diff --git a/README.md b/README.md
index c527c4363134076b2a26b0236754a64b9aae6f41..fcc733e583f9476223ee4db18792d5c7524623f3 100644
--- a/README.md
+++ b/README.md
@@ -1,27 +1,19 @@
 ---
 library_name: peft
 tags:
-- liuhaotian/llava-v1.5-13b_10.0
 - generated_from_trainer
 base_model: liuhaotian/llava-v1.5-13b
 model-index:
-- name: liuhaotian/llava-v1.5-13b_10.0
+- name: llava_13b_exact_location_name_synthetic
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# liuhaotian/llava-v1.5-13b_10.0
+# llava_13b_exact_location_name_synthetic
 
-This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b_10.0](https://huggingface.co./liuhaotian/llava-v1.5-13b_10.0) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 0.0010
-- eval_runtime: 55.7144
-- eval_samples_per_second: 15.562
-- eval_steps_per_second: 0.503
-- epoch: 9.0
-- step: 252
+This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b](https://huggingface.co./liuhaotian/llava-v1.5-13b) on an unknown dataset.
 
 ## Model description
 
diff --git a/adapter_config.json b/adapter_config.json
index c2ddee3559dca06cb07943e3c498fa859ddffe15..f6be111dde4c6451bcdee1632183fb960f7c70b3 100644
--- a/adapter_config.json
+++ b/adapter_config.json
@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "up_proj",
-    "o_proj",
+    "v_proj",
     "q_proj",
     "down_proj",
-    "gate_proj",
-    "v_proj"
+    "up_proj",
+    "o_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,
diff --git a/adapter_model.safetensors b/adapter_model.safetensors
index 6c033eed83f09db83ebb80814a6ef65a587d7537..733edd4220f0bc58016303f21240cd38a864fcbc 100644
--- a/adapter_model.safetensors
+++ b/adapter_model.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5985803a3f3f0a18082476be321a65f9db36b735e5aadd62159de53c1f605f22
+oid sha256:8bb3a80b637c433e0ea348fa437556e993ed780f00affdec993142f675c2af7d
 size 1001466944
diff --git a/num_examples=100/llava-v1.5-13b_1.0/README.md b/num_examples=100/llava-v1.5-13b_1.0/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9fb436e80fbd4c6055e6bd286b324e98c6a501cd
--- /dev/null
+++ b/num_examples=100/llava-v1.5-13b_1.0/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: liuhaotian/llava-v1.5-13b
+---
+
+# 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 0.10.0
\ No newline at end of file
diff --git a/num_examples=100/llava-v1.5-13b_1.0/adapter_config.json b/num_examples=100/llava-v1.5-13b_1.0/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f6be111dde4c6451bcdee1632183fb960f7c70b3
--- /dev/null
+++ b/num_examples=100/llava-v1.5-13b_1.0/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/num_examples=100/llava-v1.5-13b_1.0/adapter_model.safetensors b/num_examples=100/llava-v1.5-13b_1.0/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..733edd4220f0bc58016303f21240cd38a864fcbc
--- /dev/null
+++ b/num_examples=100/llava-v1.5-13b_1.0/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb3a80b637c433e0ea348fa437556e993ed780f00affdec993142f675c2af7d
+size 1001466944
diff --git a/num_examples=100/llava-v1.5-13b_1.0/special_tokens_map.json b/num_examples=100/llava-v1.5-13b_1.0/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e
--- /dev/null
+++ b/num_examples=100/llava-v1.5-13b_1.0/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/num_examples=100/llava-v1.5-13b_1.0/tokenizer.model b/num_examples=100/llava-v1.5-13b_1.0/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/num_examples=100/llava-v1.5-13b_1.0/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/num_examples=100/llava-v1.5-13b_1.0/tokenizer_config.json b/num_examples=100/llava-v1.5-13b_1.0/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d53c0f8edb049fa98763ee75652fafa68bf7f42
--- /dev/null
+++ b/num_examples=100/llava-v1.5-13b_1.0/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/num_examples=100/llava-v1.5-13b_1.0/training_args.bin b/num_examples=100/llava-v1.5-13b_1.0/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2c41a1ebb577810274e22b98f051ca0985aa7062
--- /dev/null
+++ b/num_examples=100/llava-v1.5-13b_1.0/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab60061c6db4983ad6a9334f47864cfc12b2212c4796c83a0d247a55439133a6
+size 6840
diff --git a/num_examples=200/llava-v1.5-13b_1.0/README.md b/num_examples=200/llava-v1.5-13b_1.0/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9fb436e80fbd4c6055e6bd286b324e98c6a501cd
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_1.0/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: liuhaotian/llava-v1.5-13b
+---
+
+# 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 0.10.0
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_1.0/adapter_config.json b/num_examples=200/llava-v1.5-13b_1.0/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c2ddee3559dca06cb07943e3c498fa859ddffe15
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_1.0/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_1.0/adapter_model.safetensors b/num_examples=200/llava-v1.5-13b_1.0/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..040ad72e4562e9ccff672dd1f1c216d0fda83eb2
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_1.0/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b2582b692b13611e3505defb6e50477ccb75c89fbdcca86cf157e1a7ff687f
+size 1001466944
diff --git a/num_examples=200/llava-v1.5-13b_1.0/special_tokens_map.json b/num_examples=200/llava-v1.5-13b_1.0/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_1.0/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/num_examples=200/llava-v1.5-13b_1.0/tokenizer.model b/num_examples=200/llava-v1.5-13b_1.0/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_1.0/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/num_examples=200/llava-v1.5-13b_1.0/tokenizer_config.json b/num_examples=200/llava-v1.5-13b_1.0/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d53c0f8edb049fa98763ee75652fafa68bf7f42
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_1.0/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/num_examples=200/llava-v1.5-13b_1.0/training_args.bin b/num_examples=200/llava-v1.5-13b_1.0/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbf48a1f013a581dea919afeab17d1b9883be6ca
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_1.0/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e7002d9da22439cd2142660ed0913d77b3af07a95d83f820f2b137e4beb14e
+size 6840
diff --git a/num_examples=200/llava-v1.5-13b_10.0/README.md b/num_examples=200/llava-v1.5-13b_10.0/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9fb436e80fbd4c6055e6bd286b324e98c6a501cd
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_10.0/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: liuhaotian/llava-v1.5-13b
+---
+
+# 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 0.10.0
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_10.0/adapter_config.json b/num_examples=200/llava-v1.5-13b_10.0/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c2ddee3559dca06cb07943e3c498fa859ddffe15
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_10.0/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_10.0/adapter_model.safetensors b/num_examples=200/llava-v1.5-13b_10.0/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6c033eed83f09db83ebb80814a6ef65a587d7537
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_10.0/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5985803a3f3f0a18082476be321a65f9db36b735e5aadd62159de53c1f605f22
+size 1001466944
diff --git a/num_examples=200/llava-v1.5-13b_10.0/special_tokens_map.json b/num_examples=200/llava-v1.5-13b_10.0/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_10.0/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/num_examples=200/llava-v1.5-13b_10.0/tokenizer.model b/num_examples=200/llava-v1.5-13b_10.0/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_10.0/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/num_examples=200/llava-v1.5-13b_10.0/tokenizer_config.json b/num_examples=200/llava-v1.5-13b_10.0/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d53c0f8edb049fa98763ee75652fafa68bf7f42
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_10.0/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/num_examples=200/llava-v1.5-13b_10.0/training_args.bin b/num_examples=200/llava-v1.5-13b_10.0/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbf48a1f013a581dea919afeab17d1b9883be6ca
