Upload LLaVA-OneVision weather satellite QLoRA adapter

.gitattributes

@@ -33,3 +33,7 @@ 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-124/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-147/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-62/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+base_model: llava-hf/llava-onevision-qwen2-7b-ov-hf
+library_name: peft
+model_name: llava_qlora_weather_model
+tags:
+- base_model:adapter:llava-hf/llava-onevision-qwen2-7b-ov-hf
+- lora
+- sft
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for llava_qlora_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-qlora-weather/runs/7e65t9r9) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.16.0
+- TRL: 0.20.0
+- 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 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "lm_head",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "embed_tokens"
+  ],
+  "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 sha256:94d2744f2d9ffc902b1424b194d7447ed4f2ea36074f932cfe5f522d1db179ba
+size 2526966408

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-124/README.md

@@ -0,0 +1,208 @@
+---
+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
+- 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-124/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "lm_head",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "embed_tokens"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-124/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d2744f2d9ffc902b1424b194d7447ed4f2ea36074f932cfe5f522d1db179ba
+size 2526966408

checkpoint-124/added_tokens.json

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

checkpoint-124/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-124/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c68119d019b904c3865da747377e8539e575f28190954a3e004b7a616e97d2
+size 9415913858

checkpoint-124/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17e4a4810055d820bd45f1c22b68b15d62c4009d45e02176ed32387db7a237f
+size 14244

checkpoint-124/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e48158ab734cf4986c4b1230ae3898188781c08ee539377b69e959715553080
+size 1064

checkpoint-124/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-124/tokenizer.json

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

checkpoint-124/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-124/trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_global_step": 124,
+  "best_metric": 0.19054362177848816,
+  "best_model_checkpoint": "./llava_qlora_weather_model/checkpoint-124",
+  "epoch": 2.5347043701799485,
+  "eval_steps": 31,
+  "global_step": 124,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 2.331812620162964,
+      "learning_rate": 0.0001999744599547812,
+      "loss": 1.3843,
+      "mean_token_accuracy": 0.6790310423821211,
+      "num_tokens": 1290816.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.9054113030433655,
+      "learning_rate": 0.00019692540862655585,
+      "loss": 0.2958,
+      "mean_token_accuracy": 0.9068963050842285,
+      "num_tokens": 2581570.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.7487640380859375,
+      "learning_rate": 0.00018894622845670283,
+      "loss": 0.2476,
+      "mean_token_accuracy": 0.917157232388854,
+      "num_tokens": 3872000.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.6375321336760925,
+      "eval_loss": 0.23227548599243164,
+      "eval_mean_token_accuracy": 0.9232641770289495,
+      "eval_num_tokens": 4001060.0,
+      "eval_runtime": 276.5084,
+      "eval_samples_per_second": 0.705,
