diff --git a/.gitattributes b/.gitattributes
index 82ed3f8dbfc0ed9a81e12460b22dfd5463cb0b28..68378763499be59d1f6249293ad8df66a738d181 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -798,3 +798,12 @@ gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d
 gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-437/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-875/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/README.md b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/adapter_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/adapter_model.safetensors b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2914583db0507b14a5bcd3d237d124baf41adf2d
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93008ec421c7a3492809b1931e60a60b7e286cb520e0ba8266c8862b2ae048ef
+size 143153376
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/README.md b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/adapter_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/adapter_model.safetensors b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5793b2d312d8c4c78a45529ee36122735b061e80
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d2b39ae001343be48bf95ef271c95a287b58182dff8d6611c7494b9cd4bf46
+size 143153376
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/optimizer.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1e91aaf6b4a7ab37ab111d43635fd03117c9c7db
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b7346cda1f2aa85718a88d0c05c65265a8a3bc7e0c1a5ca2c30caa60250a82
+size 72886650
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/rng_state.pth b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..112518523616d4c7374cab599a9d335e6f4d298c
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bed4367f8e2e03865f517c55f8b9b4864edcf9af1401aeb2168812d94293cce
+size 14244
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/scheduler.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..08b95ab5ffe9416570d1acf846049a319f683905
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50868e373a85900101fa12aa1d2734356df59d3850cf8a9b48cd4a6bab1e1654
+size 1064
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/special_tokens_map.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/special_tokens_map.json
@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/tokenizer.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/tokenizer.model b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/tokenizer_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/tokenizer_config.json
@@ -0,0 +1,2013 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/trainer_state.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..6a75ea362a145fe8dd5ffecd7b1629c1fc358353
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/trainer_state.json
@@ -0,0 +1,919 @@
+{
+  "best_metric": 1.1845070123672485,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612",
+  "epoch": 4.0,
+  "eval_steps": 10,
+  "global_step": 1224,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032679738562091505,
+      "grad_norm": 0.631856381893158,
+      "learning_rate": 0.0002,
+      "loss": 2.3561,
+      "step": 10
+    },
+    {
+      "epoch": 0.06535947712418301,
+      "grad_norm": 0.5065668821334839,
+      "learning_rate": 0.0002,
+      "loss": 1.8141,
+      "step": 20
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 0.6978895664215088,
+      "learning_rate": 0.0002,
+      "loss": 1.4952,
+      "step": 30
+    },
+    {
+      "epoch": 0.13071895424836602,
+      "grad_norm": 0.6619144082069397,
+      "learning_rate": 0.0002,
+      "loss": 1.4829,
+      "step": 40
+    },
+    {
+      "epoch": 0.16339869281045752,
+      "grad_norm": 0.6153793931007385,
+      "learning_rate": 0.0002,
+      "loss": 1.3038,
+      "step": 50
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.4703301787376404,
+      "learning_rate": 0.0002,
+      "loss": 1.1429,
+      "step": 60
+    },
+    {
+      "epoch": 0.22875816993464052,
+      "grad_norm": 1.1672580242156982,
+      "learning_rate": 0.0002,
+      "loss": 1.2828,
+      "step": 70
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 0.3455565273761749,
+      "learning_rate": 0.0002,
+      "loss": 1.0985,
+      "step": 80
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.36216291785240173,
+      "learning_rate": 0.0002,
+      "loss": 1.1359,
+      "step": 90
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "grad_norm": 0.4545166492462158,
+      "learning_rate": 0.0002,
+      "loss": 1.2544,
+      "step": 100
+    },
+    {
+      "epoch": 0.35947712418300654,
+      "grad_norm": 0.3612092435359955,
+      "learning_rate": 0.0002,
+      "loss": 1.2287,
+      "step": 110
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.5080830454826355,
+      "learning_rate": 0.0002,
+      "loss": 1.1868,
+      "step": 120
+    },
+    {
+      "epoch": 0.42483660130718953,
+      "grad_norm": 0.3268195390701294,
+      "learning_rate": 0.0002,
+      "loss": 1.1902,
+      "step": 130
+    },
+    {
+      "epoch": 0.45751633986928103,
+      "grad_norm": 0.33971714973449707,
+      "learning_rate": 0.0002,
+      "loss": 1.247,
+      "step": 140
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 0.4036043882369995,
+      "learning_rate": 0.0002,
+      "loss": 1.1844,
+      "step": 150
+    },
+    {
+      "epoch": 0.5228758169934641,
+      "grad_norm": 0.35938864946365356,
+      "learning_rate": 0.0002,
+      "loss": 1.1624,
+      "step": 160
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.28880223631858826,
+      "learning_rate": 0.0002,
+      "loss": 1.164,
+      "step": 170
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.3436269462108612,
+      "learning_rate": 0.0002,
+      "loss": 1.3521,
+      "step": 180
+    },
+    {
+      "epoch": 0.6209150326797386,
+      "grad_norm": 0.41923725605010986,
+      "learning_rate": 0.0002,
+      "loss": 1.2456,
+      "step": 190
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "grad_norm": 0.25119203329086304,
+      "learning_rate": 0.0002,
+      "loss": 1.2226,
+      "step": 200
+    },
+    {
+      "epoch": 0.6862745098039216,
+      "grad_norm": 0.5870180726051331,
+      "learning_rate": 0.0002,
+      "loss": 1.1568,
+      "step": 210
+    },
+    {
+      "epoch": 0.7189542483660131,
+      "grad_norm": 0.2831224203109741,
+      "learning_rate": 0.0002,
+      "loss": 1.064,
+      "step": 220
+    },
+    {
+      "epoch": 0.7516339869281046,
+      "grad_norm": 0.3192005753517151,
+      "learning_rate": 0.0002,
+      "loss": 1.2469,
+      "step": 230
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.2998219430446625,
+      "learning_rate": 0.0002,
+      "loss": 1.1613,
+      "step": 240
+    },
+    {
+      "epoch": 0.8169934640522876,
+      "grad_norm": 0.32855790853500366,
+      "learning_rate": 0.0002,
+      "loss": 1.205,
+      "step": 250
+    },
+    {
+      "epoch": 0.8496732026143791,
+      "grad_norm": 0.3403124213218689,
+      "learning_rate": 0.0002,
+      "loss": 1.1631,
+      "step": 260
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.277401328086853,
+      "learning_rate": 0.0002,
+      "loss": 1.1646,
+      "step": 270
+    },
+    {
+      "epoch": 0.9150326797385621,
+      "grad_norm": 0.2975269556045532,
+      "learning_rate": 0.0002,
+      "loss": 1.084,
+      "step": 280
+    },
+    {
+      "epoch": 0.9477124183006536,
+      "grad_norm": 1.7909578084945679,
+      "learning_rate": 0.0002,
+      "loss": 1.2039,
+      "step": 290
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 0.2917245328426361,
+      "learning_rate": 0.0002,
+      "loss": 1.1226,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1937541961669922,
+      "eval_runtime": 46.2571,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 306
+    },
+    {
+      "epoch": 1.0130718954248366,
+      "grad_norm": 0.26494982838630676,
+      "learning_rate": 0.0002,
+      "loss": 1.2011,
+      "step": 310
+    },
+    {
+      "epoch": 1.0457516339869282,
+      "grad_norm": 0.6289355754852295,
+      "learning_rate": 0.0002,
+      "loss": 1.0565,
+      "step": 320
+    },
+    {
+      "epoch": 1.0784313725490196,
+      "grad_norm": 0.26784011721611023,
+      "learning_rate": 0.0002,
+      "loss": 1.1619,
+      "step": 330
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.3392215967178345,
+      "learning_rate": 0.0002,
+      "loss": 1.1151,
+      "step": 340
+    },
+    {
+      "epoch": 1.1437908496732025,
+      "grad_norm": 0.40005937218666077,
+      "learning_rate": 0.0002,
+      "loss": 1.0752,
+      "step": 350
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.3590582013130188,
+      "learning_rate": 0.0002,
+      "loss": 1.0408,
+      "step": 360
+    },
+    {
+      "epoch": 1.2091503267973855,
+      "grad_norm": 0.3995305895805359,
+      "learning_rate": 0.0002,
+      "loss": 1.0836,
+      "step": 370
+    },
+    {
+      "epoch": 1.2418300653594772,
+      "grad_norm": 0.2950291633605957,
+      "learning_rate": 0.0002,
+      "loss": 1.0992,
+      "step": 380
+    },
+    {
+      "epoch": 1.2745098039215685,
+      "grad_norm": 0.32035166025161743,
+      "learning_rate": 0.0002,
+      "loss": 1.1152,
+      "step": 390
+    },
+    {
+      "epoch": 1.3071895424836601,
+      "grad_norm": 0.410366415977478,
+      "learning_rate": 0.0002,
+      "loss": 1.1467,
+      "step": 400
+    },
+    {
+      "epoch": 1.3398692810457518,
+      "grad_norm": 0.3106379508972168,
+      "learning_rate": 0.0002,
+      "loss": 0.9985,
+      "step": 410
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 0.38580670952796936,
+      "learning_rate": 0.0002,
+      "loss": 0.9789,
+      "step": 420
+    },
+    {
+      "epoch": 1.4052287581699345,
+      "grad_norm": 0.34411361813545227,
+      "learning_rate": 0.0002,
+      "loss": 1.0931,
+      "step": 430
+    },
+    {
+      "epoch": 1.4379084967320261,
+      "grad_norm": 0.44206851720809937,
+      "learning_rate": 0.0002,
+      "loss": 1.1685,
+      "step": 440
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.3492952585220337,
+      "learning_rate": 0.0002,
+      "loss": 1.0347,
+      "step": 450
+    },
+    {
+      "epoch": 1.5032679738562091,
+      "grad_norm": 0.376423716545105,
+      "learning_rate": 0.0002,
+      "loss": 1.0534,
+      "step": 460
+    },
+    {
+      "epoch": 1.5359477124183005,
+      "grad_norm": 0.359757661819458,
+      "learning_rate": 0.0002,
+      "loss": 1.1162,
+      "step": 470
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 0.3385067880153656,
+      "learning_rate": 0.0002,
+      "loss": 0.9586,
+      "step": 480
+    },
+    {
+      "epoch": 1.6013071895424837,
+      "grad_norm": 0.4943889379501343,
+      "learning_rate": 0.0002,
+      "loss": 1.0807,
+      "step": 490
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 0.4203241169452667,
+      "learning_rate": 0.0002,
+      "loss": 1.0796,
+      "step": 500
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.3093789219856262,
+      "learning_rate": 0.0002,
+      "loss": 1.1059,
+      "step": 510
+    },
+    {
+      "epoch": 1.6993464052287581,
+      "grad_norm": 0.3653067350387573,
+      "learning_rate": 0.0002,
+      "loss": 1.0323,
+      "step": 520
+    },
+    {
+      "epoch": 1.7320261437908497,
+      "grad_norm": 0.36761337518692017,
+      "learning_rate": 0.0002,
+      "loss": 1.0885,
+      "step": 530
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.5040399432182312,
+      "learning_rate": 0.0002,
+      "loss": 1.1698,
+      "step": 540
+    },
+    {
+      "epoch": 1.7973856209150327,
+      "grad_norm": 0.3818035125732422,
+      "learning_rate": 0.0002,
+      "loss": 1.0105,
+      "step": 550
+    },
+    {
+      "epoch": 1.8300653594771243,
+      "grad_norm": 0.4021618664264679,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 560
+    },
+    {
+      "epoch": 1.8627450980392157,
+      "grad_norm": 0.3986459970474243,
+      "learning_rate": 0.0002,
+      "loss": 1.0358,
+      "step": 570
+    },
+    {
+      "epoch": 1.8954248366013071,
+      "grad_norm": 0.48416733741760254,
+      "learning_rate": 0.0002,
+      "loss": 1.003,
+      "step": 580
+    },
+    {
+      "epoch": 1.9281045751633987,
+      "grad_norm": 0.36853986978530884,
+      "learning_rate": 0.0002,
+      "loss": 1.1146,
+      "step": 590
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.383022665977478,
+      "learning_rate": 0.0002,
+      "loss": 1.0689,
+      "step": 600
+    },
+    {
+      "epoch": 1.9934640522875817,
+      "grad_norm": 0.3169507086277008,
+      "learning_rate": 0.0002,
+      "loss": 1.098,
+      "step": 610
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1845070123672485,
+      "eval_runtime": 46.2811,
+      "eval_samples_per_second": 9.421,
+      "eval_steps_per_second": 1.188,
+      "step": 612
+    },
+    {
+      "epoch": 2.026143790849673,
+      "grad_norm": 0.8920142650604248,
+      "learning_rate": 0.0002,
+      "loss": 0.9618,
+      "step": 620
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.4814859628677368,
+      "learning_rate": 0.0002,
+      "loss": 0.9784,
+      "step": 630
+    },
+    {
+      "epoch": 2.0915032679738563,
+      "grad_norm": 0.4251559376716614,
+      "learning_rate": 0.0002,
+      "loss": 0.8464,
+      "step": 640
+    },
+    {
+      "epoch": 2.1241830065359477,
+      "grad_norm": 0.5295765399932861,
+      "learning_rate": 0.0002,
+      "loss": 0.932,
+      "step": 650
+    },
+    {
+      "epoch": 2.156862745098039,
+      "grad_norm": 0.45016610622406006,
+      "learning_rate": 0.0002,
+      "loss": 0.9603,
+      "step": 660
+    },
+    {
+      "epoch": 2.189542483660131,
+      "grad_norm": 0.5870586633682251,
+      "learning_rate": 0.0002,
+      "loss": 0.8738,
+      "step": 670
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.5174715518951416,
+      "learning_rate": 0.0002,
+      "loss": 0.9483,
+      "step": 680
+    },
+    {
+      "epoch": 2.2549019607843137,
+      "grad_norm": 0.5252485275268555,
+      "learning_rate": 0.0002,
+      "loss": 0.9551,
+      "step": 690
+    },
+    {
+      "epoch": 2.287581699346405,
+      "grad_norm": 0.5158312320709229,
+      "learning_rate": 0.0002,
+      "loss": 0.9253,
+      "step": 700
+    },
+    {
+      "epoch": 2.3202614379084965,
+      "grad_norm": 0.4824209213256836,
+      "learning_rate": 0.0002,
+      "loss": 0.9278,
+      "step": 710
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.6335175037384033,
+      "learning_rate": 0.0002,
+      "loss": 0.8804,
+      "step": 720
+    },
+    {
+      "epoch": 2.3856209150326797,
+      "grad_norm": 0.5240563154220581,
+      "learning_rate": 0.0002,
+      "loss": 0.9685,
+      "step": 730
+    },
+    {
+      "epoch": 2.418300653594771,
+      "grad_norm": 0.5172886252403259,
+      "learning_rate": 0.0002,
+      "loss": 0.8794,
+      "step": 740
+    },
+    {
+      "epoch": 2.450980392156863,
+      "grad_norm": 0.48972561955451965,
+      "learning_rate": 0.0002,
+      "loss": 0.8158,
+      "step": 750
+    },
+    {
+      "epoch": 2.4836601307189543,
+      "grad_norm": 0.5295189023017883,
+      "learning_rate": 0.0002,
+      "loss": 0.8766,
+      "step": 760
+    },
+    {
+      "epoch": 2.5163398692810457,
+      "grad_norm": 0.5487208962440491,
+      "learning_rate": 0.0002,
+      "loss": 0.8695,
+      "step": 770
+    },
+    {
+      "epoch": 2.549019607843137,
+      "grad_norm": 0.5375093221664429,
+      "learning_rate": 0.0002,
+      "loss": 1.0109,
+      "step": 780
+    },
+    {
+      "epoch": 2.581699346405229,
+      "grad_norm": 0.5424453020095825,
+      "learning_rate": 0.0002,
+      "loss": 0.9244,
+      "step": 790
+    },
+    {
+      "epoch": 2.6143790849673203,
+      "grad_norm": 0.6029134392738342,
+      "learning_rate": 0.0002,
+      "loss": 1.0424,
+      "step": 800
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.6584921479225159,
+      "learning_rate": 0.0002,
+      "loss": 0.8688,
+      "step": 810
+    },
+    {
+      "epoch": 2.6797385620915035,
+      "grad_norm": 0.5735557675361633,
+      "learning_rate": 0.0002,
+      "loss": 0.7796,
+      "step": 820
+    },
+    {
+      "epoch": 2.712418300653595,
+      "grad_norm": 0.5216763019561768,
+      "learning_rate": 0.0002,
+      "loss": 0.8834,
+      "step": 830
+    },
+    {
+      "epoch": 2.7450980392156863,
+      "grad_norm": 0.5455219149589539,
+      "learning_rate": 0.0002,
+      "loss": 0.8946,
+      "step": 840
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.5139284729957581,
+      "learning_rate": 0.0002,
+      "loss": 0.8037,
+      "step": 850
+    },
+    {
+      "epoch": 2.810457516339869,
+      "grad_norm": 0.5096403360366821,
+      "learning_rate": 0.0002,
+      "loss": 0.988,
+      "step": 860
+    },
+    {
+      "epoch": 2.843137254901961,
+      "grad_norm": 0.6337038278579712,
+      "learning_rate": 0.0002,
+      "loss": 0.9169,
+      "step": 870
+    },
+    {
+      "epoch": 2.8758169934640523,
+      "grad_norm": 0.47218772768974304,
+      "learning_rate": 0.0002,
+      "loss": 0.8938,
+      "step": 880
+    },
+    {
+      "epoch": 2.9084967320261437,
+      "grad_norm": 0.4640636742115021,
+      "learning_rate": 0.0002,
+      "loss": 0.8554,
+      "step": 890
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.4199628531932831,
+      "learning_rate": 0.0002,
+      "loss": 0.8625,
+      "step": 900
+    },
+    {
+      "epoch": 2.973856209150327,
+      "grad_norm": 0.5067117214202881,
+      "learning_rate": 0.0002,
+      "loss": 0.8104,
+      "step": 910
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2291251420974731,
+      "eval_runtime": 46.2557,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 918
+    },
+    {
+      "epoch": 3.0065359477124183,
+      "grad_norm": 0.8342176079750061,
+      "learning_rate": 0.0002,
+      "loss": 0.8157,
+      "step": 920
+    },
+    {
+      "epoch": 3.0392156862745097,
+      "grad_norm": 0.7695813775062561,
+      "learning_rate": 0.0002,
+      "loss": 0.6855,
+      "step": 930
+    },
+    {
+      "epoch": 3.0718954248366015,
+      "grad_norm": 0.6819486618041992,
+      "learning_rate": 0.0002,
+      "loss": 0.6173,
+      "step": 940
+    },
+    {
+      "epoch": 3.104575163398693,
+      "grad_norm": 0.7568879723548889,
+      "learning_rate": 0.0002,
+      "loss": 0.6495,
+      "step": 950
+    },
+    {
+      "epoch": 3.1372549019607843,
+      "grad_norm": 0.6760695576667786,
+      "learning_rate": 0.0002,
+      "loss": 0.7905,
+      "step": 960
+    },
+    {
+      "epoch": 3.1699346405228757,
+      "grad_norm": 0.6359127759933472,
+      "learning_rate": 0.0002,
+      "loss": 0.6405,
+      "step": 970
+    },
+    {
+      "epoch": 3.2026143790849675,
+      "grad_norm": 0.8414971828460693,
+      "learning_rate": 0.0002,
+      "loss": 0.7172,
+      "step": 980
+    },
+    {
+      "epoch": 3.235294117647059,
+      "grad_norm": 0.68381667137146,
+      "learning_rate": 0.0002,
+      "loss": 0.7865,
+      "step": 990
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 0.6852193474769592,
+      "learning_rate": 0.0002,
+      "loss": 0.6651,
+      "step": 1000
+    },
+    {
+      "epoch": 3.3006535947712417,
+      "grad_norm": 0.8184967041015625,
+      "learning_rate": 0.0002,
+      "loss": 0.6571,
+      "step": 1010
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.047290563583374,
+      "learning_rate": 0.0002,
+      "loss": 0.7036,
+      "step": 1020
+    },
+    {
+      "epoch": 3.366013071895425,
+      "grad_norm": 0.8291178345680237,
+      "learning_rate": 0.0002,
+      "loss": 0.7215,
+      "step": 1030
+    },
+    {
+      "epoch": 3.3986928104575163,
+      "grad_norm": 0.6668022871017456,
+      "learning_rate": 0.0002,
+      "loss": 0.6243,
+      "step": 1040
+    },
+    {
+      "epoch": 3.431372549019608,
+      "grad_norm": 0.6354008316993713,
+      "learning_rate": 0.0002,
+      "loss": 0.7459,
+      "step": 1050
+    },
+    {
+      "epoch": 3.4640522875816995,
+      "grad_norm": 1.2028366327285767,
+      "learning_rate": 0.0002,
+      "loss": 0.6826,
+      "step": 1060
+    },
+    {
+      "epoch": 3.496732026143791,
+      "grad_norm": 0.717367947101593,
+      "learning_rate": 0.0002,
+      "loss": 0.5913,
+      "step": 1070
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 0.542179524898529,
+      "learning_rate": 0.0002,
+      "loss": 0.6903,
+      "step": 1080
+    },
+    {
+      "epoch": 3.5620915032679736,
+      "grad_norm": 0.845981776714325,
+      "learning_rate": 0.0002,
+      "loss": 0.7673,
+      "step": 1090
+    },
+    {
+      "epoch": 3.5947712418300655,
+      "grad_norm": 0.7381046414375305,
+      "learning_rate": 0.0002,
+      "loss": 0.7089,
+      "step": 1100
+    },
+    {
+      "epoch": 3.627450980392157,
+      "grad_norm": 0.6563456058502197,
+      "learning_rate": 0.0002,
+      "loss": 0.6705,
+      "step": 1110
+    },
+    {
+      "epoch": 3.6601307189542482,
+      "grad_norm": 0.7130876779556274,
+      "learning_rate": 0.0002,
+      "loss": 0.7767,
+      "step": 1120
+    },
+    {
+      "epoch": 3.69281045751634,
+      "grad_norm": 0.800032913684845,
+      "learning_rate": 0.0002,
+      "loss": 0.7164,
+      "step": 1130
+    },
+    {
+      "epoch": 3.7254901960784315,
+      "grad_norm": 0.980328381061554,
+      "learning_rate": 0.0002,
+      "loss": 0.7272,
+      "step": 1140
+    },
+    {
+      "epoch": 3.758169934640523,
+      "grad_norm": 0.8542261123657227,
+      "learning_rate": 0.0002,
+      "loss": 0.7672,
+      "step": 1150
+    },
+    {
+      "epoch": 3.7908496732026142,
+      "grad_norm": 0.6302552819252014,
+      "learning_rate": 0.0002,
+      "loss": 0.679,
+      "step": 1160
+    },
+    {
+      "epoch": 3.8235294117647056,
+      "grad_norm": 0.515398383140564,
+      "learning_rate": 0.0002,
+      "loss": 0.7457,
+      "step": 1170
+    },
+    {
+      "epoch": 3.8562091503267975,
+      "grad_norm": 1.2427130937576294,
+      "learning_rate": 0.0002,
+      "loss": 0.693,
+      "step": 1180
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.8206831216812134,
+      "learning_rate": 0.0002,
+      "loss": 0.7182,
+      "step": 1190
+    },
+    {
+      "epoch": 3.9215686274509802,
+      "grad_norm": 0.7633249163627625,
+      "learning_rate": 0.0002,
+      "loss": 0.7519,
+      "step": 1200
+    },
+    {
+      "epoch": 3.954248366013072,
+      "grad_norm": 0.8034512400627136,
+      "learning_rate": 0.0002,
+      "loss": 0.7082,
+      "step": 1210
+    },
+    {
+      "epoch": 3.9869281045751634,
+      "grad_norm": 0.7667182087898254,
+      "learning_rate": 0.0002,
+      "loss": 0.6834,
+      "step": 1220
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.3456707000732422,
+      "eval_runtime": 46.2562,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 1224
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2448,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.286922464886784e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/training_args.bin b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e7fb8100bbfe18f1342e5fc87e32e8e798268e3b
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1224/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e66621362aa4eab196083c9a4bd0bf843b2425d7109d63be3ab5f4006691dd1
+size 5560
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/README.md b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/adapter_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/adapter_model.safetensors b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4936c43621fa767da307e8270e56e0efdaa4e40d
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de25c1bf3e53f3be00286eed018301ab7d6f4edaaa7a984599625f2dcc82e25c
+size 143153376
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/optimizer.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..857517e3cf85b51f2fc639aa66494ec5953c6aef
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0166704bfb9d47b832d6c61ff5149e2cc798aa8510cde99b99e079a01e60785f
+size 72886650
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/rng_state.pth b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..71ad3a571084a574b59a69e4bc0e05f3741f29e5
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a3272a32abbe607ed1e0c42e1e4209e67224653ec7a445a12bf6cb39d5b6cd
+size 14244
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/scheduler.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..12cf840f119983494dc57dcded908b0a8a439bd4
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70fd0e651657c68255bfbddaea06e66fc5308abd761799251251b4b129a8c90d
+size 1064
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/special_tokens_map.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/special_tokens_map.json
@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/tokenizer.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/tokenizer.model b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/tokenizer_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/tokenizer_config.json
@@ -0,0 +1,2013 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/trainer_state.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..8e964ad3ba74f43622e711b1d70d1fb8ed0622e3
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/trainer_state.json
@@ -0,0 +1,1144 @@
+{
+  "best_metric": 1.1845070123672485,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612",
+  "epoch": 5.0,
+  "eval_steps": 10,
+  "global_step": 1530,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032679738562091505,
+      "grad_norm": 0.631856381893158,
+      "learning_rate": 0.0002,
+      "loss": 2.3561,
+      "step": 10
+    },
+    {
+      "epoch": 0.06535947712418301,
+      "grad_norm": 0.5065668821334839,
+      "learning_rate": 0.0002,
+      "loss": 1.8141,
+      "step": 20
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 0.6978895664215088,
+      "learning_rate": 0.0002,
+      "loss": 1.4952,
+      "step": 30
+    },
+    {
+      "epoch": 0.13071895424836602,
+      "grad_norm": 0.6619144082069397,
+      "learning_rate": 0.0002,
+      "loss": 1.4829,
+      "step": 40
+    },
+    {
+      "epoch": 0.16339869281045752,
+      "grad_norm": 0.6153793931007385,
+      "learning_rate": 0.0002,
+      "loss": 1.3038,
+      "step": 50
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.4703301787376404,
+      "learning_rate": 0.0002,
+      "loss": 1.1429,
+      "step": 60
+    },
+    {
+      "epoch": 0.22875816993464052,
+      "grad_norm": 1.1672580242156982,
+      "learning_rate": 0.0002,
+      "loss": 1.2828,
+      "step": 70
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 0.3455565273761749,
+      "learning_rate": 0.0002,
+      "loss": 1.0985,
+      "step": 80
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.36216291785240173,
+      "learning_rate": 0.0002,
+      "loss": 1.1359,
+      "step": 90
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "grad_norm": 0.4545166492462158,
+      "learning_rate": 0.0002,
+      "loss": 1.2544,
+      "step": 100
+    },
+    {
+      "epoch": 0.35947712418300654,
+      "grad_norm": 0.3612092435359955,
+      "learning_rate": 0.0002,
+      "loss": 1.2287,
+      "step": 110
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.5080830454826355,
+      "learning_rate": 0.0002,
+      "loss": 1.1868,
+      "step": 120
+    },
+    {
+      "epoch": 0.42483660130718953,
+      "grad_norm": 0.3268195390701294,
+      "learning_rate": 0.0002,
+      "loss": 1.1902,
+      "step": 130
+    },
+    {
+      "epoch": 0.45751633986928103,
+      "grad_norm": 0.33971714973449707,
+      "learning_rate": 0.0002,
+      "loss": 1.247,
+      "step": 140
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 0.4036043882369995,
+      "learning_rate": 0.0002,
+      "loss": 1.1844,
+      "step": 150
+    },
+    {
+      "epoch": 0.5228758169934641,
+      "grad_norm": 0.35938864946365356,
+      "learning_rate": 0.0002,
+      "loss": 1.1624,
+      "step": 160
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.28880223631858826,
+      "learning_rate": 0.0002,
+      "loss": 1.164,
+      "step": 170
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.3436269462108612,
+      "learning_rate": 0.0002,
+      "loss": 1.3521,
+      "step": 180
+    },
+    {
+      "epoch": 0.6209150326797386,
+      "grad_norm": 0.41923725605010986,
+      "learning_rate": 0.0002,
+      "loss": 1.2456,
+      "step": 190
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "grad_norm": 0.25119203329086304,
+      "learning_rate": 0.0002,
+      "loss": 1.2226,
+      "step": 200
+    },
+    {
+      "epoch": 0.6862745098039216,
+      "grad_norm": 0.5870180726051331,
+      "learning_rate": 0.0002,
+      "loss": 1.1568,
+      "step": 210
+    },
+    {
+      "epoch": 0.7189542483660131,
+      "grad_norm": 0.2831224203109741,
+      "learning_rate": 0.0002,
+      "loss": 1.064,
+      "step": 220
+    },
+    {
+      "epoch": 0.7516339869281046,
+      "grad_norm": 0.3192005753517151,
+      "learning_rate": 0.0002,
+      "loss": 1.2469,
+      "step": 230
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.2998219430446625,
+      "learning_rate": 0.0002,
+      "loss": 1.1613,
+      "step": 240
+    },
+    {
+      "epoch": 0.8169934640522876,
+      "grad_norm": 0.32855790853500366,
+      "learning_rate": 0.0002,
+      "loss": 1.205,
+      "step": 250
+    },
+    {
+      "epoch": 0.8496732026143791,
+      "grad_norm": 0.3403124213218689,
+      "learning_rate": 0.0002,
+      "loss": 1.1631,
+      "step": 260
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.277401328086853,
+      "learning_rate": 0.0002,
+      "loss": 1.1646,
+      "step": 270
+    },
+    {
+      "epoch": 0.9150326797385621,
+      "grad_norm": 0.2975269556045532,
+      "learning_rate": 0.0002,
+      "loss": 1.084,
+      "step": 280
+    },
+    {
+      "epoch": 0.9477124183006536,
+      "grad_norm": 1.7909578084945679,
+      "learning_rate": 0.0002,
+      "loss": 1.2039,
+      "step": 290
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 0.2917245328426361,
+      "learning_rate": 0.0002,
+      "loss": 1.1226,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1937541961669922,
+      "eval_runtime": 46.2571,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 306
+    },
+    {
+      "epoch": 1.0130718954248366,
+      "grad_norm": 0.26494982838630676,
+      "learning_rate": 0.0002,
+      "loss": 1.2011,
+      "step": 310
+    },
+    {
+      "epoch": 1.0457516339869282,
+      "grad_norm": 0.6289355754852295,
+      "learning_rate": 0.0002,
+      "loss": 1.0565,
+      "step": 320
+    },
+    {
+      "epoch": 1.0784313725490196,
+      "grad_norm": 0.26784011721611023,
+      "learning_rate": 0.0002,
+      "loss": 1.1619,
+      "step": 330
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.3392215967178345,
+      "learning_rate": 0.0002,
+      "loss": 1.1151,
+      "step": 340
+    },
+    {
+      "epoch": 1.1437908496732025,
+      "grad_norm": 0.40005937218666077,
+      "learning_rate": 0.0002,
+      "loss": 1.0752,
+      "step": 350
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.3590582013130188,
+      "learning_rate": 0.0002,
+      "loss": 1.0408,
+      "step": 360
+    },
+    {
+      "epoch": 1.2091503267973855,
+      "grad_norm": 0.3995305895805359,
+      "learning_rate": 0.0002,
+      "loss": 1.0836,
+      "step": 370
+    },
+    {
+      "epoch": 1.2418300653594772,
+      "grad_norm": 0.2950291633605957,
+      "learning_rate": 0.0002,
+      "loss": 1.0992,
+      "step": 380
+    },
+    {
+      "epoch": 1.2745098039215685,
+      "grad_norm": 0.32035166025161743,
+      "learning_rate": 0.0002,
+      "loss": 1.1152,
+      "step": 390
+    },
+    {
+      "epoch": 1.3071895424836601,
+      "grad_norm": 0.410366415977478,
+      "learning_rate": 0.0002,
+      "loss": 1.1467,
+      "step": 400
+    },
+    {
+      "epoch": 1.3398692810457518,
+      "grad_norm": 0.3106379508972168,
+      "learning_rate": 0.0002,
+      "loss": 0.9985,
+      "step": 410
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 0.38580670952796936,
+      "learning_rate": 0.0002,
+      "loss": 0.9789,
+      "step": 420
+    },
+    {
+      "epoch": 1.4052287581699345,
+      "grad_norm": 0.34411361813545227,
+      "learning_rate": 0.0002,
+      "loss": 1.0931,
+      "step": 430
+    },
+    {
+      "epoch": 1.4379084967320261,
+      "grad_norm": 0.44206851720809937,
+      "learning_rate": 0.0002,
+      "loss": 1.1685,
+      "step": 440
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.3492952585220337,
+      "learning_rate": 0.0002,
+      "loss": 1.0347,
+      "step": 450
+    },
+    {
+      "epoch": 1.5032679738562091,
+      "grad_norm": 0.376423716545105,
+      "learning_rate": 0.0002,
+      "loss": 1.0534,
+      "step": 460
+    },
+    {
+      "epoch": 1.5359477124183005,
+      "grad_norm": 0.359757661819458,
+      "learning_rate": 0.0002,
+      "loss": 1.1162,
+      "step": 470
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 0.3385067880153656,
+      "learning_rate": 0.0002,
+      "loss": 0.9586,
+      "step": 480
+    },
+    {
+      "epoch": 1.6013071895424837,
+      "grad_norm": 0.4943889379501343,
+      "learning_rate": 0.0002,
+      "loss": 1.0807,
+      "step": 490
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 0.4203241169452667,
+      "learning_rate": 0.0002,
+      "loss": 1.0796,
+      "step": 500
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.3093789219856262,
+      "learning_rate": 0.0002,
+      "loss": 1.1059,
+      "step": 510
+    },
+    {
+      "epoch": 1.6993464052287581,
+      "grad_norm": 0.3653067350387573,
+      "learning_rate": 0.0002,
+      "loss": 1.0323,
+      "step": 520
+    },
+    {
+      "epoch": 1.7320261437908497,
+      "grad_norm": 0.36761337518692017,
+      "learning_rate": 0.0002,
+      "loss": 1.0885,
+      "step": 530
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.5040399432182312,
+      "learning_rate": 0.0002,
+      "loss": 1.1698,
+      "step": 540
+    },
+    {
+      "epoch": 1.7973856209150327,
+      "grad_norm": 0.3818035125732422,
+      "learning_rate": 0.0002,
+      "loss": 1.0105,
+      "step": 550
+    },
+    {
+      "epoch": 1.8300653594771243,
+      "grad_norm": 0.4021618664264679,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 560
+    },
+    {
+      "epoch": 1.8627450980392157,
+      "grad_norm": 0.3986459970474243,
+      "learning_rate": 0.0002,
+      "loss": 1.0358,
+      "step": 570
+    },
+    {
+      "epoch": 1.8954248366013071,
+      "grad_norm": 0.48416733741760254,
+      "learning_rate": 0.0002,
+      "loss": 1.003,
+      "step": 580
+    },
+    {
+      "epoch": 1.9281045751633987,
+      "grad_norm": 0.36853986978530884,
+      "learning_rate": 0.0002,
+      "loss": 1.1146,
+      "step": 590
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.383022665977478,
+      "learning_rate": 0.0002,
+      "loss": 1.0689,
+      "step": 600
+    },
+    {
+      "epoch": 1.9934640522875817,
+      "grad_norm": 0.3169507086277008,
+      "learning_rate": 0.0002,
+      "loss": 1.098,
+      "step": 610
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1845070123672485,
+      "eval_runtime": 46.2811,
+      "eval_samples_per_second": 9.421,
+      "eval_steps_per_second": 1.188,
+      "step": 612
+    },
+    {
+      "epoch": 2.026143790849673,
+      "grad_norm": 0.8920142650604248,
+      "learning_rate": 0.0002,
+      "loss": 0.9618,
+      "step": 620
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.4814859628677368,
+      "learning_rate": 0.0002,
+      "loss": 0.9784,
+      "step": 630
+    },
+    {
+      "epoch": 2.0915032679738563,
+      "grad_norm": 0.4251559376716614,
+      "learning_rate": 0.0002,
+      "loss": 0.8464,
+      "step": 640
+    },
+    {
+      "epoch": 2.1241830065359477,
+      "grad_norm": 0.5295765399932861,
+      "learning_rate": 0.0002,
+      "loss": 0.932,
+      "step": 650
+    },
+    {
+      "epoch": 2.156862745098039,
+      "grad_norm": 0.45016610622406006,
+      "learning_rate": 0.0002,
+      "loss": 0.9603,
+      "step": 660
+    },
+    {
+      "epoch": 2.189542483660131,
+      "grad_norm": 0.5870586633682251,
+      "learning_rate": 0.0002,
+      "loss": 0.8738,
+      "step": 670
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.5174715518951416,
+      "learning_rate": 0.0002,
+      "loss": 0.9483,
+      "step": 680
+    },
+    {
+      "epoch": 2.2549019607843137,
+      "grad_norm": 0.5252485275268555,
+      "learning_rate": 0.0002,
+      "loss": 0.9551,
+      "step": 690
+    },
+    {
+      "epoch": 2.287581699346405,
+      "grad_norm": 0.5158312320709229,
+      "learning_rate": 0.0002,
+      "loss": 0.9253,
+      "step": 700
+    },
+    {
+      "epoch": 2.3202614379084965,
+      "grad_norm": 0.4824209213256836,
+      "learning_rate": 0.0002,
+      "loss": 0.9278,
+      "step": 710
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.6335175037384033,
+      "learning_rate": 0.0002,
+      "loss": 0.8804,
+      "step": 720
+    },
+    {
+      "epoch": 2.3856209150326797,
+      "grad_norm": 0.5240563154220581,
+      "learning_rate": 0.0002,
+      "loss": 0.9685,
+      "step": 730
+    },
+    {
+      "epoch": 2.418300653594771,
+      "grad_norm": 0.5172886252403259,
+      "learning_rate": 0.0002,
+      "loss": 0.8794,
+      "step": 740
+    },
+    {
+      "epoch": 2.450980392156863,
+      "grad_norm": 0.48972561955451965,
+      "learning_rate": 0.0002,
+      "loss": 0.8158,
+      "step": 750
+    },
+    {
+      "epoch": 2.4836601307189543,
+      "grad_norm": 0.5295189023017883,
+      "learning_rate": 0.0002,
+      "loss": 0.8766,
+      "step": 760
+    },
+    {
+      "epoch": 2.5163398692810457,
+      "grad_norm": 0.5487208962440491,
+      "learning_rate": 0.0002,
+      "loss": 0.8695,
+      "step": 770
+    },
+    {
+      "epoch": 2.549019607843137,
+      "grad_norm": 0.5375093221664429,
+      "learning_rate": 0.0002,
+      "loss": 1.0109,
+      "step": 780
+    },
+    {
+      "epoch": 2.581699346405229,
+      "grad_norm": 0.5424453020095825,
+      "learning_rate": 0.0002,
+      "loss": 0.9244,
+      "step": 790
+    },
+    {
+      "epoch": 2.6143790849673203,
+      "grad_norm": 0.6029134392738342,
+      "learning_rate": 0.0002,
+      "loss": 1.0424,
+      "step": 800
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.6584921479225159,
+      "learning_rate": 0.0002,
+      "loss": 0.8688,
+      "step": 810
+    },
+    {
+      "epoch": 2.6797385620915035,
+      "grad_norm": 0.5735557675361633,
+      "learning_rate": 0.0002,
+      "loss": 0.7796,
+      "step": 820
+    },
+    {
+      "epoch": 2.712418300653595,
+      "grad_norm": 0.5216763019561768,
+      "learning_rate": 0.0002,
+      "loss": 0.8834,
+      "step": 830
+    },
+    {
+      "epoch": 2.7450980392156863,
+      "grad_norm": 0.5455219149589539,
+      "learning_rate": 0.0002,
+      "loss": 0.8946,
+      "step": 840
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.5139284729957581,
+      "learning_rate": 0.0002,
+      "loss": 0.8037,
+      "step": 850
+    },
+    {
+      "epoch": 2.810457516339869,
+      "grad_norm": 0.5096403360366821,
+      "learning_rate": 0.0002,
+      "loss": 0.988,
+      "step": 860
+    },
+    {
+      "epoch": 2.843137254901961,
+      "grad_norm": 0.6337038278579712,
+      "learning_rate": 0.0002,
+      "loss": 0.9169,
+      "step": 870
+    },
+    {
+      "epoch": 2.8758169934640523,
+      "grad_norm": 0.47218772768974304,
+      "learning_rate": 0.0002,
+      "loss": 0.8938,
+      "step": 880
+    },
+    {
+      "epoch": 2.9084967320261437,
+      "grad_norm": 0.4640636742115021,
+      "learning_rate": 0.0002,
+      "loss": 0.8554,
+      "step": 890
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.4199628531932831,
+      "learning_rate": 0.0002,
+      "loss": 0.8625,
+      "step": 900
+    },
+    {
+      "epoch": 2.973856209150327,
+      "grad_norm": 0.5067117214202881,
+      "learning_rate": 0.0002,
+      "loss": 0.8104,
+      "step": 910
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2291251420974731,
+      "eval_runtime": 46.2557,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 918
+    },
+    {
+      "epoch": 3.0065359477124183,
+      "grad_norm": 0.8342176079750061,
+      "learning_rate": 0.0002,
+      "loss": 0.8157,
+      "step": 920
+    },
+    {
+      "epoch": 3.0392156862745097,
+      "grad_norm": 0.7695813775062561,
+      "learning_rate": 0.0002,
+      "loss": 0.6855,
+      "step": 930
+    },
+    {
+      "epoch": 3.0718954248366015,
+      "grad_norm": 0.6819486618041992,
+      "learning_rate": 0.0002,
+      "loss": 0.6173,
+      "step": 940
+    },
+    {
+      "epoch": 3.104575163398693,
+      "grad_norm": 0.7568879723548889,
+      "learning_rate": 0.0002,
+      "loss": 0.6495,
+      "step": 950
+    },
+    {
+      "epoch": 3.1372549019607843,
+      "grad_norm": 0.6760695576667786,
+      "learning_rate": 0.0002,
+      "loss": 0.7905,
+      "step": 960
+    },
+    {
+      "epoch": 3.1699346405228757,
+      "grad_norm": 0.6359127759933472,
+      "learning_rate": 0.0002,
+      "loss": 0.6405,
+      "step": 970
+    },
+    {
+      "epoch": 3.2026143790849675,
+      "grad_norm": 0.8414971828460693,
+      "learning_rate": 0.0002,
+      "loss": 0.7172,
+      "step": 980
+    },
+    {
+      "epoch": 3.235294117647059,
+      "grad_norm": 0.68381667137146,
+      "learning_rate": 0.0002,
+      "loss": 0.7865,
+      "step": 990
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 0.6852193474769592,
+      "learning_rate": 0.0002,
+      "loss": 0.6651,
+      "step": 1000
+    },
+    {
+      "epoch": 3.3006535947712417,
+      "grad_norm": 0.8184967041015625,
+      "learning_rate": 0.0002,
+      "loss": 0.6571,
+      "step": 1010
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.047290563583374,
+      "learning_rate": 0.0002,
+      "loss": 0.7036,
+      "step": 1020
+    },
+    {
+      "epoch": 3.366013071895425,
+      "grad_norm": 0.8291178345680237,