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_10.0/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e7002d9da22439cd2142660ed0913d77b3af07a95d83f820f2b137e4beb14e
+size 6840
diff --git a/num_examples=200/llava-v1.5-13b_2.0/README.md b/num_examples=200/llava-v1.5-13b_2.0/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9fb436e80fbd4c6055e6bd286b324e98c6a501cd
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_2.0/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: liuhaotian/llava-v1.5-13b
+---
+
+# 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 0.10.0
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_2.0/adapter_config.json b/num_examples=200/llava-v1.5-13b_2.0/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c2ddee3559dca06cb07943e3c498fa859ddffe15
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_2.0/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_2.0/adapter_model.safetensors b/num_examples=200/llava-v1.5-13b_2.0/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..50624398e879de994ff31b0c9206ee5e7411fdce
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_2.0/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e42ca24e821a7632ce5d6b9865cf2dd3483723b06e69fa1f53a0eab6c19c90
+size 1001466944
diff --git a/num_examples=200/llava-v1.5-13b_2.0/special_tokens_map.json b/num_examples=200/llava-v1.5-13b_2.0/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_2.0/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/num_examples=200/llava-v1.5-13b_2.0/tokenizer.model b/num_examples=200/llava-v1.5-13b_2.0/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_2.0/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/num_examples=200/llava-v1.5-13b_2.0/tokenizer_config.json b/num_examples=200/llava-v1.5-13b_2.0/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d53c0f8edb049fa98763ee75652fafa68bf7f42
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_2.0/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/num_examples=200/llava-v1.5-13b_2.0/training_args.bin b/num_examples=200/llava-v1.5-13b_2.0/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbf48a1f013a581dea919afeab17d1b9883be6ca
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_2.0/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e7002d9da22439cd2142660ed0913d77b3af07a95d83f820f2b137e4beb14e
+size 6840
diff --git a/num_examples=200/llava-v1.5-13b_3.0/README.md b/num_examples=200/llava-v1.5-13b_3.0/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9fb436e80fbd4c6055e6bd286b324e98c6a501cd
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_3.0/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: liuhaotian/llava-v1.5-13b
+---
+
+# 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 0.10.0
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_3.0/adapter_config.json b/num_examples=200/llava-v1.5-13b_3.0/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c2ddee3559dca06cb07943e3c498fa859ddffe15
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_3.0/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_3.0/adapter_model.safetensors b/num_examples=200/llava-v1.5-13b_3.0/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..70478e78dea9a60afe33ffe3e3c50f896dc24142
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_3.0/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2089acf3bf40848a4aa479b41822462e83ee4405b34447707fcb7551f3c4341b
+size 1001466944
diff --git a/num_examples=200/llava-v1.5-13b_3.0/special_tokens_map.json b/num_examples=200/llava-v1.5-13b_3.0/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_3.0/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/num_examples=200/llava-v1.5-13b_3.0/tokenizer.model b/num_examples=200/llava-v1.5-13b_3.0/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_3.0/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/num_examples=200/llava-v1.5-13b_3.0/tokenizer_config.json b/num_examples=200/llava-v1.5-13b_3.0/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d53c0f8edb049fa98763ee75652fafa68bf7f42
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_3.0/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/num_examples=200/llava-v1.5-13b_3.0/training_args.bin b/num_examples=200/llava-v1.5-13b_3.0/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbf48a1f013a581dea919afeab17d1b9883be6ca
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_3.0/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e7002d9da22439cd2142660ed0913d77b3af07a95d83f820f2b137e4beb14e
+size 6840
diff --git a/num_examples=200/llava-v1.5-13b_4.0/README.md b/num_examples=200/llava-v1.5-13b_4.0/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9fb436e80fbd4c6055e6bd286b324e98c6a501cd
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_4.0/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: liuhaotian/llava-v1.5-13b
+---
+
+# 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 0.10.0
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_4.0/adapter_config.json b/num_examples=200/llava-v1.5-13b_4.0/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c2ddee3559dca06cb07943e3c498fa859ddffe15
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_4.0/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_4.0/adapter_model.safetensors b/num_examples=200/llava-v1.5-13b_4.0/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ec840c3ab270e56a92d2e98f33d8cd01a15901ff
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_4.0/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a6ee45a7adf5187849bca73285c3830d0db91f3c09bcf79954eda758ab7d994
+size 1001466944
diff --git a/num_examples=200/llava-v1.5-13b_4.0/special_tokens_map.json b/num_examples=200/llava-v1.5-13b_4.0/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_4.0/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/num_examples=200/llava-v1.5-13b_4.0/tokenizer.model b/num_examples=200/llava-v1.5-13b_4.0/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_4.0/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/num_examples=200/llava-v1.5-13b_4.0/tokenizer_config.json b/num_examples=200/llava-v1.5-13b_4.0/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d53c0f8edb049fa98763ee75652fafa68bf7f42
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_4.0/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/num_examples=200/llava-v1.5-13b_4.0/training_args.bin b/num_examples=200/llava-v1.5-13b_4.0/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbf48a1f013a581dea919afeab17d1b9883be6ca
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_4.0/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e7002d9da22439cd2142660ed0913d77b3af07a95d83f820f2b137e4beb14e
+size 6840
diff --git a/num_examples=200/llava-v1.5-13b_5.0/README.md b/num_examples=200/llava-v1.5-13b_5.0/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9fb436e80fbd4c6055e6bd286b324e98c6a501cd
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_5.0/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: liuhaotian/llava-v1.5-13b
+---
+
+# 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 0.10.0
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_5.0/adapter_config.json b/num_examples=200/llava-v1.5-13b_5.0/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c2ddee3559dca06cb07943e3c498fa859ddffe15
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_5.0/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_5.0/adapter_model.safetensors b/num_examples=200/llava-v1.5-13b_5.0/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a34d82e35d8c948d4c8942dfe9ba65808f1c5632
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_5.0/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e66cda615a3e3265faf5b882c6144ef5f42007c888903415f0fa9533d2f1106
+size 1001466944
diff --git a/num_examples=200/llava-v1.5-13b_5.0/special_tokens_map.json b/num_examples=200/llava-v1.5-13b_5.0/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_5.0/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/num_examples=200/llava-v1.5-13b_5.0/tokenizer.model b/num_examples=200/llava-v1.5-13b_5.0/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_5.0/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/num_examples=200/llava-v1.5-13b_5.0/tokenizer_config.json b/num_examples=200/llava-v1.5-13b_5.0/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d53c0f8edb049fa98763ee75652fafa68bf7f42
