  "vision_feature_select_strategy": "default"
+}

checkpoint-112/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ea5dcfd1b4a49b41b4fa01a8b24bba6186957162c3fd555ebff28620c7268b
+size 14917

checkpoint-112/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2a5af18bb5eae8b7fd6bdef66259014d98ba87ffb16d614bba38f2c32030798
+size 14917

checkpoint-112/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23615fd0530d96bf686130f41aba74d32c05af699e347822519a970468da7396
+size 1465

checkpoint-112/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-112/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-112/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {
+    "image_token": "<image>"
+  },
+  "image_token": "<image>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "LlavaProcessor",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-112/trainer_state.json

@@ -0,0 +1,254 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17937219730941703,
+      "grad_norm": 1.5203849077224731,
+      "learning_rate": 4.984280524733107e-05,
+      "loss": 3.5214,
+      "num_input_tokens_seen": 111952,
+      "step": 5,
+      "train_runtime": 27.5462,
+      "train_tokens_per_second": 4064.161
+    },
+    {
+      "epoch": 0.35874439461883406,
+      "grad_norm": 0.9002476334571838,
+      "learning_rate": 4.9207588053056545e-05,
+      "loss": 3.3636,
+      "num_input_tokens_seen": 223776,
+      "step": 10,
+      "train_runtime": 53.4438,
+      "train_tokens_per_second": 4187.127
+    },
+    {
+      "epoch": 0.5381165919282511,
+      "grad_norm": 0.6985305547714233,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 3.0641,
+      "num_input_tokens_seen": 335600,
+      "step": 15,
+      "train_runtime": 79.4605,
+      "train_tokens_per_second": 4223.48
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "grad_norm": 0.5677102208137512,
+      "learning_rate": 4.653281570581023e-05,
+      "loss": 2.9922,
+      "num_input_tokens_seen": 447424,
+      "step": 20,
+      "train_runtime": 105.6383,
+      "train_tokens_per_second": 4235.433
+    },
+    {
+      "epoch": 0.8968609865470852,
+      "grad_norm": 0.6143746376037598,
+      "learning_rate": 4.454578706170075e-05,
+      "loss": 3.0359,
+      "num_input_tokens_seen": 559328,
+      "step": 25,
+      "train_runtime": 131.8723,
+      "train_tokens_per_second": 4241.437
+    },
+    {
+      "epoch": 1.0717488789237668,
+      "grad_norm": 0.5885606408119202,
+      "learning_rate": 4.2174923150872544e-05,
+      "loss": 2.825,
+      "num_input_tokens_seen": 668544,
+      "step": 30,
+      "train_runtime": 157.5044,
+      "train_tokens_per_second": 4244.606
+    },
+    {
+      "epoch": 1.251121076233184,
+      "grad_norm": 0.5807215571403503,
+      "learning_rate": 3.946678240449515e-05,
+      "loss": 2.8427,
+      "num_input_tokens_seen": 780496,
+      "step": 35,
+      "train_runtime": 183.817,
+      "train_tokens_per_second": 4246.05
+    },
+    {
+      "epoch": 1.4304932735426008,
+      "grad_norm": 0.6312059164047241,
+      "learning_rate": 3.6474546611688445e-05,
+      "loss": 2.7976,
+      "num_input_tokens_seen": 892128,
+      "step": 40,
+      "train_runtime": 210.129,
+      "train_tokens_per_second": 4245.62
+    },
+    {
+      "epoch": 1.609865470852018,
+      "grad_norm": 0.6633515357971191,
+      "learning_rate": 3.3256976548879184e-05,
+      "loss": 2.6764,
+      "num_input_tokens_seen": 1004112,
+      "step": 45,
+      "train_runtime": 236.4964,
+      "train_tokens_per_second": 4245.781
+    },
+    {
+      "epoch": 1.789237668161435,
+      "grad_norm": 0.7430306077003479,
+      "learning_rate": 2.9877258050403212e-05,
+      "loss": 2.7217,
+      "num_input_tokens_seen": 1116064,
+      "step": 50,
+      "train_runtime": 262.8011,
+      "train_tokens_per_second": 4246.801
+    },
+    {
+      "epoch": 1.9686098654708521,
+      "grad_norm": 0.7268422245979309,
+      "learning_rate": 2.6401761180929797e-05,
+      "loss": 2.7066,
+      "num_input_tokens_seen": 1227808,
+      "step": 55,
+      "train_runtime": 289.1347,
+      "train_tokens_per_second": 4246.491
+    },
+    {
+      "epoch": 2.1434977578475336,
+      "grad_norm": 0.7635470032691956,
+      "learning_rate": 2.2898736876768815e-05,
+      "loss": 2.6038,
+      "num_input_tokens_seen": 1337104,
+      "step": 60,
+      "train_runtime": 314.8221,
+      "train_tokens_per_second": 4247.173
+    },
+    {
+      "epoch": 2.3228699551569507,
+      "grad_norm": 0.8516287207603455,
+      "learning_rate": 1.9436976651092144e-05,
+      "loss": 2.5954,
+      "num_input_tokens_seen": 1448976,