+      "learning_rate": 0.0002,
+      "loss": 0.7215,
+      "step": 1030
+    },
+    {
+      "epoch": 3.3986928104575163,
+      "grad_norm": 0.6668022871017456,
+      "learning_rate": 0.0002,
+      "loss": 0.6243,
+      "step": 1040
+    },
+    {
+      "epoch": 3.431372549019608,
+      "grad_norm": 0.6354008316993713,
+      "learning_rate": 0.0002,
+      "loss": 0.7459,
+      "step": 1050
+    },
+    {
+      "epoch": 3.4640522875816995,
+      "grad_norm": 1.2028366327285767,
+      "learning_rate": 0.0002,
+      "loss": 0.6826,
+      "step": 1060
+    },
+    {
+      "epoch": 3.496732026143791,
+      "grad_norm": 0.717367947101593,
+      "learning_rate": 0.0002,
+      "loss": 0.5913,
+      "step": 1070
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 0.542179524898529,
+      "learning_rate": 0.0002,
+      "loss": 0.6903,
+      "step": 1080
+    },
+    {
+      "epoch": 3.5620915032679736,
+      "grad_norm": 0.845981776714325,
+      "learning_rate": 0.0002,
+      "loss": 0.7673,
+      "step": 1090
+    },
+    {
+      "epoch": 3.5947712418300655,
+      "grad_norm": 0.7381046414375305,
+      "learning_rate": 0.0002,
+      "loss": 0.7089,
+      "step": 1100
+    },
+    {
+      "epoch": 3.627450980392157,
+      "grad_norm": 0.6563456058502197,
+      "learning_rate": 0.0002,
+      "loss": 0.6705,
+      "step": 1110
+    },
+    {
+      "epoch": 3.6601307189542482,
+      "grad_norm": 0.7130876779556274,
+      "learning_rate": 0.0002,
+      "loss": 0.7767,
+      "step": 1120
+    },
+    {
+      "epoch": 3.69281045751634,
+      "grad_norm": 0.800032913684845,
+      "learning_rate": 0.0002,
+      "loss": 0.7164,
+      "step": 1130
+    },
+    {
+      "epoch": 3.7254901960784315,
+      "grad_norm": 0.980328381061554,
+      "learning_rate": 0.0002,
+      "loss": 0.7272,
+      "step": 1140
+    },
+    {
+      "epoch": 3.758169934640523,
+      "grad_norm": 0.8542261123657227,
+      "learning_rate": 0.0002,
+      "loss": 0.7672,
+      "step": 1150
+    },
+    {
+      "epoch": 3.7908496732026142,
+      "grad_norm": 0.6302552819252014,
+      "learning_rate": 0.0002,
+      "loss": 0.679,
+      "step": 1160
+    },
+    {
+      "epoch": 3.8235294117647056,
+      "grad_norm": 0.515398383140564,
+      "learning_rate": 0.0002,
+      "loss": 0.7457,
+      "step": 1170
+    },
+    {
+      "epoch": 3.8562091503267975,
+      "grad_norm": 1.2427130937576294,
+      "learning_rate": 0.0002,
+      "loss": 0.693,
+      "step": 1180
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.8206831216812134,
+      "learning_rate": 0.0002,
+      "loss": 0.7182,
+      "step": 1190
+    },
+    {
+      "epoch": 3.9215686274509802,
+      "grad_norm": 0.7633249163627625,
+      "learning_rate": 0.0002,
+      "loss": 0.7519,
+      "step": 1200
+    },
+    {
+      "epoch": 3.954248366013072,
+      "grad_norm": 0.8034512400627136,
+      "learning_rate": 0.0002,
+      "loss": 0.7082,
+      "step": 1210
+    },
+    {
+      "epoch": 3.9869281045751634,
+      "grad_norm": 0.7667182087898254,
+      "learning_rate": 0.0002,
+      "loss": 0.6834,
+      "step": 1220
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.3456707000732422,
+      "eval_runtime": 46.2562,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 1224
+    },
+    {
+      "epoch": 4.019607843137255,
+      "grad_norm": 0.7724746465682983,
+      "learning_rate": 0.0002,
+      "loss": 0.582,
+      "step": 1230
+    },
+    {
+      "epoch": 4.052287581699346,
+      "grad_norm": 1.166916847229004,
+      "learning_rate": 0.0002,
+      "loss": 0.4759,
+      "step": 1240
+    },
+    {
+      "epoch": 4.084967320261438,
+      "grad_norm": 0.7234508991241455,
+      "learning_rate": 0.0002,
+      "loss": 0.4995,
+      "step": 1250
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 1.1418060064315796,
+      "learning_rate": 0.0002,
+      "loss": 0.4863,
+      "step": 1260
+    },
+    {
+      "epoch": 4.150326797385621,
+      "grad_norm": 0.9603922367095947,
+      "learning_rate": 0.0002,
+      "loss": 0.5425,
+      "step": 1270
+    },
+    {
+      "epoch": 4.183006535947713,
+      "grad_norm": 0.8976530432701111,
+      "learning_rate": 0.0002,
+      "loss": 0.4892,
+      "step": 1280
+    },
+    {
+      "epoch": 4.215686274509804,
+      "grad_norm": 0.6855078339576721,
+      "learning_rate": 0.0002,
+      "loss": 0.473,
+      "step": 1290
+    },
+    {
+      "epoch": 4.248366013071895,
+      "grad_norm": 1.2676647901535034,
+      "learning_rate": 0.0002,
+      "loss": 0.4416,
+      "step": 1300
+    },
+    {
+      "epoch": 4.281045751633987,
+      "grad_norm": 1.104057788848877,
+      "learning_rate": 0.0002,
+      "loss": 0.5071,
+      "step": 1310
+    },
+    {
+      "epoch": 4.313725490196078,
+      "grad_norm": 1.7076562643051147,
+      "learning_rate": 0.0002,
+      "loss": 0.5168,
+      "step": 1320
+    },
+    {
+      "epoch": 4.34640522875817,
+      "grad_norm": 1.2308520078659058,
+      "learning_rate": 0.0002,
+      "loss": 0.4655,
+      "step": 1330
+    },
+    {
+      "epoch": 4.379084967320262,
+      "grad_norm": 1.2652729749679565,
+      "learning_rate": 0.0002,
+      "loss": 0.5322,
+      "step": 1340
+    },
+    {
+      "epoch": 4.411764705882353,
+      "grad_norm": 1.054958701133728,
+      "learning_rate": 0.0002,
+      "loss": 0.5262,
+      "step": 1350
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 1.0130749940872192,
+      "learning_rate": 0.0002,
+      "loss": 0.4747,
+      "step": 1360
+    },
+    {
+      "epoch": 4.477124183006536,
+      "grad_norm": 1.0517818927764893,
+      "learning_rate": 0.0002,
+      "loss": 0.4887,
+      "step": 1370
+    },
+    {
+      "epoch": 4.509803921568627,
+      "grad_norm": 0.8593037128448486,
+      "learning_rate": 0.0002,
+      "loss": 0.4906,
+      "step": 1380
+    },
+    {
+      "epoch": 4.542483660130719,
+      "grad_norm": 1.0248081684112549,
+      "learning_rate": 0.0002,
+      "loss": 0.5049,
+      "step": 1390
+    },
+    {
+      "epoch": 4.57516339869281,
+      "grad_norm": 0.8999413847923279,
+      "learning_rate": 0.0002,
+      "loss": 0.472,
+      "step": 1400
+    },
+    {
+      "epoch": 4.607843137254902,
+      "grad_norm": 0.9106912612915039,
+      "learning_rate": 0.0002,
+      "loss": 0.5102,
+      "step": 1410
+    },
+    {
+      "epoch": 4.640522875816993,
+      "grad_norm": 1.2736181020736694,
+      "learning_rate": 0.0002,
+      "loss": 0.5203,
+      "step": 1420
+    },
+    {
+      "epoch": 4.673202614379085,
+      "grad_norm": 0.9311690926551819,
+      "learning_rate": 0.0002,
+      "loss": 0.5101,
+      "step": 1430
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 1.0455045700073242,
+      "learning_rate": 0.0002,
+      "loss": 0.5648,
+      "step": 1440
+    },
+    {
+      "epoch": 4.738562091503268,
+      "grad_norm": 1.0190727710723877,
+      "learning_rate": 0.0002,
+      "loss": 0.5004,
+      "step": 1450
+    },
+    {
+      "epoch": 4.771241830065359,
+      "grad_norm": 1.333198070526123,
+      "learning_rate": 0.0002,
+      "loss": 0.5506,
+      "step": 1460
+    },
+    {
+      "epoch": 4.803921568627451,
+      "grad_norm": 0.8808416724205017,
+      "learning_rate": 0.0002,
+      "loss": 0.5846,
+      "step": 1470
+    },
+    {
+      "epoch": 4.836601307189542,
+      "grad_norm": 0.8896227478981018,
+      "learning_rate": 0.0002,
+      "loss": 0.4671,
+      "step": 1480
+    },
+    {
+      "epoch": 4.8692810457516345,
+      "grad_norm": 1.212323784828186,
+      "learning_rate": 0.0002,
+      "loss": 0.4732,
+      "step": 1490
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 1.0490120649337769,
+      "learning_rate": 0.0002,
+      "loss": 0.5263,
+      "step": 1500
+    },
+    {
+      "epoch": 4.934640522875817,
+      "grad_norm": 0.8946618437767029,
+      "learning_rate": 0.0002,
+      "loss": 0.5815,
+      "step": 1510
+    },
+    {
+      "epoch": 4.967320261437909,
+      "grad_norm": 1.0609275102615356,
+      "learning_rate": 0.0002,
+      "loss": 0.5369,
+      "step": 1520
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.8885099291801453,
+      "learning_rate": 0.0002,
+      "loss": 0.5348,
+      "step": 1530
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.5771757364273071,
+      "eval_runtime": 46.2667,
+      "eval_samples_per_second": 9.424,
+      "eval_steps_per_second": 1.189,
+      "step": 1530
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2448,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.85865308110848e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/training_args.bin b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e7fb8100bbfe18f1342e5fc87e32e8e798268e3b
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1530/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e66621362aa4eab196083c9a4bd0bf843b2425d7109d63be3ab5f4006691dd1
+size 5560
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/README.md b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/adapter_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/adapter_model.safetensors b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..379972c93acac74527377c606066267c038ca1a0
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cba63e1e980f17fbfd7294d59c0b242ce270633ea5d80bac7f58e15a34b5394
+size 143153376
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/optimizer.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..da7f65b8fb5d04428b7cdab38a68e49ef8372da5
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09cea484d0ce018bcbf9863c62afcb363be5503137233edb1ad8309572a0d2ef
+size 72886650
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/rng_state.pth b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..81f61c0077516e02ac5c8d313ad77141e2d8301a
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c8f9dce02503f3cbf8c9bb14de9d5e9c8f903b865370691267f3556220b4ea
+size 14244
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/scheduler.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ca3ede5ec898c12dbce366c0565f25cf87bdda2b
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bcfa0cfb603077ad7bad7d25378dad56ade42ca731e5eca62b2e241e2e4d5d9
+size 1064
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/special_tokens_map.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/special_tokens_map.json
@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/tokenizer.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/tokenizer.model b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/tokenizer_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/tokenizer_config.json
@@ -0,0 +1,2013 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/trainer_state.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..133dded1b78c147b5e6866cdcff15a038870fef3
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/trainer_state.json
@@ -0,0 +1,1362 @@
+{
+  "best_metric": 1.1845070123672485,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612",
+  "epoch": 6.0,
+  "eval_steps": 10,
+  "global_step": 1836,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032679738562091505,
+      "grad_norm": 0.631856381893158,
+      "learning_rate": 0.0002,
+      "loss": 2.3561,
+      "step": 10
+    },
+    {
+      "epoch": 0.06535947712418301,
+      "grad_norm": 0.5065668821334839,
+      "learning_rate": 0.0002,
+      "loss": 1.8141,
+      "step": 20
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 0.6978895664215088,
+      "learning_rate": 0.0002,
+      "loss": 1.4952,
+      "step": 30
+    },
+    {
+      "epoch": 0.13071895424836602,
+      "grad_norm": 0.6619144082069397,
+      "learning_rate": 0.0002,
+      "loss": 1.4829,
+      "step": 40
+    },
+    {
+      "epoch": 0.16339869281045752,
+      "grad_norm": 0.6153793931007385,
+      "learning_rate": 0.0002,
+      "loss": 1.3038,
+      "step": 50
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.4703301787376404,
+      "learning_rate": 0.0002,
+      "loss": 1.1429,
+      "step": 60
+    },
+    {
+      "epoch": 0.22875816993464052,
+      "grad_norm": 1.1672580242156982,
+      "learning_rate": 0.0002,
+      "loss": 1.2828,
+      "step": 70
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 0.3455565273761749,
+      "learning_rate": 0.0002,
+      "loss": 1.0985,
+      "step": 80
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.36216291785240173,
+      "learning_rate": 0.0002,
+      "loss": 1.1359,
+      "step": 90
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "grad_norm": 0.4545166492462158,
+      "learning_rate": 0.0002,
+      "loss": 1.2544,
+      "step": 100
+    },
+    {
+      "epoch": 0.35947712418300654,
+      "grad_norm": 0.3612092435359955,
+      "learning_rate": 0.0002,
+      "loss": 1.2287,
+      "step": 110
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.5080830454826355,
+      "learning_rate": 0.0002,
+      "loss": 1.1868,
+      "step": 120
+    },
+    {
+      "epoch": 0.42483660130718953,
+      "grad_norm": 0.3268195390701294,
+      "learning_rate": 0.0002,
+      "loss": 1.1902,
+      "step": 130
+    },
+    {
+      "epoch": 0.45751633986928103,
+      "grad_norm": 0.33971714973449707,
+      "learning_rate": 0.0002,
+      "loss": 1.247,
+      "step": 140
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 0.4036043882369995,
+      "learning_rate": 0.0002,
+      "loss": 1.1844,
+      "step": 150
+    },
+    {
+      "epoch": 0.5228758169934641,
+      "grad_norm": 0.35938864946365356,
+      "learning_rate": 0.0002,
+      "loss": 1.1624,
+      "step": 160
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.28880223631858826,
+      "learning_rate": 0.0002,
+      "loss": 1.164,
+      "step": 170
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.3436269462108612,
+      "learning_rate": 0.0002,
+      "loss": 1.3521,
+      "step": 180
+    },
+    {
+      "epoch": 0.6209150326797386,
+      "grad_norm": 0.41923725605010986,
+      "learning_rate": 0.0002,
+      "loss": 1.2456,
+      "step": 190
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "grad_norm": 0.25119203329086304,
+      "learning_rate": 0.0002,
+      "loss": 1.2226,
+      "step": 200
+    },
+    {
+      "epoch": 0.6862745098039216,
+      "grad_norm": 0.5870180726051331,
+      "learning_rate": 0.0002,
+      "loss": 1.1568,
+      "step": 210
+    },
+    {
+      "epoch": 0.7189542483660131,
+      "grad_norm": 0.2831224203109741,
+      "learning_rate": 0.0002,
+      "loss": 1.064,
+      "step": 220
+    },
+    {
+      "epoch": 0.7516339869281046,
+      "grad_norm": 0.3192005753517151,
+      "learning_rate": 0.0002,
+      "loss": 1.2469,
+      "step": 230
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.2998219430446625,
+      "learning_rate": 0.0002,
+      "loss": 1.1613,
+      "step": 240
+    },
+    {
+      "epoch": 0.8169934640522876,
+      "grad_norm": 0.32855790853500366,
+      "learning_rate": 0.0002,
+      "loss": 1.205,
+      "step": 250
+    },
+    {
+      "epoch": 0.8496732026143791,
+      "grad_norm": 0.3403124213218689,
+      "learning_rate": 0.0002,
+      "loss": 1.1631,
+      "step": 260
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.277401328086853,
+      "learning_rate": 0.0002,
+      "loss": 1.1646,
+      "step": 270
+    },
+    {
+      "epoch": 0.9150326797385621,
+      "grad_norm": 0.2975269556045532,
+      "learning_rate": 0.0002,
+      "loss": 1.084,
+      "step": 280
+    },
+    {
+      "epoch": 0.9477124183006536,
+      "grad_norm": 1.7909578084945679,
+      "learning_rate": 0.0002,
+      "loss": 1.2039,
+      "step": 290
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 0.2917245328426361,
+      "learning_rate": 0.0002,
+      "loss": 1.1226,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1937541961669922,
+      "eval_runtime": 46.2571,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 306
+    },
+    {
+      "epoch": 1.0130718954248366,
+      "grad_norm": 0.26494982838630676,
+      "learning_rate": 0.0002,
+      "loss": 1.2011,
+      "step": 310
+    },
+    {
+      "epoch": 1.0457516339869282,
+      "grad_norm": 0.6289355754852295,
+      "learning_rate": 0.0002,
+      "loss": 1.0565,
+      "step": 320
+    },
+    {
+      "epoch": 1.0784313725490196,
+      "grad_norm": 0.26784011721611023,
+      "learning_rate": 0.0002,
+      "loss": 1.1619,
+      "step": 330
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.3392215967178345,
+      "learning_rate": 0.0002,
+      "loss": 1.1151,
+      "step": 340
+    },
+    {
+      "epoch": 1.1437908496732025,
+      "grad_norm": 0.40005937218666077,
+      "learning_rate": 0.0002,
+      "loss": 1.0752,
+      "step": 350
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.3590582013130188,
+      "learning_rate": 0.0002,
+      "loss": 1.0408,
+      "step": 360
+    },
+    {
+      "epoch": 1.2091503267973855,
+      "grad_norm": 0.3995305895805359,
+      "learning_rate": 0.0002,
+      "loss": 1.0836,
+      "step": 370
+    },
+    {
+      "epoch": 1.2418300653594772,
+      "grad_norm": 0.2950291633605957,
+      "learning_rate": 0.0002,
+      "loss": 1.0992,
+      "step": 380
+    },
+    {
+      "epoch": 1.2745098039215685,
+      "grad_norm": 0.32035166025161743,
+      "learning_rate": 0.0002,
+      "loss": 1.1152,
+      "step": 390
+    },
+    {
+      "epoch": 1.3071895424836601,
+      "grad_norm": 0.410366415977478,
+      "learning_rate": 0.0002,
+      "loss": 1.1467,
+      "step": 400
+    },
+    {
+      "epoch": 1.3398692810457518,
+      "grad_norm": 0.3106379508972168,
+      "learning_rate": 0.0002,
+      "loss": 0.9985,
+      "step": 410
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 0.38580670952796936,
+      "learning_rate": 0.0002,
+      "loss": 0.9789,
+      "step": 420
+    },
+    {
+      "epoch": 1.4052287581699345,
+      "grad_norm": 0.34411361813545227,
+      "learning_rate": 0.0002,
+      "loss": 1.0931,
+      "step": 430
+    },
+    {
+      "epoch": 1.4379084967320261,
+      "grad_norm": 0.44206851720809937,
+      "learning_rate": 0.0002,
+      "loss": 1.1685,
+      "step": 440
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.3492952585220337,
+      "learning_rate": 0.0002,
+      "loss": 1.0347,
+      "step": 450
+    },
+    {
+      "epoch": 1.5032679738562091,
+      "grad_norm": 0.376423716545105,
+      "learning_rate": 0.0002,
+      "loss": 1.0534,
+      "step": 460
+    },
+    {
+      "epoch": 1.5359477124183005,
+      "grad_norm": 0.359757661819458,
+      "learning_rate": 0.0002,
+      "loss": 1.1162,
+      "step": 470
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 0.3385067880153656,
+      "learning_rate": 0.0002,
+      "loss": 0.9586,
+      "step": 480
+    },
+    {
+      "epoch": 1.6013071895424837,
+      "grad_norm": 0.4943889379501343,
+      "learning_rate": 0.0002,
+      "loss": 1.0807,
+      "step": 490
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 0.4203241169452667,
+      "learning_rate": 0.0002,
+      "loss": 1.0796,
+      "step": 500
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.3093789219856262,
+      "learning_rate": 0.0002,
+      "loss": 1.1059,
+      "step": 510
+    },
+    {
+      "epoch": 1.6993464052287581,
+      "grad_norm": 0.3653067350387573,
+      "learning_rate": 0.0002,
+      "loss": 1.0323,
+      "step": 520
+    },
+    {
+      "epoch": 1.7320261437908497,
+      "grad_norm": 0.36761337518692017,
+      "learning_rate": 0.0002,
+      "loss": 1.0885,
+      "step": 530
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.5040399432182312,
+      "learning_rate": 0.0002,
+      "loss": 1.1698,
+      "step": 540
+    },
+    {
+      "epoch": 1.7973856209150327,
+      "grad_norm": 0.3818035125732422,
+      "learning_rate": 0.0002,
+      "loss": 1.0105,
+      "step": 550
+    },
+    {
+      "epoch": 1.8300653594771243,
+      "grad_norm": 0.4021618664264679,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 560
+    },
+    {
+      "epoch": 1.8627450980392157,
+      "grad_norm": 0.3986459970474243,
+      "learning_rate": 0.0002,
+      "loss": 1.0358,
+      "step": 570
+    },
+    {
+      "epoch": 1.8954248366013071,
+      "grad_norm": 0.48416733741760254,
+      "learning_rate": 0.0002,
+      "loss": 1.003,
+      "step": 580
+    },
+    {
+      "epoch": 1.9281045751633987,
+      "grad_norm": 0.36853986978530884,
+      "learning_rate": 0.0002,
+      "loss": 1.1146,
+      "step": 590
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.383022665977478,
+      "learning_rate": 0.0002,
+      "loss": 1.0689,
+      "step": 600
+    },
+    {
+      "epoch": 1.9934640522875817,
+      "grad_norm": 0.3169507086277008,
+      "learning_rate": 0.0002,
+      "loss": 1.098,
+      "step": 610
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1845070123672485,
+      "eval_runtime": 46.2811,
+      "eval_samples_per_second": 9.421,
+      "eval_steps_per_second": 1.188,
+      "step": 612
+    },
+    {
+      "epoch": 2.026143790849673,
+      "grad_norm": 0.8920142650604248,
+      "learning_rate": 0.0002,
+      "loss": 0.9618,
+      "step": 620
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.4814859628677368,
+      "learning_rate": 0.0002,
+      "loss": 0.9784,
+      "step": 630
+    },
+    {
+      "epoch": 2.0915032679738563,
+      "grad_norm": 0.4251559376716614,
+      "learning_rate": 0.0002,
+      "loss": 0.8464,
+      "step": 640
+    },
+    {
+      "epoch": 2.1241830065359477,
+      "grad_norm": 0.5295765399932861,
+      "learning_rate": 0.0002,
+      "loss": 0.932,
+      "step": 650
+    },
+    {
+      "epoch": 2.156862745098039,
+      "grad_norm": 0.45016610622406006,
+      "learning_rate": 0.0002,
+      "loss": 0.9603,
+      "step": 660
+    },
+    {
+      "epoch": 2.189542483660131,
+      "grad_norm": 0.5870586633682251,
+      "learning_rate": 0.0002,
+      "loss": 0.8738,
+      "step": 670
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.5174715518951416,
+      "learning_rate": 0.0002,
+      "loss": 0.9483,
+      "step": 680
+    },
+    {
+      "epoch": 2.2549019607843137,
+      "grad_norm": 0.5252485275268555,
+      "learning_rate": 0.0002,
+      "loss": 0.9551,
+      "step": 690
+    },
+    {
+      "epoch": 2.287581699346405,
+      "grad_norm": 0.5158312320709229,
+      "learning_rate": 0.0002,
+      "loss": 0.9253,
+      "step": 700
+    },
+    {
+      "epoch": 2.3202614379084965,
+      "grad_norm": 0.4824209213256836,
+      "learning_rate": 0.0002,
+      "loss": 0.9278,
+      "step": 710
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.6335175037384033,
+      "learning_rate": 0.0002,
+      "loss": 0.8804,
+      "step": 720
+    },
+    {
+      "epoch": 2.3856209150326797,
+      "grad_norm": 0.5240563154220581,
+      "learning_rate": 0.0002,
+      "loss": 0.9685,
+      "step": 730
+    },
+    {
+      "epoch": 2.418300653594771,
+      "grad_norm": 0.5172886252403259,
+      "learning_rate": 0.0002,
+      "loss": 0.8794,
+      "step": 740
+    },
+    {
+      "epoch": 2.450980392156863,
+      "grad_norm": 0.48972561955451965,
+      "learning_rate": 0.0002,
+      "loss": 0.8158,
+      "step": 750
+    },
+    {
+      "epoch": 2.4836601307189543,
+      "grad_norm": 0.5295189023017883,
+      "learning_rate": 0.0002,
+      "loss": 0.8766,
+      "step": 760
+    },
+    {
+      "epoch": 2.5163398692810457,
+      "grad_norm": 0.5487208962440491,
+      "learning_rate": 0.0002,
+      "loss": 0.8695,
+      "step": 770
+    },
+    {
+      "epoch": 2.549019607843137,
+      "grad_norm": 0.5375093221664429,
+      "learning_rate": 0.0002,
+      "loss": 1.0109,
+      "step": 780
+    },
+    {
+      "epoch": 2.581699346405229,
+      "grad_norm": 0.5424453020095825,
+      "learning_rate": 0.0002,
+      "loss": 0.9244,
+      "step": 790
+    },
+    {
+      "epoch": 2.6143790849673203,
+      "grad_norm": 0.6029134392738342,
+      "learning_rate": 0.0002,
+      "loss": 1.0424,
+      "step": 800
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.6584921479225159,
+      "learning_rate": 0.0002,
+      "loss": 0.8688,
+      "step": 810
+    },
+    {
+      "epoch": 2.6797385620915035,
+      "grad_norm": 0.5735557675361633,
+      "learning_rate": 0.0002,
+      "loss": 0.7796,
+      "step": 820
+    },
+    {
+      "epoch": 2.712418300653595,
+      "grad_norm": 0.5216763019561768,
+      "learning_rate": 0.0002,
+      "loss": 0.8834,
+      "step": 830
+    },
+    {
+      "epoch": 2.7450980392156863,
+      "grad_norm": 0.5455219149589539,
+      "learning_rate": 0.0002,
+      "loss": 0.8946,
+      "step": 840
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.5139284729957581,
+      "learning_rate": 0.0002,
+      "loss": 0.8037,
+      "step": 850
+    },
+    {
+      "epoch": 2.810457516339869,
+      "grad_norm": 0.5096403360366821,
+      "learning_rate": 0.0002,
+      "loss": 0.988,
+      "step": 860
+    },
+    {
+      "epoch": 2.843137254901961,
+      "grad_norm": 0.6337038278579712,
+      "learning_rate": 0.0002,
+      "loss": 0.9169,
+      "step": 870
+    },
+    {
+      "epoch": 2.8758169934640523,
+      "grad_norm": 0.47218772768974304,
+      "learning_rate": 0.0002,
+      "loss": 0.8938,
+      "step": 880
+    },
+    {
+      "epoch": 2.9084967320261437,
+      "grad_norm": 0.4640636742115021,
+      "learning_rate": 0.0002,
+      "loss": 0.8554,
+      "step": 890
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.4199628531932831,
+      "learning_rate": 0.0002,
+      "loss": 0.8625,
+      "step": 900
+    },
+    {
+      "epoch": 2.973856209150327,
+      "grad_norm": 0.5067117214202881,
+      "learning_rate": 0.0002,
+      "loss": 0.8104,
+      "step": 910
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2291251420974731,
+      "eval_runtime": 46.2557,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 918
+    },
+    {
+      "epoch": 3.0065359477124183,
+      "grad_norm": 0.8342176079750061,
+      "learning_rate": 0.0002,
+      "loss": 0.8157,
+      "step": 920
+    },
+    {
+      "epoch": 3.0392156862745097,
+      "grad_norm": 0.7695813775062561,
+      "learning_rate": 0.0002,
+      "loss": 0.6855,
+      "step": 930
+    },
+    {
+      "epoch": 3.0718954248366015,
+      "grad_norm": 0.6819486618041992,
+      "learning_rate": 0.0002,
+      "loss": 0.6173,
+      "step": 940
+    },
+    {
+      "epoch": 3.104575163398693,
+      "grad_norm": 0.7568879723548889,
+      "learning_rate": 0.0002,
+      "loss": 0.6495,
+      "step": 950
+    },
+    {
+      "epoch": 3.1372549019607843,
+      "grad_norm": 0.6760695576667786,
+      "learning_rate": 0.0002,
+      "loss": 0.7905,
+      "step": 960
+    },
+    {
+      "epoch": 3.1699346405228757,
+      "grad_norm": 0.6359127759933472,
+      "learning_rate": 0.0002,
+      "loss": 0.6405,
+      "step": 970
+    },
+    {
+      "epoch": 3.2026143790849675,
+      "grad_norm": 0.8414971828460693,
+      "learning_rate": 0.0002,
+      "loss": 0.7172,
+      "step": 980
+    },
+    {
+      "epoch": 3.235294117647059,
+      "grad_norm": 0.68381667137146,
+      "learning_rate": 0.0002,
+      "loss": 0.7865,
+      "step": 990
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 0.6852193474769592,
+      "learning_rate": 0.0002,
+      "loss": 0.6651,
+      "step": 1000
+    },
+    {
+      "epoch": 3.3006535947712417,
+      "grad_norm": 0.8184967041015625,
+      "learning_rate": 0.0002,
+      "loss": 0.6571,
+      "step": 1010
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.047290563583374,
+      "learning_rate": 0.0002,
+      "loss": 0.7036,
+      "step": 1020
+    },
+    {
+      "epoch": 3.366013071895425,
+      "grad_norm": 0.8291178345680237,
+      "learning_rate": 0.0002,
+      "loss": 0.7215,
+      "step": 1030
+    },
+    {
+      "epoch": 3.3986928104575163,
+      "grad_norm": 0.6668022871017456,
+      "learning_rate": 0.0002,
+      "loss": 0.6243,
+      "step": 1040
+    },
+    {
+      "epoch": 3.431372549019608,
+      "grad_norm": 0.6354008316993713,
+      "learning_rate": 0.0002,
+      "loss": 0.7459,
+      "step": 1050
+    },
+    {
+      "epoch": 3.4640522875816995,
+      "grad_norm": 1.2028366327285767,
+      "learning_rate": 0.0002,
+      "loss": 0.6826,
+      "step": 1060
+    },
+    {
+      "epoch": 3.496732026143791,
+      "grad_norm": 0.717367947101593,
+      "learning_rate": 0.0002,
+      "loss": 0.5913,
+      "step": 1070
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 0.542179524898529,
+      "learning_rate": 0.0002,
+      "loss": 0.6903,
+      "step": 1080
+    },
+    {
+      "epoch": 3.5620915032679736,
+      "grad_norm": 0.845981776714325,
+      "learning_rate": 0.0002,
+      "loss": 0.7673,
+      "step": 1090
+    },
+    {
+      "epoch": 3.5947712418300655,
+      "grad_norm": 0.7381046414375305,
+      "learning_rate": 0.0002,
+      "loss": 0.7089,
+      "step": 1100
+    },
+    {
+      "epoch": 3.627450980392157,
+      "grad_norm": 0.6563456058502197,
+      "learning_rate": 0.0002,
+      "loss": 0.6705,
+      "step": 1110
+    },
+    {
+      "epoch": 3.6601307189542482,
+      "grad_norm": 0.7130876779556274,
+      "learning_rate": 0.0002,
+      "loss": 0.7767,
+      "step": 1120
+    },
+    {
+      "epoch": 3.69281045751634,
+      "grad_norm": 0.800032913684845,
+      "learning_rate": 0.0002,
+      "loss": 0.7164,
+      "step": 1130
+    },
+    {
+      "epoch": 3.7254901960784315,
+      "grad_norm": 0.980328381061554,
+      "learning_rate": 0.0002,
+      "loss": 0.7272,
+      "step": 1140
+    },
+    {
+      "epoch": 3.758169934640523,
+      "grad_norm": 0.8542261123657227,
+      "learning_rate": 0.0002,
+      "loss": 0.7672,
+      "step": 1150
+    },
+    {
+      "epoch": 3.7908496732026142,
+      "grad_norm": 0.6302552819252014,
+      "learning_rate": 0.0002,
+      "loss": 0.679,
+      "step": 1160
+    },
+    {
+      "epoch": 3.8235294117647056,
+      "grad_norm": 0.515398383140564,
+      "learning_rate": 0.0002,
+      "loss": 0.7457,
+      "step": 1170
+    },
+    {
+      "epoch": 3.8562091503267975,
+      "grad_norm": 1.2427130937576294,
+      "learning_rate": 0.0002,
+      "loss": 0.693,
+      "step": 1180
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.8206831216812134,
+      "learning_rate": 0.0002,
+      "loss": 0.7182,
+      "step": 1190
+    },
+    {
+      "epoch": 3.9215686274509802,
+      "grad_norm": 0.7633249163627625,
+      "learning_rate": 0.0002,
+      "loss": 0.7519,
+      "step": 1200
+    },
+    {
+      "epoch": 3.954248366013072,
+      "grad_norm": 0.8034512400627136,
+      "learning_rate": 0.0002,
+      "loss": 0.7082,
+      "step": 1210
+    },
+    {
+      "epoch": 3.9869281045751634,
+      "grad_norm": 0.7667182087898254,
+      "learning_rate": 0.0002,
+      "loss": 0.6834,
+      "step": 1220
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.3456707000732422,
+      "eval_runtime": 46.2562,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 1224
+    },
+    {
+      "epoch": 4.019607843137255,
+      "grad_norm": 0.7724746465682983,
+      "learning_rate": 0.0002,
+      "loss": 0.582,
+      "step": 1230
+    },
+    {
+      "epoch": 4.052287581699346,
+      "grad_norm": 1.166916847229004,
+      "learning_rate": 0.0002,
+      "loss": 0.4759,
+      "step": 1240
+    },
+    {
+      "epoch": 4.084967320261438,
+      "grad_norm": 0.7234508991241455,
+      "learning_rate": 0.0002,
+      "loss": 0.4995,
+      "step": 1250
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 1.1418060064315796,
+      "learning_rate": 0.0002,
+      "loss": 0.4863,
+      "step": 1260
+    },
+    {
+      "epoch": 4.150326797385621,
+      "grad_norm": 0.9603922367095947,
+      "learning_rate": 0.0002,
+      "loss": 0.5425,
+      "step": 1270
+    },
+    {
+      "epoch": 4.183006535947713,
+      "grad_norm": 0.8976530432701111,
+      "learning_rate": 0.0002,
+      "loss": 0.4892,
+      "step": 1280
+    },
+    {
+      "epoch": 4.215686274509804,
+      "grad_norm": 0.6855078339576721,
+      "learning_rate": 0.0002,
+      "loss": 0.473,
+      "step": 1290
+    },
+    {
+      "epoch": 4.248366013071895,
+      "grad_norm": 1.2676647901535034,
+      "learning_rate": 0.0002,
+      "loss": 0.4416,
+      "step": 1300
+    },
+    {
+      "epoch": 4.281045751633987,
+      "grad_norm": 1.104057788848877,
+      "learning_rate": 0.0002,
+      "loss": 0.5071,
+      "step": 1310
+    },
+    {
+      "epoch": 4.313725490196078,
+      "grad_norm": 1.7076562643051147,
+      "learning_rate": 0.0002,
+      "loss": 0.5168,
+      "step": 1320
+    },
+    {
+      "epoch": 4.34640522875817,
+      "grad_norm": 1.2308520078659058,
+      "learning_rate": 0.0002,
+      "loss": 0.4655,
+      "step": 1330
+    },
+    {
+      "epoch": 4.379084967320262,
+      "grad_norm": 1.2652729749679565,
+      "learning_rate": 0.0002,
+      "loss": 0.5322,
+      "step": 1340
+    },
+    {
+      "epoch": 4.411764705882353,
+      "grad_norm": 1.054958701133728,
+      "learning_rate": 0.0002,
+      "loss": 0.5262,
+      "step": 1350
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 1.0130749940872192,
+      "learning_rate": 0.0002,
+      "loss": 0.4747,
+      "step": 1360
+    },
+    {
+      "epoch": 4.477124183006536,
+      "grad_norm": 1.0517818927764893,
+      "learning_rate": 0.0002,
+      "loss": 0.4887,
+      "step": 1370
+    },
+    {
+      "epoch": 4.509803921568627,
+      "grad_norm": 0.8593037128448486,
+      "learning_rate": 0.0002,
+      "loss": 0.4906,
+      "step": 1380
+    },
+    {
+      "epoch": 4.542483660130719,
+      "grad_norm": 1.0248081684112549,
+      "learning_rate": 0.0002,
+      "loss": 0.5049,
+      "step": 1390
+    },
+    {
+      "epoch": 4.57516339869281,
+      "grad_norm": 0.8999413847923279,
+      "learning_rate": 0.0002,
+      "loss": 0.472,
+      "step": 1400
+    },
+    {
+      "epoch": 4.607843137254902,
+      "grad_norm": 0.9106912612915039,
+      "learning_rate": 0.0002,
+      "loss": 0.5102,
+      "step": 1410
+    },
+    {
+      "epoch": 4.640522875816993,
+      "grad_norm": 1.2736181020736694,
+      "learning_rate": 0.0002,
+      "loss": 0.5203,
+      "step": 1420
+    },
+    {
+      "epoch": 4.673202614379085,
+      "grad_norm": 0.9311690926551819,
+      "learning_rate": 0.0002,
+      "loss": 0.5101,
+      "step": 1430
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 1.0455045700073242,
+      "learning_rate": 0.0002,
+      "loss": 0.5648,
+      "step": 1440
+    },
+    {
+      "epoch": 4.738562091503268,
+      "grad_norm": 1.0190727710723877,
+      "learning_rate": 0.0002,
+      "loss": 0.5004,
+      "step": 1450
+    },
+    {
+      "epoch": 4.771241830065359,
+      "grad_norm": 1.333198070526123,
+      "learning_rate": 0.0002,
+      "loss": 0.5506,
+      "step": 1460
+    },
+    {
+      "epoch": 4.803921568627451,
+      "grad_norm": 0.8808416724205017,
+      "learning_rate": 0.0002,
+      "loss": 0.5846,
+      "step": 1470
+    },
+    {
+      "epoch": 4.836601307189542,
+      "grad_norm": 0.8896227478981018,
+      "learning_rate": 0.0002,
+      "loss": 0.4671,
+      "step": 1480
+    },
+    {
+      "epoch": 4.8692810457516345,
+      "grad_norm": 1.212323784828186,
+      "learning_rate": 0.0002,
+      "loss": 0.4732,
+      "step": 1490
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 1.0490120649337769,
+      "learning_rate": 0.0002,
+      "loss": 0.5263,
+      "step": 1500
+    },
+    {
+      "epoch": 4.934640522875817,
+      "grad_norm": 0.8946618437767029,
+      "learning_rate": 0.0002,
+      "loss": 0.5815,
+      "step": 1510
+    },
+    {
+      "epoch": 4.967320261437909,
+      "grad_norm": 1.0609275102615356,
+      "learning_rate": 0.0002,
+      "loss": 0.5369,
+      "step": 1520
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.8885099291801453,
+      "learning_rate": 0.0002,
+      "loss": 0.5348,
+      "step": 1530
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.5771757364273071,
+      "eval_runtime": 46.2667,
+      "eval_samples_per_second": 9.424,
+      "eval_steps_per_second": 1.189,
+      "step": 1530
+    },
+    {
+      "epoch": 5.032679738562091,
+      "grad_norm": 1.401705026626587,
+      "learning_rate": 0.0002,
+      "loss": 0.3176,
+      "step": 1540
+    },
+    {
+      "epoch": 5.065359477124183,
+      "grad_norm": 0.8365539908409119,
+      "learning_rate": 0.0002,
+      "loss": 0.3346,
+      "step": 1550
+    },
+    {
+      "epoch": 5.098039215686274,
+      "grad_norm": 1.3188321590423584,
+      "learning_rate": 0.0002,
+      "loss": 0.3605,
+      "step": 1560
+    },
+    {
+      "epoch": 5.130718954248366,
+      "grad_norm": 0.9819526076316833,
+      "learning_rate": 0.0002,
+      "loss": 0.326,
+      "step": 1570
+    },
+    {
+      "epoch": 5.163398692810458,
+      "grad_norm": 1.13265061378479,
+      "learning_rate": 0.0002,
+      "loss": 0.3575,
+      "step": 1580
+    },
+    {
+      "epoch": 5.196078431372549,
+      "grad_norm": 1.478152871131897,
+      "learning_rate": 0.0002,
+      "loss": 0.3418,
+      "step": 1590
+    },
+    {
+      "epoch": 5.228758169934641,
+      "grad_norm": 1.4188750982284546,
+      "learning_rate": 0.0002,
+      "loss": 0.3388,
+      "step": 1600
+    },
+    {
+      "epoch": 5.261437908496732,
+      "grad_norm": 1.2499338388442993,
+      "learning_rate": 0.0002,
+      "loss": 0.3524,
+      "step": 1610
+    },
+    {
+      "epoch": 5.294117647058823,
+      "grad_norm": 1.7885085344314575,
+      "learning_rate": 0.0002,
+      "loss": 0.423,
+      "step": 1620
+    },
+    {
+      "epoch": 5.326797385620915,
+      "grad_norm": 1.2614946365356445,
+      "learning_rate": 0.0002,
+      "loss": 0.3237,
+      "step": 1630
+    },
+    {
+      "epoch": 5.359477124183006,
+      "grad_norm": 1.28338623046875,
+      "learning_rate": 0.0002,
+      "loss": 0.3511,
+      "step": 1640
+    },
+    {
+      "epoch": 5.392156862745098,
+      "grad_norm": 1.1973257064819336,
+      "learning_rate": 0.0002,
+      "loss": 0.3112,
+      "step": 1650
+    },
+    {
+      "epoch": 5.42483660130719,
+      "grad_norm": 1.1356301307678223,
+      "learning_rate": 0.0002,
+      "loss": 0.3645,
+      "step": 1660
+    },
+    {
+      "epoch": 5.457516339869281,
+      "grad_norm": 0.9048901200294495,
+      "learning_rate": 0.0002,
+      "loss": 0.307,
+      "step": 1670
+    },
+    {
+      "epoch": 5.490196078431373,
+      "grad_norm": 1.5352122783660889,
+      "learning_rate": 0.0002,
+      "loss": 0.3828,
+      "step": 1680
+    },
+    {
+      "epoch": 5.522875816993464,
+      "grad_norm": 0.9096335172653198,
+      "learning_rate": 0.0002,
+      "loss": 0.3826,
+      "step": 1690
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 1.1903661489486694,
+      "learning_rate": 0.0002,
+      "loss": 0.3686,
+      "step": 1700
+    },
+    {
+      "epoch": 5.588235294117647,
+      "grad_norm": 0.9234451651573181,
+      "learning_rate": 0.0002,
+      "loss": 0.325,
+      "step": 1710
+    },
+    {
+      "epoch": 5.620915032679738,
+      "grad_norm": 1.4554102420806885,
+      "learning_rate": 0.0002,
+      "loss": 0.3451,
+      "step": 1720
+    },
+    {
+      "epoch": 5.65359477124183,
+      "grad_norm": 1.1044343709945679,
+      "learning_rate": 0.0002,
+      "loss": 0.3488,
+      "step": 1730
+    },
+    {
+      "epoch": 5.686274509803922,
+      "grad_norm": 1.2219593524932861,
+      "learning_rate": 0.0002,
+      "loss": 0.3673,
+      "step": 1740
+    },
+    {
+      "epoch": 5.718954248366013,
+      "grad_norm": 0.901652455329895,
+      "learning_rate": 0.0002,
+      "loss": 0.3517,
+      "step": 1750
+    },
+    {
+      "epoch": 5.751633986928105,
+      "grad_norm": 1.3334792852401733,
+      "learning_rate": 0.0002,
+      "loss": 0.4082,
+      "step": 1760
+    },
+    {
+      "epoch": 5.784313725490196,
+      "grad_norm": 1.5595488548278809,
+      "learning_rate": 0.0002,
+      "loss": 0.4386,
+      "step": 1770
+    },
+    {
+      "epoch": 5.816993464052287,
+      "grad_norm": 1.3892982006072998,
+      "learning_rate": 0.0002,
+      "loss": 0.3217,
+      "step": 1780
+    },
+    {
+      "epoch": 5.849673202614379,
+      "grad_norm": 1.0813168287277222,
+      "learning_rate": 0.0002,
+      "loss": 0.3919,
+      "step": 1790
+    },
+    {
+      "epoch": 5.882352941176471,
+      "grad_norm": 1.145320177078247,
+      "learning_rate": 0.0002,
+      "loss": 0.3697,
+      "step": 1800
+    },
+    {
+      "epoch": 5.915032679738562,
+      "grad_norm": 1.0249533653259277,
+      "learning_rate": 0.0002,
+      "loss": 0.3903,
+      "step": 1810
+    },
+    {
+      "epoch": 5.947712418300654,
+      "grad_norm": 1.0013737678527832,
+      "learning_rate": 0.0002,
+      "loss": 0.3481,
+      "step": 1820
+    },
+    {
+      "epoch": 5.980392156862745,
+      "grad_norm": 1.212314248085022,
+      "learning_rate": 0.0002,
+      "loss": 0.4278,
+      "step": 1830
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.7506128549575806,
+      "eval_runtime": 46.2256,
+      "eval_samples_per_second": 9.432,
+      "eval_steps_per_second": 1.19,
+      "step": 1836
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2448,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.430383697330176e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/training_args.bin b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e7fb8100bbfe18f1342e5fc87e32e8e798268e3b
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-1836/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e66621362aa4eab196083c9a4bd0bf843b2425d7109d63be3ab5f4006691dd1
+size 5560
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/README.md b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/adapter_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/adapter_model.safetensors b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1b28480ca5bc1eb127b32f93614305c2d230e0c4
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb5d75fa0f4f847a671f69184c2db23aadddf2ac7a9e25d1927d28c18184fc0f
+size 143153376