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_5.0/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/num_examples=200/llava-v1.5-13b_5.0/training_args.bin b/num_examples=200/llava-v1.5-13b_5.0/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbf48a1f013a581dea919afeab17d1b9883be6ca
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_5.0/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e7002d9da22439cd2142660ed0913d77b3af07a95d83f820f2b137e4beb14e
+size 6840
diff --git a/num_examples=200/llava-v1.5-13b_6.0/README.md b/num_examples=200/llava-v1.5-13b_6.0/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9fb436e80fbd4c6055e6bd286b324e98c6a501cd
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_6.0/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: liuhaotian/llava-v1.5-13b
+---
+
+# 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 0.10.0
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_6.0/adapter_config.json b/num_examples=200/llava-v1.5-13b_6.0/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c2ddee3559dca06cb07943e3c498fa859ddffe15
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_6.0/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_6.0/adapter_model.safetensors b/num_examples=200/llava-v1.5-13b_6.0/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..756fd1ecc48226c53b79e2761ec6883bd4927af2
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_6.0/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8733188a1dd909269bb6a8365325098f5508038b794865da757eb86bd9d6c0b2
+size 1001466944
diff --git a/num_examples=200/llava-v1.5-13b_6.0/special_tokens_map.json b/num_examples=200/llava-v1.5-13b_6.0/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_6.0/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/num_examples=200/llava-v1.5-13b_6.0/tokenizer.model b/num_examples=200/llava-v1.5-13b_6.0/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_6.0/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/num_examples=200/llava-v1.5-13b_6.0/tokenizer_config.json b/num_examples=200/llava-v1.5-13b_6.0/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d53c0f8edb049fa98763ee75652fafa68bf7f42
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_6.0/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/num_examples=200/llava-v1.5-13b_6.0/training_args.bin b/num_examples=200/llava-v1.5-13b_6.0/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbf48a1f013a581dea919afeab17d1b9883be6ca
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_6.0/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e7002d9da22439cd2142660ed0913d77b3af07a95d83f820f2b137e4beb14e
+size 6840
diff --git a/num_examples=200/llava-v1.5-13b_7.0/README.md b/num_examples=200/llava-v1.5-13b_7.0/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9fb436e80fbd4c6055e6bd286b324e98c6a501cd
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_7.0/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: liuhaotian/llava-v1.5-13b
+---
+
+# 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 0.10.0
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_7.0/adapter_config.json b/num_examples=200/llava-v1.5-13b_7.0/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c2ddee3559dca06cb07943e3c498fa859ddffe15
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_7.0/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_7.0/adapter_model.safetensors b/num_examples=200/llava-v1.5-13b_7.0/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d785df380578bbb3cfee1f2fbd381ac534de6760
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_7.0/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18cf7a7d3e9dd7f3110b90091a8441cd5c95671acff2abdcbc7c4d7a6dc78566
+size 1001466944
diff --git a/num_examples=200/llava-v1.5-13b_7.0/special_tokens_map.json b/num_examples=200/llava-v1.5-13b_7.0/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_7.0/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/num_examples=200/llava-v1.5-13b_7.0/tokenizer.model b/num_examples=200/llava-v1.5-13b_7.0/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_7.0/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/num_examples=200/llava-v1.5-13b_7.0/tokenizer_config.json b/num_examples=200/llava-v1.5-13b_7.0/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d53c0f8edb049fa98763ee75652fafa68bf7f42
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_7.0/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/num_examples=200/llava-v1.5-13b_7.0/training_args.bin b/num_examples=200/llava-v1.5-13b_7.0/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbf48a1f013a581dea919afeab17d1b9883be6ca
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_7.0/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e7002d9da22439cd2142660ed0913d77b3af07a95d83f820f2b137e4beb14e
+size 6840
diff --git a/num_examples=200/llava-v1.5-13b_8.0/README.md b/num_examples=200/llava-v1.5-13b_8.0/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9fb436e80fbd4c6055e6bd286b324e98c6a501cd
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_8.0/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: liuhaotian/llava-v1.5-13b
+---
+
+# 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 0.10.0
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_8.0/adapter_config.json b/num_examples=200/llava-v1.5-13b_8.0/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c2ddee3559dca06cb07943e3c498fa859ddffe15
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_8.0/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_8.0/adapter_model.safetensors b/num_examples=200/llava-v1.5-13b_8.0/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..222648feb7076f3c633e890138d4481595f69e7e
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_8.0/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9374b70a616da686a8c382b9b31a806602de707137bd3481602bf94fa92e77ed
+size 1001466944
diff --git a/num_examples=200/llava-v1.5-13b_8.0/special_tokens_map.json b/num_examples=200/llava-v1.5-13b_8.0/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_8.0/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/num_examples=200/llava-v1.5-13b_8.0/tokenizer.model b/num_examples=200/llava-v1.5-13b_8.0/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_8.0/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/num_examples=200/llava-v1.5-13b_8.0/tokenizer_config.json b/num_examples=200/llava-v1.5-13b_8.0/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d53c0f8edb049fa98763ee75652fafa68bf7f42
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_8.0/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/num_examples=200/llava-v1.5-13b_8.0/training_args.bin b/num_examples=200/llava-v1.5-13b_8.0/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbf48a1f013a581dea919afeab17d1b9883be6ca
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_8.0/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e7002d9da22439cd2142660ed0913d77b3af07a95d83f820f2b137e4beb14e
+size 6840
diff --git a/num_examples=200/llava-v1.5-13b_9.0/README.md b/num_examples=200/llava-v1.5-13b_9.0/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9fb436e80fbd4c6055e6bd286b324e98c6a501cd
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_9.0/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: liuhaotian/llava-v1.5-13b
+---
+
+# 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 0.10.0
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_9.0/adapter_config.json b/num_examples=200/llava-v1.5-13b_9.0/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c2ddee3559dca06cb07943e3c498fa859ddffe15
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_9.0/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/num_examples=200/llava-v1.5-13b_9.0/adapter_model.safetensors b/num_examples=200/llava-v1.5-13b_9.0/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7f27e855a1d89b3c472f1456c2029e2cc6784867
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_9.0/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57bbb27dd08af15c9163170bcd6267d439b33a9de4f6f84e50c70535c3a2ef46
+size 1001466944
diff --git a/num_examples=200/llava-v1.5-13b_9.0/special_tokens_map.json b/num_examples=200/llava-v1.5-13b_9.0/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_9.0/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/num_examples=200/llava-v1.5-13b_9.0/tokenizer.model b/num_examples=200/llava-v1.5-13b_9.0/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_9.0/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/num_examples=200/llava-v1.5-13b_9.0/tokenizer_config.json b/num_examples=200/llava-v1.5-13b_9.0/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d53c0f8edb049fa98763ee75652fafa68bf7f42
