diff --git a/.gitattributes b/.gitattributes
index 700cf25fb8571363d7f9ac2f4af5e9de3a5deece..e83ad3820935b85cfcffa07caff9878724eb17ab 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -415,3 +415,12 @@ Meta-Llama-3-8B-Instruct_int4_arc_challenge-routerbench-0shot_lr-0.0002_e-8_seq-
 Meta-Llama-3-8B-Instruct_int4_arc_challenge-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-1.0-num-1029-sd-42/checkpoint-731/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Meta-Llama-3-8B-Instruct_int4_arc_challenge-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-1.0-num-1029-sd-42/checkpoint-832/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Meta-Llama-3-8B-Instruct_int4_arc_challenge-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-1.0-num-1029-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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e04e4441e0c1b29f69c16b26c142944e440b8076
--- /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-0.6-num-5885-sd-10000/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": [
+    "q_proj",
+    "v_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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..56e5920d80526c364d2343fccebf2d2c51f835ba
--- /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-0.6-num-5885-sd-10000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29626cfdf5fb74581691c2f8a4959a8bfacf991c59dce48b2a56c151db65b924
+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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e04e4441e0c1b29f69c16b26c142944e440b8076
--- /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-0.6-num-5885-sd-10000/checkpoint-1622/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": [
+    "q_proj",
+    "v_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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..56e5920d80526c364d2343fccebf2d2c51f835ba
--- /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-0.6-num-5885-sd-10000/checkpoint-1622/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29626cfdf5fb74581691c2f8a4959a8bfacf991c59dce48b2a56c151db65b924
+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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..eb818173cf135c3e668e7516a6fe114b5b7471f1
--- /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-0.6-num-5885-sd-10000/checkpoint-1622/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08fa544b6efd9931c1508e7dd19e79d63a011f1892a4a75470d8ad0d6f14126a
+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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..39bb72984a6ad4164dd3526fe83785c4a6a5494e
--- /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-0.6-num-5885-sd-10000/checkpoint-1622/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd56b345acd204cffc51ffbb4bb8808fb29c4b818fc35e6e1b2c7fc45e0218a0
+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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c4c4fa34d66b60508f0ec3a56ffe95306a5a4281
--- /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-0.6-num-5885-sd-10000/checkpoint-1622/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b30b8f3b26b2ef091d45bfcbfd165d1a71788a954adc2f9846020c65a033a2
+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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22
--- /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-0.6-num-5885-sd-10000/checkpoint-1622/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873
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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..0da0541d5ff4bf87646b50eee5d002fea4c99a19
--- /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-0.6-num-5885-sd-10000/checkpoint-1622/trainer_state.json
@@ -0,0 +1,1183 @@
+{
+  "best_metric": 1.238026738166809,
+  "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-0.6-num-5885-sd-10000/checkpoint-1622",
+  "epoch": 2.0,
+  "eval_steps": 10,
+  "global_step": 1622,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012330456226880395,
+      "grad_norm": 0.8258164525032043,
+      "learning_rate": 0.0002,
+      "loss": 2.3601,
+      "step": 10
+    },
+    {
+      "epoch": 0.02466091245376079,
+      "grad_norm": 0.4577729105949402,
+      "learning_rate": 0.0002,
+      "loss": 1.7317,
+      "step": 20
+    },
+    {
+      "epoch": 0.036991368680641186,
+      "grad_norm": 0.639807939529419,
+      "learning_rate": 0.0002,
+      "loss": 1.4729,
+      "step": 30
+    },
+    {
+      "epoch": 0.04932182490752158,
+      "grad_norm": 0.5311757922172546,
+      "learning_rate": 0.0002,
+      "loss": 1.2088,
+      "step": 40
+    },
+    {
+      "epoch": 0.06165228113440197,
+      "grad_norm": 0.386595219373703,
+      "learning_rate": 0.0002,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.07398273736128237,
+      "grad_norm": 0.4401357173919678,
+      "learning_rate": 0.0002,
+      "loss": 1.1657,
+      "step": 60
+    },
+    {
+      "epoch": 0.08631319358816276,
+      "grad_norm": 0.3234352171421051,
+      "learning_rate": 0.0002,
+      "loss": 1.1022,
+      "step": 70
+    },
+    {
+      "epoch": 0.09864364981504316,
+      "grad_norm": 0.29643672704696655,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 80
+    },
+    {
+      "epoch": 0.11097410604192355,
+      "grad_norm": 0.2941012382507324,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 90
+    },
+    {
+      "epoch": 0.12330456226880394,
+      "grad_norm": 0.5498173832893372,
+      "learning_rate": 0.0002,
+      "loss": 1.2067,
+      "step": 100
+    },
+    {
+      "epoch": 0.13563501849568435,
+      "grad_norm": 0.2545783519744873,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 110
+    },
+    {
+      "epoch": 0.14796547472256474,
+      "grad_norm": 0.2984241247177124,
+      "learning_rate": 0.0002,
+      "loss": 1.0297,
+      "step": 120
+    },
+    {
+      "epoch": 0.16029593094944514,
+      "grad_norm": 0.2710968852043152,
+      "learning_rate": 0.0002,
+      "loss": 1.1591,
+      "step": 130
+    },
+    {
+      "epoch": 0.17262638717632553,
+      "grad_norm": 0.2817152142524719,
+      "learning_rate": 0.0002,
+      "loss": 1.0427,
+      "step": 140
+    },
+    {
+      "epoch": 0.18495684340320592,
+      "grad_norm": 0.41083765029907227,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 150
+    },
+    {
+      "epoch": 0.19728729963008632,
+      "grad_norm": 0.36536213755607605,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 160
+    },
+    {
+      "epoch": 0.2096177558569667,
+      "grad_norm": 0.2738671600818634,
+      "learning_rate": 0.0002,
+      "loss": 1.0132,
+      "step": 170
+    },
+    {
+      "epoch": 0.2219482120838471,
+      "grad_norm": 0.27403146028518677,
+      "learning_rate": 0.0002,
+      "loss": 0.9555,
+      "step": 180
+    },
+    {
+      "epoch": 0.2342786683107275,
+      "grad_norm": 0.4446810483932495,
+      "learning_rate": 0.0002,
+      "loss": 1.0769,
+      "step": 190
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "grad_norm": 0.5295385718345642,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 200
+    },
+    {
+      "epoch": 0.2589395807644883,
+      "grad_norm": 0.311404824256897,
+      "learning_rate": 0.0002,
+      "loss": 1.0827,
+      "step": 210
+    },
+    {
+      "epoch": 0.2712700369913687,
+      "grad_norm": 0.2448509782552719,
+      "learning_rate": 0.0002,
+      "loss": 1.1455,
+      "step": 220
+    },
+    {
+      "epoch": 0.2836004932182491,
+      "grad_norm": 0.6507014036178589,
+      "learning_rate": 0.0002,
+      "loss": 1.0929,
+      "step": 230
+    },
+    {
+      "epoch": 0.2959309494451295,
+      "grad_norm": 0.2339320331811905,
+      "learning_rate": 0.0002,
+      "loss": 0.9875,
+      "step": 240
+    },
+    {
+      "epoch": 0.3082614056720099,
+      "grad_norm": 0.8210226893424988,
+      "learning_rate": 0.0002,
+      "loss": 0.9211,
+      "step": 250
+    },
+    {
+      "epoch": 0.3205918618988903,
+      "grad_norm": 0.27473965287208557,
+      "learning_rate": 0.0002,
+      "loss": 1.161,
+      "step": 260
+    },
+    {
+      "epoch": 0.33292231812577067,
+      "grad_norm": 0.3051395118236542,
+      "learning_rate": 0.0002,
+      "loss": 1.0218,
+      "step": 270
+    },
+    {
+      "epoch": 0.34525277435265106,
+      "grad_norm": 0.3037777245044708,
+      "learning_rate": 0.0002,
+      "loss": 1.0286,
+      "step": 280
+    },
+    {
+      "epoch": 0.35758323057953145,
+      "grad_norm": 0.2748974859714508,
+      "learning_rate": 0.0002,
+      "loss": 1.144,
+      "step": 290
+    },
+    {
+      "epoch": 0.36991368680641185,
+      "grad_norm": 0.23656068742275238,
+      "learning_rate": 0.0002,
+      "loss": 1.0858,
+      "step": 300
+    },
+    {
+      "epoch": 0.38224414303329224,
+      "grad_norm": 0.2523384094238281,
+      "learning_rate": 0.0002,
+      "loss": 1.0564,
+      "step": 310
+    },
+    {
+      "epoch": 0.39457459926017263,
+      "grad_norm": 0.27848055958747864,
+      "learning_rate": 0.0002,
+      "loss": 1.3091,
+      "step": 320
+    },
+    {
+      "epoch": 0.406905055487053,
+      "grad_norm": 0.3204525411128998,
+      "learning_rate": 0.0002,
+      "loss": 1.0252,
+      "step": 330
+    },
+    {
+      "epoch": 0.4192355117139334,
+      "grad_norm": 0.3459707498550415,
+      "learning_rate": 0.0002,
+      "loss": 0.9855,
+      "step": 340
+    },
+    {
+      "epoch": 0.4315659679408138,
+      "grad_norm": 0.2458430379629135,
+      "learning_rate": 0.0002,
+      "loss": 1.1111,
+      "step": 350
+    },
+    {
+      "epoch": 0.4438964241676942,
+      "grad_norm": 0.5022910237312317,
+      "learning_rate": 0.0002,
+      "loss": 1.1493,
+      "step": 360
+    },
+    {
+      "epoch": 0.4562268803945746,
+      "grad_norm": 0.27076372504234314,
+      "learning_rate": 0.0002,
+      "loss": 1.1272,
+      "step": 370
+    },
+    {
+      "epoch": 0.468557336621455,
+      "grad_norm": 0.6489047408103943,
+      "learning_rate": 0.0002,
+      "loss": 1.1927,
+      "step": 380
+    },
+    {
+      "epoch": 0.4808877928483354,
+      "grad_norm": 0.3324144184589386,
+      "learning_rate": 0.0002,
+      "loss": 0.9501,
+      "step": 390
+    },
+    {
+      "epoch": 0.4932182490752158,
+      "grad_norm": 0.32813116908073425,
+      "learning_rate": 0.0002,
+      "loss": 1.2012,
+      "step": 400
+    },
+    {
+      "epoch": 0.5055487053020962,
+      "grad_norm": 0.25295355916023254,
+      "learning_rate": 0.0002,
+      "loss": 1.1135,
+      "step": 410
+    },
+    {
+      "epoch": 0.5178791615289766,
+      "grad_norm": 0.2912578880786896,
+      "learning_rate": 0.0002,
+      "loss": 0.9477,
+      "step": 420
+    },
+    {
+      "epoch": 0.530209617755857,
+      "grad_norm": 0.34780189394950867,
+      "learning_rate": 0.0002,
+      "loss": 1.0121,
+      "step": 430
+    },
+    {
+      "epoch": 0.5425400739827374,
+      "grad_norm": 0.24604526162147522,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 440
+    },
+    {
+      "epoch": 0.5548705302096177,
+      "grad_norm": 0.32759982347488403,
+      "learning_rate": 0.0002,
+      "loss": 1.253,
+      "step": 450
+    },
+    {
+      "epoch": 0.5672009864364982,
+      "grad_norm": 0.40810221433639526,
+      "learning_rate": 0.0002,
+      "loss": 1.1925,
+      "step": 460
+    },
+    {
+      "epoch": 0.5795314426633785,
+      "grad_norm": 0.3590679466724396,
+      "learning_rate": 0.0002,
+      "loss": 1.174,
+      "step": 470
+    },
+    {
+      "epoch": 0.591861898890259,
+      "grad_norm": 0.5656213760375977,
+      "learning_rate": 0.0002,
+      "loss": 1.2223,
+      "step": 480
+    },
+    {
+      "epoch": 0.6041923551171393,
+      "grad_norm": 0.30830657482147217,
+      "learning_rate": 0.0002,
+      "loss": 1.1936,
+      "step": 490
+    },
+    {
+      "epoch": 0.6165228113440198,
+      "grad_norm": 0.317905455827713,
+      "learning_rate": 0.0002,
+      "loss": 1.1873,
+      "step": 500
+    },
+    {
+      "epoch": 0.6288532675709001,
+      "grad_norm": 0.3254566490650177,
+      "learning_rate": 0.0002,
+      "loss": 0.9805,
+      "step": 510
+    },
+    {
+      "epoch": 0.6411837237977805,
+      "grad_norm": 0.29187721014022827,
+      "learning_rate": 0.0002,
+      "loss": 1.0384,
+      "step": 520
+    },
+    {
+      "epoch": 0.6535141800246609,
+      "grad_norm": 0.3439238965511322,
+      "learning_rate": 0.0002,
+      "loss": 1.2526,
+      "step": 530
+    },
+    {
+      "epoch": 0.6658446362515413,
+      "grad_norm": 0.20970556139945984,
+      "learning_rate": 0.0002,
+      "loss": 1.0698,
+      "step": 540
+    },
+    {
+      "epoch": 0.6781750924784217,
+      "grad_norm": 0.4022853374481201,
+      "learning_rate": 0.0002,
+      "loss": 1.1047,
+      "step": 550
+    },
+    {
+      "epoch": 0.6905055487053021,
+      "grad_norm": 0.2235759049654007,
+      "learning_rate": 0.0002,
+      "loss": 1.0684,
+      "step": 560
+    },
+    {
+      "epoch": 0.7028360049321825,
+      "grad_norm": 0.33849895000457764,
+      "learning_rate": 0.0002,
+      "loss": 1.2339,
+      "step": 570
+    },
+    {
+      "epoch": 0.7151664611590629,
+      "grad_norm": 0.34745967388153076,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 580
+    },
+    {
+      "epoch": 0.7274969173859432,
+      "grad_norm": 0.26041269302368164,
+      "learning_rate": 0.0002,
+      "loss": 1.1158,
+      "step": 590
+    },
+    {
+      "epoch": 0.7398273736128237,
+      "grad_norm": 0.3804777264595032,
+      "learning_rate": 0.0002,
+      "loss": 1.2134,
+      "step": 600
+    },
+    {
+      "epoch": 0.752157829839704,
+      "grad_norm": 0.2456253319978714,
+      "learning_rate": 0.0002,
+      "loss": 1.0606,
+      "step": 610
+    },
+    {
+      "epoch": 0.7644882860665845,
+      "grad_norm": 0.37838423252105713,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 620
+    },
+    {
+      "epoch": 0.7768187422934648,
+      "grad_norm": 0.28105494379997253,
+      "learning_rate": 0.0002,
+      "loss": 1.0556,
+      "step": 630
+    },
+    {
+      "epoch": 0.7891491985203453,
+      "grad_norm": 0.2774018943309784,
+      "learning_rate": 0.0002,
+      "loss": 1.0672,
+      "step": 640
+    },
+    {
+      "epoch": 0.8014796547472256,
+      "grad_norm": 1.8184229135513306,
+      "learning_rate": 0.0002,
+      "loss": 0.9978,
+      "step": 650
+    },
+    {
+      "epoch": 0.813810110974106,
+      "grad_norm": 0.3325096070766449,
+      "learning_rate": 0.0002,
+      "loss": 1.1038,
+      "step": 660
+    },
+    {
+      "epoch": 0.8261405672009864,
+      "grad_norm": 0.2686693072319031,
+      "learning_rate": 0.0002,
+      "loss": 1.083,
+      "step": 670
+    },
+    {
+      "epoch": 0.8384710234278668,
+      "grad_norm": 0.3271431624889374,
+      "learning_rate": 0.0002,
+      "loss": 1.1308,
+      "step": 680
+    },
+    {
+      "epoch": 0.8508014796547472,
+      "grad_norm": 2.359999656677246,
+      "learning_rate": 0.0002,
+      "loss": 1.1116,
+      "step": 690
+    },
+    {
+      "epoch": 0.8631319358816276,
+      "grad_norm": 0.46242964267730713,
+      "learning_rate": 0.0002,
+      "loss": 1.0782,
+      "step": 700
+    },
+    {
+      "epoch": 0.8754623921085081,
+      "grad_norm": 0.34731170535087585,
+      "learning_rate": 0.0002,
+      "loss": 0.95,
+      "step": 710
+    },
+    {
+      "epoch": 0.8877928483353884,
+      "grad_norm": 0.39381715655326843,
+      "learning_rate": 0.0002,
+      "loss": 1.2236,
+      "step": 720
+    },
+    {
+      "epoch": 0.9001233045622689,
+      "grad_norm": 0.43496373295783997,
+      "learning_rate": 0.0002,
+      "loss": 1.1319,
+      "step": 730
+    },
+    {
+      "epoch": 0.9124537607891492,
+      "grad_norm": 0.32243210077285767,
+      "learning_rate": 0.0002,
+      "loss": 1.0979,
+      "step": 740
+    },
+    {
+      "epoch": 0.9247842170160296,
+      "grad_norm": 0.30396756529808044,
+      "learning_rate": 0.0002,
+      "loss": 0.9913,
+      "step": 750
+    },
+    {
+      "epoch": 0.93711467324291,
+      "grad_norm": 0.4461122751235962,
+      "learning_rate": 0.0002,
+      "loss": 1.1141,
+      "step": 760
+    },
+    {
+      "epoch": 0.9494451294697904,
+      "grad_norm": 0.24081681668758392,
+      "learning_rate": 0.0002,
+      "loss": 1.0049,
+      "step": 770
+    },
+    {
+      "epoch": 0.9617755856966708,
+      "grad_norm": 0.27461910247802734,
+      "learning_rate": 0.0002,
+      "loss": 1.0966,
+      "step": 780
+    },
+    {
+      "epoch": 0.9741060419235512,
+      "grad_norm": 0.3325668275356293,
+      "learning_rate": 0.0002,
+      "loss": 0.9942,
+      "step": 790
+    },
+    {
+      "epoch": 0.9864364981504316,
+      "grad_norm": 0.24046339094638824,
+      "learning_rate": 0.0002,
+      "loss": 1.0506,
+      "step": 800
+    },
+    {
+      "epoch": 0.998766954377312,
+      "grad_norm": 0.42950066924095154,
+      "learning_rate": 0.0002,
+      "loss": 0.9989,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.246457576751709,
+      "eval_runtime": 98.7974,
+      "eval_samples_per_second": 4.413,
+      "eval_steps_per_second": 0.557,
+      "step": 811
+    },
+    {
+      "epoch": 1.0110974106041923,
+      "grad_norm": 0.26760655641555786,
+      "learning_rate": 0.0002,
+      "loss": 1.0536,
+      "step": 820
+    },
+    {
+      "epoch": 1.0234278668310728,
+      "grad_norm": 0.4640820026397705,
+      "learning_rate": 0.0002,
+      "loss": 0.9722,
+      "step": 830
+    },
+    {
+      "epoch": 1.0357583230579532,
+      "grad_norm": 0.2699166238307953,
+      "learning_rate": 0.0002,
+      "loss": 0.9392,
+      "step": 840
+    },
+    {
+      "epoch": 1.0480887792848335,
+      "grad_norm": 0.3441709578037262,
+      "learning_rate": 0.0002,
+      "loss": 0.9335,
+      "step": 850
+    },
+    {
+      "epoch": 1.060419235511714,
+      "grad_norm": 0.299934983253479,
+      "learning_rate": 0.0002,
+      "loss": 0.9083,
+      "step": 860
+    },
+    {
+      "epoch": 1.0727496917385944,
+      "grad_norm": 0.2980666160583496,
+      "learning_rate": 0.0002,
+      "loss": 0.9416,
+      "step": 870
+    },
+    {
+      "epoch": 1.0850801479654748,
+      "grad_norm": 0.3131714463233948,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 880
+    },
+    {
+      "epoch": 1.097410604192355,
+      "grad_norm": 0.29881617426872253,
+      "learning_rate": 0.0002,
+      "loss": 0.9288,
+      "step": 890
+    },
+    {
+      "epoch": 1.1097410604192355,
+      "grad_norm": 0.29870888590812683,
+      "learning_rate": 0.0002,
+      "loss": 0.998,
+      "step": 900
+    },
+    {
+      "epoch": 1.122071516646116,
+      "grad_norm": 0.5735140442848206,
+      "learning_rate": 0.0002,
+      "loss": 0.9924,
+      "step": 910
+    },
+    {
+      "epoch": 1.1344019728729964,
+      "grad_norm": 0.33159002661705017,
+      "learning_rate": 0.0002,
+      "loss": 1.0694,
+      "step": 920
+    },
+    {
+      "epoch": 1.1467324290998766,
+      "grad_norm": 1.235399842262268,
+      "learning_rate": 0.0002,
+      "loss": 1.0069,
+      "step": 930
+    },
+    {
+      "epoch": 1.159062885326757,
+      "grad_norm": 0.27469736337661743,
+      "learning_rate": 0.0002,
+      "loss": 1.0315,
+      "step": 940
+    },
+    {
+      "epoch": 1.1713933415536375,
+      "grad_norm": 0.29130664467811584,
+      "learning_rate": 0.0002,
+      "loss": 0.9386,
+      "step": 950
+    },
+    {
+      "epoch": 1.183723797780518,
+      "grad_norm": 0.3730354607105255,
+      "learning_rate": 0.0002,
+      "loss": 0.8919,
+      "step": 960
+    },
+    {
+      "epoch": 1.1960542540073984,
+      "grad_norm": 0.5973590612411499,
+      "learning_rate": 0.0002,
+      "loss": 0.9988,
+      "step": 970
+    },
+    {
+      "epoch": 1.2083847102342786,
+      "grad_norm": 0.39631304144859314,
+      "learning_rate": 0.0002,
+      "loss": 0.9525,
+      "step": 980
+    },
+    {
+      "epoch": 1.220715166461159,
+      "grad_norm": 0.849051296710968,
+      "learning_rate": 0.0002,
+      "loss": 0.9217,
+      "step": 990
+    },
+    {
+      "epoch": 1.2330456226880395,
+      "grad_norm": 0.4390525817871094,
+      "learning_rate": 0.0002,
+      "loss": 1.0903,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2453760789149197,
+      "grad_norm": 0.30423852801322937,
+      "learning_rate": 0.0002,
+      "loss": 0.9018,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2577065351418002,
+      "grad_norm": 0.34736061096191406,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2700369913686806,
+      "grad_norm": 0.3421604037284851,
+      "learning_rate": 0.0002,
+      "loss": 0.9026,
+      "step": 1030
+    },
+    {
+      "epoch": 1.282367447595561,
+      "grad_norm": 0.544170081615448,
+      "learning_rate": 0.0002,
+      "loss": 0.8485,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2946979038224415,
+      "grad_norm": 0.5128790736198425,
+      "learning_rate": 0.0002,
+      "loss": 0.9591,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3070283600493218,
+      "grad_norm": 0.443344384431839,
+      "learning_rate": 0.0002,
+      "loss": 0.9214,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3193588162762022,
+      "grad_norm": 0.6380868554115295,
+      "learning_rate": 0.0002,
+      "loss": 0.9367,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3316892725030827,
+      "grad_norm": 0.4638073146343231,
+      "learning_rate": 0.0002,
+      "loss": 0.9849,
+      "step": 1080
+    },
+    {
+      "epoch": 1.344019728729963,
+      "grad_norm": 0.32406893372535706,
+      "learning_rate": 0.0002,
+      "loss": 0.8645,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3563501849568433,
+      "grad_norm": 0.3955065608024597,
+      "learning_rate": 0.0002,
+      "loss": 0.8278,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3686806411837238,
+      "grad_norm": 0.3489246666431427,
+      "learning_rate": 0.0002,
+      "loss": 0.9306,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3810110974106042,
+      "grad_norm": 0.48451653122901917,
+      "learning_rate": 0.0002,
+      "loss": 1.0138,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3933415536374847,
+      "grad_norm": 0.3652360439300537,
+      "learning_rate": 0.0002,
+      "loss": 0.9165,
+      "step": 1130
+    },
+    {
+      "epoch": 1.405672009864365,
+      "grad_norm": 1.3097436428070068,
+      "learning_rate": 0.0002,
+      "loss": 0.9576,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4180024660912454,
+      "grad_norm": 0.3647715449333191,
+      "learning_rate": 0.0002,
+      "loss": 0.8115,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4303329223181258,
+      "grad_norm": 0.37248560786247253,
+      "learning_rate": 0.0002,
+      "loss": 0.8573,
+      "step": 1160
+    },
+    {
+      "epoch": 1.442663378545006,
+      "grad_norm": 0.4639643430709839,
+      "learning_rate": 0.0002,
+      "loss": 0.936,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4549938347718865,
+      "grad_norm": 0.5455219745635986,
+      "learning_rate": 0.0002,
+      "loss": 0.9511,
+      "step": 1180
+    },
+    {
+      "epoch": 1.467324290998767,
+      "grad_norm": 0.38862571120262146,
+      "learning_rate": 0.0002,
+      "loss": 0.8611,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4796547472256474,
+      "grad_norm": 0.37586215138435364,
+      "learning_rate": 0.0002,
+      "loss": 0.8681,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4919852034525278,
+      "grad_norm": 0.46244436502456665,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1210
+    },
+    {
+      "epoch": 1.504315659679408,
+      "grad_norm": 0.3570359945297241,
+      "learning_rate": 0.0002,
+      "loss": 0.9388,
+      "step": 1220
+    },
+    {
+      "epoch": 1.5166461159062885,
+      "grad_norm": 0.28393083810806274,
+      "learning_rate": 0.0002,
+      "loss": 0.971,
+      "step": 1230
+    },
+    {
+      "epoch": 1.528976572133169,
+      "grad_norm": 0.5672869682312012,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5413070283600492,
+      "grad_norm": 0.41605108976364136,
+      "learning_rate": 0.0002,
+      "loss": 0.8787,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5536374845869299,
+      "grad_norm": 0.40657493472099304,
+      "learning_rate": 0.0002,
+      "loss": 0.8744,
+      "step": 1260
+    },
+    {
+      "epoch": 1.56596794081381,
+      "grad_norm": 0.43672341108322144,
+      "learning_rate": 0.0002,
+      "loss": 0.9046,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5782983970406905,
+      "grad_norm": 0.3065410554409027,
+      "learning_rate": 0.0002,
+      "loss": 0.8586,
+      "step": 1280
+    },
+    {
+      "epoch": 1.590628853267571,
+      "grad_norm": 0.37826645374298096,
+      "learning_rate": 0.0002,
+      "loss": 0.9499,
+      "step": 1290
+    },
+    {
+      "epoch": 1.6029593094944512,
+      "grad_norm": 0.42307335138320923,
+      "learning_rate": 0.0002,
+      "loss": 0.901,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6152897657213316,
+      "grad_norm": 0.3648843467235565,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1310
+    },
+    {
+      "epoch": 1.627620221948212,
+      "grad_norm": 0.8921076059341431,
+      "learning_rate": 0.0002,
+      "loss": 0.9302,
+      "step": 1320
+    },
+    {
+      "epoch": 1.6399506781750923,
+      "grad_norm": 0.37522226572036743,
+      "learning_rate": 0.0002,
+      "loss": 0.9378,
+      "step": 1330
+    },
+    {
+      "epoch": 1.652281134401973,
+      "grad_norm": 0.7489957809448242,
+      "learning_rate": 0.0002,
+      "loss": 0.8921,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6646115906288532,
+      "grad_norm": 0.31733131408691406,
+      "learning_rate": 0.0002,
+      "loss": 0.9297,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6769420468557337,
+      "grad_norm": 0.3249478340148926,
+      "learning_rate": 0.0002,
+      "loss": 0.907,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6892725030826141,
+      "grad_norm": 0.3178001344203949,
+      "learning_rate": 0.0002,
+      "loss": 1.0197,
+      "step": 1370
+    },
+    {
+      "epoch": 1.7016029593094943,
+      "grad_norm": 0.5674093961715698,
+      "learning_rate": 0.0002,
+      "loss": 1.0781,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7139334155363748,
+      "grad_norm": 0.35272449254989624,
+      "learning_rate": 0.0002,
+      "loss": 0.8972,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7262638717632552,
+      "grad_norm": 0.5778217911720276,
+      "learning_rate": 0.0002,
+      "loss": 0.9346,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7385943279901355,
+      "grad_norm": 0.33561450242996216,
+      "learning_rate": 0.0002,
+      "loss": 0.9099,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7509247842170161,
+      "grad_norm": 0.31735464930534363,
+      "learning_rate": 0.0002,
+      "loss": 0.8636,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7632552404438964,
+      "grad_norm": 1.0612670183181763,
+      "learning_rate": 0.0002,
+      "loss": 0.982,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7755856966707768,
+      "grad_norm": 0.5442509651184082,
+      "learning_rate": 0.0002,
+      "loss": 0.8224,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7879161528976573,
+      "grad_norm": 0.7471332550048828,
+      "learning_rate": 0.0002,
+      "loss": 0.9275,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8002466091245375,
+      "grad_norm": 0.4323609173297882,
+      "learning_rate": 0.0002,
+      "loss": 0.9389,
+      "step": 1460
+    },
+    {
+      "epoch": 1.8125770653514182,
+      "grad_norm": 0.47796759009361267,
+      "learning_rate": 0.0002,
+      "loss": 0.8247,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8249075215782984,
+      "grad_norm": 0.3348400592803955,
+      "learning_rate": 0.0002,
+      "loss": 0.9395,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8372379778051788,
+      "grad_norm": 0.3354550898075104,
+      "learning_rate": 0.0002,
+      "loss": 0.9793,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8495684340320593,
+      "grad_norm": 0.5988477468490601,
+      "learning_rate": 0.0002,
+      "loss": 0.8581,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8618988902589395,
+      "grad_norm": 0.5222318172454834,
+      "learning_rate": 0.0002,
+      "loss": 0.9268,
+      "step": 1510
+    },
+    {
+      "epoch": 1.87422934648582,
+      "grad_norm": 0.5246642827987671,
+      "learning_rate": 0.0002,
+      "loss": 0.8846,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8865598027127004,
+      "grad_norm": 0.3164594769477844,
+      "learning_rate": 0.0002,
+      "loss": 0.9317,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8988902589395806,
+      "grad_norm": 0.3496174216270447,
+      "learning_rate": 0.0002,
+      "loss": 0.9961,
+      "step": 1540
+    },
+    {
+      "epoch": 1.9112207151664613,
+      "grad_norm": 0.8863359689712524,
+      "learning_rate": 0.0002,
+      "loss": 0.9057,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9235511713933415,
+      "grad_norm": 0.3587026298046112,
+      "learning_rate": 0.0002,
+      "loss": 0.9405,
+      "step": 1560
+    },
+    {
+      "epoch": 1.935881627620222,
+      "grad_norm": 0.6052881479263306,
+      "learning_rate": 0.0002,
+      "loss": 0.8335,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9482120838471024,
+      "grad_norm": 0.567269504070282,
+      "learning_rate": 0.0002,
+      "loss": 0.8805,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9605425400739827,
+      "grad_norm": 0.45184487104415894,
+      "learning_rate": 0.0002,
+      "loss": 0.9581,
+      "step": 1590
+    },
+    {
+      "epoch": 1.972872996300863,
+      "grad_norm": 0.5028569102287292,
+      "learning_rate": 0.0002,
+      "loss": 0.9147,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9852034525277436,
+      "grad_norm": 0.4677547216415405,
+      "learning_rate": 0.0002,
+      "loss": 0.75,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9975339087546238,
+      "grad_norm": 0.35106056928634644,
+      "learning_rate": 0.0002,
+      "loss": 0.8469,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.238026738166809,
+      "eval_runtime": 95.4287,
+      "eval_samples_per_second": 4.569,
+      "eval_steps_per_second": 0.576,
+      "step": 1622
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6488,
+  "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": 8.331199540887552e+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-0.6-num-5885-sd-10000/checkpoint-1622/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-0.6-num-5885-sd-10000/checkpoint-1622/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..459ba5959a39ea126110113c9faed75cda19ffff