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/optimizer.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a2356b6b396fd50110a3fe45259a25171362b9e5
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8933331a45aeef95820a6919adf16536e1dbfb652c7fd8fc9e3a18fcf3d6b3d9
+size 72886650
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/rng_state.pth b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4854e975285843f95823759082b059363306ea06
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4165bc80df0386ed9547456c19949971870693610e838f12639743e2ae1879cb
+size 14244
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/scheduler.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..32cd31dfe25a652f2c346bdbb5c184bbf176f834
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d4c1af6bb74978251e7ec248a24d78e754f8d197292882e924d78e8e37d749
+size 1064
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/special_tokens_map.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/special_tokens_map.json
@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/tokenizer.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/tokenizer.model b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/tokenizer_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/tokenizer_config.json
@@ -0,0 +1,2013 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/trainer_state.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..36534ef8be2aff94238a2e5f7d0ca2e3fc2ebb94
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/trainer_state.json
@@ -0,0 +1,1587 @@
+{
+  "best_metric": 1.1845070123672485,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612",
+  "epoch": 7.0,
+  "eval_steps": 10,
+  "global_step": 2142,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032679738562091505,
+      "grad_norm": 0.631856381893158,
+      "learning_rate": 0.0002,
+      "loss": 2.3561,
+      "step": 10
+    },
+    {
+      "epoch": 0.06535947712418301,
+      "grad_norm": 0.5065668821334839,
+      "learning_rate": 0.0002,
+      "loss": 1.8141,
+      "step": 20
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 0.6978895664215088,
+      "learning_rate": 0.0002,
+      "loss": 1.4952,
+      "step": 30
+    },
+    {
+      "epoch": 0.13071895424836602,
+      "grad_norm": 0.6619144082069397,
+      "learning_rate": 0.0002,
+      "loss": 1.4829,
+      "step": 40
+    },
+    {
+      "epoch": 0.16339869281045752,
+      "grad_norm": 0.6153793931007385,
+      "learning_rate": 0.0002,
+      "loss": 1.3038,
+      "step": 50
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.4703301787376404,
+      "learning_rate": 0.0002,
+      "loss": 1.1429,
+      "step": 60
+    },
+    {
+      "epoch": 0.22875816993464052,
+      "grad_norm": 1.1672580242156982,
+      "learning_rate": 0.0002,
+      "loss": 1.2828,
+      "step": 70
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 0.3455565273761749,
+      "learning_rate": 0.0002,
+      "loss": 1.0985,
+      "step": 80
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.36216291785240173,
+      "learning_rate": 0.0002,
+      "loss": 1.1359,
+      "step": 90
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "grad_norm": 0.4545166492462158,
+      "learning_rate": 0.0002,
+      "loss": 1.2544,
+      "step": 100
+    },
+    {
+      "epoch": 0.35947712418300654,
+      "grad_norm": 0.3612092435359955,
+      "learning_rate": 0.0002,
+      "loss": 1.2287,
+      "step": 110
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.5080830454826355,
+      "learning_rate": 0.0002,
+      "loss": 1.1868,
+      "step": 120
+    },
+    {
+      "epoch": 0.42483660130718953,
+      "grad_norm": 0.3268195390701294,
+      "learning_rate": 0.0002,
+      "loss": 1.1902,
+      "step": 130
+    },
+    {
+      "epoch": 0.45751633986928103,
+      "grad_norm": 0.33971714973449707,
+      "learning_rate": 0.0002,
+      "loss": 1.247,
+      "step": 140
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 0.4036043882369995,
+      "learning_rate": 0.0002,
+      "loss": 1.1844,
+      "step": 150
+    },
+    {
+      "epoch": 0.5228758169934641,
+      "grad_norm": 0.35938864946365356,
+      "learning_rate": 0.0002,
+      "loss": 1.1624,
+      "step": 160
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.28880223631858826,
+      "learning_rate": 0.0002,
+      "loss": 1.164,
+      "step": 170
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.3436269462108612,
+      "learning_rate": 0.0002,
+      "loss": 1.3521,
+      "step": 180
+    },
+    {
+      "epoch": 0.6209150326797386,
+      "grad_norm": 0.41923725605010986,
+      "learning_rate": 0.0002,
+      "loss": 1.2456,
+      "step": 190
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "grad_norm": 0.25119203329086304,
+      "learning_rate": 0.0002,
+      "loss": 1.2226,
+      "step": 200
+    },
+    {
+      "epoch": 0.6862745098039216,
+      "grad_norm": 0.5870180726051331,
+      "learning_rate": 0.0002,
+      "loss": 1.1568,
+      "step": 210
+    },
+    {
+      "epoch": 0.7189542483660131,
+      "grad_norm": 0.2831224203109741,
+      "learning_rate": 0.0002,
+      "loss": 1.064,
+      "step": 220
+    },
+    {
+      "epoch": 0.7516339869281046,
+      "grad_norm": 0.3192005753517151,
+      "learning_rate": 0.0002,
+      "loss": 1.2469,
+      "step": 230
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.2998219430446625,
+      "learning_rate": 0.0002,
+      "loss": 1.1613,
+      "step": 240
+    },
+    {
+      "epoch": 0.8169934640522876,
+      "grad_norm": 0.32855790853500366,
+      "learning_rate": 0.0002,
+      "loss": 1.205,
+      "step": 250
+    },
+    {
+      "epoch": 0.8496732026143791,
+      "grad_norm": 0.3403124213218689,
+      "learning_rate": 0.0002,
+      "loss": 1.1631,
+      "step": 260
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.277401328086853,
+      "learning_rate": 0.0002,
+      "loss": 1.1646,
+      "step": 270
+    },
+    {
+      "epoch": 0.9150326797385621,
+      "grad_norm": 0.2975269556045532,
+      "learning_rate": 0.0002,
+      "loss": 1.084,
+      "step": 280
+    },
+    {
+      "epoch": 0.9477124183006536,
+      "grad_norm": 1.7909578084945679,
+      "learning_rate": 0.0002,
+      "loss": 1.2039,
+      "step": 290
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 0.2917245328426361,
+      "learning_rate": 0.0002,
+      "loss": 1.1226,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1937541961669922,
+      "eval_runtime": 46.2571,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 306
+    },
+    {
+      "epoch": 1.0130718954248366,
+      "grad_norm": 0.26494982838630676,
+      "learning_rate": 0.0002,
+      "loss": 1.2011,
+      "step": 310
+    },
+    {
+      "epoch": 1.0457516339869282,
+      "grad_norm": 0.6289355754852295,
+      "learning_rate": 0.0002,
+      "loss": 1.0565,
+      "step": 320
+    },
+    {
+      "epoch": 1.0784313725490196,
+      "grad_norm": 0.26784011721611023,
+      "learning_rate": 0.0002,
+      "loss": 1.1619,
+      "step": 330
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.3392215967178345,
+      "learning_rate": 0.0002,
+      "loss": 1.1151,
+      "step": 340
+    },
+    {
+      "epoch": 1.1437908496732025,
+      "grad_norm": 0.40005937218666077,
+      "learning_rate": 0.0002,
+      "loss": 1.0752,
+      "step": 350
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.3590582013130188,
+      "learning_rate": 0.0002,
+      "loss": 1.0408,
+      "step": 360
+    },
+    {
+      "epoch": 1.2091503267973855,
+      "grad_norm": 0.3995305895805359,
+      "learning_rate": 0.0002,
+      "loss": 1.0836,
+      "step": 370
+    },
+    {
+      "epoch": 1.2418300653594772,
+      "grad_norm": 0.2950291633605957,
+      "learning_rate": 0.0002,
+      "loss": 1.0992,
+      "step": 380
+    },
+    {
+      "epoch": 1.2745098039215685,
+      "grad_norm": 0.32035166025161743,
+      "learning_rate": 0.0002,
+      "loss": 1.1152,
+      "step": 390
+    },
+    {
+      "epoch": 1.3071895424836601,
+      "grad_norm": 0.410366415977478,
+      "learning_rate": 0.0002,
+      "loss": 1.1467,
+      "step": 400
+    },
+    {
+      "epoch": 1.3398692810457518,
+      "grad_norm": 0.3106379508972168,
+      "learning_rate": 0.0002,
+      "loss": 0.9985,
+      "step": 410
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 0.38580670952796936,
+      "learning_rate": 0.0002,
+      "loss": 0.9789,
+      "step": 420
+    },
+    {
+      "epoch": 1.4052287581699345,
+      "grad_norm": 0.34411361813545227,
+      "learning_rate": 0.0002,
+      "loss": 1.0931,
+      "step": 430
+    },
+    {
+      "epoch": 1.4379084967320261,
+      "grad_norm": 0.44206851720809937,
+      "learning_rate": 0.0002,
+      "loss": 1.1685,
+      "step": 440
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.3492952585220337,
+      "learning_rate": 0.0002,
+      "loss": 1.0347,
+      "step": 450
+    },
+    {
+      "epoch": 1.5032679738562091,
+      "grad_norm": 0.376423716545105,
+      "learning_rate": 0.0002,
+      "loss": 1.0534,
+      "step": 460
+    },
+    {
+      "epoch": 1.5359477124183005,
+      "grad_norm": 0.359757661819458,
+      "learning_rate": 0.0002,
+      "loss": 1.1162,
+      "step": 470
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 0.3385067880153656,
+      "learning_rate": 0.0002,
+      "loss": 0.9586,
+      "step": 480
+    },
+    {
+      "epoch": 1.6013071895424837,
+      "grad_norm": 0.4943889379501343,
+      "learning_rate": 0.0002,
+      "loss": 1.0807,
+      "step": 490
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 0.4203241169452667,
+      "learning_rate": 0.0002,
+      "loss": 1.0796,
+      "step": 500
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.3093789219856262,
+      "learning_rate": 0.0002,
+      "loss": 1.1059,
+      "step": 510
+    },
+    {
+      "epoch": 1.6993464052287581,
+      "grad_norm": 0.3653067350387573,
+      "learning_rate": 0.0002,
+      "loss": 1.0323,
+      "step": 520
+    },
+    {
+      "epoch": 1.7320261437908497,
+      "grad_norm": 0.36761337518692017,
+      "learning_rate": 0.0002,
+      "loss": 1.0885,
+      "step": 530
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.5040399432182312,
+      "learning_rate": 0.0002,
+      "loss": 1.1698,
+      "step": 540
+    },
+    {
+      "epoch": 1.7973856209150327,
+      "grad_norm": 0.3818035125732422,
+      "learning_rate": 0.0002,
+      "loss": 1.0105,
+      "step": 550
+    },
+    {
+      "epoch": 1.8300653594771243,
+      "grad_norm": 0.4021618664264679,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 560
+    },
+    {
+      "epoch": 1.8627450980392157,
+      "grad_norm": 0.3986459970474243,
+      "learning_rate": 0.0002,
+      "loss": 1.0358,
+      "step": 570
+    },
+    {
+      "epoch": 1.8954248366013071,
+      "grad_norm": 0.48416733741760254,
+      "learning_rate": 0.0002,
+      "loss": 1.003,
+      "step": 580
+    },
+    {
+      "epoch": 1.9281045751633987,
+      "grad_norm": 0.36853986978530884,
+      "learning_rate": 0.0002,
+      "loss": 1.1146,
+      "step": 590
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.383022665977478,
+      "learning_rate": 0.0002,
+      "loss": 1.0689,
+      "step": 600
+    },
+    {
+      "epoch": 1.9934640522875817,
+      "grad_norm": 0.3169507086277008,
+      "learning_rate": 0.0002,
+      "loss": 1.098,
+      "step": 610
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1845070123672485,
+      "eval_runtime": 46.2811,
+      "eval_samples_per_second": 9.421,
+      "eval_steps_per_second": 1.188,
+      "step": 612
+    },
+    {
+      "epoch": 2.026143790849673,
+      "grad_norm": 0.8920142650604248,
+      "learning_rate": 0.0002,
+      "loss": 0.9618,
+      "step": 620
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.4814859628677368,
+      "learning_rate": 0.0002,
+      "loss": 0.9784,
+      "step": 630
+    },
+    {
+      "epoch": 2.0915032679738563,
+      "grad_norm": 0.4251559376716614,
+      "learning_rate": 0.0002,
+      "loss": 0.8464,
+      "step": 640
+    },
+    {
+      "epoch": 2.1241830065359477,
+      "grad_norm": 0.5295765399932861,
+      "learning_rate": 0.0002,
+      "loss": 0.932,
+      "step": 650
+    },
+    {
+      "epoch": 2.156862745098039,
+      "grad_norm": 0.45016610622406006,
+      "learning_rate": 0.0002,
+      "loss": 0.9603,
+      "step": 660
+    },
+    {
+      "epoch": 2.189542483660131,
+      "grad_norm": 0.5870586633682251,
+      "learning_rate": 0.0002,
+      "loss": 0.8738,
+      "step": 670
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.5174715518951416,
+      "learning_rate": 0.0002,
+      "loss": 0.9483,
+      "step": 680
+    },
+    {
+      "epoch": 2.2549019607843137,
+      "grad_norm": 0.5252485275268555,
+      "learning_rate": 0.0002,
+      "loss": 0.9551,
+      "step": 690
+    },
+    {
+      "epoch": 2.287581699346405,
+      "grad_norm": 0.5158312320709229,
+      "learning_rate": 0.0002,
+      "loss": 0.9253,
+      "step": 700
+    },
+    {
+      "epoch": 2.3202614379084965,
+      "grad_norm": 0.4824209213256836,
+      "learning_rate": 0.0002,
+      "loss": 0.9278,
+      "step": 710
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.6335175037384033,
+      "learning_rate": 0.0002,
+      "loss": 0.8804,
+      "step": 720
+    },
+    {
+      "epoch": 2.3856209150326797,
+      "grad_norm": 0.5240563154220581,
+      "learning_rate": 0.0002,
+      "loss": 0.9685,
+      "step": 730
+    },
+    {
+      "epoch": 2.418300653594771,
+      "grad_norm": 0.5172886252403259,
+      "learning_rate": 0.0002,
+      "loss": 0.8794,
+      "step": 740
+    },
+    {
+      "epoch": 2.450980392156863,
+      "grad_norm": 0.48972561955451965,
+      "learning_rate": 0.0002,
+      "loss": 0.8158,
+      "step": 750
+    },
+    {
+      "epoch": 2.4836601307189543,
+      "grad_norm": 0.5295189023017883,
+      "learning_rate": 0.0002,
+      "loss": 0.8766,
+      "step": 760
+    },
+    {
+      "epoch": 2.5163398692810457,
+      "grad_norm": 0.5487208962440491,
+      "learning_rate": 0.0002,
+      "loss": 0.8695,
+      "step": 770
+    },
+    {
+      "epoch": 2.549019607843137,
+      "grad_norm": 0.5375093221664429,
+      "learning_rate": 0.0002,
+      "loss": 1.0109,
+      "step": 780
+    },
+    {
+      "epoch": 2.581699346405229,
+      "grad_norm": 0.5424453020095825,
+      "learning_rate": 0.0002,
+      "loss": 0.9244,
+      "step": 790
+    },
+    {
+      "epoch": 2.6143790849673203,
+      "grad_norm": 0.6029134392738342,
+      "learning_rate": 0.0002,
+      "loss": 1.0424,
+      "step": 800
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.6584921479225159,
+      "learning_rate": 0.0002,
+      "loss": 0.8688,
+      "step": 810
+    },
+    {
+      "epoch": 2.6797385620915035,
+      "grad_norm": 0.5735557675361633,
+      "learning_rate": 0.0002,
+      "loss": 0.7796,
+      "step": 820
+    },
+    {
+      "epoch": 2.712418300653595,
+      "grad_norm": 0.5216763019561768,
+      "learning_rate": 0.0002,
+      "loss": 0.8834,
+      "step": 830
+    },
+    {
+      "epoch": 2.7450980392156863,
+      "grad_norm": 0.5455219149589539,
+      "learning_rate": 0.0002,
+      "loss": 0.8946,
+      "step": 840
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.5139284729957581,
+      "learning_rate": 0.0002,
+      "loss": 0.8037,
+      "step": 850
+    },
+    {
+      "epoch": 2.810457516339869,
+      "grad_norm": 0.5096403360366821,
+      "learning_rate": 0.0002,
+      "loss": 0.988,
+      "step": 860
+    },
+    {
+      "epoch": 2.843137254901961,
+      "grad_norm": 0.6337038278579712,
+      "learning_rate": 0.0002,
+      "loss": 0.9169,
+      "step": 870
+    },
+    {
+      "epoch": 2.8758169934640523,
+      "grad_norm": 0.47218772768974304,
+      "learning_rate": 0.0002,
+      "loss": 0.8938,
+      "step": 880
+    },
+    {
+      "epoch": 2.9084967320261437,
+      "grad_norm": 0.4640636742115021,
+      "learning_rate": 0.0002,
+      "loss": 0.8554,
+      "step": 890
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.4199628531932831,
+      "learning_rate": 0.0002,
+      "loss": 0.8625,
+      "step": 900
+    },
+    {
+      "epoch": 2.973856209150327,
+      "grad_norm": 0.5067117214202881,
+      "learning_rate": 0.0002,
+      "loss": 0.8104,
+      "step": 910
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2291251420974731,
+      "eval_runtime": 46.2557,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 918
+    },
+    {
+      "epoch": 3.0065359477124183,
+      "grad_norm": 0.8342176079750061,
+      "learning_rate": 0.0002,
+      "loss": 0.8157,
+      "step": 920
+    },
+    {
+      "epoch": 3.0392156862745097,
+      "grad_norm": 0.7695813775062561,
+      "learning_rate": 0.0002,
+      "loss": 0.6855,
+      "step": 930
+    },
+    {
+      "epoch": 3.0718954248366015,
+      "grad_norm": 0.6819486618041992,
+      "learning_rate": 0.0002,
+      "loss": 0.6173,
+      "step": 940
+    },
+    {
+      "epoch": 3.104575163398693,
+      "grad_norm": 0.7568879723548889,
+      "learning_rate": 0.0002,
+      "loss": 0.6495,
+      "step": 950
+    },
+    {
+      "epoch": 3.1372549019607843,
+      "grad_norm": 0.6760695576667786,
+      "learning_rate": 0.0002,
+      "loss": 0.7905,
+      "step": 960
+    },
+    {
+      "epoch": 3.1699346405228757,
+      "grad_norm": 0.6359127759933472,
+      "learning_rate": 0.0002,
+      "loss": 0.6405,
+      "step": 970
+    },
+    {
+      "epoch": 3.2026143790849675,
+      "grad_norm": 0.8414971828460693,
+      "learning_rate": 0.0002,
+      "loss": 0.7172,
+      "step": 980
+    },
+    {
+      "epoch": 3.235294117647059,
+      "grad_norm": 0.68381667137146,
+      "learning_rate": 0.0002,
+      "loss": 0.7865,
+      "step": 990
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 0.6852193474769592,
+      "learning_rate": 0.0002,
+      "loss": 0.6651,
+      "step": 1000
+    },
+    {
+      "epoch": 3.3006535947712417,
+      "grad_norm": 0.8184967041015625,
+      "learning_rate": 0.0002,
+      "loss": 0.6571,
+      "step": 1010
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.047290563583374,
+      "learning_rate": 0.0002,
+      "loss": 0.7036,
+      "step": 1020
+    },
+    {
+      "epoch": 3.366013071895425,
+      "grad_norm": 0.8291178345680237,
+      "learning_rate": 0.0002,
+      "loss": 0.7215,
+      "step": 1030
+    },
+    {
+      "epoch": 3.3986928104575163,
+      "grad_norm": 0.6668022871017456,
+      "learning_rate": 0.0002,
+      "loss": 0.6243,
+      "step": 1040
+    },
+    {
+      "epoch": 3.431372549019608,
+      "grad_norm": 0.6354008316993713,
+      "learning_rate": 0.0002,
+      "loss": 0.7459,
+      "step": 1050
+    },
+    {
+      "epoch": 3.4640522875816995,
+      "grad_norm": 1.2028366327285767,
+      "learning_rate": 0.0002,
+      "loss": 0.6826,
+      "step": 1060
+    },
+    {
+      "epoch": 3.496732026143791,
+      "grad_norm": 0.717367947101593,
+      "learning_rate": 0.0002,
+      "loss": 0.5913,
+      "step": 1070
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 0.542179524898529,
+      "learning_rate": 0.0002,
+      "loss": 0.6903,
+      "step": 1080
+    },
+    {
+      "epoch": 3.5620915032679736,
+      "grad_norm": 0.845981776714325,
+      "learning_rate": 0.0002,
+      "loss": 0.7673,
+      "step": 1090
+    },
+    {
+      "epoch": 3.5947712418300655,
+      "grad_norm": 0.7381046414375305,
+      "learning_rate": 0.0002,
+      "loss": 0.7089,
+      "step": 1100
+    },
+    {
+      "epoch": 3.627450980392157,
+      "grad_norm": 0.6563456058502197,
+      "learning_rate": 0.0002,
+      "loss": 0.6705,
+      "step": 1110
+    },
+    {
+      "epoch": 3.6601307189542482,
+      "grad_norm": 0.7130876779556274,
+      "learning_rate": 0.0002,
+      "loss": 0.7767,
+      "step": 1120
+    },
+    {
+      "epoch": 3.69281045751634,
+      "grad_norm": 0.800032913684845,
+      "learning_rate": 0.0002,
+      "loss": 0.7164,
+      "step": 1130
+    },
+    {
+      "epoch": 3.7254901960784315,
+      "grad_norm": 0.980328381061554,
+      "learning_rate": 0.0002,
+      "loss": 0.7272,
+      "step": 1140
+    },
+    {
+      "epoch": 3.758169934640523,
+      "grad_norm": 0.8542261123657227,
+      "learning_rate": 0.0002,
+      "loss": 0.7672,
+      "step": 1150
+    },
+    {
+      "epoch": 3.7908496732026142,
+      "grad_norm": 0.6302552819252014,
+      "learning_rate": 0.0002,
+      "loss": 0.679,
+      "step": 1160
+    },
+    {
+      "epoch": 3.8235294117647056,
+      "grad_norm": 0.515398383140564,
+      "learning_rate": 0.0002,
+      "loss": 0.7457,
+      "step": 1170
+    },
+    {
+      "epoch": 3.8562091503267975,
+      "grad_norm": 1.2427130937576294,
+      "learning_rate": 0.0002,
+      "loss": 0.693,
+      "step": 1180
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.8206831216812134,
+      "learning_rate": 0.0002,
+      "loss": 0.7182,
+      "step": 1190
+    },
+    {
+      "epoch": 3.9215686274509802,
+      "grad_norm": 0.7633249163627625,
+      "learning_rate": 0.0002,
+      "loss": 0.7519,
+      "step": 1200
+    },
+    {
+      "epoch": 3.954248366013072,
+      "grad_norm": 0.8034512400627136,
+      "learning_rate": 0.0002,
+      "loss": 0.7082,
+      "step": 1210
+    },
+    {
+      "epoch": 3.9869281045751634,
+      "grad_norm": 0.7667182087898254,
+      "learning_rate": 0.0002,
+      "loss": 0.6834,
+      "step": 1220
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.3456707000732422,
+      "eval_runtime": 46.2562,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 1224
+    },
+    {
+      "epoch": 4.019607843137255,
+      "grad_norm": 0.7724746465682983,
+      "learning_rate": 0.0002,
+      "loss": 0.582,
+      "step": 1230
+    },
+    {
+      "epoch": 4.052287581699346,
+      "grad_norm": 1.166916847229004,
+      "learning_rate": 0.0002,
+      "loss": 0.4759,
+      "step": 1240
+    },
+    {
+      "epoch": 4.084967320261438,
+      "grad_norm": 0.7234508991241455,
+      "learning_rate": 0.0002,
+      "loss": 0.4995,
+      "step": 1250
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 1.1418060064315796,
+      "learning_rate": 0.0002,
+      "loss": 0.4863,
+      "step": 1260
+    },
+    {
+      "epoch": 4.150326797385621,
+      "grad_norm": 0.9603922367095947,
+      "learning_rate": 0.0002,
+      "loss": 0.5425,
+      "step": 1270
+    },
+    {
+      "epoch": 4.183006535947713,
+      "grad_norm": 0.8976530432701111,
+      "learning_rate": 0.0002,
+      "loss": 0.4892,
+      "step": 1280
+    },
+    {
+      "epoch": 4.215686274509804,
+      "grad_norm": 0.6855078339576721,
+      "learning_rate": 0.0002,
+      "loss": 0.473,
+      "step": 1290
+    },
+    {
+      "epoch": 4.248366013071895,
+      "grad_norm": 1.2676647901535034,
+      "learning_rate": 0.0002,
+      "loss": 0.4416,
+      "step": 1300
+    },
+    {
+      "epoch": 4.281045751633987,
+      "grad_norm": 1.104057788848877,
+      "learning_rate": 0.0002,
+      "loss": 0.5071,
+      "step": 1310
+    },
+    {
+      "epoch": 4.313725490196078,
+      "grad_norm": 1.7076562643051147,
+      "learning_rate": 0.0002,
+      "loss": 0.5168,
+      "step": 1320
+    },
+    {
+      "epoch": 4.34640522875817,
+      "grad_norm": 1.2308520078659058,
+      "learning_rate": 0.0002,
+      "loss": 0.4655,
+      "step": 1330
+    },
+    {
+      "epoch": 4.379084967320262,
+      "grad_norm": 1.2652729749679565,
+      "learning_rate": 0.0002,
+      "loss": 0.5322,
+      "step": 1340
+    },
+    {
+      "epoch": 4.411764705882353,
+      "grad_norm": 1.054958701133728,
+      "learning_rate": 0.0002,
+      "loss": 0.5262,
+      "step": 1350
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 1.0130749940872192,
+      "learning_rate": 0.0002,
+      "loss": 0.4747,
+      "step": 1360
+    },
+    {
+      "epoch": 4.477124183006536,
+      "grad_norm": 1.0517818927764893,
+      "learning_rate": 0.0002,
+      "loss": 0.4887,
+      "step": 1370
+    },
+    {
+      "epoch": 4.509803921568627,
+      "grad_norm": 0.8593037128448486,
+      "learning_rate": 0.0002,
+      "loss": 0.4906,
+      "step": 1380
+    },
+    {
+      "epoch": 4.542483660130719,
+      "grad_norm": 1.0248081684112549,
+      "learning_rate": 0.0002,
+      "loss": 0.5049,
+      "step": 1390
+    },
+    {
+      "epoch": 4.57516339869281,
+      "grad_norm": 0.8999413847923279,
+      "learning_rate": 0.0002,
+      "loss": 0.472,
+      "step": 1400
+    },
+    {
+      "epoch": 4.607843137254902,
+      "grad_norm": 0.9106912612915039,
+      "learning_rate": 0.0002,
+      "loss": 0.5102,
+      "step": 1410
+    },
+    {
+      "epoch": 4.640522875816993,
+      "grad_norm": 1.2736181020736694,
+      "learning_rate": 0.0002,
+      "loss": 0.5203,
+      "step": 1420
+    },
+    {
+      "epoch": 4.673202614379085,
+      "grad_norm": 0.9311690926551819,
+      "learning_rate": 0.0002,
+      "loss": 0.5101,
+      "step": 1430
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 1.0455045700073242,
+      "learning_rate": 0.0002,
+      "loss": 0.5648,
+      "step": 1440
+    },
+    {
+      "epoch": 4.738562091503268,
+      "grad_norm": 1.0190727710723877,
+      "learning_rate": 0.0002,
+      "loss": 0.5004,
+      "step": 1450
+    },
+    {
+      "epoch": 4.771241830065359,
+      "grad_norm": 1.333198070526123,
+      "learning_rate": 0.0002,
+      "loss": 0.5506,
+      "step": 1460
+    },
+    {
+      "epoch": 4.803921568627451,
+      "grad_norm": 0.8808416724205017,
+      "learning_rate": 0.0002,
+      "loss": 0.5846,
+      "step": 1470
+    },
+    {
+      "epoch": 4.836601307189542,
+      "grad_norm": 0.8896227478981018,
+      "learning_rate": 0.0002,
+      "loss": 0.4671,
+      "step": 1480
+    },
+    {
+      "epoch": 4.8692810457516345,
+      "grad_norm": 1.212323784828186,
+      "learning_rate": 0.0002,
+      "loss": 0.4732,
+      "step": 1490
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 1.0490120649337769,
+      "learning_rate": 0.0002,
+      "loss": 0.5263,
+      "step": 1500
+    },
+    {
+      "epoch": 4.934640522875817,
+      "grad_norm": 0.8946618437767029,
+      "learning_rate": 0.0002,
+      "loss": 0.5815,
+      "step": 1510
+    },
+    {
+      "epoch": 4.967320261437909,
+      "grad_norm": 1.0609275102615356,
+      "learning_rate": 0.0002,
+      "loss": 0.5369,
+      "step": 1520
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.8885099291801453,
+      "learning_rate": 0.0002,
+      "loss": 0.5348,
+      "step": 1530
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.5771757364273071,
+      "eval_runtime": 46.2667,
+      "eval_samples_per_second": 9.424,
+      "eval_steps_per_second": 1.189,
+      "step": 1530
+    },
+    {
+      "epoch": 5.032679738562091,
+      "grad_norm": 1.401705026626587,
+      "learning_rate": 0.0002,
+      "loss": 0.3176,
+      "step": 1540
+    },
+    {
+      "epoch": 5.065359477124183,
+      "grad_norm": 0.8365539908409119,
+      "learning_rate": 0.0002,
+      "loss": 0.3346,
+      "step": 1550
+    },
+    {
+      "epoch": 5.098039215686274,
+      "grad_norm": 1.3188321590423584,
+      "learning_rate": 0.0002,
+      "loss": 0.3605,
+      "step": 1560
+    },
+    {
+      "epoch": 5.130718954248366,
+      "grad_norm": 0.9819526076316833,
+      "learning_rate": 0.0002,
+      "loss": 0.326,
+      "step": 1570
+    },
+    {
+      "epoch": 5.163398692810458,
+      "grad_norm": 1.13265061378479,
+      "learning_rate": 0.0002,
+      "loss": 0.3575,
+      "step": 1580
+    },
+    {
+      "epoch": 5.196078431372549,
+      "grad_norm": 1.478152871131897,
+      "learning_rate": 0.0002,
+      "loss": 0.3418,
+      "step": 1590
+    },
+    {
+      "epoch": 5.228758169934641,
+      "grad_norm": 1.4188750982284546,
+      "learning_rate": 0.0002,
+      "loss": 0.3388,
+      "step": 1600
+    },
+    {
+      "epoch": 5.261437908496732,
+      "grad_norm": 1.2499338388442993,
+      "learning_rate": 0.0002,
+      "loss": 0.3524,
+      "step": 1610
+    },
+    {
+      "epoch": 5.294117647058823,
+      "grad_norm": 1.7885085344314575,
+      "learning_rate": 0.0002,
+      "loss": 0.423,
+      "step": 1620
+    },
+    {
+      "epoch": 5.326797385620915,
+      "grad_norm": 1.2614946365356445,
+      "learning_rate": 0.0002,
+      "loss": 0.3237,
+      "step": 1630
+    },
+    {
+      "epoch": 5.359477124183006,
+      "grad_norm": 1.28338623046875,
+      "learning_rate": 0.0002,
+      "loss": 0.3511,
+      "step": 1640
+    },
+    {
+      "epoch": 5.392156862745098,
+      "grad_norm": 1.1973257064819336,
+      "learning_rate": 0.0002,
+      "loss": 0.3112,
+      "step": 1650
+    },
+    {
+      "epoch": 5.42483660130719,
+      "grad_norm": 1.1356301307678223,
+      "learning_rate": 0.0002,
+      "loss": 0.3645,
+      "step": 1660
+    },
+    {
+      "epoch": 5.457516339869281,
+      "grad_norm": 0.9048901200294495,
+      "learning_rate": 0.0002,
+      "loss": 0.307,
+      "step": 1670
+    },
+    {
+      "epoch": 5.490196078431373,
+      "grad_norm": 1.5352122783660889,
+      "learning_rate": 0.0002,
+      "loss": 0.3828,
+      "step": 1680
+    },
+    {
+      "epoch": 5.522875816993464,
+      "grad_norm": 0.9096335172653198,
+      "learning_rate": 0.0002,
+      "loss": 0.3826,
+      "step": 1690
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 1.1903661489486694,
+      "learning_rate": 0.0002,
+      "loss": 0.3686,
+      "step": 1700
+    },
+    {
+      "epoch": 5.588235294117647,
+      "grad_norm": 0.9234451651573181,
+      "learning_rate": 0.0002,
+      "loss": 0.325,
+      "step": 1710
+    },
+    {
+      "epoch": 5.620915032679738,
+      "grad_norm": 1.4554102420806885,
+      "learning_rate": 0.0002,
+      "loss": 0.3451,
+      "step": 1720
+    },
+    {
+      "epoch": 5.65359477124183,
+      "grad_norm": 1.1044343709945679,
+      "learning_rate": 0.0002,
+      "loss": 0.3488,
+      "step": 1730
+    },
+    {
+      "epoch": 5.686274509803922,
+      "grad_norm": 1.2219593524932861,
+      "learning_rate": 0.0002,
+      "loss": 0.3673,
+      "step": 1740
+    },
+    {
+      "epoch": 5.718954248366013,
+      "grad_norm": 0.901652455329895,
+      "learning_rate": 0.0002,
+      "loss": 0.3517,
+      "step": 1750
+    },
+    {
+      "epoch": 5.751633986928105,
+      "grad_norm": 1.3334792852401733,
+      "learning_rate": 0.0002,
+      "loss": 0.4082,
+      "step": 1760
+    },
+    {
+      "epoch": 5.784313725490196,
+      "grad_norm": 1.5595488548278809,
+      "learning_rate": 0.0002,
+      "loss": 0.4386,
+      "step": 1770
+    },
+    {
+      "epoch": 5.816993464052287,
+      "grad_norm": 1.3892982006072998,
+      "learning_rate": 0.0002,
+      "loss": 0.3217,
+      "step": 1780
+    },
+    {
+      "epoch": 5.849673202614379,
+      "grad_norm": 1.0813168287277222,
+      "learning_rate": 0.0002,
+      "loss": 0.3919,
+      "step": 1790
+    },
+    {
+      "epoch": 5.882352941176471,
+      "grad_norm": 1.145320177078247,
+      "learning_rate": 0.0002,
+      "loss": 0.3697,
+      "step": 1800
+    },
+    {
+      "epoch": 5.915032679738562,
+      "grad_norm": 1.0249533653259277,
+      "learning_rate": 0.0002,
+      "loss": 0.3903,
+      "step": 1810
+    },
+    {
+      "epoch": 5.947712418300654,
+      "grad_norm": 1.0013737678527832,
+      "learning_rate": 0.0002,
+      "loss": 0.3481,
+      "step": 1820
+    },
+    {
+      "epoch": 5.980392156862745,
+      "grad_norm": 1.212314248085022,
+      "learning_rate": 0.0002,
+      "loss": 0.4278,
+      "step": 1830
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.7506128549575806,
+      "eval_runtime": 46.2256,
+      "eval_samples_per_second": 9.432,
+      "eval_steps_per_second": 1.19,
+      "step": 1836
+    },
+    {
+      "epoch": 6.0130718954248366,
+      "grad_norm": 0.7339767813682556,
+      "learning_rate": 0.0002,
+      "loss": 0.3283,
+      "step": 1840
+    },
+    {
+      "epoch": 6.045751633986928,
+      "grad_norm": 1.1071710586547852,
+      "learning_rate": 0.0002,
+      "loss": 0.2304,
+      "step": 1850
+    },
+    {
+      "epoch": 6.078431372549019,
+      "grad_norm": 1.2613991498947144,
+      "learning_rate": 0.0002,
+      "loss": 0.2436,
+      "step": 1860
+    },
+    {
+      "epoch": 6.111111111111111,
+      "grad_norm": 1.053133249282837,
+      "learning_rate": 0.0002,
+      "loss": 0.2403,
+      "step": 1870
+    },
+    {
+      "epoch": 6.143790849673203,
+      "grad_norm": 1.069568395614624,
+      "learning_rate": 0.0002,
+      "loss": 0.2509,
+      "step": 1880
+    },
+    {
+      "epoch": 6.176470588235294,
+      "grad_norm": 1.020458698272705,
+      "learning_rate": 0.0002,
+      "loss": 0.2272,
+      "step": 1890
+    },
+    {
+      "epoch": 6.209150326797386,
+      "grad_norm": 1.2430394887924194,
+      "learning_rate": 0.0002,
+      "loss": 0.2408,
+      "step": 1900
+    },
+    {
+      "epoch": 6.241830065359477,
+      "grad_norm": 1.3475574254989624,
+      "learning_rate": 0.0002,
+      "loss": 0.229,
+      "step": 1910
+    },
+    {
+      "epoch": 6.2745098039215685,
+      "grad_norm": 0.9094598889350891,
+      "learning_rate": 0.0002,
+      "loss": 0.2542,
+      "step": 1920
+    },
+    {
+      "epoch": 6.30718954248366,
+      "grad_norm": 1.255650520324707,
+      "learning_rate": 0.0002,
+      "loss": 0.2009,
+      "step": 1930
+    },
+    {
+      "epoch": 6.339869281045751,
+      "grad_norm": 1.4193930625915527,
+      "learning_rate": 0.0002,
+      "loss": 0.25,
+      "step": 1940
+    },
+    {
+      "epoch": 6.372549019607844,
+      "grad_norm": 1.4378032684326172,
+      "learning_rate": 0.0002,
+      "loss": 0.293,
+      "step": 1950
+    },
+    {
+      "epoch": 6.405228758169935,
+      "grad_norm": 1.2236989736557007,
+      "learning_rate": 0.0002,
+      "loss": 0.2685,
+      "step": 1960
+    },
+    {
+      "epoch": 6.437908496732026,
+      "grad_norm": 1.0902987718582153,
+      "learning_rate": 0.0002,
+      "loss": 0.2608,
+      "step": 1970
+    },
+    {
+      "epoch": 6.470588235294118,
+      "grad_norm": 1.1165062189102173,
+      "learning_rate": 0.0002,
+      "loss": 0.2267,
+      "step": 1980
+    },
+    {
+      "epoch": 6.503267973856209,
+      "grad_norm": 1.3953566551208496,
+      "learning_rate": 0.0002,
+      "loss": 0.2246,
+      "step": 1990
+    },
+    {
+      "epoch": 6.5359477124183005,
+      "grad_norm": 1.5215585231781006,
+      "learning_rate": 0.0002,
+      "loss": 0.2834,
+      "step": 2000
+    },
+    {
+      "epoch": 6.568627450980392,
+      "grad_norm": 1.3496609926223755,
+      "learning_rate": 0.0002,
+      "loss": 0.2457,
+      "step": 2010
+    },
+    {
+      "epoch": 6.601307189542483,
+      "grad_norm": 1.2511820793151855,
+      "learning_rate": 0.0002,
+      "loss": 0.2637,
+      "step": 2020
+    },
+    {
+      "epoch": 6.633986928104575,
+      "grad_norm": 1.9875848293304443,
+      "learning_rate": 0.0002,
+      "loss": 0.2956,
+      "step": 2030
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 1.0766608715057373,
+      "learning_rate": 0.0002,
+      "loss": 0.2664,
+      "step": 2040
+    },
+    {
+      "epoch": 6.699346405228758,
+      "grad_norm": 1.3594712018966675,
+      "learning_rate": 0.0002,
+      "loss": 0.2792,
+      "step": 2050
+    },
+    {
+      "epoch": 6.73202614379085,
+      "grad_norm": 1.2357292175292969,
+      "learning_rate": 0.0002,
+      "loss": 0.3194,
+      "step": 2060
+    },
+    {
+      "epoch": 6.764705882352941,
+      "grad_norm": 1.2428375482559204,
+      "learning_rate": 0.0002,
+      "loss": 0.2526,
+      "step": 2070
+    },
+    {
+      "epoch": 6.7973856209150325,
+      "grad_norm": 1.2724156379699707,
+      "learning_rate": 0.0002,
+      "loss": 0.2355,
+      "step": 2080
+    },
+    {
+      "epoch": 6.830065359477124,
+      "grad_norm": 1.4981396198272705,
+      "learning_rate": 0.0002,
+      "loss": 0.289,
+      "step": 2090
+    },
+    {
+      "epoch": 6.862745098039216,
+      "grad_norm": 0.9346088171005249,
+      "learning_rate": 0.0002,
+      "loss": 0.2443,
+      "step": 2100
+    },
+    {
+      "epoch": 6.895424836601308,
+      "grad_norm": 1.3955477476119995,
+      "learning_rate": 0.0002,
+      "loss": 0.262,
+      "step": 2110
+    },
+    {
+      "epoch": 6.928104575163399,
+      "grad_norm": 1.492382287979126,
+      "learning_rate": 0.0002,
+      "loss": 0.2981,
+      "step": 2120
+    },
+    {
+      "epoch": 6.96078431372549,
+      "grad_norm": 1.2755712270736694,
+      "learning_rate": 0.0002,
+      "loss": 0.3093,
+      "step": 2130
+    },
+    {
+      "epoch": 6.993464052287582,
+      "grad_norm": 1.4600884914398193,
+      "learning_rate": 0.0002,
+      "loss": 0.2943,
+      "step": 2140
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.9770371913909912,
+      "eval_runtime": 46.2588,
+      "eval_samples_per_second": 9.425,
+      "eval_steps_per_second": 1.189,
+      "step": 2142
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2448,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1002114313551872e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/training_args.bin b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e7fb8100bbfe18f1342e5fc87e32e8e798268e3b
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2142/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e66621362aa4eab196083c9a4bd0bf843b2425d7109d63be3ab5f4006691dd1
+size 5560
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/README.md b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/adapter_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/adapter_model.safetensors b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..95f8c4bfbad6ddb011b5ace888e988eed3a03201
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01ad95eba619b35632ef34ad74d9e86bd4fad67b3357523e689855bea266fa3
+size 143153376
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/optimizer.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..52f2e7df11628a41be9de96b6cd87ee4640fbbc7
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e596ba51a382f1ddea78022bd0d98570419e7cb21f1424f169aff90b8d5f6d44
+size 72886650
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/rng_state.pth b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a785c80deaec82ef48b6c2684b07bb516dfa5c23
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426a64bb3cacb707e0f39ada228c901d99e3164560513a6206a9021ff65e4f62
+size 14244
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/scheduler.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..998a4ffe7d8a9e39dcdd15d61ac920a5b1972ab4
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:794241e4292faf1c486dcb09e837545466e327529800d1ae841cb58adeb555e9
+size 1064
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/special_tokens_map.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/special_tokens_map.json
@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/tokenizer.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/tokenizer.model b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/tokenizer_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/tokenizer_config.json
@@ -0,0 +1,2013 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/trainer_state.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..89e51e4711f61411f21a5ef4dc467130db63a71f
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/trainer_state.json
@@ -0,0 +1,1805 @@
+{
+  "best_metric": 1.1845070123672485,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612",
+  "epoch": 8.0,
+  "eval_steps": 10,
+  "global_step": 2448,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032679738562091505,
+      "grad_norm": 0.631856381893158,
+      "learning_rate": 0.0002,
+      "loss": 2.3561,
+      "step": 10
+    },
+    {
+      "epoch": 0.06535947712418301,
+      "grad_norm": 0.5065668821334839,
+      "learning_rate": 0.0002,
+      "loss": 1.8141,
+      "step": 20
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 0.6978895664215088,
+      "learning_rate": 0.0002,
+      "loss": 1.4952,
+      "step": 30
+    },
+    {
+      "epoch": 0.13071895424836602,
+      "grad_norm": 0.6619144082069397,
+      "learning_rate": 0.0002,
+      "loss": 1.4829,
+      "step": 40
+    },
+    {
+      "epoch": 0.16339869281045752,
+      "grad_norm": 0.6153793931007385,
+      "learning_rate": 0.0002,
+      "loss": 1.3038,
+      "step": 50
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.4703301787376404,
+      "learning_rate": 0.0002,
+      "loss": 1.1429,
+      "step": 60
+    },
+    {
+      "epoch": 0.22875816993464052,
+      "grad_norm": 1.1672580242156982,
+      "learning_rate": 0.0002,
+      "loss": 1.2828,
+      "step": 70
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 0.3455565273761749,
+      "learning_rate": 0.0002,
+      "loss": 1.0985,
+      "step": 80
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.36216291785240173,
+      "learning_rate": 0.0002,
+      "loss": 1.1359,
+      "step": 90
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "grad_norm": 0.4545166492462158,
+      "learning_rate": 0.0002,
+      "loss": 1.2544,
+      "step": 100
+    },
+    {
+      "epoch": 0.35947712418300654,
+      "grad_norm": 0.3612092435359955,
+      "learning_rate": 0.0002,
+      "loss": 1.2287,
+      "step": 110
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.5080830454826355,
+      "learning_rate": 0.0002,
+      "loss": 1.1868,
+      "step": 120
+    },
+    {
+      "epoch": 0.42483660130718953,
+      "grad_norm": 0.3268195390701294,
+      "learning_rate": 0.0002,
+      "loss": 1.1902,
+      "step": 130
+    },
+    {
+      "epoch": 0.45751633986928103,
+      "grad_norm": 0.33971714973449707,
+      "learning_rate": 0.0002,
+      "loss": 1.247,
+      "step": 140
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 0.4036043882369995,
+      "learning_rate": 0.0002,
+      "loss": 1.1844,
+      "step": 150
+    },
+    {
+      "epoch": 0.5228758169934641,
+      "grad_norm": 0.35938864946365356,
+      "learning_rate": 0.0002,
+      "loss": 1.1624,
+      "step": 160