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_9.0/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/num_examples=200/llava-v1.5-13b_9.0/training_args.bin b/num_examples=200/llava-v1.5-13b_9.0/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbf48a1f013a581dea919afeab17d1b9883be6ca
--- /dev/null
+++ b/num_examples=200/llava-v1.5-13b_9.0/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e7002d9da22439cd2142660ed0913d77b3af07a95d83f820f2b137e4beb14e
+size 6840
diff --git a/trainer_state.json b/trainer_state.json
index bc28c2d2e37b6c0b4e8f4c3c0f2420ab846b4c42..0f305a8154b3b29c717ba4f9d3312e14c27ef08f 100644
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -17,383 +17,383 @@
     {
       "epoch": 0.07,
       "learning_rate": 6.309297535714573e-05,
-      "loss": 1.2013,
+      "loss": 1.2017,
       "step": 2
     },
     {
       "epoch": 0.11,
       "learning_rate": 0.0001,
-      "loss": 1.1723,
+      "loss": 1.1717,
       "step": 3
     },
     {
       "epoch": 0.14,
       "learning_rate": 0.00012618595071429146,
-      "loss": 1.1317,
+      "loss": 1.1308,
       "step": 4
     },
     {
       "epoch": 0.18,
       "learning_rate": 0.0001464973520717927,
-      "loss": 1.0776,
+      "loss": 1.0773,
       "step": 5
     },
     {
       "epoch": 0.21,
       "learning_rate": 0.00016309297535714573,
-      "loss": 1.0266,
+      "loss": 1.0267,
       "step": 6
     },
     {
       "epoch": 0.25,
       "learning_rate": 0.00017712437491614223,
-      "loss": 0.9953,
+      "loss": 0.9945,
       "step": 7
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0001892789260714372,
-      "loss": 0.9563,
+      "loss": 0.9553,
       "step": 8
     },
     {
       "epoch": 0.32,
       "learning_rate": 0.0002,
-      "loss": 0.9337,
+      "loss": 0.9318,
       "step": 9
     },
     {
       "epoch": 0.36,
       "learning_rate": 0.0002,
-      "loss": 0.9513,
+      "loss": 0.9507,
       "step": 10
     },
     {
       "epoch": 0.39,
       "learning_rate": 0.0002,
-      "loss": 0.8823,
+      "loss": 0.8816,
       "step": 11
     },
     {
       "epoch": 0.43,
       "learning_rate": 0.0002,
-      "loss": 0.8438,
+      "loss": 0.8428,
       "step": 12
     },
     {
       "epoch": 0.46,
       "learning_rate": 0.0002,
-      "loss": 0.8205,
+      "loss": 0.8199,
       "step": 13
     },
     {
       "epoch": 0.5,
       "learning_rate": 0.0002,
-      "loss": 0.7802,
+      "loss": 0.78,
       "step": 14
     },
     {
       "epoch": 0.54,
       "learning_rate": 0.0002,
-      "loss": 0.7714,
+      "loss": 0.7722,
       "step": 15
     },
     {
       "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 0.732,
+      "loss": 0.7317,
       "step": 16
     },
     {
       "epoch": 0.61,
       "learning_rate": 0.0002,
-      "loss": 0.6475,
+      "loss": 0.6472,
       "step": 17
     },
     {
       "epoch": 0.64,
       "learning_rate": 0.0002,
-      "loss": 0.7026,
+      "loss": 0.7027,
       "step": 18
     },
     {
       "epoch": 0.68,
       "learning_rate": 0.0002,
-      "loss": 0.611,
+      "loss": 0.6111,
       "step": 19
     },
     {
       "epoch": 0.71,
       "learning_rate": 0.0002,
-      "loss": 0.6581,
+      "loss": 0.6577,
       "step": 20
     },
     {
       "epoch": 0.75,
       "learning_rate": 0.0002,
-      "loss": 0.5189,
+      "loss": 0.5182,
       "step": 21
     },
     {
       "epoch": 0.79,
       "learning_rate": 0.0002,
-      "loss": 0.4852,
+      "loss": 0.4826,
       "step": 22
     },
     {
       "epoch": 0.82,
       "learning_rate": 0.0002,
-      "loss": 0.4482,
+      "loss": 0.4477,
       "step": 23
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 0.3752,
+      "loss": 0.3735,
       "step": 24
     },
     {
       "epoch": 0.89,
       "learning_rate": 0.0002,
-      "loss": 0.4258,
+      "loss": 0.4257,
       "step": 25
     },
     {
       "epoch": 0.93,
       "learning_rate": 0.0002,
-      "loss": 0.3545,
+      "loss": 0.3523,
       "step": 26
     },
     {
       "epoch": 0.96,
       "learning_rate": 0.0002,
-      "loss": 0.3977,
+      "loss": 0.3972,
       "step": 27
     },
     {
       "epoch": 1.0,
       "learning_rate": 0.0002,
-      "loss": 0.3239,
+      "loss": 0.3234,
       "step": 28
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.24691244959831238,
-      "eval_runtime": 54.9798,
-      "eval_samples_per_second": 15.769,
+      "eval_loss": 0.2477385699748993,
+      "eval_runtime": 54.9686,
+      "eval_samples_per_second": 15.773,
       "eval_steps_per_second": 0.509,
       "step": 28
     },
     {
       "epoch": 1.04,
       "learning_rate": 0.0002,
-      "loss": 0.2309,
+      "loss": 0.2312,
       "step": 29
     },
     {
       "epoch": 1.07,
       "learning_rate": 0.0002,
-      "loss": 0.2426,
+      "loss": 0.2441,
       "step": 30
     },
     {
       "epoch": 1.11,
       "learning_rate": 0.0002,
-      "loss": 0.2226,
+      "loss": 0.2217,
       "step": 31
     },
     {
       "epoch": 1.14,
       "learning_rate": 0.0002,
-      "loss": 0.1932,
+      "loss": 0.1936,
       "step": 32
     },
     {
       "epoch": 1.18,
       "learning_rate": 0.0002,
-      "loss": 0.212,
+      "loss": 0.2099,
       "step": 33
     },
     {
       "epoch": 1.21,
       "learning_rate": 0.0002,
-      "loss": 0.1909,
+      "loss": 0.1898,
       "step": 34
     },
     {
       "epoch": 1.25,
       "learning_rate": 0.0002,
-      "loss": 0.2315,
+      "loss": 0.2296,
       "step": 35
     },
     {
       "epoch": 1.29,
       "learning_rate": 0.0002,
-      "loss": 0.1531,
+      "loss": 0.1523,
       "step": 36
     },
     {
       "epoch": 1.32,
       "learning_rate": 0.0002,
-      "loss": 0.1523,
+      "loss": 0.151,
       "step": 37
     },
     {
       "epoch": 1.36,
       "learning_rate": 0.0002,
-      "loss": 0.0959,
+      "loss": 0.0952,
       "step": 38
     },
     {
       "epoch": 1.39,
       "learning_rate": 0.0002,
-      "loss": 0.1044,
+      "loss": 0.1017,
       "step": 39
     },
     {
       "epoch": 1.43,
       "learning_rate": 0.0002,
-      "loss": 0.1752,
+      "loss": 0.1736,
       "step": 40
     },
     {
       "epoch": 1.46,
       "learning_rate": 0.0002,
-      "loss": 0.1159,
+      "loss": 0.1143,
       "step": 41
     },
     {
       "epoch": 1.5,
       "learning_rate": 0.0002,
-      "loss": 0.1041,
+      "loss": 0.1064,
       "step": 42
     },
     {
       "epoch": 1.54,
       "learning_rate": 0.0002,
-      "loss": 0.1311,
+      "loss": 0.1315,
       "step": 43
     },
     {
       "epoch": 1.57,
       "learning_rate": 0.0002,
-      "loss": 0.1307,
+      "loss": 0.1297,
       "step": 44
     },
     {
       "epoch": 1.61,
       "learning_rate": 0.0002,
-      "loss": 0.0678,
+      "loss": 0.0686,
       "step": 45
     },
     {
       "epoch": 1.64,
       "learning_rate": 0.0002,
-      "loss": 0.0746,
+      "loss": 0.0729,
       "step": 46
     },
     {
       "epoch": 1.68,
       "learning_rate": 0.0002,
-      "loss": 0.0903,
+      "loss": 0.0909,
       "step": 47
     },
     {
       "epoch": 1.71,
       "learning_rate": 0.0002,
-      "loss": 0.1146,
+      "loss": 0.1128,
       "step": 48
     },
     {
       "epoch": 1.75,
       "learning_rate": 0.0002,
-      "loss": 0.1019,
+      "loss": 0.0989,
       "step": 49
     },
     {
       "epoch": 1.79,
       "learning_rate": 0.0002,
-      "loss": 0.056,
+      "loss": 0.0551,
       "step": 50
     },
     {
       "epoch": 1.82,
       "learning_rate": 0.0002,
-      "loss": 0.1291,
+      "loss": 0.1288,
       "step": 51
     },
     {
       "epoch": 1.86,
       "learning_rate": 0.0002,
-      "loss": 0.0487,
+      "loss": 0.0469,
       "step": 52
     },
     {
       "epoch": 1.89,
       "learning_rate": 0.0002,
-      "loss": 0.1094,
+      "loss": 0.1091,
       "step": 53
     },
     {
       "epoch": 1.93,
       "learning_rate": 0.0002,
-      "loss": 0.1581,
+      "loss": 0.1593,
       "step": 54
     },
     {
       "epoch": 1.96,
       "learning_rate": 0.0002,
-      "loss": 0.1083,