--- /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-0.6-num-5885-sd-10000/checkpoint-1622/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05287f447dfde244c1a85dc0f576593b4a9dd61961eb0797da4844688fc48447
+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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e04e4441e0c1b29f69c16b26c142944e440b8076
--- /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-0.6-num-5885-sd-10000/checkpoint-2433/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": [
+    "q_proj",
+    "v_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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..82f2dc4b3b1ab8fb339e854a201871ef3e9e02f2
--- /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-0.6-num-5885-sd-10000/checkpoint-2433/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98412178b503491fd12c8c313e08b1435a95e5943c2c6b15cbb06e57d9f25072
+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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c69255b3aad0a45315b4c32cb44a5f3b10ec2c2c
--- /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-0.6-num-5885-sd-10000/checkpoint-2433/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c7487133ca2b3ee4617865295c95819332404e64aaf4584cd360c373857d38
+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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b026e1358e6c3f0e63f43563997a3675389511b0
--- /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-0.6-num-5885-sd-10000/checkpoint-2433/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf62e9954e54ce4054ffe246197c1e5cf5ca07594c06a3d167d20fca185f2ac1
+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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1195b691dbde4fc073b7fe5c6b663876891add01
--- /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-0.6-num-5885-sd-10000/checkpoint-2433/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd9f5f69932f2af95a428f4d1e97bce98fdafea6df5245c7b87d7819fd124b6
+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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22
--- /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-0.6-num-5885-sd-10000/checkpoint-2433/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873
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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..86e51f628a0582d9d73e4b71162b9d76a39b3a3a
--- /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-0.6-num-5885-sd-10000/checkpoint-2433/trainer_state.json
@@ -0,0 +1,1758 @@
+{
+  "best_metric": 1.238026738166809,
+  "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-0.6-num-5885-sd-10000/checkpoint-1622",
+  "epoch": 3.0,
+  "eval_steps": 10,
+  "global_step": 2433,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012330456226880395,
+      "grad_norm": 0.8258164525032043,
+      "learning_rate": 0.0002,
+      "loss": 2.3601,
+      "step": 10
+    },
+    {
+      "epoch": 0.02466091245376079,
+      "grad_norm": 0.4577729105949402,
+      "learning_rate": 0.0002,
+      "loss": 1.7317,
+      "step": 20
+    },
+    {
+      "epoch": 0.036991368680641186,
+      "grad_norm": 0.639807939529419,
+      "learning_rate": 0.0002,
+      "loss": 1.4729,
+      "step": 30
+    },
+    {
+      "epoch": 0.04932182490752158,
+      "grad_norm": 0.5311757922172546,
+      "learning_rate": 0.0002,
+      "loss": 1.2088,
+      "step": 40
+    },
+    {
+      "epoch": 0.06165228113440197,
+      "grad_norm": 0.386595219373703,
+      "learning_rate": 0.0002,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.07398273736128237,
+      "grad_norm": 0.4401357173919678,
+      "learning_rate": 0.0002,
+      "loss": 1.1657,
+      "step": 60
+    },
+    {
+      "epoch": 0.08631319358816276,
+      "grad_norm": 0.3234352171421051,
+      "learning_rate": 0.0002,
+      "loss": 1.1022,
+      "step": 70
+    },
+    {
+      "epoch": 0.09864364981504316,
+      "grad_norm": 0.29643672704696655,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 80
+    },
+    {
+      "epoch": 0.11097410604192355,
+      "grad_norm": 0.2941012382507324,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 90
+    },
+    {
+      "epoch": 0.12330456226880394,
+      "grad_norm": 0.5498173832893372,
+      "learning_rate": 0.0002,
+      "loss": 1.2067,
+      "step": 100
+    },
+    {
+      "epoch": 0.13563501849568435,
+      "grad_norm": 0.2545783519744873,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 110
+    },
+    {
+      "epoch": 0.14796547472256474,
+      "grad_norm": 0.2984241247177124,
+      "learning_rate": 0.0002,
+      "loss": 1.0297,
+      "step": 120
+    },
+    {
+      "epoch": 0.16029593094944514,
+      "grad_norm": 0.2710968852043152,
+      "learning_rate": 0.0002,
+      "loss": 1.1591,
+      "step": 130
+    },
+    {
+      "epoch": 0.17262638717632553,
+      "grad_norm": 0.2817152142524719,
+      "learning_rate": 0.0002,
+      "loss": 1.0427,
+      "step": 140
+    },
+    {
+      "epoch": 0.18495684340320592,
+      "grad_norm": 0.41083765029907227,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 150
+    },
+    {
+      "epoch": 0.19728729963008632,
+      "grad_norm": 0.36536213755607605,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 160
+    },
+    {
+      "epoch": 0.2096177558569667,
+      "grad_norm": 0.2738671600818634,
+      "learning_rate": 0.0002,
+      "loss": 1.0132,
+      "step": 170
+    },
+    {
+      "epoch": 0.2219482120838471,
+      "grad_norm": 0.27403146028518677,
+      "learning_rate": 0.0002,
+      "loss": 0.9555,
+      "step": 180
+    },
+    {
+      "epoch": 0.2342786683107275,
+      "grad_norm": 0.4446810483932495,
+      "learning_rate": 0.0002,
+      "loss": 1.0769,
+      "step": 190
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "grad_norm": 0.5295385718345642,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 200
+    },
+    {
+      "epoch": 0.2589395807644883,
+      "grad_norm": 0.311404824256897,
+      "learning_rate": 0.0002,
+      "loss": 1.0827,
+      "step": 210
+    },
+    {
+      "epoch": 0.2712700369913687,
+      "grad_norm": 0.2448509782552719,
+      "learning_rate": 0.0002,
+      "loss": 1.1455,
+      "step": 220
+    },
+    {
+      "epoch": 0.2836004932182491,
+      "grad_norm": 0.6507014036178589,
+      "learning_rate": 0.0002,
+      "loss": 1.0929,
+      "step": 230
+    },
+    {
+      "epoch": 0.2959309494451295,
+      "grad_norm": 0.2339320331811905,
+      "learning_rate": 0.0002,
+      "loss": 0.9875,
+      "step": 240
+    },
+    {
+      "epoch": 0.3082614056720099,
+      "grad_norm": 0.8210226893424988,
+      "learning_rate": 0.0002,
+      "loss": 0.9211,
+      "step": 250
+    },
+    {
+      "epoch": 0.3205918618988903,
+      "grad_norm": 0.27473965287208557,
+      "learning_rate": 0.0002,
+      "loss": 1.161,
+      "step": 260
+    },
+    {
+      "epoch": 0.33292231812577067,
+      "grad_norm": 0.3051395118236542,
+      "learning_rate": 0.0002,
+      "loss": 1.0218,
+      "step": 270
+    },
+    {
+      "epoch": 0.34525277435265106,
+      "grad_norm": 0.3037777245044708,
+      "learning_rate": 0.0002,
+      "loss": 1.0286,
+      "step": 280
+    },
+    {
+      "epoch": 0.35758323057953145,
+      "grad_norm": 0.2748974859714508,
+      "learning_rate": 0.0002,
+      "loss": 1.144,
+      "step": 290
+    },
+    {
+      "epoch": 0.36991368680641185,
+      "grad_norm": 0.23656068742275238,
+      "learning_rate": 0.0002,
+      "loss": 1.0858,
+      "step": 300
+    },
+    {
+      "epoch": 0.38224414303329224,
+      "grad_norm": 0.2523384094238281,
+      "learning_rate": 0.0002,
+      "loss": 1.0564,
+      "step": 310
+    },
+    {
+      "epoch": 0.39457459926017263,
+      "grad_norm": 0.27848055958747864,
+      "learning_rate": 0.0002,
+      "loss": 1.3091,
+      "step": 320
+    },
+    {
+      "epoch": 0.406905055487053,
+      "grad_norm": 0.3204525411128998,
+      "learning_rate": 0.0002,
+      "loss": 1.0252,
+      "step": 330
+    },
+    {
+      "epoch": 0.4192355117139334,
+      "grad_norm": 0.3459707498550415,
+      "learning_rate": 0.0002,
+      "loss": 0.9855,
+      "step": 340
+    },
+    {
+      "epoch": 0.4315659679408138,
+      "grad_norm": 0.2458430379629135,
+      "learning_rate": 0.0002,
+      "loss": 1.1111,
+      "step": 350
+    },
+    {
+      "epoch": 0.4438964241676942,
+      "grad_norm": 0.5022910237312317,
+      "learning_rate": 0.0002,
+      "loss": 1.1493,
+      "step": 360
+    },
+    {
+      "epoch": 0.4562268803945746,
+      "grad_norm": 0.27076372504234314,
+      "learning_rate": 0.0002,
+      "loss": 1.1272,
+      "step": 370
+    },
+    {
+      "epoch": 0.468557336621455,
+      "grad_norm": 0.6489047408103943,
+      "learning_rate": 0.0002,
+      "loss": 1.1927,
+      "step": 380
+    },
+    {
+      "epoch": 0.4808877928483354,
+      "grad_norm": 0.3324144184589386,
+      "learning_rate": 0.0002,
+      "loss": 0.9501,
+      "step": 390
+    },
+    {
+      "epoch": 0.4932182490752158,
+      "grad_norm": 0.32813116908073425,
+      "learning_rate": 0.0002,
+      "loss": 1.2012,
+      "step": 400
+    },
+    {
+      "epoch": 0.5055487053020962,
+      "grad_norm": 0.25295355916023254,
+      "learning_rate": 0.0002,
+      "loss": 1.1135,
+      "step": 410
+    },
+    {
+      "epoch": 0.5178791615289766,
+      "grad_norm": 0.2912578880786896,
+      "learning_rate": 0.0002,
+      "loss": 0.9477,
+      "step": 420
+    },
+    {
+      "epoch": 0.530209617755857,
+      "grad_norm": 0.34780189394950867,
+      "learning_rate": 0.0002,
+      "loss": 1.0121,
+      "step": 430
+    },
+    {
+      "epoch": 0.5425400739827374,
+      "grad_norm": 0.24604526162147522,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 440
+    },
+    {
+      "epoch": 0.5548705302096177,
+      "grad_norm": 0.32759982347488403,
+      "learning_rate": 0.0002,
+      "loss": 1.253,
+      "step": 450
+    },
+    {
+      "epoch": 0.5672009864364982,
+      "grad_norm": 0.40810221433639526,
+      "learning_rate": 0.0002,
+      "loss": 1.1925,
+      "step": 460
+    },
+    {
+      "epoch": 0.5795314426633785,
+      "grad_norm": 0.3590679466724396,
+      "learning_rate": 0.0002,
+      "loss": 1.174,
+      "step": 470
+    },
+    {
+      "epoch": 0.591861898890259,
+      "grad_norm": 0.5656213760375977,
+      "learning_rate": 0.0002,
+      "loss": 1.2223,
+      "step": 480
+    },
+    {
+      "epoch": 0.6041923551171393,
+      "grad_norm": 0.30830657482147217,
+      "learning_rate": 0.0002,
+      "loss": 1.1936,
+      "step": 490
+    },
+    {
+      "epoch": 0.6165228113440198,
+      "grad_norm": 0.317905455827713,
+      "learning_rate": 0.0002,
+      "loss": 1.1873,
+      "step": 500
+    },
+    {
+      "epoch": 0.6288532675709001,
+      "grad_norm": 0.3254566490650177,
+      "learning_rate": 0.0002,
+      "loss": 0.9805,
+      "step": 510
+    },
+    {
+      "epoch": 0.6411837237977805,
+      "grad_norm": 0.29187721014022827,
+      "learning_rate": 0.0002,
+      "loss": 1.0384,
+      "step": 520
+    },
+    {
+      "epoch": 0.6535141800246609,
+      "grad_norm": 0.3439238965511322,
+      "learning_rate": 0.0002,
+      "loss": 1.2526,
+      "step": 530
+    },
+    {
+      "epoch": 0.6658446362515413,
+      "grad_norm": 0.20970556139945984,
+      "learning_rate": 0.0002,
+      "loss": 1.0698,
+      "step": 540
+    },
+    {
+      "epoch": 0.6781750924784217,
+      "grad_norm": 0.4022853374481201,
+      "learning_rate": 0.0002,
+      "loss": 1.1047,
+      "step": 550
+    },
+    {
+      "epoch": 0.6905055487053021,
+      "grad_norm": 0.2235759049654007,
+      "learning_rate": 0.0002,
+      "loss": 1.0684,
+      "step": 560
+    },
+    {
+      "epoch": 0.7028360049321825,
+      "grad_norm": 0.33849895000457764,
+      "learning_rate": 0.0002,
+      "loss": 1.2339,
+      "step": 570
+    },
+    {
+      "epoch": 0.7151664611590629,
+      "grad_norm": 0.34745967388153076,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 580
+    },
+    {
+      "epoch": 0.7274969173859432,
+      "grad_norm": 0.26041269302368164,
+      "learning_rate": 0.0002,
+      "loss": 1.1158,
+      "step": 590
+    },
+    {
+      "epoch": 0.7398273736128237,
+      "grad_norm": 0.3804777264595032,
+      "learning_rate": 0.0002,
+      "loss": 1.2134,
+      "step": 600
+    },
+    {
+      "epoch": 0.752157829839704,
+      "grad_norm": 0.2456253319978714,
+      "learning_rate": 0.0002,
+      "loss": 1.0606,
+      "step": 610
+    },
+    {
+      "epoch": 0.7644882860665845,
+      "grad_norm": 0.37838423252105713,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 620
+    },
+    {
+      "epoch": 0.7768187422934648,
+      "grad_norm": 0.28105494379997253,
+      "learning_rate": 0.0002,
+      "loss": 1.0556,
+      "step": 630
+    },
+    {
+      "epoch": 0.7891491985203453,
+      "grad_norm": 0.2774018943309784,
+      "learning_rate": 0.0002,
+      "loss": 1.0672,
+      "step": 640
+    },
+    {
+      "epoch": 0.8014796547472256,
+      "grad_norm": 1.8184229135513306,
+      "learning_rate": 0.0002,
+      "loss": 0.9978,
+      "step": 650
+    },
+    {
+      "epoch": 0.813810110974106,
+      "grad_norm": 0.3325096070766449,
+      "learning_rate": 0.0002,
+      "loss": 1.1038,
+      "step": 660
+    },
+    {
+      "epoch": 0.8261405672009864,
+      "grad_norm": 0.2686693072319031,
+      "learning_rate": 0.0002,
+      "loss": 1.083,
+      "step": 670
+    },
+    {
+      "epoch": 0.8384710234278668,
+      "grad_norm": 0.3271431624889374,
+      "learning_rate": 0.0002,
+      "loss": 1.1308,
+      "step": 680
+    },
+    {
+      "epoch": 0.8508014796547472,
+      "grad_norm": 2.359999656677246,
+      "learning_rate": 0.0002,
+      "loss": 1.1116,
+      "step": 690
+    },
+    {
+      "epoch": 0.8631319358816276,
+      "grad_norm": 0.46242964267730713,
+      "learning_rate": 0.0002,
+      "loss": 1.0782,
+      "step": 700
+    },
+    {
+      "epoch": 0.8754623921085081,
+      "grad_norm": 0.34731170535087585,
+      "learning_rate": 0.0002,
+      "loss": 0.95,
+      "step": 710
+    },
+    {
+      "epoch": 0.8877928483353884,
+      "grad_norm": 0.39381715655326843,
+      "learning_rate": 0.0002,
+      "loss": 1.2236,
+      "step": 720
+    },
+    {
+      "epoch": 0.9001233045622689,
+      "grad_norm": 0.43496373295783997,
+      "learning_rate": 0.0002,
+      "loss": 1.1319,
+      "step": 730
+    },
+    {
+      "epoch": 0.9124537607891492,
+      "grad_norm": 0.32243210077285767,
+      "learning_rate": 0.0002,
+      "loss": 1.0979,
+      "step": 740
+    },
+    {
+      "epoch": 0.9247842170160296,
+      "grad_norm": 0.30396756529808044,
+      "learning_rate": 0.0002,
+      "loss": 0.9913,
+      "step": 750
+    },
+    {
+      "epoch": 0.93711467324291,
+      "grad_norm": 0.4461122751235962,
+      "learning_rate": 0.0002,
+      "loss": 1.1141,
+      "step": 760
+    },
+    {
+      "epoch": 0.9494451294697904,
+      "grad_norm": 0.24081681668758392,
+      "learning_rate": 0.0002,
+      "loss": 1.0049,
+      "step": 770
+    },
+    {
+      "epoch": 0.9617755856966708,
+      "grad_norm": 0.27461910247802734,
+      "learning_rate": 0.0002,
+      "loss": 1.0966,
+      "step": 780
+    },
+    {
+      "epoch": 0.9741060419235512,
+      "grad_norm": 0.3325668275356293,
+      "learning_rate": 0.0002,
+      "loss": 0.9942,
+      "step": 790
+    },
+    {
+      "epoch": 0.9864364981504316,
+      "grad_norm": 0.24046339094638824,
+      "learning_rate": 0.0002,
+      "loss": 1.0506,
+      "step": 800
+    },
+    {
+      "epoch": 0.998766954377312,
+      "grad_norm": 0.42950066924095154,
+      "learning_rate": 0.0002,
+      "loss": 0.9989,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.246457576751709,
+      "eval_runtime": 98.7974,
+      "eval_samples_per_second": 4.413,
+      "eval_steps_per_second": 0.557,
+      "step": 811
+    },
+    {
+      "epoch": 1.0110974106041923,
+      "grad_norm": 0.26760655641555786,
+      "learning_rate": 0.0002,
+      "loss": 1.0536,
+      "step": 820
+    },
+    {
+      "epoch": 1.0234278668310728,
+      "grad_norm": 0.4640820026397705,
+      "learning_rate": 0.0002,
+      "loss": 0.9722,
+      "step": 830
+    },
+    {
+      "epoch": 1.0357583230579532,
+      "grad_norm": 0.2699166238307953,
+      "learning_rate": 0.0002,
+      "loss": 0.9392,
+      "step": 840
+    },
+    {
+      "epoch": 1.0480887792848335,
+      "grad_norm": 0.3441709578037262,
+      "learning_rate": 0.0002,
+      "loss": 0.9335,
+      "step": 850
+    },
+    {
+      "epoch": 1.060419235511714,
+      "grad_norm": 0.299934983253479,
+      "learning_rate": 0.0002,
+      "loss": 0.9083,
+      "step": 860
+    },
+    {
+      "epoch": 1.0727496917385944,
+      "grad_norm": 0.2980666160583496,
+      "learning_rate": 0.0002,
+      "loss": 0.9416,
+      "step": 870
+    },
+    {
+      "epoch": 1.0850801479654748,
+      "grad_norm": 0.3131714463233948,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 880
+    },
+    {
+      "epoch": 1.097410604192355,
+      "grad_norm": 0.29881617426872253,
+      "learning_rate": 0.0002,
+      "loss": 0.9288,
+      "step": 890
+    },
+    {
+      "epoch": 1.1097410604192355,
+      "grad_norm": 0.29870888590812683,
+      "learning_rate": 0.0002,
+      "loss": 0.998,
+      "step": 900
+    },
+    {
+      "epoch": 1.122071516646116,
+      "grad_norm": 0.5735140442848206,
+      "learning_rate": 0.0002,
+      "loss": 0.9924,
+      "step": 910
+    },
+    {
+      "epoch": 1.1344019728729964,
+      "grad_norm": 0.33159002661705017,
+      "learning_rate": 0.0002,
+      "loss": 1.0694,
+      "step": 920
+    },
+    {
+      "epoch": 1.1467324290998766,
+      "grad_norm": 1.235399842262268,
+      "learning_rate": 0.0002,
+      "loss": 1.0069,
+      "step": 930
+    },
+    {
+      "epoch": 1.159062885326757,
+      "grad_norm": 0.27469736337661743,
+      "learning_rate": 0.0002,
+      "loss": 1.0315,
+      "step": 940
+    },
+    {
+      "epoch": 1.1713933415536375,
+      "grad_norm": 0.29130664467811584,
+      "learning_rate": 0.0002,
+      "loss": 0.9386,
+      "step": 950
+    },
+    {
+      "epoch": 1.183723797780518,
+      "grad_norm": 0.3730354607105255,
+      "learning_rate": 0.0002,
+      "loss": 0.8919,
+      "step": 960
+    },
+    {
+      "epoch": 1.1960542540073984,
+      "grad_norm": 0.5973590612411499,
+      "learning_rate": 0.0002,
+      "loss": 0.9988,
+      "step": 970
+    },
+    {
+      "epoch": 1.2083847102342786,
+      "grad_norm": 0.39631304144859314,
+      "learning_rate": 0.0002,
+      "loss": 0.9525,
+      "step": 980
+    },
+    {
+      "epoch": 1.220715166461159,
+      "grad_norm": 0.849051296710968,
+      "learning_rate": 0.0002,
+      "loss": 0.9217,
+      "step": 990
+    },
+    {
+      "epoch": 1.2330456226880395,
+      "grad_norm": 0.4390525817871094,
+      "learning_rate": 0.0002,
+      "loss": 1.0903,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2453760789149197,
+      "grad_norm": 0.30423852801322937,
+      "learning_rate": 0.0002,
+      "loss": 0.9018,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2577065351418002,
+      "grad_norm": 0.34736061096191406,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2700369913686806,
+      "grad_norm": 0.3421604037284851,
+      "learning_rate": 0.0002,
+      "loss": 0.9026,
+      "step": 1030
+    },
+    {
+      "epoch": 1.282367447595561,
+      "grad_norm": 0.544170081615448,
+      "learning_rate": 0.0002,
+      "loss": 0.8485,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2946979038224415,
+      "grad_norm": 0.5128790736198425,
+      "learning_rate": 0.0002,
+      "loss": 0.9591,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3070283600493218,
+      "grad_norm": 0.443344384431839,
+      "learning_rate": 0.0002,
+      "loss": 0.9214,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3193588162762022,
+      "grad_norm": 0.6380868554115295,
+      "learning_rate": 0.0002,
+      "loss": 0.9367,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3316892725030827,
+      "grad_norm": 0.4638073146343231,
+      "learning_rate": 0.0002,
+      "loss": 0.9849,
+      "step": 1080
+    },
+    {
+      "epoch": 1.344019728729963,
+      "grad_norm": 0.32406893372535706,
+      "learning_rate": 0.0002,
+      "loss": 0.8645,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3563501849568433,
+      "grad_norm": 0.3955065608024597,
+      "learning_rate": 0.0002,
+      "loss": 0.8278,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3686806411837238,
+      "grad_norm": 0.3489246666431427,
+      "learning_rate": 0.0002,
+      "loss": 0.9306,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3810110974106042,
+      "grad_norm": 0.48451653122901917,
+      "learning_rate": 0.0002,
+      "loss": 1.0138,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3933415536374847,
+      "grad_norm": 0.3652360439300537,
+      "learning_rate": 0.0002,
+      "loss": 0.9165,
+      "step": 1130
+    },
+    {
+      "epoch": 1.405672009864365,
+      "grad_norm": 1.3097436428070068,
+      "learning_rate": 0.0002,
+      "loss": 0.9576,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4180024660912454,
+      "grad_norm": 0.3647715449333191,
+      "learning_rate": 0.0002,
+      "loss": 0.8115,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4303329223181258,
+      "grad_norm": 0.37248560786247253,
+      "learning_rate": 0.0002,
+      "loss": 0.8573,
+      "step": 1160
+    },
+    {
+      "epoch": 1.442663378545006,
+      "grad_norm": 0.4639643430709839,
+      "learning_rate": 0.0002,
+      "loss": 0.936,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4549938347718865,
+      "grad_norm": 0.5455219745635986,
+      "learning_rate": 0.0002,
+      "loss": 0.9511,
+      "step": 1180
+    },
+    {
+      "epoch": 1.467324290998767,
+      "grad_norm": 0.38862571120262146,
+      "learning_rate": 0.0002,
+      "loss": 0.8611,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4796547472256474,
+      "grad_norm": 0.37586215138435364,
+      "learning_rate": 0.0002,
+      "loss": 0.8681,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4919852034525278,
+      "grad_norm": 0.46244436502456665,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1210
+    },
+    {
+      "epoch": 1.504315659679408,
+      "grad_norm": 0.3570359945297241,
+      "learning_rate": 0.0002,
+      "loss": 0.9388,
+      "step": 1220
+    },
+    {
+      "epoch": 1.5166461159062885,
+      "grad_norm": 0.28393083810806274,
+      "learning_rate": 0.0002,
+      "loss": 0.971,
+      "step": 1230
+    },
+    {
+      "epoch": 1.528976572133169,
+      "grad_norm": 0.5672869682312012,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5413070283600492,
+      "grad_norm": 0.41605108976364136,
+      "learning_rate": 0.0002,
+      "loss": 0.8787,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5536374845869299,
+      "grad_norm": 0.40657493472099304,
+      "learning_rate": 0.0002,
+      "loss": 0.8744,
+      "step": 1260
+    },
+    {
+      "epoch": 1.56596794081381,
+      "grad_norm": 0.43672341108322144,
+      "learning_rate": 0.0002,
+      "loss": 0.9046,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5782983970406905,
+      "grad_norm": 0.3065410554409027,
+      "learning_rate": 0.0002,
+      "loss": 0.8586,
+      "step": 1280
+    },
+    {
+      "epoch": 1.590628853267571,
+      "grad_norm": 0.37826645374298096,
+      "learning_rate": 0.0002,
+      "loss": 0.9499,
+      "step": 1290
+    },
+    {
+      "epoch": 1.6029593094944512,
+      "grad_norm": 0.42307335138320923,
+      "learning_rate": 0.0002,
+      "loss": 0.901,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6152897657213316,
+      "grad_norm": 0.3648843467235565,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1310
+    },
+    {
+      "epoch": 1.627620221948212,
+      "grad_norm": 0.8921076059341431,
+      "learning_rate": 0.0002,
+      "loss": 0.9302,
+      "step": 1320
+    },
+    {
+      "epoch": 1.6399506781750923,
+      "grad_norm": 0.37522226572036743,
+      "learning_rate": 0.0002,
+      "loss": 0.9378,
+      "step": 1330
+    },
+    {
+      "epoch": 1.652281134401973,
+      "grad_norm": 0.7489957809448242,
+      "learning_rate": 0.0002,
+      "loss": 0.8921,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6646115906288532,
+      "grad_norm": 0.31733131408691406,
+      "learning_rate": 0.0002,
+      "loss": 0.9297,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6769420468557337,
+      "grad_norm": 0.3249478340148926,
+      "learning_rate": 0.0002,
+      "loss": 0.907,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6892725030826141,
+      "grad_norm": 0.3178001344203949,
+      "learning_rate": 0.0002,
+      "loss": 1.0197,
+      "step": 1370
+    },
+    {
+      "epoch": 1.7016029593094943,
+      "grad_norm": 0.5674093961715698,
+      "learning_rate": 0.0002,
+      "loss": 1.0781,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7139334155363748,
+      "grad_norm": 0.35272449254989624,
+      "learning_rate": 0.0002,
+      "loss": 0.8972,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7262638717632552,
+      "grad_norm": 0.5778217911720276,
+      "learning_rate": 0.0002,
+      "loss": 0.9346,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7385943279901355,
+      "grad_norm": 0.33561450242996216,
+      "learning_rate": 0.0002,
+      "loss": 0.9099,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7509247842170161,
+      "grad_norm": 0.31735464930534363,
+      "learning_rate": 0.0002,
+      "loss": 0.8636,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7632552404438964,
+      "grad_norm": 1.0612670183181763,
+      "learning_rate": 0.0002,
+      "loss": 0.982,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7755856966707768,
+      "grad_norm": 0.5442509651184082,
+      "learning_rate": 0.0002,
+      "loss": 0.8224,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7879161528976573,
+      "grad_norm": 0.7471332550048828,
+      "learning_rate": 0.0002,
+      "loss": 0.9275,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8002466091245375,
+      "grad_norm": 0.4323609173297882,
+      "learning_rate": 0.0002,
+      "loss": 0.9389,
+      "step": 1460
+    },
+    {
+      "epoch": 1.8125770653514182,
+      "grad_norm": 0.47796759009361267,
+      "learning_rate": 0.0002,
+      "loss": 0.8247,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8249075215782984,
+      "grad_norm": 0.3348400592803955,
+      "learning_rate": 0.0002,
+      "loss": 0.9395,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8372379778051788,
+      "grad_norm": 0.3354550898075104,
+      "learning_rate": 0.0002,
+      "loss": 0.9793,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8495684340320593,
+      "grad_norm": 0.5988477468490601,
+      "learning_rate": 0.0002,
+      "loss": 0.8581,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8618988902589395,
+      "grad_norm": 0.5222318172454834,
+      "learning_rate": 0.0002,
+      "loss": 0.9268,
+      "step": 1510
+    },
+    {
+      "epoch": 1.87422934648582,
+      "grad_norm": 0.5246642827987671,
+      "learning_rate": 0.0002,
+      "loss": 0.8846,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8865598027127004,
+      "grad_norm": 0.3164594769477844,
+      "learning_rate": 0.0002,
+      "loss": 0.9317,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8988902589395806,
+      "grad_norm": 0.3496174216270447,
+      "learning_rate": 0.0002,
+      "loss": 0.9961,
+      "step": 1540
+    },
+    {
+      "epoch": 1.9112207151664613,
+      "grad_norm": 0.8863359689712524,
+      "learning_rate": 0.0002,
+      "loss": 0.9057,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9235511713933415,
+      "grad_norm": 0.3587026298046112,
+      "learning_rate": 0.0002,
+      "loss": 0.9405,
+      "step": 1560
+    },
+    {
+      "epoch": 1.935881627620222,
+      "grad_norm": 0.6052881479263306,
+      "learning_rate": 0.0002,
+      "loss": 0.8335,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9482120838471024,
+      "grad_norm": 0.567269504070282,
+      "learning_rate": 0.0002,
+      "loss": 0.8805,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9605425400739827,
+      "grad_norm": 0.45184487104415894,
+      "learning_rate": 0.0002,
+      "loss": 0.9581,
+      "step": 1590
+    },
+    {
+      "epoch": 1.972872996300863,
+      "grad_norm": 0.5028569102287292,
+      "learning_rate": 0.0002,
+      "loss": 0.9147,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9852034525277436,
+      "grad_norm": 0.4677547216415405,
+      "learning_rate": 0.0002,
+      "loss": 0.75,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9975339087546238,
+      "grad_norm": 0.35106056928634644,
+      "learning_rate": 0.0002,
+      "loss": 0.8469,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.238026738166809,
+      "eval_runtime": 95.4287,
+      "eval_samples_per_second": 4.569,
+      "eval_steps_per_second": 0.576,
+      "step": 1622
+    },
+    {
+      "epoch": 2.0098643649815044,
+      "grad_norm": 0.444060355424881,
+      "learning_rate": 0.0002,
+      "loss": 0.7629,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0221948212083847,
+      "grad_norm": 0.627570390701294,
+      "learning_rate": 0.0002,
+      "loss": 0.772,
+      "step": 1640
+    },
+    {
+      "epoch": 2.034525277435265,
+      "grad_norm": 0.38737839460372925,
+      "learning_rate": 0.0002,
+      "loss": 0.6186,
+      "step": 1650
+    },
+    {
+      "epoch": 2.0468557336621456,
+      "grad_norm": 0.4300459623336792,
+      "learning_rate": 0.0002,
+      "loss": 0.7734,
+      "step": 1660
+    },
+    {
+      "epoch": 2.059186189889026,
+      "grad_norm": 0.43037715554237366,
+      "learning_rate": 0.0002,
+      "loss": 0.6943,
+      "step": 1670
+    },
+    {
+      "epoch": 2.0715166461159065,
+      "grad_norm": 0.40772515535354614,
+      "learning_rate": 0.0002,
+      "loss": 0.6588,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0838471023427867,
+      "grad_norm": 0.5295451879501343,
+      "learning_rate": 0.0002,
+      "loss": 0.8105,
+      "step": 1690
+    },
+    {
+      "epoch": 2.096177558569667,
+      "grad_norm": 0.7452750205993652,
+      "learning_rate": 0.0002,
+      "loss": 0.7717,
+      "step": 1700
+    },
+    {
+      "epoch": 2.1085080147965476,
+      "grad_norm": 0.809183657169342,