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.28880223631858826,
+      "learning_rate": 0.0002,
+      "loss": 1.164,
+      "step": 170
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.3436269462108612,
+      "learning_rate": 0.0002,
+      "loss": 1.3521,
+      "step": 180
+    },
+    {
+      "epoch": 0.6209150326797386,
+      "grad_norm": 0.41923725605010986,
+      "learning_rate": 0.0002,
+      "loss": 1.2456,
+      "step": 190
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "grad_norm": 0.25119203329086304,
+      "learning_rate": 0.0002,
+      "loss": 1.2226,
+      "step": 200
+    },
+    {
+      "epoch": 0.6862745098039216,
+      "grad_norm": 0.5870180726051331,
+      "learning_rate": 0.0002,
+      "loss": 1.1568,
+      "step": 210
+    },
+    {
+      "epoch": 0.7189542483660131,
+      "grad_norm": 0.2831224203109741,
+      "learning_rate": 0.0002,
+      "loss": 1.064,
+      "step": 220
+    },
+    {
+      "epoch": 0.7516339869281046,
+      "grad_norm": 0.3192005753517151,
+      "learning_rate": 0.0002,
+      "loss": 1.2469,
+      "step": 230
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.2998219430446625,
+      "learning_rate": 0.0002,
+      "loss": 1.1613,
+      "step": 240
+    },
+    {
+      "epoch": 0.8169934640522876,
+      "grad_norm": 0.32855790853500366,
+      "learning_rate": 0.0002,
+      "loss": 1.205,
+      "step": 250
+    },
+    {
+      "epoch": 0.8496732026143791,
+      "grad_norm": 0.3403124213218689,
+      "learning_rate": 0.0002,
+      "loss": 1.1631,
+      "step": 260
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.277401328086853,
+      "learning_rate": 0.0002,
+      "loss": 1.1646,
+      "step": 270
+    },
+    {
+      "epoch": 0.9150326797385621,
+      "grad_norm": 0.2975269556045532,
+      "learning_rate": 0.0002,
+      "loss": 1.084,
+      "step": 280
+    },
+    {
+      "epoch": 0.9477124183006536,
+      "grad_norm": 1.7909578084945679,
+      "learning_rate": 0.0002,
+      "loss": 1.2039,
+      "step": 290
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 0.2917245328426361,
+      "learning_rate": 0.0002,
+      "loss": 1.1226,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1937541961669922,
+      "eval_runtime": 46.2571,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 306
+    },
+    {
+      "epoch": 1.0130718954248366,
+      "grad_norm": 0.26494982838630676,
+      "learning_rate": 0.0002,
+      "loss": 1.2011,
+      "step": 310
+    },
+    {
+      "epoch": 1.0457516339869282,
+      "grad_norm": 0.6289355754852295,
+      "learning_rate": 0.0002,
+      "loss": 1.0565,
+      "step": 320
+    },
+    {
+      "epoch": 1.0784313725490196,
+      "grad_norm": 0.26784011721611023,
+      "learning_rate": 0.0002,
+      "loss": 1.1619,
+      "step": 330
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.3392215967178345,
+      "learning_rate": 0.0002,
+      "loss": 1.1151,
+      "step": 340
+    },
+    {
+      "epoch": 1.1437908496732025,
+      "grad_norm": 0.40005937218666077,
+      "learning_rate": 0.0002,
+      "loss": 1.0752,
+      "step": 350
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.3590582013130188,
+      "learning_rate": 0.0002,
+      "loss": 1.0408,
+      "step": 360
+    },
+    {
+      "epoch": 1.2091503267973855,
+      "grad_norm": 0.3995305895805359,
+      "learning_rate": 0.0002,
+      "loss": 1.0836,
+      "step": 370
+    },
+    {
+      "epoch": 1.2418300653594772,
+      "grad_norm": 0.2950291633605957,
+      "learning_rate": 0.0002,
+      "loss": 1.0992,
+      "step": 380
+    },
+    {
+      "epoch": 1.2745098039215685,
+      "grad_norm": 0.32035166025161743,
+      "learning_rate": 0.0002,
+      "loss": 1.1152,
+      "step": 390
+    },
+    {
+      "epoch": 1.3071895424836601,
+      "grad_norm": 0.410366415977478,
+      "learning_rate": 0.0002,
+      "loss": 1.1467,
+      "step": 400
+    },
+    {
+      "epoch": 1.3398692810457518,
+      "grad_norm": 0.3106379508972168,
+      "learning_rate": 0.0002,
+      "loss": 0.9985,
+      "step": 410
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 0.38580670952796936,
+      "learning_rate": 0.0002,
+      "loss": 0.9789,
+      "step": 420
+    },
+    {
+      "epoch": 1.4052287581699345,
+      "grad_norm": 0.34411361813545227,
+      "learning_rate": 0.0002,
+      "loss": 1.0931,
+      "step": 430
+    },
+    {
+      "epoch": 1.4379084967320261,
+      "grad_norm": 0.44206851720809937,
+      "learning_rate": 0.0002,
+      "loss": 1.1685,
+      "step": 440
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.3492952585220337,
+      "learning_rate": 0.0002,
+      "loss": 1.0347,
+      "step": 450
+    },
+    {
+      "epoch": 1.5032679738562091,
+      "grad_norm": 0.376423716545105,
+      "learning_rate": 0.0002,
+      "loss": 1.0534,
+      "step": 460
+    },
+    {
+      "epoch": 1.5359477124183005,
+      "grad_norm": 0.359757661819458,
+      "learning_rate": 0.0002,
+      "loss": 1.1162,
+      "step": 470
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 0.3385067880153656,
+      "learning_rate": 0.0002,
+      "loss": 0.9586,
+      "step": 480
+    },
+    {
+      "epoch": 1.6013071895424837,
+      "grad_norm": 0.4943889379501343,
+      "learning_rate": 0.0002,
+      "loss": 1.0807,
+      "step": 490
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 0.4203241169452667,
+      "learning_rate": 0.0002,
+      "loss": 1.0796,
+      "step": 500
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.3093789219856262,
+      "learning_rate": 0.0002,
+      "loss": 1.1059,
+      "step": 510
+    },
+    {
+      "epoch": 1.6993464052287581,
+      "grad_norm": 0.3653067350387573,
+      "learning_rate": 0.0002,
+      "loss": 1.0323,
+      "step": 520
+    },
+    {
+      "epoch": 1.7320261437908497,
+      "grad_norm": 0.36761337518692017,
+      "learning_rate": 0.0002,
+      "loss": 1.0885,
+      "step": 530
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.5040399432182312,
+      "learning_rate": 0.0002,
+      "loss": 1.1698,
+      "step": 540
+    },
+    {
+      "epoch": 1.7973856209150327,
+      "grad_norm": 0.3818035125732422,
+      "learning_rate": 0.0002,
+      "loss": 1.0105,
+      "step": 550
+    },
+    {
+      "epoch": 1.8300653594771243,
+      "grad_norm": 0.4021618664264679,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 560
+    },
+    {
+      "epoch": 1.8627450980392157,
+      "grad_norm": 0.3986459970474243,
+      "learning_rate": 0.0002,
+      "loss": 1.0358,
+      "step": 570
+    },
+    {
+      "epoch": 1.8954248366013071,
+      "grad_norm": 0.48416733741760254,
+      "learning_rate": 0.0002,
+      "loss": 1.003,
+      "step": 580
+    },
+    {
+      "epoch": 1.9281045751633987,
+      "grad_norm": 0.36853986978530884,
+      "learning_rate": 0.0002,
+      "loss": 1.1146,
+      "step": 590
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.383022665977478,
+      "learning_rate": 0.0002,
+      "loss": 1.0689,
+      "step": 600
+    },
+    {
+      "epoch": 1.9934640522875817,
+      "grad_norm": 0.3169507086277008,
+      "learning_rate": 0.0002,
+      "loss": 1.098,
+      "step": 610
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1845070123672485,
+      "eval_runtime": 46.2811,
+      "eval_samples_per_second": 9.421,
+      "eval_steps_per_second": 1.188,
+      "step": 612
+    },
+    {
+      "epoch": 2.026143790849673,
+      "grad_norm": 0.8920142650604248,
+      "learning_rate": 0.0002,
+      "loss": 0.9618,
+      "step": 620
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.4814859628677368,
+      "learning_rate": 0.0002,
+      "loss": 0.9784,
+      "step": 630
+    },
+    {
+      "epoch": 2.0915032679738563,
+      "grad_norm": 0.4251559376716614,
+      "learning_rate": 0.0002,
+      "loss": 0.8464,
+      "step": 640
+    },
+    {
+      "epoch": 2.1241830065359477,
+      "grad_norm": 0.5295765399932861,
+      "learning_rate": 0.0002,
+      "loss": 0.932,
+      "step": 650
+    },
+    {
+      "epoch": 2.156862745098039,
+      "grad_norm": 0.45016610622406006,
+      "learning_rate": 0.0002,
+      "loss": 0.9603,
+      "step": 660
+    },
+    {
+      "epoch": 2.189542483660131,
+      "grad_norm": 0.5870586633682251,
+      "learning_rate": 0.0002,
+      "loss": 0.8738,
+      "step": 670
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.5174715518951416,
+      "learning_rate": 0.0002,
+      "loss": 0.9483,
+      "step": 680
+    },
+    {
+      "epoch": 2.2549019607843137,
+      "grad_norm": 0.5252485275268555,
+      "learning_rate": 0.0002,
+      "loss": 0.9551,
+      "step": 690
+    },
+    {
+      "epoch": 2.287581699346405,
+      "grad_norm": 0.5158312320709229,
+      "learning_rate": 0.0002,
+      "loss": 0.9253,
+      "step": 700
+    },
+    {
+      "epoch": 2.3202614379084965,
+      "grad_norm": 0.4824209213256836,
+      "learning_rate": 0.0002,
+      "loss": 0.9278,
+      "step": 710
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.6335175037384033,
+      "learning_rate": 0.0002,
+      "loss": 0.8804,
+      "step": 720
+    },
+    {
+      "epoch": 2.3856209150326797,
+      "grad_norm": 0.5240563154220581,
+      "learning_rate": 0.0002,
+      "loss": 0.9685,
+      "step": 730
+    },
+    {
+      "epoch": 2.418300653594771,
+      "grad_norm": 0.5172886252403259,
+      "learning_rate": 0.0002,
+      "loss": 0.8794,
+      "step": 740
+    },
+    {
+      "epoch": 2.450980392156863,
+      "grad_norm": 0.48972561955451965,
+      "learning_rate": 0.0002,
+      "loss": 0.8158,
+      "step": 750
+    },
+    {
+      "epoch": 2.4836601307189543,
+      "grad_norm": 0.5295189023017883,
+      "learning_rate": 0.0002,
+      "loss": 0.8766,
+      "step": 760
+    },
+    {
+      "epoch": 2.5163398692810457,
+      "grad_norm": 0.5487208962440491,
+      "learning_rate": 0.0002,
+      "loss": 0.8695,
+      "step": 770
+    },
+    {
+      "epoch": 2.549019607843137,
+      "grad_norm": 0.5375093221664429,
+      "learning_rate": 0.0002,
+      "loss": 1.0109,
+      "step": 780
+    },
+    {
+      "epoch": 2.581699346405229,
+      "grad_norm": 0.5424453020095825,
+      "learning_rate": 0.0002,
+      "loss": 0.9244,
+      "step": 790
+    },
+    {
+      "epoch": 2.6143790849673203,
+      "grad_norm": 0.6029134392738342,
+      "learning_rate": 0.0002,
+      "loss": 1.0424,
+      "step": 800
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.6584921479225159,
+      "learning_rate": 0.0002,
+      "loss": 0.8688,
+      "step": 810
+    },
+    {
+      "epoch": 2.6797385620915035,
+      "grad_norm": 0.5735557675361633,
+      "learning_rate": 0.0002,
+      "loss": 0.7796,
+      "step": 820
+    },
+    {
+      "epoch": 2.712418300653595,
+      "grad_norm": 0.5216763019561768,
+      "learning_rate": 0.0002,
+      "loss": 0.8834,
+      "step": 830
+    },
+    {
+      "epoch": 2.7450980392156863,
+      "grad_norm": 0.5455219149589539,
+      "learning_rate": 0.0002,
+      "loss": 0.8946,
+      "step": 840
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.5139284729957581,
+      "learning_rate": 0.0002,
+      "loss": 0.8037,
+      "step": 850
+    },
+    {
+      "epoch": 2.810457516339869,
+      "grad_norm": 0.5096403360366821,
+      "learning_rate": 0.0002,
+      "loss": 0.988,
+      "step": 860
+    },
+    {
+      "epoch": 2.843137254901961,
+      "grad_norm": 0.6337038278579712,
+      "learning_rate": 0.0002,
+      "loss": 0.9169,
+      "step": 870
+    },
+    {
+      "epoch": 2.8758169934640523,
+      "grad_norm": 0.47218772768974304,
+      "learning_rate": 0.0002,
+      "loss": 0.8938,
+      "step": 880
+    },
+    {
+      "epoch": 2.9084967320261437,
+      "grad_norm": 0.4640636742115021,
+      "learning_rate": 0.0002,
+      "loss": 0.8554,
+      "step": 890
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.4199628531932831,
+      "learning_rate": 0.0002,
+      "loss": 0.8625,
+      "step": 900
+    },
+    {
+      "epoch": 2.973856209150327,
+      "grad_norm": 0.5067117214202881,
+      "learning_rate": 0.0002,
+      "loss": 0.8104,
+      "step": 910
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2291251420974731,
+      "eval_runtime": 46.2557,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 918
+    },
+    {
+      "epoch": 3.0065359477124183,
+      "grad_norm": 0.8342176079750061,
+      "learning_rate": 0.0002,
+      "loss": 0.8157,
+      "step": 920
+    },
+    {
+      "epoch": 3.0392156862745097,
+      "grad_norm": 0.7695813775062561,
+      "learning_rate": 0.0002,
+      "loss": 0.6855,
+      "step": 930
+    },
+    {
+      "epoch": 3.0718954248366015,
+      "grad_norm": 0.6819486618041992,
+      "learning_rate": 0.0002,
+      "loss": 0.6173,
+      "step": 940
+    },
+    {
+      "epoch": 3.104575163398693,
+      "grad_norm": 0.7568879723548889,
+      "learning_rate": 0.0002,
+      "loss": 0.6495,
+      "step": 950
+    },
+    {
+      "epoch": 3.1372549019607843,
+      "grad_norm": 0.6760695576667786,
+      "learning_rate": 0.0002,
+      "loss": 0.7905,
+      "step": 960
+    },
+    {
+      "epoch": 3.1699346405228757,
+      "grad_norm": 0.6359127759933472,
+      "learning_rate": 0.0002,
+      "loss": 0.6405,
+      "step": 970
+    },
+    {
+      "epoch": 3.2026143790849675,
+      "grad_norm": 0.8414971828460693,
+      "learning_rate": 0.0002,
+      "loss": 0.7172,
+      "step": 980
+    },
+    {
+      "epoch": 3.235294117647059,
+      "grad_norm": 0.68381667137146,
+      "learning_rate": 0.0002,
+      "loss": 0.7865,
+      "step": 990
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 0.6852193474769592,
+      "learning_rate": 0.0002,
+      "loss": 0.6651,
+      "step": 1000
+    },
+    {
+      "epoch": 3.3006535947712417,
+      "grad_norm": 0.8184967041015625,
+      "learning_rate": 0.0002,
+      "loss": 0.6571,
+      "step": 1010
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.047290563583374,
+      "learning_rate": 0.0002,
+      "loss": 0.7036,
+      "step": 1020
+    },
+    {
+      "epoch": 3.366013071895425,
+      "grad_norm": 0.8291178345680237,
+      "learning_rate": 0.0002,
+      "loss": 0.7215,
+      "step": 1030
+    },
+    {
+      "epoch": 3.3986928104575163,
+      "grad_norm": 0.6668022871017456,
+      "learning_rate": 0.0002,
+      "loss": 0.6243,
+      "step": 1040
+    },
+    {
+      "epoch": 3.431372549019608,
+      "grad_norm": 0.6354008316993713,
+      "learning_rate": 0.0002,
+      "loss": 0.7459,
+      "step": 1050
+    },
+    {
+      "epoch": 3.4640522875816995,
+      "grad_norm": 1.2028366327285767,
+      "learning_rate": 0.0002,
+      "loss": 0.6826,
+      "step": 1060
+    },
+    {
+      "epoch": 3.496732026143791,
+      "grad_norm": 0.717367947101593,
+      "learning_rate": 0.0002,
+      "loss": 0.5913,
+      "step": 1070
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 0.542179524898529,
+      "learning_rate": 0.0002,
+      "loss": 0.6903,
+      "step": 1080
+    },
+    {
+      "epoch": 3.5620915032679736,
+      "grad_norm": 0.845981776714325,
+      "learning_rate": 0.0002,
+      "loss": 0.7673,
+      "step": 1090
+    },
+    {
+      "epoch": 3.5947712418300655,
+      "grad_norm": 0.7381046414375305,
+      "learning_rate": 0.0002,
+      "loss": 0.7089,
+      "step": 1100
+    },
+    {
+      "epoch": 3.627450980392157,
+      "grad_norm": 0.6563456058502197,
+      "learning_rate": 0.0002,
+      "loss": 0.6705,
+      "step": 1110
+    },
+    {
+      "epoch": 3.6601307189542482,
+      "grad_norm": 0.7130876779556274,
+      "learning_rate": 0.0002,
+      "loss": 0.7767,
+      "step": 1120
+    },
+    {
+      "epoch": 3.69281045751634,
+      "grad_norm": 0.800032913684845,
+      "learning_rate": 0.0002,
+      "loss": 0.7164,
+      "step": 1130
+    },
+    {
+      "epoch": 3.7254901960784315,
+      "grad_norm": 0.980328381061554,
+      "learning_rate": 0.0002,
+      "loss": 0.7272,
+      "step": 1140
+    },
+    {
+      "epoch": 3.758169934640523,
+      "grad_norm": 0.8542261123657227,
+      "learning_rate": 0.0002,
+      "loss": 0.7672,
+      "step": 1150
+    },
+    {
+      "epoch": 3.7908496732026142,
+      "grad_norm": 0.6302552819252014,
+      "learning_rate": 0.0002,
+      "loss": 0.679,
+      "step": 1160
+    },
+    {
+      "epoch": 3.8235294117647056,
+      "grad_norm": 0.515398383140564,
+      "learning_rate": 0.0002,
+      "loss": 0.7457,
+      "step": 1170
+    },
+    {
+      "epoch": 3.8562091503267975,
+      "grad_norm": 1.2427130937576294,
+      "learning_rate": 0.0002,
+      "loss": 0.693,
+      "step": 1180
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.8206831216812134,
+      "learning_rate": 0.0002,
+      "loss": 0.7182,
+      "step": 1190
+    },
+    {
+      "epoch": 3.9215686274509802,
+      "grad_norm": 0.7633249163627625,
+      "learning_rate": 0.0002,
+      "loss": 0.7519,
+      "step": 1200
+    },
+    {
+      "epoch": 3.954248366013072,
+      "grad_norm": 0.8034512400627136,
+      "learning_rate": 0.0002,
+      "loss": 0.7082,
+      "step": 1210
+    },
+    {
+      "epoch": 3.9869281045751634,
+      "grad_norm": 0.7667182087898254,
+      "learning_rate": 0.0002,
+      "loss": 0.6834,
+      "step": 1220
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.3456707000732422,
+      "eval_runtime": 46.2562,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 1224
+    },
+    {
+      "epoch": 4.019607843137255,
+      "grad_norm": 0.7724746465682983,
+      "learning_rate": 0.0002,
+      "loss": 0.582,
+      "step": 1230
+    },
+    {
+      "epoch": 4.052287581699346,
+      "grad_norm": 1.166916847229004,
+      "learning_rate": 0.0002,
+      "loss": 0.4759,
+      "step": 1240
+    },
+    {
+      "epoch": 4.084967320261438,
+      "grad_norm": 0.7234508991241455,
+      "learning_rate": 0.0002,
+      "loss": 0.4995,
+      "step": 1250
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 1.1418060064315796,
+      "learning_rate": 0.0002,
+      "loss": 0.4863,
+      "step": 1260
+    },
+    {
+      "epoch": 4.150326797385621,
+      "grad_norm": 0.9603922367095947,
+      "learning_rate": 0.0002,
+      "loss": 0.5425,
+      "step": 1270
+    },
+    {
+      "epoch": 4.183006535947713,
+      "grad_norm": 0.8976530432701111,
+      "learning_rate": 0.0002,
+      "loss": 0.4892,
+      "step": 1280
+    },
+    {
+      "epoch": 4.215686274509804,
+      "grad_norm": 0.6855078339576721,
+      "learning_rate": 0.0002,
+      "loss": 0.473,
+      "step": 1290
+    },
+    {
+      "epoch": 4.248366013071895,
+      "grad_norm": 1.2676647901535034,
+      "learning_rate": 0.0002,
+      "loss": 0.4416,
+      "step": 1300
+    },
+    {
+      "epoch": 4.281045751633987,
+      "grad_norm": 1.104057788848877,
+      "learning_rate": 0.0002,
+      "loss": 0.5071,
+      "step": 1310
+    },
+    {
+      "epoch": 4.313725490196078,
+      "grad_norm": 1.7076562643051147,
+      "learning_rate": 0.0002,
+      "loss": 0.5168,
+      "step": 1320
+    },
+    {
+      "epoch": 4.34640522875817,
+      "grad_norm": 1.2308520078659058,
+      "learning_rate": 0.0002,
+      "loss": 0.4655,
+      "step": 1330
+    },
+    {
+      "epoch": 4.379084967320262,
+      "grad_norm": 1.2652729749679565,
+      "learning_rate": 0.0002,
+      "loss": 0.5322,
+      "step": 1340
+    },
+    {
+      "epoch": 4.411764705882353,
+      "grad_norm": 1.054958701133728,
+      "learning_rate": 0.0002,
+      "loss": 0.5262,
+      "step": 1350
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 1.0130749940872192,
+      "learning_rate": 0.0002,
+      "loss": 0.4747,
+      "step": 1360
+    },
+    {
+      "epoch": 4.477124183006536,
+      "grad_norm": 1.0517818927764893,
+      "learning_rate": 0.0002,
+      "loss": 0.4887,
+      "step": 1370
+    },
+    {
+      "epoch": 4.509803921568627,
+      "grad_norm": 0.8593037128448486,
+      "learning_rate": 0.0002,
+      "loss": 0.4906,
+      "step": 1380
+    },
+    {
+      "epoch": 4.542483660130719,
+      "grad_norm": 1.0248081684112549,
+      "learning_rate": 0.0002,
+      "loss": 0.5049,
+      "step": 1390
+    },
+    {
+      "epoch": 4.57516339869281,
+      "grad_norm": 0.8999413847923279,
+      "learning_rate": 0.0002,
+      "loss": 0.472,
+      "step": 1400
+    },
+    {
+      "epoch": 4.607843137254902,
+      "grad_norm": 0.9106912612915039,
+      "learning_rate": 0.0002,
+      "loss": 0.5102,
+      "step": 1410
+    },
+    {
+      "epoch": 4.640522875816993,
+      "grad_norm": 1.2736181020736694,
+      "learning_rate": 0.0002,
+      "loss": 0.5203,
+      "step": 1420
+    },
+    {
+      "epoch": 4.673202614379085,
+      "grad_norm": 0.9311690926551819,
+      "learning_rate": 0.0002,
+      "loss": 0.5101,
+      "step": 1430
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 1.0455045700073242,
+      "learning_rate": 0.0002,
+      "loss": 0.5648,
+      "step": 1440
+    },
+    {
+      "epoch": 4.738562091503268,
+      "grad_norm": 1.0190727710723877,
+      "learning_rate": 0.0002,
+      "loss": 0.5004,
+      "step": 1450
+    },
+    {
+      "epoch": 4.771241830065359,
+      "grad_norm": 1.333198070526123,
+      "learning_rate": 0.0002,
+      "loss": 0.5506,
+      "step": 1460
+    },
+    {
+      "epoch": 4.803921568627451,
+      "grad_norm": 0.8808416724205017,
+      "learning_rate": 0.0002,
+      "loss": 0.5846,
+      "step": 1470
+    },
+    {
+      "epoch": 4.836601307189542,
+      "grad_norm": 0.8896227478981018,
+      "learning_rate": 0.0002,
+      "loss": 0.4671,
+      "step": 1480
+    },
+    {
+      "epoch": 4.8692810457516345,
+      "grad_norm": 1.212323784828186,
+      "learning_rate": 0.0002,
+      "loss": 0.4732,
+      "step": 1490
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 1.0490120649337769,
+      "learning_rate": 0.0002,
+      "loss": 0.5263,
+      "step": 1500
+    },
+    {
+      "epoch": 4.934640522875817,
+      "grad_norm": 0.8946618437767029,
+      "learning_rate": 0.0002,
+      "loss": 0.5815,
+      "step": 1510
+    },
+    {
+      "epoch": 4.967320261437909,
+      "grad_norm": 1.0609275102615356,
+      "learning_rate": 0.0002,
+      "loss": 0.5369,
+      "step": 1520
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.8885099291801453,
+      "learning_rate": 0.0002,
+      "loss": 0.5348,
+      "step": 1530
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.5771757364273071,
+      "eval_runtime": 46.2667,
+      "eval_samples_per_second": 9.424,
+      "eval_steps_per_second": 1.189,
+      "step": 1530
+    },
+    {
+      "epoch": 5.032679738562091,
+      "grad_norm": 1.401705026626587,
+      "learning_rate": 0.0002,
+      "loss": 0.3176,
+      "step": 1540
+    },
+    {
+      "epoch": 5.065359477124183,
+      "grad_norm": 0.8365539908409119,
+      "learning_rate": 0.0002,
+      "loss": 0.3346,
+      "step": 1550
+    },
+    {
+      "epoch": 5.098039215686274,
+      "grad_norm": 1.3188321590423584,
+      "learning_rate": 0.0002,
+      "loss": 0.3605,
+      "step": 1560
+    },
+    {
+      "epoch": 5.130718954248366,
+      "grad_norm": 0.9819526076316833,
+      "learning_rate": 0.0002,
+      "loss": 0.326,
+      "step": 1570
+    },
+    {
+      "epoch": 5.163398692810458,
+      "grad_norm": 1.13265061378479,
+      "learning_rate": 0.0002,
+      "loss": 0.3575,
+      "step": 1580
+    },
+    {
+      "epoch": 5.196078431372549,
+      "grad_norm": 1.478152871131897,
+      "learning_rate": 0.0002,
+      "loss": 0.3418,
+      "step": 1590
+    },
+    {
+      "epoch": 5.228758169934641,
+      "grad_norm": 1.4188750982284546,
+      "learning_rate": 0.0002,
+      "loss": 0.3388,
+      "step": 1600
+    },
+    {
+      "epoch": 5.261437908496732,
+      "grad_norm": 1.2499338388442993,
+      "learning_rate": 0.0002,
+      "loss": 0.3524,
+      "step": 1610
+    },
+    {
+      "epoch": 5.294117647058823,
+      "grad_norm": 1.7885085344314575,
+      "learning_rate": 0.0002,
+      "loss": 0.423,
+      "step": 1620
+    },
+    {
+      "epoch": 5.326797385620915,
+      "grad_norm": 1.2614946365356445,
+      "learning_rate": 0.0002,
+      "loss": 0.3237,
+      "step": 1630
+    },
+    {
+      "epoch": 5.359477124183006,
+      "grad_norm": 1.28338623046875,
+      "learning_rate": 0.0002,
+      "loss": 0.3511,
+      "step": 1640
+    },
+    {
+      "epoch": 5.392156862745098,
+      "grad_norm": 1.1973257064819336,
+      "learning_rate": 0.0002,
+      "loss": 0.3112,
+      "step": 1650
+    },
+    {
+      "epoch": 5.42483660130719,
+      "grad_norm": 1.1356301307678223,
+      "learning_rate": 0.0002,
+      "loss": 0.3645,
+      "step": 1660
+    },
+    {
+      "epoch": 5.457516339869281,
+      "grad_norm": 0.9048901200294495,
+      "learning_rate": 0.0002,
+      "loss": 0.307,
+      "step": 1670
+    },
+    {
+      "epoch": 5.490196078431373,
+      "grad_norm": 1.5352122783660889,
+      "learning_rate": 0.0002,
+      "loss": 0.3828,
+      "step": 1680
+    },
+    {
+      "epoch": 5.522875816993464,
+      "grad_norm": 0.9096335172653198,
+      "learning_rate": 0.0002,
+      "loss": 0.3826,
+      "step": 1690
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 1.1903661489486694,
+      "learning_rate": 0.0002,
+      "loss": 0.3686,
+      "step": 1700
+    },
+    {
+      "epoch": 5.588235294117647,
+      "grad_norm": 0.9234451651573181,
+      "learning_rate": 0.0002,
+      "loss": 0.325,
+      "step": 1710
+    },
+    {
+      "epoch": 5.620915032679738,
+      "grad_norm": 1.4554102420806885,
+      "learning_rate": 0.0002,
+      "loss": 0.3451,
+      "step": 1720
+    },
+    {
+      "epoch": 5.65359477124183,
+      "grad_norm": 1.1044343709945679,
+      "learning_rate": 0.0002,
+      "loss": 0.3488,
+      "step": 1730
+    },
+    {
+      "epoch": 5.686274509803922,
+      "grad_norm": 1.2219593524932861,
+      "learning_rate": 0.0002,
+      "loss": 0.3673,
+      "step": 1740
+    },
+    {
+      "epoch": 5.718954248366013,
+      "grad_norm": 0.901652455329895,
+      "learning_rate": 0.0002,
+      "loss": 0.3517,
+      "step": 1750
+    },
+    {
+      "epoch": 5.751633986928105,
+      "grad_norm": 1.3334792852401733,
+      "learning_rate": 0.0002,
+      "loss": 0.4082,
+      "step": 1760
+    },
+    {
+      "epoch": 5.784313725490196,
+      "grad_norm": 1.5595488548278809,
+      "learning_rate": 0.0002,
+      "loss": 0.4386,
+      "step": 1770
+    },
+    {
+      "epoch": 5.816993464052287,
+      "grad_norm": 1.3892982006072998,
+      "learning_rate": 0.0002,
+      "loss": 0.3217,
+      "step": 1780
+    },
+    {
+      "epoch": 5.849673202614379,
+      "grad_norm": 1.0813168287277222,
+      "learning_rate": 0.0002,
+      "loss": 0.3919,
+      "step": 1790
+    },
+    {
+      "epoch": 5.882352941176471,
+      "grad_norm": 1.145320177078247,
+      "learning_rate": 0.0002,
+      "loss": 0.3697,
+      "step": 1800
+    },
+    {
+      "epoch": 5.915032679738562,
+      "grad_norm": 1.0249533653259277,
+      "learning_rate": 0.0002,
+      "loss": 0.3903,
+      "step": 1810
+    },
+    {
+      "epoch": 5.947712418300654,
+      "grad_norm": 1.0013737678527832,
+      "learning_rate": 0.0002,
+      "loss": 0.3481,
+      "step": 1820
+    },
+    {
+      "epoch": 5.980392156862745,
+      "grad_norm": 1.212314248085022,
+      "learning_rate": 0.0002,
+      "loss": 0.4278,
+      "step": 1830
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.7506128549575806,
+      "eval_runtime": 46.2256,
+      "eval_samples_per_second": 9.432,
+      "eval_steps_per_second": 1.19,
+      "step": 1836
+    },
+    {
+      "epoch": 6.0130718954248366,
+      "grad_norm": 0.7339767813682556,
+      "learning_rate": 0.0002,
+      "loss": 0.3283,
+      "step": 1840
+    },
+    {
+      "epoch": 6.045751633986928,
+      "grad_norm": 1.1071710586547852,
+      "learning_rate": 0.0002,
+      "loss": 0.2304,
+      "step": 1850
+    },
+    {
+      "epoch": 6.078431372549019,
+      "grad_norm": 1.2613991498947144,
+      "learning_rate": 0.0002,
+      "loss": 0.2436,
+      "step": 1860
+    },
+    {
+      "epoch": 6.111111111111111,
+      "grad_norm": 1.053133249282837,
+      "learning_rate": 0.0002,
+      "loss": 0.2403,
+      "step": 1870
+    },
+    {
+      "epoch": 6.143790849673203,
+      "grad_norm": 1.069568395614624,
+      "learning_rate": 0.0002,
+      "loss": 0.2509,
+      "step": 1880
+    },
+    {
+      "epoch": 6.176470588235294,
+      "grad_norm": 1.020458698272705,
+      "learning_rate": 0.0002,
+      "loss": 0.2272,
+      "step": 1890
+    },
+    {
+      "epoch": 6.209150326797386,
+      "grad_norm": 1.2430394887924194,
+      "learning_rate": 0.0002,
+      "loss": 0.2408,
+      "step": 1900
+    },
+    {
+      "epoch": 6.241830065359477,
+      "grad_norm": 1.3475574254989624,
+      "learning_rate": 0.0002,
+      "loss": 0.229,
+      "step": 1910
+    },
+    {
+      "epoch": 6.2745098039215685,
+      "grad_norm": 0.9094598889350891,
+      "learning_rate": 0.0002,
+      "loss": 0.2542,
+      "step": 1920
+    },
+    {
+      "epoch": 6.30718954248366,
+      "grad_norm": 1.255650520324707,
+      "learning_rate": 0.0002,
+      "loss": 0.2009,
+      "step": 1930
+    },
+    {
+      "epoch": 6.339869281045751,
+      "grad_norm": 1.4193930625915527,
+      "learning_rate": 0.0002,
+      "loss": 0.25,
+      "step": 1940
+    },
+    {
+      "epoch": 6.372549019607844,
+      "grad_norm": 1.4378032684326172,
+      "learning_rate": 0.0002,
+      "loss": 0.293,
+      "step": 1950
+    },
+    {
+      "epoch": 6.405228758169935,
+      "grad_norm": 1.2236989736557007,
+      "learning_rate": 0.0002,
+      "loss": 0.2685,
+      "step": 1960
+    },
+    {
+      "epoch": 6.437908496732026,
+      "grad_norm": 1.0902987718582153,
+      "learning_rate": 0.0002,
+      "loss": 0.2608,
+      "step": 1970
+    },
+    {
+      "epoch": 6.470588235294118,
+      "grad_norm": 1.1165062189102173,
+      "learning_rate": 0.0002,
+      "loss": 0.2267,
+      "step": 1980
+    },
+    {
+      "epoch": 6.503267973856209,
+      "grad_norm": 1.3953566551208496,
+      "learning_rate": 0.0002,
+      "loss": 0.2246,
+      "step": 1990
+    },
+    {
+      "epoch": 6.5359477124183005,
+      "grad_norm": 1.5215585231781006,
+      "learning_rate": 0.0002,
+      "loss": 0.2834,
+      "step": 2000
+    },
+    {
+      "epoch": 6.568627450980392,
+      "grad_norm": 1.3496609926223755,
+      "learning_rate": 0.0002,
+      "loss": 0.2457,
+      "step": 2010
+    },
+    {
+      "epoch": 6.601307189542483,
+      "grad_norm": 1.2511820793151855,
+      "learning_rate": 0.0002,
+      "loss": 0.2637,
+      "step": 2020
+    },
+    {
+      "epoch": 6.633986928104575,
+      "grad_norm": 1.9875848293304443,
+      "learning_rate": 0.0002,
+      "loss": 0.2956,
+      "step": 2030
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 1.0766608715057373,
+      "learning_rate": 0.0002,
+      "loss": 0.2664,
+      "step": 2040
+    },
+    {
+      "epoch": 6.699346405228758,
+      "grad_norm": 1.3594712018966675,
+      "learning_rate": 0.0002,
+      "loss": 0.2792,
+      "step": 2050
+    },
+    {
+      "epoch": 6.73202614379085,
+      "grad_norm": 1.2357292175292969,
+      "learning_rate": 0.0002,
+      "loss": 0.3194,
+      "step": 2060
+    },
+    {
+      "epoch": 6.764705882352941,
+      "grad_norm": 1.2428375482559204,
+      "learning_rate": 0.0002,
+      "loss": 0.2526,
+      "step": 2070
+    },
+    {
+      "epoch": 6.7973856209150325,
+      "grad_norm": 1.2724156379699707,
+      "learning_rate": 0.0002,
+      "loss": 0.2355,
+      "step": 2080
+    },
+    {
+      "epoch": 6.830065359477124,
+      "grad_norm": 1.4981396198272705,
+      "learning_rate": 0.0002,
+      "loss": 0.289,
+      "step": 2090
+    },
+    {
+      "epoch": 6.862745098039216,
+      "grad_norm": 0.9346088171005249,
+      "learning_rate": 0.0002,
+      "loss": 0.2443,
+      "step": 2100
+    },
+    {
+      "epoch": 6.895424836601308,
+      "grad_norm": 1.3955477476119995,
+      "learning_rate": 0.0002,
+      "loss": 0.262,
+      "step": 2110
+    },
+    {
+      "epoch": 6.928104575163399,
+      "grad_norm": 1.492382287979126,
+      "learning_rate": 0.0002,
+      "loss": 0.2981,
+      "step": 2120
+    },
+    {
+      "epoch": 6.96078431372549,
+      "grad_norm": 1.2755712270736694,
+      "learning_rate": 0.0002,
+      "loss": 0.3093,
+      "step": 2130
+    },
+    {
+      "epoch": 6.993464052287582,
+      "grad_norm": 1.4600884914398193,
+      "learning_rate": 0.0002,
+      "loss": 0.2943,
+      "step": 2140
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.9770371913909912,
+      "eval_runtime": 46.2588,
+      "eval_samples_per_second": 9.425,
+      "eval_steps_per_second": 1.189,
+      "step": 2142
+    },
+    {
+      "epoch": 7.026143790849673,
+      "grad_norm": 1.205262541770935,
+      "learning_rate": 0.0002,
+      "loss": 0.2032,
+      "step": 2150
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "grad_norm": 1.1699777841567993,
+      "learning_rate": 0.0002,
+      "loss": 0.1642,
+      "step": 2160
+    },
+    {
+      "epoch": 7.091503267973856,
+      "grad_norm": 1.2428505420684814,
+      "learning_rate": 0.0002,
+      "loss": 0.1886,
+      "step": 2170
+    },
+    {
+      "epoch": 7.124183006535947,
+      "grad_norm": 0.9843717813491821,
+      "learning_rate": 0.0002,
+      "loss": 0.1762,
+      "step": 2180
+    },
+    {
+      "epoch": 7.1568627450980395,
+      "grad_norm": 1.089490532875061,
+      "learning_rate": 0.0002,
+      "loss": 0.1723,
+      "step": 2190
+    },
+    {
+      "epoch": 7.189542483660131,
+      "grad_norm": 1.2811459302902222,
+      "learning_rate": 0.0002,
+      "loss": 0.1721,
+      "step": 2200
+    },
+    {
+      "epoch": 7.222222222222222,
+      "grad_norm": 1.4558671712875366,
+      "learning_rate": 0.0002,
+      "loss": 0.1983,
+      "step": 2210
+    },
+    {
+      "epoch": 7.254901960784314,
+      "grad_norm": 1.2111164331436157,
+      "learning_rate": 0.0002,
+      "loss": 0.178,
+      "step": 2220
+    },
+    {
+      "epoch": 7.287581699346405,
+      "grad_norm": 1.46672785282135,
+      "learning_rate": 0.0002,
+      "loss": 0.1463,
+      "step": 2230
+    },
+    {
+      "epoch": 7.3202614379084965,
+      "grad_norm": 1.464061975479126,
+      "learning_rate": 0.0002,
+      "loss": 0.1883,
+      "step": 2240
+    },
+    {
+      "epoch": 7.352941176470588,
+      "grad_norm": 1.6276377439498901,
+      "learning_rate": 0.0002,
+      "loss": 0.2276,
+      "step": 2250
+    },
+    {
+      "epoch": 7.38562091503268,
+      "grad_norm": 1.4011811017990112,
+      "learning_rate": 0.0002,
+      "loss": 0.1771,
+      "step": 2260
+    },
+    {
+      "epoch": 7.4183006535947715,
+      "grad_norm": 0.9894806146621704,
+      "learning_rate": 0.0002,
+      "loss": 0.1875,
+      "step": 2270
+    },
+    {
+      "epoch": 7.450980392156863,
+      "grad_norm": 0.9357670545578003,
+      "learning_rate": 0.0002,
+      "loss": 0.1725,
+      "step": 2280
+    },
+    {
+      "epoch": 7.483660130718954,
+      "grad_norm": 1.7790061235427856,
+      "learning_rate": 0.0002,
+      "loss": 0.1891,
+      "step": 2290
+    },
+    {
+      "epoch": 7.516339869281046,
+      "grad_norm": 1.468843698501587,
+      "learning_rate": 0.0002,
+      "loss": 0.1967,
+      "step": 2300
+    },
+    {
+      "epoch": 7.549019607843137,
+      "grad_norm": 1.063189148902893,
+      "learning_rate": 0.0002,
+      "loss": 0.195,
+      "step": 2310
+    },
+    {
+      "epoch": 7.5816993464052285,
+      "grad_norm": 0.7940694689750671,
+      "learning_rate": 0.0002,
+      "loss": 0.1752,
+      "step": 2320
+    },
+    {
+      "epoch": 7.61437908496732,
+      "grad_norm": 1.555564045906067,
+      "learning_rate": 0.0002,
+      "loss": 0.2169,
+      "step": 2330
+    },
+    {
+      "epoch": 7.647058823529412,
+      "grad_norm": 0.7388061881065369,
+      "learning_rate": 0.0002,
+      "loss": 0.1755,
+      "step": 2340
+    },
+    {
+      "epoch": 7.6797385620915035,
+      "grad_norm": 1.2422513961791992,
+      "learning_rate": 0.0002,
+      "loss": 0.2206,
+      "step": 2350
+    },
+    {
+      "epoch": 7.712418300653595,
+      "grad_norm": 1.3868855237960815,
+      "learning_rate": 0.0002,
+      "loss": 0.2015,
+      "step": 2360
+    },
+    {
+      "epoch": 7.745098039215686,
+      "grad_norm": 1.2965079545974731,
+      "learning_rate": 0.0002,
+      "loss": 0.1888,
+      "step": 2370
+    },
+    {
+      "epoch": 7.777777777777778,
+      "grad_norm": 1.4052339792251587,
+      "learning_rate": 0.0002,
+      "loss": 0.2257,
+      "step": 2380
+    },
+    {
+      "epoch": 7.810457516339869,
+      "grad_norm": 1.9005945920944214,
+      "learning_rate": 0.0002,
+      "loss": 0.2145,
+      "step": 2390
+    },
+    {
+      "epoch": 7.8431372549019605,
+      "grad_norm": 0.9947215914726257,
+      "learning_rate": 0.0002,
+      "loss": 0.2154,
+      "step": 2400
+    },
+    {
+      "epoch": 7.875816993464053,
+      "grad_norm": 0.796757698059082,
+      "learning_rate": 0.0002,
+      "loss": 0.1841,
+      "step": 2410
+    },
+    {
+      "epoch": 7.908496732026144,
+      "grad_norm": 2.4196858406066895,
+      "learning_rate": 0.0002,
+      "loss": 0.2476,
+      "step": 2420
+    },
+    {
+      "epoch": 7.9411764705882355,
+      "grad_norm": 1.7430493831634521,
+      "learning_rate": 0.0002,
+      "loss": 0.2136,
+      "step": 2430
+    },
+    {
+      "epoch": 7.973856209150327,
+      "grad_norm": 1.0432168245315552,
+      "learning_rate": 0.0002,
+      "loss": 0.2053,
+      "step": 2440
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.267362356185913,
+      "eval_runtime": 46.2388,
+      "eval_samples_per_second": 9.429,
+      "eval_steps_per_second": 1.189,
+      "step": 2448
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2448,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2573844929773568e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/training_args.bin b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e7fb8100bbfe18f1342e5fc87e32e8e798268e3b
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-2448/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e66621362aa4eab196083c9a4bd0bf843b2425d7109d63be3ab5f4006691dd1
+size 5560
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/README.md b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/adapter_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/adapter_model.safetensors b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1edf24ee4cadcc04acc1504ec06cbb61422ed17b
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230681bf5243219bb35baf9f833a124d007877d8340320327edd113ecb7b143d
+size 143153376
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/optimizer.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c9da28b3935caf42e2a919220e7900268864181a
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91cbee641f98a3cde44341c640d36578bd48cad6ef3fb6647875183555308dc1
+size 72886650
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/rng_state.pth b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8176904e301bb5c02f9b815bdbca4b9b39921f71
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a652197f45495263a8d6ed01735d5c581d6b93ff6ee3f05b0166b309d15f9a24
+size 14244
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/scheduler.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d6a5305e91aa357e406ba671b5468558cd08ddba
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2737a31bade0c3c61d75256b61229477411c368f4ee01fd483bd841307ca525a
+size 1064
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/special_tokens_map.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/special_tokens_map.json
@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/tokenizer.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/tokenizer.model b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/tokenizer_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/tokenizer_config.json
@@ -0,0 +1,2013 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/trainer_state.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..852ff0a273d12a4e2f8e7d9c8214c3c8b2ea0c91
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/trainer_state.json
@@ -0,0 +1,251 @@
+{
+  "best_metric": 1.1937541961669922,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306",
+  "epoch": 1.0,
+  "eval_steps": 10,
+  "global_step": 306,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032679738562091505,
+      "grad_norm": 0.631856381893158,
+      "learning_rate": 0.0002,
+      "loss": 2.3561,
+      "step": 10
+    },
+    {
+      "epoch": 0.06535947712418301,
+      "grad_norm": 0.5065668821334839,
+      "learning_rate": 0.0002,
+      "loss": 1.8141,
+      "step": 20
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 0.6978895664215088,
+      "learning_rate": 0.0002,
+      "loss": 1.4952,
+      "step": 30
+    },
+    {
+      "epoch": 0.13071895424836602,
+      "grad_norm": 0.6619144082069397,
+      "learning_rate": 0.0002,
+      "loss": 1.4829,
+      "step": 40
+    },
+    {
+      "epoch": 0.16339869281045752,
+      "grad_norm": 0.6153793931007385,
+      "learning_rate": 0.0002,
+      "loss": 1.3038,
+      "step": 50
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.4703301787376404,
+      "learning_rate": 0.0002,
+      "loss": 1.1429,
+      "step": 60
+    },
+    {
+      "epoch": 0.22875816993464052,
+      "grad_norm": 1.1672580242156982,
+      "learning_rate": 0.0002,
+      "loss": 1.2828,
+      "step": 70
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 0.3455565273761749,
+      "learning_rate": 0.0002,
+      "loss": 1.0985,
+      "step": 80
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.36216291785240173,
+      "learning_rate": 0.0002,
+      "loss": 1.1359,
+      "step": 90
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "grad_norm": 0.4545166492462158,
+      "learning_rate": 0.0002,
+      "loss": 1.2544,
+      "step": 100
+    },
+    {
+      "epoch": 0.35947712418300654,