+      "loss": 0.1075,
       "step": 55
     },
     {
       "epoch": 2.0,
       "learning_rate": 0.0002,
-      "loss": 0.0396,
+      "loss": 0.0391,
       "step": 56
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.04381483793258667,
-      "eval_runtime": 55.1711,
-      "eval_samples_per_second": 15.715,
+      "eval_loss": 0.04489068686962128,
+      "eval_runtime": 55.0922,
+      "eval_samples_per_second": 15.737,
       "eval_steps_per_second": 0.508,
       "step": 56
     },
     {
       "epoch": 2.04,
       "learning_rate": 0.0002,
-      "loss": 0.0368,
+      "loss": 0.0387,
       "step": 57
     },
     {
       "epoch": 2.07,
       "learning_rate": 0.0002,
-      "loss": 0.0299,
+      "loss": 0.0306,
       "step": 58
     },
     {
       "epoch": 2.11,
       "learning_rate": 0.0002,
-      "loss": 0.0304,
+      "loss": 0.0307,
       "step": 59
     },
     {
       "epoch": 2.14,
       "learning_rate": 0.0002,
-      "loss": 0.0429,
+      "loss": 0.0451,
       "step": 60
     },
     {
       "epoch": 2.18,
       "learning_rate": 0.0002,
-      "loss": 0.0256,
+      "loss": 0.0245,
       "step": 61
     },
     {
       "epoch": 2.21,
       "learning_rate": 0.0002,
-      "loss": 0.0375,
+      "loss": 0.0351,
       "step": 62
     },
     {
@@ -405,323 +405,323 @@
     {
       "epoch": 2.29,
       "learning_rate": 0.0002,
-      "loss": 0.022,
+      "loss": 0.0244,
       "step": 64
     },
     {
       "epoch": 2.32,
       "learning_rate": 0.0002,
-      "loss": 0.0292,
+      "loss": 0.0309,
       "step": 65
     },
     {
       "epoch": 2.36,
       "learning_rate": 0.0002,
-      "loss": 0.0273,
+      "loss": 0.0272,
       "step": 66
     },
     {
       "epoch": 2.39,
       "learning_rate": 0.0002,
-      "loss": 0.0152,
+      "loss": 0.0136,
       "step": 67
     },
     {
       "epoch": 2.43,
       "learning_rate": 0.0002,
-      "loss": 0.0301,
+      "loss": 0.0297,
       "step": 68
     },
     {
       "epoch": 2.46,
       "learning_rate": 0.0002,
-      "loss": 0.0358,
+      "loss": 0.0356,
       "step": 69
     },
     {
       "epoch": 2.5,
       "learning_rate": 0.0002,
-      "loss": 0.0269,
+      "loss": 0.0284,
       "step": 70
     },
     {
       "epoch": 2.54,
       "learning_rate": 0.0002,
-      "loss": 0.0179,
+      "loss": 0.0189,
       "step": 71
     },
     {
       "epoch": 2.57,
       "learning_rate": 0.0002,
-      "loss": 0.0183,
+      "loss": 0.0199,
       "step": 72
     },
     {
       "epoch": 2.61,
       "learning_rate": 0.0002,
-      "loss": 0.0132,
+      "loss": 0.0121,
       "step": 73
     },
     {
       "epoch": 2.64,
       "learning_rate": 0.0002,
-      "loss": 0.0329,
+      "loss": 0.0389,
       "step": 74
     },
     {
       "epoch": 2.68,
       "learning_rate": 0.0002,
-      "loss": 0.0267,
+      "loss": 0.0298,
       "step": 75
     },
     {
       "epoch": 2.71,
       "learning_rate": 0.0002,
-      "loss": 0.0193,
+      "loss": 0.0176,
       "step": 76
     },
     {
       "epoch": 2.75,
       "learning_rate": 0.0002,
-      "loss": 0.0101,
+      "loss": 0.0165,
       "step": 77
     },
     {
       "epoch": 2.79,
       "learning_rate": 0.0002,
-      "loss": 0.023,
+      "loss": 0.0255,
       "step": 78
     },
     {
       "epoch": 2.82,
       "learning_rate": 0.0002,
-      "loss": 0.0317,
+      "loss": 0.0282,
       "step": 79
     },
     {
       "epoch": 2.86,
       "learning_rate": 0.0002,
-      "loss": 0.0225,
+      "loss": 0.0247,
       "step": 80
     },
     {
       "epoch": 2.89,
       "learning_rate": 0.0002,
-      "loss": 0.0198,
+      "loss": 0.021,
       "step": 81
     },
     {
       "epoch": 2.93,
       "learning_rate": 0.0002,
-      "loss": 0.0232,
+      "loss": 0.024,
       "step": 82
     },
     {
       "epoch": 2.96,
       "learning_rate": 0.0002,
-      "loss": 0.0287,
+      "loss": 0.0321,
       "step": 83
     },
     {
       "epoch": 3.0,
       "learning_rate": 0.0002,
-      "loss": 0.0086,
+      "loss": 0.0123,
       "step": 84
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.01250830665230751,
-      "eval_runtime": 54.9958,
-      "eval_samples_per_second": 15.765,
-      "eval_steps_per_second": 0.509,
+      "eval_loss": 0.012368076480925083,
+      "eval_runtime": 55.1635,
+      "eval_samples_per_second": 15.717,
+      "eval_steps_per_second": 0.508,
       "step": 84
     },
     {
       "epoch": 3.04,
       "learning_rate": 0.0002,
-      "loss": 0.0059,
+      "loss": 0.0057,
       "step": 85
     },
     {
       "epoch": 3.07,
       "learning_rate": 0.0002,
-      "loss": 0.0121,
+      "loss": 0.0139,
       "step": 86
     },
     {
       "epoch": 3.11,
       "learning_rate": 0.0002,
-      "loss": 0.0091,
+      "loss": 0.0095,
       "step": 87
     },
     {
       "epoch": 3.14,
       "learning_rate": 0.0002,
-      "loss": 0.0078,
+      "loss": 0.009,
       "step": 88
     },
     {
       "epoch": 3.18,
       "learning_rate": 0.0002,
-      "loss": 0.0124,
+      "loss": 0.0123,
       "step": 89
     },
     {
       "epoch": 3.21,
       "learning_rate": 0.0002,
-      "loss": 0.0107,
+      "loss": 0.0109,
       "step": 90
     },
     {
       "epoch": 3.25,
       "learning_rate": 0.0002,
-      "loss": 0.0106,
+      "loss": 0.0098,
       "step": 91
     },
     {
       "epoch": 3.29,
       "learning_rate": 0.0002,
-      "loss": 0.0107,
+      "loss": 0.0063,
       "step": 92
     },
     {
       "epoch": 3.32,
       "learning_rate": 0.0002,
-      "loss": 0.0119,
+      "loss": 0.0105,
       "step": 93
     },
     {
       "epoch": 3.36,
       "learning_rate": 0.0002,
-      "loss": 0.0054,
+      "loss": 0.0062,
       "step": 94
     },
     {
       "epoch": 3.39,
       "learning_rate": 0.0002,
-      "loss": 0.0078,
+      "loss": 0.0139,
       "step": 95
     },
     {
       "epoch": 3.43,
       "learning_rate": 0.0002,
-      "loss": 0.0132,
+      "loss": 0.0141,
       "step": 96
     },
     {
       "epoch": 3.46,
       "learning_rate": 0.0002,
-      "loss": 0.0123,
+      "loss": 0.011,
       "step": 97
     },
     {
       "epoch": 3.5,
       "learning_rate": 0.0002,
-      "loss": 0.0144,
+      "loss": 0.0106,
       "step": 98
     },
     {
       "epoch": 3.54,
       "learning_rate": 0.0002,
-      "loss": 0.0099,
+      "loss": 0.0131,
       "step": 99
     },
     {
       "epoch": 3.57,
       "learning_rate": 0.0002,
-      "loss": 0.0075,
+      "loss": 0.009,
       "step": 100
     },
     {
       "epoch": 3.61,
       "learning_rate": 0.0002,
-      "loss": 0.0131,
+      "loss": 0.0204,
       "step": 101
     },
     {
       "epoch": 3.64,
       "learning_rate": 0.0002,
-      "loss": 0.0076,
+      "loss": 0.0117,
       "step": 102
     },
     {
       "epoch": 3.68,
       "learning_rate": 0.0002,
-      "loss": 0.0129,
+      "loss": 0.0156,
       "step": 103
     },
     {
       "epoch": 3.71,
       "learning_rate": 0.0002,
-      "loss": 0.0122,
+      "loss": 0.0137,
       "step": 104
     },
     {
       "epoch": 3.75,
       "learning_rate": 0.0002,
-      "loss": 0.0113,
+      "loss": 0.0157,
       "step": 105
     },
     {
       "epoch": 3.79,
       "learning_rate": 0.0002,
-      "loss": 0.0101,
+      "loss": 0.0143,
       "step": 106
     },
     {
       "epoch": 3.82,
       "learning_rate": 0.0002,
-      "loss": 0.006,
+      "loss": 0.007,
       "step": 107
     },
     {
       "epoch": 3.86,
       "learning_rate": 0.0002,
-      "loss": 0.0078,
+      "loss": 0.0092,
       "step": 108
     },
     {
       "epoch": 3.89,
       "learning_rate": 0.0002,
-      "loss": 0.0052,
+      "loss": 0.0091,
       "step": 109
     },
     {
       "epoch": 3.93,
       "learning_rate": 0.0002,
-      "loss": 0.0155,
+      "loss": 0.0249,
       "step": 110
     },
     {
       "epoch": 3.96,
       "learning_rate": 0.0002,
-      "loss": 0.0043,
+      "loss": 0.0055,
       "step": 111
     },
     {
       "epoch": 4.0,
       "learning_rate": 0.0002,
-      "loss": 0.005,
+      "loss": 0.0055,
       "step": 112
     },
     {
       "epoch": 4.0,
-      "eval_loss": 0.005612094886600971,
-      "eval_runtime": 55.1695,
-      "eval_samples_per_second": 15.715,
-      "eval_steps_per_second": 0.508,
+      "eval_loss": 0.006369821261614561,