+      "learning_rate": 0.0002,
+      "loss": 0.7458,
+      "step": 1710
+    },
+    {
+      "epoch": 2.120838471023428,
+      "grad_norm": 0.4597688913345337,
+      "learning_rate": 0.0002,
+      "loss": 0.7398,
+      "step": 1720
+    },
+    {
+      "epoch": 2.133168927250308,
+      "grad_norm": 0.806919276714325,
+      "learning_rate": 0.0002,
+      "loss": 0.6856,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1454993834771887,
+      "grad_norm": 0.3755643665790558,
+      "learning_rate": 0.0002,
+      "loss": 0.679,
+      "step": 1740
+    },
+    {
+      "epoch": 2.157829839704069,
+      "grad_norm": 0.5882734060287476,
+      "learning_rate": 0.0002,
+      "loss": 0.7938,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1701602959309496,
+      "grad_norm": 0.692960798740387,
+      "learning_rate": 0.0002,
+      "loss": 0.6782,
+      "step": 1760
+    },
+    {
+      "epoch": 2.18249075215783,
+      "grad_norm": 0.4737096428871155,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 1770
+    },
+    {
+      "epoch": 2.19482120838471,
+      "grad_norm": 0.6637021899223328,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 1780
+    },
+    {
+      "epoch": 2.2071516646115907,
+      "grad_norm": 0.9109764099121094,
+      "learning_rate": 0.0002,
+      "loss": 0.7139,
+      "step": 1790
+    },
+    {
+      "epoch": 2.219482120838471,
+      "grad_norm": 0.4137539267539978,
+      "learning_rate": 0.0002,
+      "loss": 0.7373,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2318125770653516,
+      "grad_norm": 0.44995415210723877,
+      "learning_rate": 0.0002,
+      "loss": 0.7266,
+      "step": 1810
+    },
+    {
+      "epoch": 2.244143033292232,
+      "grad_norm": 0.5985036492347717,
+      "learning_rate": 0.0002,
+      "loss": 0.7663,
+      "step": 1820
+    },
+    {
+      "epoch": 2.256473489519112,
+      "grad_norm": 0.7549490332603455,
+      "learning_rate": 0.0002,
+      "loss": 0.7502,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2688039457459928,
+      "grad_norm": 0.4490937888622284,
+      "learning_rate": 0.0002,
+      "loss": 0.7452,
+      "step": 1840
+    },
+    {
+      "epoch": 2.281134401972873,
+      "grad_norm": 0.38859808444976807,
+      "learning_rate": 0.0002,
+      "loss": 0.7531,
+      "step": 1850
+    },
+    {
+      "epoch": 2.293464858199753,
+      "grad_norm": 1.0704916715621948,
+      "learning_rate": 0.0002,
+      "loss": 0.7278,
+      "step": 1860
+    },
+    {
+      "epoch": 2.305795314426634,
+      "grad_norm": 0.4647100865840912,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 1870
+    },
+    {
+      "epoch": 2.318125770653514,
+      "grad_norm": 0.6181163787841797,
+      "learning_rate": 0.0002,
+      "loss": 0.7146,
+      "step": 1880
+    },
+    {
+      "epoch": 2.3304562268803943,
+      "grad_norm": 0.9241904020309448,
+      "learning_rate": 0.0002,
+      "loss": 0.7689,
+      "step": 1890
+    },
+    {
+      "epoch": 2.342786683107275,
+      "grad_norm": 0.39101317524909973,
+      "learning_rate": 0.0002,
+      "loss": 0.7294,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3551171393341552,
+      "grad_norm": 0.49442458152770996,
+      "learning_rate": 0.0002,
+      "loss": 0.7079,
+      "step": 1910
+    },
+    {
+      "epoch": 2.367447595561036,
+      "grad_norm": 0.4864824414253235,
+      "learning_rate": 0.0002,
+      "loss": 0.7586,
+      "step": 1920
+    },
+    {
+      "epoch": 2.379778051787916,
+      "grad_norm": 0.5427613854408264,
+      "learning_rate": 0.0002,
+      "loss": 0.7434,
+      "step": 1930
+    },
+    {
+      "epoch": 2.392108508014797,
+      "grad_norm": 0.7164974808692932,
+      "learning_rate": 0.0002,
+      "loss": 0.8423,
+      "step": 1940
+    },
+    {
+      "epoch": 2.404438964241677,
+      "grad_norm": 0.562979519367218,
+      "learning_rate": 0.0002,
+      "loss": 0.6888,
+      "step": 1950
+    },
+    {
+      "epoch": 2.4167694204685573,
+      "grad_norm": 0.5631861090660095,
+      "learning_rate": 0.0002,
+      "loss": 0.7692,
+      "step": 1960
+    },
+    {
+      "epoch": 2.429099876695438,
+      "grad_norm": 0.4895121157169342,
+      "learning_rate": 0.0002,
+      "loss": 0.67,
+      "step": 1970
+    },
+    {
+      "epoch": 2.441430332922318,
+      "grad_norm": 0.45674824714660645,
+      "learning_rate": 0.0002,
+      "loss": 0.7735,
+      "step": 1980
+    },
+    {
+      "epoch": 2.4537607891491984,
+      "grad_norm": 1.1424206495285034,
+      "learning_rate": 0.0002,
+      "loss": 0.685,
+      "step": 1990
+    },
+    {
+      "epoch": 2.466091245376079,
+      "grad_norm": 0.6314579844474792,
+      "learning_rate": 0.0002,
+      "loss": 0.7627,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4784217016029593,
+      "grad_norm": 0.5481605529785156,
+      "learning_rate": 0.0002,
+      "loss": 0.7118,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4907521578298395,
+      "grad_norm": 0.4671579599380493,
+      "learning_rate": 0.0002,
+      "loss": 0.6947,
+      "step": 2020
+    },
+    {
+      "epoch": 2.50308261405672,
+      "grad_norm": 0.7621194124221802,
+      "learning_rate": 0.0002,
+      "loss": 0.7377,
+      "step": 2030
+    },
+    {
+      "epoch": 2.5154130702836004,
+      "grad_norm": 0.38983288407325745,
+      "learning_rate": 0.0002,
+      "loss": 0.69,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5277435265104806,
+      "grad_norm": 0.6341150999069214,
+      "learning_rate": 0.0002,
+      "loss": 0.8381,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5400739827373613,
+      "grad_norm": 0.7151971459388733,
+      "learning_rate": 0.0002,
+      "loss": 0.773,
+      "step": 2060
+    },
+    {
+      "epoch": 2.5524044389642415,
+      "grad_norm": 0.9665895104408264,
+      "learning_rate": 0.0002,
+      "loss": 0.6733,
+      "step": 2070
+    },
+    {
+      "epoch": 2.564734895191122,
+      "grad_norm": 0.9572727680206299,
+      "learning_rate": 0.0002,
+      "loss": 0.7791,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5770653514180024,
+      "grad_norm": 1.1970765590667725,
+      "learning_rate": 0.0002,
+      "loss": 0.7205,
+      "step": 2090
+    },
+    {
+      "epoch": 2.589395807644883,
+      "grad_norm": 0.5505942702293396,
+      "learning_rate": 0.0002,
+      "loss": 0.6736,
+      "step": 2100
+    },
+    {
+      "epoch": 2.6017262638717633,
+      "grad_norm": 0.5903949737548828,
+      "learning_rate": 0.0002,
+      "loss": 0.673,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6140567200986435,
+      "grad_norm": 0.45640307664871216,
+      "learning_rate": 0.0002,
+      "loss": 0.678,
+      "step": 2120
+    },
+    {
+      "epoch": 2.626387176325524,
+      "grad_norm": 0.8763944506645203,
+      "learning_rate": 0.0002,
+      "loss": 0.6562,
+      "step": 2130
+    },
+    {
+      "epoch": 2.6387176325524044,
+      "grad_norm": 0.4472963213920593,
+      "learning_rate": 0.0002,
+      "loss": 0.6484,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6510480887792847,
+      "grad_norm": 0.5335086584091187,
+      "learning_rate": 0.0002,
+      "loss": 0.7702,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6633785450061653,
+      "grad_norm": 0.805263340473175,
+      "learning_rate": 0.0002,
+      "loss": 0.6851,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6757090012330456,
+      "grad_norm": 0.6332727670669556,
+      "learning_rate": 0.0002,
+      "loss": 0.7026,
+      "step": 2170
+    },
+    {
+      "epoch": 2.688039457459926,
+      "grad_norm": 0.8667435646057129,
+      "learning_rate": 0.0002,
+      "loss": 0.7925,
+      "step": 2180
+    },
+    {
+      "epoch": 2.7003699136868065,
+      "grad_norm": 0.5638955235481262,
+      "learning_rate": 0.0002,
+      "loss": 0.8044,
+      "step": 2190
+    },
+    {
+      "epoch": 2.7127003699136867,
+      "grad_norm": 0.4176250696182251,
+      "learning_rate": 0.0002,
+      "loss": 0.7117,
+      "step": 2200
+    },
+    {
+      "epoch": 2.7250308261405674,
+      "grad_norm": 0.6013461351394653,
+      "learning_rate": 0.0002,
+      "loss": 0.6932,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7373612823674476,
+      "grad_norm": 0.553961992263794,
+      "learning_rate": 0.0002,
+      "loss": 0.7843,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7496917385943282,
+      "grad_norm": 0.4710180461406708,
+      "learning_rate": 0.0002,
+      "loss": 0.8633,
+      "step": 2230
+    },
+    {
+      "epoch": 2.7620221948212085,
+      "grad_norm": 0.8141706585884094,
+      "learning_rate": 0.0002,
+      "loss": 0.7469,
+      "step": 2240
+    },
+    {
+      "epoch": 2.7743526510480887,
+      "grad_norm": 0.7449556589126587,
+      "learning_rate": 0.0002,
+      "loss": 0.7086,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7866831072749694,
+      "grad_norm": 0.5366780757904053,
+      "learning_rate": 0.0002,
+      "loss": 0.6933,
+      "step": 2260
+    },
+    {
+      "epoch": 2.7990135635018496,
+      "grad_norm": 0.5316720604896545,
+      "learning_rate": 0.0002,
+      "loss": 0.7192,
+      "step": 2270
+    },
+    {
+      "epoch": 2.81134401972873,
+      "grad_norm": 0.4598459005355835,
+      "learning_rate": 0.0002,
+      "loss": 0.6212,
+      "step": 2280
+    },
+    {
+      "epoch": 2.8236744759556105,
+      "grad_norm": 0.6852091550827026,
+      "learning_rate": 0.0002,
+      "loss": 0.7024,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8360049321824907,
+      "grad_norm": 0.8040902018547058,
+      "learning_rate": 0.0002,
+      "loss": 0.7357,
+      "step": 2300
+    },
+    {
+      "epoch": 2.848335388409371,
+      "grad_norm": 0.46976321935653687,
+      "learning_rate": 0.0002,
+      "loss": 0.7563,
+      "step": 2310
+    },
+    {
+      "epoch": 2.8606658446362516,
+      "grad_norm": 0.5214090347290039,
+      "learning_rate": 0.0002,
+      "loss": 0.731,
+      "step": 2320
+    },
+    {
+      "epoch": 2.872996300863132,
+      "grad_norm": 0.5323054790496826,
+      "learning_rate": 0.0002,
+      "loss": 0.6687,
+      "step": 2330
+    },
+    {
+      "epoch": 2.885326757090012,
+      "grad_norm": 0.6842264533042908,
+      "learning_rate": 0.0002,
+      "loss": 0.7895,
+      "step": 2340
+    },
+    {
+      "epoch": 2.8976572133168927,
+      "grad_norm": 0.9157055616378784,
+      "learning_rate": 0.0002,
+      "loss": 0.7737,
+      "step": 2350
+    },
+    {
+      "epoch": 2.909987669543773,
+      "grad_norm": 0.5253258347511292,
+      "learning_rate": 0.0002,
+      "loss": 0.7217,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9223181257706536,
+      "grad_norm": 0.4937705099582672,
+      "learning_rate": 0.0002,
+      "loss": 0.7162,
+      "step": 2370
+    },
+    {
+      "epoch": 2.934648581997534,
+      "grad_norm": 0.48762989044189453,
+      "learning_rate": 0.0002,
+      "loss": 0.7008,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9469790382244145,
+      "grad_norm": 0.544335126876831,
+      "learning_rate": 0.0002,
+      "loss": 0.8086,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9593094944512948,
+      "grad_norm": 0.4847845435142517,
+      "learning_rate": 0.0002,
+      "loss": 0.643,
+      "step": 2400
+    },
+    {
+      "epoch": 2.971639950678175,
+      "grad_norm": 0.4787445366382599,
+      "learning_rate": 0.0002,
+      "loss": 0.7757,
+      "step": 2410
+    },
+    {
+      "epoch": 2.9839704069050557,
+      "grad_norm": 1.022318959236145,
+      "learning_rate": 0.0002,
+      "loss": 0.7678,
+      "step": 2420
+    },
+    {
+      "epoch": 2.996300863131936,
+      "grad_norm": 0.4987848103046417,
+      "learning_rate": 0.0002,
+      "loss": 0.6548,
+      "step": 2430
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2936296463012695,
+      "eval_runtime": 94.7897,
+      "eval_samples_per_second": 4.6,
+      "eval_steps_per_second": 0.58,
+      "step": 2433
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6488,
+  "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": 1.2496799311331328e+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-0.6-num-5885-sd-10000/checkpoint-2433/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-0.6-num-5885-sd-10000/checkpoint-2433/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..459ba5959a39ea126110113c9faed75cda19ffff
--- /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-0.6-num-5885-sd-10000/checkpoint-2433/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05287f447dfde244c1a85dc0f576593b4a9dd61961eb0797da4844688fc48447
+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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e04e4441e0c1b29f69c16b26c142944e440b8076
--- /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-0.6-num-5885-sd-10000/checkpoint-3244/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": [
+    "q_proj",
+    "v_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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3396826926c797985a101e13a42e897a206698bb
--- /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-0.6-num-5885-sd-10000/checkpoint-3244/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc38cb62d14fbd06e9bdb04a1e84d0455b3987e1fa9b83f322fc2df44acc8b7
+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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..99a8264523d4d282cf0eb84f66c9bbde70b38f3f
--- /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-0.6-num-5885-sd-10000/checkpoint-3244/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b55169fe31e37a2e2dde32ccf2a2fdcd1cc7b30c0a06fd77dd13ffc4fa4fb97
+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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cc69645c774895d9d3cf59924729f721ada04388
--- /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-0.6-num-5885-sd-10000/checkpoint-3244/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b5fa4db2ec9f1dd83c22e31ef62ef4da0a2145da06b57bfd033599abd353ad
+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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..aa72a11a725fca0e62be390038a08eb9c1db7907
--- /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-0.6-num-5885-sd-10000/checkpoint-3244/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d807bbd0c95f2d5fe6d3a34fd392cb32d62db708c74f56525909e7e3cc107e
+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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22
--- /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-0.6-num-5885-sd-10000/checkpoint-3244/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873
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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..de29095b7c91f8b12544a22f6bc6e04d22574b06
--- /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-0.6-num-5885-sd-10000/checkpoint-3244/trainer_state.json
@@ -0,0 +1,2333 @@
+{
+  "best_metric": 1.238026738166809,
+  "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-0.6-num-5885-sd-10000/checkpoint-1622",
+  "epoch": 4.0,
+  "eval_steps": 10,
+  "global_step": 3244,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012330456226880395,
+      "grad_norm": 0.8258164525032043,
+      "learning_rate": 0.0002,
+      "loss": 2.3601,
+      "step": 10
+    },
+    {
+      "epoch": 0.02466091245376079,
+      "grad_norm": 0.4577729105949402,
+      "learning_rate": 0.0002,
+      "loss": 1.7317,
+      "step": 20
+    },
+    {
+      "epoch": 0.036991368680641186,
+      "grad_norm": 0.639807939529419,
+      "learning_rate": 0.0002,
+      "loss": 1.4729,
+      "step": 30
+    },
+    {
+      "epoch": 0.04932182490752158,
+      "grad_norm": 0.5311757922172546,
+      "learning_rate": 0.0002,
+      "loss": 1.2088,
+      "step": 40
+    },
+    {
+      "epoch": 0.06165228113440197,
+      "grad_norm": 0.386595219373703,
+      "learning_rate": 0.0002,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.07398273736128237,
+      "grad_norm": 0.4401357173919678,
+      "learning_rate": 0.0002,
+      "loss": 1.1657,
+      "step": 60
+    },
+    {
+      "epoch": 0.08631319358816276,
+      "grad_norm": 0.3234352171421051,
+      "learning_rate": 0.0002,
+      "loss": 1.1022,
+      "step": 70
+    },
+    {
+      "epoch": 0.09864364981504316,
+      "grad_norm": 0.29643672704696655,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 80
+    },
+    {
+      "epoch": 0.11097410604192355,
+      "grad_norm": 0.2941012382507324,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 90
+    },
+    {
+      "epoch": 0.12330456226880394,
+      "grad_norm": 0.5498173832893372,
+      "learning_rate": 0.0002,
+      "loss": 1.2067,
+      "step": 100
+    },
+    {
+      "epoch": 0.13563501849568435,
+      "grad_norm": 0.2545783519744873,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 110
+    },
+    {
+      "epoch": 0.14796547472256474,
+      "grad_norm": 0.2984241247177124,
+      "learning_rate": 0.0002,
+      "loss": 1.0297,
+      "step": 120
+    },
+    {
+      "epoch": 0.16029593094944514,
+      "grad_norm": 0.2710968852043152,
+      "learning_rate": 0.0002,
+      "loss": 1.1591,
+      "step": 130
+    },
+    {
+      "epoch": 0.17262638717632553,
+      "grad_norm": 0.2817152142524719,
+      "learning_rate": 0.0002,
+      "loss": 1.0427,
+      "step": 140
+    },
+    {
+      "epoch": 0.18495684340320592,
+      "grad_norm": 0.41083765029907227,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 150
+    },
+    {
+      "epoch": 0.19728729963008632,
+      "grad_norm": 0.36536213755607605,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 160
+    },
+    {
+      "epoch": 0.2096177558569667,
+      "grad_norm": 0.2738671600818634,
+      "learning_rate": 0.0002,
+      "loss": 1.0132,
+      "step": 170
+    },
+    {
+      "epoch": 0.2219482120838471,
+      "grad_norm": 0.27403146028518677,
+      "learning_rate": 0.0002,
+      "loss": 0.9555,
+      "step": 180
+    },
+    {
+      "epoch": 0.2342786683107275,
+      "grad_norm": 0.4446810483932495,
+      "learning_rate": 0.0002,
+      "loss": 1.0769,
+      "step": 190
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "grad_norm": 0.5295385718345642,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 200
+    },
+    {
+      "epoch": 0.2589395807644883,
+      "grad_norm": 0.311404824256897,
+      "learning_rate": 0.0002,
+      "loss": 1.0827,
+      "step": 210
+    },
+    {
+      "epoch": 0.2712700369913687,
+      "grad_norm": 0.2448509782552719,
+      "learning_rate": 0.0002,
+      "loss": 1.1455,
+      "step": 220
+    },
+    {
+      "epoch": 0.2836004932182491,
+      "grad_norm": 0.6507014036178589,
+      "learning_rate": 0.0002,
+      "loss": 1.0929,
+      "step": 230
+    },
+    {
+      "epoch": 0.2959309494451295,
+      "grad_norm": 0.2339320331811905,
+      "learning_rate": 0.0002,
+      "loss": 0.9875,
+      "step": 240
+    },
+    {
+      "epoch": 0.3082614056720099,
+      "grad_norm": 0.8210226893424988,
+      "learning_rate": 0.0002,
+      "loss": 0.9211,
+      "step": 250
+    },
+    {
+      "epoch": 0.3205918618988903,
+      "grad_norm": 0.27473965287208557,
+      "learning_rate": 0.0002,
+      "loss": 1.161,
+      "step": 260
+    },
+    {
+      "epoch": 0.33292231812577067,
+      "grad_norm": 0.3051395118236542,
+      "learning_rate": 0.0002,
+      "loss": 1.0218,
+      "step": 270
+    },
+    {
+      "epoch": 0.34525277435265106,
+      "grad_norm": 0.3037777245044708,
+      "learning_rate": 0.0002,
+      "loss": 1.0286,
+      "step": 280
+    },
+    {
+      "epoch": 0.35758323057953145,
+      "grad_norm": 0.2748974859714508,
+      "learning_rate": 0.0002,
+      "loss": 1.144,
+      "step": 290
+    },
+    {
+      "epoch": 0.36991368680641185,
+      "grad_norm": 0.23656068742275238,
+      "learning_rate": 0.0002,
+      "loss": 1.0858,
+      "step": 300
+    },
+    {
+      "epoch": 0.38224414303329224,
+      "grad_norm": 0.2523384094238281,
+      "learning_rate": 0.0002,
+      "loss": 1.0564,
+      "step": 310
+    },
+    {
+      "epoch": 0.39457459926017263,
+      "grad_norm": 0.27848055958747864,
+      "learning_rate": 0.0002,
+      "loss": 1.3091,
+      "step": 320
+    },
+    {
+      "epoch": 0.406905055487053,
+      "grad_norm": 0.3204525411128998,
+      "learning_rate": 0.0002,
+      "loss": 1.0252,
+      "step": 330
+    },
+    {
+      "epoch": 0.4192355117139334,
+      "grad_norm": 0.3459707498550415,
+      "learning_rate": 0.0002,
+      "loss": 0.9855,
+      "step": 340
+    },
+    {
+      "epoch": 0.4315659679408138,
+      "grad_norm": 0.2458430379629135,
+      "learning_rate": 0.0002,
+      "loss": 1.1111,
+      "step": 350
+    },
+    {
+      "epoch": 0.4438964241676942,
+      "grad_norm": 0.5022910237312317,
+      "learning_rate": 0.0002,
+      "loss": 1.1493,
+      "step": 360
+    },
+    {
+      "epoch": 0.4562268803945746,
+      "grad_norm": 0.27076372504234314,
+      "learning_rate": 0.0002,
+      "loss": 1.1272,
+      "step": 370
+    },
+    {
+      "epoch": 0.468557336621455,
+      "grad_norm": 0.6489047408103943,
+      "learning_rate": 0.0002,
+      "loss": 1.1927,
+      "step": 380
+    },
+    {
+      "epoch": 0.4808877928483354,
+      "grad_norm": 0.3324144184589386,
+      "learning_rate": 0.0002,
+      "loss": 0.9501,
+      "step": 390
+    },
+    {
+      "epoch": 0.4932182490752158,
+      "grad_norm": 0.32813116908073425,
+      "learning_rate": 0.0002,
+      "loss": 1.2012,
+      "step": 400
+    },
+    {
+      "epoch": 0.5055487053020962,
+      "grad_norm": 0.25295355916023254,
+      "learning_rate": 0.0002,
+      "loss": 1.1135,
+      "step": 410
+    },
+    {
+      "epoch": 0.5178791615289766,
+      "grad_norm": 0.2912578880786896,
+      "learning_rate": 0.0002,
+      "loss": 0.9477,
+      "step": 420
+    },
+    {
+      "epoch": 0.530209617755857,
+      "grad_norm": 0.34780189394950867,
+      "learning_rate": 0.0002,
+      "loss": 1.0121,
+      "step": 430
+    },
+    {
+      "epoch": 0.5425400739827374,
+      "grad_norm": 0.24604526162147522,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 440
+    },
+    {
+      "epoch": 0.5548705302096177,
+      "grad_norm": 0.32759982347488403,
+      "learning_rate": 0.0002,
+      "loss": 1.253,
+      "step": 450
+    },
+    {
+      "epoch": 0.5672009864364982,
+      "grad_norm": 0.40810221433639526,
+      "learning_rate": 0.0002,
+      "loss": 1.1925,
+      "step": 460
+    },
+    {
+      "epoch": 0.5795314426633785,
+      "grad_norm": 0.3590679466724396,
+      "learning_rate": 0.0002,
+      "loss": 1.174,
+      "step": 470
+    },
+    {
+      "epoch": 0.591861898890259,
+      "grad_norm": 0.5656213760375977,
+      "learning_rate": 0.0002,
+      "loss": 1.2223,
+      "step": 480
+    },
+    {
+      "epoch": 0.6041923551171393,
+      "grad_norm": 0.30830657482147217,
+      "learning_rate": 0.0002,
+      "loss": 1.1936,
+      "step": 490
+    },
+    {
+      "epoch": 0.6165228113440198,
+      "grad_norm": 0.317905455827713,
+      "learning_rate": 0.0002,
+      "loss": 1.1873,
+      "step": 500
+    },
+    {
+      "epoch": 0.6288532675709001,
+      "grad_norm": 0.3254566490650177,
+      "learning_rate": 0.0002,
+      "loss": 0.9805,
+      "step": 510
+    },
+    {
+      "epoch": 0.6411837237977805,
+      "grad_norm": 0.29187721014022827,
+      "learning_rate": 0.0002,
+      "loss": 1.0384,
+      "step": 520
+    },
+    {
+      "epoch": 0.6535141800246609,
+      "grad_norm": 0.3439238965511322,
+      "learning_rate": 0.0002,
+      "loss": 1.2526,
+      "step": 530
+    },
+    {
+      "epoch": 0.6658446362515413,
+      "grad_norm": 0.20970556139945984,
+      "learning_rate": 0.0002,
+      "loss": 1.0698,
+      "step": 540
+    },
+    {
+      "epoch": 0.6781750924784217,
+      "grad_norm": 0.4022853374481201,
+      "learning_rate": 0.0002,
+      "loss": 1.1047,
+      "step": 550
+    },
+    {
+      "epoch": 0.6905055487053021,
+      "grad_norm": 0.2235759049654007,
+      "learning_rate": 0.0002,
+      "loss": 1.0684,
+      "step": 560
+    },
+    {
+      "epoch": 0.7028360049321825,
+      "grad_norm": 0.33849895000457764,
+      "learning_rate": 0.0002,
+      "loss": 1.2339,
+      "step": 570
+    },
+    {
+      "epoch": 0.7151664611590629,
+      "grad_norm": 0.34745967388153076,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 580
+    },
+    {
+      "epoch": 0.7274969173859432,
+      "grad_norm": 0.26041269302368164,
+      "learning_rate": 0.0002,
+      "loss": 1.1158,
+      "step": 590
+    },
+    {
+      "epoch": 0.7398273736128237,
+      "grad_norm": 0.3804777264595032,
+      "learning_rate": 0.0002,
+      "loss": 1.2134,
+      "step": 600
+    },
+    {
+      "epoch": 0.752157829839704,
+      "grad_norm": 0.2456253319978714,
+      "learning_rate": 0.0002,
+      "loss": 1.0606,
+      "step": 610
+    },
+    {
+      "epoch": 0.7644882860665845,
+      "grad_norm": 0.37838423252105713,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 620
+    },
+    {
+      "epoch": 0.7768187422934648,
+      "grad_norm": 0.28105494379997253,
+      "learning_rate": 0.0002,
+      "loss": 1.0556,
+      "step": 630
+    },
+    {
+      "epoch": 0.7891491985203453,
+      "grad_norm": 0.2774018943309784,
+      "learning_rate": 0.0002,
+      "loss": 1.0672,
+      "step": 640
+    },
+    {
+      "epoch": 0.8014796547472256,
+      "grad_norm": 1.8184229135513306,
+      "learning_rate": 0.0002,
+      "loss": 0.9978,
+      "step": 650
+    },
+    {
+      "epoch": 0.813810110974106,
+      "grad_norm": 0.3325096070766449,
+      "learning_rate": 0.0002,
+      "loss": 1.1038,
+      "step": 660
+    },
+    {
+      "epoch": 0.8261405672009864,
+      "grad_norm": 0.2686693072319031,
+      "learning_rate": 0.0002,
+      "loss": 1.083,
+      "step": 670
+    },
+    {
+      "epoch": 0.8384710234278668,
+      "grad_norm": 0.3271431624889374,
+      "learning_rate": 0.0002,
+      "loss": 1.1308,
+      "step": 680
+    },
+    {
+      "epoch": 0.8508014796547472,
+      "grad_norm": 2.359999656677246,
+      "learning_rate": 0.0002,
+      "loss": 1.1116,
+      "step": 690
+    },
+    {
+      "epoch": 0.8631319358816276,
+      "grad_norm": 0.46242964267730713,
+      "learning_rate": 0.0002,
+      "loss": 1.0782,
+      "step": 700
+    },
+    {
+      "epoch": 0.8754623921085081,
+      "grad_norm": 0.34731170535087585,
+      "learning_rate": 0.0002,
+      "loss": 0.95,
+      "step": 710
+    },
+    {
+      "epoch": 0.8877928483353884,
+      "grad_norm": 0.39381715655326843,
+      "learning_rate": 0.0002,
+      "loss": 1.2236,
+      "step": 720
+    },
+    {
+      "epoch": 0.9001233045622689,
+      "grad_norm": 0.43496373295783997,
+      "learning_rate": 0.0002,
+      "loss": 1.1319,
+      "step": 730
+    },
+    {
+      "epoch": 0.9124537607891492,
+      "grad_norm": 0.32243210077285767,
+      "learning_rate": 0.0002,
+      "loss": 1.0979,
+      "step": 740
+    },
+    {
+      "epoch": 0.9247842170160296,
+      "grad_norm": 0.30396756529808044,
+      "learning_rate": 0.0002,
+      "loss": 0.9913,
+      "step": 750
+    },
+    {
+      "epoch": 0.93711467324291,
+      "grad_norm": 0.4461122751235962,
+      "learning_rate": 0.0002,
+      "loss": 1.1141,
+      "step": 760
+    },
+    {
+      "epoch": 0.9494451294697904,
+      "grad_norm": 0.24081681668758392,
+      "learning_rate": 0.0002,
+      "loss": 1.0049,
+      "step": 770
+    },
+    {
+      "epoch": 0.9617755856966708,
+      "grad_norm": 0.27461910247802734,
+      "learning_rate": 0.0002,
+      "loss": 1.0966,
+      "step": 780
+    },
+    {
+      "epoch": 0.9741060419235512,
+      "grad_norm": 0.3325668275356293,
+      "learning_rate": 0.0002,
+      "loss": 0.9942,
+      "step": 790
+    },
+    {
+      "epoch": 0.9864364981504316,
+      "grad_norm": 0.24046339094638824,
+      "learning_rate": 0.0002,
+      "loss": 1.0506,
+      "step": 800
+    },
+    {
+      "epoch": 0.998766954377312,
+      "grad_norm": 0.42950066924095154,
+      "learning_rate": 0.0002,
+      "loss": 0.9989,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.246457576751709,
+      "eval_runtime": 98.7974,
+      "eval_samples_per_second": 4.413,
+      "eval_steps_per_second": 0.557,
+      "step": 811
+    },
+    {
+      "epoch": 1.0110974106041923,
+      "grad_norm": 0.26760655641555786,
+      "learning_rate": 0.0002,
+      "loss": 1.0536,
+      "step": 820
+    },
+    {
+      "epoch": 1.0234278668310728,
+      "grad_norm": 0.4640820026397705,
+      "learning_rate": 0.0002,
+      "loss": 0.9722,
+      "step": 830
+    },
+    {
+      "epoch": 1.0357583230579532,
+      "grad_norm": 0.2699166238307953,
+      "learning_rate": 0.0002,
+      "loss": 0.9392,
+      "step": 840
+    },
+    {
+      "epoch": 1.0480887792848335,
+      "grad_norm": 0.3441709578037262,
+      "learning_rate": 0.0002,
+      "loss": 0.9335,
+      "step": 850
+    },
+    {
+      "epoch": 1.060419235511714,
+      "grad_norm": 0.299934983253479,
+      "learning_rate": 0.0002,
+      "loss": 0.9083,
+      "step": 860
+    },
+    {
+      "epoch": 1.0727496917385944,
+      "grad_norm": 0.2980666160583496,
+      "learning_rate": 0.0002,
+      "loss": 0.9416,
+      "step": 870
+    },
+    {
+      "epoch": 1.0850801479654748,
+      "grad_norm": 0.3131714463233948,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 880
+    },
+    {
+      "epoch": 1.097410604192355,
+      "grad_norm": 0.29881617426872253,
+      "learning_rate": 0.0002,
+      "loss": 0.9288,
+      "step": 890
+    },
+    {
+      "epoch": 1.1097410604192355,
+      "grad_norm": 0.29870888590812683,
+      "learning_rate": 0.0002,
+      "loss": 0.998,
+      "step": 900
+    },
+    {
+      "epoch": 1.122071516646116,
+      "grad_norm": 0.5735140442848206,
+      "learning_rate": 0.0002,
+      "loss": 0.9924,
+      "step": 910
+    },
+    {
+      "epoch": 1.1344019728729964,
+      "grad_norm": 0.33159002661705017,
+      "learning_rate": 0.0002,
+      "loss": 1.0694,
+      "step": 920
+    },
+    {
+      "epoch": 1.1467324290998766,
+      "grad_norm": 1.235399842262268,
+      "learning_rate": 0.0002,
+      "loss": 1.0069,
+      "step": 930
+    },
+    {
+      "epoch": 1.159062885326757,
+      "grad_norm": 0.27469736337661743,
+      "learning_rate": 0.0002,
+      "loss": 1.0315,
+      "step": 940
+    },
+    {
+      "epoch": 1.1713933415536375,
+      "grad_norm": 0.29130664467811584,
+      "learning_rate": 0.0002,
+      "loss": 0.9386,
+      "step": 950
+    },
+    {
+      "epoch": 1.183723797780518,
+      "grad_norm": 0.3730354607105255,