+      "grad_norm": 0.3612092435359955,
+      "learning_rate": 0.0002,
+      "loss": 1.2287,
+      "step": 110
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.5080830454826355,
+      "learning_rate": 0.0002,
+      "loss": 1.1868,
+      "step": 120
+    },
+    {
+      "epoch": 0.42483660130718953,
+      "grad_norm": 0.3268195390701294,
+      "learning_rate": 0.0002,
+      "loss": 1.1902,
+      "step": 130
+    },
+    {
+      "epoch": 0.45751633986928103,
+      "grad_norm": 0.33971714973449707,
+      "learning_rate": 0.0002,
+      "loss": 1.247,
+      "step": 140
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 0.4036043882369995,
+      "learning_rate": 0.0002,
+      "loss": 1.1844,
+      "step": 150
+    },
+    {
+      "epoch": 0.5228758169934641,
+      "grad_norm": 0.35938864946365356,
+      "learning_rate": 0.0002,
+      "loss": 1.1624,
+      "step": 160
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.28880223631858826,
+      "learning_rate": 0.0002,
+      "loss": 1.164,
+      "step": 170
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.3436269462108612,
+      "learning_rate": 0.0002,
+      "loss": 1.3521,
+      "step": 180
+    },
+    {
+      "epoch": 0.6209150326797386,
+      "grad_norm": 0.41923725605010986,
+      "learning_rate": 0.0002,
+      "loss": 1.2456,
+      "step": 190
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "grad_norm": 0.25119203329086304,
+      "learning_rate": 0.0002,
+      "loss": 1.2226,
+      "step": 200
+    },
+    {
+      "epoch": 0.6862745098039216,
+      "grad_norm": 0.5870180726051331,
+      "learning_rate": 0.0002,
+      "loss": 1.1568,
+      "step": 210
+    },
+    {
+      "epoch": 0.7189542483660131,
+      "grad_norm": 0.2831224203109741,
+      "learning_rate": 0.0002,
+      "loss": 1.064,
+      "step": 220
+    },
+    {
+      "epoch": 0.7516339869281046,
+      "grad_norm": 0.3192005753517151,
+      "learning_rate": 0.0002,
+      "loss": 1.2469,
+      "step": 230
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.2998219430446625,
+      "learning_rate": 0.0002,
+      "loss": 1.1613,
+      "step": 240
+    },
+    {
+      "epoch": 0.8169934640522876,
+      "grad_norm": 0.32855790853500366,
+      "learning_rate": 0.0002,
+      "loss": 1.205,
+      "step": 250
+    },
+    {
+      "epoch": 0.8496732026143791,
+      "grad_norm": 0.3403124213218689,
+      "learning_rate": 0.0002,
+      "loss": 1.1631,
+      "step": 260
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.277401328086853,
+      "learning_rate": 0.0002,
+      "loss": 1.1646,
+      "step": 270
+    },
+    {
+      "epoch": 0.9150326797385621,
+      "grad_norm": 0.2975269556045532,
+      "learning_rate": 0.0002,
+      "loss": 1.084,
+      "step": 280
+    },
+    {
+      "epoch": 0.9477124183006536,
+      "grad_norm": 1.7909578084945679,
+      "learning_rate": 0.0002,
+      "loss": 1.2039,
+      "step": 290
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 0.2917245328426361,
+      "learning_rate": 0.0002,
+      "loss": 1.1226,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1937541961669922,
+      "eval_runtime": 46.2571,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 306
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2448,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.571730616221696e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/training_args.bin b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e7fb8100bbfe18f1342e5fc87e32e8e798268e3b
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e66621362aa4eab196083c9a4bd0bf843b2425d7109d63be3ab5f4006691dd1
+size 5560
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/README.md b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/adapter_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/adapter_model.safetensors b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2914583db0507b14a5bcd3d237d124baf41adf2d
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93008ec421c7a3492809b1931e60a60b7e286cb520e0ba8266c8862b2ae048ef
+size 143153376
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/optimizer.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0f420b92573242ad17878f0879e17cfb7d9f6fb3
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ea03e3f874fa525cf92b58d1cef19cd1f3b877f72d27e4032797302e8a17262
+size 72886650
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/rng_state.pth b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d01faf1aeb8b9794df153b175963d4b0ed6ad22b
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ce3a7fcd5cd53f7179a619892f1f719be4fc9bb92dc0937e3c2762a64412c5
+size 14244
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/scheduler.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..158a77b829de4b5d6071e89d482ad5a7ee259eec
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd201f99b49f06e01aa3df0f7df59fbc2c43546fb5710460cca23f33754c7ff
+size 1064
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/special_tokens_map.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/special_tokens_map.json
@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/tokenizer.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/tokenizer.model b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/tokenizer_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/tokenizer_config.json
@@ -0,0 +1,2013 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/trainer_state.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b652e6c26830d5e3b390a072760290ef3f020bf5
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/trainer_state.json
@@ -0,0 +1,476 @@
+{
+  "best_metric": 1.1845070123672485,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612",
+  "epoch": 2.0,
+  "eval_steps": 10,
+  "global_step": 612,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032679738562091505,
+      "grad_norm": 0.631856381893158,
+      "learning_rate": 0.0002,
+      "loss": 2.3561,
+      "step": 10
+    },
+    {
+      "epoch": 0.06535947712418301,
+      "grad_norm": 0.5065668821334839,
+      "learning_rate": 0.0002,
+      "loss": 1.8141,
+      "step": 20
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 0.6978895664215088,
+      "learning_rate": 0.0002,
+      "loss": 1.4952,
+      "step": 30
+    },
+    {
+      "epoch": 0.13071895424836602,
+      "grad_norm": 0.6619144082069397,
+      "learning_rate": 0.0002,
+      "loss": 1.4829,
+      "step": 40
+    },
+    {
+      "epoch": 0.16339869281045752,
+      "grad_norm": 0.6153793931007385,
+      "learning_rate": 0.0002,
+      "loss": 1.3038,
+      "step": 50
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.4703301787376404,
+      "learning_rate": 0.0002,
+      "loss": 1.1429,
+      "step": 60
+    },
+    {
+      "epoch": 0.22875816993464052,
+      "grad_norm": 1.1672580242156982,
+      "learning_rate": 0.0002,
+      "loss": 1.2828,
+      "step": 70
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 0.3455565273761749,
+      "learning_rate": 0.0002,
+      "loss": 1.0985,
+      "step": 80
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.36216291785240173,
+      "learning_rate": 0.0002,
+      "loss": 1.1359,
+      "step": 90
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "grad_norm": 0.4545166492462158,
+      "learning_rate": 0.0002,
+      "loss": 1.2544,
+      "step": 100
+    },
+    {
+      "epoch": 0.35947712418300654,
+      "grad_norm": 0.3612092435359955,
+      "learning_rate": 0.0002,
+      "loss": 1.2287,
+      "step": 110
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.5080830454826355,
+      "learning_rate": 0.0002,
+      "loss": 1.1868,
+      "step": 120
+    },
+    {
+      "epoch": 0.42483660130718953,
+      "grad_norm": 0.3268195390701294,
+      "learning_rate": 0.0002,
+      "loss": 1.1902,
+      "step": 130
+    },
+    {
+      "epoch": 0.45751633986928103,
+      "grad_norm": 0.33971714973449707,
+      "learning_rate": 0.0002,
+      "loss": 1.247,
+      "step": 140
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 0.4036043882369995,
+      "learning_rate": 0.0002,
+      "loss": 1.1844,
+      "step": 150
+    },
+    {
+      "epoch": 0.5228758169934641,
+      "grad_norm": 0.35938864946365356,
+      "learning_rate": 0.0002,
+      "loss": 1.1624,
+      "step": 160
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.28880223631858826,
+      "learning_rate": 0.0002,
+      "loss": 1.164,
+      "step": 170
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.3436269462108612,
+      "learning_rate": 0.0002,
+      "loss": 1.3521,
+      "step": 180
+    },
+    {
+      "epoch": 0.6209150326797386,
+      "grad_norm": 0.41923725605010986,
+      "learning_rate": 0.0002,
+      "loss": 1.2456,
+      "step": 190
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "grad_norm": 0.25119203329086304,
+      "learning_rate": 0.0002,
+      "loss": 1.2226,
+      "step": 200
+    },
+    {
+      "epoch": 0.6862745098039216,
+      "grad_norm": 0.5870180726051331,
+      "learning_rate": 0.0002,
+      "loss": 1.1568,
+      "step": 210
+    },
+    {
+      "epoch": 0.7189542483660131,
+      "grad_norm": 0.2831224203109741,
+      "learning_rate": 0.0002,
+      "loss": 1.064,
+      "step": 220
+    },
+    {
+      "epoch": 0.7516339869281046,
+      "grad_norm": 0.3192005753517151,
+      "learning_rate": 0.0002,
+      "loss": 1.2469,
+      "step": 230
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.2998219430446625,
+      "learning_rate": 0.0002,
+      "loss": 1.1613,
+      "step": 240
+    },
+    {
+      "epoch": 0.8169934640522876,
+      "grad_norm": 0.32855790853500366,
+      "learning_rate": 0.0002,
+      "loss": 1.205,
+      "step": 250
+    },
+    {
+      "epoch": 0.8496732026143791,
+      "grad_norm": 0.3403124213218689,
+      "learning_rate": 0.0002,
+      "loss": 1.1631,
+      "step": 260
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.277401328086853,
+      "learning_rate": 0.0002,
+      "loss": 1.1646,
+      "step": 270
+    },
+    {
+      "epoch": 0.9150326797385621,
+      "grad_norm": 0.2975269556045532,
+      "learning_rate": 0.0002,
+      "loss": 1.084,
+      "step": 280
+    },
+    {
+      "epoch": 0.9477124183006536,
+      "grad_norm": 1.7909578084945679,
+      "learning_rate": 0.0002,
+      "loss": 1.2039,
+      "step": 290
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 0.2917245328426361,
+      "learning_rate": 0.0002,
+      "loss": 1.1226,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1937541961669922,
+      "eval_runtime": 46.2571,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 306
+    },
+    {
+      "epoch": 1.0130718954248366,
+      "grad_norm": 0.26494982838630676,
+      "learning_rate": 0.0002,
+      "loss": 1.2011,
+      "step": 310
+    },
+    {
+      "epoch": 1.0457516339869282,
+      "grad_norm": 0.6289355754852295,
+      "learning_rate": 0.0002,
+      "loss": 1.0565,
+      "step": 320
+    },
+    {
+      "epoch": 1.0784313725490196,
+      "grad_norm": 0.26784011721611023,
+      "learning_rate": 0.0002,
+      "loss": 1.1619,
+      "step": 330
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.3392215967178345,
+      "learning_rate": 0.0002,
+      "loss": 1.1151,
+      "step": 340
+    },
+    {
+      "epoch": 1.1437908496732025,
+      "grad_norm": 0.40005937218666077,
+      "learning_rate": 0.0002,
+      "loss": 1.0752,
+      "step": 350
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.3590582013130188,
+      "learning_rate": 0.0002,
+      "loss": 1.0408,
+      "step": 360
+    },
+    {
+      "epoch": 1.2091503267973855,
+      "grad_norm": 0.3995305895805359,
+      "learning_rate": 0.0002,
+      "loss": 1.0836,
+      "step": 370
+    },
+    {
+      "epoch": 1.2418300653594772,
+      "grad_norm": 0.2950291633605957,
+      "learning_rate": 0.0002,
+      "loss": 1.0992,
+      "step": 380
+    },
+    {
+      "epoch": 1.2745098039215685,
+      "grad_norm": 0.32035166025161743,
+      "learning_rate": 0.0002,
+      "loss": 1.1152,
+      "step": 390
+    },
+    {
+      "epoch": 1.3071895424836601,
+      "grad_norm": 0.410366415977478,
+      "learning_rate": 0.0002,
+      "loss": 1.1467,
+      "step": 400
+    },
+    {
+      "epoch": 1.3398692810457518,
+      "grad_norm": 0.3106379508972168,
+      "learning_rate": 0.0002,
+      "loss": 0.9985,
+      "step": 410
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 0.38580670952796936,
+      "learning_rate": 0.0002,
+      "loss": 0.9789,
+      "step": 420
+    },
+    {
+      "epoch": 1.4052287581699345,
+      "grad_norm": 0.34411361813545227,
+      "learning_rate": 0.0002,
+      "loss": 1.0931,
+      "step": 430
+    },
+    {
+      "epoch": 1.4379084967320261,
+      "grad_norm": 0.44206851720809937,
+      "learning_rate": 0.0002,
+      "loss": 1.1685,
+      "step": 440
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.3492952585220337,
+      "learning_rate": 0.0002,
+      "loss": 1.0347,
+      "step": 450
+    },
+    {
+      "epoch": 1.5032679738562091,
+      "grad_norm": 0.376423716545105,
+      "learning_rate": 0.0002,
+      "loss": 1.0534,
+      "step": 460
+    },
+    {
+      "epoch": 1.5359477124183005,
+      "grad_norm": 0.359757661819458,
+      "learning_rate": 0.0002,
+      "loss": 1.1162,
+      "step": 470
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 0.3385067880153656,
+      "learning_rate": 0.0002,
+      "loss": 0.9586,
+      "step": 480
+    },
+    {
+      "epoch": 1.6013071895424837,
+      "grad_norm": 0.4943889379501343,
+      "learning_rate": 0.0002,
+      "loss": 1.0807,
+      "step": 490
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 0.4203241169452667,
+      "learning_rate": 0.0002,
+      "loss": 1.0796,
+      "step": 500
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.3093789219856262,
+      "learning_rate": 0.0002,
+      "loss": 1.1059,
+      "step": 510
+    },
+    {
+      "epoch": 1.6993464052287581,
+      "grad_norm": 0.3653067350387573,
+      "learning_rate": 0.0002,
+      "loss": 1.0323,
+      "step": 520
+    },
+    {
+      "epoch": 1.7320261437908497,
+      "grad_norm": 0.36761337518692017,
+      "learning_rate": 0.0002,
+      "loss": 1.0885,
+      "step": 530
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.5040399432182312,
+      "learning_rate": 0.0002,
+      "loss": 1.1698,
+      "step": 540
+    },
+    {
+      "epoch": 1.7973856209150327,
+      "grad_norm": 0.3818035125732422,
+      "learning_rate": 0.0002,
+      "loss": 1.0105,
+      "step": 550
+    },
+    {
+      "epoch": 1.8300653594771243,
+      "grad_norm": 0.4021618664264679,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 560
+    },
+    {
+      "epoch": 1.8627450980392157,
+      "grad_norm": 0.3986459970474243,
+      "learning_rate": 0.0002,
+      "loss": 1.0358,
+      "step": 570
+    },
+    {
+      "epoch": 1.8954248366013071,
+      "grad_norm": 0.48416733741760254,
+      "learning_rate": 0.0002,
+      "loss": 1.003,
+      "step": 580
+    },
+    {
+      "epoch": 1.9281045751633987,
+      "grad_norm": 0.36853986978530884,
+      "learning_rate": 0.0002,
+      "loss": 1.1146,
+      "step": 590
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.383022665977478,
+      "learning_rate": 0.0002,
+      "loss": 1.0689,
+      "step": 600
+    },
+    {
+      "epoch": 1.9934640522875817,
+      "grad_norm": 0.3169507086277008,
+      "learning_rate": 0.0002,
+      "loss": 1.098,
+      "step": 610
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1845070123672485,
+      "eval_runtime": 46.2811,
+      "eval_samples_per_second": 9.421,
+      "eval_steps_per_second": 1.188,
+      "step": 612
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2448,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.143461232443392e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/training_args.bin b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e7fb8100bbfe18f1342e5fc87e32e8e798268e3b
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e66621362aa4eab196083c9a4bd0bf843b2425d7109d63be3ab5f4006691dd1
+size 5560
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/README.md b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/README.md
@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/adapter_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/adapter_model.safetensors b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..59d65db48836bfe0ef605bfa7cd536d39f19682e
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:333a1f7cd97a1519fa2bf79b681920b9d489b8c24815bff2dbbb8d9d6a94a2c3
+size 143153376
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/optimizer.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ac3ca5d7e4a823dfc7056dfe2cd58b00eb219505
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1548a10f56596ad71632e59372b11e84d3d16ced48bc523a6b2cfbef7f6357aa
+size 72886650
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/rng_state.pth b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..950d6ef77c3bf6ab948deec1d6281b128a25a551
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c74af3530660bab801a8ab3745f732675c92e87cf6a7368f8d53a1c2a0c3453
+size 14244
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/scheduler.pt b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1fb300a3f7d7cc9ed714944aa5dd73eca56c827f
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b19d92e4fc21e9c90f025ac58543229cd4f340397ea61c83f015e60019e3d85
+size 1064
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/special_tokens_map.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/special_tokens_map.json
@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/tokenizer.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/tokenizer.model b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/tokenizer_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/tokenizer_config.json
@@ -0,0 +1,2013 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/trainer_state.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..cf990d703919caa83cd874168246c11c39f3ae8e
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/trainer_state.json
@@ -0,0 +1,694 @@
+{
+  "best_metric": 1.1845070123672485,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612",
+  "epoch": 3.0,
+  "eval_steps": 10,
+  "global_step": 918,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032679738562091505,
+      "grad_norm": 0.631856381893158,
+      "learning_rate": 0.0002,
+      "loss": 2.3561,
+      "step": 10
+    },
+    {
+      "epoch": 0.06535947712418301,
+      "grad_norm": 0.5065668821334839,
+      "learning_rate": 0.0002,
+      "loss": 1.8141,
+      "step": 20
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 0.6978895664215088,
+      "learning_rate": 0.0002,
+      "loss": 1.4952,
+      "step": 30
+    },
+    {
+      "epoch": 0.13071895424836602,
+      "grad_norm": 0.6619144082069397,
+      "learning_rate": 0.0002,
+      "loss": 1.4829,
+      "step": 40
+    },
+    {
+      "epoch": 0.16339869281045752,
+      "grad_norm": 0.6153793931007385,
+      "learning_rate": 0.0002,
+      "loss": 1.3038,
+      "step": 50
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.4703301787376404,
+      "learning_rate": 0.0002,
+      "loss": 1.1429,
+      "step": 60
+    },
+    {
+      "epoch": 0.22875816993464052,
+      "grad_norm": 1.1672580242156982,
+      "learning_rate": 0.0002,
+      "loss": 1.2828,
+      "step": 70
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 0.3455565273761749,
+      "learning_rate": 0.0002,
+      "loss": 1.0985,
+      "step": 80
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.36216291785240173,
+      "learning_rate": 0.0002,
+      "loss": 1.1359,
+      "step": 90
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "grad_norm": 0.4545166492462158,
+      "learning_rate": 0.0002,
+      "loss": 1.2544,
+      "step": 100
+    },
+    {
+      "epoch": 0.35947712418300654,
+      "grad_norm": 0.3612092435359955,
+      "learning_rate": 0.0002,
+      "loss": 1.2287,
+      "step": 110
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.5080830454826355,
+      "learning_rate": 0.0002,
+      "loss": 1.1868,
+      "step": 120
+    },
+    {
+      "epoch": 0.42483660130718953,
+      "grad_norm": 0.3268195390701294,
+      "learning_rate": 0.0002,
+      "loss": 1.1902,
+      "step": 130
+    },
+    {
+      "epoch": 0.45751633986928103,
+      "grad_norm": 0.33971714973449707,
+      "learning_rate": 0.0002,
+      "loss": 1.247,
+      "step": 140
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 0.4036043882369995,
+      "learning_rate": 0.0002,
+      "loss": 1.1844,
+      "step": 150
+    },
+    {
+      "epoch": 0.5228758169934641,
+      "grad_norm": 0.35938864946365356,
+      "learning_rate": 0.0002,
+      "loss": 1.1624,
+      "step": 160
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.28880223631858826,
+      "learning_rate": 0.0002,
+      "loss": 1.164,
+      "step": 170
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.3436269462108612,
+      "learning_rate": 0.0002,
+      "loss": 1.3521,
+      "step": 180
+    },
+    {
+      "epoch": 0.6209150326797386,
+      "grad_norm": 0.41923725605010986,
+      "learning_rate": 0.0002,
+      "loss": 1.2456,
+      "step": 190
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "grad_norm": 0.25119203329086304,
+      "learning_rate": 0.0002,
+      "loss": 1.2226,
+      "step": 200
+    },
+    {
+      "epoch": 0.6862745098039216,
+      "grad_norm": 0.5870180726051331,
+      "learning_rate": 0.0002,
+      "loss": 1.1568,
+      "step": 210
+    },
+    {
+      "epoch": 0.7189542483660131,
+      "grad_norm": 0.2831224203109741,
+      "learning_rate": 0.0002,
+      "loss": 1.064,
+      "step": 220
+    },
+    {
+      "epoch": 0.7516339869281046,
+      "grad_norm": 0.3192005753517151,
+      "learning_rate": 0.0002,
+      "loss": 1.2469,
+      "step": 230
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.2998219430446625,
+      "learning_rate": 0.0002,
+      "loss": 1.1613,
+      "step": 240
+    },
+    {
+      "epoch": 0.8169934640522876,
+      "grad_norm": 0.32855790853500366,
+      "learning_rate": 0.0002,
+      "loss": 1.205,
+      "step": 250
+    },
+    {
+      "epoch": 0.8496732026143791,
+      "grad_norm": 0.3403124213218689,
+      "learning_rate": 0.0002,
+      "loss": 1.1631,
+      "step": 260
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.277401328086853,
+      "learning_rate": 0.0002,
+      "loss": 1.1646,
+      "step": 270
+    },
+    {
+      "epoch": 0.9150326797385621,
+      "grad_norm": 0.2975269556045532,
+      "learning_rate": 0.0002,
+      "loss": 1.084,
+      "step": 280
+    },
+    {
+      "epoch": 0.9477124183006536,
+      "grad_norm": 1.7909578084945679,
+      "learning_rate": 0.0002,
+      "loss": 1.2039,
+      "step": 290
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 0.2917245328426361,
+      "learning_rate": 0.0002,
+      "loss": 1.1226,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1937541961669922,
+      "eval_runtime": 46.2571,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 306
+    },
+    {
+      "epoch": 1.0130718954248366,
+      "grad_norm": 0.26494982838630676,
+      "learning_rate": 0.0002,
+      "loss": 1.2011,
+      "step": 310
+    },
+    {
+      "epoch": 1.0457516339869282,
+      "grad_norm": 0.6289355754852295,
+      "learning_rate": 0.0002,
+      "loss": 1.0565,
+      "step": 320
+    },
+    {
+      "epoch": 1.0784313725490196,
+      "grad_norm": 0.26784011721611023,
+      "learning_rate": 0.0002,
+      "loss": 1.1619,
+      "step": 330
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.3392215967178345,
+      "learning_rate": 0.0002,
+      "loss": 1.1151,
+      "step": 340
+    },
+    {
+      "epoch": 1.1437908496732025,
+      "grad_norm": 0.40005937218666077,
+      "learning_rate": 0.0002,
+      "loss": 1.0752,
+      "step": 350
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.3590582013130188,
+      "learning_rate": 0.0002,
+      "loss": 1.0408,
+      "step": 360
+    },
+    {
+      "epoch": 1.2091503267973855,
+      "grad_norm": 0.3995305895805359,
+      "learning_rate": 0.0002,
+      "loss": 1.0836,
+      "step": 370
+    },
+    {
+      "epoch": 1.2418300653594772,
+      "grad_norm": 0.2950291633605957,
+      "learning_rate": 0.0002,
+      "loss": 1.0992,
+      "step": 380
+    },
+    {
+      "epoch": 1.2745098039215685,
+      "grad_norm": 0.32035166025161743,
+      "learning_rate": 0.0002,
+      "loss": 1.1152,
+      "step": 390
+    },
+    {
+      "epoch": 1.3071895424836601,
+      "grad_norm": 0.410366415977478,
+      "learning_rate": 0.0002,
+      "loss": 1.1467,
+      "step": 400
+    },
+    {
+      "epoch": 1.3398692810457518,
+      "grad_norm": 0.3106379508972168,
+      "learning_rate": 0.0002,
+      "loss": 0.9985,
+      "step": 410
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 0.38580670952796936,
+      "learning_rate": 0.0002,
+      "loss": 0.9789,
+      "step": 420
+    },
+    {
+      "epoch": 1.4052287581699345,
+      "grad_norm": 0.34411361813545227,
+      "learning_rate": 0.0002,
+      "loss": 1.0931,
+      "step": 430
+    },
+    {
+      "epoch": 1.4379084967320261,
+      "grad_norm": 0.44206851720809937,
+      "learning_rate": 0.0002,
+      "loss": 1.1685,
+      "step": 440
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.3492952585220337,
+      "learning_rate": 0.0002,
+      "loss": 1.0347,
+      "step": 450
+    },
+    {
+      "epoch": 1.5032679738562091,
+      "grad_norm": 0.376423716545105,
+      "learning_rate": 0.0002,
+      "loss": 1.0534,
+      "step": 460
+    },
+    {
+      "epoch": 1.5359477124183005,
+      "grad_norm": 0.359757661819458,
+      "learning_rate": 0.0002,
+      "loss": 1.1162,
+      "step": 470
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 0.3385067880153656,
+      "learning_rate": 0.0002,
+      "loss": 0.9586,
+      "step": 480
+    },
+    {
+      "epoch": 1.6013071895424837,
+      "grad_norm": 0.4943889379501343,
+      "learning_rate": 0.0002,
+      "loss": 1.0807,
+      "step": 490
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 0.4203241169452667,
+      "learning_rate": 0.0002,
+      "loss": 1.0796,
+      "step": 500
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.3093789219856262,
+      "learning_rate": 0.0002,
+      "loss": 1.1059,
+      "step": 510
+    },
+    {
+      "epoch": 1.6993464052287581,
+      "grad_norm": 0.3653067350387573,
+      "learning_rate": 0.0002,
+      "loss": 1.0323,
+      "step": 520
+    },
+    {
+      "epoch": 1.7320261437908497,
+      "grad_norm": 0.36761337518692017,
+      "learning_rate": 0.0002,
+      "loss": 1.0885,
+      "step": 530
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.5040399432182312,
+      "learning_rate": 0.0002,
+      "loss": 1.1698,
+      "step": 540
+    },
+    {
+      "epoch": 1.7973856209150327,
+      "grad_norm": 0.3818035125732422,
+      "learning_rate": 0.0002,
+      "loss": 1.0105,
+      "step": 550
+    },
+    {
+      "epoch": 1.8300653594771243,
+      "grad_norm": 0.4021618664264679,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 560
+    },
+    {
+      "epoch": 1.8627450980392157,
+      "grad_norm": 0.3986459970474243,
+      "learning_rate": 0.0002,
+      "loss": 1.0358,
+      "step": 570
+    },
+    {
+      "epoch": 1.8954248366013071,
+      "grad_norm": 0.48416733741760254,
+      "learning_rate": 0.0002,
+      "loss": 1.003,
+      "step": 580
+    },
+    {
+      "epoch": 1.9281045751633987,
+      "grad_norm": 0.36853986978530884,
+      "learning_rate": 0.0002,
+      "loss": 1.1146,
+      "step": 590
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.383022665977478,
+      "learning_rate": 0.0002,
+      "loss": 1.0689,
+      "step": 600
+    },
+    {
+      "epoch": 1.9934640522875817,
+      "grad_norm": 0.3169507086277008,
+      "learning_rate": 0.0002,
+      "loss": 1.098,
+      "step": 610
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1845070123672485,
+      "eval_runtime": 46.2811,
+      "eval_samples_per_second": 9.421,
+      "eval_steps_per_second": 1.188,
+      "step": 612
+    },
+    {
+      "epoch": 2.026143790849673,
+      "grad_norm": 0.8920142650604248,
+      "learning_rate": 0.0002,
+      "loss": 0.9618,
+      "step": 620
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.4814859628677368,
+      "learning_rate": 0.0002,
+      "loss": 0.9784,
+      "step": 630
+    },
+    {
+      "epoch": 2.0915032679738563,
+      "grad_norm": 0.4251559376716614,
+      "learning_rate": 0.0002,
+      "loss": 0.8464,
+      "step": 640
+    },
+    {
+      "epoch": 2.1241830065359477,
+      "grad_norm": 0.5295765399932861,
+      "learning_rate": 0.0002,
+      "loss": 0.932,
+      "step": 650
+    },
+    {
+      "epoch": 2.156862745098039,
+      "grad_norm": 0.45016610622406006,
+      "learning_rate": 0.0002,
+      "loss": 0.9603,
+      "step": 660
+    },
+    {
+      "epoch": 2.189542483660131,
+      "grad_norm": 0.5870586633682251,
+      "learning_rate": 0.0002,
+      "loss": 0.8738,
+      "step": 670
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.5174715518951416,
+      "learning_rate": 0.0002,
+      "loss": 0.9483,
+      "step": 680
+    },
+    {
+      "epoch": 2.2549019607843137,
+      "grad_norm": 0.5252485275268555,
+      "learning_rate": 0.0002,
+      "loss": 0.9551,
+      "step": 690
+    },
+    {
+      "epoch": 2.287581699346405,
+      "grad_norm": 0.5158312320709229,
+      "learning_rate": 0.0002,
+      "loss": 0.9253,
+      "step": 700
+    },
+    {
+      "epoch": 2.3202614379084965,
+      "grad_norm": 0.4824209213256836,
+      "learning_rate": 0.0002,
+      "loss": 0.9278,
+      "step": 710
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.6335175037384033,
+      "learning_rate": 0.0002,
+      "loss": 0.8804,
+      "step": 720
+    },
+    {
+      "epoch": 2.3856209150326797,
+      "grad_norm": 0.5240563154220581,
+      "learning_rate": 0.0002,
+      "loss": 0.9685,
+      "step": 730
+    },
+    {
+      "epoch": 2.418300653594771,
+      "grad_norm": 0.5172886252403259,
+      "learning_rate": 0.0002,
+      "loss": 0.8794,
+      "step": 740
+    },
+    {
+      "epoch": 2.450980392156863,
+      "grad_norm": 0.48972561955451965,
+      "learning_rate": 0.0002,
+      "loss": 0.8158,
+      "step": 750
+    },
+    {
+      "epoch": 2.4836601307189543,
+      "grad_norm": 0.5295189023017883,
+      "learning_rate": 0.0002,
+      "loss": 0.8766,
+      "step": 760
+    },
+    {
+      "epoch": 2.5163398692810457,
+      "grad_norm": 0.5487208962440491,
+      "learning_rate": 0.0002,
+      "loss": 0.8695,
+      "step": 770
+    },
+    {
+      "epoch": 2.549019607843137,
+      "grad_norm": 0.5375093221664429,
+      "learning_rate": 0.0002,
+      "loss": 1.0109,
+      "step": 780
+    },
+    {
+      "epoch": 2.581699346405229,
+      "grad_norm": 0.5424453020095825,
+      "learning_rate": 0.0002,
+      "loss": 0.9244,
+      "step": 790
+    },
+    {
+      "epoch": 2.6143790849673203,
+      "grad_norm": 0.6029134392738342,
+      "learning_rate": 0.0002,
+      "loss": 1.0424,
+      "step": 800
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.6584921479225159,
+      "learning_rate": 0.0002,
+      "loss": 0.8688,
+      "step": 810
+    },
+    {
+      "epoch": 2.6797385620915035,
+      "grad_norm": 0.5735557675361633,
+      "learning_rate": 0.0002,
+      "loss": 0.7796,
+      "step": 820
+    },
+    {
+      "epoch": 2.712418300653595,
+      "grad_norm": 0.5216763019561768,
+      "learning_rate": 0.0002,
+      "loss": 0.8834,
+      "step": 830
+    },
+    {
+      "epoch": 2.7450980392156863,
+      "grad_norm": 0.5455219149589539,
+      "learning_rate": 0.0002,
+      "loss": 0.8946,
+      "step": 840
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.5139284729957581,
+      "learning_rate": 0.0002,
+      "loss": 0.8037,
+      "step": 850
+    },
+    {
+      "epoch": 2.810457516339869,
+      "grad_norm": 0.5096403360366821,
+      "learning_rate": 0.0002,
+      "loss": 0.988,
+      "step": 860
+    },
+    {
+      "epoch": 2.843137254901961,
+      "grad_norm": 0.6337038278579712,
+      "learning_rate": 0.0002,
+      "loss": 0.9169,
+      "step": 870
+    },
+    {
+      "epoch": 2.8758169934640523,
+      "grad_norm": 0.47218772768974304,
+      "learning_rate": 0.0002,
+      "loss": 0.8938,
+      "step": 880
+    },
+    {
+      "epoch": 2.9084967320261437,
+      "grad_norm": 0.4640636742115021,
+      "learning_rate": 0.0002,
+      "loss": 0.8554,
+      "step": 890
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.4199628531932831,
+      "learning_rate": 0.0002,
+      "loss": 0.8625,
+      "step": 900
+    },
+    {
+      "epoch": 2.973856209150327,
+      "grad_norm": 0.5067117214202881,
+      "learning_rate": 0.0002,
+      "loss": 0.8104,
+      "step": 910
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2291251420974731,
+      "eval_runtime": 46.2557,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 1.189,
+      "step": 918
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2448,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.715191848665088e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/training_args.bin b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e7fb8100bbfe18f1342e5fc87e32e8e798268e3b
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-918/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e66621362aa4eab196083c9a4bd0bf843b2425d7109d63be3ab5f4006691dd1
+size 5560
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/special_tokens_map.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/special_tokens_map.json
@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/tokenizer.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/tokenizer.model b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/tokenizer_config.json b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/tokenizer_config.json
@@ -0,0 +1,2013 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/training_args.bin b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e7fb8100bbfe18f1342e5fc87e32e8e798268e3b
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e66621362aa4eab196083c9a4bd0bf843b2425d7109d63be3ab5f4006691dd1
+size 5560
diff --git a/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/training_log.jsonl b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/training_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..2502e837e2dd8c2b50ba274147b4ea8faad54b05
--- /dev/null
+++ b/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/training_log.jsonl
@@ -0,0 +1,8 @@
+{"epoch": 1.0, "step": 306, "epoch_duration": 456.216677904129, "total_accumulated_duration": 456.216677904129, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 11696.9921875}, "avg_memory_reserved": {"GPU_0": 12758.0}, "peak_memory_reserved": {"GPU_0": 12758.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.3561, "grad_norm": 0.631856381893158, "learning_rate": 0.0002, "epoch": 0.032679738562091505, "step": 10}, {"loss": 1.8141, "grad_norm": 0.5065668821334839, "learning_rate": 0.0002, "epoch": 0.06535947712418301, "step": 20}, {"loss": 1.4952, "grad_norm": 0.6978895664215088, "learning_rate": 0.0002, "epoch": 0.09803921568627451, "step": 30}, {"loss": 1.4829, "grad_norm": 0.6619144082069397, "learning_rate": 0.0002, "epoch": 0.13071895424836602, "step": 40}, {"loss": 1.3038, "grad_norm": 0.6153793931007385, "learning_rate": 0.0002, "epoch": 0.16339869281045752, "step": 50}, {"loss": 1.1429, "grad_norm": 0.4703301787376404, "learning_rate": 0.0002, "epoch": 0.19607843137254902, "step": 60}, {"loss": 1.2828, "grad_norm": 1.1672580242156982, "learning_rate": 0.0002, "epoch": 0.22875816993464052, "step": 70}, {"loss": 1.0985, "grad_norm": 0.3455565273761749, "learning_rate": 0.0002, "epoch": 0.26143790849673204, "step": 80}, {"loss": 1.1359, "grad_norm": 0.36216291785240173, "learning_rate": 0.0002, "epoch": 0.29411764705882354, "step": 90}, {"loss": 1.2544, "grad_norm": 0.4545166492462158, "learning_rate": 0.0002, "epoch": 0.32679738562091504, "step": 100}, {"loss": 1.2287, "grad_norm": 0.3612092435359955, "learning_rate": 0.0002, "epoch": 0.35947712418300654, "step": 110}, {"loss": 1.1868, "grad_norm": 0.5080830454826355, "learning_rate": 0.0002, "epoch": 0.39215686274509803, "step": 120}, {"loss": 1.1902, "grad_norm": 0.3268195390701294, "learning_rate": 0.0002, "epoch": 0.42483660130718953, "step": 130}, {"loss": 1.247, "grad_norm": 0.33971714973449707, "learning_rate": 0.0002, "epoch": 0.45751633986928103, "step": 140}, {"loss": 1.1844, "grad_norm": 0.4036043882369995, "learning_rate": 0.0002, "epoch": 0.49019607843137253, "step": 150}, {"loss": 1.1624, "grad_norm": 0.35938864946365356, "learning_rate": 0.0002, "epoch": 0.5228758169934641, "step": 160}, {"loss": 1.164, "grad_norm": 0.28880223631858826, "learning_rate": 0.0002, "epoch": 0.5555555555555556, "step": 170}, {"loss": 1.3521, "grad_norm": 0.3436269462108612, "learning_rate": 0.0002, "epoch": 0.5882352941176471, "step": 180}, {"loss": 1.2456, "grad_norm": 0.41923725605010986, "learning_rate": 0.0002, "epoch": 0.6209150326797386, "step": 190}, {"loss": 1.2226, "grad_norm": 0.25119203329086304, "learning_rate": 0.0002, "epoch": 0.6535947712418301, "step": 200}, {"loss": 1.1568, "grad_norm": 0.5870180726051331, "learning_rate": 0.0002, "epoch": 0.6862745098039216, "step": 210}, {"loss": 1.064, "grad_norm": 0.2831224203109741, "learning_rate": 0.0002, "epoch": 0.7189542483660131, "step": 220}, {"loss": 1.2469, "grad_norm": 0.3192005753517151, "learning_rate": 0.0002, "epoch": 0.7516339869281046, "step": 230}, {"loss": 1.1613, "grad_norm": 0.2998219430446625, "learning_rate": 0.0002, "epoch": 0.7843137254901961, "step": 240}, {"loss": 1.205, "grad_norm": 0.32855790853500366, "learning_rate": 0.0002, "epoch": 0.8169934640522876, "step": 250}, {"loss": 1.1631, "grad_norm": 0.3403124213218689, "learning_rate": 0.0002, "epoch": 0.8496732026143791, "step": 260}, {"loss": 1.1646, "grad_norm": 0.277401328086853, "learning_rate": 0.0002, "epoch": 0.8823529411764706, "step": 270}, {"loss": 1.084, "grad_norm": 0.2975269556045532, "learning_rate": 0.0002, "epoch": 0.9150326797385621, "step": 280}, {"loss": 1.2039, "grad_norm": 1.7909578084945679, "learning_rate": 0.0002, "epoch": 0.9477124183006536, "step": 290}, {"loss": 1.1226, "grad_norm": 0.2917245328426361, "learning_rate": 0.0002, "epoch": 0.9803921568627451, "step": 300}]}