+      "step": 65,
+      "train_runtime": 341.1436,
+      "train_tokens_per_second": 4247.407
+    },
+    {
+      "epoch": 2.502242152466368,
+      "grad_norm": 0.8331743478775024,
+      "learning_rate": 1.6084461683442176e-05,
+      "loss": 2.6679,
+      "num_input_tokens_seen": 1560352,
+      "step": 70,
+      "train_runtime": 367.4136,
+      "train_tokens_per_second": 4246.854
+    },
+    {
+      "epoch": 2.681614349775785,
+      "grad_norm": 0.8733316659927368,
+      "learning_rate": 1.2907027822369005e-05,
+      "loss": 2.5975,
+      "num_input_tokens_seen": 1672176,
+      "step": 75,
+      "train_runtime": 393.7208,
+      "train_tokens_per_second": 4247.111
+    },
+    {
+      "epoch": 2.8609865470852016,
+      "grad_norm": 0.927335798740387,
+      "learning_rate": 9.967072717539851e-06,
+      "loss": 2.6389,
+      "num_input_tokens_seen": 1784448,
+      "step": 80,
+      "train_runtime": 420.1259,
+      "train_tokens_per_second": 4247.412
+    },
+    {
+      "epoch": 3.0358744394618835,
+      "grad_norm": 0.821441650390625,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 2.4908,
+      "num_input_tokens_seen": 1893216,
+      "step": 85,
+      "train_runtime": 445.7557,
+      "train_tokens_per_second": 4247.205
+    },
+    {
+      "epoch": 3.2152466367713006,
+      "grad_norm": 0.8318443894386292,
+      "learning_rate": 5.02473786604378e-06,
+      "loss": 2.6384,
+      "num_input_tokens_seen": 2005392,
+      "step": 90,
+      "train_runtime": 472.0937,
+      "train_tokens_per_second": 4247.869
+    },
+    {
+      "epoch": 3.3946188340807173,
+      "grad_norm": 0.8994652628898621,
+      "learning_rate": 3.119414452281158e-06,
+      "loss": 2.5131,
+      "num_input_tokens_seen": 2117168,
+      "step": 95,
+      "train_runtime": 498.4113,
+      "train_tokens_per_second": 4247.833
+    },
+    {
+      "epoch": 3.5739910313901344,
+      "grad_norm": 0.9667345881462097,
+      "learning_rate": 1.6437764926350074e-06,
+      "loss": 2.5565,
+      "num_input_tokens_seen": 2229024,
+      "step": 100,
+      "train_runtime": 524.7221,
+      "train_tokens_per_second": 4248.009
+    },
+    {
+      "epoch": 3.7533632286995515,
+      "grad_norm": 0.8132877349853516,
+      "learning_rate": 6.268021954544096e-07,
+      "loss": 2.5378,
+      "num_input_tokens_seen": 2340688,
+      "step": 105,
+      "train_runtime": 552.8372,
+      "train_tokens_per_second": 4233.955
+    },
+    {
+      "epoch": 3.9327354260089686,
+      "grad_norm": 0.9859150648117065,
+      "learning_rate": 8.846264705952289e-08,
+      "loss": 2.5846,
+      "num_input_tokens_seen": 2452784,
+      "step": 110,
+      "train_runtime": 579.23,
+      "train_tokens_per_second": 4234.56
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 112,
+  "num_input_tokens_seen": 2494624,
+  "num_train_epochs": 4,
+  "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": 1.0404813073494835e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-112/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c43db658eaa1d450fd25da35350814f9c84e2c2f8aed15977213a4dd95ff5d
+size 6161

llamaboard_config.yaml

@@ -0,0 +1,85 @@
+top.booster: auto
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: LLaVA-1.5-7B-Chat
+top.quantization_bit: none
+top.quantization_method: bnb
+top.rope_scaling: none
+top.template: llava
+train.additional_target: ''
+train.apollo_rank: 16
+train.apollo_scale: 32
+train.apollo_target: all
+train.apollo_update_interval: 200
+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: 2048
+train.dataset:
+- sticker_labels_kfolds_train_4
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.enable_thinking: true
+train.extra_args: '{"optim": "adamw_torch"}'
+train.freeze_extra_modules: ''
+train.freeze_language_model: false
+train.freeze_multi_modal_projector: true
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.freeze_vision_tower: true
+train.galore_rank: 16
+train.galore_scale: 2
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 8
+train.image_max_pixels: 768*768
+train.image_min_pixels: 32*32
+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: '4'
+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: none
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 100
+train.swanlab_api_key: ''
+train.swanlab_link: ''
+train.swanlab_mode: cloud
+train.swanlab_project: llamafactory
+train.swanlab_run_name: ''
+train.swanlab_workspace: ''
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_apollo: false
+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.use_swanlab: false
+train.val_size: 0
+train.video_max_pixels: 256*256