+      "learning_rate": 0.0002,
+      "loss": 0.8919,
+      "step": 960
+    },
+    {
+      "epoch": 1.1960542540073984,
+      "grad_norm": 0.5973590612411499,
+      "learning_rate": 0.0002,
+      "loss": 0.9988,
+      "step": 970
+    },
+    {
+      "epoch": 1.2083847102342786,
+      "grad_norm": 0.39631304144859314,
+      "learning_rate": 0.0002,
+      "loss": 0.9525,
+      "step": 980
+    },
+    {
+      "epoch": 1.220715166461159,
+      "grad_norm": 0.849051296710968,
+      "learning_rate": 0.0002,
+      "loss": 0.9217,
+      "step": 990
+    },
+    {
+      "epoch": 1.2330456226880395,
+      "grad_norm": 0.4390525817871094,
+      "learning_rate": 0.0002,
+      "loss": 1.0903,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2453760789149197,
+      "grad_norm": 0.30423852801322937,
+      "learning_rate": 0.0002,
+      "loss": 0.9018,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2577065351418002,
+      "grad_norm": 0.34736061096191406,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2700369913686806,
+      "grad_norm": 0.3421604037284851,
+      "learning_rate": 0.0002,
+      "loss": 0.9026,
+      "step": 1030
+    },
+    {
+      "epoch": 1.282367447595561,
+      "grad_norm": 0.544170081615448,
+      "learning_rate": 0.0002,
+      "loss": 0.8485,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2946979038224415,
+      "grad_norm": 0.5128790736198425,
+      "learning_rate": 0.0002,
+      "loss": 0.9591,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3070283600493218,
+      "grad_norm": 0.443344384431839,
+      "learning_rate": 0.0002,
+      "loss": 0.9214,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3193588162762022,
+      "grad_norm": 0.6380868554115295,
+      "learning_rate": 0.0002,
+      "loss": 0.9367,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3316892725030827,
+      "grad_norm": 0.4638073146343231,
+      "learning_rate": 0.0002,
+      "loss": 0.9849,
+      "step": 1080
+    },
+    {
+      "epoch": 1.344019728729963,
+      "grad_norm": 0.32406893372535706,
+      "learning_rate": 0.0002,
+      "loss": 0.8645,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3563501849568433,
+      "grad_norm": 0.3955065608024597,
+      "learning_rate": 0.0002,
+      "loss": 0.8278,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3686806411837238,
+      "grad_norm": 0.3489246666431427,
+      "learning_rate": 0.0002,
+      "loss": 0.9306,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3810110974106042,
+      "grad_norm": 0.48451653122901917,
+      "learning_rate": 0.0002,
+      "loss": 1.0138,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3933415536374847,
+      "grad_norm": 0.3652360439300537,
+      "learning_rate": 0.0002,
+      "loss": 0.9165,
+      "step": 1130
+    },
+    {
+      "epoch": 1.405672009864365,
+      "grad_norm": 1.3097436428070068,
+      "learning_rate": 0.0002,
+      "loss": 0.9576,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4180024660912454,
+      "grad_norm": 0.3647715449333191,
+      "learning_rate": 0.0002,
+      "loss": 0.8115,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4303329223181258,
+      "grad_norm": 0.37248560786247253,
+      "learning_rate": 0.0002,
+      "loss": 0.8573,
+      "step": 1160
+    },
+    {
+      "epoch": 1.442663378545006,
+      "grad_norm": 0.4639643430709839,
+      "learning_rate": 0.0002,
+      "loss": 0.936,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4549938347718865,
+      "grad_norm": 0.5455219745635986,
+      "learning_rate": 0.0002,
+      "loss": 0.9511,
+      "step": 1180
+    },
+    {
+      "epoch": 1.467324290998767,
+      "grad_norm": 0.38862571120262146,
+      "learning_rate": 0.0002,
+      "loss": 0.8611,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4796547472256474,
+      "grad_norm": 0.37586215138435364,
+      "learning_rate": 0.0002,
+      "loss": 0.8681,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4919852034525278,
+      "grad_norm": 0.46244436502456665,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1210
+    },
+    {
+      "epoch": 1.504315659679408,
+      "grad_norm": 0.3570359945297241,
+      "learning_rate": 0.0002,
+      "loss": 0.9388,
+      "step": 1220
+    },
+    {
+      "epoch": 1.5166461159062885,
+      "grad_norm": 0.28393083810806274,
+      "learning_rate": 0.0002,
+      "loss": 0.971,
+      "step": 1230
+    },
+    {
+      "epoch": 1.528976572133169,
+      "grad_norm": 0.5672869682312012,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5413070283600492,
+      "grad_norm": 0.41605108976364136,
+      "learning_rate": 0.0002,
+      "loss": 0.8787,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5536374845869299,
+      "grad_norm": 0.40657493472099304,
+      "learning_rate": 0.0002,
+      "loss": 0.8744,
+      "step": 1260
+    },
+    {
+      "epoch": 1.56596794081381,
+      "grad_norm": 0.43672341108322144,
+      "learning_rate": 0.0002,
+      "loss": 0.9046,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5782983970406905,
+      "grad_norm": 0.3065410554409027,
+      "learning_rate": 0.0002,
+      "loss": 0.8586,
+      "step": 1280
+    },
+    {
+      "epoch": 1.590628853267571,
+      "grad_norm": 0.37826645374298096,
+      "learning_rate": 0.0002,
+      "loss": 0.9499,
+      "step": 1290
+    },
+    {
+      "epoch": 1.6029593094944512,
+      "grad_norm": 0.42307335138320923,
+      "learning_rate": 0.0002,
+      "loss": 0.901,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6152897657213316,
+      "grad_norm": 0.3648843467235565,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1310
+    },
+    {
+      "epoch": 1.627620221948212,
+      "grad_norm": 0.8921076059341431,
+      "learning_rate": 0.0002,
+      "loss": 0.9302,
+      "step": 1320
+    },
+    {
+      "epoch": 1.6399506781750923,
+      "grad_norm": 0.37522226572036743,
+      "learning_rate": 0.0002,
+      "loss": 0.9378,
+      "step": 1330
+    },
+    {
+      "epoch": 1.652281134401973,
+      "grad_norm": 0.7489957809448242,
+      "learning_rate": 0.0002,
+      "loss": 0.8921,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6646115906288532,
+      "grad_norm": 0.31733131408691406,
+      "learning_rate": 0.0002,
+      "loss": 0.9297,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6769420468557337,
+      "grad_norm": 0.3249478340148926,
+      "learning_rate": 0.0002,
+      "loss": 0.907,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6892725030826141,
+      "grad_norm": 0.3178001344203949,
+      "learning_rate": 0.0002,
+      "loss": 1.0197,
+      "step": 1370
+    },
+    {
+      "epoch": 1.7016029593094943,
+      "grad_norm": 0.5674093961715698,
+      "learning_rate": 0.0002,
+      "loss": 1.0781,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7139334155363748,
+      "grad_norm": 0.35272449254989624,
+      "learning_rate": 0.0002,
+      "loss": 0.8972,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7262638717632552,
+      "grad_norm": 0.5778217911720276,
+      "learning_rate": 0.0002,
+      "loss": 0.9346,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7385943279901355,
+      "grad_norm": 0.33561450242996216,
+      "learning_rate": 0.0002,
+      "loss": 0.9099,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7509247842170161,
+      "grad_norm": 0.31735464930534363,
+      "learning_rate": 0.0002,
+      "loss": 0.8636,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7632552404438964,
+      "grad_norm": 1.0612670183181763,
+      "learning_rate": 0.0002,
+      "loss": 0.982,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7755856966707768,
+      "grad_norm": 0.5442509651184082,
+      "learning_rate": 0.0002,
+      "loss": 0.8224,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7879161528976573,
+      "grad_norm": 0.7471332550048828,
+      "learning_rate": 0.0002,
+      "loss": 0.9275,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8002466091245375,
+      "grad_norm": 0.4323609173297882,
+      "learning_rate": 0.0002,
+      "loss": 0.9389,
+      "step": 1460
+    },
+    {
+      "epoch": 1.8125770653514182,
+      "grad_norm": 0.47796759009361267,
+      "learning_rate": 0.0002,
+      "loss": 0.8247,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8249075215782984,
+      "grad_norm": 0.3348400592803955,
+      "learning_rate": 0.0002,
+      "loss": 0.9395,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8372379778051788,
+      "grad_norm": 0.3354550898075104,
+      "learning_rate": 0.0002,
+      "loss": 0.9793,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8495684340320593,
+      "grad_norm": 0.5988477468490601,
+      "learning_rate": 0.0002,
+      "loss": 0.8581,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8618988902589395,
+      "grad_norm": 0.5222318172454834,
+      "learning_rate": 0.0002,
+      "loss": 0.9268,
+      "step": 1510
+    },
+    {
+      "epoch": 1.87422934648582,
+      "grad_norm": 0.5246642827987671,
+      "learning_rate": 0.0002,
+      "loss": 0.8846,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8865598027127004,
+      "grad_norm": 0.3164594769477844,
+      "learning_rate": 0.0002,
+      "loss": 0.9317,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8988902589395806,
+      "grad_norm": 0.3496174216270447,
+      "learning_rate": 0.0002,
+      "loss": 0.9961,
+      "step": 1540
+    },
+    {
+      "epoch": 1.9112207151664613,
+      "grad_norm": 0.8863359689712524,
+      "learning_rate": 0.0002,
+      "loss": 0.9057,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9235511713933415,
+      "grad_norm": 0.3587026298046112,
+      "learning_rate": 0.0002,
+      "loss": 0.9405,
+      "step": 1560
+    },
+    {
+      "epoch": 1.935881627620222,
+      "grad_norm": 0.6052881479263306,
+      "learning_rate": 0.0002,
+      "loss": 0.8335,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9482120838471024,
+      "grad_norm": 0.567269504070282,
+      "learning_rate": 0.0002,
+      "loss": 0.8805,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9605425400739827,
+      "grad_norm": 0.45184487104415894,
+      "learning_rate": 0.0002,
+      "loss": 0.9581,
+      "step": 1590
+    },
+    {
+      "epoch": 1.972872996300863,
+      "grad_norm": 0.5028569102287292,
+      "learning_rate": 0.0002,
+      "loss": 0.9147,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9852034525277436,
+      "grad_norm": 0.4677547216415405,
+      "learning_rate": 0.0002,
+      "loss": 0.75,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9975339087546238,
+      "grad_norm": 0.35106056928634644,
+      "learning_rate": 0.0002,
+      "loss": 0.8469,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.238026738166809,
+      "eval_runtime": 95.4287,
+      "eval_samples_per_second": 4.569,
+      "eval_steps_per_second": 0.576,
+      "step": 1622
+    },
+    {
+      "epoch": 2.0098643649815044,
+      "grad_norm": 0.444060355424881,
+      "learning_rate": 0.0002,
+      "loss": 0.7629,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0221948212083847,
+      "grad_norm": 0.627570390701294,
+      "learning_rate": 0.0002,
+      "loss": 0.772,
+      "step": 1640
+    },
+    {
+      "epoch": 2.034525277435265,
+      "grad_norm": 0.38737839460372925,
+      "learning_rate": 0.0002,
+      "loss": 0.6186,
+      "step": 1650
+    },
+    {
+      "epoch": 2.0468557336621456,
+      "grad_norm": 0.4300459623336792,
+      "learning_rate": 0.0002,
+      "loss": 0.7734,
+      "step": 1660
+    },
+    {
+      "epoch": 2.059186189889026,
+      "grad_norm": 0.43037715554237366,
+      "learning_rate": 0.0002,
+      "loss": 0.6943,
+      "step": 1670
+    },
+    {
+      "epoch": 2.0715166461159065,
+      "grad_norm": 0.40772515535354614,
+      "learning_rate": 0.0002,
+      "loss": 0.6588,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0838471023427867,
+      "grad_norm": 0.5295451879501343,
+      "learning_rate": 0.0002,
+      "loss": 0.8105,
+      "step": 1690
+    },
+    {
+      "epoch": 2.096177558569667,
+      "grad_norm": 0.7452750205993652,
+      "learning_rate": 0.0002,
+      "loss": 0.7717,
+      "step": 1700
+    },
+    {
+      "epoch": 2.1085080147965476,
+      "grad_norm": 0.809183657169342,
+      "learning_rate": 0.0002,
+      "loss": 0.7458,
+      "step": 1710
+    },
+    {
+      "epoch": 2.120838471023428,
+      "grad_norm": 0.4597688913345337,
+      "learning_rate": 0.0002,
+      "loss": 0.7398,
+      "step": 1720
+    },
+    {
+      "epoch": 2.133168927250308,
+      "grad_norm": 0.806919276714325,
+      "learning_rate": 0.0002,
+      "loss": 0.6856,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1454993834771887,
+      "grad_norm": 0.3755643665790558,
+      "learning_rate": 0.0002,
+      "loss": 0.679,
+      "step": 1740
+    },
+    {
+      "epoch": 2.157829839704069,
+      "grad_norm": 0.5882734060287476,
+      "learning_rate": 0.0002,
+      "loss": 0.7938,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1701602959309496,
+      "grad_norm": 0.692960798740387,
+      "learning_rate": 0.0002,
+      "loss": 0.6782,
+      "step": 1760
+    },
+    {
+      "epoch": 2.18249075215783,
+      "grad_norm": 0.4737096428871155,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 1770
+    },
+    {
+      "epoch": 2.19482120838471,
+      "grad_norm": 0.6637021899223328,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 1780
+    },
+    {
+      "epoch": 2.2071516646115907,
+      "grad_norm": 0.9109764099121094,
+      "learning_rate": 0.0002,
+      "loss": 0.7139,
+      "step": 1790
+    },
+    {
+      "epoch": 2.219482120838471,
+      "grad_norm": 0.4137539267539978,
+      "learning_rate": 0.0002,
+      "loss": 0.7373,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2318125770653516,
+      "grad_norm": 0.44995415210723877,
+      "learning_rate": 0.0002,
+      "loss": 0.7266,
+      "step": 1810
+    },
+    {
+      "epoch": 2.244143033292232,
+      "grad_norm": 0.5985036492347717,
+      "learning_rate": 0.0002,
+      "loss": 0.7663,
+      "step": 1820
+    },
+    {
+      "epoch": 2.256473489519112,
+      "grad_norm": 0.7549490332603455,
+      "learning_rate": 0.0002,
+      "loss": 0.7502,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2688039457459928,
+      "grad_norm": 0.4490937888622284,
+      "learning_rate": 0.0002,
+      "loss": 0.7452,
+      "step": 1840
+    },
+    {
+      "epoch": 2.281134401972873,
+      "grad_norm": 0.38859808444976807,
+      "learning_rate": 0.0002,
+      "loss": 0.7531,
+      "step": 1850
+    },
+    {
+      "epoch": 2.293464858199753,
+      "grad_norm": 1.0704916715621948,
+      "learning_rate": 0.0002,
+      "loss": 0.7278,
+      "step": 1860
+    },
+    {
+      "epoch": 2.305795314426634,
+      "grad_norm": 0.4647100865840912,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 1870
+    },
+    {
+      "epoch": 2.318125770653514,
+      "grad_norm": 0.6181163787841797,
+      "learning_rate": 0.0002,
+      "loss": 0.7146,
+      "step": 1880
+    },
+    {
+      "epoch": 2.3304562268803943,
+      "grad_norm": 0.9241904020309448,
+      "learning_rate": 0.0002,
+      "loss": 0.7689,
+      "step": 1890
+    },
+    {
+      "epoch": 2.342786683107275,
+      "grad_norm": 0.39101317524909973,
+      "learning_rate": 0.0002,
+      "loss": 0.7294,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3551171393341552,
+      "grad_norm": 0.49442458152770996,
+      "learning_rate": 0.0002,
+      "loss": 0.7079,
+      "step": 1910
+    },
+    {
+      "epoch": 2.367447595561036,
+      "grad_norm": 0.4864824414253235,
+      "learning_rate": 0.0002,
+      "loss": 0.7586,
+      "step": 1920
+    },
+    {
+      "epoch": 2.379778051787916,
+      "grad_norm": 0.5427613854408264,
+      "learning_rate": 0.0002,
+      "loss": 0.7434,
+      "step": 1930
+    },
+    {
+      "epoch": 2.392108508014797,
+      "grad_norm": 0.7164974808692932,
+      "learning_rate": 0.0002,
+      "loss": 0.8423,
+      "step": 1940
+    },
+    {
+      "epoch": 2.404438964241677,
+      "grad_norm": 0.562979519367218,
+      "learning_rate": 0.0002,
+      "loss": 0.6888,
+      "step": 1950
+    },
+    {
+      "epoch": 2.4167694204685573,
+      "grad_norm": 0.5631861090660095,
+      "learning_rate": 0.0002,
+      "loss": 0.7692,
+      "step": 1960
+    },
+    {
+      "epoch": 2.429099876695438,
+      "grad_norm": 0.4895121157169342,
+      "learning_rate": 0.0002,
+      "loss": 0.67,
+      "step": 1970
+    },
+    {
+      "epoch": 2.441430332922318,
+      "grad_norm": 0.45674824714660645,
+      "learning_rate": 0.0002,
+      "loss": 0.7735,
+      "step": 1980
+    },
+    {
+      "epoch": 2.4537607891491984,
+      "grad_norm": 1.1424206495285034,
+      "learning_rate": 0.0002,
+      "loss": 0.685,
+      "step": 1990
+    },
+    {
+      "epoch": 2.466091245376079,
+      "grad_norm": 0.6314579844474792,
+      "learning_rate": 0.0002,
+      "loss": 0.7627,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4784217016029593,
+      "grad_norm": 0.5481605529785156,
+      "learning_rate": 0.0002,
+      "loss": 0.7118,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4907521578298395,
+      "grad_norm": 0.4671579599380493,
+      "learning_rate": 0.0002,
+      "loss": 0.6947,
+      "step": 2020
+    },
+    {
+      "epoch": 2.50308261405672,
+      "grad_norm": 0.7621194124221802,
+      "learning_rate": 0.0002,
+      "loss": 0.7377,
+      "step": 2030
+    },
+    {
+      "epoch": 2.5154130702836004,
+      "grad_norm": 0.38983288407325745,
+      "learning_rate": 0.0002,
+      "loss": 0.69,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5277435265104806,
+      "grad_norm": 0.6341150999069214,
+      "learning_rate": 0.0002,
+      "loss": 0.8381,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5400739827373613,
+      "grad_norm": 0.7151971459388733,
+      "learning_rate": 0.0002,
+      "loss": 0.773,
+      "step": 2060
+    },
+    {
+      "epoch": 2.5524044389642415,
+      "grad_norm": 0.9665895104408264,
+      "learning_rate": 0.0002,
+      "loss": 0.6733,
+      "step": 2070
+    },
+    {
+      "epoch": 2.564734895191122,
+      "grad_norm": 0.9572727680206299,
+      "learning_rate": 0.0002,
+      "loss": 0.7791,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5770653514180024,
+      "grad_norm": 1.1970765590667725,
+      "learning_rate": 0.0002,
+      "loss": 0.7205,
+      "step": 2090
+    },
+    {
+      "epoch": 2.589395807644883,
+      "grad_norm": 0.5505942702293396,
+      "learning_rate": 0.0002,
+      "loss": 0.6736,
+      "step": 2100
+    },
+    {
+      "epoch": 2.6017262638717633,
+      "grad_norm": 0.5903949737548828,
+      "learning_rate": 0.0002,
+      "loss": 0.673,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6140567200986435,
+      "grad_norm": 0.45640307664871216,
+      "learning_rate": 0.0002,
+      "loss": 0.678,
+      "step": 2120
+    },
+    {
+      "epoch": 2.626387176325524,
+      "grad_norm": 0.8763944506645203,
+      "learning_rate": 0.0002,
+      "loss": 0.6562,
+      "step": 2130
+    },
+    {
+      "epoch": 2.6387176325524044,
+      "grad_norm": 0.4472963213920593,
+      "learning_rate": 0.0002,
+      "loss": 0.6484,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6510480887792847,
+      "grad_norm": 0.5335086584091187,
+      "learning_rate": 0.0002,
+      "loss": 0.7702,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6633785450061653,
+      "grad_norm": 0.805263340473175,
+      "learning_rate": 0.0002,
+      "loss": 0.6851,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6757090012330456,
+      "grad_norm": 0.6332727670669556,
+      "learning_rate": 0.0002,
+      "loss": 0.7026,
+      "step": 2170
+    },
+    {
+      "epoch": 2.688039457459926,
+      "grad_norm": 0.8667435646057129,
+      "learning_rate": 0.0002,
+      "loss": 0.7925,
+      "step": 2180
+    },
+    {
+      "epoch": 2.7003699136868065,
+      "grad_norm": 0.5638955235481262,
+      "learning_rate": 0.0002,
+      "loss": 0.8044,
+      "step": 2190
+    },
+    {
+      "epoch": 2.7127003699136867,
+      "grad_norm": 0.4176250696182251,
+      "learning_rate": 0.0002,
+      "loss": 0.7117,
+      "step": 2200
+    },
+    {
+      "epoch": 2.7250308261405674,
+      "grad_norm": 0.6013461351394653,
+      "learning_rate": 0.0002,
+      "loss": 0.6932,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7373612823674476,
+      "grad_norm": 0.553961992263794,
+      "learning_rate": 0.0002,
+      "loss": 0.7843,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7496917385943282,
+      "grad_norm": 0.4710180461406708,
+      "learning_rate": 0.0002,
+      "loss": 0.8633,
+      "step": 2230
+    },
+    {
+      "epoch": 2.7620221948212085,
+      "grad_norm": 0.8141706585884094,
+      "learning_rate": 0.0002,
+      "loss": 0.7469,
+      "step": 2240
+    },
+    {
+      "epoch": 2.7743526510480887,
+      "grad_norm": 0.7449556589126587,
+      "learning_rate": 0.0002,
+      "loss": 0.7086,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7866831072749694,
+      "grad_norm": 0.5366780757904053,
+      "learning_rate": 0.0002,
+      "loss": 0.6933,
+      "step": 2260
+    },
+    {
+      "epoch": 2.7990135635018496,
+      "grad_norm": 0.5316720604896545,
+      "learning_rate": 0.0002,
+      "loss": 0.7192,
+      "step": 2270
+    },
+    {
+      "epoch": 2.81134401972873,
+      "grad_norm": 0.4598459005355835,
+      "learning_rate": 0.0002,
+      "loss": 0.6212,
+      "step": 2280
+    },
+    {
+      "epoch": 2.8236744759556105,
+      "grad_norm": 0.6852091550827026,
+      "learning_rate": 0.0002,
+      "loss": 0.7024,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8360049321824907,
+      "grad_norm": 0.8040902018547058,
+      "learning_rate": 0.0002,
+      "loss": 0.7357,
+      "step": 2300
+    },
+    {
+      "epoch": 2.848335388409371,
+      "grad_norm": 0.46976321935653687,
+      "learning_rate": 0.0002,
+      "loss": 0.7563,
+      "step": 2310
+    },
+    {
+      "epoch": 2.8606658446362516,
+      "grad_norm": 0.5214090347290039,
+      "learning_rate": 0.0002,
+      "loss": 0.731,
+      "step": 2320
+    },
+    {
+      "epoch": 2.872996300863132,
+      "grad_norm": 0.5323054790496826,
+      "learning_rate": 0.0002,
+      "loss": 0.6687,
+      "step": 2330
+    },
+    {
+      "epoch": 2.885326757090012,
+      "grad_norm": 0.6842264533042908,
+      "learning_rate": 0.0002,
+      "loss": 0.7895,
+      "step": 2340
+    },
+    {
+      "epoch": 2.8976572133168927,
+      "grad_norm": 0.9157055616378784,
+      "learning_rate": 0.0002,
+      "loss": 0.7737,
+      "step": 2350
+    },
+    {
+      "epoch": 2.909987669543773,
+      "grad_norm": 0.5253258347511292,
+      "learning_rate": 0.0002,
+      "loss": 0.7217,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9223181257706536,
+      "grad_norm": 0.4937705099582672,
+      "learning_rate": 0.0002,
+      "loss": 0.7162,
+      "step": 2370
+    },
+    {
+      "epoch": 2.934648581997534,
+      "grad_norm": 0.48762989044189453,
+      "learning_rate": 0.0002,
+      "loss": 0.7008,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9469790382244145,
+      "grad_norm": 0.544335126876831,
+      "learning_rate": 0.0002,
+      "loss": 0.8086,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9593094944512948,
+      "grad_norm": 0.4847845435142517,
+      "learning_rate": 0.0002,
+      "loss": 0.643,
+      "step": 2400
+    },
+    {
+      "epoch": 2.971639950678175,
+      "grad_norm": 0.4787445366382599,
+      "learning_rate": 0.0002,
+      "loss": 0.7757,
+      "step": 2410
+    },
+    {
+      "epoch": 2.9839704069050557,
+      "grad_norm": 1.022318959236145,
+      "learning_rate": 0.0002,
+      "loss": 0.7678,
+      "step": 2420
+    },
+    {
+      "epoch": 2.996300863131936,
+      "grad_norm": 0.4987848103046417,
+      "learning_rate": 0.0002,
+      "loss": 0.6548,
+      "step": 2430
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2936296463012695,
+      "eval_runtime": 94.7897,
+      "eval_samples_per_second": 4.6,
+      "eval_steps_per_second": 0.58,
+      "step": 2433
+    },
+    {
+      "epoch": 3.008631319358816,
+      "grad_norm": 0.5562372803688049,
+      "learning_rate": 0.0002,
+      "loss": 0.6073,
+      "step": 2440
+    },
+    {
+      "epoch": 3.020961775585697,
+      "grad_norm": 1.133402705192566,
+      "learning_rate": 0.0002,
+      "loss": 0.5181,
+      "step": 2450
+    },
+    {
+      "epoch": 3.033292231812577,
+      "grad_norm": 0.6480470299720764,
+      "learning_rate": 0.0002,
+      "loss": 0.5333,
+      "step": 2460
+    },
+    {
+      "epoch": 3.0456226880394572,
+      "grad_norm": 0.8989138007164001,
+      "learning_rate": 0.0002,
+      "loss": 0.4828,
+      "step": 2470
+    },
+    {
+      "epoch": 3.057953144266338,
+      "grad_norm": 0.8257461786270142,
+      "learning_rate": 0.0002,
+      "loss": 0.5097,
+      "step": 2480
+    },
+    {
+      "epoch": 3.070283600493218,
+      "grad_norm": 0.6813381910324097,
+      "learning_rate": 0.0002,
+      "loss": 0.6229,
+      "step": 2490
+    },
+    {
+      "epoch": 3.082614056720099,
+      "grad_norm": 0.6989586353302002,
+      "learning_rate": 0.0002,
+      "loss": 0.531,
+      "step": 2500
+    },
+    {
+      "epoch": 3.094944512946979,
+      "grad_norm": 0.7992092967033386,
+      "learning_rate": 0.0002,
+      "loss": 0.54,
+      "step": 2510
+    },
+    {
+      "epoch": 3.1072749691738593,
+      "grad_norm": 0.698077917098999,
+      "learning_rate": 0.0002,
+      "loss": 0.5054,
+      "step": 2520
+    },
+    {
+      "epoch": 3.11960542540074,
+      "grad_norm": 0.5699033141136169,
+      "learning_rate": 0.0002,
+      "loss": 0.5064,
+      "step": 2530
+    },
+    {
+      "epoch": 3.13193588162762,
+      "grad_norm": 0.6142355799674988,
+      "learning_rate": 0.0002,
+      "loss": 0.6088,
+      "step": 2540
+    },
+    {
+      "epoch": 3.144266337854501,
+      "grad_norm": 0.7089933753013611,
+      "learning_rate": 0.0002,
+      "loss": 0.585,
+      "step": 2550
+    },
+    {
+      "epoch": 3.156596794081381,
+      "grad_norm": 1.0107015371322632,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 2560
+    },
+    {
+      "epoch": 3.1689272503082613,
+      "grad_norm": 0.568138837814331,
+      "learning_rate": 0.0002,
+      "loss": 0.5429,
+      "step": 2570
+    },
+    {
+      "epoch": 3.181257706535142,
+      "grad_norm": 0.9960416555404663,
+      "learning_rate": 0.0002,
+      "loss": 0.5897,
+      "step": 2580
+    },
+    {
+      "epoch": 3.193588162762022,
+      "grad_norm": 0.6277595162391663,
+      "learning_rate": 0.0002,
+      "loss": 0.5211,
+      "step": 2590
+    },
+    {
+      "epoch": 3.2059186189889024,
+      "grad_norm": 0.681083619594574,
+      "learning_rate": 0.0002,
+      "loss": 0.5787,
+      "step": 2600
+    },
+    {
+      "epoch": 3.218249075215783,
+      "grad_norm": 0.5816057324409485,
+      "learning_rate": 0.0002,
+      "loss": 0.5166,
+      "step": 2610
+    },
+    {
+      "epoch": 3.2305795314426633,
+      "grad_norm": 0.7197734117507935,
+      "learning_rate": 0.0002,
+      "loss": 0.545,
+      "step": 2620
+    },
+    {
+      "epoch": 3.242909987669544,
+      "grad_norm": 0.6524068117141724,
+      "learning_rate": 0.0002,
+      "loss": 0.614,
+      "step": 2630
+    },
+    {
+      "epoch": 3.255240443896424,
+      "grad_norm": 1.273668646812439,
+      "learning_rate": 0.0002,
+      "loss": 0.5456,
+      "step": 2640
+    },
+    {
+      "epoch": 3.2675709001233044,
+      "grad_norm": 0.6950451731681824,
+      "learning_rate": 0.0002,
+      "loss": 0.5266,
+      "step": 2650
+    },
+    {
+      "epoch": 3.279901356350185,
+      "grad_norm": 0.8029071688652039,
+      "learning_rate": 0.0002,
+      "loss": 0.5194,
+      "step": 2660
+    },
+    {
+      "epoch": 3.2922318125770653,
+      "grad_norm": 0.7464073896408081,
+      "learning_rate": 0.0002,
+      "loss": 0.5729,
+      "step": 2670
+    },
+    {
+      "epoch": 3.304562268803946,
+      "grad_norm": 0.8342001438140869,
+      "learning_rate": 0.0002,
+      "loss": 0.5366,
+      "step": 2680
+    },
+    {
+      "epoch": 3.316892725030826,
+      "grad_norm": 0.5629868507385254,
+      "learning_rate": 0.0002,
+      "loss": 0.5413,
+      "step": 2690
+    },
+    {
+      "epoch": 3.3292231812577064,
+      "grad_norm": 0.753999650478363,
+      "learning_rate": 0.0002,
+      "loss": 0.633,
+      "step": 2700
+    },
+    {
+      "epoch": 3.341553637484587,
+      "grad_norm": 1.0271371603012085,
+      "learning_rate": 0.0002,
+      "loss": 0.5048,
+      "step": 2710
+    },
+    {
+      "epoch": 3.3538840937114673,
+      "grad_norm": 0.9608535170555115,
+      "learning_rate": 0.0002,
+      "loss": 0.5233,
+      "step": 2720
+    },
+    {
+      "epoch": 3.3662145499383476,
+      "grad_norm": 0.7796488404273987,
+      "learning_rate": 0.0002,
+      "loss": 0.5102,
+      "step": 2730
+    },
+    {
+      "epoch": 3.3785450061652282,
+      "grad_norm": 0.5666437149047852,
+      "learning_rate": 0.0002,
+      "loss": 0.5172,
+      "step": 2740
+    },
+    {
+      "epoch": 3.3908754623921085,
+      "grad_norm": 0.5462956428527832,
+      "learning_rate": 0.0002,
+      "loss": 0.491,
+      "step": 2750
+    },
+    {
+      "epoch": 3.4032059186189887,
+      "grad_norm": 1.289099097251892,
+      "learning_rate": 0.0002,
+      "loss": 0.5855,
+      "step": 2760
+    },
+    {
+      "epoch": 3.4155363748458694,
+      "grad_norm": 0.825566828250885,
+      "learning_rate": 0.0002,
+      "loss": 0.635,
+      "step": 2770
+    },
+    {
+      "epoch": 3.4278668310727496,
+      "grad_norm": 0.8366670608520508,
+      "learning_rate": 0.0002,
+      "loss": 0.4998,
+      "step": 2780
+    },
+    {
+      "epoch": 3.4401972872996303,
+      "grad_norm": 1.0931549072265625,
+      "learning_rate": 0.0002,
+      "loss": 0.5732,
+      "step": 2790
+    },
+    {
+      "epoch": 3.4525277435265105,
+      "grad_norm": 0.9228858351707458,
+      "learning_rate": 0.0002,
+      "loss": 0.6093,
+      "step": 2800
+    },
+    {
+      "epoch": 3.4648581997533907,
+      "grad_norm": 1.3182806968688965,
+      "learning_rate": 0.0002,
+      "loss": 0.6089,
+      "step": 2810
+    },
+    {
+      "epoch": 3.4771886559802714,
+      "grad_norm": 0.8366976380348206,
+      "learning_rate": 0.0002,
+      "loss": 0.5665,
+      "step": 2820
+    },
+    {
+      "epoch": 3.4895191122071516,
+      "grad_norm": 0.8067695498466492,