+{"epoch": 2.0, "step": 612, "epoch_duration": 456.3443353176117, "total_accumulated_duration": 912.5610132217407, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.224609375}, "avg_memory_reserved": {"GPU_0": 28746.0}, "peak_memory_reserved": {"GPU_0": 28746.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-306", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.3561, "grad_norm": 0.631856381893158, "learning_rate": 0.0002, "epoch": 0.032679738562091505, "step": 10}, {"loss": 1.8141, "grad_norm": 0.5065668821334839, "learning_rate": 0.0002, "epoch": 0.06535947712418301, "step": 20}, {"loss": 1.4952, "grad_norm": 0.6978895664215088, "learning_rate": 0.0002, "epoch": 0.09803921568627451, "step": 30}, {"loss": 1.4829, "grad_norm": 0.6619144082069397, "learning_rate": 0.0002, "epoch": 0.13071895424836602, "step": 40}, {"loss": 1.3038, "grad_norm": 0.6153793931007385, "learning_rate": 0.0002, "epoch": 0.16339869281045752, "step": 50}, {"loss": 1.1429, "grad_norm": 0.4703301787376404, "learning_rate": 0.0002, "epoch": 0.19607843137254902, "step": 60}, {"loss": 1.2828, "grad_norm": 1.1672580242156982, "learning_rate": 0.0002, "epoch": 0.22875816993464052, "step": 70}, {"loss": 1.0985, "grad_norm": 0.3455565273761749, "learning_rate": 0.0002, "epoch": 0.26143790849673204, "step": 80}, {"loss": 1.1359, "grad_norm": 0.36216291785240173, "learning_rate": 0.0002, "epoch": 0.29411764705882354, "step": 90}, {"loss": 1.2544, "grad_norm": 0.4545166492462158, "learning_rate": 0.0002, "epoch": 0.32679738562091504, "step": 100}, {"loss": 1.2287, "grad_norm": 0.3612092435359955, "learning_rate": 0.0002, "epoch": 0.35947712418300654, "step": 110}, {"loss": 1.1868, "grad_norm": 0.5080830454826355, "learning_rate": 0.0002, "epoch": 0.39215686274509803, "step": 120}, {"loss": 1.1902, "grad_norm": 0.3268195390701294, "learning_rate": 0.0002, "epoch": 0.42483660130718953, "step": 130}, {"loss": 1.247, "grad_norm": 0.33971714973449707, "learning_rate": 0.0002, "epoch": 0.45751633986928103, "step": 140}, {"loss": 1.1844, "grad_norm": 0.4036043882369995, "learning_rate": 0.0002, "epoch": 0.49019607843137253, "step": 150}, {"loss": 1.1624, "grad_norm": 0.35938864946365356, "learning_rate": 0.0002, "epoch": 0.5228758169934641, "step": 160}, {"loss": 1.164, "grad_norm": 0.28880223631858826, "learning_rate": 0.0002, "epoch": 0.5555555555555556, "step": 170}, {"loss": 1.3521, "grad_norm": 0.3436269462108612, "learning_rate": 0.0002, "epoch": 0.5882352941176471, "step": 180}, {"loss": 1.2456, "grad_norm": 0.41923725605010986, "learning_rate": 0.0002, "epoch": 0.6209150326797386, "step": 190}, {"loss": 1.2226, "grad_norm": 0.25119203329086304, "learning_rate": 0.0002, "epoch": 0.6535947712418301, "step": 200}, {"loss": 1.1568, "grad_norm": 0.5870180726051331, "learning_rate": 0.0002, "epoch": 0.6862745098039216, "step": 210}, {"loss": 1.064, "grad_norm": 0.2831224203109741, "learning_rate": 0.0002, "epoch": 0.7189542483660131, "step": 220}, {"loss": 1.2469, "grad_norm": 0.3192005753517151, "learning_rate": 0.0002, "epoch": 0.7516339869281046, "step": 230}, {"loss": 1.1613, "grad_norm": 0.2998219430446625, "learning_rate": 0.0002, "epoch": 0.7843137254901961, "step": 240}, {"loss": 1.205, "grad_norm": 0.32855790853500366, "learning_rate": 0.0002, "epoch": 0.8169934640522876, "step": 250}, {"loss": 1.1631, "grad_norm": 0.3403124213218689, "learning_rate": 0.0002, "epoch": 0.8496732026143791, "step": 260}, {"loss": 1.1646, "grad_norm": 0.277401328086853, "learning_rate": 0.0002, "epoch": 0.8823529411764706, "step": 270}, {"loss": 1.084, "grad_norm": 0.2975269556045532, "learning_rate": 0.0002, "epoch": 0.9150326797385621, "step": 280}, {"loss": 1.2039, "grad_norm": 1.7909578084945679, "learning_rate": 0.0002, "epoch": 0.9477124183006536, "step": 290}, {"loss": 1.1226, "grad_norm": 0.2917245328426361, "learning_rate": 0.0002, "epoch": 0.9803921568627451, "step": 300}, {"eval_loss": 1.1937541961669922, "eval_runtime": 46.2571, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 1.0, "step": 306}, {"loss": 1.2011, "grad_norm": 0.26494982838630676, "learning_rate": 0.0002, "epoch": 1.0130718954248366, "step": 310}, {"loss": 1.0565, "grad_norm": 0.6289355754852295, "learning_rate": 0.0002, "epoch": 1.0457516339869282, "step": 320}, {"loss": 1.1619, "grad_norm": 0.26784011721611023, "learning_rate": 0.0002, "epoch": 1.0784313725490196, "step": 330}, {"loss": 1.1151, "grad_norm": 0.3392215967178345, "learning_rate": 0.0002, "epoch": 1.1111111111111112, "step": 340}, {"loss": 1.0752, "grad_norm": 0.40005937218666077, "learning_rate": 0.0002, "epoch": 1.1437908496732025, "step": 350}, {"loss": 1.0408, "grad_norm": 0.3590582013130188, "learning_rate": 0.0002, "epoch": 1.1764705882352942, "step": 360}, {"loss": 1.0836, "grad_norm": 0.3995305895805359, "learning_rate": 0.0002, "epoch": 1.2091503267973855, "step": 370}, {"loss": 1.0992, "grad_norm": 0.2950291633605957, "learning_rate": 0.0002, "epoch": 1.2418300653594772, "step": 380}, {"loss": 1.1152, "grad_norm": 0.32035166025161743, "learning_rate": 0.0002, "epoch": 1.2745098039215685, "step": 390}, {"loss": 1.1467, "grad_norm": 0.410366415977478, "learning_rate": 0.0002, "epoch": 1.3071895424836601, "step": 400}, {"loss": 0.9985, "grad_norm": 0.3106379508972168, "learning_rate": 0.0002, "epoch": 1.3398692810457518, "step": 410}, {"loss": 0.9789, "grad_norm": 0.38580670952796936, "learning_rate": 0.0002, "epoch": 1.3725490196078431, "step": 420}, {"loss": 1.0931, "grad_norm": 0.34411361813545227, "learning_rate": 0.0002, "epoch": 1.4052287581699345, "step": 430}, {"loss": 1.1685, "grad_norm": 0.44206851720809937, "learning_rate": 0.0002, "epoch": 1.4379084967320261, "step": 440}, {"loss": 1.0347, "grad_norm": 0.3492952585220337, "learning_rate": 0.0002, "epoch": 1.4705882352941178, "step": 450}, {"loss": 1.0534, "grad_norm": 0.376423716545105, "learning_rate": 0.0002, "epoch": 1.5032679738562091, "step": 460}, {"loss": 1.1162, "grad_norm": 0.359757661819458, "learning_rate": 0.0002, "epoch": 1.5359477124183005, "step": 470}, {"loss": 0.9586, "grad_norm": 0.3385067880153656, "learning_rate": 0.0002, "epoch": 1.5686274509803921, "step": 480}, {"loss": 1.0807, "grad_norm": 0.4943889379501343, "learning_rate": 0.0002, "epoch": 1.6013071895424837, "step": 490}, {"loss": 1.0796, "grad_norm": 0.4203241169452667, "learning_rate": 0.0002, "epoch": 1.6339869281045751, "step": 500}, {"loss": 1.1059, "grad_norm": 0.3093789219856262, "learning_rate": 0.0002, "epoch": 1.6666666666666665, "step": 510}, {"loss": 1.0323, "grad_norm": 0.3653067350387573, "learning_rate": 0.0002, "epoch": 1.6993464052287581, "step": 520}, {"loss": 1.0885, "grad_norm": 0.36761337518692017, "learning_rate": 0.0002, "epoch": 1.7320261437908497, "step": 530}, {"loss": 1.1698, "grad_norm": 0.5040399432182312, "learning_rate": 0.0002, "epoch": 1.7647058823529411, "step": 540}, {"loss": 1.0105, "grad_norm": 0.3818035125732422, "learning_rate": 0.0002, "epoch": 1.7973856209150327, "step": 550}, {"loss": 0.94, "grad_norm": 0.4021618664264679, "learning_rate": 0.0002, "epoch": 1.8300653594771243, "step": 560}, {"loss": 1.0358, "grad_norm": 0.3986459970474243, "learning_rate": 0.0002, "epoch": 1.8627450980392157, "step": 570}, {"loss": 1.003, "grad_norm": 0.48416733741760254, "learning_rate": 0.0002, "epoch": 1.8954248366013071, "step": 580}, {"loss": 1.1146, "grad_norm": 0.36853986978530884, "learning_rate": 0.0002, "epoch": 1.9281045751633987, "step": 590}, {"loss": 1.0689, "grad_norm": 0.383022665977478, "learning_rate": 0.0002, "epoch": 1.9607843137254903, "step": 600}, {"loss": 1.098, "grad_norm": 0.3169507086277008, "learning_rate": 0.0002, "epoch": 1.9934640522875817, "step": 610}]}
+{"epoch": 3.0, "step": 918, "epoch_duration": 455.7831633090973, "total_accumulated_duration": 1368.344176530838, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.224609375}, "avg_memory_reserved": {"GPU_0": 28746.0}, "peak_memory_reserved": {"GPU_0": 28746.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.3561, "grad_norm": 0.631856381893158, "learning_rate": 0.0002, "epoch": 0.032679738562091505, "step": 10}, {"loss": 1.8141, "grad_norm": 0.5065668821334839, "learning_rate": 0.0002, "epoch": 0.06535947712418301, "step": 20}, {"loss": 1.4952, "grad_norm": 0.6978895664215088, "learning_rate": 0.0002, "epoch": 0.09803921568627451, "step": 30}, {"loss": 1.4829, "grad_norm": 0.6619144082069397, "learning_rate": 0.0002, "epoch": 0.13071895424836602, "step": 40}, {"loss": 1.3038, "grad_norm": 0.6153793931007385, "learning_rate": 0.0002, "epoch": 0.16339869281045752, "step": 50}, {"loss": 1.1429, "grad_norm": 0.4703301787376404, "learning_rate": 0.0002, "epoch": 0.19607843137254902, "step": 60}, {"loss": 1.2828, "grad_norm": 1.1672580242156982, "learning_rate": 0.0002, "epoch": 0.22875816993464052, "step": 70}, {"loss": 1.0985, "grad_norm": 0.3455565273761749, "learning_rate": 0.0002, "epoch": 0.26143790849673204, "step": 80}, {"loss": 1.1359, "grad_norm": 0.36216291785240173, "learning_rate": 0.0002, "epoch": 0.29411764705882354, "step": 90}, {"loss": 1.2544, "grad_norm": 0.4545166492462158, "learning_rate": 0.0002, "epoch": 0.32679738562091504, "step": 100}, {"loss": 1.2287, "grad_norm": 0.3612092435359955, "learning_rate": 0.0002, "epoch": 0.35947712418300654, "step": 110}, {"loss": 1.1868, "grad_norm": 0.5080830454826355, "learning_rate": 0.0002, "epoch": 0.39215686274509803, "step": 120}, {"loss": 1.1902, "grad_norm": 0.3268195390701294, "learning_rate": 0.0002, "epoch": 0.42483660130718953, "step": 130}, {"loss": 1.247, "grad_norm": 0.33971714973449707, "learning_rate": 0.0002, "epoch": 0.45751633986928103, "step": 140}, {"loss": 1.1844, "grad_norm": 0.4036043882369995, "learning_rate": 0.0002, "epoch": 0.49019607843137253, "step": 150}, {"loss": 1.1624, "grad_norm": 0.35938864946365356, "learning_rate": 0.0002, "epoch": 0.5228758169934641, "step": 160}, {"loss": 1.164, "grad_norm": 0.28880223631858826, "learning_rate": 0.0002, "epoch": 0.5555555555555556, "step": 170}, {"loss": 1.3521, "grad_norm": 0.3436269462108612, "learning_rate": 0.0002, "epoch": 0.5882352941176471, "step": 180}, {"loss": 1.2456, "grad_norm": 0.41923725605010986, "learning_rate": 0.0002, "epoch": 0.6209150326797386, "step": 190}, {"loss": 1.2226, "grad_norm": 0.25119203329086304, "learning_rate": 0.0002, "epoch": 0.6535947712418301, "step": 200}, {"loss": 1.1568, "grad_norm": 0.5870180726051331, "learning_rate": 0.0002, "epoch": 0.6862745098039216, "step": 210}, {"loss": 1.064, "grad_norm": 0.2831224203109741, "learning_rate": 0.0002, "epoch": 0.7189542483660131, "step": 220}, {"loss": 1.2469, "grad_norm": 0.3192005753517151, "learning_rate": 0.0002, "epoch": 0.7516339869281046, "step": 230}, {"loss": 1.1613, "grad_norm": 0.2998219430446625, "learning_rate": 0.0002, "epoch": 0.7843137254901961, "step": 240}, {"loss": 1.205, "grad_norm": 0.32855790853500366, "learning_rate": 0.0002, "epoch": 0.8169934640522876, "step": 250}, {"loss": 1.1631, "grad_norm": 0.3403124213218689, "learning_rate": 0.0002, "epoch": 0.8496732026143791, "step": 260}, {"loss": 1.1646, "grad_norm": 0.277401328086853, "learning_rate": 0.0002, "epoch": 0.8823529411764706, "step": 270}, {"loss": 1.084, "grad_norm": 0.2975269556045532, "learning_rate": 0.0002, "epoch": 0.9150326797385621, "step": 280}, {"loss": 1.2039, "grad_norm": 1.7909578084945679, "learning_rate": 0.0002, "epoch": 0.9477124183006536, "step": 290}, {"loss": 1.1226, "grad_norm": 0.2917245328426361, "learning_rate": 0.0002, "epoch": 0.9803921568627451, "step": 300}, {"eval_loss": 1.1937541961669922, "eval_runtime": 46.2571, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 1.0, "step": 306}, {"loss": 1.2011, "grad_norm": 0.26494982838630676, "learning_rate": 0.0002, "epoch": 1.0130718954248366, "step": 310}, {"loss": 1.0565, "grad_norm": 0.6289355754852295, "learning_rate": 0.0002, "epoch": 1.0457516339869282, "step": 320}, {"loss": 1.1619, "grad_norm": 0.26784011721611023, "learning_rate": 0.0002, "epoch": 1.0784313725490196, "step": 330}, {"loss": 1.1151, "grad_norm": 0.3392215967178345, "learning_rate": 0.0002, "epoch": 1.1111111111111112, "step": 340}, {"loss": 1.0752, "grad_norm": 0.40005937218666077, "learning_rate": 0.0002, "epoch": 1.1437908496732025, "step": 350}, {"loss": 1.0408, "grad_norm": 0.3590582013130188, "learning_rate": 0.0002, "epoch": 1.1764705882352942, "step": 360}, {"loss": 1.0836, "grad_norm": 0.3995305895805359, "learning_rate": 0.0002, "epoch": 1.2091503267973855, "step": 370}, {"loss": 1.0992, "grad_norm": 0.2950291633605957, "learning_rate": 0.0002, "epoch": 1.2418300653594772, "step": 380}, {"loss": 1.1152, "grad_norm": 0.32035166025161743, "learning_rate": 0.0002, "epoch": 1.2745098039215685, "step": 390}, {"loss": 1.1467, "grad_norm": 0.410366415977478, "learning_rate": 0.0002, "epoch": 1.3071895424836601, "step": 400}, {"loss": 0.9985, "grad_norm": 0.3106379508972168, "learning_rate": 0.0002, "epoch": 1.3398692810457518, "step": 410}, {"loss": 0.9789, "grad_norm": 0.38580670952796936, "learning_rate": 0.0002, "epoch": 1.3725490196078431, "step": 420}, {"loss": 1.0931, "grad_norm": 0.34411361813545227, "learning_rate": 0.0002, "epoch": 1.4052287581699345, "step": 430}, {"loss": 1.1685, "grad_norm": 0.44206851720809937, "learning_rate": 0.0002, "epoch": 1.4379084967320261, "step": 440}, {"loss": 1.0347, "grad_norm": 0.3492952585220337, "learning_rate": 0.0002, "epoch": 1.4705882352941178, "step": 450}, {"loss": 1.0534, "grad_norm": 0.376423716545105, "learning_rate": 0.0002, "epoch": 1.5032679738562091, "step": 460}, {"loss": 1.1162, "grad_norm": 0.359757661819458, "learning_rate": 0.0002, "epoch": 1.5359477124183005, "step": 470}, {"loss": 0.9586, "grad_norm": 0.3385067880153656, "learning_rate": 0.0002, "epoch": 1.5686274509803921, "step": 480}, {"loss": 1.0807, "grad_norm": 0.4943889379501343, "learning_rate": 0.0002, "epoch": 1.6013071895424837, "step": 490}, {"loss": 1.0796, "grad_norm": 0.4203241169452667, "learning_rate": 0.0002, "epoch": 1.6339869281045751, "step": 500}, {"loss": 1.1059, "grad_norm": 0.3093789219856262, "learning_rate": 0.0002, "epoch": 1.6666666666666665, "step": 510}, {"loss": 1.0323, "grad_norm": 0.3653067350387573, "learning_rate": 0.0002, "epoch": 1.6993464052287581, "step": 520}, {"loss": 1.0885, "grad_norm": 0.36761337518692017, "learning_rate": 0.0002, "epoch": 1.7320261437908497, "step": 530}, {"loss": 1.1698, "grad_norm": 0.5040399432182312, "learning_rate": 0.0002, "epoch": 1.7647058823529411, "step": 540}, {"loss": 1.0105, "grad_norm": 0.3818035125732422, "learning_rate": 0.0002, "epoch": 1.7973856209150327, "step": 550}, {"loss": 0.94, "grad_norm": 0.4021618664264679, "learning_rate": 0.0002, "epoch": 1.8300653594771243, "step": 560}, {"loss": 1.0358, "grad_norm": 0.3986459970474243, "learning_rate": 0.0002, "epoch": 1.8627450980392157, "step": 570}, {"loss": 1.003, "grad_norm": 0.48416733741760254, "learning_rate": 0.0002, "epoch": 1.8954248366013071, "step": 580}, {"loss": 1.1146, "grad_norm": 0.36853986978530884, "learning_rate": 0.0002, "epoch": 1.9281045751633987, "step": 590}, {"loss": 1.0689, "grad_norm": 0.383022665977478, "learning_rate": 0.0002, "epoch": 1.9607843137254903, "step": 600}, {"loss": 1.098, "grad_norm": 0.3169507086277008, "learning_rate": 0.0002, "epoch": 1.9934640522875817, "step": 610}, {"eval_loss": 1.1845070123672485, "eval_runtime": 46.2811, "eval_samples_per_second": 9.421, "eval_steps_per_second": 1.188, "epoch": 2.0, "step": 612}, {"loss": 0.9618, "grad_norm": 0.8920142650604248, "learning_rate": 0.0002, "epoch": 2.026143790849673, "step": 620}, {"loss": 0.9784, "grad_norm": 0.4814859628677368, "learning_rate": 0.0002, "epoch": 2.0588235294117645, "step": 630}, {"loss": 0.8464, "grad_norm": 0.4251559376716614, "learning_rate": 0.0002, "epoch": 2.0915032679738563, "step": 640}, {"loss": 0.932, "grad_norm": 0.5295765399932861, "learning_rate": 0.0002, "epoch": 2.1241830065359477, "step": 650}, {"loss": 0.9603, "grad_norm": 0.45016610622406006, "learning_rate": 0.0002, "epoch": 2.156862745098039, "step": 660}, {"loss": 0.8738, "grad_norm": 0.5870586633682251, "learning_rate": 0.0002, "epoch": 2.189542483660131, "step": 670}, {"loss": 0.9483, "grad_norm": 0.5174715518951416, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 680}, {"loss": 0.9551, "grad_norm": 0.5252485275268555, "learning_rate": 0.0002, "epoch": 2.2549019607843137, "step": 690}, {"loss": 0.9253, "grad_norm": 0.5158312320709229, "learning_rate": 0.0002, "epoch": 2.287581699346405, "step": 700}, {"loss": 0.9278, "grad_norm": 0.4824209213256836, "learning_rate": 0.0002, "epoch": 2.3202614379084965, "step": 710}, {"loss": 0.8804, "grad_norm": 0.6335175037384033, "learning_rate": 0.0002, "epoch": 2.3529411764705883, "step": 720}, {"loss": 0.9685, "grad_norm": 0.5240563154220581, "learning_rate": 0.0002, "epoch": 2.3856209150326797, "step": 730}, {"loss": 0.8794, "grad_norm": 0.5172886252403259, "learning_rate": 0.0002, "epoch": 2.418300653594771, "step": 740}, {"loss": 0.8158, "grad_norm": 0.48972561955451965, "learning_rate": 0.0002, "epoch": 2.450980392156863, "step": 750}, {"loss": 0.8766, "grad_norm": 0.5295189023017883, "learning_rate": 0.0002, "epoch": 2.4836601307189543, "step": 760}, {"loss": 0.8695, "grad_norm": 0.5487208962440491, "learning_rate": 0.0002, "epoch": 2.5163398692810457, "step": 770}, {"loss": 1.0109, "grad_norm": 0.5375093221664429, "learning_rate": 0.0002, "epoch": 2.549019607843137, "step": 780}, {"loss": 0.9244, "grad_norm": 0.5424453020095825, "learning_rate": 0.0002, "epoch": 2.581699346405229, "step": 790}, {"loss": 1.0424, "grad_norm": 0.6029134392738342, "learning_rate": 0.0002, "epoch": 2.6143790849673203, "step": 800}, {"loss": 0.8688, "grad_norm": 0.6584921479225159, "learning_rate": 0.0002, "epoch": 2.6470588235294117, "step": 810}, {"loss": 0.7796, "grad_norm": 0.5735557675361633, "learning_rate": 0.0002, "epoch": 2.6797385620915035, "step": 820}, {"loss": 0.8834, "grad_norm": 0.5216763019561768, "learning_rate": 0.0002, "epoch": 2.712418300653595, "step": 830}, {"loss": 0.8946, "grad_norm": 0.5455219149589539, "learning_rate": 0.0002, "epoch": 2.7450980392156863, "step": 840}, {"loss": 0.8037, "grad_norm": 0.5139284729957581, "learning_rate": 0.0002, "epoch": 2.7777777777777777, "step": 850}, {"loss": 0.988, "grad_norm": 0.5096403360366821, "learning_rate": 0.0002, "epoch": 2.810457516339869, "step": 860}, {"loss": 0.9169, "grad_norm": 0.6337038278579712, "learning_rate": 0.0002, "epoch": 2.843137254901961, "step": 870}, {"loss": 0.8938, "grad_norm": 0.47218772768974304, "learning_rate": 0.0002, "epoch": 2.8758169934640523, "step": 880}, {"loss": 0.8554, "grad_norm": 0.4640636742115021, "learning_rate": 0.0002, "epoch": 2.9084967320261437, "step": 890}, {"loss": 0.8625, "grad_norm": 0.4199628531932831, "learning_rate": 0.0002, "epoch": 2.9411764705882355, "step": 900}, {"loss": 0.8104, "grad_norm": 0.5067117214202881, "learning_rate": 0.0002, "epoch": 2.973856209150327, "step": 910}]}
+{"epoch": 4.0, "step": 1224, "epoch_duration": 455.8060460090637, "total_accumulated_duration": 1824.1502225399017, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.224609375}, "avg_memory_reserved": {"GPU_0": 28746.0}, "peak_memory_reserved": {"GPU_0": 28746.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.3561, "grad_norm": 0.631856381893158, "learning_rate": 0.0002, "epoch": 0.032679738562091505, "step": 10}, {"loss": 1.8141, "grad_norm": 0.5065668821334839, "learning_rate": 0.0002, "epoch": 0.06535947712418301, "step": 20}, {"loss": 1.4952, "grad_norm": 0.6978895664215088, "learning_rate": 0.0002, "epoch": 0.09803921568627451, "step": 30}, {"loss": 1.4829, "grad_norm": 0.6619144082069397, "learning_rate": 0.0002, "epoch": 0.13071895424836602, "step": 40}, {"loss": 1.3038, "grad_norm": 0.6153793931007385, "learning_rate": 0.0002, "epoch": 0.16339869281045752, "step": 50}, {"loss": 1.1429, "grad_norm": 0.4703301787376404, "learning_rate": 0.0002, "epoch": 0.19607843137254902, "step": 60}, {"loss": 1.2828, "grad_norm": 1.1672580242156982, "learning_rate": 0.0002, "epoch": 0.22875816993464052, "step": 70}, {"loss": 1.0985, "grad_norm": 0.3455565273761749, "learning_rate": 0.0002, "epoch": 0.26143790849673204, "step": 80}, {"loss": 1.1359, "grad_norm": 0.36216291785240173, "learning_rate": 0.0002, "epoch": 0.29411764705882354, "step": 90}, {"loss": 1.2544, "grad_norm": 0.4545166492462158, "learning_rate": 0.0002, "epoch": 0.32679738562091504, "step": 100}, {"loss": 1.2287, "grad_norm": 0.3612092435359955, "learning_rate": 0.0002, "epoch": 0.35947712418300654, "step": 110}, {"loss": 1.1868, "grad_norm": 0.5080830454826355, "learning_rate": 0.0002, "epoch": 0.39215686274509803, "step": 120}, {"loss": 1.1902, "grad_norm": 0.3268195390701294, "learning_rate": 0.0002, "epoch": 0.42483660130718953, "step": 130}, {"loss": 1.247, "grad_norm": 0.33971714973449707, "learning_rate": 0.0002, "epoch": 0.45751633986928103, "step": 140}, {"loss": 1.1844, "grad_norm": 0.4036043882369995, "learning_rate": 0.0002, "epoch": 0.49019607843137253, "step": 150}, {"loss": 1.1624, "grad_norm": 0.35938864946365356, "learning_rate": 0.0002, "epoch": 0.5228758169934641, "step": 160}, {"loss": 1.164, "grad_norm": 0.28880223631858826, "learning_rate": 0.0002, "epoch": 0.5555555555555556, "step": 170}, {"loss": 1.3521, "grad_norm": 0.3436269462108612, "learning_rate": 0.0002, "epoch": 0.5882352941176471, "step": 180}, {"loss": 1.2456, "grad_norm": 0.41923725605010986, "learning_rate": 0.0002, "epoch": 0.6209150326797386, "step": 190}, {"loss": 1.2226, "grad_norm": 0.25119203329086304, "learning_rate": 0.0002, "epoch": 0.6535947712418301, "step": 200}, {"loss": 1.1568, "grad_norm": 0.5870180726051331, "learning_rate": 0.0002, "epoch": 0.6862745098039216, "step": 210}, {"loss": 1.064, "grad_norm": 0.2831224203109741, "learning_rate": 0.0002, "epoch": 0.7189542483660131, "step": 220}, {"loss": 1.2469, "grad_norm": 0.3192005753517151, "learning_rate": 0.0002, "epoch": 0.7516339869281046, "step": 230}, {"loss": 1.1613, "grad_norm": 0.2998219430446625, "learning_rate": 0.0002, "epoch": 0.7843137254901961, "step": 240}, {"loss": 1.205, "grad_norm": 0.32855790853500366, "learning_rate": 0.0002, "epoch": 0.8169934640522876, "step": 250}, {"loss": 1.1631, "grad_norm": 0.3403124213218689, "learning_rate": 0.0002, "epoch": 0.8496732026143791, "step": 260}, {"loss": 1.1646, "grad_norm": 0.277401328086853, "learning_rate": 0.0002, "epoch": 0.8823529411764706, "step": 270}, {"loss": 1.084, "grad_norm": 0.2975269556045532, "learning_rate": 0.0002, "epoch": 0.9150326797385621, "step": 280}, {"loss": 1.2039, "grad_norm": 1.7909578084945679, "learning_rate": 0.0002, "epoch": 0.9477124183006536, "step": 290}, {"loss": 1.1226, "grad_norm": 0.2917245328426361, "learning_rate": 0.0002, "epoch": 0.9803921568627451, "step": 300}, {"eval_loss": 1.1937541961669922, "eval_runtime": 46.2571, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 1.0, "step": 306}, {"loss": 1.2011, "grad_norm": 0.26494982838630676, "learning_rate": 0.0002, "epoch": 1.0130718954248366, "step": 310}, {"loss": 1.0565, "grad_norm": 0.6289355754852295, "learning_rate": 0.0002, "epoch": 1.0457516339869282, "step": 320}, {"loss": 1.1619, "grad_norm": 0.26784011721611023, "learning_rate": 0.0002, "epoch": 1.0784313725490196, "step": 330}, {"loss": 1.1151, "grad_norm": 0.3392215967178345, "learning_rate": 0.0002, "epoch": 1.1111111111111112, "step": 340}, {"loss": 1.0752, "grad_norm": 0.40005937218666077, "learning_rate": 0.0002, "epoch": 1.1437908496732025, "step": 350}, {"loss": 1.0408, "grad_norm": 0.3590582013130188, "learning_rate": 0.0002, "epoch": 1.1764705882352942, "step": 360}, {"loss": 1.0836, "grad_norm": 0.3995305895805359, "learning_rate": 0.0002, "epoch": 1.2091503267973855, "step": 370}, {"loss": 1.0992, "grad_norm": 0.2950291633605957, "learning_rate": 0.0002, "epoch": 1.2418300653594772, "step": 380}, {"loss": 1.1152, "grad_norm": 0.32035166025161743, "learning_rate": 0.0002, "epoch": 1.2745098039215685, "step": 390}, {"loss": 1.1467, "grad_norm": 0.410366415977478, "learning_rate": 0.0002, "epoch": 1.3071895424836601, "step": 400}, {"loss": 0.9985, "grad_norm": 0.3106379508972168, "learning_rate": 0.0002, "epoch": 1.3398692810457518, "step": 410}, {"loss": 0.9789, "grad_norm": 0.38580670952796936, "learning_rate": 0.0002, "epoch": 1.3725490196078431, "step": 420}, {"loss": 1.0931, "grad_norm": 0.34411361813545227, "learning_rate": 0.0002, "epoch": 1.4052287581699345, "step": 430}, {"loss": 1.1685, "grad_norm": 0.44206851720809937, "learning_rate": 0.0002, "epoch": 1.4379084967320261, "step": 440}, {"loss": 1.0347, "grad_norm": 0.3492952585220337, "learning_rate": 0.0002, "epoch": 1.4705882352941178, "step": 450}, {"loss": 1.0534, "grad_norm": 0.376423716545105, "learning_rate": 0.0002, "epoch": 1.5032679738562091, "step": 460}, {"loss": 1.1162, "grad_norm": 0.359757661819458, "learning_rate": 0.0002, "epoch": 1.5359477124183005, "step": 470}, {"loss": 0.9586, "grad_norm": 0.3385067880153656, "learning_rate": 0.0002, "epoch": 1.5686274509803921, "step": 480}, {"loss": 1.0807, "grad_norm": 0.4943889379501343, "learning_rate": 0.0002, "epoch": 1.6013071895424837, "step": 490}, {"loss": 1.0796, "grad_norm": 0.4203241169452667, "learning_rate": 0.0002, "epoch": 1.6339869281045751, "step": 500}, {"loss": 1.1059, "grad_norm": 0.3093789219856262, "learning_rate": 0.0002, "epoch": 1.6666666666666665, "step": 510}, {"loss": 1.0323, "grad_norm": 0.3653067350387573, "learning_rate": 0.0002, "epoch": 1.6993464052287581, "step": 520}, {"loss": 1.0885, "grad_norm": 0.36761337518692017, "learning_rate": 0.0002, "epoch": 1.7320261437908497, "step": 530}, {"loss": 1.1698, "grad_norm": 0.5040399432182312, "learning_rate": 0.0002, "epoch": 1.7647058823529411, "step": 540}, {"loss": 1.0105, "grad_norm": 0.3818035125732422, "learning_rate": 0.0002, "epoch": 1.7973856209150327, "step": 550}, {"loss": 0.94, "grad_norm": 0.4021618664264679, "learning_rate": 0.0002, "epoch": 1.8300653594771243, "step": 560}, {"loss": 1.0358, "grad_norm": 0.3986459970474243, "learning_rate": 0.0002, "epoch": 1.8627450980392157, "step": 570}, {"loss": 1.003, "grad_norm": 0.48416733741760254, "learning_rate": 0.0002, "epoch": 1.8954248366013071, "step": 580}, {"loss": 1.1146, "grad_norm": 0.36853986978530884, "learning_rate": 0.0002, "epoch": 1.9281045751633987, "step": 590}, {"loss": 1.0689, "grad_norm": 0.383022665977478, "learning_rate": 0.0002, "epoch": 1.9607843137254903, "step": 600}, {"loss": 1.098, "grad_norm": 0.3169507086277008, "learning_rate": 0.0002, "epoch": 1.9934640522875817, "step": 610}, {"eval_loss": 1.1845070123672485, "eval_runtime": 46.2811, "eval_samples_per_second": 9.421, "eval_steps_per_second": 1.188, "epoch": 2.0, "step": 612}, {"loss": 0.9618, "grad_norm": 0.8920142650604248, "learning_rate": 0.0002, "epoch": 2.026143790849673, "step": 620}, {"loss": 0.9784, "grad_norm": 0.4814859628677368, "learning_rate": 0.0002, "epoch": 2.0588235294117645, "step": 630}, {"loss": 0.8464, "grad_norm": 0.4251559376716614, "learning_rate": 0.0002, "epoch": 2.0915032679738563, "step": 640}, {"loss": 0.932, "grad_norm": 0.5295765399932861, "learning_rate": 0.0002, "epoch": 2.1241830065359477, "step": 650}, {"loss": 0.9603, "grad_norm": 0.45016610622406006, "learning_rate": 0.0002, "epoch": 2.156862745098039, "step": 660}, {"loss": 0.8738, "grad_norm": 0.5870586633682251, "learning_rate": 0.0002, "epoch": 2.189542483660131, "step": 670}, {"loss": 0.9483, "grad_norm": 0.5174715518951416, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 680}, {"loss": 0.9551, "grad_norm": 0.5252485275268555, "learning_rate": 0.0002, "epoch": 2.2549019607843137, "step": 690}, {"loss": 0.9253, "grad_norm": 0.5158312320709229, "learning_rate": 0.0002, "epoch": 2.287581699346405, "step": 700}, {"loss": 0.9278, "grad_norm": 0.4824209213256836, "learning_rate": 0.0002, "epoch": 2.3202614379084965, "step": 710}, {"loss": 0.8804, "grad_norm": 0.6335175037384033, "learning_rate": 0.0002, "epoch": 2.3529411764705883, "step": 720}, {"loss": 0.9685, "grad_norm": 0.5240563154220581, "learning_rate": 0.0002, "epoch": 2.3856209150326797, "step": 730}, {"loss": 0.8794, "grad_norm": 0.5172886252403259, "learning_rate": 0.0002, "epoch": 2.418300653594771, "step": 740}, {"loss": 0.8158, "grad_norm": 0.48972561955451965, "learning_rate": 0.0002, "epoch": 2.450980392156863, "step": 750}, {"loss": 0.8766, "grad_norm": 0.5295189023017883, "learning_rate": 0.0002, "epoch": 2.4836601307189543, "step": 760}, {"loss": 0.8695, "grad_norm": 0.5487208962440491, "learning_rate": 0.0002, "epoch": 2.5163398692810457, "step": 770}, {"loss": 1.0109, "grad_norm": 0.5375093221664429, "learning_rate": 0.0002, "epoch": 2.549019607843137, "step": 780}, {"loss": 0.9244, "grad_norm": 0.5424453020095825, "learning_rate": 0.0002, "epoch": 2.581699346405229, "step": 790}, {"loss": 1.0424, "grad_norm": 0.6029134392738342, "learning_rate": 0.0002, "epoch": 2.6143790849673203, "step": 800}, {"loss": 0.8688, "grad_norm": 0.6584921479225159, "learning_rate": 0.0002, "epoch": 2.6470588235294117, "step": 810}, {"loss": 0.7796, "grad_norm": 0.5735557675361633, "learning_rate": 0.0002, "epoch": 2.6797385620915035, "step": 820}, {"loss": 0.8834, "grad_norm": 0.5216763019561768, "learning_rate": 0.0002, "epoch": 2.712418300653595, "step": 830}, {"loss": 0.8946, "grad_norm": 0.5455219149589539, "learning_rate": 0.0002, "epoch": 2.7450980392156863, "step": 840}, {"loss": 0.8037, "grad_norm": 0.5139284729957581, "learning_rate": 0.0002, "epoch": 2.7777777777777777, "step": 850}, {"loss": 0.988, "grad_norm": 0.5096403360366821, "learning_rate": 0.0002, "epoch": 2.810457516339869, "step": 860}, {"loss": 0.9169, "grad_norm": 0.6337038278579712, "learning_rate": 0.0002, "epoch": 2.843137254901961, "step": 870}, {"loss": 0.8938, "grad_norm": 0.47218772768974304, "learning_rate": 0.0002, "epoch": 2.8758169934640523, "step": 880}, {"loss": 0.8554, "grad_norm": 0.4640636742115021, "learning_rate": 0.0002, "epoch": 2.9084967320261437, "step": 890}, {"loss": 0.8625, "grad_norm": 0.4199628531932831, "learning_rate": 0.0002, "epoch": 2.9411764705882355, "step": 900}, {"loss": 0.8104, "grad_norm": 0.5067117214202881, "learning_rate": 0.0002, "epoch": 2.973856209150327, "step": 910}, {"eval_loss": 1.2291251420974731, "eval_runtime": 46.2557, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 3.0, "step": 918}, {"loss": 0.8157, "grad_norm": 0.8342176079750061, "learning_rate": 0.0002, "epoch": 3.0065359477124183, "step": 920}, {"loss": 0.6855, "grad_norm": 0.7695813775062561, "learning_rate": 0.0002, "epoch": 3.0392156862745097, "step": 930}, {"loss": 0.6173, "grad_norm": 0.6819486618041992, "learning_rate": 0.0002, "epoch": 3.0718954248366015, "step": 940}, {"loss": 0.6495, "grad_norm": 0.7568879723548889, "learning_rate": 0.0002, "epoch": 3.104575163398693, "step": 950}, {"loss": 0.7905, "grad_norm": 0.6760695576667786, "learning_rate": 0.0002, "epoch": 3.1372549019607843, "step": 960}, {"loss": 0.6405, "grad_norm": 0.6359127759933472, "learning_rate": 0.0002, "epoch": 3.1699346405228757, "step": 970}, {"loss": 0.7172, "grad_norm": 0.8414971828460693, "learning_rate": 0.0002, "epoch": 3.2026143790849675, "step": 980}, {"loss": 0.7865, "grad_norm": 0.68381667137146, "learning_rate": 0.0002, "epoch": 3.235294117647059, "step": 990}, {"loss": 0.6651, "grad_norm": 0.6852193474769592, "learning_rate": 0.0002, "epoch": 3.2679738562091503, "step": 1000}, {"loss": 0.6571, "grad_norm": 0.8184967041015625, "learning_rate": 0.0002, "epoch": 3.3006535947712417, "step": 1010}, {"loss": 0.7036, "grad_norm": 1.047290563583374, "learning_rate": 0.0002, "epoch": 3.3333333333333335, "step": 1020}, {"loss": 0.7215, "grad_norm": 0.8291178345680237, "learning_rate": 0.0002, "epoch": 3.366013071895425, "step": 1030}, {"loss": 0.6243, "grad_norm": 0.6668022871017456, "learning_rate": 0.0002, "epoch": 3.3986928104575163, "step": 1040}, {"loss": 0.7459, "grad_norm": 0.6354008316993713, "learning_rate": 0.0002, "epoch": 3.431372549019608, "step": 1050}, {"loss": 0.6826, "grad_norm": 1.2028366327285767, "learning_rate": 0.0002, "epoch": 3.4640522875816995, "step": 1060}, {"loss": 0.5913, "grad_norm": 0.717367947101593, "learning_rate": 0.0002, "epoch": 3.496732026143791, "step": 1070}, {"loss": 0.6903, "grad_norm": 0.542179524898529, "learning_rate": 0.0002, "epoch": 3.5294117647058822, "step": 1080}, {"loss": 0.7673, "grad_norm": 0.845981776714325, "learning_rate": 0.0002, "epoch": 3.5620915032679736, "step": 1090}, {"loss": 0.7089, "grad_norm": 0.7381046414375305, "learning_rate": 0.0002, "epoch": 3.5947712418300655, "step": 1100}, {"loss": 0.6705, "grad_norm": 0.6563456058502197, "learning_rate": 0.0002, "epoch": 3.627450980392157, "step": 1110}, {"loss": 0.7767, "grad_norm": 0.7130876779556274, "learning_rate": 0.0002, "epoch": 3.6601307189542482, "step": 1120}, {"loss": 0.7164, "grad_norm": 0.800032913684845, "learning_rate": 0.0002, "epoch": 3.69281045751634, "step": 1130}, {"loss": 0.7272, "grad_norm": 0.980328381061554, "learning_rate": 0.0002, "epoch": 3.7254901960784315, "step": 1140}, {"loss": 0.7672, "grad_norm": 0.8542261123657227, "learning_rate": 0.0002, "epoch": 3.758169934640523, "step": 1150}, {"loss": 0.679, "grad_norm": 0.6302552819252014, "learning_rate": 0.0002, "epoch": 3.7908496732026142, "step": 1160}, {"loss": 0.7457, "grad_norm": 0.515398383140564, "learning_rate": 0.0002, "epoch": 3.8235294117647056, "step": 1170}, {"loss": 0.693, "grad_norm": 1.2427130937576294, "learning_rate": 0.0002, "epoch": 3.8562091503267975, "step": 1180}, {"loss": 0.7182, "grad_norm": 0.8206831216812134, "learning_rate": 0.0002, "epoch": 3.888888888888889, "step": 1190}, {"loss": 0.7519, "grad_norm": 0.7633249163627625, "learning_rate": 0.0002, "epoch": 3.9215686274509802, "step": 1200}, {"loss": 0.7082, "grad_norm": 0.8034512400627136, "learning_rate": 0.0002, "epoch": 3.954248366013072, "step": 1210}, {"loss": 0.6834, "grad_norm": 0.7667182087898254, "learning_rate": 0.0002, "epoch": 3.9869281045751634, "step": 1220}]}
+{"epoch": 5.0, "step": 1530, "epoch_duration": 455.743275642395, "total_accumulated_duration": 2279.8934981822968, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.224609375}, "avg_memory_reserved": {"GPU_0": 28746.0}, "peak_memory_reserved": {"GPU_0": 28746.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.3561, "grad_norm": 0.631856381893158, "learning_rate": 0.0002, "epoch": 0.032679738562091505, "step": 10}, {"loss": 1.8141, "grad_norm": 0.5065668821334839, "learning_rate": 0.0002, "epoch": 0.06535947712418301, "step": 20}, {"loss": 1.4952, "grad_norm": 0.6978895664215088, "learning_rate": 0.0002, "epoch": 0.09803921568627451, "step": 30}, {"loss": 1.4829, "grad_norm": 0.6619144082069397, "learning_rate": 0.0002, "epoch": 0.13071895424836602, "step": 40}, {"loss": 1.3038, "grad_norm": 0.6153793931007385, "learning_rate": 0.0002, "epoch": 0.16339869281045752, "step": 50}, {"loss": 1.1429, "grad_norm": 0.4703301787376404, "learning_rate": 0.0002, "epoch": 0.19607843137254902, "step": 60}, {"loss": 1.2828, "grad_norm": 1.1672580242156982, "learning_rate": 0.0002, "epoch": 0.22875816993464052, "step": 70}, {"loss": 1.0985, "grad_norm": 0.3455565273761749, "learning_rate": 0.0002, "epoch": 0.26143790849673204, "step": 80}, {"loss": 1.1359, "grad_norm": 0.36216291785240173, "learning_rate": 0.0002, "epoch": 0.29411764705882354, "step": 90}, {"loss": 1.2544, "grad_norm": 0.4545166492462158, "learning_rate": 0.0002, "epoch": 0.32679738562091504, "step": 100}, {"loss": 1.2287, "grad_norm": 0.3612092435359955, "learning_rate": 0.0002, "epoch": 0.35947712418300654, "step": 110}, {"loss": 1.1868, "grad_norm": 0.5080830454826355, "learning_rate": 0.0002, "epoch": 0.39215686274509803, "step": 120}, {"loss": 1.1902, "grad_norm": 0.3268195390701294, "learning_rate": 0.0002, "epoch": 0.42483660130718953, "step": 130}, {"loss": 1.247, "grad_norm": 0.33971714973449707, "learning_rate": 0.0002, "epoch": 0.45751633986928103, "step": 140}, {"loss": 1.1844, "grad_norm": 0.4036043882369995, "learning_rate": 0.0002, "epoch": 0.49019607843137253, "step": 150}, {"loss": 1.1624, "grad_norm": 0.35938864946365356, "learning_rate": 0.0002, "epoch": 0.5228758169934641, "step": 160}, {"loss": 1.164, "grad_norm": 0.28880223631858826, "learning_rate": 0.0002, "epoch": 0.5555555555555556, "step": 170}, {"loss": 1.3521, "grad_norm": 0.3436269462108612, "learning_rate": 0.0002, "epoch": 0.5882352941176471, "step": 180}, {"loss": 1.2456, "grad_norm": 0.41923725605010986, "learning_rate": 0.0002, "epoch": 0.6209150326797386, "step": 190}, {"loss": 1.2226, "grad_norm": 0.25119203329086304, "learning_rate": 0.0002, "epoch": 0.6535947712418301, "step": 200}, {"loss": 1.1568, "grad_norm": 0.5870180726051331, "learning_rate": 0.0002, "epoch": 0.6862745098039216, "step": 210}, {"loss": 1.064, "grad_norm": 0.2831224203109741, "learning_rate": 0.0002, "epoch": 0.7189542483660131, "step": 220}, {"loss": 1.2469, "grad_norm": 0.3192005753517151, "learning_rate": 0.0002, "epoch": 0.7516339869281046, "step": 230}, {"loss": 1.1613, "grad_norm": 0.2998219430446625, "learning_rate": 0.0002, "epoch": 0.7843137254901961, "step": 240}, {"loss": 1.205, "grad_norm": 0.32855790853500366, "learning_rate": 0.0002, "epoch": 0.8169934640522876, "step": 250}, {"loss": 1.1631, "grad_norm": 0.3403124213218689, "learning_rate": 0.0002, "epoch": 0.8496732026143791, "step": 260}, {"loss": 1.1646, "grad_norm": 0.277401328086853, "learning_rate": 0.0002, "epoch": 0.8823529411764706, "step": 270}, {"loss": 1.084, "grad_norm": 0.2975269556045532, "learning_rate": 0.0002, "epoch": 0.9150326797385621, "step": 280}, {"loss": 1.2039, "grad_norm": 1.7909578084945679, "learning_rate": 0.0002, "epoch": 0.9477124183006536, "step": 290}, {"loss": 1.1226, "grad_norm": 0.2917245328426361, "learning_rate": 0.0002, "epoch": 0.9803921568627451, "step": 300}, {"eval_loss": 1.1937541961669922, "eval_runtime": 46.2571, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 1.0, "step": 306}, {"loss": 1.2011, "grad_norm": 0.26494982838630676, "learning_rate": 0.0002, "epoch": 1.0130718954248366, "step": 310}, {"loss": 1.0565, "grad_norm": 0.6289355754852295, "learning_rate": 0.0002, "epoch": 1.0457516339869282, "step": 320}, {"loss": 1.1619, "grad_norm": 0.26784011721611023, "learning_rate": 0.0002, "epoch": 1.0784313725490196, "step": 330}, {"loss": 1.1151, "grad_norm": 0.3392215967178345, "learning_rate": 0.0002, "epoch": 1.1111111111111112, "step": 340}, {"loss": 1.0752, "grad_norm": 0.40005937218666077, "learning_rate": 0.0002, "epoch": 1.1437908496732025, "step": 350}, {"loss": 1.0408, "grad_norm": 0.3590582013130188, "learning_rate": 0.0002, "epoch": 1.1764705882352942, "step": 360}, {"loss": 1.0836, "grad_norm": 0.3995305895805359, "learning_rate": 0.0002, "epoch": 1.2091503267973855, "step": 370}, {"loss": 1.0992, "grad_norm": 0.2950291633605957, "learning_rate": 0.0002, "epoch": 1.2418300653594772, "step": 380}, {"loss": 1.1152, "grad_norm": 0.32035166025161743, "learning_rate": 0.0002, "epoch": 1.2745098039215685, "step": 390}, {"loss": 1.1467, "grad_norm": 0.410366415977478, "learning_rate": 0.0002, "epoch": 1.3071895424836601, "step": 400}, {"loss": 0.9985, "grad_norm": 0.3106379508972168, "learning_rate": 0.0002, "epoch": 1.3398692810457518, "step": 410}, {"loss": 0.9789, "grad_norm": 0.38580670952796936, "learning_rate": 0.0002, "epoch": 1.3725490196078431, "step": 420}, {"loss": 1.0931, "grad_norm": 0.34411361813545227, "learning_rate": 0.0002, "epoch": 1.4052287581699345, "step": 430}, {"loss": 1.1685, "grad_norm": 0.44206851720809937, "learning_rate": 0.0002, "epoch": 1.4379084967320261, "step": 440}, {"loss": 1.0347, "grad_norm": 0.3492952585220337, "learning_rate": 0.0002, "epoch": 1.4705882352941178, "step": 450}, {"loss": 1.0534, "grad_norm": 0.376423716545105, "learning_rate": 0.0002, "epoch": 1.5032679738562091, "step": 460}, {"loss": 1.1162, "grad_norm": 0.359757661819458, "learning_rate": 0.0002, "epoch": 1.5359477124183005, "step": 470}, {"loss": 0.9586, "grad_norm": 0.3385067880153656, "learning_rate": 0.0002, "epoch": 1.5686274509803921, "step": 480}, {"loss": 1.0807, "grad_norm": 0.4943889379501343, "learning_rate": 0.0002, "epoch": 1.6013071895424837, "step": 490}, {"loss": 1.0796, "grad_norm": 0.4203241169452667, "learning_rate": 0.0002, "epoch": 1.6339869281045751, "step": 500}, {"loss": 1.1059, "grad_norm": 0.3093789219856262, "learning_rate": 0.0002, "epoch": 1.6666666666666665, "step": 510}, {"loss": 1.0323, "grad_norm": 0.3653067350387573, "learning_rate": 0.0002, "epoch": 1.6993464052287581, "step": 520}, {"loss": 1.0885, "grad_norm": 0.36761337518692017, "learning_rate": 0.0002, "epoch": 1.7320261437908497, "step": 530}, {"loss": 1.1698, "grad_norm": 0.5040399432182312, "learning_rate": 0.0002, "epoch": 1.7647058823529411, "step": 540}, {"loss": 1.0105, "grad_norm": 0.3818035125732422, "learning_rate": 0.0002, "epoch": 1.7973856209150327, "step": 550}, {"loss": 0.94, "grad_norm": 0.4021618664264679, "learning_rate": 0.0002, "epoch": 1.8300653594771243, "step": 560}, {"loss": 1.0358, "grad_norm": 0.3986459970474243, "learning_rate": 0.0002, "epoch": 1.8627450980392157, "step": 570}, {"loss": 1.003, "grad_norm": 0.48416733741760254, "learning_rate": 0.0002, "epoch": 1.8954248366013071, "step": 580}, {"loss": 1.1146, "grad_norm": 0.36853986978530884, "learning_rate": 0.0002, "epoch": 1.9281045751633987, "step": 590}, {"loss": 1.0689, "grad_norm": 0.383022665977478, "learning_rate": 0.0002, "epoch": 1.9607843137254903, "step": 600}, {"loss": 1.098, "grad_norm": 0.3169507086277008, "learning_rate": 0.0002, "epoch": 1.9934640522875817, "step": 610}, {"eval_loss": 1.1845070123672485, "eval_runtime": 46.2811, "eval_samples_per_second": 9.421, "eval_steps_per_second": 1.188, "epoch": 2.0, "step": 612}, {"loss": 0.9618, "grad_norm": 0.8920142650604248, "learning_rate": 0.0002, "epoch": 2.026143790849673, "step": 620}, {"loss": 0.9784, "grad_norm": 0.4814859628677368, "learning_rate": 0.0002, "epoch": 2.0588235294117645, "step": 630}, {"loss": 0.8464, "grad_norm": 0.4251559376716614, "learning_rate": 0.0002, "epoch": 2.0915032679738563, "step": 640}, {"loss": 0.932, "grad_norm": 0.5295765399932861, "learning_rate": 0.0002, "epoch": 2.1241830065359477, "step": 650}, {"loss": 0.9603, "grad_norm": 0.45016610622406006, "learning_rate": 0.0002, "epoch": 2.156862745098039, "step": 660}, {"loss": 0.8738, "grad_norm": 0.5870586633682251, "learning_rate": 0.0002, "epoch": 2.189542483660131, "step": 670}, {"loss": 0.9483, "grad_norm": 0.5174715518951416, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 680}, {"loss": 0.9551, "grad_norm": 0.5252485275268555, "learning_rate": 0.0002, "epoch": 2.2549019607843137, "step": 690}, {"loss": 0.9253, "grad_norm": 0.5158312320709229, "learning_rate": 0.0002, "epoch": 2.287581699346405, "step": 700}, {"loss": 0.9278, "grad_norm": 0.4824209213256836, "learning_rate": 0.0002, "epoch": 2.3202614379084965, "step": 710}, {"loss": 0.8804, "grad_norm": 0.6335175037384033, "learning_rate": 0.0002, "epoch": 2.3529411764705883, "step": 720}, {"loss": 0.9685, "grad_norm": 0.5240563154220581, "learning_rate": 0.0002, "epoch": 2.3856209150326797, "step": 730}, {"loss": 0.8794, "grad_norm": 0.5172886252403259, "learning_rate": 0.0002, "epoch": 2.418300653594771, "step": 740}, {"loss": 0.8158, "grad_norm": 0.48972561955451965, "learning_rate": 0.0002, "epoch": 2.450980392156863, "step": 750}, {"loss": 0.8766, "grad_norm": 0.5295189023017883, "learning_rate": 0.0002, "epoch": 2.4836601307189543, "step": 760}, {"loss": 0.8695, "grad_norm": 0.5487208962440491, "learning_rate": 0.0002, "epoch": 2.5163398692810457, "step": 770}, {"loss": 1.0109, "grad_norm": 0.5375093221664429, "learning_rate": 0.0002, "epoch": 2.549019607843137, "step": 780}, {"loss": 0.9244, "grad_norm": 0.5424453020095825, "learning_rate": 0.0002, "epoch": 2.581699346405229, "step": 790}, {"loss": 1.0424, "grad_norm": 0.6029134392738342, "learning_rate": 0.0002, "epoch": 2.6143790849673203, "step": 800}, {"loss": 0.8688, "grad_norm": 0.6584921479225159, "learning_rate": 0.0002, "epoch": 2.6470588235294117, "step": 810}, {"loss": 0.7796, "grad_norm": 0.5735557675361633, "learning_rate": 0.0002, "epoch": 2.6797385620915035, "step": 820}, {"loss": 0.8834, "grad_norm": 0.5216763019561768, "learning_rate": 0.0002, "epoch": 2.712418300653595, "step": 830}, {"loss": 0.8946, "grad_norm": 0.5455219149589539, "learning_rate": 0.0002, "epoch": 2.7450980392156863, "step": 840}, {"loss": 0.8037, "grad_norm": 0.5139284729957581, "learning_rate": 0.0002, "epoch": 2.7777777777777777, "step": 850}, {"loss": 0.988, "grad_norm": 0.5096403360366821, "learning_rate": 0.0002, "epoch": 2.810457516339869, "step": 860}, {"loss": 0.9169, "grad_norm": 0.6337038278579712, "learning_rate": 0.0002, "epoch": 2.843137254901961, "step": 870}, {"loss": 0.8938, "grad_norm": 0.47218772768974304, "learning_rate": 0.0002, "epoch": 2.8758169934640523, "step": 880}, {"loss": 0.8554, "grad_norm": 0.4640636742115021, "learning_rate": 0.0002, "epoch": 2.9084967320261437, "step": 890}, {"loss": 0.8625, "grad_norm": 0.4199628531932831, "learning_rate": 0.0002, "epoch": 2.9411764705882355, "step": 900}, {"loss": 0.8104, "grad_norm": 0.5067117214202881, "learning_rate": 0.0002, "epoch": 2.973856209150327, "step": 910}, {"eval_loss": 1.2291251420974731, "eval_runtime": 46.2557, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 3.0, "step": 918}, {"loss": 0.8157, "grad_norm": 0.8342176079750061, "learning_rate": 0.0002, "epoch": 3.0065359477124183, "step": 920}, {"loss": 0.6855, "grad_norm": 0.7695813775062561, "learning_rate": 0.0002, "epoch": 3.0392156862745097, "step": 930}, {"loss": 0.6173, "grad_norm": 0.6819486618041992, "learning_rate": 0.0002, "epoch": 3.0718954248366015, "step": 940}, {"loss": 0.6495, "grad_norm": 0.7568879723548889, "learning_rate": 0.0002, "epoch": 3.104575163398693, "step": 950}, {"loss": 0.7905, "grad_norm": 0.6760695576667786, "learning_rate": 0.0002, "epoch": 3.1372549019607843, "step": 960}, {"loss": 0.6405, "grad_norm": 0.6359127759933472, "learning_rate": 0.0002, "epoch": 3.1699346405228757, "step": 970}, {"loss": 0.7172, "grad_norm": 0.8414971828460693, "learning_rate": 0.0002, "epoch": 3.2026143790849675, "step": 980}, {"loss": 0.7865, "grad_norm": 0.68381667137146, "learning_rate": 0.0002, "epoch": 3.235294117647059, "step": 