+train.video_min_pixels: 16*16
+train.warmup_steps: 0

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

processor_config.json

@@ -0,0 +1,7 @@
+{
+  "image_token": "<image>",
+  "num_additional_image_tokens": 1,
+  "patch_size": 14,
+  "processor_class": "LlavaProcessor",
+  "vision_feature_select_strategy": "default"
+}

running_log.txt

@@ -0,0 +1,564 @@
+[INFO|2025-05-27 22:39:19] tokenization_utils_base.py:2023 >> loading file tokenizer.model from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/tokenizer.model
+
+[INFO|2025-05-27 22:39:19] tokenization_utils_base.py:2023 >> loading file tokenizer.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/tokenizer.json
+
+[INFO|2025-05-27 22:39:19] tokenization_utils_base.py:2023 >> loading file added_tokens.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/added_tokens.json
+
+[INFO|2025-05-27 22:39:19] tokenization_utils_base.py:2023 >> loading file special_tokens_map.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/special_tokens_map.json
+
+[INFO|2025-05-27 22:39:19] tokenization_utils_base.py:2023 >> loading file tokenizer_config.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/tokenizer_config.json
+
+[INFO|2025-05-27 22:39:19] tokenization_utils_base.py:2023 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-05-27 22:39:19] tokenization_utils_base.py:2299 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[WARNING|2025-05-27 22:39:20] logging.py:328 >> Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
+
+[INFO|2025-05-27 22:39:20] processing_utils.py:930 >> loading configuration file processor_config.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/processor_config.json
+
+[INFO|2025-05-27 22:39:20] image_processing_base.py:380 >> loading configuration file preprocessor_config.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/preprocessor_config.json
+
+[WARNING|2025-05-27 22:39:20] logging.py:328 >> Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
+
+[INFO|2025-05-27 22:39:20] image_processing_base.py:433 >> Image processor CLIPImageProcessor {
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}
+
+
+[INFO|2025-05-27 22:39:21] tokenization_utils_base.py:2023 >> loading file tokenizer.model from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/tokenizer.model
+
+[INFO|2025-05-27 22:39:21] tokenization_utils_base.py:2023 >> loading file tokenizer.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/tokenizer.json
+
+[INFO|2025-05-27 22:39:21] tokenization_utils_base.py:2023 >> loading file added_tokens.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/added_tokens.json
+
+[INFO|2025-05-27 22:39:21] tokenization_utils_base.py:2023 >> loading file special_tokens_map.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/special_tokens_map.json
+
+[INFO|2025-05-27 22:39:21] tokenization_utils_base.py:2023 >> loading file tokenizer_config.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/tokenizer_config.json
+
+[INFO|2025-05-27 22:39:21] tokenization_utils_base.py:2023 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-05-27 22:39:21] tokenization_utils_base.py:2299 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-05-27 22:39:22] processing_utils.py:930 >> loading configuration file processor_config.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/processor_config.json
+
+[INFO|2025-05-27 22:39:22] processing_utils.py:990 >> Processor LlavaProcessor:
+- image_processor: CLIPImageProcessor {
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}
+
+- tokenizer: LlamaTokenizerFast(name_or_path='llava-hf/llava-1.5-7b-hf', vocab_size=32000, model_max_length=1000000000000000019884624838656, is_fast=True, padding_side='left', truncation_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '</s>', 'unk_token': '<unk>', 'pad_token': '<pad>', 'image_token': '<image>'}, clean_up_tokenization_spaces=False, added_tokens_decoder={
+	0: AddedToken("<unk>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	1: AddedToken("<s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	2: AddedToken("</s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	32000: AddedToken("<image>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	32001: AddedToken("<pad>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+}
+)
+
+{
+  "image_token": "<image>",
+  "num_additional_image_tokens": 1,
+  "patch_size": 14,
+  "processor_class": "LlavaProcessor",
+  "vision_feature_select_strategy": "default"
+}
+
+
+[INFO|2025-05-27 22:39:22] logging.py:143 >> Loading dataset /home/tsinghuaair/mawz/xxe_metchee/finetune-llms/llava-1.5-7b-hf-sticker-labels/kfold_output/fold_4/stickers_label_train.json...