+      "learning_rate": 0.0002,
+      "loss": 0.5666,
+      "step": 2830
+    },
+    {
+      "epoch": 3.5018495684340323,
+      "grad_norm": 1.1163437366485596,
+      "learning_rate": 0.0002,
+      "loss": 0.579,
+      "step": 2840
+    },
+    {
+      "epoch": 3.5141800246609125,
+      "grad_norm": 1.7196556329727173,
+      "learning_rate": 0.0002,
+      "loss": 0.5785,
+      "step": 2850
+    },
+    {
+      "epoch": 3.5265104808877927,
+      "grad_norm": 1.1267012357711792,
+      "learning_rate": 0.0002,
+      "loss": 0.5346,
+      "step": 2860
+    },
+    {
+      "epoch": 3.5388409371146734,
+      "grad_norm": 0.7220137119293213,
+      "learning_rate": 0.0002,
+      "loss": 0.447,
+      "step": 2870
+    },
+    {
+      "epoch": 3.5511713933415536,
+      "grad_norm": 0.914114773273468,
+      "learning_rate": 0.0002,
+      "loss": 0.6099,
+      "step": 2880
+    },
+    {
+      "epoch": 3.563501849568434,
+      "grad_norm": 0.6193503141403198,
+      "learning_rate": 0.0002,
+      "loss": 0.6143,
+      "step": 2890
+    },
+    {
+      "epoch": 3.5758323057953145,
+      "grad_norm": 0.6060135960578918,
+      "learning_rate": 0.0002,
+      "loss": 0.5171,
+      "step": 2900
+    },
+    {
+      "epoch": 3.5881627620221948,
+      "grad_norm": 1.0177327394485474,
+      "learning_rate": 0.0002,
+      "loss": 0.5659,
+      "step": 2910
+    },
+    {
+      "epoch": 3.600493218249075,
+      "grad_norm": 0.5994468331336975,
+      "learning_rate": 0.0002,
+      "loss": 0.5711,
+      "step": 2920
+    },
+    {
+      "epoch": 3.6128236744759556,
+      "grad_norm": 0.7450457215309143,
+      "learning_rate": 0.0002,
+      "loss": 0.6373,
+      "step": 2930
+    },
+    {
+      "epoch": 3.625154130702836,
+      "grad_norm": 0.5825870037078857,
+      "learning_rate": 0.0002,
+      "loss": 0.4933,
+      "step": 2940
+    },
+    {
+      "epoch": 3.6374845869297165,
+      "grad_norm": 0.6289743781089783,
+      "learning_rate": 0.0002,
+      "loss": 0.6016,
+      "step": 2950
+    },
+    {
+      "epoch": 3.6498150431565968,
+      "grad_norm": 0.7801929116249084,
+      "learning_rate": 0.0002,
+      "loss": 0.5507,
+      "step": 2960
+    },
+    {
+      "epoch": 3.6621454993834774,
+      "grad_norm": 1.1206634044647217,
+      "learning_rate": 0.0002,
+      "loss": 0.5695,
+      "step": 2970
+    },
+    {
+      "epoch": 3.6744759556103577,
+      "grad_norm": 0.6738817691802979,
+      "learning_rate": 0.0002,
+      "loss": 0.4985,
+      "step": 2980
+    },
+    {
+      "epoch": 3.686806411837238,
+      "grad_norm": 1.1917344331741333,
+      "learning_rate": 0.0002,
+      "loss": 0.6209,
+      "step": 2990
+    },
+    {
+      "epoch": 3.6991368680641186,
+      "grad_norm": 1.3738657236099243,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 3000
+    },
+    {
+      "epoch": 3.711467324290999,
+      "grad_norm": 0.6642793416976929,
+      "learning_rate": 0.0002,
+      "loss": 0.5467,
+      "step": 3010
+    },
+    {
+      "epoch": 3.723797780517879,
+      "grad_norm": 0.9030995965003967,
+      "learning_rate": 0.0002,
+      "loss": 0.6243,
+      "step": 3020
+    },
+    {
+      "epoch": 3.7361282367447597,
+      "grad_norm": 1.0203914642333984,
+      "learning_rate": 0.0002,
+      "loss": 0.592,
+      "step": 3030
+    },
+    {
+      "epoch": 3.74845869297164,
+      "grad_norm": 0.648394763469696,
+      "learning_rate": 0.0002,
+      "loss": 0.5453,
+      "step": 3040
+    },
+    {
+      "epoch": 3.76078914919852,
+      "grad_norm": 0.6304570436477661,
+      "learning_rate": 0.0002,
+      "loss": 0.498,
+      "step": 3050
+    },
+    {
+      "epoch": 3.773119605425401,
+      "grad_norm": 0.8286601901054382,
+      "learning_rate": 0.0002,
+      "loss": 0.683,
+      "step": 3060
+    },
+    {
+      "epoch": 3.785450061652281,
+      "grad_norm": 0.906444251537323,
+      "learning_rate": 0.0002,
+      "loss": 0.5302,
+      "step": 3070
+    },
+    {
+      "epoch": 3.7977805178791613,
+      "grad_norm": 1.4212149381637573,
+      "learning_rate": 0.0002,
+      "loss": 0.5345,
+      "step": 3080
+    },
+    {
+      "epoch": 3.810110974106042,
+      "grad_norm": 0.7574319839477539,
+      "learning_rate": 0.0002,
+      "loss": 0.6403,
+      "step": 3090
+    },
+    {
+      "epoch": 3.822441430332922,
+      "grad_norm": 0.6534451246261597,
+      "learning_rate": 0.0002,
+      "loss": 0.5756,
+      "step": 3100
+    },
+    {
+      "epoch": 3.834771886559803,
+      "grad_norm": 0.7525447010993958,
+      "learning_rate": 0.0002,
+      "loss": 0.5306,
+      "step": 3110
+    },
+    {
+      "epoch": 3.847102342786683,
+      "grad_norm": 0.6513990759849548,
+      "learning_rate": 0.0002,
+      "loss": 0.5368,
+      "step": 3120
+    },
+    {
+      "epoch": 3.8594327990135637,
+      "grad_norm": 0.7782694697380066,
+      "learning_rate": 0.0002,
+      "loss": 0.5492,
+      "step": 3130
+    },
+    {
+      "epoch": 3.871763255240444,
+      "grad_norm": 0.7998530268669128,
+      "learning_rate": 0.0002,
+      "loss": 0.5727,
+      "step": 3140
+    },
+    {
+      "epoch": 3.884093711467324,
+      "grad_norm": 0.8045353293418884,
+      "learning_rate": 0.0002,
+      "loss": 0.5156,
+      "step": 3150
+    },
+    {
+      "epoch": 3.896424167694205,
+      "grad_norm": 0.8242645263671875,
+      "learning_rate": 0.0002,
+      "loss": 0.5341,
+      "step": 3160
+    },
+    {
+      "epoch": 3.908754623921085,
+      "grad_norm": 0.8302360773086548,
+      "learning_rate": 0.0002,
+      "loss": 0.5563,
+      "step": 3170
+    },
+    {
+      "epoch": 3.9210850801479653,
+      "grad_norm": 0.8653109073638916,
+      "learning_rate": 0.0002,
+      "loss": 0.5793,
+      "step": 3180
+    },
+    {
+      "epoch": 3.933415536374846,
+      "grad_norm": 0.6461338996887207,
+      "learning_rate": 0.0002,
+      "loss": 0.5219,
+      "step": 3190
+    },
+    {
+      "epoch": 3.945745992601726,
+      "grad_norm": 0.8267415165901184,
+      "learning_rate": 0.0002,
+      "loss": 0.6009,
+      "step": 3200
+    },
+    {
+      "epoch": 3.9580764488286064,
+      "grad_norm": 1.1963194608688354,
+      "learning_rate": 0.0002,
+      "loss": 0.5956,
+      "step": 3210
+    },
+    {
+      "epoch": 3.970406905055487,
+      "grad_norm": 0.7101966142654419,
+      "learning_rate": 0.0002,
+      "loss": 0.5692,
+      "step": 3220
+    },
+    {
+      "epoch": 3.9827373612823673,
+      "grad_norm": 0.5931660532951355,
+      "learning_rate": 0.0002,
+      "loss": 0.5471,
+      "step": 3230
+    },
+    {
+      "epoch": 3.995067817509248,
+      "grad_norm": 0.7465988993644714,
+      "learning_rate": 0.0002,
+      "loss": 0.5619,
+      "step": 3240
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4066498279571533,
+      "eval_runtime": 95.7145,
+      "eval_samples_per_second": 4.555,
+      "eval_steps_per_second": 0.575,
+      "step": 3244
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6488,
+  "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": 1.6662399081775104e+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-0.6-num-5885-sd-10000/checkpoint-3244/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-0.6-num-5885-sd-10000/checkpoint-3244/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..459ba5959a39ea126110113c9faed75cda19ffff
--- /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-0.6-num-5885-sd-10000/checkpoint-3244/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05287f447dfde244c1a85dc0f576593b4a9dd61961eb0797da4844688fc48447
+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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e04e4441e0c1b29f69c16b26c142944e440b8076
--- /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-0.6-num-5885-sd-10000/checkpoint-4055/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": [
+    "q_proj",
+    "v_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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9d32ce67bf19f9ae0f1f748ab6885e8fd375ae59
--- /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-0.6-num-5885-sd-10000/checkpoint-4055/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9786380ee461ab167b48ed45d7cab6fe7094739f47f6a289d7af4b8dbce5f32
+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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e2418a195bae7a0e5c9e7414002a84e91e188bdf
--- /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-0.6-num-5885-sd-10000/checkpoint-4055/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b540c0bafda6b1b36ff3606a04dbc7c435a3c90649787c75efe0834bc6bfa2
+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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1d180450c89011f65f5e86d532745005d7b2a98c
--- /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-0.6-num-5885-sd-10000/checkpoint-4055/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e8376d55b7ad0f26d2ad80687f603a0e7227268397353a249ca7fb285073fa
+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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..444d4820854e1010c6e443f3b82a9df3f3968356
--- /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-0.6-num-5885-sd-10000/checkpoint-4055/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edf44369560a6c20c2f557bcf58956ff63bc4bddae5bb9da652c28530e4c47b5
+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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22
--- /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-0.6-num-5885-sd-10000/checkpoint-4055/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873
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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..7815ab576e5e2478c6394f873e8ce71cdbdeb276
--- /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-0.6-num-5885-sd-10000/checkpoint-4055/trainer_state.json
@@ -0,0 +1,2908 @@
+{
+  "best_metric": 1.238026738166809,
+  "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-0.6-num-5885-sd-10000/checkpoint-1622",
+  "epoch": 5.0,
+  "eval_steps": 10,
+  "global_step": 4055,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012330456226880395,
+      "grad_norm": 0.8258164525032043,
+      "learning_rate": 0.0002,
+      "loss": 2.3601,
+      "step": 10
+    },
+    {
+      "epoch": 0.02466091245376079,
+      "grad_norm": 0.4577729105949402,
+      "learning_rate": 0.0002,
+      "loss": 1.7317,
+      "step": 20
+    },
+    {
+      "epoch": 0.036991368680641186,
+      "grad_norm": 0.639807939529419,
+      "learning_rate": 0.0002,
+      "loss": 1.4729,
+      "step": 30
+    },
+    {
+      "epoch": 0.04932182490752158,
+      "grad_norm": 0.5311757922172546,
+      "learning_rate": 0.0002,
+      "loss": 1.2088,
+      "step": 40
+    },
+    {
+      "epoch": 0.06165228113440197,
+      "grad_norm": 0.386595219373703,
+      "learning_rate": 0.0002,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.07398273736128237,
+      "grad_norm": 0.4401357173919678,
+      "learning_rate": 0.0002,
+      "loss": 1.1657,
+      "step": 60
+    },
+    {
+      "epoch": 0.08631319358816276,
+      "grad_norm": 0.3234352171421051,
+      "learning_rate": 0.0002,
+      "loss": 1.1022,
+      "step": 70
+    },
+    {
+      "epoch": 0.09864364981504316,
+      "grad_norm": 0.29643672704696655,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 80
+    },
+    {
+      "epoch": 0.11097410604192355,
+      "grad_norm": 0.2941012382507324,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 90
+    },
+    {
+      "epoch": 0.12330456226880394,
+      "grad_norm": 0.5498173832893372,
+      "learning_rate": 0.0002,
+      "loss": 1.2067,
+      "step": 100
+    },
+    {
+      "epoch": 0.13563501849568435,
+      "grad_norm": 0.2545783519744873,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 110
+    },
+    {
+      "epoch": 0.14796547472256474,
+      "grad_norm": 0.2984241247177124,
+      "learning_rate": 0.0002,
+      "loss": 1.0297,
+      "step": 120
+    },
+    {
+      "epoch": 0.16029593094944514,
+      "grad_norm": 0.2710968852043152,
+      "learning_rate": 0.0002,
+      "loss": 1.1591,
+      "step": 130
+    },
+    {
+      "epoch": 0.17262638717632553,
+      "grad_norm": 0.2817152142524719,
+      "learning_rate": 0.0002,
+      "loss": 1.0427,
+      "step": 140
+    },
+    {
+      "epoch": 0.18495684340320592,
+      "grad_norm": 0.41083765029907227,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 150
+    },
+    {
+      "epoch": 0.19728729963008632,
+      "grad_norm": 0.36536213755607605,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 160
+    },
+    {
+      "epoch": 0.2096177558569667,
+      "grad_norm": 0.2738671600818634,
+      "learning_rate": 0.0002,
+      "loss": 1.0132,
+      "step": 170
+    },
+    {
+      "epoch": 0.2219482120838471,
+      "grad_norm": 0.27403146028518677,
+      "learning_rate": 0.0002,
+      "loss": 0.9555,
+      "step": 180
+    },
+    {
+      "epoch": 0.2342786683107275,
+      "grad_norm": 0.4446810483932495,
+      "learning_rate": 0.0002,
+      "loss": 1.0769,
+      "step": 190
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "grad_norm": 0.5295385718345642,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 200
+    },
+    {
+      "epoch": 0.2589395807644883,
+      "grad_norm": 0.311404824256897,
+      "learning_rate": 0.0002,
+      "loss": 1.0827,
+      "step": 210
+    },
+    {
+      "epoch": 0.2712700369913687,
+      "grad_norm": 0.2448509782552719,
+      "learning_rate": 0.0002,
+      "loss": 1.1455,
+      "step": 220
+    },
+    {
+      "epoch": 0.2836004932182491,
+      "grad_norm": 0.6507014036178589,
+      "learning_rate": 0.0002,
+      "loss": 1.0929,
+      "step": 230
+    },
+    {
+      "epoch": 0.2959309494451295,
+      "grad_norm": 0.2339320331811905,
+      "learning_rate": 0.0002,
+      "loss": 0.9875,
+      "step": 240
+    },
+    {
+      "epoch": 0.3082614056720099,
+      "grad_norm": 0.8210226893424988,
+      "learning_rate": 0.0002,
+      "loss": 0.9211,
+      "step": 250
+    },
+    {
+      "epoch": 0.3205918618988903,
+      "grad_norm": 0.27473965287208557,
+      "learning_rate": 0.0002,
+      "loss": 1.161,
+      "step": 260
+    },
+    {
+      "epoch": 0.33292231812577067,
+      "grad_norm": 0.3051395118236542,
+      "learning_rate": 0.0002,
+      "loss": 1.0218,
+      "step": 270
+    },
+    {
+      "epoch": 0.34525277435265106,
+      "grad_norm": 0.3037777245044708,
+      "learning_rate": 0.0002,
+      "loss": 1.0286,
+      "step": 280
+    },
+    {
+      "epoch": 0.35758323057953145,
+      "grad_norm": 0.2748974859714508,
+      "learning_rate": 0.0002,
+      "loss": 1.144,
+      "step": 290
+    },
+    {
+      "epoch": 0.36991368680641185,
+      "grad_norm": 0.23656068742275238,
+      "learning_rate": 0.0002,
+      "loss": 1.0858,
+      "step": 300
+    },
+    {
+      "epoch": 0.38224414303329224,
+      "grad_norm": 0.2523384094238281,
+      "learning_rate": 0.0002,
+      "loss": 1.0564,
+      "step": 310
+    },
+    {
+      "epoch": 0.39457459926017263,
+      "grad_norm": 0.27848055958747864,
+      "learning_rate": 0.0002,
+      "loss": 1.3091,
+      "step": 320
+    },
+    {
+      "epoch": 0.406905055487053,
+      "grad_norm": 0.3204525411128998,
+      "learning_rate": 0.0002,
+      "loss": 1.0252,
+      "step": 330
+    },
+    {
+      "epoch": 0.4192355117139334,
+      "grad_norm": 0.3459707498550415,
+      "learning_rate": 0.0002,
+      "loss": 0.9855,
+      "step": 340
+    },
+    {
+      "epoch": 0.4315659679408138,
+      "grad_norm": 0.2458430379629135,
+      "learning_rate": 0.0002,
+      "loss": 1.1111,
+      "step": 350
+    },
+    {
+      "epoch": 0.4438964241676942,
+      "grad_norm": 0.5022910237312317,
+      "learning_rate": 0.0002,
+      "loss": 1.1493,
+      "step": 360
+    },
+    {
+      "epoch": 0.4562268803945746,
+      "grad_norm": 0.27076372504234314,
+      "learning_rate": 0.0002,
+      "loss": 1.1272,
+      "step": 370
+    },
+    {
+      "epoch": 0.468557336621455,
+      "grad_norm": 0.6489047408103943,
+      "learning_rate": 0.0002,
+      "loss": 1.1927,
+      "step": 380
+    },
+    {
+      "epoch": 0.4808877928483354,
+      "grad_norm": 0.3324144184589386,
+      "learning_rate": 0.0002,
+      "loss": 0.9501,
+      "step": 390
+    },
+    {
+      "epoch": 0.4932182490752158,
+      "grad_norm": 0.32813116908073425,
+      "learning_rate": 0.0002,
+      "loss": 1.2012,
+      "step": 400
+    },
+    {
+      "epoch": 0.5055487053020962,
+      "grad_norm": 0.25295355916023254,
+      "learning_rate": 0.0002,
+      "loss": 1.1135,
+      "step": 410
+    },
+    {
+      "epoch": 0.5178791615289766,
+      "grad_norm": 0.2912578880786896,
+      "learning_rate": 0.0002,
+      "loss": 0.9477,
+      "step": 420
+    },
+    {
+      "epoch": 0.530209617755857,
+      "grad_norm": 0.34780189394950867,
+      "learning_rate": 0.0002,
+      "loss": 1.0121,
+      "step": 430
+    },
+    {
+      "epoch": 0.5425400739827374,
+      "grad_norm": 0.24604526162147522,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 440
+    },
+    {
+      "epoch": 0.5548705302096177,
+      "grad_norm": 0.32759982347488403,
+      "learning_rate": 0.0002,
+      "loss": 1.253,
+      "step": 450
+    },
+    {
+      "epoch": 0.5672009864364982,
+      "grad_norm": 0.40810221433639526,
+      "learning_rate": 0.0002,
+      "loss": 1.1925,
+      "step": 460
+    },
+    {
+      "epoch": 0.5795314426633785,
+      "grad_norm": 0.3590679466724396,
+      "learning_rate": 0.0002,
+      "loss": 1.174,
+      "step": 470
+    },
+    {
+      "epoch": 0.591861898890259,
+      "grad_norm": 0.5656213760375977,
+      "learning_rate": 0.0002,
+      "loss": 1.2223,
+      "step": 480
+    },
+    {
+      "epoch": 0.6041923551171393,
+      "grad_norm": 0.30830657482147217,
+      "learning_rate": 0.0002,
+      "loss": 1.1936,
+      "step": 490
+    },
+    {
+      "epoch": 0.6165228113440198,
+      "grad_norm": 0.317905455827713,
+      "learning_rate": 0.0002,
+      "loss": 1.1873,
+      "step": 500
+    },
+    {
+      "epoch": 0.6288532675709001,
+      "grad_norm": 0.3254566490650177,
+      "learning_rate": 0.0002,
+      "loss": 0.9805,
+      "step": 510
+    },
+    {
+      "epoch": 0.6411837237977805,
+      "grad_norm": 0.29187721014022827,
+      "learning_rate": 0.0002,
+      "loss": 1.0384,
+      "step": 520
+    },
+    {
+      "epoch": 0.6535141800246609,
+      "grad_norm": 0.3439238965511322,
+      "learning_rate": 0.0002,
+      "loss": 1.2526,
+      "step": 530
+    },
+    {
+      "epoch": 0.6658446362515413,
+      "grad_norm": 0.20970556139945984,
+      "learning_rate": 0.0002,
+      "loss": 1.0698,
+      "step": 540
+    },
+    {
+      "epoch": 0.6781750924784217,
+      "grad_norm": 0.4022853374481201,
+      "learning_rate": 0.0002,
+      "loss": 1.1047,
+      "step": 550
+    },
+    {
+      "epoch": 0.6905055487053021,
+      "grad_norm": 0.2235759049654007,
+      "learning_rate": 0.0002,
+      "loss": 1.0684,
+      "step": 560
+    },
+    {
+      "epoch": 0.7028360049321825,
+      "grad_norm": 0.33849895000457764,
+      "learning_rate": 0.0002,
+      "loss": 1.2339,
+      "step": 570
+    },
+    {
+      "epoch": 0.7151664611590629,
+      "grad_norm": 0.34745967388153076,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 580
+    },
+    {
+      "epoch": 0.7274969173859432,
+      "grad_norm": 0.26041269302368164,
+      "learning_rate": 0.0002,
+      "loss": 1.1158,
+      "step": 590
+    },
+    {
+      "epoch": 0.7398273736128237,
+      "grad_norm": 0.3804777264595032,
+      "learning_rate": 0.0002,
+      "loss": 1.2134,
+      "step": 600
+    },
+    {
+      "epoch": 0.752157829839704,
+      "grad_norm": 0.2456253319978714,
+      "learning_rate": 0.0002,
+      "loss": 1.0606,
+      "step": 610
+    },
+    {
+      "epoch": 0.7644882860665845,
+      "grad_norm": 0.37838423252105713,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 620
+    },
+    {
+      "epoch": 0.7768187422934648,
+      "grad_norm": 0.28105494379997253,
+      "learning_rate": 0.0002,
+      "loss": 1.0556,
+      "step": 630
+    },
+    {
+      "epoch": 0.7891491985203453,
+      "grad_norm": 0.2774018943309784,
+      "learning_rate": 0.0002,
+      "loss": 1.0672,
+      "step": 640
+    },
+    {
+      "epoch": 0.8014796547472256,
+      "grad_norm": 1.8184229135513306,
+      "learning_rate": 0.0002,
+      "loss": 0.9978,
+      "step": 650
+    },
+    {
+      "epoch": 0.813810110974106,
+      "grad_norm": 0.3325096070766449,
+      "learning_rate": 0.0002,
+      "loss": 1.1038,
+      "step": 660
+    },
+    {
+      "epoch": 0.8261405672009864,
+      "grad_norm": 0.2686693072319031,
+      "learning_rate": 0.0002,
+      "loss": 1.083,
+      "step": 670
+    },
+    {
+      "epoch": 0.8384710234278668,
+      "grad_norm": 0.3271431624889374,
+      "learning_rate": 0.0002,
+      "loss": 1.1308,
+      "step": 680
+    },
+    {
+      "epoch": 0.8508014796547472,
+      "grad_norm": 2.359999656677246,
+      "learning_rate": 0.0002,
+      "loss": 1.1116,
+      "step": 690
+    },
+    {
+      "epoch": 0.8631319358816276,
+      "grad_norm": 0.46242964267730713,
+      "learning_rate": 0.0002,
+      "loss": 1.0782,
+      "step": 700
+    },
+    {
+      "epoch": 0.8754623921085081,
+      "grad_norm": 0.34731170535087585,
+      "learning_rate": 0.0002,
+      "loss": 0.95,
+      "step": 710
+    },
+    {
+      "epoch": 0.8877928483353884,
+      "grad_norm": 0.39381715655326843,
+      "learning_rate": 0.0002,
+      "loss": 1.2236,
+      "step": 720
+    },
+    {
+      "epoch": 0.9001233045622689,
+      "grad_norm": 0.43496373295783997,
+      "learning_rate": 0.0002,
+      "loss": 1.1319,
+      "step": 730
+    },
+    {
+      "epoch": 0.9124537607891492,
+      "grad_norm": 0.32243210077285767,
+      "learning_rate": 0.0002,
+      "loss": 1.0979,
+      "step": 740
+    },
+    {
+      "epoch": 0.9247842170160296,
+      "grad_norm": 0.30396756529808044,
+      "learning_rate": 0.0002,
+      "loss": 0.9913,
+      "step": 750
+    },
+    {
+      "epoch": 0.93711467324291,
+      "grad_norm": 0.4461122751235962,
+      "learning_rate": 0.0002,
+      "loss": 1.1141,
+      "step": 760
+    },
+    {
+      "epoch": 0.9494451294697904,
+      "grad_norm": 0.24081681668758392,
+      "learning_rate": 0.0002,
+      "loss": 1.0049,
+      "step": 770
+    },
+    {
+      "epoch": 0.9617755856966708,
+      "grad_norm": 0.27461910247802734,
+      "learning_rate": 0.0002,
+      "loss": 1.0966,
+      "step": 780
+    },
+    {
+      "epoch": 0.9741060419235512,
+      "grad_norm": 0.3325668275356293,
+      "learning_rate": 0.0002,
+      "loss": 0.9942,
+      "step": 790
+    },
+    {
+      "epoch": 0.9864364981504316,
+      "grad_norm": 0.24046339094638824,
+      "learning_rate": 0.0002,
+      "loss": 1.0506,
+      "step": 800
+    },
+    {
+      "epoch": 0.998766954377312,
+      "grad_norm": 0.42950066924095154,
+      "learning_rate": 0.0002,
+      "loss": 0.9989,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.246457576751709,
+      "eval_runtime": 98.7974,
+      "eval_samples_per_second": 4.413,
+      "eval_steps_per_second": 0.557,
+      "step": 811
+    },
+    {
+      "epoch": 1.0110974106041923,
+      "grad_norm": 0.26760655641555786,
+      "learning_rate": 0.0002,
+      "loss": 1.0536,
+      "step": 820
+    },
+    {
+      "epoch": 1.0234278668310728,
+      "grad_norm": 0.4640820026397705,
+      "learning_rate": 0.0002,
+      "loss": 0.9722,
+      "step": 830
+    },
+    {
+      "epoch": 1.0357583230579532,
+      "grad_norm": 0.2699166238307953,
+      "learning_rate": 0.0002,
+      "loss": 0.9392,
+      "step": 840
+    },
+    {
+      "epoch": 1.0480887792848335,
+      "grad_norm": 0.3441709578037262,
+      "learning_rate": 0.0002,
+      "loss": 0.9335,
+      "step": 850
+    },
+    {
+      "epoch": 1.060419235511714,
+      "grad_norm": 0.299934983253479,
+      "learning_rate": 0.0002,
+      "loss": 0.9083,
+      "step": 860
+    },
+    {
+      "epoch": 1.0727496917385944,
+      "grad_norm": 0.2980666160583496,
+      "learning_rate": 0.0002,
+      "loss": 0.9416,
+      "step": 870
+    },
+    {
+      "epoch": 1.0850801479654748,
+      "grad_norm": 0.3131714463233948,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 880
+    },
+    {
+      "epoch": 1.097410604192355,
+      "grad_norm": 0.29881617426872253,
+      "learning_rate": 0.0002,
+      "loss": 0.9288,
+      "step": 890
+    },
+    {
+      "epoch": 1.1097410604192355,
+      "grad_norm": 0.29870888590812683,
+      "learning_rate": 0.0002,
+      "loss": 0.998,
+      "step": 900
+    },
+    {
+      "epoch": 1.122071516646116,
+      "grad_norm": 0.5735140442848206,
+      "learning_rate": 0.0002,
+      "loss": 0.9924,
+      "step": 910
+    },
+    {
+      "epoch": 1.1344019728729964,
+      "grad_norm": 0.33159002661705017,
+      "learning_rate": 0.0002,
+      "loss": 1.0694,
+      "step": 920
+    },
+    {
+      "epoch": 1.1467324290998766,
+      "grad_norm": 1.235399842262268,
+      "learning_rate": 0.0002,
+      "loss": 1.0069,
+      "step": 930
+    },
+    {
+      "epoch": 1.159062885326757,
+      "grad_norm": 0.27469736337661743,
+      "learning_rate": 0.0002,
+      "loss": 1.0315,
+      "step": 940
+    },
+    {
+      "epoch": 1.1713933415536375,
+      "grad_norm": 0.29130664467811584,
+      "learning_rate": 0.0002,
+      "loss": 0.9386,
+      "step": 950
+    },
+    {
+      "epoch": 1.183723797780518,
+      "grad_norm": 0.3730354607105255,
+      "learning_rate": 0.0002,
+      "loss": 0.8919,
+      "step": 960
+    },
+    {
+      "epoch": 1.1960542540073984,
+      "grad_norm": 0.5973590612411499,
+      "learning_rate": 0.0002,
+      "loss": 0.9988,
+      "step": 970
+    },
+    {
+      "epoch": 1.2083847102342786,
+      "grad_norm": 0.39631304144859314,
+      "learning_rate": 0.0002,
+      "loss": 0.9525,
+      "step": 980
+    },
+    {
+      "epoch": 1.220715166461159,
+      "grad_norm": 0.849051296710968,
+      "learning_rate": 0.0002,
+      "loss": 0.9217,
+      "step": 990
+    },
+    {
+      "epoch": 1.2330456226880395,
+      "grad_norm": 0.4390525817871094,
+      "learning_rate": 0.0002,
+      "loss": 1.0903,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2453760789149197,
+      "grad_norm": 0.30423852801322937,
+      "learning_rate": 0.0002,
+      "loss": 0.9018,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2577065351418002,
+      "grad_norm": 0.34736061096191406,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2700369913686806,
+      "grad_norm": 0.3421604037284851,
+      "learning_rate": 0.0002,
+      "loss": 0.9026,
+      "step": 1030
+    },
+    {
+      "epoch": 1.282367447595561,
+      "grad_norm": 0.544170081615448,
+      "learning_rate": 0.0002,
+      "loss": 0.8485,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2946979038224415,
+      "grad_norm": 0.5128790736198425,
+      "learning_rate": 0.0002,
+      "loss": 0.9591,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3070283600493218,
+      "grad_norm": 0.443344384431839,
+      "learning_rate": 0.0002,
+      "loss": 0.9214,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3193588162762022,
+      "grad_norm": 0.6380868554115295,
+      "learning_rate": 0.0002,
+      "loss": 0.9367,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3316892725030827,
+      "grad_norm": 0.4638073146343231,
+      "learning_rate": 0.0002,
+      "loss": 0.9849,
+      "step": 1080
+    },
+    {
+      "epoch": 1.344019728729963,
+      "grad_norm": 0.32406893372535706,
+      "learning_rate": 0.0002,
+      "loss": 0.8645,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3563501849568433,
+      "grad_norm": 0.3955065608024597,
+      "learning_rate": 0.0002,
+      "loss": 0.8278,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3686806411837238,
+      "grad_norm": 0.3489246666431427,
+      "learning_rate": 0.0002,
+      "loss": 0.9306,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3810110974106042,
+      "grad_norm": 0.48451653122901917,
+      "learning_rate": 0.0002,
+      "loss": 1.0138,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3933415536374847,
+      "grad_norm": 0.3652360439300537,
+      "learning_rate": 0.0002,
+      "loss": 0.9165,
+      "step": 1130
+    },
+    {
+      "epoch": 1.405672009864365,
+      "grad_norm": 1.3097436428070068,
+      "learning_rate": 0.0002,
+      "loss": 0.9576,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4180024660912454,
+      "grad_norm": 0.3647715449333191,
+      "learning_rate": 0.0002,
+      "loss": 0.8115,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4303329223181258,
+      "grad_norm": 0.37248560786247253,
+      "learning_rate": 0.0002,
+      "loss": 0.8573,
+      "step": 1160
+    },
+    {
+      "epoch": 1.442663378545006,
+      "grad_norm": 0.4639643430709839,
+      "learning_rate": 0.0002,
+      "loss": 0.936,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4549938347718865,
+      "grad_norm": 0.5455219745635986,
+      "learning_rate": 0.0002,
+      "loss": 0.9511,
+      "step": 1180
+    },
+    {
+      "epoch": 1.467324290998767,
+      "grad_norm": 0.38862571120262146,
+      "learning_rate": 0.0002,
+      "loss": 0.8611,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4796547472256474,
+      "grad_norm": 0.37586215138435364,
+      "learning_rate": 0.0002,
+      "loss": 0.8681,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4919852034525278,
+      "grad_norm": 0.46244436502456665,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1210
+    },
+    {
+      "epoch": 1.504315659679408,
+      "grad_norm": 0.3570359945297241,
+      "learning_rate": 0.0002,
+      "loss": 0.9388,
+      "step": 1220
+    },
+    {
+      "epoch": 1.5166461159062885,
+      "grad_norm": 0.28393083810806274,
+      "learning_rate": 0.0002,
+      "loss": 0.971,
+      "step": 1230
+    },
+    {
+      "epoch": 1.528976572133169,
+      "grad_norm": 0.5672869682312012,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5413070283600492,
+      "grad_norm": 0.41605108976364136,
+      "learning_rate": 0.0002,
+      "loss": 0.8787,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5536374845869299,
+      "grad_norm": 0.40657493472099304,
+      "learning_rate": 0.0002,
+      "loss": 0.8744,
+      "step": 1260
+    },
+    {
+      "epoch": 1.56596794081381,
+      "grad_norm": 0.43672341108322144,
+      "learning_rate": 0.0002,
+      "loss": 0.9046,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5782983970406905,