990}, {"loss": 0.6651, "grad_norm": 0.6852193474769592, "learning_rate": 0.0002, "epoch": 3.2679738562091503, "step": 1000}, {"loss": 0.6571, "grad_norm": 0.8184967041015625, "learning_rate": 0.0002, "epoch": 3.3006535947712417, "step": 1010}, {"loss": 0.7036, "grad_norm": 1.047290563583374, "learning_rate": 0.0002, "epoch": 3.3333333333333335, "step": 1020}, {"loss": 0.7215, "grad_norm": 0.8291178345680237, "learning_rate": 0.0002, "epoch": 3.366013071895425, "step": 1030}, {"loss": 0.6243, "grad_norm": 0.6668022871017456, "learning_rate": 0.0002, "epoch": 3.3986928104575163, "step": 1040}, {"loss": 0.7459, "grad_norm": 0.6354008316993713, "learning_rate": 0.0002, "epoch": 3.431372549019608, "step": 1050}, {"loss": 0.6826, "grad_norm": 1.2028366327285767, "learning_rate": 0.0002, "epoch": 3.4640522875816995, "step": 1060}, {"loss": 0.5913, "grad_norm": 0.717367947101593, "learning_rate": 0.0002, "epoch": 3.496732026143791, "step": 1070}, {"loss": 0.6903, "grad_norm": 0.542179524898529, "learning_rate": 0.0002, "epoch": 3.5294117647058822, "step": 1080}, {"loss": 0.7673, "grad_norm": 0.845981776714325, "learning_rate": 0.0002, "epoch": 3.5620915032679736, "step": 1090}, {"loss": 0.7089, "grad_norm": 0.7381046414375305, "learning_rate": 0.0002, "epoch": 3.5947712418300655, "step": 1100}, {"loss": 0.6705, "grad_norm": 0.6563456058502197, "learning_rate": 0.0002, "epoch": 3.627450980392157, "step": 1110}, {"loss": 0.7767, "grad_norm": 0.7130876779556274, "learning_rate": 0.0002, "epoch": 3.6601307189542482, "step": 1120}, {"loss": 0.7164, "grad_norm": 0.800032913684845, "learning_rate": 0.0002, "epoch": 3.69281045751634, "step": 1130}, {"loss": 0.7272, "grad_norm": 0.980328381061554, "learning_rate": 0.0002, "epoch": 3.7254901960784315, "step": 1140}, {"loss": 0.7672, "grad_norm": 0.8542261123657227, "learning_rate": 0.0002, "epoch": 3.758169934640523, "step": 1150}, {"loss": 0.679, "grad_norm": 0.6302552819252014, "learning_rate": 0.0002, "epoch": 3.7908496732026142, "step": 1160}, {"loss": 0.7457, "grad_norm": 0.515398383140564, "learning_rate": 0.0002, "epoch": 3.8235294117647056, "step": 1170}, {"loss": 0.693, "grad_norm": 1.2427130937576294, "learning_rate": 0.0002, "epoch": 3.8562091503267975, "step": 1180}, {"loss": 0.7182, "grad_norm": 0.8206831216812134, "learning_rate": 0.0002, "epoch": 3.888888888888889, "step": 1190}, {"loss": 0.7519, "grad_norm": 0.7633249163627625, "learning_rate": 0.0002, "epoch": 3.9215686274509802, "step": 1200}, {"loss": 0.7082, "grad_norm": 0.8034512400627136, "learning_rate": 0.0002, "epoch": 3.954248366013072, "step": 1210}, {"loss": 0.6834, "grad_norm": 0.7667182087898254, "learning_rate": 0.0002, "epoch": 3.9869281045751634, "step": 1220}, {"eval_loss": 1.3456707000732422, "eval_runtime": 46.2562, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 4.0, "step": 1224}, {"loss": 0.582, "grad_norm": 0.7724746465682983, "learning_rate": 0.0002, "epoch": 4.019607843137255, "step": 1230}, {"loss": 0.4759, "grad_norm": 1.166916847229004, "learning_rate": 0.0002, "epoch": 4.052287581699346, "step": 1240}, {"loss": 0.4995, "grad_norm": 0.7234508991241455, "learning_rate": 0.0002, "epoch": 4.084967320261438, "step": 1250}, {"loss": 0.4863, "grad_norm": 1.1418060064315796, "learning_rate": 0.0002, "epoch": 4.117647058823529, "step": 1260}, {"loss": 0.5425, "grad_norm": 0.9603922367095947, "learning_rate": 0.0002, "epoch": 4.150326797385621, "step": 1270}, {"loss": 0.4892, "grad_norm": 0.8976530432701111, "learning_rate": 0.0002, "epoch": 4.183006535947713, "step": 1280}, {"loss": 0.473, "grad_norm": 0.6855078339576721, "learning_rate": 0.0002, "epoch": 4.215686274509804, "step": 1290}, {"loss": 0.4416, "grad_norm": 1.2676647901535034, "learning_rate": 0.0002, "epoch": 4.248366013071895, "step": 1300}, {"loss": 0.5071, "grad_norm": 1.104057788848877, "learning_rate": 0.0002, "epoch": 4.281045751633987, "step": 1310}, {"loss": 0.5168, "grad_norm": 1.7076562643051147, "learning_rate": 0.0002, "epoch": 4.313725490196078, "step": 1320}, {"loss": 0.4655, "grad_norm": 1.2308520078659058, "learning_rate": 0.0002, "epoch": 4.34640522875817, "step": 1330}, {"loss": 0.5322, "grad_norm": 1.2652729749679565, "learning_rate": 0.0002, "epoch": 4.379084967320262, "step": 1340}, {"loss": 0.5262, "grad_norm": 1.054958701133728, "learning_rate": 0.0002, "epoch": 4.411764705882353, "step": 1350}, {"loss": 0.4747, "grad_norm": 1.0130749940872192, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 1360}, {"loss": 0.4887, "grad_norm": 1.0517818927764893, "learning_rate": 0.0002, "epoch": 4.477124183006536, "step": 1370}, {"loss": 0.4906, "grad_norm": 0.8593037128448486, "learning_rate": 0.0002, "epoch": 4.509803921568627, "step": 1380}, {"loss": 0.5049, "grad_norm": 1.0248081684112549, "learning_rate": 0.0002, "epoch": 4.542483660130719, "step": 1390}, {"loss": 0.472, "grad_norm": 0.8999413847923279, "learning_rate": 0.0002, "epoch": 4.57516339869281, "step": 1400}, {"loss": 0.5102, "grad_norm": 0.9106912612915039, "learning_rate": 0.0002, "epoch": 4.607843137254902, "step": 1410}, {"loss": 0.5203, "grad_norm": 1.2736181020736694, "learning_rate": 0.0002, "epoch": 4.640522875816993, "step": 1420}, {"loss": 0.5101, "grad_norm": 0.9311690926551819, "learning_rate": 0.0002, "epoch": 4.673202614379085, "step": 1430}, {"loss": 0.5648, "grad_norm": 1.0455045700073242, "learning_rate": 0.0002, "epoch": 4.705882352941177, "step": 1440}, {"loss": 0.5004, "grad_norm": 1.0190727710723877, "learning_rate": 0.0002, "epoch": 4.738562091503268, "step": 1450}, {"loss": 0.5506, "grad_norm": 1.333198070526123, "learning_rate": 0.0002, "epoch": 4.771241830065359, "step": 1460}, {"loss": 0.5846, "grad_norm": 0.8808416724205017, "learning_rate": 0.0002, "epoch": 4.803921568627451, "step": 1470}, {"loss": 0.4671, "grad_norm": 0.8896227478981018, "learning_rate": 0.0002, "epoch": 4.836601307189542, "step": 1480}, {"loss": 0.4732, "grad_norm": 1.212323784828186, "learning_rate": 0.0002, "epoch": 4.8692810457516345, "step": 1490}, {"loss": 0.5263, "grad_norm": 1.0490120649337769, "learning_rate": 0.0002, "epoch": 4.901960784313726, "step": 1500}, {"loss": 0.5815, "grad_norm": 0.8946618437767029, "learning_rate": 0.0002, "epoch": 4.934640522875817, "step": 1510}, {"loss": 0.5369, "grad_norm": 1.0609275102615356, "learning_rate": 0.0002, "epoch": 4.967320261437909, "step": 1520}, {"loss": 0.5348, "grad_norm": 0.8885099291801453, "learning_rate": 0.0002, "epoch": 5.0, "step": 1530}]}
+{"epoch": 6.0, "step": 1836, "epoch_duration": 457.0913918018341, "total_accumulated_duration": 2736.984889984131, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.224609375}, "avg_memory_reserved": {"GPU_0": 28746.0}, "peak_memory_reserved": {"GPU_0": 28746.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.3561, "grad_norm": 0.631856381893158, "learning_rate": 0.0002, "epoch": 0.032679738562091505, "step": 10}, {"loss": 1.8141, "grad_norm": 0.5065668821334839, "learning_rate": 0.0002, "epoch": 0.06535947712418301, "step": 20}, {"loss": 1.4952, "grad_norm": 0.6978895664215088, "learning_rate": 0.0002, "epoch": 0.09803921568627451, "step": 30}, {"loss": 1.4829, "grad_norm": 0.6619144082069397, "learning_rate": 0.0002, "epoch": 0.13071895424836602, "step": 40}, {"loss": 1.3038, "grad_norm": 0.6153793931007385, "learning_rate": 0.0002, "epoch": 0.16339869281045752, "step": 50}, {"loss": 1.1429, "grad_norm": 0.4703301787376404, "learning_rate": 0.0002, "epoch": 0.19607843137254902, "step": 60}, {"loss": 1.2828, "grad_norm": 1.1672580242156982, "learning_rate": 0.0002, "epoch": 0.22875816993464052, "step": 70}, {"loss": 1.0985, "grad_norm": 0.3455565273761749, "learning_rate": 0.0002, "epoch": 0.26143790849673204, "step": 80}, {"loss": 1.1359, "grad_norm": 0.36216291785240173, "learning_rate": 0.0002, "epoch": 0.29411764705882354, "step": 90}, {"loss": 1.2544, "grad_norm": 0.4545166492462158, "learning_rate": 0.0002, "epoch": 0.32679738562091504, "step": 100}, {"loss": 1.2287, "grad_norm": 0.3612092435359955, "learning_rate": 0.0002, "epoch": 0.35947712418300654, "step": 110}, {"loss": 1.1868, "grad_norm": 0.5080830454826355, "learning_rate": 0.0002, "epoch": 0.39215686274509803, "step": 120}, {"loss": 1.1902, "grad_norm": 0.3268195390701294, "learning_rate": 0.0002, "epoch": 0.42483660130718953, "step": 130}, {"loss": 1.247, "grad_norm": 0.33971714973449707, "learning_rate": 0.0002, "epoch": 0.45751633986928103, "step": 140}, {"loss": 1.1844, "grad_norm": 0.4036043882369995, "learning_rate": 0.0002, "epoch": 0.49019607843137253, "step": 150}, {"loss": 1.1624, "grad_norm": 0.35938864946365356, "learning_rate": 0.0002, "epoch": 0.5228758169934641, "step": 160}, {"loss": 1.164, "grad_norm": 0.28880223631858826, "learning_rate": 0.0002, "epoch": 0.5555555555555556, "step": 170}, {"loss": 1.3521, "grad_norm": 0.3436269462108612, "learning_rate": 0.0002, "epoch": 0.5882352941176471, "step": 180}, {"loss": 1.2456, "grad_norm": 0.41923725605010986, "learning_rate": 0.0002, "epoch": 0.6209150326797386, "step": 190}, {"loss": 1.2226, "grad_norm": 0.25119203329086304, "learning_rate": 0.0002, "epoch": 0.6535947712418301, "step": 200}, {"loss": 1.1568, "grad_norm": 0.5870180726051331, "learning_rate": 0.0002, "epoch": 0.6862745098039216, "step": 210}, {"loss": 1.064, "grad_norm": 0.2831224203109741, "learning_rate": 0.0002, "epoch": 0.7189542483660131, "step": 220}, {"loss": 1.2469, "grad_norm": 0.3192005753517151, "learning_rate": 0.0002, "epoch": 0.7516339869281046, "step": 230}, {"loss": 1.1613, "grad_norm": 0.2998219430446625, "learning_rate": 0.0002, "epoch": 0.7843137254901961, "step": 240}, {"loss": 1.205, "grad_norm": 0.32855790853500366, "learning_rate": 0.0002, "epoch": 0.8169934640522876, "step": 250}, {"loss": 1.1631, "grad_norm": 0.3403124213218689, "learning_rate": 0.0002, "epoch": 0.8496732026143791, "step": 260}, {"loss": 1.1646, "grad_norm": 0.277401328086853, "learning_rate": 0.0002, "epoch": 0.8823529411764706, "step": 270}, {"loss": 1.084, "grad_norm": 0.2975269556045532, "learning_rate": 0.0002, "epoch": 0.9150326797385621, "step": 280}, {"loss": 1.2039, "grad_norm": 1.7909578084945679, "learning_rate": 0.0002, "epoch": 0.9477124183006536, "step": 290}, {"loss": 1.1226, "grad_norm": 0.2917245328426361, "learning_rate": 0.0002, "epoch": 0.9803921568627451, "step": 300}, {"eval_loss": 1.1937541961669922, "eval_runtime": 46.2571, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 1.0, "step": 306}, {"loss": 1.2011, "grad_norm": 0.26494982838630676, "learning_rate": 0.0002, "epoch": 1.0130718954248366, "step": 310}, {"loss": 1.0565, "grad_norm": 0.6289355754852295, "learning_rate": 0.0002, "epoch": 1.0457516339869282, "step": 320}, {"loss": 1.1619, "grad_norm": 0.26784011721611023, "learning_rate": 0.0002, "epoch": 1.0784313725490196, "step": 330}, {"loss": 1.1151, "grad_norm": 0.3392215967178345, "learning_rate": 0.0002, "epoch": 1.1111111111111112, "step": 340}, {"loss": 1.0752, "grad_norm": 0.40005937218666077, "learning_rate": 0.0002, "epoch": 1.1437908496732025, "step": 350}, {"loss": 1.0408, "grad_norm": 0.3590582013130188, "learning_rate": 0.0002, "epoch": 1.1764705882352942, "step": 360}, {"loss": 1.0836, "grad_norm": 0.3995305895805359, "learning_rate": 0.0002, "epoch": 1.2091503267973855, "step": 370}, {"loss": 1.0992, "grad_norm": 0.2950291633605957, "learning_rate": 0.0002, "epoch": 1.2418300653594772, "step": 380}, {"loss": 1.1152, "grad_norm": 0.32035166025161743, "learning_rate": 0.0002, "epoch": 1.2745098039215685, "step": 390}, {"loss": 1.1467, "grad_norm": 0.410366415977478, "learning_rate": 0.0002, "epoch": 1.3071895424836601, "step": 400}, {"loss": 0.9985, "grad_norm": 0.3106379508972168, "learning_rate": 0.0002, "epoch": 1.3398692810457518, "step": 410}, {"loss": 0.9789, "grad_norm": 0.38580670952796936, "learning_rate": 0.0002, "epoch": 1.3725490196078431, "step": 420}, {"loss": 1.0931, "grad_norm": 0.34411361813545227, "learning_rate": 0.0002, "epoch": 1.4052287581699345, "step": 430}, {"loss": 1.1685, "grad_norm": 0.44206851720809937, "learning_rate": 0.0002, "epoch": 1.4379084967320261, "step": 440}, {"loss": 1.0347, "grad_norm": 0.3492952585220337, "learning_rate": 0.0002, "epoch": 1.4705882352941178, "step": 450}, {"loss": 1.0534, "grad_norm": 0.376423716545105, "learning_rate": 0.0002, "epoch": 1.5032679738562091, "step": 460}, {"loss": 1.1162, "grad_norm": 0.359757661819458, "learning_rate": 0.0002, "epoch": 1.5359477124183005, "step": 470}, {"loss": 0.9586, "grad_norm": 0.3385067880153656, "learning_rate": 0.0002, "epoch": 1.5686274509803921, "step": 480}, {"loss": 1.0807, "grad_norm": 0.4943889379501343, "learning_rate": 0.0002, "epoch": 1.6013071895424837, "step": 490}, {"loss": 1.0796, "grad_norm": 0.4203241169452667, "learning_rate": 0.0002, "epoch": 1.6339869281045751, "step": 500}, {"loss": 1.1059, "grad_norm": 0.3093789219856262, "learning_rate": 0.0002, "epoch": 1.6666666666666665, "step": 510}, {"loss": 1.0323, "grad_norm": 0.3653067350387573, "learning_rate": 0.0002, "epoch": 1.6993464052287581, "step": 520}, {"loss": 1.0885, "grad_norm": 0.36761337518692017, "learning_rate": 0.0002, "epoch": 1.7320261437908497, "step": 530}, {"loss": 1.1698, "grad_norm": 0.5040399432182312, "learning_rate": 0.0002, "epoch": 1.7647058823529411, "step": 540}, {"loss": 1.0105, "grad_norm": 0.3818035125732422, "learning_rate": 0.0002, "epoch": 1.7973856209150327, "step": 550}, {"loss": 0.94, "grad_norm": 0.4021618664264679, "learning_rate": 0.0002, "epoch": 1.8300653594771243, "step": 560}, {"loss": 1.0358, "grad_norm": 0.3986459970474243, "learning_rate": 0.0002, "epoch": 1.8627450980392157, "step": 570}, {"loss": 1.003, "grad_norm": 0.48416733741760254, "learning_rate": 0.0002, "epoch": 1.8954248366013071, "step": 580}, {"loss": 1.1146, "grad_norm": 0.36853986978530884, "learning_rate": 0.0002, "epoch": 1.9281045751633987, "step": 590}, {"loss": 1.0689, "grad_norm": 0.383022665977478, "learning_rate": 0.0002, "epoch": 1.9607843137254903, "step": 600}, {"loss": 1.098, "grad_norm": 0.3169507086277008, "learning_rate": 0.0002, "epoch": 1.9934640522875817, "step": 610}, {"eval_loss": 1.1845070123672485, "eval_runtime": 46.2811, "eval_samples_per_second": 9.421, "eval_steps_per_second": 1.188, "epoch": 2.0, "step": 612}, {"loss": 0.9618, "grad_norm": 0.8920142650604248, "learning_rate": 0.0002, "epoch": 2.026143790849673, "step": 620}, {"loss": 0.9784, "grad_norm": 0.4814859628677368, "learning_rate": 0.0002, "epoch": 2.0588235294117645, "step": 630}, {"loss": 0.8464, "grad_norm": 0.4251559376716614, "learning_rate": 0.0002, "epoch": 2.0915032679738563, "step": 640}, {"loss": 0.932, "grad_norm": 0.5295765399932861, "learning_rate": 0.0002, "epoch": 2.1241830065359477, "step": 650}, {"loss": 0.9603, "grad_norm": 0.45016610622406006, "learning_rate": 0.0002, "epoch": 2.156862745098039, "step": 660}, {"loss": 0.8738, "grad_norm": 0.5870586633682251, "learning_rate": 0.0002, "epoch": 2.189542483660131, "step": 670}, {"loss": 0.9483, "grad_norm": 0.5174715518951416, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 680}, {"loss": 0.9551, "grad_norm": 0.5252485275268555, "learning_rate": 0.0002, "epoch": 2.2549019607843137, "step": 690}, {"loss": 0.9253, "grad_norm": 0.5158312320709229, "learning_rate": 0.0002, "epoch": 2.287581699346405, "step": 700}, {"loss": 0.9278, "grad_norm": 0.4824209213256836, "learning_rate": 0.0002, "epoch": 2.3202614379084965, "step": 710}, {"loss": 0.8804, "grad_norm": 0.6335175037384033, "learning_rate": 0.0002, "epoch": 2.3529411764705883, "step": 720}, {"loss": 0.9685, "grad_norm": 0.5240563154220581, "learning_rate": 0.0002, "epoch": 2.3856209150326797, "step": 730}, {"loss": 0.8794, "grad_norm": 0.5172886252403259, "learning_rate": 0.0002, "epoch": 2.418300653594771, "step": 740}, {"loss": 0.8158, "grad_norm": 0.48972561955451965, "learning_rate": 0.0002, "epoch": 2.450980392156863, "step": 750}, {"loss": 0.8766, "grad_norm": 0.5295189023017883, "learning_rate": 0.0002, "epoch": 2.4836601307189543, "step": 760}, {"loss": 0.8695, "grad_norm": 0.5487208962440491, "learning_rate": 0.0002, "epoch": 2.5163398692810457, "step": 770}, {"loss": 1.0109, "grad_norm": 0.5375093221664429, "learning_rate": 0.0002, "epoch": 2.549019607843137, "step": 780}, {"loss": 0.9244, "grad_norm": 0.5424453020095825, "learning_rate": 0.0002, "epoch": 2.581699346405229, "step": 790}, {"loss": 1.0424, "grad_norm": 0.6029134392738342, "learning_rate": 0.0002, "epoch": 2.6143790849673203, "step": 800}, {"loss": 0.8688, "grad_norm": 0.6584921479225159, "learning_rate": 0.0002, "epoch": 2.6470588235294117, "step": 810}, {"loss": 0.7796, "grad_norm": 0.5735557675361633, "learning_rate": 0.0002, "epoch": 2.6797385620915035, "step": 820}, {"loss": 0.8834, "grad_norm": 0.5216763019561768, "learning_rate": 0.0002, "epoch": 2.712418300653595, "step": 830}, {"loss": 0.8946, "grad_norm": 0.5455219149589539, "learning_rate": 0.0002, "epoch": 2.7450980392156863, "step": 840}, {"loss": 0.8037, "grad_norm": 0.5139284729957581, "learning_rate": 0.0002, "epoch": 2.7777777777777777, "step": 850}, {"loss": 0.988, "grad_norm": 0.5096403360366821, "learning_rate": 0.0002, "epoch": 2.810457516339869, "step": 860}, {"loss": 0.9169, "grad_norm": 0.6337038278579712, "learning_rate": 0.0002, "epoch": 2.843137254901961, "step": 870}, {"loss": 0.8938, "grad_norm": 0.47218772768974304, "learning_rate": 0.0002, "epoch": 2.8758169934640523, "step": 880}, {"loss": 0.8554, "grad_norm": 0.4640636742115021, "learning_rate": 0.0002, "epoch": 2.9084967320261437, "step": 890}, {"loss": 0.8625, "grad_norm": 0.4199628531932831, "learning_rate": 0.0002, "epoch": 2.9411764705882355, "step": 900}, {"loss": 0.8104, "grad_norm": 0.5067117214202881, "learning_rate": 0.0002, "epoch": 2.973856209150327, "step": 910}, {"eval_loss": 1.2291251420974731, "eval_runtime": 46.2557, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 3.0, "step": 918}, {"loss": 0.8157, "grad_norm": 0.8342176079750061, "learning_rate": 0.0002, "epoch": 3.0065359477124183, "step": 920}, {"loss": 0.6855, "grad_norm": 0.7695813775062561, "learning_rate": 0.0002, "epoch": 3.0392156862745097, "step": 930}, {"loss": 0.6173, "grad_norm": 0.6819486618041992, "learning_rate": 0.0002, "epoch": 3.0718954248366015, "step": 940}, {"loss": 0.6495, "grad_norm": 0.7568879723548889, "learning_rate": 0.0002, "epoch": 3.104575163398693, "step": 950}, {"loss": 0.7905, "grad_norm": 0.6760695576667786, "learning_rate": 0.0002, "epoch": 3.1372549019607843, "step": 960}, {"loss": 0.6405, "grad_norm": 0.6359127759933472, "learning_rate": 0.0002, "epoch": 3.1699346405228757, "step": 970}, {"loss": 0.7172, "grad_norm": 0.8414971828460693, "learning_rate": 0.0002, "epoch": 3.2026143790849675, "step": 980}, {"loss": 0.7865, "grad_norm": 0.68381667137146, "learning_rate": 0.0002, "epoch": 3.235294117647059, "step": 990}, {"loss": 0.6651, "grad_norm": 0.6852193474769592, "learning_rate": 0.0002, "epoch": 3.2679738562091503, "step": 1000}, {"loss": 0.6571, "grad_norm": 0.8184967041015625, "learning_rate": 0.0002, "epoch": 3.3006535947712417, "step": 1010}, {"loss": 0.7036, "grad_norm": 1.047290563583374, "learning_rate": 0.0002, "epoch": 3.3333333333333335, "step": 1020}, {"loss": 0.7215, "grad_norm": 0.8291178345680237, "learning_rate": 0.0002, "epoch": 3.366013071895425, "step": 1030}, {"loss": 0.6243, "grad_norm": 0.6668022871017456, "learning_rate": 0.0002, "epoch": 3.3986928104575163, "step": 1040}, {"loss": 0.7459, "grad_norm": 0.6354008316993713, "learning_rate": 0.0002, "epoch": 3.431372549019608, "step": 1050}, {"loss": 0.6826, "grad_norm": 1.2028366327285767, "learning_rate": 0.0002, "epoch": 3.4640522875816995, "step": 1060}, {"loss": 0.5913, "grad_norm": 0.717367947101593, "learning_rate": 0.0002, "epoch": 3.496732026143791, "step": 1070}, {"loss": 0.6903, "grad_norm": 0.542179524898529, "learning_rate": 0.0002, "epoch": 3.5294117647058822, "step": 1080}, {"loss": 0.7673, "grad_norm": 0.845981776714325, "learning_rate": 0.0002, "epoch": 3.5620915032679736, "step": 1090}, {"loss": 0.7089, "grad_norm": 0.7381046414375305, "learning_rate": 0.0002, "epoch": 3.5947712418300655, "step": 1100}, {"loss": 0.6705, "grad_norm": 0.6563456058502197, "learning_rate": 0.0002, "epoch": 3.627450980392157, "step": 1110}, {"loss": 0.7767, "grad_norm": 0.7130876779556274, "learning_rate": 0.0002, "epoch": 3.6601307189542482, "step": 1120}, {"loss": 0.7164, "grad_norm": 0.800032913684845, "learning_rate": 0.0002, "epoch": 3.69281045751634, "step": 1130}, {"loss": 0.7272, "grad_norm": 0.980328381061554, "learning_rate": 0.0002, "epoch": 3.7254901960784315, "step": 1140}, {"loss": 0.7672, "grad_norm": 0.8542261123657227, "learning_rate": 0.0002, "epoch": 3.758169934640523, "step": 1150}, {"loss": 0.679, "grad_norm": 0.6302552819252014, "learning_rate": 0.0002, "epoch": 3.7908496732026142, "step": 1160}, {"loss": 0.7457, "grad_norm": 0.515398383140564, "learning_rate": 0.0002, "epoch": 3.8235294117647056, "step": 1170}, {"loss": 0.693, "grad_norm": 1.2427130937576294, "learning_rate": 0.0002, "epoch": 3.8562091503267975, "step": 1180}, {"loss": 0.7182, "grad_norm": 0.8206831216812134, "learning_rate": 0.0002, "epoch": 3.888888888888889, "step": 1190}, {"loss": 0.7519, "grad_norm": 0.7633249163627625, "learning_rate": 0.0002, "epoch": 3.9215686274509802, "step": 1200}, {"loss": 0.7082, "grad_norm": 0.8034512400627136, "learning_rate": 0.0002, "epoch": 3.954248366013072, "step": 1210}, {"loss": 0.6834, "grad_norm": 0.7667182087898254, "learning_rate": 0.0002, "epoch": 3.9869281045751634, "step": 1220}, {"eval_loss": 1.3456707000732422, "eval_runtime": 46.2562, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 4.0, "step": 1224}, {"loss": 0.582, "grad_norm": 0.7724746465682983, "learning_rate": 0.0002, "epoch": 4.019607843137255, "step": 1230}, {"loss": 0.4759, "grad_norm": 1.166916847229004, "learning_rate": 0.0002, "epoch": 4.052287581699346, "step": 1240}, {"loss": 0.4995, "grad_norm": 0.7234508991241455, "learning_rate": 0.0002, "epoch": 4.084967320261438, "step": 1250}, {"loss": 0.4863, "grad_norm": 1.1418060064315796, "learning_rate": 0.0002, "epoch": 4.117647058823529, "step": 1260}, {"loss": 0.5425, "grad_norm": 0.9603922367095947, "learning_rate": 0.0002, "epoch": 4.150326797385621, "step": 1270}, {"loss": 0.4892, "grad_norm": 0.8976530432701111, "learning_rate": 0.0002, "epoch": 4.183006535947713, "step": 1280}, {"loss": 0.473, "grad_norm": 0.6855078339576721, "learning_rate": 0.0002, "epoch": 4.215686274509804, "step": 1290}, {"loss": 0.4416, "grad_norm": 1.2676647901535034, "learning_rate": 0.0002, "epoch": 4.248366013071895, "step": 1300}, {"loss": 0.5071, "grad_norm": 1.104057788848877, "learning_rate": 0.0002, "epoch": 4.281045751633987, "step": 1310}, {"loss": 0.5168, "grad_norm": 1.7076562643051147, "learning_rate": 0.0002, "epoch": 4.313725490196078, "step": 1320}, {"loss": 0.4655, "grad_norm": 1.2308520078659058, "learning_rate": 0.0002, "epoch": 4.34640522875817, "step": 1330}, {"loss": 0.5322, "grad_norm": 1.2652729749679565, "learning_rate": 0.0002, "epoch": 4.379084967320262, "step": 1340}, {"loss": 0.5262, "grad_norm": 1.054958701133728, "learning_rate": 0.0002, "epoch": 4.411764705882353, "step": 1350}, {"loss": 0.4747, "grad_norm": 1.0130749940872192, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 1360}, {"loss": 0.4887, "grad_norm": 1.0517818927764893, "learning_rate": 0.0002, "epoch": 4.477124183006536, "step": 1370}, {"loss": 0.4906, "grad_norm": 0.8593037128448486, "learning_rate": 0.0002, "epoch": 4.509803921568627, "step": 1380}, {"loss": 0.5049, "grad_norm": 1.0248081684112549, "learning_rate": 0.0002, "epoch": 4.542483660130719, "step": 1390}, {"loss": 0.472, "grad_norm": 0.8999413847923279, "learning_rate": 0.0002, "epoch": 4.57516339869281, "step": 1400}, {"loss": 0.5102, "grad_norm": 0.9106912612915039, "learning_rate": 0.0002, "epoch": 4.607843137254902, "step": 1410}, {"loss": 0.5203, "grad_norm": 1.2736181020736694, "learning_rate": 0.0002, "epoch": 4.640522875816993, "step": 1420}, {"loss": 0.5101, "grad_norm": 0.9311690926551819, "learning_rate": 0.0002, "epoch": 4.673202614379085, "step": 1430}, {"loss": 0.5648, "grad_norm": 1.0455045700073242, "learning_rate": 0.0002, "epoch": 4.705882352941177, "step": 1440}, {"loss": 0.5004, "grad_norm": 1.0190727710723877, "learning_rate": 0.0002, "epoch": 4.738562091503268, "step": 1450}, {"loss": 0.5506, "grad_norm": 1.333198070526123, "learning_rate": 0.0002, "epoch": 4.771241830065359, "step": 1460}, {"loss": 0.5846, "grad_norm": 0.8808416724205017, "learning_rate": 0.0002, "epoch": 4.803921568627451, "step": 1470}, {"loss": 0.4671, "grad_norm": 0.8896227478981018, "learning_rate": 0.0002, "epoch": 4.836601307189542, "step": 1480}, {"loss": 0.4732, "grad_norm": 1.212323784828186, "learning_rate": 0.0002, "epoch": 4.8692810457516345, "step": 1490}, {"loss": 0.5263, "grad_norm": 1.0490120649337769, "learning_rate": 0.0002, "epoch": 4.901960784313726, "step": 1500}, {"loss": 0.5815, "grad_norm": 0.8946618437767029, "learning_rate": 0.0002, "epoch": 4.934640522875817, "step": 1510}, {"loss": 0.5369, "grad_norm": 1.0609275102615356, "learning_rate": 0.0002, "epoch": 4.967320261437909, "step": 1520}, {"loss": 0.5348, "grad_norm": 0.8885099291801453, "learning_rate": 0.0002, "epoch": 5.0, "step": 1530}, {"eval_loss": 1.5771757364273071, "eval_runtime": 46.2667, "eval_samples_per_second": 9.424, "eval_steps_per_second": 1.189, "epoch": 5.0, "step": 1530}, {"loss": 0.3176, "grad_norm": 1.401705026626587, "learning_rate": 0.0002, "epoch": 5.032679738562091, "step": 1540}, {"loss": 0.3346, "grad_norm": 0.8365539908409119, "learning_rate": 0.0002, "epoch": 5.065359477124183, "step": 1550}, {"loss": 0.3605, "grad_norm": 1.3188321590423584, "learning_rate": 0.0002, "epoch": 5.098039215686274, "step": 1560}, {"loss": 0.326, "grad_norm": 0.9819526076316833, "learning_rate": 0.0002, "epoch": 5.130718954248366, "step": 1570}, {"loss": 0.3575, "grad_norm": 1.13265061378479, "learning_rate": 0.0002, "epoch": 5.163398692810458, "step": 1580}, {"loss": 0.3418, "grad_norm": 1.478152871131897, "learning_rate": 0.0002, "epoch": 5.196078431372549, "step": 1590}, {"loss": 0.3388, "grad_norm": 1.4188750982284546, "learning_rate": 0.0002, "epoch": 5.228758169934641, "step": 1600}, {"loss": 0.3524, "grad_norm": 1.2499338388442993, "learning_rate": 0.0002, "epoch": 5.261437908496732, "step": 1610}, {"loss": 0.423, "grad_norm": 1.7885085344314575, "learning_rate": 0.0002, "epoch": 5.294117647058823, "step": 1620}, {"loss": 0.3237, "grad_norm": 1.2614946365356445, "learning_rate": 0.0002, "epoch": 5.326797385620915, "step": 1630}, {"loss": 0.3511, "grad_norm": 1.28338623046875, "learning_rate": 0.0002, "epoch": 5.359477124183006, "step": 1640}, {"loss": 0.3112, "grad_norm": 1.1973257064819336, "learning_rate": 0.0002, "epoch": 5.392156862745098, "step": 1650}, {"loss": 0.3645, "grad_norm": 1.1356301307678223, "learning_rate": 0.0002, "epoch": 5.42483660130719, "step": 1660}, {"loss": 0.307, "grad_norm": 0.9048901200294495, "learning_rate": 0.0002, "epoch": 5.457516339869281, "step": 1670}, {"loss": 0.3828, "grad_norm": 1.5352122783660889, "learning_rate": 0.0002, "epoch": 5.490196078431373, "step": 1680}, {"loss": 0.3826, "grad_norm": 0.9096335172653198, "learning_rate": 0.0002, "epoch": 5.522875816993464, "step": 1690}, {"loss": 0.3686, "grad_norm": 1.1903661489486694, "learning_rate": 0.0002, "epoch": 5.555555555555555, "step": 1700}, {"loss": 0.325, "grad_norm": 0.9234451651573181, "learning_rate": 0.0002, "epoch": 5.588235294117647, "step": 1710}, {"loss": 0.3451, "grad_norm": 1.4554102420806885, "learning_rate": 0.0002, "epoch": 5.620915032679738, "step": 1720}, {"loss": 0.3488, "grad_norm": 1.1044343709945679, "learning_rate": 0.0002, "epoch": 5.65359477124183, "step": 1730}, {"loss": 0.3673, "grad_norm": 1.2219593524932861, "learning_rate": 0.0002, "epoch": 5.686274509803922, "step": 1740}, {"loss": 0.3517, "grad_norm": 0.901652455329895, "learning_rate": 0.0002, "epoch": 5.718954248366013, "step": 1750}, {"loss": 0.4082, "grad_norm": 1.3334792852401733, "learning_rate": 0.0002, "epoch": 5.751633986928105, "step": 1760}, {"loss": 0.4386, "grad_norm": 1.5595488548278809, "learning_rate": 0.0002, "epoch": 5.784313725490196, "step": 1770}, {"loss": 0.3217, "grad_norm": 1.3892982006072998, "learning_rate": 0.0002, "epoch": 5.816993464052287, "step": 1780}, {"loss": 0.3919, "grad_norm": 1.0813168287277222, "learning_rate": 0.0002, "epoch": 5.849673202614379, "step": 1790}, {"loss": 0.3697, "grad_norm": 1.145320177078247, "learning_rate": 0.0002, "epoch": 5.882352941176471, "step": 1800}, {"loss": 0.3903, "grad_norm": 1.0249533653259277, "learning_rate": 0.0002, "epoch": 5.915032679738562, "step": 1810}, {"loss": 0.3481, "grad_norm": 1.0013737678527832, "learning_rate": 0.0002, "epoch": 5.947712418300654, "step": 1820}, {"loss": 0.4278, "grad_norm": 1.212314248085022, "learning_rate": 0.0002, "epoch": 5.980392156862745, "step": 1830}]}
+{"epoch": 7.0, "step": 2142, "epoch_duration": 455.7560234069824, "total_accumulated_duration": 3192.7409133911133, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.224609375}, "avg_memory_reserved": {"GPU_0": 28746.0}, "peak_memory_reserved": {"GPU_0": 28746.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.3561, "grad_norm": 0.631856381893158, "learning_rate": 0.0002, "epoch": 0.032679738562091505, "step": 10}, {"loss": 1.8141, "grad_norm": 0.5065668821334839, "learning_rate": 0.0002, "epoch": 0.06535947712418301, "step": 20}, {"loss": 1.4952, "grad_norm": 0.6978895664215088, "learning_rate": 0.0002, "epoch": 0.09803921568627451, "step": 30}, {"loss": 1.4829, "grad_norm": 0.6619144082069397, "learning_rate": 0.0002, "epoch": 0.13071895424836602, "step": 40}, {"loss": 1.3038, "grad_norm": 0.6153793931007385, "learning_rate": 0.0002, "epoch": 0.16339869281045752, "step": 50}, {"loss": 1.1429, "grad_norm": 0.4703301787376404, "learning_rate": 0.0002, "epoch": 0.19607843137254902, "step": 60}, {"loss": 1.2828, "grad_norm": 1.1672580242156982, "learning_rate": 0.0002, "epoch": 0.22875816993464052, "step": 70}, {"loss": 1.0985, "grad_norm": 0.3455565273761749, "learning_rate": 0.0002, "epoch": 0.26143790849673204, "step": 80}, {"loss": 1.1359, "grad_norm": 0.36216291785240173, "learning_rate": 0.0002, "epoch": 0.29411764705882354, "step": 90}, {"loss": 1.2544, "grad_norm": 0.4545166492462158, "learning_rate": 0.0002, "epoch": 0.32679738562091504, "step": 100}, {"loss": 1.2287, "grad_norm": 0.3612092435359955, "learning_rate": 0.0002, "epoch": 0.35947712418300654, "step": 110}, {"loss": 1.1868, "grad_norm": 0.5080830454826355, "learning_rate": 0.0002, "epoch": 0.39215686274509803, "step": 120}, {"loss": 1.1902, "grad_norm": 0.3268195390701294, "learning_rate": 0.0002, "epoch": 0.42483660130718953, "step": 130}, {"loss": 1.247, "grad_norm": 0.33971714973449707, "learning_rate": 0.0002, "epoch": 0.45751633986928103, "step": 140}, {"loss": 1.1844, "grad_norm": 0.4036043882369995, "learning_rate": 0.0002, "epoch": 0.49019607843137253, "step": 150}, {"loss": 1.1624, "grad_norm": 0.35938864946365356, "learning_rate": 0.0002, "epoch": 0.5228758169934641, "step": 160}, {"loss": 1.164, "grad_norm": 0.28880223631858826, "learning_rate": 0.0002, "epoch": 0.5555555555555556, "step": 170}, {"loss": 1.3521, "grad_norm": 0.3436269462108612, "learning_rate": 0.0002, "epoch": 0.5882352941176471, "step": 180}, {"loss": 1.2456, "grad_norm": 0.41923725605010986, "learning_rate": 0.0002, "epoch": 0.6209150326797386, "step": 190}, {"loss": 1.2226, "grad_norm": 0.25119203329086304, "learning_rate": 0.0002, "epoch": 0.6535947712418301, "step": 200}, {"loss": 1.1568, "grad_norm": 0.5870180726051331, "learning_rate": 0.0002, "epoch": 0.6862745098039216, "step": 210}, {"loss": 1.064, "grad_norm": 0.2831224203109741, "learning_rate": 0.0002, "epoch": 0.7189542483660131, "step": 220}, {"loss": 1.2469, "grad_norm": 0.3192005753517151, "learning_rate": 0.0002, "epoch": 0.7516339869281046, "step": 230}, {"loss": 1.1613, "grad_norm": 0.2998219430446625, "learning_rate": 0.0002, "epoch": 0.7843137254901961, "step": 240}, {"loss": 1.205, "grad_norm": 0.32855790853500366, "learning_rate": 0.0002, "epoch": 0.8169934640522876, "step": 250}, {"loss": 1.1631, "grad_norm": 0.3403124213218689, "learning_rate": 0.0002, "epoch": 0.8496732026143791, "step": 260}, {"loss": 1.1646, "grad_norm": 0.277401328086853, "learning_rate": 0.0002, "epoch": 0.8823529411764706, "step": 270}, {"loss": 1.084, "grad_norm": 0.2975269556045532, "learning_rate": 0.0002, "epoch": 0.9150326797385621, "step": 280}, {"loss": 1.2039, "grad_norm": 1.7909578084945679, "learning_rate": 0.0002, "epoch": 0.9477124183006536, "step": 290}, {"loss": 1.1226, "grad_norm": 0.2917245328426361, "learning_rate": 0.0002, "epoch": 0.9803921568627451, "step": 300}, {"eval_loss": 1.1937541961669922, "eval_runtime": 46.2571, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 1.0, "step": 306}, {"loss": 1.2011, "grad_norm": 0.26494982838630676, "learning_rate": 0.0002, "epoch": 1.0130718954248366, "step": 310}, {"loss": 1.0565, "grad_norm": 0.6289355754852295, "learning_rate": 0.0002, "epoch": 1.0457516339869282, "step": 320}, {"loss": 1.1619, "grad_norm": 0.26784011721611023, "learning_rate": 0.0002, "epoch": 1.0784313725490196, "step": 330}, {"loss": 1.1151, "grad_norm": 0.3392215967178345, "learning_rate": 0.0002, "epoch": 1.1111111111111112, "step": 340}, {"loss": 1.0752, "grad_norm": 0.40005937218666077, "learning_rate": 0.0002, "epoch": 1.1437908496732025, "step": 350}, {"loss": 1.0408, "grad_norm": 0.3590582013130188, "learning_rate": 0.0002, "epoch": 1.1764705882352942, "step": 360}, {"loss": 1.0836, "grad_norm": 0.3995305895805359, "learning_rate": 0.0002, "epoch": 1.2091503267973855, "step": 370}, {"loss": 1.0992, "grad_norm": 0.2950291633605957, "learning_rate": 0.0002, "epoch": 1.2418300653594772, "step": 380}, {"loss": 1.1152, "grad_norm": 0.32035166025161743, "learning_rate": 0.0002, "epoch": 1.2745098039215685, "step": 390}, {"loss": 1.1467, "grad_norm": 0.410366415977478, "learning_rate": 0.0002, "epoch": 1.3071895424836601, "step": 400}, {"loss": 0.9985, "grad_norm": 0.3106379508972168, "learning_rate": 0.0002, "epoch": 1.3398692810457518, "step": 410}, {"loss": 0.9789, "grad_norm": 0.38580670952796936, "learning_rate": 0.0002, "epoch": 1.3725490196078431, "step": 420}, {"loss": 1.0931, "grad_norm": 0.34411361813545227, "learning_rate": 0.0002, "epoch": 1.4052287581699345, "step": 430}, {"loss": 1.1685, "grad_norm": 0.44206851720809937, "learning_rate": 0.0002, "epoch": 1.4379084967320261, "step": 440}, {"loss": 1.0347, "grad_norm": 0.3492952585220337, "learning_rate": 0.0002, "epoch": 1.4705882352941178, "step": 450}, {"loss": 1.0534, "grad_norm": 0.376423716545105, "learning_rate": 0.0002, "epoch": 1.5032679738562091, "step": 460}, {"loss": 1.1162, "grad_norm": 0.359757661819458, "learning_rate": 0.0002, "epoch": 1.5359477124183005, "step": 470}, {"loss": 0.9586, "grad_norm": 0.3385067880153656, "learning_rate": 0.0002, "epoch": 1.5686274509803921, "step": 480}, {"loss": 1.0807, "grad_norm": 0.4943889379501343, "learning_rate": 0.0002, "epoch": 1.6013071895424837, "step": 490}, {"loss": 1.0796, "grad_norm": 0.4203241169452667, "learning_rate": 0.0002, "epoch": 1.6339869281045751, "step": 500}, {"loss": 1.1059, "grad_norm": 0.3093789219856262, "learning_rate": 0.0002, "epoch": 1.6666666666666665, "step": 510}, {"loss": 1.0323, "grad_norm": 0.3653067350387573, "learning_rate": 0.0002, "epoch": 1.6993464052287581, "step": 520}, {"loss": 1.0885, "grad_norm": 0.36761337518692017, "learning_rate": 0.0002, "epoch": 1.7320261437908497, "step": 530}, {"loss": 1.1698, "grad_norm": 0.5040399432182312, "learning_rate": 0.0002, "epoch": 1.7647058823529411, "step": 540}, {"loss": 1.0105, "grad_norm": 0.3818035125732422, "learning_rate": 0.0002, "epoch": 1.7973856209150327, "step": 550}, {"loss": 0.94, "grad_norm": 0.4021618664264679, "learning_rate": 0.0002, "epoch": 1.8300653594771243, "step": 560}, {"loss": 1.0358, "grad_norm": 0.3986459970474243, "learning_rate": 0.0002, "epoch": 1.8627450980392157, "step": 570}, {"loss": 1.003, "grad_norm": 0.48416733741760254, "learning_rate": 0.0002, "epoch": 1.8954248366013071, "step": 580}, {"loss": 1.1146, "grad_norm": 0.36853986978530884, "learning_rate": 0.0002, "epoch": 1.9281045751633987, "step": 590}, {"loss": 1.0689, "grad_norm": 0.383022665977478, "learning_rate": 0.0002, "epoch": 1.9607843137254903, "step": 600}, {"loss": 1.098, "grad_norm": 0.3169507086277008, "learning_rate": 0.0002, "epoch": 1.9934640522875817, "step": 610}, {"eval_loss": 1.1845070123672485, "eval_runtime": 46.2811, "eval_samples_per_second": 9.421, "eval_steps_per_second": 1.188, "epoch": 2.0, "step": 612}, {"loss": 0.9618, "grad_norm": 0.8920142650604248, "learning_rate": 0.0002, "epoch": 2.026143790849673, "step": 620}, {"loss": 0.9784, "grad_norm": 0.4814859628677368, "learning_rate": 0.0002, "epoch": 2.0588235294117645, "step": 630}, {"loss": 0.8464, "grad_norm": 0.4251559376716614, "learning_rate": 0.0002, "epoch": 2.0915032679738563, "step": 640}, {"loss": 0.932, "grad_norm": 0.5295765399932861, "learning_rate": 0.0002, "epoch": 2.1241830065359477, "step": 650}, {"loss": 0.9603, "grad_norm": 0.45016610622406006, "learning_rate": 0.0002, "epoch": 2.156862745098039, "step": 660}, {"loss": 0.8738, "grad_norm": 0.5870586633682251, "learning_rate": 0.0002, "epoch": 2.189542483660131, "step": 670}, {"loss": 0.9483, "grad_norm": 0.5174715518951416, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 680}, {"loss": 0.9551, "grad_norm": 0.5252485275268555, "learning_rate": 0.0002, "epoch": 2.2549019607843137, "step": 690}, {"loss": 0.9253, "grad_norm": 0.5158312320709229, "learning_rate": 0.0002, "epoch": 2.287581699346405, "step": 700}, {"loss": 0.9278, "grad_norm": 0.4824209213256836, "learning_rate": 0.0002, "epoch": 2.3202614379084965, "step": 710}, {"loss": 0.8804, "grad_norm": 0.6335175037384033, "learning_rate": 0.0002, "epoch": 2.3529411764705883, "step": 720}, {"loss": 0.9685, "grad_norm": 0.5240563154220581, "learning_rate": 0.0002, "epoch": 2.3856209150326797, "step": 730}, {"loss": 0.8794, "grad_norm": 0.5172886252403259, "learning_rate": 0.0002, "epoch": 2.418300653594771, "step": 740}, {"loss": 0.8158, "grad_norm": 0.48972561955451965, "learning_rate": 0.0002, "epoch": 2.450980392156863, "step": 750}, {"loss": 0.8766, "grad_norm": 0.5295189023017883, "learning_rate": 0.0002, "epoch": 2.4836601307189543, "step": 760}, {"loss": 0.8695, "grad_norm": 0.5487208962440491, "learning_rate": 0.0002, "epoch": 2.5163398692810457, "step": 770}, {"loss": 1.0109, "grad_norm": 0.5375093221664429, "learning_rate": 0.0002, "epoch": 2.549019607843137, "step": 780}, {"loss": 0.9244, "grad_norm": 0.5424453020095825, "learning_rate": 0.0002, "epoch": 2.581699346405229, "step": 790}, {"loss": 1.0424, "grad_norm": 0.6029134392738342, "learning_rate": 0.0002, "epoch": 2.6143790849673203, "step": 800}, {"loss": 0.8688, "grad_norm": 0.6584921479225159, "learning_rate": 0.0002, "epoch": 2.6470588235294117, "step": 810}, {"loss": 0.7796, "grad_norm": 0.5735557675361633, "learning_rate": 0.0002, "epoch": 2.6797385620915035, "step": 820}, {"loss": 0.8834, "grad_norm": 0.5216763019561768, "learning_rate": 0.0002, "epoch": 2.712418300653595, "step": 830}, {"loss": 0.8946, "grad_norm": 0.5455219149589539, "learning_rate": 0.0002, "epoch": 2.7450980392156863, "step": 840}, {"loss": 0.8037, "grad_norm": 0.5139284729957581, "learning_rate": 0.0002, "epoch": 2.7777777777777777, "step": 850}, {"loss": 0.988, "grad_norm": 0.5096403360366821, "learning_rate": 0.0002, "epoch": 2.810457516339869, "step": 860}, {"loss": 0.9169, "grad_norm": 0.6337038278579712, "learning_rate": 0.0002, "epoch": 2.843137254901961, "step": 870}, {"loss": 0.8938, "grad_norm": 0.47218772768974304, "learning_rate": 0.0002, "epoch": 2.8758169934640523, "step": 880}, {"loss": 0.8554, "grad_norm": 0.4640636742115021, "learning_rate": 0.0002, "epoch": 2.9084967320261437, "step": 890}, {"loss": 0.8625, "grad_norm": 0.4199628531932831, "learning_rate": 0.0002, "epoch": 2.9411764705882355, "step": 900}, {"loss": 0.8104, "grad_norm": 0.5067117214202881, "learning_rate": 0.0002, "epoch": 2.973856209150327, "step": 910}, {"eval_loss": 1.2291251420974731, "eval_runtime": 46.2557, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 3.0, "step": 918}, {"loss": 0.8157, "grad_norm": 0.8342176079750061, "learning_rate": 0.0002, "epoch": 3.0065359477124183, "step": 920}, {"loss": 0.6855, "grad_norm": 0.7695813775062561, "learning_rate": 0.0002, "epoch": 3.0392156862745097, "step": 930}, {"loss": 0.6173, "grad_norm": 0.6819486618041992, "learning_rate": 0.0002, "epoch": 3.0718954248366015, "step": 940}, {"loss": 0.6495, "grad_norm": 0.7568879723548889, "learning_rate": 0.0002, "epoch": 3.104575163398693, "step": 950}, {"loss": 0.7905, "grad_norm": 0.6760695576667786, "learning_rate": 0.0002, "epoch": 3.1372549019607843, "step": 960}, {"loss": 0.6405, "grad_norm": 0.6359127759933472, "learning_rate": 0.0002, "epoch": 3.1699346405228757, "step": 970}, {"loss": 0.7172, "grad_norm": 0.8414971828460693, "learning_rate": 0.0002, "epoch": 3.2026143790849675, "step": 980}, {"loss": 0.7865, "grad_norm": 0.68381667137146, "learning_rate": 0.0002, "epoch": 3.235294117647059, "step": 990}, {"loss": 0.6651, "grad_norm": 0.6852193474769592, "learning_rate": 0.0002, "epoch": 3.2679738562091503, "step": 1000}, {"loss": 0.6571, "grad_norm": 0.8184967041015625, "learning_rate": 0.0002, "epoch": 3.3006535947712417, "step": 1010}, {"loss": 0.7036, "grad_norm": 1.047290563583374, "learning_rate": 0.0002, "epoch": 3.3333333333333335, "step": 1020}, {"loss": 0.7215, "grad_norm": 0.8291178345680237, "learning_rate": 0.0002, "epoch": 3.366013071895425, "step": 1030}, {"loss": 0.6243, "grad_norm": 0.6668022871017456, "learning_rate": 0.0002, "epoch": 3.3986928104575163, "step": 1040}, {"loss": 0.7459, "grad_norm": 0.6354008316993713, "learning_rate": 0.0002, "epoch": 3.431372549019608, "step": 1050}, {"loss": 0.6826, "grad_norm": 1.2028366327285767, "learning_rate": 0.0002, "epoch": 3.4640522875816995, "step": 1060}, {"loss": 0.5913, "grad_norm": 0.717367947101593, "learning_rate": 0.0002, "epoch": 3.496732026143791, "step": 1070}, {"loss": 0.6903, "grad_norm": 0.542179524898529, "learning_rate": 0.0002, "epoch": 3.5294117647058822, "step": 1080}, {"loss": 0.7673, "grad_norm": 0.845981776714325, "learning_rate": 0.0002, "epoch": 3.5620915032679736, "step": 1090}, {"loss": 0.7089, "grad_norm": 0.7381046414375305, "learning_rate": 0.0002, "epoch": 3.5947712418300655, "step": 1100}, {"loss": 0.6705, "grad_norm": 