+
+[INFO|2025-05-27 22:39:26] configuration_utils.py:698 >> loading configuration file config.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/config.json
+
+[INFO|2025-05-27 22:39:26] configuration_utils.py:770 >> Model config LlavaConfig {
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava",
+  "multimodal_projector_bias": true,
+  "pad_token_id": 32001,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "lmsys/vicuna-7b-v1.5",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 4096,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 32,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "torch_dtype": "float16",
+    "use_cache": true,
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.1",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "image_size": 336,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-05,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}
+
+
+[INFO|2025-05-27 22:39:26] logging.py:143 >> KV cache is disabled during training.
+
+[INFO|2025-05-27 22:39:26] modeling_utils.py:1149 >> loading weights file model.safetensors from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/model.safetensors.index.json
+
+[INFO|2025-05-27 22:39:26] modeling_utils.py:2239 >> Instantiating LlavaForConditionalGeneration model under default dtype torch.bfloat16.
+
+[INFO|2025-05-27 22:39:26] configuration_utils.py:1135 >> Generate config GenerationConfig {
+  "pad_token_id": 32001,
+  "use_cache": false
+}
+
+
+[INFO|2025-05-27 22:39:27] modeling_utils.py:2239 >> Instantiating CLIPVisionModel model under default dtype torch.bfloat16.
+
+[INFO|2025-05-27 22:39:27] modeling_utils.py:2239 >> Instantiating LlamaModel model under default dtype torch.bfloat16.
+
+[INFO|2025-05-27 22:39:30] modeling_utils.py:5170 >> All model checkpoint weights were used when initializing LlavaForConditionalGeneration.
+
+
+[INFO|2025-05-27 22:39:30] modeling_utils.py:5178 >> All the weights of LlavaForConditionalGeneration were initialized from the model checkpoint at llava-hf/llava-1.5-7b-hf.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaForConditionalGeneration for predictions without further training.
+
+[INFO|2025-05-27 22:39:30] configuration_utils.py:1090 >> loading configuration file generation_config.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/generation_config.json
+
+[INFO|2025-05-27 22:39:30] configuration_utils.py:1135 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 32001
+}
+
+
+[INFO|2025-05-27 22:39:31] logging.py:143 >> Gradient checkpointing enabled.
+
+[INFO|2025-05-27 22:39:31] logging.py:143 >> Using torch SDPA for faster training and inference.
+
+[INFO|2025-05-27 22:39:31] logging.py:143 >> Upcasting trainable params to float32.
+
+[INFO|2025-05-27 22:39:31] logging.py:143 >> Fine-tuning method: LoRA
+
+[INFO|2025-05-27 22:39:31] logging.py:143 >> Found linear modules: k_proj,v_proj,q_proj,o_proj,gate_proj,up_proj,down_proj
+
+[INFO|2025-05-27 22:39:31] logging.py:143 >> Set vision model not trainable: ['vision_tower'].
+
+[INFO|2025-05-27 22:39:31] logging.py:143 >> Set multi model projector not trainable: multi_modal_projector.
+
+[INFO|2025-05-27 22:39:31] logging.py:143 >> trainable params: 19,988,480 || all params: 7,083,415,552 || trainable%: 0.2822
+
+[INFO|2025-05-27 22:39:31] trainer.py:756 >> Using auto half precision backend
+
+[INFO|2025-05-27 22:39:32] trainer.py:2409 >> ***** Running training *****
+
+[INFO|2025-05-27 22:39:32] trainer.py:2410 >>   Num examples = 890
+
+[INFO|2025-05-27 22:39:32] trainer.py:2411 >>   Num Epochs = 4
+
+[INFO|2025-05-27 22:39:32] trainer.py:2412 >>   Instantaneous batch size per device = 2
+
+[INFO|2025-05-27 22:39:32] trainer.py:2415 >>   Total train batch size (w. parallel, distributed & accumulation) = 32
+
+[INFO|2025-05-27 22:39:32] trainer.py:2416 >>   Gradient Accumulation steps = 8
+
+[INFO|2025-05-27 22:39:32] trainer.py:2417 >>   Total optimization steps = 112
+
+[INFO|2025-05-27 22:39:32] trainer.py:2418 >>   Number of trainable parameters = 19,988,480
+
+[WARNING|2025-05-27 22:39:34] logging.py:328 >> `loss_type=None` was set in the config but it is unrecognised.Using the default loss: `ForCausalLMLoss`.