+      "eval_runtime": 55.1727,
+      "eval_samples_per_second": 15.714,
+      "eval_steps_per_second": 0.507,
       "step": 112
     },
     {
       "epoch": 4.04,
       "learning_rate": 0.0002,
-      "loss": 0.0061,
+      "loss": 0.0069,
       "step": 113
     },
     {
       "epoch": 4.07,
       "learning_rate": 0.0002,
-      "loss": 0.0056,
+      "loss": 0.0044,
       "step": 114
     },
     {
@@ -733,31 +733,31 @@
     {
       "epoch": 4.14,
       "learning_rate": 0.0002,
-      "loss": 0.0048,
+      "loss": 0.004,
       "step": 116
     },
     {
       "epoch": 4.18,
       "learning_rate": 0.0002,
-      "loss": 0.005,
+      "loss": 0.0049,
       "step": 117
     },
     {
       "epoch": 4.21,
       "learning_rate": 0.0002,
-      "loss": 0.0062,
+      "loss": 0.0048,
       "step": 118
     },
     {
       "epoch": 4.25,
       "learning_rate": 0.0002,
-      "loss": 0.0131,
+      "loss": 0.0122,
       "step": 119
     },
     {
       "epoch": 4.29,
       "learning_rate": 0.0002,
-      "loss": 0.0064,
+      "loss": 0.0052,
       "step": 120
     },
     {
@@ -769,474 +769,474 @@
     {
       "epoch": 4.36,
       "learning_rate": 0.0002,
-      "loss": 0.0044,
+      "loss": 0.006,
       "step": 122
     },
     {
       "epoch": 4.39,
       "learning_rate": 0.0002,
-      "loss": 0.0069,
+      "loss": 0.0059,
       "step": 123
     },
     {
       "epoch": 4.43,
       "learning_rate": 0.0002,
-      "loss": 0.0031,
+      "loss": 0.0027,
       "step": 124
     },
     {
       "epoch": 4.46,
       "learning_rate": 0.0002,
-      "loss": 0.0043,
+      "loss": 0.0025,
       "step": 125
     },
     {
       "epoch": 4.5,
       "learning_rate": 0.0002,
-      "loss": 0.0032,
+      "loss": 0.004,
       "step": 126
     },
     {
       "epoch": 4.54,
       "learning_rate": 0.0002,
-      "loss": 0.0028,
+      "loss": 0.0033,
       "step": 127
     },
     {
       "epoch": 4.57,
       "learning_rate": 0.0002,
-      "loss": 0.0053,
+      "loss": 0.0024,
       "step": 128
     },
     {
       "epoch": 4.61,
       "learning_rate": 0.0002,
-      "loss": 0.0052,
+      "loss": 0.0034,
       "step": 129
     },
     {
       "epoch": 4.64,
       "learning_rate": 0.0002,
-      "loss": 0.0106,
+      "loss": 0.0051,
       "step": 130
     },
     {
       "epoch": 4.68,
       "learning_rate": 0.0002,
-      "loss": 0.0071,
+      "loss": 0.0025,
       "step": 131
     },
     {
       "epoch": 4.71,
       "learning_rate": 0.0002,
-      "loss": 0.0044,
+      "loss": 0.0039,
       "step": 132
     },
     {
       "epoch": 4.75,
       "learning_rate": 0.0002,
-      "loss": 0.0075,
+      "loss": 0.005,
       "step": 133
     },
     {
       "epoch": 4.79,
       "learning_rate": 0.0002,
-      "loss": 0.0026,
+      "loss": 0.0013,
       "step": 134
     },
     {
       "epoch": 4.82,
       "learning_rate": 0.0002,
-      "loss": 0.0071,
+      "loss": 0.0041,
       "step": 135
     },
     {
       "epoch": 4.86,
       "learning_rate": 0.0002,
-      "loss": 0.005,
+      "loss": 0.0045,
       "step": 136
     },
     {
       "epoch": 4.89,
       "learning_rate": 0.0002,
-      "loss": 0.0042,
+      "loss": 0.0037,
       "step": 137
     },
     {
       "epoch": 4.93,
       "learning_rate": 0.0002,
-      "loss": 0.0059,
+      "loss": 0.0045,
       "step": 138
     },
     {
       "epoch": 4.96,
       "learning_rate": 0.0002,
-      "loss": 0.004,
+      "loss": 0.0029,
       "step": 139
     },
     {
       "epoch": 5.0,
       "learning_rate": 0.0002,
-      "loss": 0.0051,
+      "loss": 0.0023,
       "step": 140
     },
     {
       "epoch": 5.0,
-      "eval_loss": 0.004839635919779539,
-      "eval_runtime": 55.1037,
-      "eval_samples_per_second": 15.734,
-      "eval_steps_per_second": 0.508,
+      "eval_loss": 0.0037152974400669336,
+      "eval_runtime": 55.1887,
+      "eval_samples_per_second": 15.71,
+      "eval_steps_per_second": 0.507,
       "step": 140
     },
     {
       "epoch": 5.04,
       "learning_rate": 0.0002,
-      "loss": 0.0045,
+      "loss": 0.001,
       "step": 141
     },
     {
       "epoch": 5.07,
       "learning_rate": 0.0002,
-      "loss": 0.0066,
+      "loss": 0.0036,
       "step": 142
     },
     {
       "epoch": 5.11,
       "learning_rate": 0.0002,
-      "loss": 0.0023,
+      "loss": 0.0031,
       "step": 143
     },
     {
       "epoch": 5.14,
       "learning_rate": 0.0002,
-      "loss": 0.0047,
+      "loss": 0.0085,
       "step": 144
     },
     {
       "epoch": 5.18,
       "learning_rate": 0.0002,
-      "loss": 0.0081,
+      "loss": 0.0053,
       "step": 145
     },
     {
       "epoch": 5.21,
       "learning_rate": 0.0002,
-      "loss": 0.0074,
+      "loss": 0.004,
       "step": 146
     },
     {
       "epoch": 5.25,
       "learning_rate": 0.0002,
-      "loss": 0.002,
+      "loss": 0.0057,
       "step": 147
     },
     {
       "epoch": 5.29,
       "learning_rate": 0.0002,
-      "loss": 0.0049,
+      "loss": 0.0057,
       "step": 148
     },
     {
       "epoch": 5.32,
       "learning_rate": 0.0002,
-      "loss": 0.0093,
+      "loss": 0.0046,
       "step": 149
     },
     {
       "epoch": 5.36,
       "learning_rate": 0.0002,
-      "loss": 0.0028,
+      "loss": 0.003,
       "step": 150
     },
     {
       "epoch": 5.39,
       "learning_rate": 0.0002,
-      "loss": 0.005,
+      "loss": 0.0019,
       "step": 151
     },
     {
       "epoch": 5.43,
       "learning_rate": 0.0002,
-      "loss": 0.0027,
+      "loss": 0.0043,
       "step": 152
     },
     {
       "epoch": 5.46,
       "learning_rate": 0.0002,
-      "loss": 0.0024,
+      "loss": 0.0019,
       "step": 153
     },
     {
       "epoch": 5.5,
       "learning_rate": 0.0002,
-      "loss": 0.0051,
+      "loss": 0.0094,
       "step": 154
     },
     {
       "epoch": 5.54,
       "learning_rate": 0.0002,
-      "loss": 0.0057,
+      "loss": 0.0033,
       "step": 155
     },
     {
       "epoch": 5.57,
       "learning_rate": 0.0002,
-      "loss": 0.0042,
+      "loss": 0.0028,
       "step": 156
     },
     {
       "epoch": 5.61,
       "learning_rate": 0.0002,
-      "loss": 0.0076,
+      "loss": 0.0013,
       "step": 157
     },
     {
       "epoch": 5.64,
       "learning_rate": 0.0002,
-      "loss": 0.0026,
+      "loss": 0.0073,
       "step": 158
     },
     {
       "epoch": 5.68,
       "learning_rate": 0.0002,
-      "loss": 0.0062,
+      "loss": 0.0054,
       "step": 159
     },
     {
       "epoch": 5.71,
       "learning_rate": 0.0002,
-      "loss": 0.0039,
+      "loss": 0.0066,
       "step": 160
     },
     {
       "epoch": 5.75,
       "learning_rate": 0.0002,
-      "loss": 0.0028,
+      "loss": 0.0019,
       "step": 161
     },
     {
       "epoch": 5.79,
       "learning_rate": 0.0002,
-      "loss": 0.0068,
+      "loss": 0.0014,
       "step": 162
     },
     {
       "epoch": 5.82,
       "learning_rate": 0.0002,
-      "loss": 0.001,
+      "loss": 0.0026,
       "step": 163
     },
     {
       "epoch": 5.86,
       "learning_rate": 0.0002,
-      "loss": 0.0036,
+      "loss": 0.0016,
       "step": 164
     },
     {
       "epoch": 5.89,
       "learning_rate": 0.0002,
-      "loss": 0.004,
+      "loss": 0.0022,
       "step": 165
     },
     {
       "epoch": 5.93,
       "learning_rate": 0.0002,
-      "loss": 0.0028,
+      "loss": 0.0077,
       "step": 166
     },
     {
       "epoch": 5.96,
       "learning_rate": 0.0002,
-      "loss": 0.0046,
+      "loss": 0.0054,
       "step": 167
     },
     {
       "epoch": 6.0,
       "learning_rate": 0.0002,
-      "loss": 0.0036,
+      "loss": 0.0049,
       "step": 168
     },
     {
       "epoch": 6.0,
-      "eval_loss": 0.0032981247641146183,
-      "eval_runtime": 55.1126,
-      "eval_samples_per_second": 15.731,
-      "eval_steps_per_second": 0.508,
+      "eval_loss": 0.003725806251168251,
+      "eval_runtime": 55.2317,
+      "eval_samples_per_second": 15.698,
+      "eval_steps_per_second": 0.507,
       "step": 168
     },
     {
       "epoch": 6.04,
       "learning_rate": 0.0002,
-      "loss": 0.0021,
+      "loss": 0.0037,
       "step": 169
     },
     {
       "epoch": 6.07,
       "learning_rate": 0.0002,
-      "loss": 0.0053,
+      "loss": 0.0022,
       "step": 170
     },
