Upload LLaVA-OneVision weather satellite AdaLoRA adapter

.gitattributes

@@ -33,3 +33,14 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-160/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-80/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+base_model: llava-hf/llava-onevision-qwen2-7b-ov-hf
+library_name: peft
+model_name: llava_adalora_weather_model
+tags:
+- base_model:adapter:llava-hf/llava-onevision-qwen2-7b-ov-hf
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for llava_adalora_weather_model
+
+This model is a fine-tuned version of [llava-hf/llava-onevision-qwen2-7b-ov-hf](https://huggingface.co/llava-hf/llava-onevision-qwen2-7b-ov-hf).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/azdinsahir11-university-mohamed-v/llava-onevision-adalora-weather/runs/m8m1fc1p) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.16.0
+- TRL: 0.19.1
+- Transformers: 4.53.3
+- Pytorch: 2.6.0+cu124
+- Datasets: 4.0.0
+- Tokenizers: 0.21.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "llava-hf/llava-onevision-qwen2-7b-ov-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": 24,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 12,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da2dcff2f87ae9076f1d4e58d793438cadcf2dd8ed88a111f7e65eabd1b4ca8
+size 38963456

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<image>": 151646,
+  "<video>": 151647,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-120/README.md

@@ -0,0 +1,209 @@
+---
+base_model: llava-hf/llava-onevision-qwen2-7b-ov-hf
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:llava-hf/llava-onevision-qwen2-7b-ov-hf
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.16.0

checkpoint-120/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "llava-hf/llava-onevision-qwen2-7b-ov-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": 24,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 12,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-120/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6fc447c381e3ce4d3b2968c9b75cf6fa45a5762a815cd7785e020b0c64fc676
+size 38963456

checkpoint-120/added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<image>": 151646,
+  "<video>": 151647,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-120/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-120/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08fdcf2f84ca67d8f54e649d2bae932f91f1124a76555bc9aedfe5992fb8ad1a
+size 78126726

checkpoint-120/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c3b4908440fbf2ecbdd495cd2dac383cc2b9bfde82fdc9a566927e28f3892a
+size 14244

checkpoint-120/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fade00f111acdd833f7b0d851d6af49db2dd6691910453c9ee7b286f7574ebc4
+size 1064

checkpoint-120/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-120/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22acdce2f613a63fdd5803fbf73706de47621ed05578ba2553482f4d59a3d611
+size 11418802

checkpoint-120/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<video>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_max_length": 131072,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "LlavaOnevisionProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-120/trainer_state.json