+
+[WARNING|2025-05-27 22:39:34] logging.py:328 >> `loss_type=None` was set in the config but it is unrecognised.Using the default loss: `ForCausalLMLoss`.
+
+[INFO|2025-05-27 22:39:59] logging.py:143 >> {'loss': 3.5214, 'learning_rate': 4.9843e-05, 'epoch': 0.18, 'throughput': 4196.48}
+
+[INFO|2025-05-27 22:40:25] logging.py:143 >> {'loss': 3.3636, 'learning_rate': 4.9208e-05, 'epoch': 0.36, 'throughput': 4256.30}
+
+[INFO|2025-05-27 22:40:51] logging.py:143 >> {'loss': 3.0641, 'learning_rate': 4.8097e-05, 'epoch': 0.54, 'throughput': 4270.16}
+
+[INFO|2025-05-27 22:41:17] logging.py:143 >> {'loss': 2.9922, 'learning_rate': 4.6533e-05, 'epoch': 0.72, 'throughput': 4270.54}
+
+[INFO|2025-05-27 22:41:44] logging.py:143 >> {'loss': 3.0359, 'learning_rate': 4.4546e-05, 'epoch': 0.90, 'throughput': 4269.56}
+
+[INFO|2025-05-27 22:42:09] logging.py:143 >> {'loss': 2.8250, 'learning_rate': 4.2175e-05, 'epoch': 1.07, 'throughput': 4268.14}
+
+[INFO|2025-05-27 22:42:35] logging.py:143 >> {'loss': 2.8427, 'learning_rate': 3.9467e-05, 'epoch': 1.25, 'throughput': 4266.21}
+
+[INFO|2025-05-27 22:43:02] logging.py:143 >> {'loss': 2.7976, 'learning_rate': 3.6475e-05, 'epoch': 1.43, 'throughput': 4263.24}
+
+[INFO|2025-05-27 22:43:28] logging.py:143 >> {'loss': 2.6764, 'learning_rate': 3.3257e-05, 'epoch': 1.61, 'throughput': 4261.43}
+
+[INFO|2025-05-27 22:43:54] logging.py:143 >> {'loss': 2.7217, 'learning_rate': 2.9877e-05, 'epoch': 1.79, 'throughput': 4260.88}
+
+[INFO|2025-05-27 22:44:21] logging.py:143 >> {'loss': 2.7066, 'learning_rate': 2.6402e-05, 'epoch': 1.97, 'throughput': 4259.29}
+
+[INFO|2025-05-27 22:44:46] logging.py:143 >> {'loss': 2.6038, 'learning_rate': 2.2899e-05, 'epoch': 2.14, 'throughput': 4258.92}
+
+[INFO|2025-05-27 22:45:13] logging.py:143 >> {'loss': 2.5954, 'learning_rate': 1.9437e-05, 'epoch': 2.32, 'throughput': 4258.25}
+
+[INFO|2025-05-27 22:45:39] logging.py:143 >> {'loss': 2.6679, 'learning_rate': 1.6084e-05, 'epoch': 2.50, 'throughput': 4256.92}
+
+[INFO|2025-05-27 22:46:05] logging.py:143 >> {'loss': 2.5975, 'learning_rate': 1.2907e-05, 'epoch': 2.68, 'throughput': 4256.50}
+
+[INFO|2025-05-27 22:46:32] logging.py:143 >> {'loss': 2.6389, 'learning_rate': 9.9671e-06, 'epoch': 2.86, 'throughput': 4256.21}
+
+[INFO|2025-05-27 22:46:57] logging.py:143 >> {'loss': 2.4908, 'learning_rate': 7.3223e-06, 'epoch': 3.04, 'throughput': 4255.50}
+
+[INFO|2025-05-27 22:47:24] logging.py:143 >> {'loss': 2.6384, 'learning_rate': 5.0247e-06, 'epoch': 3.22, 'throughput': 4255.70}
+
+[INFO|2025-05-27 22:47:50] logging.py:143 >> {'loss': 2.5131, 'learning_rate': 3.1194e-06, 'epoch': 3.39, 'throughput': 4255.25}
+
+[INFO|2025-05-27 22:48:16] logging.py:143 >> {'loss': 2.5565, 'learning_rate': 1.6438e-06, 'epoch': 3.57, 'throughput': 4255.05}
+
+[INFO|2025-05-27 22:48:16] trainer.py:3993 >> Saving model checkpoint to saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-100
+
+[INFO|2025-05-27 22:48:17] configuration_utils.py:698 >> loading configuration file config.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/config.json
+
+[INFO|2025-05-27 22:48:17] configuration_utils.py:770 >> Model config LlavaConfig {
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava",
+  "multimodal_projector_bias": true,
+  "pad_token_id": 32001,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "lmsys/vicuna-7b-v1.5",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 4096,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 32,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "torch_dtype": "float16",
+    "use_cache": true,
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.1",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "image_size": 336,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-05,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}
+
+
+[INFO|2025-05-27 22:48:17] tokenization_utils_base.py:2356 >> chat template saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-100/chat_template.jinja
+
+[INFO|2025-05-27 22:48:17] tokenization_utils_base.py:2525 >> tokenizer config file saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-100/tokenizer_config.json
+
