Upload LLaVA-OneVision weather satellite DoRA adapter

.gitattributes

@@ -33,3 +33,10 @@ 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-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-294/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-50/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_dora_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_dora_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-dora-weather/runs/09qiypsh) 
+
+
+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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2008d98e89dbe34b1e38956e0b4601cf086ac0d8044ad98ffeeb8b8fcf16382
+size 53239112

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-100/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-100/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60c0f47bf8e97bfb2329957b30552eaf288993a553aad4d0cc6037649dc07a29
+size 53239112

checkpoint-100/added_tokens.json

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

checkpoint-100/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-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68e1f19a0041ad4b7898317dee489e82becfc9ebb5207821b50fe6ab9bc3b49b
+size 106775296

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e1a02341c12a5fdd53d49cd47f95d0762f9f640033fdb1c0b669e3b9e3d061
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9721d5ba1fb05d41f214a5bebb8206b88b746e805209d13e654bce65e0ffa08
+size 1064

checkpoint-100/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-100/tokenizer.json

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

checkpoint-100/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-100/trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_global_step": 100,
+  "best_metric": 0.26103895902633667,
+  "best_model_checkpoint": "./llava_dora_weather_model/checkpoint-100",
+  "epoch": 1.0205655526992288,
+  "eval_steps": 25,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 0.5152251720428467,
+      "learning_rate": 0.0001,
+      "loss": 2.0854,
+      "mean_token_accuracy": 0.5449784517288208,
+      "num_tokens": 645254.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.8606380820274353,
+      "learning_rate": 0.0001,
+      "loss": 1.4846,
+      "mean_token_accuracy": 0.6233440130949021,
+      "num_tokens": 1290816.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "eval_loss": 0.7531503438949585,
+      "eval_mean_token_accuracy": 0.7884166170389224,
+      "eval_num_tokens": 1613469.0,
+      "eval_runtime": 262.0989,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 25
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.7467573881149292,
+      "learning_rate": 0.0001,
+      "loss": 0.8003,
+      "mean_token_accuracy": 0.7741554424166679,
+      "num_tokens": 1936067.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.35523706674575806,
+      "learning_rate": 0.0001,
+      "loss": 0.4382,
+      "mean_token_accuracy": 0.8741505913436413,
+      "num_tokens": 2581570.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.3796336352825165,
+      "learning_rate": 0.0001,
+      "loss": 0.3519,
+      "mean_token_accuracy": 0.8941524222493171,
+      "num_tokens": 3226740.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "eval_loss": 0.33243268728256226,
+      "eval_mean_token_accuracy": 0.9004789113998413,
+      "eval_num_tokens": 3226740.0,
+      "eval_runtime": 262.0578,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 50
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.37023383378982544,
+      "learning_rate": 0.0001,
+      "loss": 0.3303,
+      "mean_token_accuracy": 0.8990803204476834,
+      "num_tokens": 3872000.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.4363132417201996,
+      "learning_rate": 0.0001,
+      "loss": 0.2998,
+      "mean_token_accuracy": 0.9075073637068272,
+      "num_tokens": 4517650.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "eval_loss": 0.28144383430480957,
+      "eval_mean_token_accuracy": 0.9120607966031784,
+      "eval_num_tokens": 4840076.0,
+      "eval_runtime": 262.1457,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 75
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.37328270077705383,
+      "learning_rate": 0.0001,
+      "loss": 0.2725,
+      "mean_token_accuracy": 0.9144053891301155,
+      "num_tokens": 5162524.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.37761208415031433,
+      "learning_rate": 0.0001,
+      "loss": 0.2699,
+      "mean_token_accuracy": 0.914168405532837,
+      "num_tokens": 5808159.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.4116646647453308,
+      "learning_rate": 0.0001,
+      "loss": 0.2577,
+      "mean_token_accuracy": 0.9184043850447681,
+      "num_tokens": 6405024.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "eval_loss": 0.26103895902633667,
+      "eval_mean_token_accuracy": 0.9167074130131648,
+      "eval_num_tokens": 6405024.0,
+      "eval_runtime": 262.2039,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 294,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.8815030313461965e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f1fe3f434674752ff42761b7dcdbf6116320f5a4ad9e8d736732e4ab05e75c
+size 5816

checkpoint-150/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-150/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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c131a6b721cf32f852977ee09a79625cf5ca40854ed9f7c3f77ad41a45b1cf0f
+size 53239112

checkpoint-150/added_tokens.json

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

checkpoint-150/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-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4df92ab984e1913680d611d7dcea29cbe38afbc547cd76e2c8c40f7b0707348e
+size 106775296

checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7069701bb19b2602f94eff91aadf457a861795f0497bf873d0cbb12cab6d880c
+size 14244