+      "grad_norm": 0.3065410554409027,
+      "learning_rate": 0.0002,
+      "loss": 0.8586,
+      "step": 1280
+    },
+    {
+      "epoch": 1.590628853267571,
+      "grad_norm": 0.37826645374298096,
+      "learning_rate": 0.0002,
+      "loss": 0.9499,
+      "step": 1290
+    },
+    {
+      "epoch": 1.6029593094944512,
+      "grad_norm": 0.42307335138320923,
+      "learning_rate": 0.0002,
+      "loss": 0.901,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6152897657213316,
+      "grad_norm": 0.3648843467235565,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1310
+    },
+    {
+      "epoch": 1.627620221948212,
+      "grad_norm": 0.8921076059341431,
+      "learning_rate": 0.0002,
+      "loss": 0.9302,
+      "step": 1320
+    },
+    {
+      "epoch": 1.6399506781750923,
+      "grad_norm": 0.37522226572036743,
+      "learning_rate": 0.0002,
+      "loss": 0.9378,
+      "step": 1330
+    },
+    {
+      "epoch": 1.652281134401973,
+      "grad_norm": 0.7489957809448242,
+      "learning_rate": 0.0002,
+      "loss": 0.8921,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6646115906288532,
+      "grad_norm": 0.31733131408691406,
+      "learning_rate": 0.0002,
+      "loss": 0.9297,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6769420468557337,
+      "grad_norm": 0.3249478340148926,
+      "learning_rate": 0.0002,
+      "loss": 0.907,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6892725030826141,
+      "grad_norm": 0.3178001344203949,
+      "learning_rate": 0.0002,
+      "loss": 1.0197,
+      "step": 1370
+    },
+    {
+      "epoch": 1.7016029593094943,
+      "grad_norm": 0.5674093961715698,
+      "learning_rate": 0.0002,
+      "loss": 1.0781,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7139334155363748,
+      "grad_norm": 0.35272449254989624,
+      "learning_rate": 0.0002,
+      "loss": 0.8972,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7262638717632552,
+      "grad_norm": 0.5778217911720276,
+      "learning_rate": 0.0002,
+      "loss": 0.9346,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7385943279901355,
+      "grad_norm": 0.33561450242996216,
+      "learning_rate": 0.0002,
+      "loss": 0.9099,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7509247842170161,
+      "grad_norm": 0.31735464930534363,
+      "learning_rate": 0.0002,
+      "loss": 0.8636,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7632552404438964,
+      "grad_norm": 1.0612670183181763,
+      "learning_rate": 0.0002,
+      "loss": 0.982,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7755856966707768,
+      "grad_norm": 0.5442509651184082,
+      "learning_rate": 0.0002,
+      "loss": 0.8224,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7879161528976573,
+      "grad_norm": 0.7471332550048828,
+      "learning_rate": 0.0002,
+      "loss": 0.9275,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8002466091245375,
+      "grad_norm": 0.4323609173297882,
+      "learning_rate": 0.0002,
+      "loss": 0.9389,
+      "step": 1460
+    },
+    {
+      "epoch": 1.8125770653514182,
+      "grad_norm": 0.47796759009361267,
+      "learning_rate": 0.0002,
+      "loss": 0.8247,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8249075215782984,
+      "grad_norm": 0.3348400592803955,
+      "learning_rate": 0.0002,
+      "loss": 0.9395,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8372379778051788,
+      "grad_norm": 0.3354550898075104,
+      "learning_rate": 0.0002,
+      "loss": 0.9793,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8495684340320593,
+      "grad_norm": 0.5988477468490601,
+      "learning_rate": 0.0002,
+      "loss": 0.8581,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8618988902589395,
+      "grad_norm": 0.5222318172454834,
+      "learning_rate": 0.0002,
+      "loss": 0.9268,
+      "step": 1510
+    },
+    {
+      "epoch": 1.87422934648582,
+      "grad_norm": 0.5246642827987671,
+      "learning_rate": 0.0002,
+      "loss": 0.8846,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8865598027127004,
+      "grad_norm": 0.3164594769477844,
+      "learning_rate": 0.0002,
+      "loss": 0.9317,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8988902589395806,
+      "grad_norm": 0.3496174216270447,
+      "learning_rate": 0.0002,
+      "loss": 0.9961,
+      "step": 1540
+    },
+    {
+      "epoch": 1.9112207151664613,
+      "grad_norm": 0.8863359689712524,
+      "learning_rate": 0.0002,
+      "loss": 0.9057,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9235511713933415,
+      "grad_norm": 0.3587026298046112,
+      "learning_rate": 0.0002,
+      "loss": 0.9405,
+      "step": 1560
+    },
+    {
+      "epoch": 1.935881627620222,
+      "grad_norm": 0.6052881479263306,
+      "learning_rate": 0.0002,
+      "loss": 0.8335,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9482120838471024,
+      "grad_norm": 0.567269504070282,
+      "learning_rate": 0.0002,
+      "loss": 0.8805,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9605425400739827,
+      "grad_norm": 0.45184487104415894,
+      "learning_rate": 0.0002,
+      "loss": 0.9581,
+      "step": 1590
+    },
+    {
+      "epoch": 1.972872996300863,
+      "grad_norm": 0.5028569102287292,
+      "learning_rate": 0.0002,
+      "loss": 0.9147,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9852034525277436,
+      "grad_norm": 0.4677547216415405,
+      "learning_rate": 0.0002,
+      "loss": 0.75,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9975339087546238,
+      "grad_norm": 0.35106056928634644,
+      "learning_rate": 0.0002,
+      "loss": 0.8469,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.238026738166809,
+      "eval_runtime": 95.4287,
+      "eval_samples_per_second": 4.569,
+      "eval_steps_per_second": 0.576,
+      "step": 1622
+    },
+    {
+      "epoch": 2.0098643649815044,
+      "grad_norm": 0.444060355424881,
+      "learning_rate": 0.0002,
+      "loss": 0.7629,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0221948212083847,
+      "grad_norm": 0.627570390701294,
+      "learning_rate": 0.0002,
+      "loss": 0.772,
+      "step": 1640
+    },
+    {
+      "epoch": 2.034525277435265,
+      "grad_norm": 0.38737839460372925,
+      "learning_rate": 0.0002,
+      "loss": 0.6186,
+      "step": 1650
+    },
+    {
+      "epoch": 2.0468557336621456,
+      "grad_norm": 0.4300459623336792,
+      "learning_rate": 0.0002,
+      "loss": 0.7734,
+      "step": 1660
+    },
+    {
+      "epoch": 2.059186189889026,
+      "grad_norm": 0.43037715554237366,
+      "learning_rate": 0.0002,
+      "loss": 0.6943,
+      "step": 1670
+    },
+    {
+      "epoch": 2.0715166461159065,
+      "grad_norm": 0.40772515535354614,
+      "learning_rate": 0.0002,
+      "loss": 0.6588,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0838471023427867,
+      "grad_norm": 0.5295451879501343,
+      "learning_rate": 0.0002,
+      "loss": 0.8105,
+      "step": 1690
+    },
+    {
+      "epoch": 2.096177558569667,
+      "grad_norm": 0.7452750205993652,
+      "learning_rate": 0.0002,
+      "loss": 0.7717,
+      "step": 1700
+    },
+    {
+      "epoch": 2.1085080147965476,
+      "grad_norm": 0.809183657169342,
+      "learning_rate": 0.0002,
+      "loss": 0.7458,
+      "step": 1710
+    },
+    {
+      "epoch": 2.120838471023428,
+      "grad_norm": 0.4597688913345337,
+      "learning_rate": 0.0002,
+      "loss": 0.7398,
+      "step": 1720
+    },
+    {
+      "epoch": 2.133168927250308,
+      "grad_norm": 0.806919276714325,
+      "learning_rate": 0.0002,
+      "loss": 0.6856,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1454993834771887,
+      "grad_norm": 0.3755643665790558,
+      "learning_rate": 0.0002,
+      "loss": 0.679,
+      "step": 1740
+    },
+    {
+      "epoch": 2.157829839704069,
+      "grad_norm": 0.5882734060287476,
+      "learning_rate": 0.0002,
+      "loss": 0.7938,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1701602959309496,
+      "grad_norm": 0.692960798740387,
+      "learning_rate": 0.0002,
+      "loss": 0.6782,
+      "step": 1760
+    },
+    {
+      "epoch": 2.18249075215783,
+      "grad_norm": 0.4737096428871155,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 1770
+    },
+    {
+      "epoch": 2.19482120838471,
+      "grad_norm": 0.6637021899223328,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 1780
+    },
+    {
+      "epoch": 2.2071516646115907,
+      "grad_norm": 0.9109764099121094,
+      "learning_rate": 0.0002,
+      "loss": 0.7139,
+      "step": 1790
+    },
+    {
+      "epoch": 2.219482120838471,
+      "grad_norm": 0.4137539267539978,
+      "learning_rate": 0.0002,
+      "loss": 0.7373,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2318125770653516,
+      "grad_norm": 0.44995415210723877,
+      "learning_rate": 0.0002,
+      "loss": 0.7266,
+      "step": 1810
+    },
+    {
+      "epoch": 2.244143033292232,
+      "grad_norm": 0.5985036492347717,
+      "learning_rate": 0.0002,
+      "loss": 0.7663,
+      "step": 1820
+    },
+    {
+      "epoch": 2.256473489519112,
+      "grad_norm": 0.7549490332603455,
+      "learning_rate": 0.0002,
+      "loss": 0.7502,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2688039457459928,
+      "grad_norm": 0.4490937888622284,
+      "learning_rate": 0.0002,
+      "loss": 0.7452,
+      "step": 1840
+    },
+    {
+      "epoch": 2.281134401972873,
+      "grad_norm": 0.38859808444976807,
+      "learning_rate": 0.0002,
+      "loss": 0.7531,
+      "step": 1850
+    },
+    {
+      "epoch": 2.293464858199753,
+      "grad_norm": 1.0704916715621948,
+      "learning_rate": 0.0002,
+      "loss": 0.7278,
+      "step": 1860
+    },
+    {
+      "epoch": 2.305795314426634,
+      "grad_norm": 0.4647100865840912,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 1870
+    },
+    {
+      "epoch": 2.318125770653514,
+      "grad_norm": 0.6181163787841797,
+      "learning_rate": 0.0002,
+      "loss": 0.7146,
+      "step": 1880
+    },
+    {
+      "epoch": 2.3304562268803943,
+      "grad_norm": 0.9241904020309448,
+      "learning_rate": 0.0002,
+      "loss": 0.7689,
+      "step": 1890
+    },
+    {
+      "epoch": 2.342786683107275,
+      "grad_norm": 0.39101317524909973,
+      "learning_rate": 0.0002,
+      "loss": 0.7294,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3551171393341552,
+      "grad_norm": 0.49442458152770996,
+      "learning_rate": 0.0002,
+      "loss": 0.7079,
+      "step": 1910
+    },
+    {
+      "epoch": 2.367447595561036,
+      "grad_norm": 0.4864824414253235,
+      "learning_rate": 0.0002,
+      "loss": 0.7586,
+      "step": 1920
+    },
+    {
+      "epoch": 2.379778051787916,
+      "grad_norm": 0.5427613854408264,
+      "learning_rate": 0.0002,
+      "loss": 0.7434,
+      "step": 1930
+    },
+    {
+      "epoch": 2.392108508014797,
+      "grad_norm": 0.7164974808692932,
+      "learning_rate": 0.0002,
+      "loss": 0.8423,
+      "step": 1940
+    },
+    {
+      "epoch": 2.404438964241677,
+      "grad_norm": 0.562979519367218,
+      "learning_rate": 0.0002,
+      "loss": 0.6888,
+      "step": 1950
+    },
+    {
+      "epoch": 2.4167694204685573,
+      "grad_norm": 0.5631861090660095,
+      "learning_rate": 0.0002,
+      "loss": 0.7692,
+      "step": 1960
+    },
+    {
+      "epoch": 2.429099876695438,
+      "grad_norm": 0.4895121157169342,
+      "learning_rate": 0.0002,
+      "loss": 0.67,
+      "step": 1970
+    },
+    {
+      "epoch": 2.441430332922318,
+      "grad_norm": 0.45674824714660645,
+      "learning_rate": 0.0002,
+      "loss": 0.7735,
+      "step": 1980
+    },
+    {
+      "epoch": 2.4537607891491984,
+      "grad_norm": 1.1424206495285034,
+      "learning_rate": 0.0002,
+      "loss": 0.685,
+      "step": 1990
+    },
+    {
+      "epoch": 2.466091245376079,
+      "grad_norm": 0.6314579844474792,
+      "learning_rate": 0.0002,
+      "loss": 0.7627,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4784217016029593,
+      "grad_norm": 0.5481605529785156,
+      "learning_rate": 0.0002,
+      "loss": 0.7118,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4907521578298395,
+      "grad_norm": 0.4671579599380493,
+      "learning_rate": 0.0002,
+      "loss": 0.6947,
+      "step": 2020
+    },
+    {
+      "epoch": 2.50308261405672,
+      "grad_norm": 0.7621194124221802,
+      "learning_rate": 0.0002,
+      "loss": 0.7377,
+      "step": 2030
+    },
+    {
+      "epoch": 2.5154130702836004,
+      "grad_norm": 0.38983288407325745,
+      "learning_rate": 0.0002,
+      "loss": 0.69,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5277435265104806,
+      "grad_norm": 0.6341150999069214,
+      "learning_rate": 0.0002,
+      "loss": 0.8381,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5400739827373613,
+      "grad_norm": 0.7151971459388733,
+      "learning_rate": 0.0002,
+      "loss": 0.773,
+      "step": 2060
+    },
+    {
+      "epoch": 2.5524044389642415,
+      "grad_norm": 0.9665895104408264,
+      "learning_rate": 0.0002,
+      "loss": 0.6733,
+      "step": 2070
+    },
+    {
+      "epoch": 2.564734895191122,
+      "grad_norm": 0.9572727680206299,
+      "learning_rate": 0.0002,
+      "loss": 0.7791,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5770653514180024,
+      "grad_norm": 1.1970765590667725,
+      "learning_rate": 0.0002,
+      "loss": 0.7205,
+      "step": 2090
+    },
+    {
+      "epoch": 2.589395807644883,
+      "grad_norm": 0.5505942702293396,
+      "learning_rate": 0.0002,
+      "loss": 0.6736,
+      "step": 2100
+    },
+    {
+      "epoch": 2.6017262638717633,
+      "grad_norm": 0.5903949737548828,
+      "learning_rate": 0.0002,
+      "loss": 0.673,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6140567200986435,
+      "grad_norm": 0.45640307664871216,
+      "learning_rate": 0.0002,
+      "loss": 0.678,
+      "step": 2120
+    },
+    {
+      "epoch": 2.626387176325524,
+      "grad_norm": 0.8763944506645203,
+      "learning_rate": 0.0002,
+      "loss": 0.6562,
+      "step": 2130
+    },
+    {
+      "epoch": 2.6387176325524044,
+      "grad_norm": 0.4472963213920593,
+      "learning_rate": 0.0002,
+      "loss": 0.6484,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6510480887792847,
+      "grad_norm": 0.5335086584091187,
+      "learning_rate": 0.0002,
+      "loss": 0.7702,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6633785450061653,
+      "grad_norm": 0.805263340473175,
+      "learning_rate": 0.0002,
+      "loss": 0.6851,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6757090012330456,
+      "grad_norm": 0.6332727670669556,
+      "learning_rate": 0.0002,
+      "loss": 0.7026,
+      "step": 2170
+    },
+    {
+      "epoch": 2.688039457459926,
+      "grad_norm": 0.8667435646057129,
+      "learning_rate": 0.0002,
+      "loss": 0.7925,
+      "step": 2180
+    },
+    {
+      "epoch": 2.7003699136868065,
+      "grad_norm": 0.5638955235481262,
+      "learning_rate": 0.0002,
+      "loss": 0.8044,
+      "step": 2190
+    },
+    {
+      "epoch": 2.7127003699136867,
+      "grad_norm": 0.4176250696182251,
+      "learning_rate": 0.0002,
+      "loss": 0.7117,
+      "step": 2200
+    },
+    {
+      "epoch": 2.7250308261405674,
+      "grad_norm": 0.6013461351394653,
+      "learning_rate": 0.0002,
+      "loss": 0.6932,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7373612823674476,
+      "grad_norm": 0.553961992263794,
+      "learning_rate": 0.0002,
+      "loss": 0.7843,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7496917385943282,
+      "grad_norm": 0.4710180461406708,
+      "learning_rate": 0.0002,
+      "loss": 0.8633,
+      "step": 2230
+    },
+    {
+      "epoch": 2.7620221948212085,
+      "grad_norm": 0.8141706585884094,
+      "learning_rate": 0.0002,
+      "loss": 0.7469,
+      "step": 2240
+    },
+    {
+      "epoch": 2.7743526510480887,
+      "grad_norm": 0.7449556589126587,
+      "learning_rate": 0.0002,
+      "loss": 0.7086,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7866831072749694,
+      "grad_norm": 0.5366780757904053,
+      "learning_rate": 0.0002,
+      "loss": 0.6933,
+      "step": 2260
+    },
+    {
+      "epoch": 2.7990135635018496,
+      "grad_norm": 0.5316720604896545,
+      "learning_rate": 0.0002,
+      "loss": 0.7192,
+      "step": 2270
+    },
+    {
+      "epoch": 2.81134401972873,
+      "grad_norm": 0.4598459005355835,
+      "learning_rate": 0.0002,
+      "loss": 0.6212,
+      "step": 2280
+    },
+    {
+      "epoch": 2.8236744759556105,
+      "grad_norm": 0.6852091550827026,
+      "learning_rate": 0.0002,
+      "loss": 0.7024,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8360049321824907,
+      "grad_norm": 0.8040902018547058,
+      "learning_rate": 0.0002,
+      "loss": 0.7357,
+      "step": 2300
+    },
+    {
+      "epoch": 2.848335388409371,
+      "grad_norm": 0.46976321935653687,
+      "learning_rate": 0.0002,
+      "loss": 0.7563,
+      "step": 2310
+    },
+    {
+      "epoch": 2.8606658446362516,
+      "grad_norm": 0.5214090347290039,
+      "learning_rate": 0.0002,
+      "loss": 0.731,
+      "step": 2320
+    },
+    {
+      "epoch": 2.872996300863132,
+      "grad_norm": 0.5323054790496826,
+      "learning_rate": 0.0002,
+      "loss": 0.6687,
+      "step": 2330
+    },
+    {
+      "epoch": 2.885326757090012,
+      "grad_norm": 0.6842264533042908,
+      "learning_rate": 0.0002,
+      "loss": 0.7895,
+      "step": 2340
+    },
+    {
+      "epoch": 2.8976572133168927,
+      "grad_norm": 0.9157055616378784,
+      "learning_rate": 0.0002,
+      "loss": 0.7737,
+      "step": 2350
+    },
+    {
+      "epoch": 2.909987669543773,
+      "grad_norm": 0.5253258347511292,
+      "learning_rate": 0.0002,
+      "loss": 0.7217,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9223181257706536,
+      "grad_norm": 0.4937705099582672,
+      "learning_rate": 0.0002,
+      "loss": 0.7162,
+      "step": 2370
+    },
+    {
+      "epoch": 2.934648581997534,
+      "grad_norm": 0.48762989044189453,
+      "learning_rate": 0.0002,
+      "loss": 0.7008,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9469790382244145,
+      "grad_norm": 0.544335126876831,
+      "learning_rate": 0.0002,
+      "loss": 0.8086,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9593094944512948,
+      "grad_norm": 0.4847845435142517,
+      "learning_rate": 0.0002,
+      "loss": 0.643,
+      "step": 2400
+    },
+    {
+      "epoch": 2.971639950678175,
+      "grad_norm": 0.4787445366382599,
+      "learning_rate": 0.0002,
+      "loss": 0.7757,
+      "step": 2410
+    },
+    {
+      "epoch": 2.9839704069050557,
+      "grad_norm": 1.022318959236145,
+      "learning_rate": 0.0002,
+      "loss": 0.7678,
+      "step": 2420
+    },
+    {
+      "epoch": 2.996300863131936,
+      "grad_norm": 0.4987848103046417,
+      "learning_rate": 0.0002,
+      "loss": 0.6548,
+      "step": 2430
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2936296463012695,
+      "eval_runtime": 94.7897,
+      "eval_samples_per_second": 4.6,
+      "eval_steps_per_second": 0.58,
+      "step": 2433
+    },
+    {
+      "epoch": 3.008631319358816,
+      "grad_norm": 0.5562372803688049,
+      "learning_rate": 0.0002,
+      "loss": 0.6073,
+      "step": 2440
+    },
+    {
+      "epoch": 3.020961775585697,
+      "grad_norm": 1.133402705192566,
+      "learning_rate": 0.0002,
+      "loss": 0.5181,
+      "step": 2450
+    },
+    {
+      "epoch": 3.033292231812577,
+      "grad_norm": 0.6480470299720764,
+      "learning_rate": 0.0002,
+      "loss": 0.5333,
+      "step": 2460
+    },
+    {
+      "epoch": 3.0456226880394572,
+      "grad_norm": 0.8989138007164001,
+      "learning_rate": 0.0002,
+      "loss": 0.4828,
+      "step": 2470
+    },
+    {
+      "epoch": 3.057953144266338,
+      "grad_norm": 0.8257461786270142,
+      "learning_rate": 0.0002,
+      "loss": 0.5097,
+      "step": 2480
+    },
+    {
+      "epoch": 3.070283600493218,
+      "grad_norm": 0.6813381910324097,
+      "learning_rate": 0.0002,
+      "loss": 0.6229,
+      "step": 2490
+    },
+    {
+      "epoch": 3.082614056720099,
+      "grad_norm": 0.6989586353302002,
+      "learning_rate": 0.0002,
+      "loss": 0.531,
+      "step": 2500
+    },
+    {
+      "epoch": 3.094944512946979,
+      "grad_norm": 0.7992092967033386,
+      "learning_rate": 0.0002,
+      "loss": 0.54,
+      "step": 2510
+    },
+    {
+      "epoch": 3.1072749691738593,
+      "grad_norm": 0.698077917098999,
+      "learning_rate": 0.0002,
+      "loss": 0.5054,
+      "step": 2520
+    },
+    {
+      "epoch": 3.11960542540074,
+      "grad_norm": 0.5699033141136169,
+      "learning_rate": 0.0002,
+      "loss": 0.5064,
+      "step": 2530
+    },
+    {
+      "epoch": 3.13193588162762,
+      "grad_norm": 0.6142355799674988,
+      "learning_rate": 0.0002,
+      "loss": 0.6088,
+      "step": 2540
+    },
+    {
+      "epoch": 3.144266337854501,
+      "grad_norm": 0.7089933753013611,
+      "learning_rate": 0.0002,
+      "loss": 0.585,
+      "step": 2550
+    },
+    {
+      "epoch": 3.156596794081381,
+      "grad_norm": 1.0107015371322632,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 2560
+    },
+    {
+      "epoch": 3.1689272503082613,
+      "grad_norm": 0.568138837814331,
+      "learning_rate": 0.0002,
+      "loss": 0.5429,
+      "step": 2570
+    },
+    {
+      "epoch": 3.181257706535142,
+      "grad_norm": 0.9960416555404663,
+      "learning_rate": 0.0002,
+      "loss": 0.5897,
+      "step": 2580
+    },
+    {
+      "epoch": 3.193588162762022,
+      "grad_norm": 0.6277595162391663,
+      "learning_rate": 0.0002,
+      "loss": 0.5211,
+      "step": 2590
+    },
+    {
+      "epoch": 3.2059186189889024,
+      "grad_norm": 0.681083619594574,
+      "learning_rate": 0.0002,
+      "loss": 0.5787,
+      "step": 2600
+    },
+    {
+      "epoch": 3.218249075215783,
+      "grad_norm": 0.5816057324409485,
+      "learning_rate": 0.0002,
+      "loss": 0.5166,
+      "step": 2610
+    },
+    {
+      "epoch": 3.2305795314426633,
+      "grad_norm": 0.7197734117507935,
+      "learning_rate": 0.0002,
+      "loss": 0.545,
+      "step": 2620
+    },
+    {
+      "epoch": 3.242909987669544,
+      "grad_norm": 0.6524068117141724,
+      "learning_rate": 0.0002,
+      "loss": 0.614,
+      "step": 2630
+    },
+    {
+      "epoch": 3.255240443896424,
+      "grad_norm": 1.273668646812439,
+      "learning_rate": 0.0002,
+      "loss": 0.5456,
+      "step": 2640
+    },
+    {
+      "epoch": 3.2675709001233044,
+      "grad_norm": 0.6950451731681824,
+      "learning_rate": 0.0002,
+      "loss": 0.5266,
+      "step": 2650
+    },
+    {
+      "epoch": 3.279901356350185,
+      "grad_norm": 0.8029071688652039,
+      "learning_rate": 0.0002,
+      "loss": 0.5194,
+      "step": 2660
+    },
+    {
+      "epoch": 3.2922318125770653,
+      "grad_norm": 0.7464073896408081,
+      "learning_rate": 0.0002,
+      "loss": 0.5729,
+      "step": 2670
+    },
+    {
+      "epoch": 3.304562268803946,
+      "grad_norm": 0.8342001438140869,
+      "learning_rate": 0.0002,
+      "loss": 0.5366,
+      "step": 2680
+    },
+    {
+      "epoch": 3.316892725030826,
+      "grad_norm": 0.5629868507385254,
+      "learning_rate": 0.0002,
+      "loss": 0.5413,
+      "step": 2690
+    },
+    {
+      "epoch": 3.3292231812577064,
+      "grad_norm": 0.753999650478363,
+      "learning_rate": 0.0002,
+      "loss": 0.633,
+      "step": 2700
+    },
+    {
+      "epoch": 3.341553637484587,
+      "grad_norm": 1.0271371603012085,
+      "learning_rate": 0.0002,
+      "loss": 0.5048,
+      "step": 2710
+    },
+    {
+      "epoch": 3.3538840937114673,
+      "grad_norm": 0.9608535170555115,
+      "learning_rate": 0.0002,
+      "loss": 0.5233,
+      "step": 2720
+    },
+    {
+      "epoch": 3.3662145499383476,
+      "grad_norm": 0.7796488404273987,
+      "learning_rate": 0.0002,
+      "loss": 0.5102,
+      "step": 2730
+    },
+    {
+      "epoch": 3.3785450061652282,
+      "grad_norm": 0.5666437149047852,
+      "learning_rate": 0.0002,
+      "loss": 0.5172,
+      "step": 2740
+    },
+    {
+      "epoch": 3.3908754623921085,
+      "grad_norm": 0.5462956428527832,
+      "learning_rate": 0.0002,
+      "loss": 0.491,
+      "step": 2750
+    },
+    {
+      "epoch": 3.4032059186189887,
+      "grad_norm": 1.289099097251892,
+      "learning_rate": 0.0002,
+      "loss": 0.5855,
+      "step": 2760
+    },
+    {
+      "epoch": 3.4155363748458694,
+      "grad_norm": 0.825566828250885,
+      "learning_rate": 0.0002,
+      "loss": 0.635,
+      "step": 2770
+    },
+    {
+      "epoch": 3.4278668310727496,
+      "grad_norm": 0.8366670608520508,
+      "learning_rate": 0.0002,
+      "loss": 0.4998,
+      "step": 2780
+    },
+    {
+      "epoch": 3.4401972872996303,
+      "grad_norm": 1.0931549072265625,
+      "learning_rate": 0.0002,
+      "loss": 0.5732,
+      "step": 2790
+    },
+    {
+      "epoch": 3.4525277435265105,
+      "grad_norm": 0.9228858351707458,
+      "learning_rate": 0.0002,
+      "loss": 0.6093,
+      "step": 2800
+    },
+    {
+      "epoch": 3.4648581997533907,
+      "grad_norm": 1.3182806968688965,
+      "learning_rate": 0.0002,
+      "loss": 0.6089,
+      "step": 2810
+    },
+    {
+      "epoch": 3.4771886559802714,
+      "grad_norm": 0.8366976380348206,
+      "learning_rate": 0.0002,
+      "loss": 0.5665,
+      "step": 2820
+    },
+    {
+      "epoch": 3.4895191122071516,
+      "grad_norm": 0.8067695498466492,
+      "learning_rate": 0.0002,
+      "loss": 0.5666,
+      "step": 2830
+    },
+    {
+      "epoch": 3.5018495684340323,
+      "grad_norm": 1.1163437366485596,
+      "learning_rate": 0.0002,
+      "loss": 0.579,
+      "step": 2840
+    },
+    {
+      "epoch": 3.5141800246609125,
+      "grad_norm": 1.7196556329727173,
+      "learning_rate": 0.0002,
+      "loss": 0.5785,
+      "step": 2850
+    },
+    {
+      "epoch": 3.5265104808877927,
+      "grad_norm": 1.1267012357711792,
+      "learning_rate": 0.0002,
+      "loss": 0.5346,
+      "step": 2860
+    },
+    {
+      "epoch": 3.5388409371146734,
+      "grad_norm": 0.7220137119293213,
+      "learning_rate": 0.0002,
+      "loss": 0.447,
+      "step": 2870
+    },
+    {
+      "epoch": 3.5511713933415536,
+      "grad_norm": 0.914114773273468,
+      "learning_rate": 0.0002,
+      "loss": 0.6099,
+      "step": 2880
+    },
+    {
+      "epoch": 3.563501849568434,
+      "grad_norm": 0.6193503141403198,
+      "learning_rate": 0.0002,
+      "loss": 0.6143,
+      "step": 2890
+    },
+    {
+      "epoch": 3.5758323057953145,
+      "grad_norm": 0.6060135960578918,
+      "learning_rate": 0.0002,
+      "loss": 0.5171,
+      "step": 2900
+    },
+    {
+      "epoch": 3.5881627620221948,
+      "grad_norm": 1.0177327394485474,
+      "learning_rate": 0.0002,
+      "loss": 0.5659,
+      "step": 2910
+    },
+    {
+      "epoch": 3.600493218249075,
+      "grad_norm": 0.5994468331336975,
+      "learning_rate": 0.0002,
+      "loss": 0.5711,
+      "step": 2920
+    },
+    {
+      "epoch": 3.6128236744759556,
+      "grad_norm": 0.7450457215309143,
+      "learning_rate": 0.0002,
+      "loss": 0.6373,
+      "step": 2930
+    },
+    {
+      "epoch": 3.625154130702836,
+      "grad_norm": 0.5825870037078857,
+      "learning_rate": 0.0002,
+      "loss": 0.4933,
+      "step": 2940
+    },
+    {
+      "epoch": 3.6374845869297165,
+      "grad_norm": 0.6289743781089783,
+      "learning_rate": 0.0002,
+      "loss": 0.6016,
+      "step": 2950
+    },
+    {
+      "epoch": 3.6498150431565968,
+      "grad_norm": 0.7801929116249084,
+      "learning_rate": 0.0002,
+      "loss": 0.5507,
+      "step": 2960
+    },
+    {
+      "epoch": 3.6621454993834774,
+      "grad_norm": 1.1206634044647217,
+      "learning_rate": 0.0002,
+      "loss": 0.5695,
+      "step": 2970
+    },
+    {
+      "epoch": 3.6744759556103577,
+      "grad_norm": 0.6738817691802979,
+      "learning_rate": 0.0002,
+      "loss": 0.4985,
+      "step": 2980
+    },
+    {
+      "epoch": 3.686806411837238,
+      "grad_norm": 1.1917344331741333,
+      "learning_rate": 0.0002,
+      "loss": 0.6209,
+      "step": 2990
+    },
+    {
+      "epoch": 3.6991368680641186,
+      "grad_norm": 1.3738657236099243,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 3000
+    },
+    {
+      "epoch": 3.711467324290999,
+      "grad_norm": 0.6642793416976929,
+      "learning_rate": 0.0002,
+      "loss": 0.5467,
+      "step": 3010
+    },
+    {
+      "epoch": 3.723797780517879,
+      "grad_norm": 0.9030995965003967,
+      "learning_rate": 0.0002,
+      "loss": 0.6243,
+      "step": 3020
+    },
+    {
+      "epoch": 3.7361282367447597,
+      "grad_norm": 1.0203914642333984,
+      "learning_rate": 0.0002,
+      "loss": 0.592,
+      "step": 3030
+    },
+    {
+      "epoch": 3.74845869297164,
+      "grad_norm": 0.648394763469696,
+      "learning_rate": 0.0002,
+      "loss": 0.5453,
+      "step": 3040
+    },
+    {
+      "epoch": 3.76078914919852,
+      "grad_norm": 0.6304570436477661,
+      "learning_rate": 0.0002,
+      "loss": 0.498,
+      "step": 3050
+    },
+    {
+      "epoch": 3.773119605425401,
+      "grad_norm": 0.8286601901054382,
+      "learning_rate": 0.0002,
+      "loss": 0.683,
+      "step": 3060
+    },
+    {
+      "epoch": 3.785450061652281,
+      "grad_norm": 0.906444251537323,
+      "learning_rate": 0.0002,
+      "loss": 0.5302,
+      "step": 3070
+    },
+    {
+      "epoch": 3.7977805178791613,
+      "grad_norm": 1.4212149381637573,
+      "learning_rate": 0.0002,
+      "loss": 0.5345,
+      "step": 3080
+    },
+    {
+      "epoch": 3.810110974106042,
+      "grad_norm": 0.7574319839477539,
+      "learning_rate": 0.0002,
+      "loss": 0.6403,
+      "step": 3090
+    },
+    {
+      "epoch": 3.822441430332922,
+      "grad_norm": 0.6534451246261597,
+      "learning_rate": 0.0002,
+      "loss": 0.5756,
+      "step": 3100
+    },
+    {
+      "epoch": 3.834771886559803,
+      "grad_norm": 0.7525447010993958,
+      "learning_rate": 0.0002,
+      "loss": 0.5306,
+      "step": 3110
+    },
+    {
+      "epoch": 3.847102342786683,
+      "grad_norm": 0.6513990759849548,
+      "learning_rate": 0.0002,
+      "loss": 0.5368,
+      "step": 3120
+    },
+    {
+      "epoch": 3.8594327990135637,
+      "grad_norm": 0.7782694697380066,
+      "learning_rate": 0.0002,
+      "loss": 0.5492,
+      "step": 3130
+    },
+    {
+      "epoch": 3.871763255240444,
+      "grad_norm": 0.7998530268669128,