+[INFO|2025-05-27 22:48:17] tokenization_utils_base.py:2534 >> Special tokens file saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-100/special_tokens_map.json
+
+[INFO|2025-05-27 22:48:18] image_processing_base.py:260 >> Image processor saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-100/preprocessor_config.json
+
+[INFO|2025-05-27 22:48:18] tokenization_utils_base.py:2356 >> chat template saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-100/chat_template.jinja
+
+[INFO|2025-05-27 22:48:18] tokenization_utils_base.py:2525 >> tokenizer config file saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-100/tokenizer_config.json
+
+[INFO|2025-05-27 22:48:18] tokenization_utils_base.py:2534 >> Special tokens file saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-100/special_tokens_map.json
+
+[INFO|2025-05-27 22:48:18] processing_utils.py:674 >> chat template saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-100/chat_template.jinja
+
+[INFO|2025-05-27 22:48:18] processing_utils.py:709 >> processor saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-100/processor_config.json
+
+[INFO|2025-05-27 22:48:45] logging.py:143 >> {'loss': 2.5378, 'learning_rate': 6.2680e-07, 'epoch': 3.75, 'throughput': 4240.62}
+
+[INFO|2025-05-27 22:49:11] logging.py:143 >> {'loss': 2.5846, 'learning_rate': 8.8463e-08, 'epoch': 3.93, 'throughput': 4240.92}
+
+[INFO|2025-05-27 22:49:21] trainer.py:3993 >> Saving model checkpoint to saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-112
+
+[INFO|2025-05-27 22:49:22] configuration_utils.py:698 >> loading configuration file config.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/config.json
+
+[INFO|2025-05-27 22:49:22] configuration_utils.py:770 >> Model config LlavaConfig {
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava",
+  "multimodal_projector_bias": true,
+  "pad_token_id": 32001,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "lmsys/vicuna-7b-v1.5",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 4096,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 32,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "torch_dtype": "float16",
+    "use_cache": true,
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.1",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "image_size": 336,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-05,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}
+
+
+[INFO|2025-05-27 22:49:22] tokenization_utils_base.py:2356 >> chat template saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-112/chat_template.jinja
+
+[INFO|2025-05-27 22:49:22] tokenization_utils_base.py:2525 >> tokenizer config file saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-112/tokenizer_config.json
+
+[INFO|2025-05-27 22:49:22] tokenization_utils_base.py:2534 >> Special tokens file saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-112/special_tokens_map.json
+
+[INFO|2025-05-27 22:49:23] image_processing_base.py:260 >> Image processor saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-112/preprocessor_config.json
+
+[INFO|2025-05-27 22:49:23] tokenization_utils_base.py:2356 >> chat template saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-112/chat_template.jinja
+
+[INFO|2025-05-27 22:49:23] tokenization_utils_base.py:2525 >> tokenizer config file saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-112/tokenizer_config.json
+
+[INFO|2025-05-27 22:49:23] tokenization_utils_base.py:2534 >> Special tokens file saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-112/special_tokens_map.json
+
+[INFO|2025-05-27 22:49:23] processing_utils.py:674 >> chat template saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-112/chat_template.jinja
+
+[INFO|2025-05-27 22:49:23] processing_utils.py:709 >> processor saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/checkpoint-112/processor_config.json
+
+[INFO|2025-05-27 22:49:23] trainer.py:2676 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-05-27 22:49:23] image_processing_base.py:260 >> Image processor saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/preprocessor_config.json
+
+[INFO|2025-05-27 22:49:23] tokenization_utils_base.py:2356 >> chat template saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/chat_template.jinja
+