+      "eval_steps_per_second": 0.705,
+      "step": 31
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.6455361843109131,
+      "learning_rate": 0.0001764427819207624,
+      "loss": 0.2208,
+      "mean_token_accuracy": 0.9249804724007845,
+      "num_tokens": 5162524.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.5358895659446716,
+      "learning_rate": 0.00016005105914000507,
+      "loss": 0.2077,
+      "mean_token_accuracy": 0.929297363990313,
+      "num_tokens": 6405024.0,
+      "step": 50
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.5378326177597046,
+      "learning_rate": 0.00014060482812625055,
+      "loss": 0.1782,
+      "mean_token_accuracy": 0.9367100398987531,
+      "num_tokens": 7695653.0,
+      "step": 60
+    },
+    {
+      "epoch": 1.2673521850899743,
+      "eval_loss": 0.20991797745227814,
+      "eval_mean_token_accuracy": 0.9294621323927855,
+      "eval_num_tokens": 7953894.0,
+      "eval_runtime": 276.7899,
+      "eval_samples_per_second": 0.705,
+      "eval_steps_per_second": 0.705,
+      "step": 62
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 0.5556976199150085,
+      "learning_rate": 0.00011909322501769406,
+      "loss": 0.1738,
+      "mean_token_accuracy": 0.9374068416655064,
+      "num_tokens": 8986431.0,
+      "step": 70
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "grad_norm": 0.5379733443260193,
+      "learning_rate": 9.661044148624037e-05,
+      "loss": 0.17,
+      "mean_token_accuracy": 0.9386381138116121,
+      "num_tokens": 10277533.0,
+      "step": 80
+    },
+    {
+      "epoch": 1.8431876606683804,
+      "grad_norm": 0.532435417175293,
+      "learning_rate": 7.430006847567972e-05,
+      "loss": 0.1691,
+      "mean_token_accuracy": 0.9383826002478599,
+      "num_tokens": 11568708.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.904884318766067,
+      "eval_loss": 0.19236187636852264,
+      "eval_mean_token_accuracy": 0.934929045347067,
+      "eval_num_tokens": 11955105.0,
+      "eval_runtime": 277.3902,
+      "eval_samples_per_second": 0.703,
+      "eval_steps_per_second": 0.703,
+      "step": 93
+    },
+    {
+      "epoch": 2.0411311053984575,
+      "grad_norm": 0.4640503525733948,
+      "learning_rate": 5.329692723675994e-05,
+      "loss": 0.1587,
+      "mean_token_accuracy": 0.9431061984656693,
+      "num_tokens": 12809961.0,
+      "step": 100
+    },
+    {
+      "epoch": 2.2467866323907453,
+      "grad_norm": 0.4997648596763611,
+      "learning_rate": 3.466934643431795e-05,
+      "loss": 0.1347,
+      "mean_token_accuracy": 0.950631283223629,
+      "num_tokens": 14099963.0,
+      "step": 110
+    },
+    {
+      "epoch": 2.4524421593830334,
+      "grad_norm": 0.44113558530807495,
+      "learning_rate": 1.9364821412094857e-05,
+      "loss": 0.131,
+      "mean_token_accuracy": 0.9509662713855505,
+      "num_tokens": 15390859.0,
+      "step": 120
+    },
+    {
+      "epoch": 2.5347043701799485,
+      "eval_loss": 0.19054362177848816,
+      "eval_mean_token_accuracy": 0.9369476150243711,
+      "eval_num_tokens": 15906771.0,
+      "eval_runtime": 277.9929,
+      "eval_samples_per_second": 0.701,
+      "eval_steps_per_second": 0.701,
+      "step": 124
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 147,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 62,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.74639919464559e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-124/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49fff2d1203219cc878018833c87f658db4d4ce0e3b67c7202208dbe4d946cd8
+size 5752