@@ -0,0 +1,202 @@
+{
+  "best_global_step": 120,
+  "best_metric": 0.2247939258813858,
+  "best_model_checkpoint": "./llava_adalora_weather_model/checkpoint-120",
+  "epoch": 1.2262210796915167,
+  "eval_steps": 20,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 0.5032290816307068,
+      "learning_rate": 6.75e-05,
+      "loss": 2.3108,
+      "mean_token_accuracy": 0.5181779790669679,
+      "num_tokens": 645254.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.5140016078948975,
+      "learning_rate": 0.0001425,
+      "loss": 1.9876,
+      "mean_token_accuracy": 0.5564090937376023,
+      "num_tokens": 1290816.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "eval_loss": 1.6786144971847534,
+      "eval_mean_token_accuracy": 0.5918497213950524,
+      "eval_num_tokens": 1290816.0,
+      "eval_runtime": 199.77,
+      "eval_samples_per_second": 0.976,
+      "eval_steps_per_second": 0.976,
+      "step": 20
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 1.200245976448059,
+      "learning_rate": 0.00021749999999999997,
+      "loss": 1.2898,
+      "mean_token_accuracy": 0.6574281774461269,
+      "num_tokens": 1936067.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.3560621440410614,
+      "learning_rate": 0.00029249999999999995,
+      "loss": 0.5269,
+      "mean_token_accuracy": 0.8504049643874169,
+      "num_tokens": 2581570.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "eval_loss": 0.3815372884273529,
+      "eval_mean_token_accuracy": 0.8895098340816987,
+      "eval_num_tokens": 2581570.0,
+      "eval_runtime": 199.91,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 40
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.36290714144706726,
+      "learning_rate": 0.0002995163544683256,
+      "loss": 0.3431,
+      "mean_token_accuracy": 0.8966262958943844,
+      "num_tokens": 3226740.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.3132888674736023,
+      "learning_rate": 0.00029784849709745616,
+      "loss": 0.3131,
+      "mean_token_accuracy": 0.9030718393623829,
+      "num_tokens": 3872000.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "eval_loss": 0.2877984046936035,
+      "eval_mean_token_accuracy": 0.9094783853261899,
+      "eval_num_tokens": 3872000.0,
+      "eval_runtime": 200.0291,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 60
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.3172520697116852,
+      "learning_rate": 0.0002950037303267096,
+      "loss": 0.2776,
+      "mean_token_accuracy": 0.9121568284928798,
+      "num_tokens": 4517650.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.2681174576282501,
+      "learning_rate": 0.0002910046991800035,
+      "loss": 0.2463,
+      "mean_token_accuracy": 0.9197294652462006,
+      "num_tokens": 5162524.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "eval_loss": 0.24699676036834717,
+      "eval_mean_token_accuracy": 0.918833449559334,
+      "eval_num_tokens": 5162524.0,
+      "eval_runtime": 199.9764,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 80
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.25532031059265137,
+      "learning_rate": 0.00028588323690176954,
+      "loss": 0.2409,
+      "mean_token_accuracy": 0.9201722621917725,
+      "num_tokens": 5808159.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.2883255183696747,
+      "learning_rate": 0.0002796801115567139,
+      "loss": 0.229,
+      "mean_token_accuracy": 0.9240316643908217,
+      "num_tokens": 6405024.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "eval_loss": 0.2340758889913559,
+      "eval_mean_token_accuracy": 0.9224844058354695,
+      "eval_num_tokens": 6405024.0,
+      "eval_runtime": 199.917,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 100
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 0.30399489402770996,
+      "learning_rate": 0.0002724447015062708,
+      "loss": 0.2179,
+      "mean_token_accuracy": 0.927613090723753,
+      "num_tokens": 7050233.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.28451991081237793,
+      "learning_rate": 0.0002642346023450357,
+      "loss": 0.216,
+      "mean_token_accuracy": 0.9265601448714733,
+      "num_tokens": 7695653.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "eval_loss": 0.2247939258813858,
+      "eval_mean_token_accuracy": 0.925137395125169,
+      "eval_num_tokens": 7695653.0,
+      "eval_runtime": 199.5418,
+      "eval_samples_per_second": 0.977,
+      "eval_steps_per_second": 0.977,
+      "step": 120
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 392,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.4604890360353197e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-120/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ee18fc7fc6461abdc27ef50b94a39880806ee3c787211adab9a8a0c2d2ed0c
+size 5816

checkpoint-160/README.md

@@ -0,0 +1,209 @@
+---
+base_model: llava-hf/llava-onevision-qwen2-7b-ov-hf
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:llava-hf/llava-onevision-qwen2-7b-ov-hf
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.16.0

checkpoint-160/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "llava-hf/llava-onevision-qwen2-7b-ov-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": 24,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 12,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-160/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b3bd2e6fcec92a0413bb0b0ae69eb661fd89d444815d2757934c8494a50d3a5
+size 38963456

checkpoint-160/added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<image>": 151646,
+  "<video>": 151647,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-160/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-160/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b2eb742e96a127f01686548229ac91cec39d4e96962ce02d1a300dc23c1a88
+size 78126726

checkpoint-160/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1363ed0cee96992d997af407c2663ebdbfbaded8d2e82aab54e259ec142bde37
+size 14244

checkpoint-160/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4078e2a7c02601d5e0eeb618902a971f3d69ca4bff8d896454ff2d0d00f255c8
+size 1064

checkpoint-160/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-160/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22acdce2f613a63fdd5803fbf73706de47621ed05578ba2553482f4d59a3d611
+size 11418802

checkpoint-160/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<video>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_max_length": 131072,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "LlavaOnevisionProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-160/trainer_state.json