+[INFO|2025-05-27 22:49:23] tokenization_utils_base.py:2525 >> tokenizer config file saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/tokenizer_config.json
+
+[INFO|2025-05-27 22:49:23] tokenization_utils_base.py:2534 >> Special tokens file saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/special_tokens_map.json
+
+[INFO|2025-05-27 22:49:23] processing_utils.py:674 >> chat template saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/chat_template.jinja
+
+[INFO|2025-05-27 22:49:23] processing_utils.py:709 >> processor saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/processor_config.json
+
+[INFO|2025-05-27 22:49:23] trainer.py:3993 >> Saving model checkpoint to saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs
+
+[INFO|2025-05-27 22:49:24] configuration_utils.py:698 >> loading configuration file config.json from cache at /home/tsinghuaair/.cache/huggingface/hub/models--llava-hf--llava-1.5-7b-hf/snapshots/6ceb2ed33cb8f107a781c431fe2e61574da69369/config.json
+
+[INFO|2025-05-27 22:49:24] configuration_utils.py:770 >> Model config LlavaConfig {
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava",
+  "multimodal_projector_bias": true,
+  "pad_token_id": 32001,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "lmsys/vicuna-7b-v1.5",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 4096,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 32,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "torch_dtype": "float16",
+    "use_cache": true,
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.1",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "image_size": 336,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-05,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}
+
+
+[INFO|2025-05-27 22:49:24] tokenization_utils_base.py:2356 >> chat template saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/chat_template.jinja
+
+[INFO|2025-05-27 22:49:24] tokenization_utils_base.py:2525 >> tokenizer config file saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/tokenizer_config.json
+
+[INFO|2025-05-27 22:49:24] tokenization_utils_base.py:2534 >> Special tokens file saved in saves/LLaVA-1.5-7B-Chat/lora/train_k_folds_4_4_epochs/special_tokens_map.json
+
+[WARNING|2025-05-27 22:49:25] logging.py:148 >> No metric eval_loss to plot.
+
+[WARNING|2025-05-27 22:49:25] logging.py:148 >> No metric eval_accuracy to plot.
+
+[INFO|2025-05-27 22:49:25] modelcard.py:450 >> 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 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {
+    "image_token": "<image>"
+  },
+  "image_token": "<image>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "LlavaProcessor",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "num_input_tokens_seen": 2494624,
+    "total_flos": 1.0404813073494835e+17,
+    "train_loss": 2.765545678990228,
+    "train_runtime": 591.3728,
+    "train_samples_per_second": 6.02,
+    "train_steps_per_second": 0.189
+}

trainer_log.jsonl

@@ -0,0 +1,23 @@
+{"current_steps": 5, "total_steps": 112, "loss": 3.5214, "lr": 4.984280524733107e-05, "epoch": 0.17937219730941703, "percentage": 4.46, "elapsed_time": "0:00:26", "remaining_time": "0:09:30", "throughput": 4196.48, "total_tokens": 111952}
+{"current_steps": 10, "total_steps": 112, "loss": 3.3636, "lr": 4.9207588053056545e-05, "epoch": 0.35874439461883406, "percentage": 8.93, "elapsed_time": "0:00:52", "remaining_time": "0:08:56", "throughput": 4256.3, "total_tokens": 223776}
+{"current_steps": 15, "total_steps": 112, "loss": 3.0641, "lr": 4.8096988312782174e-05, "epoch": 0.5381165919282511, "percentage": 13.39, "elapsed_time": "0:01:18", "remaining_time": "0:08:28", "throughput": 4270.16, "total_tokens": 335600}
+{"current_steps": 20, "total_steps": 112, "loss": 2.9922, "lr": 4.653281570581023e-05, "epoch": 0.7174887892376681, "percentage": 17.86, "elapsed_time": "0:01:44", "remaining_time": "0:08:01", "throughput": 4270.54, "total_tokens": 447424}
+{"current_steps": 25, "total_steps": 112, "loss": 3.0359, "lr": 4.454578706170075e-05, "epoch": 0.8968609865470852, "percentage": 22.32, "elapsed_time": "0:02:11", "remaining_time": "0:07:35", "throughput": 4269.56, "total_tokens": 559328}