checkpoint-147/README.md

@@ -0,0 +1,208 @@
+---
+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
+- 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-147/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "lm_head",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "embed_tokens"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-147/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06768588a1dc0d8ada082ac83bd50d1b627121dbbc04c89dfdcbf5234b73c80f
+size 2526966408

checkpoint-147/added_tokens.json

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

checkpoint-147/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-147/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49718654eb47775861d656a7e75c028abcf826f69f6d8a3030a341dda19454a3
+size 9415913858

checkpoint-147/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f5a8e5c6d873225df490f02b63a1f405cb473321d3536455236518dece1c99
+size 14244

checkpoint-147/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a2b69bb4306abd607226c01acaffda59e24b3e5c1c98b4f97c58d439a57aaa8
+size 1064

checkpoint-147/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-147/tokenizer.json

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

checkpoint-147/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-147/trainer_state.json

@@ -0,0 +1,200 @@
+{
+  "best_global_step": 124,
+  "best_metric": 0.19054362177848816,
+  "best_model_checkpoint": "./llava_qlora_weather_model/checkpoint-124",
+  "epoch": 3.0,
+  "eval_steps": 31,
+  "global_step": 147,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 2.331812620162964,
+      "learning_rate": 0.0001999744599547812,
+      "loss": 1.3843,
+      "mean_token_accuracy": 0.6790310423821211,
+      "num_tokens": 1290816.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.9054113030433655,
+      "learning_rate": 0.00019692540862655585,
+      "loss": 0.2958,
+      "mean_token_accuracy": 0.9068963050842285,
+      "num_tokens": 2581570.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.7487640380859375,
+      "learning_rate": 0.00018894622845670283,
+      "loss": 0.2476,
+      "mean_token_accuracy": 0.917157232388854,
+      "num_tokens": 3872000.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.6375321336760925,
+      "eval_loss": 0.23227548599243164,
+      "eval_mean_token_accuracy": 0.9232641770289495,
+      "eval_num_tokens": 4001060.0,
+      "eval_runtime": 276.5084,
+      "eval_samples_per_second": 0.705,
+      "eval_steps_per_second": 0.705,
+      "step": 31
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.6455361843109131,
+      "learning_rate": 0.0001764427819207624,
+      "loss": 0.2208,
+      "mean_token_accuracy": 0.9249804724007845,
+      "num_tokens": 5162524.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.5358895659446716,
+      "learning_rate": 0.00016005105914000507,
+      "loss": 0.2077,
+      "mean_token_accuracy": 0.929297363990313,
+      "num_tokens": 6405024.0,
+      "step": 50
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.5378326177597046,
+      "learning_rate": 0.00014060482812625055,
+      "loss": 0.1782,
+      "mean_token_accuracy": 0.9367100398987531,
+      "num_tokens": 7695653.0,
+      "step": 60
+    },
+    {
+      "epoch": 1.2673521850899743,
+      "eval_loss": 0.20991797745227814,
+      "eval_mean_token_accuracy": 0.9294621323927855,
+      "eval_num_tokens": 7953894.0,
+      "eval_runtime": 276.7899,
+      "eval_samples_per_second": 0.705,
+      "eval_steps_per_second": 0.705,
+      "step": 62
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 0.5556976199150085,
+      "learning_rate": 0.00011909322501769406,
+      "loss": 0.1738,
+      "mean_token_accuracy": 0.9374068416655064,
+      "num_tokens": 8986431.0,
+      "step": 70
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "grad_norm": 0.5379733443260193,
+      "learning_rate": 9.661044148624037e-05,
+      "loss": 0.17,
+      "mean_token_accuracy": 0.9386381138116121,
+      "num_tokens": 10277533.0,
+      "step": 80
+    },
+    {
+      "epoch": 1.8431876606683804,
+      "grad_norm": 0.532435417175293,
+      "learning_rate": 7.430006847567972e-05,
+      "loss": 0.1691,
+      "mean_token_accuracy": 0.9383826002478599,
+      "num_tokens": 11568708.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.904884318766067,
+      "eval_loss": 0.19236187636852264,
+      "eval_mean_token_accuracy": 0.934929045347067,
+      "eval_num_tokens": 11955105.0,
+      "eval_runtime": 277.3902,
+      "eval_samples_per_second": 0.703,
+      "eval_steps_per_second": 0.703,
+      "step": 93
+    },
+    {
+      "epoch": 2.0411311053984575,
+      "grad_norm": 0.4640503525733948,
+      "learning_rate": 5.329692723675994e-05,
+      "loss": 0.1587,
+      "mean_token_accuracy": 0.9431061984656693,
+      "num_tokens": 12809961.0,
+      "step": 100
+    },
+    {
+      "epoch": 2.2467866323907453,
+      "grad_norm": 0.4997648596763611,
+      "learning_rate": 3.466934643431795e-05,
+      "loss": 0.1347,
+      "mean_token_accuracy": 0.950631283223629,
+      "num_tokens": 14099963.0,
+      "step": 110
+    },
+    {
+      "epoch": 2.4524421593830334,
+      "grad_norm": 0.44113558530807495,
+      "learning_rate": 1.9364821412094857e-05,
+      "loss": 0.131,
+      "mean_token_accuracy": 0.9509662713855505,
+      "num_tokens": 15390859.0,
+      "step": 120
+    },
+    {
+      "epoch": 2.5347043701799485,
+      "eval_loss": 0.19054362177848816,
+      "eval_mean_token_accuracy": 0.9369476150243711,
+      "eval_num_tokens": 15906771.0,
+      "eval_runtime": 277.9929,
+      "eval_samples_per_second": 0.701,
+      "eval_steps_per_second": 0.701,
+      "step": 124
+    },
+    {
+      "epoch": 2.658097686375321,
+      "grad_norm": 0.44858983159065247,
+      "learning_rate": 8.161819666783888e-06,
+      "loss": 0.1324,
+      "mean_token_accuracy": 0.9513279229402543,
+      "num_tokens": 16681649.0,
+      "step": 130
+    },
+    {
+      "epoch": 2.8637532133676094,
+      "grad_norm": 0.4972115159034729,
+      "learning_rate": 1.6301839547892328e-06,
+      "loss": 0.1297,
+      "mean_token_accuracy": 0.9516113791614771,
+      "num_tokens": 17972810.0,
+      "step": 140
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 147,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 62,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.168897575363267e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-147/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49fff2d1203219cc878018833c87f658db4d4ce0e3b67c7202208dbe4d946cd8
+size 5752