@@ -0,0 +1,258 @@
+{
+  "best_global_step": 160,
+  "best_metric": 0.21295307576656342,
+  "best_model_checkpoint": "./llava_adalora_weather_model/checkpoint-160",
+  "epoch": 1.6375321336760926,
+  "eval_steps": 20,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 0.5032290816307068,
+      "learning_rate": 6.75e-05,
+      "loss": 2.3108,
+      "mean_token_accuracy": 0.5181779790669679,
+      "num_tokens": 645254.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.5140016078948975,
+      "learning_rate": 0.0001425,
+      "loss": 1.9876,
+      "mean_token_accuracy": 0.5564090937376023,
+      "num_tokens": 1290816.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "eval_loss": 1.6786144971847534,
+      "eval_mean_token_accuracy": 0.5918497213950524,
+      "eval_num_tokens": 1290816.0,
+      "eval_runtime": 199.77,
+      "eval_samples_per_second": 0.976,
+      "eval_steps_per_second": 0.976,
+      "step": 20
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 1.200245976448059,
+      "learning_rate": 0.00021749999999999997,
+      "loss": 1.2898,
+      "mean_token_accuracy": 0.6574281774461269,
+      "num_tokens": 1936067.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.3560621440410614,
+      "learning_rate": 0.00029249999999999995,
+      "loss": 0.5269,
+      "mean_token_accuracy": 0.8504049643874169,
+      "num_tokens": 2581570.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "eval_loss": 0.3815372884273529,
+      "eval_mean_token_accuracy": 0.8895098340816987,
+      "eval_num_tokens": 2581570.0,
+      "eval_runtime": 199.91,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 40
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.36290714144706726,
+      "learning_rate": 0.0002995163544683256,
+      "loss": 0.3431,
+      "mean_token_accuracy": 0.8966262958943844,
+      "num_tokens": 3226740.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.3132888674736023,
+      "learning_rate": 0.00029784849709745616,
+      "loss": 0.3131,
+      "mean_token_accuracy": 0.9030718393623829,
+      "num_tokens": 3872000.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "eval_loss": 0.2877984046936035,
+      "eval_mean_token_accuracy": 0.9094783853261899,
+      "eval_num_tokens": 3872000.0,
+      "eval_runtime": 200.0291,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 60
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.3172520697116852,
+      "learning_rate": 0.0002950037303267096,
+      "loss": 0.2776,
+      "mean_token_accuracy": 0.9121568284928798,
+      "num_tokens": 4517650.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.2681174576282501,
+      "learning_rate": 0.0002910046991800035,
+      "loss": 0.2463,
+      "mean_token_accuracy": 0.9197294652462006,
+      "num_tokens": 5162524.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "eval_loss": 0.24699676036834717,
+      "eval_mean_token_accuracy": 0.918833449559334,
+      "eval_num_tokens": 5162524.0,
+      "eval_runtime": 199.9764,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 80
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.25532031059265137,
+      "learning_rate": 0.00028588323690176954,
+      "loss": 0.2409,
+      "mean_token_accuracy": 0.9201722621917725,
+      "num_tokens": 5808159.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.2883255183696747,
+      "learning_rate": 0.0002796801115567139,
+      "loss": 0.229,
+      "mean_token_accuracy": 0.9240316643908217,
+      "num_tokens": 6405024.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "eval_loss": 0.2340758889913559,
+      "eval_mean_token_accuracy": 0.9224844058354695,
+      "eval_num_tokens": 6405024.0,
+      "eval_runtime": 199.917,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 100
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 0.30399489402770996,
+      "learning_rate": 0.0002724447015062708,
+      "loss": 0.2179,
+      "mean_token_accuracy": 0.927613090723753,
+      "num_tokens": 7050233.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.28451991081237793,
+      "learning_rate": 0.0002642346023450357,
+      "loss": 0.216,
+      "mean_token_accuracy": 0.9265601448714733,
+      "num_tokens": 7695653.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "eval_loss": 0.2247939258813858,
+      "eval_mean_token_accuracy": 0.925137395125169,
+      "eval_num_tokens": 7695653.0,
+      "eval_runtime": 199.5418,
+      "eval_samples_per_second": 0.977,
+      "eval_steps_per_second": 0.977,
+      "step": 120
+    },
+    {
+      "epoch": 1.3290488431876606,
+      "grad_norm": 0.28032347559928894,
+      "learning_rate": 0.0002551151684260553,
+      "loss": 0.2093,
+      "mean_token_accuracy": 0.9289478570222854,
+      "num_tokens": 8341317.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 0.3006415367126465,
+      "learning_rate": 0.0002451589926245468,
+      "loss": 0.2017,
+      "mean_token_accuracy": 0.930090955644846,
+      "num_tokens": 8986431.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "eval_loss": 0.22003041207790375,
+      "eval_mean_token_accuracy": 0.9265705820841666,
+      "eval_num_tokens": 8986431.0,
+      "eval_runtime": 199.7226,
+      "eval_samples_per_second": 0.976,
+      "eval_steps_per_second": 0.976,
+      "step": 140
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "grad_norm": 0.27291589975357056,
+      "learning_rate": 0.00023444532848124715,
+      "loss": 0.2008,
+      "mean_token_accuracy": 0.9297313310205937,
+      "num_tokens": 9631882.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "grad_norm": 0.2605527639389038,
+      "learning_rate": 0.00022305945932527308,
+      "loss": 0.2019,
+      "mean_token_accuracy": 0.9302895963191986,
+      "num_tokens": 10277533.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "eval_loss": 0.21295307576656342,
+      "eval_mean_token_accuracy": 0.9283858265632238,
+      "eval_num_tokens": 10277533.0,
+      "eval_runtime": 199.8041,
+      "eval_samples_per_second": 0.976,
+      "eval_steps_per_second": 0.976,
+      "step": 160
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 392,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.6214778997950125e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-160/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ee18fc7fc6461abdc27ef50b94a39880806ee3c787211adab9a8a0c2d2ed0c
+size 5816