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa625c3d289d110f65fab1387b954cea711ff0d79423e66f88e963a9e2a838b7
+size 1064

checkpoint-150/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-150/tokenizer.json

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

checkpoint-150/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-150/trainer_state.json

@@ -0,0 +1,229 @@
+{
+  "best_global_step": 150,
+  "best_metric": 0.22957810759544373,
+  "best_model_checkpoint": "./llava_dora_weather_model/checkpoint-150",
+  "epoch": 1.5347043701799485,
+  "eval_steps": 25,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 0.5152251720428467,
+      "learning_rate": 0.0001,
+      "loss": 2.0854,
+      "mean_token_accuracy": 0.5449784517288208,
+      "num_tokens": 645254.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.8606380820274353,
+      "learning_rate": 0.0001,
+      "loss": 1.4846,
+      "mean_token_accuracy": 0.6233440130949021,
+      "num_tokens": 1290816.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "eval_loss": 0.7531503438949585,
+      "eval_mean_token_accuracy": 0.7884166170389224,
+      "eval_num_tokens": 1613469.0,
+      "eval_runtime": 262.0989,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 25
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.7467573881149292,
+      "learning_rate": 0.0001,
+      "loss": 0.8003,
+      "mean_token_accuracy": 0.7741554424166679,
+      "num_tokens": 1936067.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.35523706674575806,
+      "learning_rate": 0.0001,
+      "loss": 0.4382,
+      "mean_token_accuracy": 0.8741505913436413,
+      "num_tokens": 2581570.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.3796336352825165,
+      "learning_rate": 0.0001,
+      "loss": 0.3519,
+      "mean_token_accuracy": 0.8941524222493171,
+      "num_tokens": 3226740.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "eval_loss": 0.33243268728256226,
+      "eval_mean_token_accuracy": 0.9004789113998413,
+      "eval_num_tokens": 3226740.0,
+      "eval_runtime": 262.0578,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 50
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.37023383378982544,
+      "learning_rate": 0.0001,
+      "loss": 0.3303,
+      "mean_token_accuracy": 0.8990803204476834,
+      "num_tokens": 3872000.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.4363132417201996,
+      "learning_rate": 0.0001,
+      "loss": 0.2998,
+      "mean_token_accuracy": 0.9075073637068272,
+      "num_tokens": 4517650.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "eval_loss": 0.28144383430480957,
+      "eval_mean_token_accuracy": 0.9120607966031784,
+      "eval_num_tokens": 4840076.0,
+      "eval_runtime": 262.1457,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 75
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.37328270077705383,
+      "learning_rate": 0.0001,
+      "loss": 0.2725,
+      "mean_token_accuracy": 0.9144053891301155,
+      "num_tokens": 5162524.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.37761208415031433,
+      "learning_rate": 0.0001,
+      "loss": 0.2699,
+      "mean_token_accuracy": 0.914168405532837,
+      "num_tokens": 5808159.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.4116646647453308,
+      "learning_rate": 0.0001,
+      "loss": 0.2577,
+      "mean_token_accuracy": 0.9184043850447681,
+      "num_tokens": 6405024.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "eval_loss": 0.26103895902633667,
+      "eval_mean_token_accuracy": 0.9167074130131648,
+      "eval_num_tokens": 6405024.0,
+      "eval_runtime": 262.2039,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 100
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 0.47321799397468567,
+      "learning_rate": 0.0001,
+      "loss": 0.2496,
+      "mean_token_accuracy": 0.9199652373790741,
+      "num_tokens": 7050233.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.43690064549446106,
+      "learning_rate": 0.0001,
+      "loss": 0.2435,
+      "mean_token_accuracy": 0.9212526880204678,
+      "num_tokens": 7695653.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.2776349614395888,
+      "eval_loss": 0.23867399990558624,
+      "eval_mean_token_accuracy": 0.9220352160624968,
+      "eval_num_tokens": 8018413.0,
+      "eval_runtime": 262.0533,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 125
+    },
+    {
+      "epoch": 1.3290488431876606,
+      "grad_norm": 0.4848271608352661,
+      "learning_rate": 0.0001,
+      "loss": 0.2325,
+      "mean_token_accuracy": 0.9234701178967952,
+      "num_tokens": 8341317.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 0.471851110458374,
+      "learning_rate": 0.0001,
+      "loss": 0.2214,
+      "mean_token_accuracy": 0.9266947895288468,
+      "num_tokens": 8986431.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "grad_norm": 0.4235078692436218,
+      "learning_rate": 0.0001,
+      "loss": 0.2204,
+      "mean_token_accuracy": 0.9253557249903679,
+      "num_tokens": 9631882.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "eval_loss": 0.22957810759544373,
+      "eval_mean_token_accuracy": 0.9235361132866297,
+      "eval_num_tokens": 9631882.0,
+      "eval_runtime": 262.1591,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 150
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 294,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.3332073666810406e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f1fe3f434674752ff42761b7dcdbf6116320f5a4ad9e8d736732e4ab05e75c
+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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "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:db5ae50cc079c6d79fc0fc743fc1ba954dc7b62d1a88d112d8a401e356a64d92
+size 53239112