     {
       "epoch": 6.11,
       "learning_rate": 0.0002,
-      "loss": 0.0034,
+      "loss": 0.0021,
       "step": 171
     },
     {
       "epoch": 6.14,
       "learning_rate": 0.0002,
-      "loss": 0.0051,
+      "loss": 0.0045,
       "step": 172
     },
     {
       "epoch": 6.18,
       "learning_rate": 0.0002,
-      "loss": 0.004,
+      "loss": 0.0026,
       "step": 173
     },
     {
       "epoch": 6.21,
       "learning_rate": 0.0002,
-      "loss": 0.0032,
+      "loss": 0.0026,
       "step": 174
     },
     {
       "epoch": 6.25,
       "learning_rate": 0.0002,
-      "loss": 0.0039,
+      "loss": 0.005,
       "step": 175
     },
     {
       "epoch": 6.29,
       "learning_rate": 0.0002,
-      "loss": 0.0045,
+      "loss": 0.0048,
       "step": 176
     },
     {
       "epoch": 6.32,
       "learning_rate": 0.0002,
-      "loss": 0.0105,
+      "loss": 0.0066,
       "step": 177
     },
     {
       "epoch": 6.36,
       "learning_rate": 0.0002,
-      "loss": 0.0017,
+      "loss": 0.0028,
       "step": 178
     },
     {
       "epoch": 6.39,
       "learning_rate": 0.0002,
-      "loss": 0.0073,
+      "loss": 0.006,
       "step": 179
     },
     {
       "epoch": 6.43,
       "learning_rate": 0.0002,
-      "loss": 0.0088,
+      "loss": 0.0008,
       "step": 180
     },
     {
       "epoch": 6.46,
       "learning_rate": 0.0002,
-      "loss": 0.0029,
+      "loss": 0.0037,
       "step": 181
     },
     {
       "epoch": 6.5,
       "learning_rate": 0.0002,
-      "loss": 0.0087,
+      "loss": 0.0051,
       "step": 182
     },
     {
       "epoch": 6.54,
       "learning_rate": 0.0002,
-      "loss": 0.0045,
+      "loss": 0.0028,
       "step": 183
     },
     {
       "epoch": 6.57,
       "learning_rate": 0.0002,
-      "loss": 0.0096,
+      "loss": 0.0064,
       "step": 184
     },
     {
       "epoch": 6.61,
       "learning_rate": 0.0002,
-      "loss": 0.0036,
+      "loss": 0.0025,
       "step": 185
     },
     {
       "epoch": 6.64,
       "learning_rate": 0.0002,
-      "loss": 0.0061,
+      "loss": 0.0025,
       "step": 186
     },
     {
       "epoch": 6.68,
       "learning_rate": 0.0002,
-      "loss": 0.0052,
+      "loss": 0.0043,
       "step": 187
     },
     {
       "epoch": 6.71,
       "learning_rate": 0.0002,
-      "loss": 0.0033,
+      "loss": 0.0017,
       "step": 188
     },
     {
       "epoch": 6.75,
       "learning_rate": 0.0002,
-      "loss": 0.0072,
+      "loss": 0.002,
       "step": 189
     },
     {
       "epoch": 6.79,
       "learning_rate": 0.0002,
-      "loss": 0.0016,
+      "loss": 0.0009,
       "step": 190
     },
     {
       "epoch": 6.82,
       "learning_rate": 0.0002,
-      "loss": 0.0024,
+      "loss": 0.0018,
       "step": 191
     },
     {
       "epoch": 6.86,
       "learning_rate": 0.0002,
-      "loss": 0.0044,
+      "loss": 0.0037,
       "step": 192
     },
     {
       "epoch": 6.89,
       "learning_rate": 0.0002,
-      "loss": 0.0011,
+      "loss": 0.0013,
       "step": 193
     },
     {
       "epoch": 6.93,
       "learning_rate": 0.0002,
-      "loss": 0.0054,
+      "loss": 0.002,
       "step": 194
     },
     {
       "epoch": 6.96,
       "learning_rate": 0.0002,
-      "loss": 0.0023,
+      "loss": 0.002,
       "step": 195
     },
     {
       "epoch": 7.0,
       "learning_rate": 0.0002,
-      "loss": 0.006,
+      "loss": 0.0009,
       "step": 196
     },
     {
       "epoch": 7.0,
-      "eval_loss": 0.0035514547489583492,
-      "eval_runtime": 55.2585,
-      "eval_samples_per_second": 15.69,
+      "eval_loss": 0.0015701488591730595,
+      "eval_runtime": 55.1955,
+      "eval_samples_per_second": 15.708,
       "eval_steps_per_second": 0.507,
       "step": 196
     },
@@ -1249,522 +1249,522 @@
     {
       "epoch": 7.07,
       "learning_rate": 0.0002,
-      "loss": 0.0049,
+      "loss": 0.0018,
       "step": 198
     },
     {
       "epoch": 7.11,
       "learning_rate": 0.0002,
-      "loss": 0.002,
+      "loss": 0.0015,
       "step": 199
     },
     {
       "epoch": 7.14,
       "learning_rate": 0.0002,
-      "loss": 0.0067,
+      "loss": 0.0016,
       "step": 200
     },
     {
       "epoch": 7.18,
       "learning_rate": 0.0002,
-      "loss": 0.002,
+      "loss": 0.0014,
       "step": 201
     },
     {
       "epoch": 7.21,
       "learning_rate": 0.0002,
-      "loss": 0.0024,
+      "loss": 0.0032,
       "step": 202
     },
     {
       "epoch": 7.25,
       "learning_rate": 0.0002,
-      "loss": 0.0032,
+      "loss": 0.0006,
       "step": 203
     },
     {
       "epoch": 7.29,
       "learning_rate": 0.0002,
-      "loss": 0.0088,
+      "loss": 0.0018,
       "step": 204
     },
     {
       "epoch": 7.32,
       "learning_rate": 0.0002,
-      "loss": 0.0013,
+      "loss": 0.0005,
       "step": 205
     },
     {
       "epoch": 7.36,
       "learning_rate": 0.0002,
-      "loss": 0.0034,
+      "loss": 0.0024,
       "step": 206
     },
     {
       "epoch": 7.39,
       "learning_rate": 0.0002,
-      "loss": 0.0022,
+      "loss": 0.0027,
       "step": 207
     },
     {
       "epoch": 7.43,
       "learning_rate": 0.0002,
-      "loss": 0.0016,
+      "loss": 0.0005,
       "step": 208
     },
     {
       "epoch": 7.46,
       "learning_rate": 0.0002,
-      "loss": 0.0024,
+      "loss": 0.0056,
       "step": 209
     },
     {
       "epoch": 7.5,
       "learning_rate": 0.0002,
-      "loss": 0.0023,
+      "loss": 0.0015,
       "step": 210
     },
     {
       "epoch": 7.54,
       "learning_rate": 0.0002,
-      "loss": 0.0022,
+      "loss": 0.0019,
       "step": 211
     },
     {
       "epoch": 7.57,
       "learning_rate": 0.0002,
-      "loss": 0.0022,
+      "loss": 0.0014,
       "step": 212
     },
     {
       "epoch": 7.61,
       "learning_rate": 0.0002,
-      "loss": 0.0084,
+      "loss": 0.0009,
       "step": 213
     },
     {
       "epoch": 7.64,
       "learning_rate": 0.0002,
-      "loss": 0.0039,
+      "loss": 0.0017,
       "step": 214
     },
     {
       "epoch": 7.68,
       "learning_rate": 0.0002,
-      "loss": 0.0035,
+      "loss": 0.0037,
       "step": 215
     },
     {
       "epoch": 7.71,
       "learning_rate": 0.0002,
-      "loss": 0.0021,
+      "loss": 0.0009,
       "step": 216
     },
     {
       "epoch": 7.75,
       "learning_rate": 0.0002,
-      "loss": 0.004,
+      "loss": 0.0021,
       "step": 217
     },
     {
       "epoch": 7.79,
       "learning_rate": 0.0002,
-      "loss": 0.0027,
+      "loss": 0.0024,
       "step": 218
     },
     {
       "epoch": 7.82,
       "learning_rate": 0.0002,
-      "loss": 0.0019,
+      "loss": 0.002,
       "step": 219
     },
     {
       "epoch": 7.86,
       "learning_rate": 0.0002,
-      "loss": 0.0013,
+      "loss": 0.0011,
       "step": 220
     },
     {
       "epoch": 7.89,
       "learning_rate": 0.0002,
-      "loss": 0.0043,
+      "loss": 0.002,
       "step": 221
     },
     {
       "epoch": 7.93,
       "learning_rate": 0.0002,
-      "loss": 0.0012,
+      "loss": 0.0042,
       "step": 222
     },
     {
       "epoch": 7.96,
       "learning_rate": 0.0002,
-      "loss": 0.0008,
+      "loss": 0.0046,
       "step": 223
     },
     {
       "epoch": 8.0,
       "learning_rate": 0.0002,
-      "loss": 0.0017,
+      "loss": 0.0009,
       "step": 224
     },
     {
       "epoch": 8.0,
-      "eval_loss": 0.0020963489077985287,
-      "eval_runtime": 55.1683,
-      "eval_samples_per_second": 15.716,
-      "eval_steps_per_second": 0.508,
+      "eval_loss": 0.00099816860165447,
+      "eval_runtime": 55.2372,
+      "eval_samples_per_second": 15.696,
+      "eval_steps_per_second": 0.507,
       "step": 224
     },
     {
       "epoch": 8.04,
       "learning_rate": 0.0002,
-      "loss": 0.002,
+      "loss": 0.0005,
       "step": 225
     },
     {
       "epoch": 8.07,
       "learning_rate": 0.0002,
-      "loss": 0.0008,
+      "loss": 0.0007,
       "step": 226
     },
     {
       "epoch": 8.11,
       "learning_rate": 0.0002,
-      "loss": 0.0017,
+      "loss": 0.003,
       "step": 227
     },
     {
       "epoch": 8.14,
       "learning_rate": 0.0002,
-      "loss": 0.0013,
+      "loss": 0.0024,
       "step": 228
     },
     {
       "epoch": 8.18,
       "learning_rate": 0.0002,
-      "loss": 0.0007,