checkpoint-200/README.md

@@ -0,0 +1,209 @@
+---
+base_model: llava-hf/llava-onevision-qwen2-7b-ov-hf
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:llava-hf/llava-onevision-qwen2-7b-ov-hf
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.16.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "llava-hf/llava-onevision-qwen2-7b-ov-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": 24,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 12,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0a86e48c68c28953bc3d111de3cef10fdbcc8e0d4bd8436ee4d800034aa58f
+size 38963456

checkpoint-200/added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<image>": 151646,
+  "<video>": 151647,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-200/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886468e8b3d249d16598096b819c91ce8e3e2ba88c26de3c3bee879d9e39e6a3
+size 78126726

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b039ba5878e493b5725ddd19920f58db431c5db2862e3c050886795fabb06b1
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:466a3e032ea2a04b4fd1ef71f9841bdf4f29fc0770db16c430c9234351b79982
+size 1064

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22acdce2f613a63fdd5803fbf73706de47621ed05578ba2553482f4d59a3d611
+size 11418802

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<video>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_max_length": 131072,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "LlavaOnevisionProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,314 @@
+{
+  "best_global_step": 200,
+  "best_metric": 0.20741970837116241,
+  "best_model_checkpoint": "./llava_adalora_weather_model/checkpoint-200",
+  "epoch": 2.0411311053984575,
+  "eval_steps": 20,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 0.5032290816307068,
+      "learning_rate": 6.75e-05,
+      "loss": 2.3108,
+      "mean_token_accuracy": 0.5181779790669679,
+      "num_tokens": 645254.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.5140016078948975,
+      "learning_rate": 0.0001425,
+      "loss": 1.9876,
+      "mean_token_accuracy": 0.5564090937376023,
+      "num_tokens": 1290816.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "eval_loss": 1.6786144971847534,
+      "eval_mean_token_accuracy": 0.5918497213950524,
+      "eval_num_tokens": 1290816.0,
+      "eval_runtime": 199.77,
+      "eval_samples_per_second": 0.976,
+      "eval_steps_per_second": 0.976,
+      "step": 20
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 1.200245976448059,
+      "learning_rate": 0.00021749999999999997,
+      "loss": 1.2898,
+      "mean_token_accuracy": 0.6574281774461269,
+      "num_tokens": 1936067.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.3560621440410614,
+      "learning_rate": 0.00029249999999999995,
+      "loss": 0.5269,
+      "mean_token_accuracy": 0.8504049643874169,
+      "num_tokens": 2581570.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "eval_loss": 0.3815372884273529,
+      "eval_mean_token_accuracy": 0.8895098340816987,
+      "eval_num_tokens": 2581570.0,
+      "eval_runtime": 199.91,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 40
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.36290714144706726,
+      "learning_rate": 0.0002995163544683256,
+      "loss": 0.3431,
+      "mean_token_accuracy": 0.8966262958943844,
+      "num_tokens": 3226740.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.3132888674736023,
+      "learning_rate": 0.00029784849709745616,
+      "loss": 0.3131,
+      "mean_token_accuracy": 0.9030718393623829,
+      "num_tokens": 3872000.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "eval_loss": 0.2877984046936035,
+      "eval_mean_token_accuracy": 0.9094783853261899,
+      "eval_num_tokens": 3872000.0,
+      "eval_runtime": 200.0291,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 60
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.3172520697116852,
+      "learning_rate": 0.0002950037303267096,
+      "loss": 0.2776,
+      "mean_token_accuracy": 0.9121568284928798,
+      "num_tokens": 4517650.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.2681174576282501,
+      "learning_rate": 0.0002910046991800035,
+      "loss": 0.2463,
+      "mean_token_accuracy": 0.9197294652462006,
+      "num_tokens": 5162524.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "eval_loss": 0.24699676036834717,
+      "eval_mean_token_accuracy": 0.918833449559334,
+      "eval_num_tokens": 5162524.0,
+      "eval_runtime": 199.9764,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 80
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.25532031059265137,
+      "learning_rate": 0.00028588323690176954,
+      "loss": 0.2409,