+      "learning_rate": 0.0002,
+      "loss": 0.5727,
+      "step": 3140
+    },
+    {
+      "epoch": 3.884093711467324,
+      "grad_norm": 0.8045353293418884,
+      "learning_rate": 0.0002,
+      "loss": 0.5156,
+      "step": 3150
+    },
+    {
+      "epoch": 3.896424167694205,
+      "grad_norm": 0.8242645263671875,
+      "learning_rate": 0.0002,
+      "loss": 0.5341,
+      "step": 3160
+    },
+    {
+      "epoch": 3.908754623921085,
+      "grad_norm": 0.8302360773086548,
+      "learning_rate": 0.0002,
+      "loss": 0.5563,
+      "step": 3170
+    },
+    {
+      "epoch": 3.9210850801479653,
+      "grad_norm": 0.8653109073638916,
+      "learning_rate": 0.0002,
+      "loss": 0.5793,
+      "step": 3180
+    },
+    {
+      "epoch": 3.933415536374846,
+      "grad_norm": 0.6461338996887207,
+      "learning_rate": 0.0002,
+      "loss": 0.5219,
+      "step": 3190
+    },
+    {
+      "epoch": 3.945745992601726,
+      "grad_norm": 0.8267415165901184,
+      "learning_rate": 0.0002,
+      "loss": 0.6009,
+      "step": 3200
+    },
+    {
+      "epoch": 3.9580764488286064,
+      "grad_norm": 1.1963194608688354,
+      "learning_rate": 0.0002,
+      "loss": 0.5956,
+      "step": 3210
+    },
+    {
+      "epoch": 3.970406905055487,
+      "grad_norm": 0.7101966142654419,
+      "learning_rate": 0.0002,
+      "loss": 0.5692,
+      "step": 3220
+    },
+    {
+      "epoch": 3.9827373612823673,
+      "grad_norm": 0.5931660532951355,
+      "learning_rate": 0.0002,
+      "loss": 0.5471,
+      "step": 3230
+    },
+    {
+      "epoch": 3.995067817509248,
+      "grad_norm": 0.7465988993644714,
+      "learning_rate": 0.0002,
+      "loss": 0.5619,
+      "step": 3240
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4066498279571533,
+      "eval_runtime": 95.7145,
+      "eval_samples_per_second": 4.555,
+      "eval_steps_per_second": 0.575,
+      "step": 3244
+    },
+    {
+      "epoch": 4.007398273736128,
+      "grad_norm": 0.9478800296783447,
+      "learning_rate": 0.0002,
+      "loss": 0.4948,
+      "step": 3250
+    },
+    {
+      "epoch": 4.019728729963009,
+      "grad_norm": 1.207059621810913,
+      "learning_rate": 0.0002,
+      "loss": 0.4129,
+      "step": 3260
+    },
+    {
+      "epoch": 4.032059186189889,
+      "grad_norm": 0.8984074592590332,
+      "learning_rate": 0.0002,
+      "loss": 0.3577,
+      "step": 3270
+    },
+    {
+      "epoch": 4.044389642416769,
+      "grad_norm": 0.8104140758514404,
+      "learning_rate": 0.0002,
+      "loss": 0.3798,
+      "step": 3280
+    },
+    {
+      "epoch": 4.05672009864365,
+      "grad_norm": 1.0875468254089355,
+      "learning_rate": 0.0002,
+      "loss": 0.3657,
+      "step": 3290
+    },
+    {
+      "epoch": 4.06905055487053,
+      "grad_norm": 0.8520309329032898,
+      "learning_rate": 0.0002,
+      "loss": 0.3703,
+      "step": 3300
+    },
+    {
+      "epoch": 4.0813810110974105,
+      "grad_norm": 1.076735496520996,
+      "learning_rate": 0.0002,
+      "loss": 0.3933,
+      "step": 3310
+    },
+    {
+      "epoch": 4.093711467324291,
+      "grad_norm": 0.7789369821548462,
+      "learning_rate": 0.0002,
+      "loss": 0.4422,
+      "step": 3320
+    },
+    {
+      "epoch": 4.106041923551172,
+      "grad_norm": 0.916862964630127,
+      "learning_rate": 0.0002,
+      "loss": 0.4009,
+      "step": 3330
+    },
+    {
+      "epoch": 4.118372379778052,
+      "grad_norm": 1.1251654624938965,
+      "learning_rate": 0.0002,
+      "loss": 0.3934,
+      "step": 3340
+    },
+    {
+      "epoch": 4.130702836004932,
+      "grad_norm": 0.9373420476913452,
+      "learning_rate": 0.0002,
+      "loss": 0.3651,
+      "step": 3350
+    },
+    {
+      "epoch": 4.143033292231813,
+      "grad_norm": 1.03253972530365,
+      "learning_rate": 0.0002,
+      "loss": 0.384,
+      "step": 3360
+    },
+    {
+      "epoch": 4.155363748458693,
+      "grad_norm": 0.947023332118988,
+      "learning_rate": 0.0002,
+      "loss": 0.372,
+      "step": 3370
+    },
+    {
+      "epoch": 4.167694204685573,
+      "grad_norm": 0.8709157109260559,
+      "learning_rate": 0.0002,
+      "loss": 0.4018,
+      "step": 3380
+    },
+    {
+      "epoch": 4.180024660912454,
+      "grad_norm": 0.930983304977417,
+      "learning_rate": 0.0002,
+      "loss": 0.3754,
+      "step": 3390
+    },
+    {
+      "epoch": 4.192355117139334,
+      "grad_norm": 1.092809796333313,
+      "learning_rate": 0.0002,
+      "loss": 0.4248,
+      "step": 3400
+    },
+    {
+      "epoch": 4.2046855733662145,
+      "grad_norm": 0.8454303741455078,
+      "learning_rate": 0.0002,
+      "loss": 0.4453,
+      "step": 3410
+    },
+    {
+      "epoch": 4.217016029593095,
+      "grad_norm": 0.957210123538971,
+      "learning_rate": 0.0002,
+      "loss": 0.4198,
+      "step": 3420
+    },
+    {
+      "epoch": 4.229346485819975,
+      "grad_norm": 0.854333758354187,
+      "learning_rate": 0.0002,
+      "loss": 0.3743,
+      "step": 3430
+    },
+    {
+      "epoch": 4.241676942046856,
+      "grad_norm": 1.0457639694213867,
+      "learning_rate": 0.0002,
+      "loss": 0.4041,
+      "step": 3440
+    },
+    {
+      "epoch": 4.254007398273736,
+      "grad_norm": 0.8972977995872498,
+      "learning_rate": 0.0002,
+      "loss": 0.3817,
+      "step": 3450
+    },
+    {
+      "epoch": 4.266337854500616,
+      "grad_norm": 1.0438238382339478,
+      "learning_rate": 0.0002,
+      "loss": 0.4445,
+      "step": 3460
+    },
+    {
+      "epoch": 4.278668310727497,
+      "grad_norm": 0.7000405192375183,
+      "learning_rate": 0.0002,
+      "loss": 0.4078,
+      "step": 3470
+    },
+    {
+      "epoch": 4.290998766954377,
+      "grad_norm": 1.0451240539550781,
+      "learning_rate": 0.0002,
+      "loss": 0.3718,
+      "step": 3480
+    },
+    {
+      "epoch": 4.303329223181258,
+      "grad_norm": 1.3339767456054688,
+      "learning_rate": 0.0002,
+      "loss": 0.4506,
+      "step": 3490
+    },
+    {
+      "epoch": 4.315659679408138,
+      "grad_norm": 0.7503946423530579,
+      "learning_rate": 0.0002,
+      "loss": 0.3999,
+      "step": 3500
+    },
+    {
+      "epoch": 4.3279901356350186,
+      "grad_norm": 0.8443584442138672,
+      "learning_rate": 0.0002,
+      "loss": 0.4503,
+      "step": 3510
+    },
+    {
+      "epoch": 4.340320591861899,
+      "grad_norm": 1.1681201457977295,
+      "learning_rate": 0.0002,
+      "loss": 0.3793,
+      "step": 3520
+    },
+    {
+      "epoch": 4.352651048088779,
+      "grad_norm": 1.078883171081543,
+      "learning_rate": 0.0002,
+      "loss": 0.4462,
+      "step": 3530
+    },
+    {
+      "epoch": 4.36498150431566,
+      "grad_norm": 0.6894834041595459,
+      "learning_rate": 0.0002,
+      "loss": 0.4216,
+      "step": 3540
+    },
+    {
+      "epoch": 4.37731196054254,
+      "grad_norm": 0.7059480547904968,
+      "learning_rate": 0.0002,
+      "loss": 0.4315,
+      "step": 3550
+    },
+    {
+      "epoch": 4.38964241676942,
+      "grad_norm": 1.1807256937026978,
+      "learning_rate": 0.0002,
+      "loss": 0.3821,
+      "step": 3560
+    },
+    {
+      "epoch": 4.401972872996301,
+      "grad_norm": 0.8341359496116638,
+      "learning_rate": 0.0002,
+      "loss": 0.4192,
+      "step": 3570
+    },
+    {
+      "epoch": 4.4143033292231815,
+      "grad_norm": 1.0273033380508423,
+      "learning_rate": 0.0002,
+      "loss": 0.4123,
+      "step": 3580
+    },
+    {
+      "epoch": 4.426633785450061,
+      "grad_norm": 0.6916454434394836,
+      "learning_rate": 0.0002,
+      "loss": 0.5018,
+      "step": 3590
+    },
+    {
+      "epoch": 4.438964241676942,
+      "grad_norm": 0.8210113644599915,
+      "learning_rate": 0.0002,
+      "loss": 0.3909,
+      "step": 3600
+    },
+    {
+      "epoch": 4.451294697903823,
+      "grad_norm": 1.0309500694274902,
+      "learning_rate": 0.0002,
+      "loss": 0.3893,
+      "step": 3610
+    },
+    {
+      "epoch": 4.463625154130703,
+      "grad_norm": 0.8847399353981018,
+      "learning_rate": 0.0002,
+      "loss": 0.3902,
+      "step": 3620
+    },
+    {
+      "epoch": 4.475955610357583,
+      "grad_norm": 1.668636679649353,
+      "learning_rate": 0.0002,
+      "loss": 0.4198,
+      "step": 3630
+    },
+    {
+      "epoch": 4.488286066584464,
+      "grad_norm": 1.3087958097457886,
+      "learning_rate": 0.0002,
+      "loss": 0.4075,
+      "step": 3640
+    },
+    {
+      "epoch": 4.500616522811344,
+      "grad_norm": 0.837852418422699,
+      "learning_rate": 0.0002,
+      "loss": 0.4294,
+      "step": 3650
+    },
+    {
+      "epoch": 4.512946979038224,
+      "grad_norm": 9.7662353515625,
+      "learning_rate": 0.0002,
+      "loss": 0.4053,
+      "step": 3660
+    },
+    {
+      "epoch": 4.525277435265105,
+      "grad_norm": 1.125719428062439,
+      "learning_rate": 0.0002,
+      "loss": 0.4033,
+      "step": 3670
+    },
+    {
+      "epoch": 4.5376078914919855,
+      "grad_norm": 0.7755377292633057,
+      "learning_rate": 0.0002,
+      "loss": 0.4566,
+      "step": 3680
+    },
+    {
+      "epoch": 4.549938347718865,
+      "grad_norm": 0.7185089588165283,
+      "learning_rate": 0.0002,
+      "loss": 0.4415,
+      "step": 3690
+    },
+    {
+      "epoch": 4.562268803945746,
+      "grad_norm": 1.182063102722168,
+      "learning_rate": 0.0002,
+      "loss": 0.4616,
+      "step": 3700
+    },
+    {
+      "epoch": 4.574599260172627,
+      "grad_norm": 1.001197338104248,
+      "learning_rate": 0.0002,
+      "loss": 0.4572,
+      "step": 3710
+    },
+    {
+      "epoch": 4.586929716399506,
+      "grad_norm": 0.9705429077148438,
+      "learning_rate": 0.0002,
+      "loss": 0.4493,
+      "step": 3720
+    },
+    {
+      "epoch": 4.599260172626387,
+      "grad_norm": 0.7136746048927307,
+      "learning_rate": 0.0002,
+      "loss": 0.42,
+      "step": 3730
+    },
+    {
+      "epoch": 4.611590628853268,
+      "grad_norm": 1.0004864931106567,
+      "learning_rate": 0.0002,
+      "loss": 0.3757,
+      "step": 3740
+    },
+    {
+      "epoch": 4.623921085080148,
+      "grad_norm": 1.3193715810775757,
+      "learning_rate": 0.0002,
+      "loss": 0.4418,
+      "step": 3750
+    },
+    {
+      "epoch": 4.636251541307028,
+      "grad_norm": 0.6945042014122009,
+      "learning_rate": 0.0002,
+      "loss": 0.4572,
+      "step": 3760
+    },
+    {
+      "epoch": 4.648581997533909,
+      "grad_norm": 0.8903936743736267,
+      "learning_rate": 0.0002,
+      "loss": 0.4255,
+      "step": 3770
+    },
+    {
+      "epoch": 4.660912453760789,
+      "grad_norm": 0.7960889339447021,
+      "learning_rate": 0.0002,
+      "loss": 0.3582,
+      "step": 3780
+    },
+    {
+      "epoch": 4.673242909987669,
+      "grad_norm": 1.0439172983169556,
+      "learning_rate": 0.0002,
+      "loss": 0.3864,
+      "step": 3790
+    },
+    {
+      "epoch": 4.68557336621455,
+      "grad_norm": 1.4546219110488892,
+      "learning_rate": 0.0002,
+      "loss": 0.4378,
+      "step": 3800
+    },
+    {
+      "epoch": 4.697903822441431,
+      "grad_norm": 0.8194343447685242,
+      "learning_rate": 0.0002,
+      "loss": 0.4191,
+      "step": 3810
+    },
+    {
+      "epoch": 4.7102342786683105,
+      "grad_norm": 1.0727602243423462,
+      "learning_rate": 0.0002,
+      "loss": 0.4473,
+      "step": 3820
+    },
+    {
+      "epoch": 4.722564734895191,
+      "grad_norm": 0.7785195708274841,
+      "learning_rate": 0.0002,
+      "loss": 0.4021,
+      "step": 3830
+    },
+    {
+      "epoch": 4.734895191122072,
+      "grad_norm": 0.846783459186554,
+      "learning_rate": 0.0002,
+      "loss": 0.4252,
+      "step": 3840
+    },
+    {
+      "epoch": 4.747225647348952,
+      "grad_norm": 1.0481648445129395,
+      "learning_rate": 0.0002,
+      "loss": 0.4647,
+      "step": 3850
+    },
+    {
+      "epoch": 4.759556103575832,
+      "grad_norm": 0.7324008941650391,
+      "learning_rate": 0.0002,
+      "loss": 0.4944,
+      "step": 3860
+    },
+    {
+      "epoch": 4.771886559802713,
+      "grad_norm": 1.06382417678833,
+      "learning_rate": 0.0002,
+      "loss": 0.3831,
+      "step": 3870
+    },
+    {
+      "epoch": 4.784217016029594,
+      "grad_norm": 0.9851241111755371,
+      "learning_rate": 0.0002,
+      "loss": 0.3934,
+      "step": 3880
+    },
+    {
+      "epoch": 4.796547472256473,
+      "grad_norm": 0.8215277791023254,
+      "learning_rate": 0.0002,
+      "loss": 0.5172,
+      "step": 3890
+    },
+    {
+      "epoch": 4.808877928483354,
+      "grad_norm": 0.9901723861694336,
+      "learning_rate": 0.0002,
+      "loss": 0.4437,
+      "step": 3900
+    },
+    {
+      "epoch": 4.821208384710234,
+      "grad_norm": 0.9149112701416016,
+      "learning_rate": 0.0002,
+      "loss": 0.4673,
+      "step": 3910
+    },
+    {
+      "epoch": 4.8335388409371145,
+      "grad_norm": 0.9772973656654358,
+      "learning_rate": 0.0002,
+      "loss": 0.4295,
+      "step": 3920
+    },
+    {
+      "epoch": 4.845869297163995,
+      "grad_norm": 0.8889636397361755,
+      "learning_rate": 0.0002,
+      "loss": 0.4346,
+      "step": 3930
+    },
+    {
+      "epoch": 4.858199753390876,
+      "grad_norm": 1.3032807111740112,
+      "learning_rate": 0.0002,
+      "loss": 0.421,
+      "step": 3940
+    },
+    {
+      "epoch": 4.870530209617756,
+      "grad_norm": 0.8575899600982666,
+      "learning_rate": 0.0002,
+      "loss": 0.434,
+      "step": 3950
+    },
+    {
+      "epoch": 4.882860665844636,
+      "grad_norm": 1.04326331615448,
+      "learning_rate": 0.0002,
+      "loss": 0.4295,
+      "step": 3960
+    },
+    {
+      "epoch": 4.895191122071517,
+      "grad_norm": 1.041210651397705,
+      "learning_rate": 0.0002,
+      "loss": 0.3633,
+      "step": 3970
+    },
+    {
+      "epoch": 4.907521578298397,
+      "grad_norm": 0.9113056063652039,
+      "learning_rate": 0.0002,
+      "loss": 0.4104,
+      "step": 3980
+    },
+    {
+      "epoch": 4.919852034525277,
+      "grad_norm": 1.019347906112671,
+      "learning_rate": 0.0002,
+      "loss": 0.4496,
+      "step": 3990
+    },
+    {
+      "epoch": 4.932182490752158,
+      "grad_norm": 0.7709218859672546,
+      "learning_rate": 0.0002,
+      "loss": 0.457,
+      "step": 4000
+    },
+    {
+      "epoch": 4.944512946979038,
+      "grad_norm": 0.8891775608062744,
+      "learning_rate": 0.0002,
+      "loss": 0.4697,
+      "step": 4010
+    },
+    {
+      "epoch": 4.9568434032059185,
+      "grad_norm": 1.0396920442581177,
+      "learning_rate": 0.0002,
+      "loss": 0.4436,
+      "step": 4020
+    },
+    {
+      "epoch": 4.969173859432799,
+      "grad_norm": 0.9239833354949951,
+      "learning_rate": 0.0002,
+      "loss": 0.4251,
+      "step": 4030
+    },
+    {
+      "epoch": 4.981504315659679,
+      "grad_norm": 1.801400065422058,
+      "learning_rate": 0.0002,
+      "loss": 0.5049,
+      "step": 4040
+    },
+    {
+      "epoch": 4.99383477188656,
+      "grad_norm": 0.6194164752960205,
+      "learning_rate": 0.0002,
+      "loss": 0.4481,
+      "step": 4050
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.544758915901184,
+      "eval_runtime": 96.2573,
+      "eval_samples_per_second": 4.53,
+      "eval_steps_per_second": 0.571,
+      "step": 4055
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6488,
+  "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": 2.082799885221888e+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-0.6-num-5885-sd-10000/checkpoint-4055/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-0.6-num-5885-sd-10000/checkpoint-4055/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..459ba5959a39ea126110113c9faed75cda19ffff
--- /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-0.6-num-5885-sd-10000/checkpoint-4055/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05287f447dfde244c1a85dc0f576593b4a9dd61961eb0797da4844688fc48447
+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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e04e4441e0c1b29f69c16b26c142944e440b8076
--- /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-0.6-num-5885-sd-10000/checkpoint-4866/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": [
+    "q_proj",
+    "v_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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1a0267c8163302f579a50e891f2ce9e79ff79446
--- /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-0.6-num-5885-sd-10000/checkpoint-4866/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abb743a3afc40061af249d32efbaa49e8d42853ef57a9ec9768d8a351ca7832
+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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5e2a88aa78451f454727122fd93f979b8f1888f9
--- /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-0.6-num-5885-sd-10000/checkpoint-4866/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:354d119b98533a9c8d5ab57f273c8ecc866ad44dea1afbd90e7f91cff4f44fac
+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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1618f54ce3d4debb08fc1e47dbb0d0dd3635c7a2
--- /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-0.6-num-5885-sd-10000/checkpoint-4866/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c570874288ce5fe516c21989469aa2e53d25b4d879077e9e7762412bf3f1bd
+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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..365254da1f0cca2244b245ed9d7bf33826738212
--- /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-0.6-num-5885-sd-10000/checkpoint-4866/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad6e8aba39276d3c67a0c338dee56450410d9e0eddf4f04cbe6bde7c669d697
+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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22
--- /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-0.6-num-5885-sd-10000/checkpoint-4866/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873
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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..9f637cd8759c966b4773976802310e3e4aae1965
--- /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-0.6-num-5885-sd-10000/checkpoint-4866/trainer_state.json
@@ -0,0 +1,3483 @@
+{
+  "best_metric": 1.238026738166809,
+  "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-0.6-num-5885-sd-10000/checkpoint-1622",
+  "epoch": 6.0,
+  "eval_steps": 10,
+  "global_step": 4866,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012330456226880395,
+      "grad_norm": 0.8258164525032043,
+      "learning_rate": 0.0002,
+      "loss": 2.3601,
+      "step": 10
+    },
+    {
+      "epoch": 0.02466091245376079,
+      "grad_norm": 0.4577729105949402,
+      "learning_rate": 0.0002,
+      "loss": 1.7317,
+      "step": 20
+    },
+    {
+      "epoch": 0.036991368680641186,
+      "grad_norm": 0.639807939529419,
+      "learning_rate": 0.0002,
+      "loss": 1.4729,
+      "step": 30
+    },
+    {
+      "epoch": 0.04932182490752158,
+      "grad_norm": 0.5311757922172546,
+      "learning_rate": 0.0002,
+      "loss": 1.2088,
+      "step": 40
+    },
+    {
+      "epoch": 0.06165228113440197,
+      "grad_norm": 0.386595219373703,
+      "learning_rate": 0.0002,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.07398273736128237,
+      "grad_norm": 0.4401357173919678,
+      "learning_rate": 0.0002,
+      "loss": 1.1657,
+      "step": 60
+    },
+    {
+      "epoch": 0.08631319358816276,
+      "grad_norm": 0.3234352171421051,
+      "learning_rate": 0.0002,
+      "loss": 1.1022,
+      "step": 70
+    },
+    {
+      "epoch": 0.09864364981504316,
+      "grad_norm": 0.29643672704696655,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 80
+    },
+    {
+      "epoch": 0.11097410604192355,
+      "grad_norm": 0.2941012382507324,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 90
+    },
+    {
+      "epoch": 0.12330456226880394,
+      "grad_norm": 0.5498173832893372,
+      "learning_rate": 0.0002,
+      "loss": 1.2067,
+      "step": 100
+    },
+    {
+      "epoch": 0.13563501849568435,
+      "grad_norm": 0.2545783519744873,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 110
+    },
+    {
+      "epoch": 0.14796547472256474,
+      "grad_norm": 0.2984241247177124,
+      "learning_rate": 0.0002,
+      "loss": 1.0297,
+      "step": 120
+    },
+    {
+      "epoch": 0.16029593094944514,
+      "grad_norm": 0.2710968852043152,
+      "learning_rate": 0.0002,
+      "loss": 1.1591,
+      "step": 130
+    },
+    {
+      "epoch": 0.17262638717632553,
+      "grad_norm": 0.2817152142524719,
+      "learning_rate": 0.0002,
+      "loss": 1.0427,
+      "step": 140
+    },
+    {
+      "epoch": 0.18495684340320592,
+      "grad_norm": 0.41083765029907227,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 150
+    },
+    {
+      "epoch": 0.19728729963008632,
+      "grad_norm": 0.36536213755607605,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 160
+    },
+    {
+      "epoch": 0.2096177558569667,
+      "grad_norm": 0.2738671600818634,
+      "learning_rate": 0.0002,
+      "loss": 1.0132,
+      "step": 170
+    },
+    {
+      "epoch": 0.2219482120838471,
+      "grad_norm": 0.27403146028518677,
+      "learning_rate": 0.0002,
+      "loss": 0.9555,
+      "step": 180
+    },
+    {
+      "epoch": 0.2342786683107275,
+      "grad_norm": 0.4446810483932495,
+      "learning_rate": 0.0002,
+      "loss": 1.0769,
+      "step": 190
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "grad_norm": 0.5295385718345642,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 200
+    },
+    {
+      "epoch": 0.2589395807644883,
+      "grad_norm": 0.311404824256897,
+      "learning_rate": 0.0002,
+      "loss": 1.0827,
+      "step": 210
+    },
+    {
+      "epoch": 0.2712700369913687,
+      "grad_norm": 0.2448509782552719,
+      "learning_rate": 0.0002,
+      "loss": 1.1455,
+      "step": 220
+    },
+    {
+      "epoch": 0.2836004932182491,
+      "grad_norm": 0.6507014036178589,
+      "learning_rate": 0.0002,
+      "loss": 1.0929,
+      "step": 230
+    },
+    {
+      "epoch": 0.2959309494451295,
+      "grad_norm": 0.2339320331811905,
+      "learning_rate": 0.0002,
+      "loss": 0.9875,
+      "step": 240
+    },
+    {
+      "epoch": 0.3082614056720099,
+      "grad_norm": 0.8210226893424988,
+      "learning_rate": 0.0002,
+      "loss": 0.9211,
+      "step": 250
+    },
+    {
+      "epoch": 0.3205918618988903,
+      "grad_norm": 0.27473965287208557,
+      "learning_rate": 0.0002,
+      "loss": 1.161,
+      "step": 260
+    },
+    {
+      "epoch": 0.33292231812577067,
+      "grad_norm": 0.3051395118236542,
+      "learning_rate": 0.0002,
+      "loss": 1.0218,
+      "step": 270
+    },
+    {
+      "epoch": 0.34525277435265106,
+      "grad_norm": 0.3037777245044708,
+      "learning_rate": 0.0002,
+      "loss": 1.0286,
+      "step": 280
+    },
+    {
+      "epoch": 0.35758323057953145,
+      "grad_norm": 0.2748974859714508,
+      "learning_rate": 0.0002,
+      "loss": 1.144,
+      "step": 290
+    },
+    {
+      "epoch": 0.36991368680641185,
+      "grad_norm": 0.23656068742275238,
+      "learning_rate": 0.0002,
+      "loss": 1.0858,
+      "step": 300
+    },
+    {
+      "epoch": 0.38224414303329224,
+      "grad_norm": 0.2523384094238281,
+      "learning_rate": 0.0002,
+      "loss": 1.0564,
+      "step": 310
+    },
+    {
+      "epoch": 0.39457459926017263,
+      "grad_norm": 0.27848055958747864,
+      "learning_rate": 0.0002,
+      "loss": 1.3091,
+      "step": 320
+    },
+    {
+      "epoch": 0.406905055487053,
+      "grad_norm": 0.3204525411128998,
+      "learning_rate": 0.0002,
+      "loss": 1.0252,
+      "step": 330
+    },
+    {
+      "epoch": 0.4192355117139334,
+      "grad_norm": 0.3459707498550415,
+      "learning_rate": 0.0002,
+      "loss": 0.9855,
+      "step": 340
+    },
+    {
+      "epoch": 0.4315659679408138,
+      "grad_norm": 0.2458430379629135,
+      "learning_rate": 0.0002,
+      "loss": 1.1111,
+      "step": 350
+    },
+    {
+      "epoch": 0.4438964241676942,
+      "grad_norm": 0.5022910237312317,
+      "learning_rate": 0.0002,
+      "loss": 1.1493,
+      "step": 360
+    },
+    {
+      "epoch": 0.4562268803945746,
+      "grad_norm": 0.27076372504234314,
+      "learning_rate": 0.0002,
+      "loss": 1.1272,
+      "step": 370
+    },
+    {
+      "epoch": 0.468557336621455,
+      "grad_norm": 0.6489047408103943,
+      "learning_rate": 0.0002,
+      "loss": 1.1927,
+      "step": 380
+    },
+    {
+      "epoch": 0.4808877928483354,
+      "grad_norm": 0.3324144184589386,
+      "learning_rate": 0.0002,
+      "loss": 0.9501,
+      "step": 390
+    },
+    {
+      "epoch": 0.4932182490752158,
+      "grad_norm": 0.32813116908073425,
+      "learning_rate": 0.0002,
+      "loss": 1.2012,
+      "step": 400
+    },
+    {
+      "epoch": 0.5055487053020962,
+      "grad_norm": 0.25295355916023254,
+      "learning_rate": 0.0002,
+      "loss": 1.1135,
+      "step": 410
+    },
+    {
+      "epoch": 0.5178791615289766,
+      "grad_norm": 0.2912578880786896,
+      "learning_rate": 0.0002,
+      "loss": 0.9477,
+      "step": 420
+    },
+    {
+      "epoch": 0.530209617755857,
+      "grad_norm": 0.34780189394950867,
+      "learning_rate": 0.0002,
+      "loss": 1.0121,
+      "step": 430
+    },
+    {
+      "epoch": 0.5425400739827374,
+      "grad_norm": 0.24604526162147522,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 440
+    },
+    {
+      "epoch": 0.5548705302096177,
+      "grad_norm": 0.32759982347488403,
+      "learning_rate": 0.0002,
+      "loss": 1.253,
+      "step": 450
+    },
+    {
+      "epoch": 0.5672009864364982,
+      "grad_norm": 0.40810221433639526,
+      "learning_rate": 0.0002,
+      "loss": 1.1925,
+      "step": 460
+    },
+    {
+      "epoch": 0.5795314426633785,
+      "grad_norm": 0.3590679466724396,
+      "learning_rate": 0.0002,
+      "loss": 1.174,
+      "step": 470
+    },
+    {
+      "epoch": 0.591861898890259,
+      "grad_norm": 0.5656213760375977,
+      "learning_rate": 0.0002,
+      "loss": 1.2223,
+      "step": 480
+    },
+    {
+      "epoch": 0.6041923551171393,
+      "grad_norm": 0.30830657482147217,
+      "learning_rate": 0.0002,
+      "loss": 1.1936,
+      "step": 490
+    },
+    {
+      "epoch": 0.6165228113440198,
+      "grad_norm": 0.317905455827713,
+      "learning_rate": 0.0002,
+      "loss": 1.1873,
+      "step": 500
+    },
+    {
+      "epoch": 0.6288532675709001,
+      "grad_norm": 0.3254566490650177,
+      "learning_rate": 0.0002,
+      "loss": 0.9805,
+      "step": 510
+    },
+    {
+      "epoch": 0.6411837237977805,
+      "grad_norm": 0.29187721014022827,
+      "learning_rate": 0.0002,
+      "loss": 1.0384,
+      "step": 520
+    },
+    {
+      "epoch": 0.6535141800246609,
+      "grad_norm": 0.3439238965511322,
+      "learning_rate": 0.0002,
+      "loss": 1.2526,
+      "step": 530
+    },
+    {
+      "epoch": 0.6658446362515413,
+      "grad_norm": 0.20970556139945984,
+      "learning_rate": 0.0002,
+      "loss": 1.0698,
+      "step": 540
+    },
+    {
+      "epoch": 0.6781750924784217,
+      "grad_norm": 0.4022853374481201,
+      "learning_rate": 0.0002,
+      "loss": 1.1047,
+      "step": 550
+    },
+    {
+      "epoch": 0.6905055487053021,
+      "grad_norm": 0.2235759049654007,
+      "learning_rate": 0.0002,
+      "loss": 1.0684,
+      "step": 560
+    },
+    {
+      "epoch": 0.7028360049321825,
+      "grad_norm": 0.33849895000457764,
+      "learning_rate": 0.0002,
+      "loss": 1.2339,
+      "step": 570
+    },
+    {
+      "epoch": 0.7151664611590629,
+      "grad_norm": 0.34745967388153076,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 580
+    },
+    {
+      "epoch": 0.7274969173859432,
+      "grad_norm": 0.26041269302368164,
+      "learning_rate": 0.0002,
+      "loss": 1.1158,
+      "step": 590
+    },
+    {
+      "epoch": 0.7398273736128237,
+      "grad_norm": 0.3804777264595032,
+      "learning_rate": 0.0002,
+      "loss": 1.2134,
+      "step": 600
+    },
+    {
+      "epoch": 0.752157829839704,
+      "grad_norm": 0.2456253319978714,
+      "learning_rate": 0.0002,
+      "loss": 1.0606,
+      "step": 610
+    },
+    {
+      "epoch": 0.7644882860665845,
+      "grad_norm": 0.37838423252105713,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 620
+    },
+    {
+      "epoch": 0.7768187422934648,
+      "grad_norm": 0.28105494379997253,
+      "learning_rate": 0.0002,
+      "loss": 1.0556,
+      "step": 630
+    },
+    {
+      "epoch": 0.7891491985203453,
+      "grad_norm": 0.2774018943309784,
+      "learning_rate": 0.0002,
+      "loss": 1.0672,
+      "step": 640
+    },
+    {
+      "epoch": 0.8014796547472256,
+      "grad_norm": 1.8184229135513306,
+      "learning_rate": 0.0002,
+      "loss": 0.9978,
+      "step": 650
+    },
+    {
+      "epoch": 0.813810110974106,
+      "grad_norm": 0.3325096070766449,
+      "learning_rate": 0.0002,
+      "loss": 1.1038,
+      "step": 660
+    },
+    {
+      "epoch": 0.8261405672009864,
+      "grad_norm": 0.2686693072319031,
+      "learning_rate": 0.0002,
+      "loss": 1.083,
+      "step": 670
+    },
+    {
+      "epoch": 0.8384710234278668,
+      "grad_norm": 0.3271431624889374,
+      "learning_rate": 0.0002,
+      "loss": 1.1308,
+      "step": 680
+    },
+    {
+      "epoch": 0.8508014796547472,
+      "grad_norm": 2.359999656677246,
+      "learning_rate": 0.0002,
+      "loss": 1.1116,
+      "step": 690
+    },
+    {
+      "epoch": 0.8631319358816276,
+      "grad_norm": 0.46242964267730713,
+      "learning_rate": 0.0002,
+      "loss": 1.0782,
+      "step": 700
+    },
+    {
+      "epoch": 0.8754623921085081,
+      "grad_norm": 0.34731170535087585,
+      "learning_rate": 0.0002,
+      "loss": 0.95,
+      "step": 710
+    },
+    {
+      "epoch": 0.8877928483353884,
+      "grad_norm": 0.39381715655326843,
+      "learning_rate": 0.0002,
+      "loss": 1.2236,
+      "step": 720
+    },
+    {
+      "epoch": 0.9001233045622689,
+      "grad_norm": 0.43496373295783997,
+      "learning_rate": 0.0002,
+      "loss": 1.1319,
+      "step": 730
+    },
+    {
+      "epoch": 0.9124537607891492,
+      "grad_norm": 0.32243210077285767,
+      "learning_rate": 0.0002,
+      "loss": 1.0979,
+      "step": 740
+    },
+    {
+      "epoch": 0.9247842170160296,
+      "grad_norm": 0.30396756529808044,
+      "learning_rate": 0.0002,
+      "loss": 0.9913,
+      "step": 750
+    },
+    {
+      "epoch": 0.93711467324291,
+      "grad_norm": 0.4461122751235962,
+      "learning_rate": 0.0002,
+      "loss": 1.1141,
+      "step": 760
+    },
+    {