+      "loss": 0.0023,
       "step": 229
     },
     {
       "epoch": 8.21,
       "learning_rate": 0.0002,
-      "loss": 0.0005,
+      "loss": 0.0024,
       "step": 230
     },
     {
       "epoch": 8.25,
       "learning_rate": 0.0002,
-      "loss": 0.0021,
+      "loss": 0.0018,
       "step": 231
     },
     {
       "epoch": 8.29,
       "learning_rate": 0.0002,
-      "loss": 0.0037,
+      "loss": 0.0031,
       "step": 232
     },
     {
       "epoch": 8.32,
       "learning_rate": 0.0002,
-      "loss": 0.0034,
+      "loss": 0.001,
       "step": 233
     },
     {
       "epoch": 8.36,
       "learning_rate": 0.0002,
-      "loss": 0.0038,
+      "loss": 0.0011,
       "step": 234
     },
     {
       "epoch": 8.39,
       "learning_rate": 0.0002,
-      "loss": 0.0018,
+      "loss": 0.0022,
       "step": 235
     },
     {
       "epoch": 8.43,
       "learning_rate": 0.0002,
-      "loss": 0.0006,
+      "loss": 0.0008,
       "step": 236
     },
     {
       "epoch": 8.46,
       "learning_rate": 0.0002,
-      "loss": 0.0118,
+      "loss": 0.0006,
       "step": 237
     },
     {
       "epoch": 8.5,
       "learning_rate": 0.0002,
-      "loss": 0.0046,
+      "loss": 0.0016,
       "step": 238
     },
     {
       "epoch": 8.54,
       "learning_rate": 0.0002,
-      "loss": 0.0043,
+      "loss": 0.0016,
       "step": 239
     },
     {
       "epoch": 8.57,
       "learning_rate": 0.0002,
-      "loss": 0.0023,
+      "loss": 0.0012,
       "step": 240
     },
     {
       "epoch": 8.61,
       "learning_rate": 0.0002,
-      "loss": 0.0038,
+      "loss": 0.0011,
       "step": 241
     },
     {
       "epoch": 8.64,
       "learning_rate": 0.0002,
-      "loss": 0.0056,
+      "loss": 0.0024,
       "step": 242
     },
     {
       "epoch": 8.68,
       "learning_rate": 0.0002,
-      "loss": 0.0083,
+      "loss": 0.0013,
       "step": 243
     },
     {
       "epoch": 8.71,
       "learning_rate": 0.0002,
-      "loss": 0.0039,
+      "loss": 0.0006,
       "step": 244
     },
     {
       "epoch": 8.75,
       "learning_rate": 0.0002,
-      "loss": 0.003,
+      "loss": 0.0005,
       "step": 245
     },
     {
       "epoch": 8.79,
       "learning_rate": 0.0002,
-      "loss": 0.0021,
+      "loss": 0.0025,
       "step": 246
     },
     {
       "epoch": 8.82,
       "learning_rate": 0.0002,
-      "loss": 0.002,
+      "loss": 0.0026,
       "step": 247
     },
     {
       "epoch": 8.86,
       "learning_rate": 0.0002,
-      "loss": 0.0037,
+      "loss": 0.0015,
       "step": 248
     },
     {
       "epoch": 8.89,
       "learning_rate": 0.0002,
-      "loss": 0.0014,
+      "loss": 0.0012,
       "step": 249
     },
     {
       "epoch": 8.93,
       "learning_rate": 0.0002,
-      "loss": 0.0037,
+      "loss": 0.0012,
       "step": 250
     },
     {
       "epoch": 8.96,
       "learning_rate": 0.0002,
-      "loss": 0.0031,
+      "loss": 0.0011,
       "step": 251
     },
     {
       "epoch": 9.0,
       "learning_rate": 0.0002,
-      "loss": 0.0041,
+      "loss": 0.0007,
       "step": 252
     },
     {
       "epoch": 9.0,
-      "eval_loss": 0.0022224283311516047,
-      "eval_runtime": 55.1607,
-      "eval_samples_per_second": 15.718,
-      "eval_steps_per_second": 0.508,
+      "eval_loss": 0.0009729066514410079,
+      "eval_runtime": 55.7144,
+      "eval_samples_per_second": 15.562,
+      "eval_steps_per_second": 0.503,
       "step": 252
     },
     {
       "epoch": 9.04,
       "learning_rate": 0.0002,
-      "loss": 0.0009,
+      "loss": 0.0019,
       "step": 253
     },
     {
       "epoch": 9.07,
       "learning_rate": 0.0002,
-      "loss": 0.0011,
+      "loss": 0.001,
       "step": 254
     },
     {
       "epoch": 9.11,
       "learning_rate": 0.0002,
-      "loss": 0.0038,
+      "loss": 0.0004,
       "step": 255
     },
     {
       "epoch": 9.14,
       "learning_rate": 0.0002,
-      "loss": 0.0026,
+      "loss": 0.0004,
       "step": 256
     },
     {
       "epoch": 9.18,
       "learning_rate": 0.0002,
-      "loss": 0.004,
+      "loss": 0.0022,
       "step": 257
     },
     {
       "epoch": 9.21,
       "learning_rate": 0.0002,
-      "loss": 0.0047,
+      "loss": 0.001,
       "step": 258
     },
     {
       "epoch": 9.25,
       "learning_rate": 0.0002,
-      "loss": 0.0023,
+      "loss": 0.0013,
       "step": 259
     },
     {
       "epoch": 9.29,
       "learning_rate": 0.0002,
-      "loss": 0.003,
+      "loss": 0.0012,
       "step": 260
     },
     {
       "epoch": 9.32,
       "learning_rate": 0.0002,
-      "loss": 0.0007,
+      "loss": 0.0028,
       "step": 261
     },
     {
       "epoch": 9.36,
       "learning_rate": 0.0002,
-      "loss": 0.0073,
+      "loss": 0.0004,
       "step": 262
     },
     {
       "epoch": 9.39,
       "learning_rate": 0.0002,
-      "loss": 0.0023,
+      "loss": 0.0006,
       "step": 263
     },
     {
       "epoch": 9.43,
       "learning_rate": 0.0002,
-      "loss": 0.0081,
+      "loss": 0.0053,
       "step": 264
     },
     {
       "epoch": 9.46,
       "learning_rate": 0.0002,
-      "loss": 0.0043,
+      "loss": 0.001,
       "step": 265
     },
     {
       "epoch": 9.5,
       "learning_rate": 0.0002,
-      "loss": 0.0039,
+      "loss": 0.0029,
       "step": 266
     },
     {
       "epoch": 9.54,
       "learning_rate": 0.0002,
-      "loss": 0.0052,
+      "loss": 0.0008,
       "step": 267
     },
     {
       "epoch": 9.57,
       "learning_rate": 0.0002,
-      "loss": 0.0049,
+      "loss": 0.0044,
       "step": 268
     },
     {
       "epoch": 9.61,
       "learning_rate": 0.0002,
-      "loss": 0.0076,
+      "loss": 0.0012,
       "step": 269
     },
     {
       "epoch": 9.64,
       "learning_rate": 0.0002,
-      "loss": 0.0062,
+      "loss": 0.0017,
       "step": 270
     },
     {
       "epoch": 9.68,
       "learning_rate": 0.0002,
-      "loss": 0.005,
+      "loss": 0.0033,
       "step": 271
     },
     {
       "epoch": 9.71,
       "learning_rate": 0.0002,
-      "loss": 0.0063,
+      "loss": 0.0021,
       "step": 272
     },
     {
       "epoch": 9.75,
       "learning_rate": 0.0002,
-      "loss": 0.0052,
+      "loss": 0.0019,
       "step": 273
     },
     {
       "epoch": 9.79,
       "learning_rate": 0.0002,
-      "loss": 0.0042,
+      "loss": 0.001,
       "step": 274
     },
     {
       "epoch": 9.82,
       "learning_rate": 0.0002,
-      "loss": 0.0087,
+      "loss": 0.0045,
       "step": 275
     },
     {
       "epoch": 9.86,
       "learning_rate": 0.0002,
-      "loss": 0.0064,
+      "loss": 0.0032,
       "step": 276
     },
     {
       "epoch": 9.89,
       "learning_rate": 0.0002,
-      "loss": 0.0047,
+      "loss": 0.0039,
       "step": 277
     },
     {
       "epoch": 9.93,
       "learning_rate": 0.0002,
-      "loss": 0.0034,
+      "loss": 0.0048,
       "step": 278
     },
     {
       "epoch": 9.96,
       "learning_rate": 0.0002,
-      "loss": 0.0054,
+      "loss": 0.0035,
       "step": 279
     },
     {
       "epoch": 10.0,
       "learning_rate": 0.0002,
-      "loss": 0.0031,
+      "loss": 0.0018,
       "step": 280
     },
     {
       "epoch": 10.0,
-      "eval_loss": 0.004367400426417589,
-      "eval_runtime": 55.2334,
-      "eval_samples_per_second": 15.697,
+      "eval_loss": 0.0019094761228188872,
+      "eval_runtime": 55.2125,
+      "eval_samples_per_second": 15.703,
       "eval_steps_per_second": 0.507,
       "step": 280
     },
@@ -1772,10 +1772,10 @@
       "epoch": 10.0,
       "step": 280,
       "total_flos": 8.298694499798876e+17,
-      "train_loss": 0.09713323155904488,
-      "train_runtime": 3137.8873,
-      "train_samples_per_second": 2.763,
-      "train_steps_per_second": 0.089
+      "train_loss": 0.09645156941977413,
+      "train_runtime": 3386.4389,
+      "train_samples_per_second": 2.56,
+      "train_steps_per_second": 0.083
     }
   ],
   "logging_steps": 1.0,
diff --git a/training_args.bin b/training_args.bin
index cbf48a1f013a581dea919afeab17d1b9883be6ca..2c41a1ebb577810274e22b98f051ca0985aa7062 100644
--- a/training_args.bin
+++ b/training_args.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e7002d9da22439cd2142660ed0913d77b3af07a95d83f820f2b137e4beb14e
+oid sha256:ab60061c6db4983ad6a9334f47864cfc12b2212c4796c83a0d247a55439133a6
 size 6840