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 sha256:417a627da803614520c1a2b0841c170633bdc9f59a2a35b16e4db374db9cf683
+size 106775296

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e27bc1caa861384209f0c7f33514d4f9a979391846e9df83276b128300dab0f
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da963d3b7106f3b4c395d03ef6897e64220165c23480563310345c76ab7b120d
+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 +1,294 @@
+{
+  "best_global_step": 200,
+  "best_metric": 0.21981394290924072,
+  "best_model_checkpoint": "./llava_dora_weather_model/checkpoint-200",
+  "epoch": 2.0411311053984575,
+  "eval_steps": 25,
+  "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": 0.5152251720428467,
+      "learning_rate": 0.0001,
+      "loss": 2.0854,
+      "mean_token_accuracy": 0.5449784517288208,
+      "num_tokens": 645254.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.8606380820274353,
+      "learning_rate": 0.0001,
+      "loss": 1.4846,
+      "mean_token_accuracy": 0.6233440130949021,
+      "num_tokens": 1290816.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "eval_loss": 0.7531503438949585,
+      "eval_mean_token_accuracy": 0.7884166170389224,
+      "eval_num_tokens": 1613469.0,
+      "eval_runtime": 262.0989,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 25
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.7467573881149292,
+      "learning_rate": 0.0001,
+      "loss": 0.8003,
+      "mean_token_accuracy": 0.7741554424166679,
+      "num_tokens": 1936067.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.35523706674575806,
+      "learning_rate": 0.0001,
+      "loss": 0.4382,
+      "mean_token_accuracy": 0.8741505913436413,
+      "num_tokens": 2581570.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.3796336352825165,
+      "learning_rate": 0.0001,
+      "loss": 0.3519,
+      "mean_token_accuracy": 0.8941524222493171,
+      "num_tokens": 3226740.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "eval_loss": 0.33243268728256226,
+      "eval_mean_token_accuracy": 0.9004789113998413,
+      "eval_num_tokens": 3226740.0,
+      "eval_runtime": 262.0578,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 50
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.37023383378982544,
+      "learning_rate": 0.0001,
+      "loss": 0.3303,
+      "mean_token_accuracy": 0.8990803204476834,
+      "num_tokens": 3872000.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.4363132417201996,
+      "learning_rate": 0.0001,
+      "loss": 0.2998,
+      "mean_token_accuracy": 0.9075073637068272,
+      "num_tokens": 4517650.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "eval_loss": 0.28144383430480957,
+      "eval_mean_token_accuracy": 0.9120607966031784,
+      "eval_num_tokens": 4840076.0,
+      "eval_runtime": 262.1457,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 75
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.37328270077705383,
+      "learning_rate": 0.0001,
+      "loss": 0.2725,
+      "mean_token_accuracy": 0.9144053891301155,
+      "num_tokens": 5162524.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.37761208415031433,
+      "learning_rate": 0.0001,
+      "loss": 0.2699,
+      "mean_token_accuracy": 0.914168405532837,
+      "num_tokens": 5808159.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.4116646647453308,
+      "learning_rate": 0.0001,
+      "loss": 0.2577,
+      "mean_token_accuracy": 0.9184043850447681,
+      "num_tokens": 6405024.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "eval_loss": 0.26103895902633667,
+      "eval_mean_token_accuracy": 0.9167074130131648,
+      "eval_num_tokens": 6405024.0,
+      "eval_runtime": 262.2039,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 100