0.6563456058502197, "learning_rate": 0.0002, "epoch": 3.627450980392157, "step": 1110}, {"loss": 0.7767, "grad_norm": 0.7130876779556274, "learning_rate": 0.0002, "epoch": 3.6601307189542482, "step": 1120}, {"loss": 0.7164, "grad_norm": 0.800032913684845, "learning_rate": 0.0002, "epoch": 3.69281045751634, "step": 1130}, {"loss": 0.7272, "grad_norm": 0.980328381061554, "learning_rate": 0.0002, "epoch": 3.7254901960784315, "step": 1140}, {"loss": 0.7672, "grad_norm": 0.8542261123657227, "learning_rate": 0.0002, "epoch": 3.758169934640523, "step": 1150}, {"loss": 0.679, "grad_norm": 0.6302552819252014, "learning_rate": 0.0002, "epoch": 3.7908496732026142, "step": 1160}, {"loss": 0.7457, "grad_norm": 0.515398383140564, "learning_rate": 0.0002, "epoch": 3.8235294117647056, "step": 1170}, {"loss": 0.693, "grad_norm": 1.2427130937576294, "learning_rate": 0.0002, "epoch": 3.8562091503267975, "step": 1180}, {"loss": 0.7182, "grad_norm": 0.8206831216812134, "learning_rate": 0.0002, "epoch": 3.888888888888889, "step": 1190}, {"loss": 0.7519, "grad_norm": 0.7633249163627625, "learning_rate": 0.0002, "epoch": 3.9215686274509802, "step": 1200}, {"loss": 0.7082, "grad_norm": 0.8034512400627136, "learning_rate": 0.0002, "epoch": 3.954248366013072, "step": 1210}, {"loss": 0.6834, "grad_norm": 0.7667182087898254, "learning_rate": 0.0002, "epoch": 3.9869281045751634, "step": 1220}, {"eval_loss": 1.3456707000732422, "eval_runtime": 46.2562, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 4.0, "step": 1224}, {"loss": 0.582, "grad_norm": 0.7724746465682983, "learning_rate": 0.0002, "epoch": 4.019607843137255, "step": 1230}, {"loss": 0.4759, "grad_norm": 1.166916847229004, "learning_rate": 0.0002, "epoch": 4.052287581699346, "step": 1240}, {"loss": 0.4995, "grad_norm": 0.7234508991241455, "learning_rate": 0.0002, "epoch": 4.084967320261438, "step": 1250}, {"loss": 0.4863, "grad_norm": 1.1418060064315796, "learning_rate": 0.0002, "epoch": 4.117647058823529, "step": 1260}, {"loss": 0.5425, "grad_norm": 0.9603922367095947, "learning_rate": 0.0002, "epoch": 4.150326797385621, "step": 1270}, {"loss": 0.4892, "grad_norm": 0.8976530432701111, "learning_rate": 0.0002, "epoch": 4.183006535947713, "step": 1280}, {"loss": 0.473, "grad_norm": 0.6855078339576721, "learning_rate": 0.0002, "epoch": 4.215686274509804, "step": 1290}, {"loss": 0.4416, "grad_norm": 1.2676647901535034, "learning_rate": 0.0002, "epoch": 4.248366013071895, "step": 1300}, {"loss": 0.5071, "grad_norm": 1.104057788848877, "learning_rate": 0.0002, "epoch": 4.281045751633987, "step": 1310}, {"loss": 0.5168, "grad_norm": 1.7076562643051147, "learning_rate": 0.0002, "epoch": 4.313725490196078, "step": 1320}, {"loss": 0.4655, "grad_norm": 1.2308520078659058, "learning_rate": 0.0002, "epoch": 4.34640522875817, "step": 1330}, {"loss": 0.5322, "grad_norm": 1.2652729749679565, "learning_rate": 0.0002, "epoch": 4.379084967320262, "step": 1340}, {"loss": 0.5262, "grad_norm": 1.054958701133728, "learning_rate": 0.0002, "epoch": 4.411764705882353, "step": 1350}, {"loss": 0.4747, "grad_norm": 1.0130749940872192, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 1360}, {"loss": 0.4887, "grad_norm": 1.0517818927764893, "learning_rate": 0.0002, "epoch": 4.477124183006536, "step": 1370}, {"loss": 0.4906, "grad_norm": 0.8593037128448486, "learning_rate": 0.0002, "epoch": 4.509803921568627, "step": 1380}, {"loss": 0.5049, "grad_norm": 1.0248081684112549, "learning_rate": 0.0002, "epoch": 4.542483660130719, "step": 1390}, {"loss": 0.472, "grad_norm": 0.8999413847923279, "learning_rate": 0.0002, "epoch": 4.57516339869281, "step": 1400}, {"loss": 0.5102, "grad_norm": 0.9106912612915039, "learning_rate": 0.0002, "epoch": 4.607843137254902, "step": 1410}, {"loss": 0.5203, "grad_norm": 1.2736181020736694, "learning_rate": 0.0002, "epoch": 4.640522875816993, "step": 1420}, {"loss": 0.5101, "grad_norm": 0.9311690926551819, "learning_rate": 0.0002, "epoch": 4.673202614379085, "step": 1430}, {"loss": 0.5648, "grad_norm": 1.0455045700073242, "learning_rate": 0.0002, "epoch": 4.705882352941177, "step": 1440}, {"loss": 0.5004, "grad_norm": 1.0190727710723877, "learning_rate": 0.0002, "epoch": 4.738562091503268, "step": 1450}, {"loss": 0.5506, "grad_norm": 1.333198070526123, "learning_rate": 0.0002, "epoch": 4.771241830065359, "step": 1460}, {"loss": 0.5846, "grad_norm": 0.8808416724205017, "learning_rate": 0.0002, "epoch": 4.803921568627451, "step": 1470}, {"loss": 0.4671, "grad_norm": 0.8896227478981018, "learning_rate": 0.0002, "epoch": 4.836601307189542, "step": 1480}, {"loss": 0.4732, "grad_norm": 1.212323784828186, "learning_rate": 0.0002, "epoch": 4.8692810457516345, "step": 1490}, {"loss": 0.5263, "grad_norm": 1.0490120649337769, "learning_rate": 0.0002, "epoch": 4.901960784313726, "step": 1500}, {"loss": 0.5815, "grad_norm": 0.8946618437767029, "learning_rate": 0.0002, "epoch": 4.934640522875817, "step": 1510}, {"loss": 0.5369, "grad_norm": 1.0609275102615356, "learning_rate": 0.0002, "epoch": 4.967320261437909, "step": 1520}, {"loss": 0.5348, "grad_norm": 0.8885099291801453, "learning_rate": 0.0002, "epoch": 5.0, "step": 1530}, {"eval_loss": 1.5771757364273071, "eval_runtime": 46.2667, "eval_samples_per_second": 9.424, "eval_steps_per_second": 1.189, "epoch": 5.0, "step": 1530}, {"loss": 0.3176, "grad_norm": 1.401705026626587, "learning_rate": 0.0002, "epoch": 5.032679738562091, "step": 1540}, {"loss": 0.3346, "grad_norm": 0.8365539908409119, "learning_rate": 0.0002, "epoch": 5.065359477124183, "step": 1550}, {"loss": 0.3605, "grad_norm": 1.3188321590423584, "learning_rate": 0.0002, "epoch": 5.098039215686274, "step": 1560}, {"loss": 0.326, "grad_norm": 0.9819526076316833, "learning_rate": 0.0002, "epoch": 5.130718954248366, "step": 1570}, {"loss": 0.3575, "grad_norm": 1.13265061378479, "learning_rate": 0.0002, "epoch": 5.163398692810458, "step": 1580}, {"loss": 0.3418, "grad_norm": 1.478152871131897, "learning_rate": 0.0002, "epoch": 5.196078431372549, "step": 1590}, {"loss": 0.3388, "grad_norm": 1.4188750982284546, "learning_rate": 0.0002, "epoch": 5.228758169934641, "step": 1600}, {"loss": 0.3524, "grad_norm": 1.2499338388442993, "learning_rate": 0.0002, "epoch": 5.261437908496732, "step": 1610}, {"loss": 0.423, "grad_norm": 1.7885085344314575, "learning_rate": 0.0002, "epoch": 5.294117647058823, "step": 1620}, {"loss": 0.3237, "grad_norm": 1.2614946365356445, "learning_rate": 0.0002, "epoch": 5.326797385620915, "step": 1630}, {"loss": 0.3511, "grad_norm": 1.28338623046875, "learning_rate": 0.0002, "epoch": 5.359477124183006, "step": 1640}, {"loss": 0.3112, "grad_norm": 1.1973257064819336, "learning_rate": 0.0002, "epoch": 5.392156862745098, "step": 1650}, {"loss": 0.3645, "grad_norm": 1.1356301307678223, "learning_rate": 0.0002, "epoch": 5.42483660130719, "step": 1660}, {"loss": 0.307, "grad_norm": 0.9048901200294495, "learning_rate": 0.0002, "epoch": 5.457516339869281, "step": 1670}, {"loss": 0.3828, "grad_norm": 1.5352122783660889, "learning_rate": 0.0002, "epoch": 5.490196078431373, "step": 1680}, {"loss": 0.3826, "grad_norm": 0.9096335172653198, "learning_rate": 0.0002, "epoch": 5.522875816993464, "step": 1690}, {"loss": 0.3686, "grad_norm": 1.1903661489486694, "learning_rate": 0.0002, "epoch": 5.555555555555555, "step": 1700}, {"loss": 0.325, "grad_norm": 0.9234451651573181, "learning_rate": 0.0002, "epoch": 5.588235294117647, "step": 1710}, {"loss": 0.3451, "grad_norm": 1.4554102420806885, "learning_rate": 0.0002, "epoch": 5.620915032679738, "step": 1720}, {"loss": 0.3488, "grad_norm": 1.1044343709945679, "learning_rate": 0.0002, "epoch": 5.65359477124183, "step": 1730}, {"loss": 0.3673, "grad_norm": 1.2219593524932861, "learning_rate": 0.0002, "epoch": 5.686274509803922, "step": 1740}, {"loss": 0.3517, "grad_norm": 0.901652455329895, "learning_rate": 0.0002, "epoch": 5.718954248366013, "step": 1750}, {"loss": 0.4082, "grad_norm": 1.3334792852401733, "learning_rate": 0.0002, "epoch": 5.751633986928105, "step": 1760}, {"loss": 0.4386, "grad_norm": 1.5595488548278809, "learning_rate": 0.0002, "epoch": 5.784313725490196, "step": 1770}, {"loss": 0.3217, "grad_norm": 1.3892982006072998, "learning_rate": 0.0002, "epoch": 5.816993464052287, "step": 1780}, {"loss": 0.3919, "grad_norm": 1.0813168287277222, "learning_rate": 0.0002, "epoch": 5.849673202614379, "step": 1790}, {"loss": 0.3697, "grad_norm": 1.145320177078247, "learning_rate": 0.0002, "epoch": 5.882352941176471, "step": 1800}, {"loss": 0.3903, "grad_norm": 1.0249533653259277, "learning_rate": 0.0002, "epoch": 5.915032679738562, "step": 1810}, {"loss": 0.3481, "grad_norm": 1.0013737678527832, "learning_rate": 0.0002, "epoch": 5.947712418300654, "step": 1820}, {"loss": 0.4278, "grad_norm": 1.212314248085022, "learning_rate": 0.0002, "epoch": 5.980392156862745, "step": 1830}, {"eval_loss": 1.7506128549575806, "eval_runtime": 46.2256, "eval_samples_per_second": 9.432, "eval_steps_per_second": 1.19, "epoch": 6.0, "step": 1836}, {"loss": 0.3283, "grad_norm": 0.7339767813682556, "learning_rate": 0.0002, "epoch": 6.0130718954248366, "step": 1840}, {"loss": 0.2304, "grad_norm": 1.1071710586547852, "learning_rate": 0.0002, "epoch": 6.045751633986928, "step": 1850}, {"loss": 0.2436, "grad_norm": 1.2613991498947144, "learning_rate": 0.0002, "epoch": 6.078431372549019, "step": 1860}, {"loss": 0.2403, "grad_norm": 1.053133249282837, "learning_rate": 0.0002, "epoch": 6.111111111111111, "step": 1870}, {"loss": 0.2509, "grad_norm": 1.069568395614624, "learning_rate": 0.0002, "epoch": 6.143790849673203, "step": 1880}, {"loss": 0.2272, "grad_norm": 1.020458698272705, "learning_rate": 0.0002, "epoch": 6.176470588235294, "step": 1890}, {"loss": 0.2408, "grad_norm": 1.2430394887924194, "learning_rate": 0.0002, "epoch": 6.209150326797386, "step": 1900}, {"loss": 0.229, "grad_norm": 1.3475574254989624, "learning_rate": 0.0002, "epoch": 6.241830065359477, "step": 1910}, {"loss": 0.2542, "grad_norm": 0.9094598889350891, "learning_rate": 0.0002, "epoch": 6.2745098039215685, "step": 1920}, {"loss": 0.2009, "grad_norm": 1.255650520324707, "learning_rate": 0.0002, "epoch": 6.30718954248366, "step": 1930}, {"loss": 0.25, "grad_norm": 1.4193930625915527, "learning_rate": 0.0002, "epoch": 6.339869281045751, "step": 1940}, {"loss": 0.293, "grad_norm": 1.4378032684326172, "learning_rate": 0.0002, "epoch": 6.372549019607844, "step": 1950}, {"loss": 0.2685, "grad_norm": 1.2236989736557007, "learning_rate": 0.0002, "epoch": 6.405228758169935, "step": 1960}, {"loss": 0.2608, "grad_norm": 1.0902987718582153, "learning_rate": 0.0002, "epoch": 6.437908496732026, "step": 1970}, {"loss": 0.2267, "grad_norm": 1.1165062189102173, "learning_rate": 0.0002, "epoch": 6.470588235294118, "step": 1980}, {"loss": 0.2246, "grad_norm": 1.3953566551208496, "learning_rate": 0.0002, "epoch": 6.503267973856209, "step": 1990}, {"loss": 0.2834, "grad_norm": 1.5215585231781006, "learning_rate": 0.0002, "epoch": 6.5359477124183005, "step": 2000}, {"loss": 0.2457, "grad_norm": 1.3496609926223755, "learning_rate": 0.0002, "epoch": 6.568627450980392, "step": 2010}, {"loss": 0.2637, "grad_norm": 1.2511820793151855, "learning_rate": 0.0002, "epoch": 6.601307189542483, "step": 2020}, {"loss": 0.2956, "grad_norm": 1.9875848293304443, "learning_rate": 0.0002, "epoch": 6.633986928104575, "step": 2030}, {"loss": 0.2664, "grad_norm": 1.0766608715057373, "learning_rate": 0.0002, "epoch": 6.666666666666667, "step": 2040}, {"loss": 0.2792, "grad_norm": 1.3594712018966675, "learning_rate": 0.0002, "epoch": 6.699346405228758, "step": 2050}, {"loss": 0.3194, "grad_norm": 1.2357292175292969, "learning_rate": 0.0002, "epoch": 6.73202614379085, "step": 2060}, {"loss": 0.2526, "grad_norm": 1.2428375482559204, "learning_rate": 0.0002, "epoch": 6.764705882352941, "step": 2070}, {"loss": 0.2355, "grad_norm": 1.2724156379699707, "learning_rate": 0.0002, "epoch": 6.7973856209150325, "step": 2080}, {"loss": 0.289, "grad_norm": 1.4981396198272705, "learning_rate": 0.0002, "epoch": 6.830065359477124, "step": 2090}, {"loss": 0.2443, "grad_norm": 0.9346088171005249, "learning_rate": 0.0002, "epoch": 6.862745098039216, "step": 2100}, {"loss": 0.262, "grad_norm": 1.3955477476119995, "learning_rate": 0.0002, "epoch": 6.895424836601308, "step": 2110}, {"loss": 0.2981, "grad_norm": 1.492382287979126, "learning_rate": 0.0002, "epoch": 6.928104575163399, "step": 2120}, {"loss": 0.3093, "grad_norm": 1.2755712270736694, "learning_rate": 0.0002, "epoch": 6.96078431372549, "step": 2130}, {"loss": 0.2943, "grad_norm": 1.4600884914398193, "learning_rate": 0.0002, "epoch": 6.993464052287582, "step": 2140}]}
+{"epoch": 8.0, "step": 2448, "epoch_duration": 457.8266222476959, "total_accumulated_duration": 3650.567535638809, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.224609375}, "avg_memory_reserved": {"GPU_0": 28746.0}, "peak_memory_reserved": {"GPU_0": 28746.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-1961-sd-42/checkpoint-612", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.3561, "grad_norm": 0.631856381893158, "learning_rate": 0.0002, "epoch": 0.032679738562091505, "step": 10}, {"loss": 1.8141, "grad_norm": 0.5065668821334839, "learning_rate": 0.0002, "epoch": 0.06535947712418301, "step": 20}, {"loss": 1.4952, "grad_norm": 0.6978895664215088, "learning_rate": 0.0002, "epoch": 0.09803921568627451, "step": 30}, {"loss": 1.4829, "grad_norm": 0.6619144082069397, "learning_rate": 0.0002, "epoch": 0.13071895424836602, "step": 40}, {"loss": 1.3038, "grad_norm": 0.6153793931007385, "learning_rate": 0.0002, "epoch": 0.16339869281045752, "step": 50}, {"loss": 1.1429, "grad_norm": 0.4703301787376404, "learning_rate": 0.0002, "epoch": 0.19607843137254902, "step": 60}, {"loss": 1.2828, "grad_norm": 1.1672580242156982, "learning_rate": 0.0002, "epoch": 0.22875816993464052, "step": 70}, {"loss": 1.0985, "grad_norm": 0.3455565273761749, "learning_rate": 0.0002, "epoch": 0.26143790849673204, "step": 80}, {"loss": 1.1359, "grad_norm": 0.36216291785240173, "learning_rate": 0.0002, "epoch": 0.29411764705882354, "step": 90}, {"loss": 1.2544, "grad_norm": 0.4545166492462158, "learning_rate": 0.0002, "epoch": 0.32679738562091504, "step": 100}, {"loss": 1.2287, "grad_norm": 0.3612092435359955, "learning_rate": 0.0002, "epoch": 0.35947712418300654, "step": 110}, {"loss": 1.1868, "grad_norm": 0.5080830454826355, "learning_rate": 0.0002, "epoch": 0.39215686274509803, "step": 120}, {"loss": 1.1902, "grad_norm": 0.3268195390701294, "learning_rate": 0.0002, "epoch": 0.42483660130718953, "step": 130}, {"loss": 1.247, "grad_norm": 0.33971714973449707, "learning_rate": 0.0002, "epoch": 0.45751633986928103, "step": 140}, {"loss": 1.1844, "grad_norm": 0.4036043882369995, "learning_rate": 0.0002, "epoch": 0.49019607843137253, "step": 150}, {"loss": 1.1624, "grad_norm": 0.35938864946365356, "learning_rate": 0.0002, "epoch": 0.5228758169934641, "step": 160}, {"loss": 1.164, "grad_norm": 0.28880223631858826, "learning_rate": 0.0002, "epoch": 0.5555555555555556, "step": 170}, {"loss": 1.3521, "grad_norm": 0.3436269462108612, "learning_rate": 0.0002, "epoch": 0.5882352941176471, "step": 180}, {"loss": 1.2456, "grad_norm": 0.41923725605010986, "learning_rate": 0.0002, "epoch": 0.6209150326797386, "step": 190}, {"loss": 1.2226, "grad_norm": 0.25119203329086304, "learning_rate": 0.0002, "epoch": 0.6535947712418301, "step": 200}, {"loss": 1.1568, "grad_norm": 0.5870180726051331, "learning_rate": 0.0002, "epoch": 0.6862745098039216, "step": 210}, {"loss": 1.064, "grad_norm": 0.2831224203109741, "learning_rate": 0.0002, "epoch": 0.7189542483660131, "step": 220}, {"loss": 1.2469, "grad_norm": 0.3192005753517151, "learning_rate": 0.0002, "epoch": 0.7516339869281046, "step": 230}, {"loss": 1.1613, "grad_norm": 0.2998219430446625, "learning_rate": 0.0002, "epoch": 0.7843137254901961, "step": 240}, {"loss": 1.205, "grad_norm": 0.32855790853500366, "learning_rate": 0.0002, "epoch": 0.8169934640522876, "step": 250}, {"loss": 1.1631, "grad_norm": 0.3403124213218689, "learning_rate": 0.0002, "epoch": 0.8496732026143791, "step": 260}, {"loss": 1.1646, "grad_norm": 0.277401328086853, "learning_rate": 0.0002, "epoch": 0.8823529411764706, "step": 270}, {"loss": 1.084, "grad_norm": 0.2975269556045532, "learning_rate": 0.0002, "epoch": 0.9150326797385621, "step": 280}, {"loss": 1.2039, "grad_norm": 1.7909578084945679, "learning_rate": 0.0002, "epoch": 0.9477124183006536, "step": 290}, {"loss": 1.1226, "grad_norm": 0.2917245328426361, "learning_rate": 0.0002, "epoch": 0.9803921568627451, "step": 300}, {"eval_loss": 1.1937541961669922, "eval_runtime": 46.2571, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 1.0, "step": 306}, {"loss": 1.2011, "grad_norm": 0.26494982838630676, "learning_rate": 0.0002, "epoch": 1.0130718954248366, "step": 310}, {"loss": 1.0565, "grad_norm": 0.6289355754852295, "learning_rate": 0.0002, "epoch": 1.0457516339869282, "step": 320}, {"loss": 1.1619, "grad_norm": 0.26784011721611023, "learning_rate": 0.0002, "epoch": 1.0784313725490196, "step": 330}, {"loss": 1.1151, "grad_norm": 0.3392215967178345, "learning_rate": 0.0002, "epoch": 1.1111111111111112, "step": 340}, {"loss": 1.0752, "grad_norm": 0.40005937218666077, "learning_rate": 0.0002, "epoch": 1.1437908496732025, "step": 350}, {"loss": 1.0408, "grad_norm": 0.3590582013130188, "learning_rate": 0.0002, "epoch": 1.1764705882352942, "step": 360}, {"loss": 1.0836, "grad_norm": 0.3995305895805359, "learning_rate": 0.0002, "epoch": 1.2091503267973855, "step": 370}, {"loss": 1.0992, "grad_norm": 0.2950291633605957, "learning_rate": 0.0002, "epoch": 1.2418300653594772, "step": 380}, {"loss": 1.1152, "grad_norm": 0.32035166025161743, "learning_rate": 0.0002, "epoch": 1.2745098039215685, "step": 390}, {"loss": 1.1467, "grad_norm": 0.410366415977478, "learning_rate": 0.0002, "epoch": 1.3071895424836601, "step": 400}, {"loss": 0.9985, "grad_norm": 0.3106379508972168, "learning_rate": 0.0002, "epoch": 1.3398692810457518, "step": 410}, {"loss": 0.9789, "grad_norm": 0.38580670952796936, "learning_rate": 0.0002, "epoch": 1.3725490196078431, "step": 420}, {"loss": 1.0931, "grad_norm": 0.34411361813545227, "learning_rate": 0.0002, "epoch": 1.4052287581699345, "step": 430}, {"loss": 1.1685, "grad_norm": 0.44206851720809937, "learning_rate": 0.0002, "epoch": 1.4379084967320261, "step": 440}, {"loss": 1.0347, "grad_norm": 0.3492952585220337, "learning_rate": 0.0002, "epoch": 1.4705882352941178, "step": 450}, {"loss": 1.0534, "grad_norm": 0.376423716545105, "learning_rate": 0.0002, "epoch": 1.5032679738562091, "step": 460}, {"loss": 1.1162, "grad_norm": 0.359757661819458, "learning_rate": 0.0002, "epoch": 1.5359477124183005, "step": 470}, {"loss": 0.9586, "grad_norm": 0.3385067880153656, "learning_rate": 0.0002, "epoch": 1.5686274509803921, "step": 480}, {"loss": 1.0807, "grad_norm": 0.4943889379501343, "learning_rate": 0.0002, "epoch": 1.6013071895424837, "step": 490}, {"loss": 1.0796, "grad_norm": 0.4203241169452667, "learning_rate": 0.0002, "epoch": 1.6339869281045751, "step": 500}, {"loss": 1.1059, "grad_norm": 0.3093789219856262, "learning_rate": 0.0002, "epoch": 1.6666666666666665, "step": 510}, {"loss": 1.0323, "grad_norm": 0.3653067350387573, "learning_rate": 0.0002, "epoch": 1.6993464052287581, "step": 520}, {"loss": 1.0885, "grad_norm": 0.36761337518692017, "learning_rate": 0.0002, "epoch": 1.7320261437908497, "step": 530}, {"loss": 1.1698, "grad_norm": 0.5040399432182312, "learning_rate": 0.0002, "epoch": 1.7647058823529411, "step": 540}, {"loss": 1.0105, "grad_norm": 0.3818035125732422, "learning_rate": 0.0002, "epoch": 1.7973856209150327, "step": 550}, {"loss": 0.94, "grad_norm": 0.4021618664264679, "learning_rate": 0.0002, "epoch": 1.8300653594771243, "step": 560}, {"loss": 1.0358, "grad_norm": 0.3986459970474243, "learning_rate": 0.0002, "epoch": 1.8627450980392157, "step": 570}, {"loss": 1.003, "grad_norm": 0.48416733741760254, "learning_rate": 0.0002, "epoch": 1.8954248366013071, "step": 580}, {"loss": 1.1146, "grad_norm": 0.36853986978530884, "learning_rate": 0.0002, "epoch": 1.9281045751633987, "step": 590}, {"loss": 1.0689, "grad_norm": 0.383022665977478, "learning_rate": 0.0002, "epoch": 1.9607843137254903, "step": 600}, {"loss": 1.098, "grad_norm": 0.3169507086277008, "learning_rate": 0.0002, "epoch": 1.9934640522875817, "step": 610}, {"eval_loss": 1.1845070123672485, "eval_runtime": 46.2811, "eval_samples_per_second": 9.421, "eval_steps_per_second": 1.188, "epoch": 2.0, "step": 612}, {"loss": 0.9618, "grad_norm": 0.8920142650604248, "learning_rate": 0.0002, "epoch": 2.026143790849673, "step": 620}, {"loss": 0.9784, "grad_norm": 0.4814859628677368, "learning_rate": 0.0002, "epoch": 2.0588235294117645, "step": 630}, {"loss": 0.8464, "grad_norm": 0.4251559376716614, "learning_rate": 0.0002, "epoch": 2.0915032679738563, "step": 640}, {"loss": 0.932, "grad_norm": 0.5295765399932861, "learning_rate": 0.0002, "epoch": 2.1241830065359477, "step": 650}, {"loss": 0.9603, "grad_norm": 0.45016610622406006, "learning_rate": 0.0002, "epoch": 2.156862745098039, "step": 660}, {"loss": 0.8738, "grad_norm": 0.5870586633682251, "learning_rate": 0.0002, "epoch": 2.189542483660131, "step": 670}, {"loss": 0.9483, "grad_norm": 0.5174715518951416, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 680}, {"loss": 0.9551, "grad_norm": 0.5252485275268555, "learning_rate": 0.0002, "epoch": 2.2549019607843137, "step": 690}, {"loss": 0.9253, "grad_norm": 0.5158312320709229, "learning_rate": 0.0002, "epoch": 2.287581699346405, "step": 700}, {"loss": 0.9278, "grad_norm": 0.4824209213256836, "learning_rate": 0.0002, "epoch": 2.3202614379084965, "step": 710}, {"loss": 0.8804, "grad_norm": 0.6335175037384033, "learning_rate": 0.0002, "epoch": 2.3529411764705883, "step": 720}, {"loss": 0.9685, "grad_norm": 0.5240563154220581, "learning_rate": 0.0002, "epoch": 2.3856209150326797, "step": 730}, {"loss": 0.8794, "grad_norm": 0.5172886252403259, "learning_rate": 0.0002, "epoch": 2.418300653594771, "step": 740}, {"loss": 0.8158, "grad_norm": 0.48972561955451965, "learning_rate": 0.0002, "epoch": 2.450980392156863, "step": 750}, {"loss": 0.8766, "grad_norm": 0.5295189023017883, "learning_rate": 0.0002, "epoch": 2.4836601307189543, "step": 760}, {"loss": 0.8695, "grad_norm": 0.5487208962440491, "learning_rate": 0.0002, "epoch": 2.5163398692810457, "step": 770}, {"loss": 1.0109, "grad_norm": 0.5375093221664429, "learning_rate": 0.0002, "epoch": 2.549019607843137, "step": 780}, {"loss": 0.9244, "grad_norm": 0.5424453020095825, "learning_rate": 0.0002, "epoch": 2.581699346405229, "step": 790}, {"loss": 1.0424, "grad_norm": 0.6029134392738342, "learning_rate": 0.0002, "epoch": 2.6143790849673203, "step": 800}, {"loss": 0.8688, "grad_norm": 0.6584921479225159, "learning_rate": 0.0002, "epoch": 2.6470588235294117, "step": 810}, {"loss": 0.7796, "grad_norm": 0.5735557675361633, "learning_rate": 0.0002, "epoch": 2.6797385620915035, "step": 820}, {"loss": 0.8834, "grad_norm": 0.5216763019561768, "learning_rate": 0.0002, "epoch": 2.712418300653595, "step": 830}, {"loss": 0.8946, "grad_norm": 0.5455219149589539, "learning_rate": 0.0002, "epoch": 2.7450980392156863, "step": 840}, {"loss": 0.8037, "grad_norm": 0.5139284729957581, "learning_rate": 0.0002, "epoch": 2.7777777777777777, "step": 850}, {"loss": 0.988, "grad_norm": 0.5096403360366821, "learning_rate": 0.0002, "epoch": 2.810457516339869, "step": 860}, {"loss": 0.9169, "grad_norm": 0.6337038278579712, "learning_rate": 0.0002, "epoch": 2.843137254901961, "step": 870}, {"loss": 0.8938, "grad_norm": 0.47218772768974304, "learning_rate": 0.0002, "epoch": 2.8758169934640523, "step": 880}, {"loss": 0.8554, "grad_norm": 0.4640636742115021, "learning_rate": 0.0002, "epoch": 2.9084967320261437, "step": 890}, {"loss": 0.8625, "grad_norm": 0.4199628531932831, "learning_rate": 0.0002, "epoch": 2.9411764705882355, "step": 900}, {"loss": 0.8104, "grad_norm": 0.5067117214202881, "learning_rate": 0.0002, "epoch": 2.973856209150327, "step": 910}, {"eval_loss": 1.2291251420974731, "eval_runtime": 46.2557, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 3.0, "step": 918}, {"loss": 0.8157, "grad_norm": 0.8342176079750061, "learning_rate": 0.0002, "epoch": 3.0065359477124183, "step": 920}, {"loss": 0.6855, "grad_norm": 0.7695813775062561, "learning_rate": 0.0002, "epoch": 3.0392156862745097, "step": 930}, {"loss": 0.6173, "grad_norm": 0.6819486618041992, "learning_rate": 0.0002, "epoch": 3.0718954248366015, "step": 940}, {"loss": 0.6495, "grad_norm": 0.7568879723548889, "learning_rate": 0.0002, "epoch": 3.104575163398693, "step": 950}, {"loss": 0.7905, "grad_norm": 0.6760695576667786, "learning_rate": 0.0002, "epoch": 3.1372549019607843, "step": 960}, {"loss": 0.6405, "grad_norm": 0.6359127759933472, "learning_rate": 0.0002, "epoch": 3.1699346405228757, "step": 970}, {"loss": 0.7172, "grad_norm": 0.8414971828460693, "learning_rate": 0.0002, "epoch": 3.2026143790849675, "step": 980}, {"loss": 0.7865, "grad_norm": 0.68381667137146, "learning_rate": 0.0002, "epoch": 3.235294117647059, "step": 990}, {"loss": 0.6651, "grad_norm": 0.6852193474769592, "learning_rate": 0.0002, "epoch": 3.2679738562091503, "step": 1000}, {"loss": 0.6571, "grad_norm": 0.8184967041015625, "learning_rate": 0.0002, "epoch": 3.3006535947712417, "step": 1010}, {"loss": 0.7036, "grad_norm": 1.047290563583374, "learning_rate": 0.0002, "epoch": 3.3333333333333335, "step": 1020}, {"loss": 0.7215, "grad_norm": 0.8291178345680237, "learning_rate": 0.0002, "epoch": 3.366013071895425, "step": 1030}, {"loss": 0.6243, "grad_norm": 0.6668022871017456, "learning_rate": 0.0002, "epoch": 3.3986928104575163, "step": 1040}, {"loss": 0.7459, "grad_norm": 0.6354008316993713, "learning_rate": 0.0002, "epoch": 3.431372549019608, "step": 1050}, {"loss": 0.6826, "grad_norm": 1.2028366327285767, "learning_rate": 0.0002, "epoch": 3.4640522875816995, "step": 1060}, {"loss": 0.5913, "grad_norm": 0.717367947101593, "learning_rate": 0.0002, "epoch": 3.496732026143791, "step": 1070}, {"loss": 0.6903, "grad_norm": 0.542179524898529, "learning_rate": 0.0002, "epoch": 3.5294117647058822, "step": 1080}, {"loss": 0.7673, "grad_norm": 0.845981776714325, "learning_rate": 0.0002, "epoch": 3.5620915032679736, "step": 1090}, {"loss": 0.7089, "grad_norm": 0.7381046414375305, "learning_rate": 0.0002, "epoch": 3.5947712418300655, "step": 1100}, {"loss": 0.6705, "grad_norm": 0.6563456058502197, "learning_rate": 0.0002, "epoch": 3.627450980392157, "step": 1110}, {"loss": 0.7767, "grad_norm": 0.7130876779556274, "learning_rate": 0.0002, "epoch": 3.6601307189542482, "step": 1120}, {"loss": 0.7164, "grad_norm": 0.800032913684845, "learning_rate": 0.0002, "epoch": 3.69281045751634, "step": 1130}, {"loss": 0.7272, "grad_norm": 0.980328381061554, "learning_rate": 0.0002, "epoch": 3.7254901960784315, "step": 1140}, {"loss": 0.7672, "grad_norm": 0.8542261123657227, "learning_rate": 0.0002, "epoch": 3.758169934640523, "step": 1150}, {"loss": 0.679, "grad_norm": 0.6302552819252014, "learning_rate": 0.0002, "epoch": 3.7908496732026142, "step": 1160}, {"loss": 0.7457, "grad_norm": 0.515398383140564, "learning_rate": 0.0002, "epoch": 3.8235294117647056, "step": 1170}, {"loss": 0.693, "grad_norm": 1.2427130937576294, "learning_rate": 0.0002, "epoch": 3.8562091503267975, "step": 1180}, {"loss": 0.7182, "grad_norm": 0.8206831216812134, "learning_rate": 0.0002, "epoch": 3.888888888888889, "step": 1190}, {"loss": 0.7519, "grad_norm": 0.7633249163627625, "learning_rate": 0.0002, "epoch": 3.9215686274509802, "step": 1200}, {"loss": 0.7082, "grad_norm": 0.8034512400627136, "learning_rate": 0.0002, "epoch": 3.954248366013072, "step": 1210}, {"loss": 0.6834, "grad_norm": 0.7667182087898254, "learning_rate": 0.0002, "epoch": 3.9869281045751634, "step": 1220}, {"eval_loss": 1.3456707000732422, "eval_runtime": 46.2562, "eval_samples_per_second": 9.426, "eval_steps_per_second": 1.189, "epoch": 4.0, "step": 1224}, {"loss": 0.582, "grad_norm": 0.7724746465682983, "learning_rate": 0.0002, "epoch": 4.019607843137255, "step": 1230}, {"loss": 0.4759, "grad_norm": 1.166916847229004, "learning_rate": 0.0002, "epoch": 4.052287581699346, "step": 1240}, {"loss": 0.4995, "grad_norm": 0.7234508991241455, "learning_rate": 0.0002, "epoch": 4.084967320261438, "step": 1250}, {"loss": 0.4863, "grad_norm": 1.1418060064315796, "learning_rate": 0.0002, "epoch": 4.117647058823529, "step": 1260}, {"loss": 0.5425, "grad_norm": 0.9603922367095947, "learning_rate": 0.0002, "epoch": 4.150326797385621, "step": 1270}, {"loss": 0.4892, "grad_norm": 0.8976530432701111, "learning_rate": 0.0002, "epoch": 4.183006535947713, "step": 1280}, {"loss": 0.473, "grad_norm": 0.6855078339576721, "learning_rate": 0.0002, "epoch": 4.215686274509804, "step": 1290}, {"loss": 0.4416, "grad_norm": 1.2676647901535034, "learning_rate": 0.0002, "epoch": 4.248366013071895, "step": 1300}, {"loss": 0.5071, "grad_norm": 1.104057788848877, "learning_rate": 0.0002, "epoch": 4.281045751633987, "step": 1310}, {"loss": 0.5168, "grad_norm": 1.7076562643051147, "learning_rate": 0.0002, "epoch": 4.313725490196078, "step": 1320}, {"loss": 0.4655, "grad_norm": 1.2308520078659058, "learning_rate": 0.0002, "epoch": 4.34640522875817, "step": 1330}, {"loss": 0.5322, "grad_norm": 1.2652729749679565, "learning_rate": 0.0002, "epoch": 4.379084967320262, "step": 1340}, {"loss": 0.5262, "grad_norm": 1.054958701133728, "learning_rate": 0.0002, "epoch": 4.411764705882353, "step": 1350}, {"loss": 0.4747, "grad_norm": 1.0130749940872192, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 1360}, {"loss": 0.4887, "grad_norm": 1.0517818927764893, "learning_rate": 0.0002, "epoch": 4.477124183006536, "step": 1370}, {"loss": 0.4906, "grad_norm": 0.8593037128448486, "learning_rate": 0.0002, "epoch": 4.509803921568627, "step": 1380}, {"loss": 0.5049, "grad_norm": 1.0248081684112549, "learning_rate": 0.0002, "epoch": 4.542483660130719, "step": 1390}, {"loss": 0.472, "grad_norm": 0.8999413847923279, "learning_rate": 0.0002, "epoch": 4.57516339869281, "step": 1400}, {"loss": 0.5102, "grad_norm": 0.9106912612915039, "learning_rate": 0.0002, "epoch": 4.607843137254902, "step": 1410}, {"loss": 0.5203, "grad_norm": 1.2736181020736694, "learning_rate": 0.0002, "epoch": 4.640522875816993, "step": 1420}, {"loss": 0.5101, "grad_norm": 0.9311690926551819, "learning_rate": 0.0002, "epoch": 4.673202614379085, "step": 1430}, {"loss": 0.5648, "grad_norm": 1.0455045700073242, "learning_rate": 0.0002, "epoch": 4.705882352941177, "step": 1440}, {"loss": 0.5004, "grad_norm": 1.0190727710723877, "learning_rate": 0.0002, "epoch": 4.738562091503268, "step": 1450}, {"loss": 0.5506, "grad_norm": 1.333198070526123, "learning_rate": 0.0002, "epoch": 4.771241830065359, "step": 1460}, {"loss": 0.5846, "grad_norm": 0.8808416724205017, "learning_rate": 0.0002, "epoch": 4.803921568627451, "step": 1470}, {"loss": 0.4671, "grad_norm": 0.8896227478981018, "learning_rate": 0.0002, "epoch": 4.836601307189542, "step": 1480}, {"loss": 0.4732, "grad_norm": 1.212323784828186, "learning_rate": 0.0002, "epoch": 4.8692810457516345, "step": 1490}, {"loss": 0.5263, "grad_norm": 1.0490120649337769, "learning_rate": 0.0002, "epoch": 4.901960784313726, "step": 1500}, {"loss": 0.5815, "grad_norm": 0.8946618437767029, "learning_rate": 0.0002, "epoch": 4.934640522875817, "step": 1510}, {"loss": 0.5369, "grad_norm": 1.0609275102615356, "learning_rate": 0.0002, "epoch": 4.967320261437909, "step": 1520}, {"loss": 0.5348, "grad_norm": 0.8885099291801453, "learning_rate": 0.0002, "epoch": 5.0, "step": 1530}, {"eval_loss": 1.5771757364273071, "eval_runtime": 46.2667, "eval_samples_per_second": 9.424, "eval_steps_per_second": 1.189, "epoch": 5.0, "step": 1530}, {"loss": 0.3176, "grad_norm": 1.401705026626587, "learning_rate": 0.0002, "epoch": 5.032679738562091, "step": 1540}, {"loss": 0.3346, "grad_norm": 0.8365539908409119, "learning_rate": 0.0002, "epoch": 5.065359477124183, "step": 1550}, {"loss": 0.3605, "grad_norm": 1.3188321590423584, "learning_rate": 0.0002, "epoch": 5.098039215686274, "step": 1560}, {"loss": 0.326, "grad_norm": 0.9819526076316833, "learning_rate": 0.0002, "epoch": 5.130718954248366, "step": 1570}, {"loss": 0.3575, "grad_norm": 1.13265061378479, "learning_rate": 0.0002, "epoch": 5.163398692810458, "step": 1580}, {"loss": 0.3418, "grad_norm": 1.478152871131897, "learning_rate": 0.0002, "epoch": 5.196078431372549, "step": 1590}, {"loss": 0.3388, "grad_norm": 1.4188750982284546, "learning_rate": 0.0002, "epoch": 5.228758169934641, "step": 1600}, {"loss": 0.3524, "grad_norm": 1.2499338388442993, "learning_rate": 0.0002, "epoch": 5.261437908496732, "step": 1610}, {"loss": 0.423, "grad_norm": 1.7885085344314575, "learning_rate": 0.0002, "epoch": 5.294117647058823, "step": 1620}, {"loss": 0.3237, "grad_norm": 1.2614946365356445, "learning_rate": 0.0002, "epoch": 5.326797385620915, "step": 1630}, {"loss": 0.3511, "grad_norm": 1.28338623046875, "learning_rate": 0.0002, "epoch": 5.359477124183006, "step": 1640}, {"loss": 0.3112, "grad_norm": 1.1973257064819336, "learning_rate": 0.0002, "epoch": 5.392156862745098, "step": 1650}, {"loss": 0.3645, "grad_norm": 1.1356301307678223, "learning_rate": 0.0002, "epoch": 5.42483660130719, "step": 1660}, {"loss": 0.307, "grad_norm": 0.9048901200294495, "learning_rate": 0.0002, "epoch": 5.457516339869281, "step": 1670}, {"loss": 0.3828, "grad_norm": 1.5352122783660889, "learning_rate": 0.0002, "epoch": 5.490196078431373, "step": 1680}, {"loss": 0.3826, "grad_norm": 0.9096335172653198, "learning_rate": 0.0002, "epoch": 5.522875816993464, "step": 1690}, {"loss": 0.3686, "grad_norm": 1.1903661489486694, "learning_rate": 0.0002, "epoch": 5.555555555555555, "step": 1700}, {"loss": 0.325, "grad_norm": 0.9234451651573181, "learning_rate": 0.0002, "epoch": 5.588235294117647, "step": 1710}, {"loss": 0.3451, "grad_norm": 1.4554102420806885, "learning_rate": 0.0002, "epoch": 5.620915032679738, "step": 1720}, {"loss": 0.3488, "grad_norm": 1.1044343709945679, "learning_rate": 0.0002, "epoch": 5.65359477124183, "step": 1730}, {"loss": 0.3673, "grad_norm": 1.2219593524932861, "learning_rate": 0.0002, "epoch": 5.686274509803922, "step": 1740}, {"loss": 0.3517, "grad_norm": 0.901652455329895, "learning_rate": 0.0002, "epoch": 5.718954248366013, "step": 1750}, {"loss": 0.4082, "grad_norm": 1.3334792852401733, "learning_rate": 0.0002, "epoch": 5.751633986928105, "step": 1760}, {"loss": 0.4386, "grad_norm": 1.5595488548278809, "learning_rate": 0.0002, "epoch": 5.784313725490196, "step": 1770}, {"loss": 0.3217, "grad_norm": 1.3892982006072998, "learning_rate": 0.0002, "epoch": 5.816993464052287, "step": 1780}, {"loss": 0.3919, "grad_norm": 1.0813168287277222, "learning_rate": 0.0002, "epoch": 5.849673202614379, "step": 1790}, {"loss": 0.3697, "grad_norm": 1.145320177078247, "learning_rate": 0.0002, "epoch": 5.882352941176471, "step": 1800}, {"loss": 0.3903, "grad_norm": 1.0249533653259277, "learning_rate": 0.0002, "epoch": 5.915032679738562, "step": 1810}, {"loss": 0.3481, "grad_norm": 1.0013737678527832, "learning_rate": 0.0002, "epoch": 5.947712418300654, "step": 1820}, {"loss": 0.4278, "grad_norm": 1.212314248085022, "learning_rate": 0.0002, "epoch": 5.980392156862745, "step": 1830}, {"eval_loss": 1.7506128549575806, "eval_runtime": 46.2256, "eval_samples_per_second": 9.432, "eval_steps_per_second": 1.19, "epoch": 6.0, "step": 1836}, {"loss": 0.3283, "grad_norm": 0.7339767813682556, "learning_rate": 0.0002, "epoch": 6.0130718954248366, "step": 1840}, {"loss": 0.2304, "grad_norm": 1.1071710586547852, "learning_rate": 0.0002, "epoch": 6.045751633986928, "step": 1850}, {"loss": 0.2436, "grad_norm": 1.2613991498947144, "learning_rate": 0.0002, "epoch": 6.078431372549019, "step": 1860}, {"loss": 0.2403, "grad_norm": 1.053133249282837, "learning_rate": 0.0002, "epoch": 6.111111111111111, "step": 1870}, {"loss": 0.2509, "grad_norm": 1.069568395614624, "learning_rate": 0.0002, "epoch": 6.143790849673203, "step": 1880}, {"loss": 0.2272, "grad_norm": 1.020458698272705, "learning_rate": 0.0002, "epoch": 6.176470588235294, "step": 1890}, {"loss": 0.2408, "grad_norm": 1.2430394887924194, "learning_rate": 0.0002, "epoch": 6.209150326797386, "step": 1900}, {"loss": 0.229, "grad_norm": 1.3475574254989624, "learning_rate": 0.0002, "epoch": 6.241830065359477, "step": 1910}, {"loss": 0.2542, "grad_norm": 0.9094598889350891, "learning_rate": 0.0002, "epoch": 6.2745098039215685, "step": 1920}, {"loss": 0.2009, "grad_norm": 1.255650520324707, "learning_rate": 0.0002, "epoch": 6.30718954248366, "step": 1930}, {"loss": 0.25, "grad_norm": 1.4193930625915527, "learning_rate": 0.0002, "epoch": 6.339869281045751, "step": 1940}, {"loss": 0.293, "grad_norm": 1.4378032684326172, "learning_rate": 0.0002, "epoch": 6.372549019607844, "step": 1950}, {"loss": 0.2685, "grad_norm": 1.2236989736557007, "learning_rate": 0.0002, "epoch": 6.405228758169935, "step": 1960}, {"loss": 0.2608, "grad_norm": 1.0902987718582153, "learning_rate": 0.0002, "epoch": 6.437908496732026, "step": 1970}, {"loss": 0.2267, "grad_norm": 1.1165062189102173, "learning_rate": 0.0002, "epoch": 6.470588235294118, "step": 1980}, {"loss": 0.2246, "grad_norm": 1.3953566551208496, "learning_rate": 0.0002, "epoch": 6.503267973856209, "step": 1990}, {"loss": 0.2834, "grad_norm": 1.5215585231781006, "learning_rate": 0.0002, "epoch": 6.5359477124183005, "step": 2000}, {"loss": 0.2457, "grad_norm": 1.3496609926223755, "learning_rate": 0.0002, "epoch": 6.568627450980392, "step": 2010}, {"loss": 0.2637, "grad_norm": 1.2511820793151855, "learning_rate": 0.0002, "epoch": 6.601307189542483, "step": 2020}, {"loss": 0.2956, "grad_norm": 1.9875848293304443, "learning_rate": 0.0002, "epoch": 6.633986928104575, "step": 2030}, {"loss": 0.2664, "grad_norm": 1.0766608715057373, "learning_rate": 0.0002, "epoch": 6.666666666666667, "step": 2040}, {"loss": 0.2792, "grad_norm": 1.3594712018966675, "learning_rate": 0.0002, "epoch": 6.699346405228758, "step": 2050}, {"loss": 0.3194, "grad_norm": 1.2357292175292969, "learning_rate": 0.0002, "epoch": 6.73202614379085, "step": 2060}, {"loss": 0.2526, "grad_norm": 1.2428375482559204, "learning_rate": 0.0002, "epoch": 6.764705882352941, "step": 2070}, {"loss": 0.2355, "grad_norm": 1.2724156379699707, "learning_rate": 0.0002, "epoch": 6.7973856209150325, "step": 2080}, {"loss": 0.289, "grad_norm": 1.4981396198272705, "learning_rate": 0.0002, "epoch": 6.830065359477124, "step": 2090}, {"loss": 0.2443, "grad_norm": 0.9346088171005249, "learning_rate": 0.0002, "epoch": 6.862745098039216, "step": 2100}, {"loss": 0.262, "grad_norm": 1.3955477476119995, "learning_rate": 0.0002, "epoch": 6.895424836601308, "step": 2110}, {"loss": 0.2981, "grad_norm": 1.492382287979126, "learning_rate": 0.0002, "epoch": 6.928104575163399, "step": 2120}, {"loss": 0.3093, "grad_norm": 1.2755712270736694, "learning_rate": 0.0002, "epoch": 6.96078431372549, "step": 2130}, {"loss": 0.2943, "grad_norm": 1.4600884914398193, "learning_rate": 0.0002, "epoch": 6.993464052287582, "step": 2140}, {"eval_loss": 1.9770371913909912, "eval_runtime": 46.2588, "eval_samples_per_second": 9.425, "eval_steps_per_second": 1.189, "epoch": 7.0, "step": 2142}, {"loss": 0.2032, "grad_norm": 1.205262541770935, "learning_rate": 0.0002, "epoch": 7.026143790849673, "step": 2150}, {"loss": 0.1642, "grad_norm": 1.1699777841567993, "learning_rate": 0.0002, "epoch": 7.0588235294117645, "step": 2160}, {"loss": 0.1886, "grad_norm": 1.2428505420684814, "learning_rate": 0.0002, "epoch": 7.091503267973856, "step": 2170}, {"loss": 0.1762, "grad_norm": 0.9843717813491821, "learning_rate": 0.0002, "epoch": 7.124183006535947, "step": 2180}, {"loss": 0.1723, "grad_norm": 1.089490532875061, "learning_rate": 0.0002, "epoch": 7.1568627450980395, "step": 2190}, {"loss": 0.1721, "grad_norm": 1.2811459302902222, "learning_rate": 0.0002, "epoch": 7.189542483660131, "step": 2200}, {"loss": 0.1983, "grad_norm": 1.4558671712875366, "learning_rate": 0.0002, "epoch": 7.222222222222222, "step": 2210}, {"loss": 0.178, "grad_norm": 1.2111164331436157, "learning_rate": 0.0002, "epoch": 7.254901960784314, "step": 2220}, {"loss": 0.1463, "grad_norm": 1.46672785282135, "learning_rate": 0.0002, "epoch": 7.287581699346405, "step": 2230}, {"loss": 0.1883, "grad_norm": 1.464061975479126, "learning_rate": 0.0002, "epoch": 7.3202614379084965, "step": 2240}, {"loss": 0.2276, "grad_norm": 1.6276377439498901, "learning_rate": 0.0002, "epoch": 7.352941176470588, "step": 2250}, {"loss": 0.1771, "grad_norm": 1.4011811017990112, "learning_rate": 0.0002, "epoch": 7.38562091503268, "step": 2260}, {"loss": 0.1875, "grad_norm": 0.9894806146621704, "learning_rate": 0.0002, "epoch": 7.4183006535947715, "step": 2270}, {"loss": 0.1725, "grad_norm": 0.9357670545578003, "learning_rate": 0.0002, "epoch": 7.450980392156863, "step": 2280}, {"loss": 0.1891, "grad_norm": 1.7790061235427856, "learning_rate": 0.0002, "epoch": 7.483660130718954, "step": 2290}, {"loss": 0.1967, "grad_norm": 1.468843698501587, "learning_rate": 0.0002, "epoch": 7.516339869281046, "step": 2300}, {"loss": 0.195, "grad_norm": 1.063189148902893, "learning_rate": 0.0002, "epoch": 7.549019607843137, "step": 2310}, {"loss": 0.1752, "grad_norm": 0.7940694689750671, "learning_rate": 0.0002, "epoch": 7.5816993464052285, "step": 2320}, {"loss": 0.2169, "grad_norm": 1.555564045906067, "learning_rate": 0.0002, "epoch": 7.61437908496732, "step": 2330}, {"loss": 0.1755, "grad_norm": 0.7388061881065369, "learning_rate": 0.0002, "epoch": 7.647058823529412, "step": 2340}, {"loss": 0.2206, "grad_norm": 1.2422513961791992, "learning_rate": 0.0002, "epoch": 7.6797385620915035, "step": 2350}, {"loss": 0.2015, "grad_norm": 1.3868855237960815, "learning_rate": 0.0002, "epoch": 7.712418300653595, "step": 2360}, {"loss": 0.1888, "grad_norm": 1.2965079545974731, "learning_rate": 0.0002, "epoch": 7.745098039215686, "step": 2370}, {"loss": 0.2257, "grad_norm": 1.4052339792251587, "learning_rate": 0.0002, "epoch": 7.777777777777778, "step": 2380}, {"loss": 0.2145, "grad_norm": 1.9005945920944214, "learning_rate": 0.0002, "epoch": 7.810457516339869, "step": 2390}, {"loss": 0.2154, "grad_norm": 0.9947215914726257, "learning_rate": 0.0002, "epoch": 7.8431372549019605, "step": 2400}, {"loss": 0.1841, "grad_norm": 0.796757698059082, "learning_rate": 0.0002, "epoch": 7.875816993464053, "step": 2410}, {"loss": 0.2476, "grad_norm": 2.4196858406066895, "learning_rate": 0.0002, "epoch": 7.908496732026144, "step": 2420}, {"loss": 0.2136, "grad_norm": 1.7430493831634521, "learning_rate": 0.0002, "epoch": 7.9411764705882355, "step": 2430}, {"loss": 0.2053, "grad_norm": 1.0432168245315552, "learning_rate": 0.0002, "epoch": 7.973856209150327, "step": 2440}]}