checkpoint-62/README.md

@@ -0,0 +1,208 @@
+---
+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
+- 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-62/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "lm_head",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "embed_tokens"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-62/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065ec5086f99883c5df6e78a61ae7344b0c41795aefb9a3a862ec63dd5eb3002
+size 2526966408

checkpoint-62/added_tokens.json

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

checkpoint-62/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-62/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a39a4b6c5928154f3656e3186e45a7fa62f0eae22c77d24c3d49cfede73ccb2
+size 9415913858

checkpoint-62/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:436ebb50e412d70300dc810eb548298a1f57bbdf0b1bcbf824884d07b71aac2b
+size 14244

checkpoint-62/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e74f9b9ed0178bca9e7569779772c62079dd9a735258cb31079a11af41bdd6c
+size 1064

checkpoint-62/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-62/tokenizer.json

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

checkpoint-62/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-62/trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_global_step": 62,
+  "best_metric": 0.20991797745227814,
+  "best_model_checkpoint": "./llava_qlora_weather_model/checkpoint-62",
+  "epoch": 1.2673521850899743,
+  "eval_steps": 31,
+  "global_step": 62,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 2.331812620162964,
+      "learning_rate": 0.0001999744599547812,
+      "loss": 1.3843,
+      "mean_token_accuracy": 0.6790310423821211,
+      "num_tokens": 1290816.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.9054113030433655,
+      "learning_rate": 0.00019692540862655585,
+      "loss": 0.2958,
+      "mean_token_accuracy": 0.9068963050842285,
+      "num_tokens": 2581570.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.7487640380859375,
+      "learning_rate": 0.00018894622845670283,
+      "loss": 0.2476,
+      "mean_token_accuracy": 0.917157232388854,
+      "num_tokens": 3872000.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.6375321336760925,
+      "eval_loss": 0.23227548599243164,
+      "eval_mean_token_accuracy": 0.9232641770289495,
+      "eval_num_tokens": 4001060.0,
+      "eval_runtime": 276.5084,
+      "eval_samples_per_second": 0.705,
+      "eval_steps_per_second": 0.705,
+      "step": 31
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.6455361843109131,
+      "learning_rate": 0.0001764427819207624,
+      "loss": 0.2208,
+      "mean_token_accuracy": 0.9249804724007845,
+      "num_tokens": 5162524.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.5358895659446716,
+      "learning_rate": 0.00016005105914000507,
+      "loss": 0.2077,
+      "mean_token_accuracy": 0.929297363990313,
+      "num_tokens": 6405024.0,
+      "step": 50
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.5378326177597046,
+      "learning_rate": 0.00014060482812625055,
+      "loss": 0.1782,
+      "mean_token_accuracy": 0.9367100398987531,
+      "num_tokens": 7695653.0,
+      "step": 60
+    },
+    {
+      "epoch": 1.2673521850899743,
+      "eval_loss": 0.20991797745227814,
+      "eval_mean_token_accuracy": 0.9294621323927855,
+      "eval_num_tokens": 7953894.0,
+      "eval_runtime": 276.7899,
+      "eval_samples_per_second": 0.705,
+      "eval_steps_per_second": 0.705,
+      "step": 62
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 147,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 62,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.8734472304842e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-62/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49fff2d1203219cc878018833c87f658db4d4ce0e3b67c7202208dbe4d946cd8
+size 5752