+{"current_steps": 30, "total_steps": 112, "loss": 2.825, "lr": 4.2174923150872544e-05, "epoch": 1.0717488789237668, "percentage": 26.79, "elapsed_time": "0:02:36", "remaining_time": "0:07:08", "throughput": 4268.14, "total_tokens": 668544}
+{"current_steps": 35, "total_steps": 112, "loss": 2.8427, "lr": 3.946678240449515e-05, "epoch": 1.251121076233184, "percentage": 31.25, "elapsed_time": "0:03:02", "remaining_time": "0:06:42", "throughput": 4266.21, "total_tokens": 780496}
+{"current_steps": 40, "total_steps": 112, "loss": 2.7976, "lr": 3.6474546611688445e-05, "epoch": 1.4304932735426008, "percentage": 35.71, "elapsed_time": "0:03:29", "remaining_time": "0:06:16", "throughput": 4263.24, "total_tokens": 892128}
+{"current_steps": 45, "total_steps": 112, "loss": 2.6764, "lr": 3.3256976548879184e-05, "epoch": 1.609865470852018, "percentage": 40.18, "elapsed_time": "0:03:55", "remaining_time": "0:05:50", "throughput": 4261.43, "total_tokens": 1004112}
+{"current_steps": 50, "total_steps": 112, "loss": 2.7217, "lr": 2.9877258050403212e-05, "epoch": 1.789237668161435, "percentage": 44.64, "elapsed_time": "0:04:21", "remaining_time": "0:05:24", "throughput": 4260.88, "total_tokens": 1116064}
+{"current_steps": 55, "total_steps": 112, "loss": 2.7066, "lr": 2.6401761180929797e-05, "epoch": 1.9686098654708521, "percentage": 49.11, "elapsed_time": "0:04:48", "remaining_time": "0:04:58", "throughput": 4259.29, "total_tokens": 1227808}
+{"current_steps": 60, "total_steps": 112, "loss": 2.6038, "lr": 2.2898736876768815e-05, "epoch": 2.1434977578475336, "percentage": 53.57, "elapsed_time": "0:05:13", "remaining_time": "0:04:32", "throughput": 4258.92, "total_tokens": 1337104}
+{"current_steps": 65, "total_steps": 112, "loss": 2.5954, "lr": 1.9436976651092144e-05, "epoch": 2.3228699551569507, "percentage": 58.04, "elapsed_time": "0:05:40", "remaining_time": "0:04:06", "throughput": 4258.25, "total_tokens": 1448976}
+{"current_steps": 70, "total_steps": 112, "loss": 2.6679, "lr": 1.6084461683442176e-05, "epoch": 2.502242152466368, "percentage": 62.5, "elapsed_time": "0:06:06", "remaining_time": "0:03:39", "throughput": 4256.92, "total_tokens": 1560352}
+{"current_steps": 75, "total_steps": 112, "loss": 2.5975, "lr": 1.2907027822369005e-05, "epoch": 2.681614349775785, "percentage": 66.96, "elapsed_time": "0:06:32", "remaining_time": "0:03:13", "throughput": 4256.5, "total_tokens": 1672176}
+{"current_steps": 80, "total_steps": 112, "loss": 2.6389, "lr": 9.967072717539851e-06, "epoch": 2.8609865470852016, "percentage": 71.43, "elapsed_time": "0:06:59", "remaining_time": "0:02:47", "throughput": 4256.21, "total_tokens": 1784448}
+{"current_steps": 85, "total_steps": 112, "loss": 2.4908, "lr": 7.3223304703363135e-06, "epoch": 3.0358744394618835, "percentage": 75.89, "elapsed_time": "0:07:24", "remaining_time": "0:02:21", "throughput": 4255.5, "total_tokens": 1893216}
+{"current_steps": 90, "total_steps": 112, "loss": 2.6384, "lr": 5.02473786604378e-06, "epoch": 3.2152466367713006, "percentage": 80.36, "elapsed_time": "0:07:51", "remaining_time": "0:01:55", "throughput": 4255.7, "total_tokens": 2005392}
+{"current_steps": 95, "total_steps": 112, "loss": 2.5131, "lr": 3.119414452281158e-06, "epoch": 3.3946188340807173, "percentage": 84.82, "elapsed_time": "0:08:17", "remaining_time": "0:01:29", "throughput": 4255.25, "total_tokens": 2117168}
+{"current_steps": 100, "total_steps": 112, "loss": 2.5565, "lr": 1.6437764926350074e-06, "epoch": 3.5739910313901344, "percentage": 89.29, "elapsed_time": "0:08:43", "remaining_time": "0:01:02", "throughput": 4255.05, "total_tokens": 2229024}
+{"current_steps": 105, "total_steps": 112, "loss": 2.5378, "lr": 6.268021954544096e-07, "epoch": 3.7533632286995515, "percentage": 93.75, "elapsed_time": "0:09:11", "remaining_time": "0:00:36", "throughput": 4240.62, "total_tokens": 2340688}
+{"current_steps": 110, "total_steps": 112, "loss": 2.5846, "lr": 8.846264705952289e-08, "epoch": 3.9327354260089686, "percentage": 98.21, "elapsed_time": "0:09:38", "remaining_time": "0:00:10", "throughput": 4240.92, "total_tokens": 2452784}
+{"current_steps": 112, "total_steps": 112, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "0:09:50", "remaining_time": "0:00:00", "throughput": 4224.56, "total_tokens": 2494624}