+      "mean_token_accuracy": 0.9201722621917725,
+      "num_tokens": 5808159.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.2883255183696747,
+      "learning_rate": 0.0002796801115567139,
+      "loss": 0.229,
+      "mean_token_accuracy": 0.9240316643908217,
+      "num_tokens": 6405024.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "eval_loss": 0.2340758889913559,
+      "eval_mean_token_accuracy": 0.9224844058354695,
+      "eval_num_tokens": 6405024.0,
+      "eval_runtime": 199.917,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 100
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 0.30399489402770996,
+      "learning_rate": 0.0002724447015062708,
+      "loss": 0.2179,
+      "mean_token_accuracy": 0.927613090723753,
+      "num_tokens": 7050233.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.28451991081237793,
+      "learning_rate": 0.0002642346023450357,
+      "loss": 0.216,
+      "mean_token_accuracy": 0.9265601448714733,
+      "num_tokens": 7695653.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "eval_loss": 0.2247939258813858,
+      "eval_mean_token_accuracy": 0.925137395125169,
+      "eval_num_tokens": 7695653.0,
+      "eval_runtime": 199.5418,
+      "eval_samples_per_second": 0.977,
+      "eval_steps_per_second": 0.977,
+      "step": 120
+    },
+    {
+      "epoch": 1.3290488431876606,
+      "grad_norm": 0.28032347559928894,
+      "learning_rate": 0.0002551151684260553,
+      "loss": 0.2093,
+      "mean_token_accuracy": 0.9289478570222854,
+      "num_tokens": 8341317.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 0.3006415367126465,
+      "learning_rate": 0.0002451589926245468,
+      "loss": 0.2017,
+      "mean_token_accuracy": 0.930090955644846,
+      "num_tokens": 8986431.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "eval_loss": 0.22003041207790375,
+      "eval_mean_token_accuracy": 0.9265705820841666,
+      "eval_num_tokens": 8986431.0,
+      "eval_runtime": 199.7226,
+      "eval_samples_per_second": 0.976,
+      "eval_steps_per_second": 0.976,
+      "step": 140
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "grad_norm": 0.27291589975357056,
+      "learning_rate": 0.00023444532848124715,
+      "loss": 0.2008,
+      "mean_token_accuracy": 0.9297313310205937,
+      "num_tokens": 9631882.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "grad_norm": 0.2605527639389038,
+      "learning_rate": 0.00022305945932527308,
+      "loss": 0.2019,
+      "mean_token_accuracy": 0.9302895963191986,
+      "num_tokens": 10277533.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "eval_loss": 0.21295307576656342,
+      "eval_mean_token_accuracy": 0.9283858265632238,
+      "eval_num_tokens": 10277533.0,
+      "eval_runtime": 199.8041,
+      "eval_samples_per_second": 0.976,
+      "eval_steps_per_second": 0.976,
+      "step": 160
+    },
+    {
+      "epoch": 1.7403598971722365,
+      "grad_norm": 0.2581302523612976,
+      "learning_rate": 0.0002110920193984228,
+      "loss": 0.2082,
+      "mean_token_accuracy": 0.9276637695729733,
+      "num_tokens": 10922895.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.8431876606683804,
+      "grad_norm": 0.2544514238834381,
+      "learning_rate": 0.00019863827238493308,
+      "loss": 0.1954,
+      "mean_token_accuracy": 0.9318794839084148,
+      "num_tokens": 11568708.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.8431876606683804,
+      "eval_loss": 0.20810775458812714,
+      "eval_mean_token_accuracy": 0.9295981232936565,
+      "eval_num_tokens": 11568708.0,
+      "eval_runtime": 200.1655,
+      "eval_samples_per_second": 0.974,
+      "eval_steps_per_second": 0.974,
+      "step": 180
+    },
+    {
+      "epoch": 1.9460154241645244,
+      "grad_norm": 0.2642477750778198,
+      "learning_rate": 0.00018579735308976727,
+      "loss": 0.1966,
+      "mean_token_accuracy": 0.9328551657497883,
+      "num_tokens": 12213156.0,
+      "step": 190
+    },
+    {
+      "epoch": 2.0411311053984575,
+      "grad_norm": 0.25700676441192627,
+      "learning_rate": 0.00017267147830185608,
+      "loss": 0.1901,
+      "mean_token_accuracy": 0.9336085150370727,
+      "num_tokens": 12809961.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.0411311053984575,
+      "eval_loss": 0.20741970837116241,
+      "eval_mean_token_accuracy": 0.9298222092481759,
+      "eval_num_tokens": 12809961.0,
+      "eval_runtime": 199.9295,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 392,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.760229780700876e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ee18fc7fc6461abdc27ef50b94a39880806ee3c787211adab9a8a0c2d2ed0c
+size 5816