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 0.47321799397468567,
+      "learning_rate": 0.0001,
+      "loss": 0.2496,
+      "mean_token_accuracy": 0.9199652373790741,
+      "num_tokens": 7050233.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.43690064549446106,
+      "learning_rate": 0.0001,
+      "loss": 0.2435,
+      "mean_token_accuracy": 0.9212526880204678,
+      "num_tokens": 7695653.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.2776349614395888,
+      "eval_loss": 0.23867399990558624,
+      "eval_mean_token_accuracy": 0.9220352160624968,
+      "eval_num_tokens": 8018413.0,
+      "eval_runtime": 262.0533,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 125
+    },
+    {
+      "epoch": 1.3290488431876606,
+      "grad_norm": 0.4848271608352661,
+      "learning_rate": 0.0001,
+      "loss": 0.2325,
+      "mean_token_accuracy": 0.9234701178967952,
+      "num_tokens": 8341317.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 0.471851110458374,
+      "learning_rate": 0.0001,
+      "loss": 0.2214,
+      "mean_token_accuracy": 0.9266947895288468,
+      "num_tokens": 8986431.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "grad_norm": 0.4235078692436218,
+      "learning_rate": 0.0001,
+      "loss": 0.2204,
+      "mean_token_accuracy": 0.9253557249903679,
+      "num_tokens": 9631882.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "eval_loss": 0.22957810759544373,
+      "eval_mean_token_accuracy": 0.9235361132866297,
+      "eval_num_tokens": 9631882.0,
+      "eval_runtime": 262.1591,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.744,
+      "step": 150
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "grad_norm": 0.4376716613769531,
+      "learning_rate": 0.0001,
+      "loss": 0.2201,
+      "mean_token_accuracy": 0.9248783186078071,
+      "num_tokens": 10277533.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.7403598971722365,
+      "grad_norm": 0.43904566764831543,
+      "learning_rate": 0.0001,
+      "loss": 0.2287,
+      "mean_token_accuracy": 0.9224192254245281,
+      "num_tokens": 10922895.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.7917737789203085,
+      "eval_loss": 0.22500084340572357,
+      "eval_mean_token_accuracy": 0.9243928493597569,
+      "eval_num_tokens": 11245730.0,
+      "eval_runtime": 262.5112,
+      "eval_samples_per_second": 0.743,
+      "eval_steps_per_second": 0.743,
+      "step": 175
+    },
+    {
+      "epoch": 1.8431876606683804,
+      "grad_norm": 0.39153727889060974,
+      "learning_rate": 0.0001,
+      "loss": 0.2142,
+      "mean_token_accuracy": 0.9261229902505874,
+      "num_tokens": 11568708.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.9460154241645244,
+      "grad_norm": 0.44200599193573,
+      "learning_rate": 0.0001,
+      "loss": 0.2144,
+      "mean_token_accuracy": 0.9287430047988892,
+      "num_tokens": 12213156.0,
+      "step": 190
+    },
+    {
+      "epoch": 2.0411311053984575,
+      "grad_norm": 0.40645667910575867,
+      "learning_rate": 0.0001,
+      "loss": 0.2113,
+      "mean_token_accuracy": 0.9269847950419864,
+      "num_tokens": 12809961.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.0411311053984575,
+      "eval_loss": 0.21981394290924072,
+      "eval_mean_token_accuracy": 0.9264772112552936,
+      "eval_num_tokens": 12809961.0,
+      "eval_runtime": 262.3645,
+      "eval_samples_per_second": 0.743,
+      "eval_steps_per_second": 0.743,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 294,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.762966922985231e+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 sha256:89f1fe3f434674752ff42761b7dcdbf6116320f5a4ad9e8d736732e4ab05e75c
+size 5816