+      "epoch": 0.9494451294697904,
+      "grad_norm": 0.24081681668758392,
+      "learning_rate": 0.0002,
+      "loss": 1.0049,
+      "step": 770
+    },
+    {
+      "epoch": 0.9617755856966708,
+      "grad_norm": 0.27461910247802734,
+      "learning_rate": 0.0002,
+      "loss": 1.0966,
+      "step": 780
+    },
+    {
+      "epoch": 0.9741060419235512,
+      "grad_norm": 0.3325668275356293,
+      "learning_rate": 0.0002,
+      "loss": 0.9942,
+      "step": 790
+    },
+    {
+      "epoch": 0.9864364981504316,
+      "grad_norm": 0.24046339094638824,
+      "learning_rate": 0.0002,
+      "loss": 1.0506,
+      "step": 800
+    },
+    {
+      "epoch": 0.998766954377312,
+      "grad_norm": 0.42950066924095154,
+      "learning_rate": 0.0002,
+      "loss": 0.9989,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.246457576751709,
+      "eval_runtime": 98.7974,
+      "eval_samples_per_second": 4.413,
+      "eval_steps_per_second": 0.557,
+      "step": 811
+    },
+    {
+      "epoch": 1.0110974106041923,
+      "grad_norm": 0.26760655641555786,
+      "learning_rate": 0.0002,
+      "loss": 1.0536,
+      "step": 820
+    },
+    {
+      "epoch": 1.0234278668310728,
+      "grad_norm": 0.4640820026397705,
+      "learning_rate": 0.0002,
+      "loss": 0.9722,
+      "step": 830
+    },
+    {
+      "epoch": 1.0357583230579532,
+      "grad_norm": 0.2699166238307953,
+      "learning_rate": 0.0002,
+      "loss": 0.9392,
+      "step": 840
+    },
+    {
+      "epoch": 1.0480887792848335,
+      "grad_norm": 0.3441709578037262,
+      "learning_rate": 0.0002,
+      "loss": 0.9335,
+      "step": 850
+    },
+    {
+      "epoch": 1.060419235511714,
+      "grad_norm": 0.299934983253479,
+      "learning_rate": 0.0002,
+      "loss": 0.9083,
+      "step": 860
+    },
+    {
+      "epoch": 1.0727496917385944,
+      "grad_norm": 0.2980666160583496,
+      "learning_rate": 0.0002,
+      "loss": 0.9416,
+      "step": 870
+    },
+    {
+      "epoch": 1.0850801479654748,
+      "grad_norm": 0.3131714463233948,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 880
+    },
+    {
+      "epoch": 1.097410604192355,
+      "grad_norm": 0.29881617426872253,
+      "learning_rate": 0.0002,
+      "loss": 0.9288,
+      "step": 890
+    },
+    {
+      "epoch": 1.1097410604192355,
+      "grad_norm": 0.29870888590812683,
+      "learning_rate": 0.0002,
+      "loss": 0.998,
+      "step": 900
+    },
+    {
+      "epoch": 1.122071516646116,
+      "grad_norm": 0.5735140442848206,
+      "learning_rate": 0.0002,
+      "loss": 0.9924,
+      "step": 910
+    },
+    {
+      "epoch": 1.1344019728729964,
+      "grad_norm": 0.33159002661705017,
+      "learning_rate": 0.0002,
+      "loss": 1.0694,
+      "step": 920
+    },
+    {
+      "epoch": 1.1467324290998766,
+      "grad_norm": 1.235399842262268,
+      "learning_rate": 0.0002,
+      "loss": 1.0069,
+      "step": 930
+    },
+    {
+      "epoch": 1.159062885326757,
+      "grad_norm": 0.27469736337661743,
+      "learning_rate": 0.0002,
+      "loss": 1.0315,
+      "step": 940
+    },
+    {
+      "epoch": 1.1713933415536375,
+      "grad_norm": 0.29130664467811584,
+      "learning_rate": 0.0002,
+      "loss": 0.9386,
+      "step": 950
+    },
+    {
+      "epoch": 1.183723797780518,
+      "grad_norm": 0.3730354607105255,
+      "learning_rate": 0.0002,
+      "loss": 0.8919,
+      "step": 960
+    },
+    {
+      "epoch": 1.1960542540073984,
+      "grad_norm": 0.5973590612411499,
+      "learning_rate": 0.0002,
+      "loss": 0.9988,
+      "step": 970
+    },
+    {
+      "epoch": 1.2083847102342786,
+      "grad_norm": 0.39631304144859314,
+      "learning_rate": 0.0002,
+      "loss": 0.9525,
+      "step": 980
+    },
+    {
+      "epoch": 1.220715166461159,
+      "grad_norm": 0.849051296710968,
+      "learning_rate": 0.0002,
+      "loss": 0.9217,
+      "step": 990
+    },
+    {
+      "epoch": 1.2330456226880395,
+      "grad_norm": 0.4390525817871094,
+      "learning_rate": 0.0002,
+      "loss": 1.0903,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2453760789149197,
+      "grad_norm": 0.30423852801322937,
+      "learning_rate": 0.0002,
+      "loss": 0.9018,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2577065351418002,
+      "grad_norm": 0.34736061096191406,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2700369913686806,
+      "grad_norm": 0.3421604037284851,
+      "learning_rate": 0.0002,
+      "loss": 0.9026,
+      "step": 1030
+    },
+    {
+      "epoch": 1.282367447595561,
+      "grad_norm": 0.544170081615448,
+      "learning_rate": 0.0002,
+      "loss": 0.8485,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2946979038224415,
+      "grad_norm": 0.5128790736198425,
+      "learning_rate": 0.0002,
+      "loss": 0.9591,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3070283600493218,
+      "grad_norm": 0.443344384431839,
+      "learning_rate": 0.0002,
+      "loss": 0.9214,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3193588162762022,
+      "grad_norm": 0.6380868554115295,
+      "learning_rate": 0.0002,
+      "loss": 0.9367,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3316892725030827,
+      "grad_norm": 0.4638073146343231,
+      "learning_rate": 0.0002,
+      "loss": 0.9849,
+      "step": 1080
+    },
+    {
+      "epoch": 1.344019728729963,
+      "grad_norm": 0.32406893372535706,
+      "learning_rate": 0.0002,
+      "loss": 0.8645,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3563501849568433,
+      "grad_norm": 0.3955065608024597,
+      "learning_rate": 0.0002,
+      "loss": 0.8278,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3686806411837238,
+      "grad_norm": 0.3489246666431427,
+      "learning_rate": 0.0002,
+      "loss": 0.9306,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3810110974106042,
+      "grad_norm": 0.48451653122901917,
+      "learning_rate": 0.0002,
+      "loss": 1.0138,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3933415536374847,
+      "grad_norm": 0.3652360439300537,
+      "learning_rate": 0.0002,
+      "loss": 0.9165,
+      "step": 1130
+    },
+    {
+      "epoch": 1.405672009864365,
+      "grad_norm": 1.3097436428070068,
+      "learning_rate": 0.0002,
+      "loss": 0.9576,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4180024660912454,
+      "grad_norm": 0.3647715449333191,
+      "learning_rate": 0.0002,
+      "loss": 0.8115,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4303329223181258,
+      "grad_norm": 0.37248560786247253,
+      "learning_rate": 0.0002,
+      "loss": 0.8573,
+      "step": 1160
+    },
+    {
+      "epoch": 1.442663378545006,
+      "grad_norm": 0.4639643430709839,
+      "learning_rate": 0.0002,
+      "loss": 0.936,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4549938347718865,
+      "grad_norm": 0.5455219745635986,
+      "learning_rate": 0.0002,
+      "loss": 0.9511,
+      "step": 1180
+    },
+    {
+      "epoch": 1.467324290998767,
+      "grad_norm": 0.38862571120262146,
+      "learning_rate": 0.0002,
+      "loss": 0.8611,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4796547472256474,
+      "grad_norm": 0.37586215138435364,
+      "learning_rate": 0.0002,
+      "loss": 0.8681,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4919852034525278,
+      "grad_norm": 0.46244436502456665,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1210
+    },
+    {
+      "epoch": 1.504315659679408,
+      "grad_norm": 0.3570359945297241,
+      "learning_rate": 0.0002,
+      "loss": 0.9388,
+      "step": 1220
+    },
+    {
+      "epoch": 1.5166461159062885,
+      "grad_norm": 0.28393083810806274,
+      "learning_rate": 0.0002,
+      "loss": 0.971,
+      "step": 1230
+    },
+    {
+      "epoch": 1.528976572133169,
+      "grad_norm": 0.5672869682312012,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5413070283600492,
+      "grad_norm": 0.41605108976364136,
+      "learning_rate": 0.0002,
+      "loss": 0.8787,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5536374845869299,
+      "grad_norm": 0.40657493472099304,
+      "learning_rate": 0.0002,
+      "loss": 0.8744,
+      "step": 1260
+    },
+    {
+      "epoch": 1.56596794081381,
+      "grad_norm": 0.43672341108322144,
+      "learning_rate": 0.0002,
+      "loss": 0.9046,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5782983970406905,
+      "grad_norm": 0.3065410554409027,
+      "learning_rate": 0.0002,
+      "loss": 0.8586,
+      "step": 1280
+    },
+    {
+      "epoch": 1.590628853267571,
+      "grad_norm": 0.37826645374298096,
+      "learning_rate": 0.0002,
+      "loss": 0.9499,
+      "step": 1290
+    },
+    {
+      "epoch": 1.6029593094944512,
+      "grad_norm": 0.42307335138320923,
+      "learning_rate": 0.0002,
+      "loss": 0.901,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6152897657213316,
+      "grad_norm": 0.3648843467235565,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1310
+    },
+    {
+      "epoch": 1.627620221948212,
+      "grad_norm": 0.8921076059341431,
+      "learning_rate": 0.0002,
+      "loss": 0.9302,
+      "step": 1320
+    },
+    {
+      "epoch": 1.6399506781750923,
+      "grad_norm": 0.37522226572036743,
+      "learning_rate": 0.0002,
+      "loss": 0.9378,
+      "step": 1330
+    },
+    {
+      "epoch": 1.652281134401973,
+      "grad_norm": 0.7489957809448242,
+      "learning_rate": 0.0002,
+      "loss": 0.8921,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6646115906288532,
+      "grad_norm": 0.31733131408691406,
+      "learning_rate": 0.0002,
+      "loss": 0.9297,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6769420468557337,
+      "grad_norm": 0.3249478340148926,
+      "learning_rate": 0.0002,
+      "loss": 0.907,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6892725030826141,
+      "grad_norm": 0.3178001344203949,
+      "learning_rate": 0.0002,
+      "loss": 1.0197,
+      "step": 1370
+    },
+    {
+      "epoch": 1.7016029593094943,
+      "grad_norm": 0.5674093961715698,
+      "learning_rate": 0.0002,
+      "loss": 1.0781,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7139334155363748,
+      "grad_norm": 0.35272449254989624,
+      "learning_rate": 0.0002,
+      "loss": 0.8972,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7262638717632552,
+      "grad_norm": 0.5778217911720276,
+      "learning_rate": 0.0002,
+      "loss": 0.9346,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7385943279901355,
+      "grad_norm": 0.33561450242996216,
+      "learning_rate": 0.0002,
+      "loss": 0.9099,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7509247842170161,
+      "grad_norm": 0.31735464930534363,
+      "learning_rate": 0.0002,
+      "loss": 0.8636,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7632552404438964,
+      "grad_norm": 1.0612670183181763,
+      "learning_rate": 0.0002,
+      "loss": 0.982,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7755856966707768,
+      "grad_norm": 0.5442509651184082,
+      "learning_rate": 0.0002,
+      "loss": 0.8224,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7879161528976573,
+      "grad_norm": 0.7471332550048828,
+      "learning_rate": 0.0002,
+      "loss": 0.9275,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8002466091245375,
+      "grad_norm": 0.4323609173297882,
+      "learning_rate": 0.0002,
+      "loss": 0.9389,
+      "step": 1460
+    },
+    {
+      "epoch": 1.8125770653514182,
+      "grad_norm": 0.47796759009361267,
+      "learning_rate": 0.0002,
+      "loss": 0.8247,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8249075215782984,
+      "grad_norm": 0.3348400592803955,
+      "learning_rate": 0.0002,
+      "loss": 0.9395,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8372379778051788,
+      "grad_norm": 0.3354550898075104,
+      "learning_rate": 0.0002,
+      "loss": 0.9793,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8495684340320593,
+      "grad_norm": 0.5988477468490601,
+      "learning_rate": 0.0002,
+      "loss": 0.8581,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8618988902589395,
+      "grad_norm": 0.5222318172454834,
+      "learning_rate": 0.0002,
+      "loss": 0.9268,
+      "step": 1510
+    },
+    {
+      "epoch": 1.87422934648582,
+      "grad_norm": 0.5246642827987671,
+      "learning_rate": 0.0002,
+      "loss": 0.8846,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8865598027127004,
+      "grad_norm": 0.3164594769477844,
+      "learning_rate": 0.0002,
+      "loss": 0.9317,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8988902589395806,
+      "grad_norm": 0.3496174216270447,
+      "learning_rate": 0.0002,
+      "loss": 0.9961,
+      "step": 1540
+    },
+    {
+      "epoch": 1.9112207151664613,
+      "grad_norm": 0.8863359689712524,
+      "learning_rate": 0.0002,
+      "loss": 0.9057,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9235511713933415,
+      "grad_norm": 0.3587026298046112,
+      "learning_rate": 0.0002,
+      "loss": 0.9405,
+      "step": 1560
+    },
+    {
+      "epoch": 1.935881627620222,
+      "grad_norm": 0.6052881479263306,
+      "learning_rate": 0.0002,
+      "loss": 0.8335,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9482120838471024,
+      "grad_norm": 0.567269504070282,
+      "learning_rate": 0.0002,
+      "loss": 0.8805,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9605425400739827,
+      "grad_norm": 0.45184487104415894,
+      "learning_rate": 0.0002,
+      "loss": 0.9581,
+      "step": 1590
+    },
+    {
+      "epoch": 1.972872996300863,
+      "grad_norm": 0.5028569102287292,
+      "learning_rate": 0.0002,
+      "loss": 0.9147,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9852034525277436,
+      "grad_norm": 0.4677547216415405,
+      "learning_rate": 0.0002,
+      "loss": 0.75,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9975339087546238,
+      "grad_norm": 0.35106056928634644,
+      "learning_rate": 0.0002,
+      "loss": 0.8469,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.238026738166809,
+      "eval_runtime": 95.4287,
+      "eval_samples_per_second": 4.569,
+      "eval_steps_per_second": 0.576,
+      "step": 1622
+    },
+    {
+      "epoch": 2.0098643649815044,
+      "grad_norm": 0.444060355424881,
+      "learning_rate": 0.0002,
+      "loss": 0.7629,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0221948212083847,
+      "grad_norm": 0.627570390701294,
+      "learning_rate": 0.0002,
+      "loss": 0.772,
+      "step": 1640
+    },
+    {
+      "epoch": 2.034525277435265,
+      "grad_norm": 0.38737839460372925,
+      "learning_rate": 0.0002,
+      "loss": 0.6186,
+      "step": 1650
+    },
+    {
+      "epoch": 2.0468557336621456,
+      "grad_norm": 0.4300459623336792,
+      "learning_rate": 0.0002,
+      "loss": 0.7734,
+      "step": 1660
+    },
+    {
+      "epoch": 2.059186189889026,
+      "grad_norm": 0.43037715554237366,
+      "learning_rate": 0.0002,
+      "loss": 0.6943,
+      "step": 1670
+    },
+    {
+      "epoch": 2.0715166461159065,
+      "grad_norm": 0.40772515535354614,
+      "learning_rate": 0.0002,
+      "loss": 0.6588,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0838471023427867,
+      "grad_norm": 0.5295451879501343,
+      "learning_rate": 0.0002,
+      "loss": 0.8105,
+      "step": 1690
+    },
+    {
+      "epoch": 2.096177558569667,
+      "grad_norm": 0.7452750205993652,
+      "learning_rate": 0.0002,
+      "loss": 0.7717,
+      "step": 1700
+    },
+    {
+      "epoch": 2.1085080147965476,
+      "grad_norm": 0.809183657169342,
+      "learning_rate": 0.0002,
+      "loss": 0.7458,
+      "step": 1710
+    },
+    {
+      "epoch": 2.120838471023428,
+      "grad_norm": 0.4597688913345337,
+      "learning_rate": 0.0002,
+      "loss": 0.7398,
+      "step": 1720
+    },
+    {
+      "epoch": 2.133168927250308,
+      "grad_norm": 0.806919276714325,
+      "learning_rate": 0.0002,
+      "loss": 0.6856,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1454993834771887,
+      "grad_norm": 0.3755643665790558,
+      "learning_rate": 0.0002,
+      "loss": 0.679,
+      "step": 1740
+    },
+    {
+      "epoch": 2.157829839704069,
+      "grad_norm": 0.5882734060287476,
+      "learning_rate": 0.0002,
+      "loss": 0.7938,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1701602959309496,
+      "grad_norm": 0.692960798740387,
+      "learning_rate": 0.0002,
+      "loss": 0.6782,
+      "step": 1760
+    },
+    {
+      "epoch": 2.18249075215783,
+      "grad_norm": 0.4737096428871155,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 1770
+    },
+    {
+      "epoch": 2.19482120838471,
+      "grad_norm": 0.6637021899223328,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 1780
+    },
+    {
+      "epoch": 2.2071516646115907,
+      "grad_norm": 0.9109764099121094,
+      "learning_rate": 0.0002,
+      "loss": 0.7139,
+      "step": 1790
+    },
+    {
+      "epoch": 2.219482120838471,
+      "grad_norm": 0.4137539267539978,
+      "learning_rate": 0.0002,
+      "loss": 0.7373,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2318125770653516,
+      "grad_norm": 0.44995415210723877,
+      "learning_rate": 0.0002,
+      "loss": 0.7266,
+      "step": 1810
+    },
+    {
+      "epoch": 2.244143033292232,
+      "grad_norm": 0.5985036492347717,
+      "learning_rate": 0.0002,
+      "loss": 0.7663,
+      "step": 1820
+    },
+    {
+      "epoch": 2.256473489519112,
+      "grad_norm": 0.7549490332603455,
+      "learning_rate": 0.0002,
+      "loss": 0.7502,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2688039457459928,
+      "grad_norm": 0.4490937888622284,
+      "learning_rate": 0.0002,
+      "loss": 0.7452,
+      "step": 1840
+    },
+    {
+      "epoch": 2.281134401972873,
+      "grad_norm": 0.38859808444976807,
+      "learning_rate": 0.0002,
+      "loss": 0.7531,
+      "step": 1850
+    },
+    {
+      "epoch": 2.293464858199753,
+      "grad_norm": 1.0704916715621948,
+      "learning_rate": 0.0002,
+      "loss": 0.7278,
+      "step": 1860
+    },
+    {
+      "epoch": 2.305795314426634,
+      "grad_norm": 0.4647100865840912,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 1870
+    },
+    {
+      "epoch": 2.318125770653514,
+      "grad_norm": 0.6181163787841797,
+      "learning_rate": 0.0002,
+      "loss": 0.7146,
+      "step": 1880
+    },
+    {
+      "epoch": 2.3304562268803943,
+      "grad_norm": 0.9241904020309448,
+      "learning_rate": 0.0002,
+      "loss": 0.7689,
+      "step": 1890
+    },
+    {
+      "epoch": 2.342786683107275,
+      "grad_norm": 0.39101317524909973,
+      "learning_rate": 0.0002,
+      "loss": 0.7294,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3551171393341552,
+      "grad_norm": 0.49442458152770996,
+      "learning_rate": 0.0002,
+      "loss": 0.7079,
+      "step": 1910
+    },
+    {
+      "epoch": 2.367447595561036,
+      "grad_norm": 0.4864824414253235,
+      "learning_rate": 0.0002,
+      "loss": 0.7586,
+      "step": 1920
+    },
+    {
+      "epoch": 2.379778051787916,
+      "grad_norm": 0.5427613854408264,
+      "learning_rate": 0.0002,
+      "loss": 0.7434,
+      "step": 1930
+    },
+    {
+      "epoch": 2.392108508014797,
+      "grad_norm": 0.7164974808692932,
+      "learning_rate": 0.0002,
+      "loss": 0.8423,
+      "step": 1940
+    },
+    {
+      "epoch": 2.404438964241677,
+      "grad_norm": 0.562979519367218,
+      "learning_rate": 0.0002,
+      "loss": 0.6888,
+      "step": 1950
+    },
+    {
+      "epoch": 2.4167694204685573,
+      "grad_norm": 0.5631861090660095,
+      "learning_rate": 0.0002,
+      "loss": 0.7692,
+      "step": 1960
+    },
+    {
+      "epoch": 2.429099876695438,
+      "grad_norm": 0.4895121157169342,
+      "learning_rate": 0.0002,
+      "loss": 0.67,
+      "step": 1970
+    },
+    {
+      "epoch": 2.441430332922318,
+      "grad_norm": 0.45674824714660645,
+      "learning_rate": 0.0002,
+      "loss": 0.7735,
+      "step": 1980
+    },
+    {
+      "epoch": 2.4537607891491984,
+      "grad_norm": 1.1424206495285034,
+      "learning_rate": 0.0002,
+      "loss": 0.685,
+      "step": 1990
+    },
+    {
+      "epoch": 2.466091245376079,
+      "grad_norm": 0.6314579844474792,
+      "learning_rate": 0.0002,
+      "loss": 0.7627,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4784217016029593,
+      "grad_norm": 0.5481605529785156,
+      "learning_rate": 0.0002,
+      "loss": 0.7118,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4907521578298395,
+      "grad_norm": 0.4671579599380493,
+      "learning_rate": 0.0002,
+      "loss": 0.6947,
+      "step": 2020
+    },
+    {
+      "epoch": 2.50308261405672,
+      "grad_norm": 0.7621194124221802,
+      "learning_rate": 0.0002,
+      "loss": 0.7377,
+      "step": 2030
+    },
+    {
+      "epoch": 2.5154130702836004,
+      "grad_norm": 0.38983288407325745,
+      "learning_rate": 0.0002,
+      "loss": 0.69,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5277435265104806,
+      "grad_norm": 0.6341150999069214,
+      "learning_rate": 0.0002,
+      "loss": 0.8381,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5400739827373613,
+      "grad_norm": 0.7151971459388733,
+      "learning_rate": 0.0002,
+      "loss": 0.773,
+      "step": 2060
+    },
+    {
+      "epoch": 2.5524044389642415,
+      "grad_norm": 0.9665895104408264,
+      "learning_rate": 0.0002,
+      "loss": 0.6733,
+      "step": 2070
+    },
+    {
+      "epoch": 2.564734895191122,
+      "grad_norm": 0.9572727680206299,
+      "learning_rate": 0.0002,
+      "loss": 0.7791,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5770653514180024,
+      "grad_norm": 1.1970765590667725,
+      "learning_rate": 0.0002,
+      "loss": 0.7205,
+      "step": 2090
+    },
+    {
+      "epoch": 2.589395807644883,
+      "grad_norm": 0.5505942702293396,
+      "learning_rate": 0.0002,
+      "loss": 0.6736,
+      "step": 2100
+    },
+    {
+      "epoch": 2.6017262638717633,
+      "grad_norm": 0.5903949737548828,
+      "learning_rate": 0.0002,
+      "loss": 0.673,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6140567200986435,
+      "grad_norm": 0.45640307664871216,
+      "learning_rate": 0.0002,
+      "loss": 0.678,
+      "step": 2120
+    },
+    {
+      "epoch": 2.626387176325524,
+      "grad_norm": 0.8763944506645203,
+      "learning_rate": 0.0002,
+      "loss": 0.6562,
+      "step": 2130
+    },
+    {
+      "epoch": 2.6387176325524044,
+      "grad_norm": 0.4472963213920593,
+      "learning_rate": 0.0002,
+      "loss": 0.6484,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6510480887792847,
+      "grad_norm": 0.5335086584091187,
+      "learning_rate": 0.0002,
+      "loss": 0.7702,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6633785450061653,
+      "grad_norm": 0.805263340473175,
+      "learning_rate": 0.0002,
+      "loss": 0.6851,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6757090012330456,
+      "grad_norm": 0.6332727670669556,
+      "learning_rate": 0.0002,
+      "loss": 0.7026,
+      "step": 2170
+    },
+    {
+      "epoch": 2.688039457459926,
+      "grad_norm": 0.8667435646057129,
+      "learning_rate": 0.0002,
+      "loss": 0.7925,
+      "step": 2180
+    },
+    {
+      "epoch": 2.7003699136868065,
+      "grad_norm": 0.5638955235481262,
+      "learning_rate": 0.0002,
+      "loss": 0.8044,
+      "step": 2190
+    },
+    {
+      "epoch": 2.7127003699136867,
+      "grad_norm": 0.4176250696182251,
+      "learning_rate": 0.0002,
+      "loss": 0.7117,
+      "step": 2200
+    },
+    {
+      "epoch": 2.7250308261405674,
+      "grad_norm": 0.6013461351394653,
+      "learning_rate": 0.0002,
+      "loss": 0.6932,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7373612823674476,
+      "grad_norm": 0.553961992263794,
+      "learning_rate": 0.0002,
+      "loss": 0.7843,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7496917385943282,
+      "grad_norm": 0.4710180461406708,
+      "learning_rate": 0.0002,
+      "loss": 0.8633,
+      "step": 2230
+    },
+    {
+      "epoch": 2.7620221948212085,
+      "grad_norm": 0.8141706585884094,
+      "learning_rate": 0.0002,
+      "loss": 0.7469,
+      "step": 2240
+    },
+    {
+      "epoch": 2.7743526510480887,
+      "grad_norm": 0.7449556589126587,
+      "learning_rate": 0.0002,
+      "loss": 0.7086,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7866831072749694,
+      "grad_norm": 0.5366780757904053,
+      "learning_rate": 0.0002,
+      "loss": 0.6933,
+      "step": 2260
+    },
+    {
+      "epoch": 2.7990135635018496,
+      "grad_norm": 0.5316720604896545,
+      "learning_rate": 0.0002,
+      "loss": 0.7192,
+      "step": 2270
+    },
+    {
+      "epoch": 2.81134401972873,
+      "grad_norm": 0.4598459005355835,
+      "learning_rate": 0.0002,
+      "loss": 0.6212,
+      "step": 2280
+    },
+    {
+      "epoch": 2.8236744759556105,
+      "grad_norm": 0.6852091550827026,
+      "learning_rate": 0.0002,
+      "loss": 0.7024,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8360049321824907,
+      "grad_norm": 0.8040902018547058,
+      "learning_rate": 0.0002,
+      "loss": 0.7357,
+      "step": 2300
+    },
+    {
+      "epoch": 2.848335388409371,
+      "grad_norm": 0.46976321935653687,
+      "learning_rate": 0.0002,
+      "loss": 0.7563,
+      "step": 2310
+    },
+    {
+      "epoch": 2.8606658446362516,
+      "grad_norm": 0.5214090347290039,
+      "learning_rate": 0.0002,
+      "loss": 0.731,
+      "step": 2320
+    },
+    {
+      "epoch": 2.872996300863132,
+      "grad_norm": 0.5323054790496826,
+      "learning_rate": 0.0002,
+      "loss": 0.6687,
+      "step": 2330
+    },
+    {
+      "epoch": 2.885326757090012,
+      "grad_norm": 0.6842264533042908,
+      "learning_rate": 0.0002,
+      "loss": 0.7895,
+      "step": 2340
+    },
+    {
+      "epoch": 2.8976572133168927,
+      "grad_norm": 0.9157055616378784,
+      "learning_rate": 0.0002,
+      "loss": 0.7737,
+      "step": 2350
+    },
+    {
+      "epoch": 2.909987669543773,
+      "grad_norm": 0.5253258347511292,
+      "learning_rate": 0.0002,
+      "loss": 0.7217,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9223181257706536,
+      "grad_norm": 0.4937705099582672,
+      "learning_rate": 0.0002,
+      "loss": 0.7162,
+      "step": 2370
+    },
+    {
+      "epoch": 2.934648581997534,
+      "grad_norm": 0.48762989044189453,
+      "learning_rate": 0.0002,
+      "loss": 0.7008,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9469790382244145,
+      "grad_norm": 0.544335126876831,
+      "learning_rate": 0.0002,
+      "loss": 0.8086,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9593094944512948,
+      "grad_norm": 0.4847845435142517,
+      "learning_rate": 0.0002,
+      "loss": 0.643,
+      "step": 2400
+    },
+    {
+      "epoch": 2.971639950678175,
+      "grad_norm": 0.4787445366382599,
+      "learning_rate": 0.0002,
+      "loss": 0.7757,
+      "step": 2410
+    },
+    {
+      "epoch": 2.9839704069050557,
+      "grad_norm": 1.022318959236145,
+      "learning_rate": 0.0002,
+      "loss": 0.7678,
+      "step": 2420
+    },
+    {
+      "epoch": 2.996300863131936,
+      "grad_norm": 0.4987848103046417,
+      "learning_rate": 0.0002,
+      "loss": 0.6548,
+      "step": 2430
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2936296463012695,
+      "eval_runtime": 94.7897,
+      "eval_samples_per_second": 4.6,
+      "eval_steps_per_second": 0.58,
+      "step": 2433
+    },
+    {
+      "epoch": 3.008631319358816,
+      "grad_norm": 0.5562372803688049,
+      "learning_rate": 0.0002,
+      "loss": 0.6073,
+      "step": 2440
+    },
+    {
+      "epoch": 3.020961775585697,
+      "grad_norm": 1.133402705192566,
+      "learning_rate": 0.0002,
+      "loss": 0.5181,
+      "step": 2450
+    },
+    {
+      "epoch": 3.033292231812577,
+      "grad_norm": 0.6480470299720764,
+      "learning_rate": 0.0002,
+      "loss": 0.5333,
+      "step": 2460
+    },
+    {
+      "epoch": 3.0456226880394572,
+      "grad_norm": 0.8989138007164001,
+      "learning_rate": 0.0002,
+      "loss": 0.4828,
+      "step": 2470
+    },
+    {
+      "epoch": 3.057953144266338,
+      "grad_norm": 0.8257461786270142,
+      "learning_rate": 0.0002,
+      "loss": 0.5097,
+      "step": 2480
+    },
+    {
+      "epoch": 3.070283600493218,
+      "grad_norm": 0.6813381910324097,
+      "learning_rate": 0.0002,
+      "loss": 0.6229,
+      "step": 2490
+    },
+    {
+      "epoch": 3.082614056720099,
+      "grad_norm": 0.6989586353302002,
+      "learning_rate": 0.0002,
+      "loss": 0.531,
+      "step": 2500
+    },
+    {
+      "epoch": 3.094944512946979,
+      "grad_norm": 0.7992092967033386,
+      "learning_rate": 0.0002,
+      "loss": 0.54,
+      "step": 2510
+    },
+    {
+      "epoch": 3.1072749691738593,
+      "grad_norm": 0.698077917098999,
+      "learning_rate": 0.0002,
+      "loss": 0.5054,
+      "step": 2520
+    },
+    {
+      "epoch": 3.11960542540074,
+      "grad_norm": 0.5699033141136169,
+      "learning_rate": 0.0002,
+      "loss": 0.5064,
+      "step": 2530
+    },
+    {
+      "epoch": 3.13193588162762,
+      "grad_norm": 0.6142355799674988,
+      "learning_rate": 0.0002,
+      "loss": 0.6088,
+      "step": 2540
+    },
+    {
+      "epoch": 3.144266337854501,
+      "grad_norm": 0.7089933753013611,
+      "learning_rate": 0.0002,
+      "loss": 0.585,
+      "step": 2550
+    },
+    {
+      "epoch": 3.156596794081381,
+      "grad_norm": 1.0107015371322632,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 2560
+    },
+    {
+      "epoch": 3.1689272503082613,
+      "grad_norm": 0.568138837814331,
+      "learning_rate": 0.0002,
+      "loss": 0.5429,
+      "step": 2570
+    },
+    {
+      "epoch": 3.181257706535142,
+      "grad_norm": 0.9960416555404663,
+      "learning_rate": 0.0002,
+      "loss": 0.5897,
+      "step": 2580
+    },
+    {
+      "epoch": 3.193588162762022,
+      "grad_norm": 0.6277595162391663,
+      "learning_rate": 0.0002,
+      "loss": 0.5211,
+      "step": 2590
+    },
+    {
+      "epoch": 3.2059186189889024,
+      "grad_norm": 0.681083619594574,
+      "learning_rate": 0.0002,
+      "loss": 0.5787,
+      "step": 2600
+    },
+    {
+      "epoch": 3.218249075215783,
+      "grad_norm": 0.5816057324409485,
+      "learning_rate": 0.0002,
+      "loss": 0.5166,
+      "step": 2610
+    },
+    {
+      "epoch": 3.2305795314426633,
+      "grad_norm": 0.7197734117507935,
+      "learning_rate": 0.0002,
+      "loss": 0.545,
+      "step": 2620
+    },
+    {
+      "epoch": 3.242909987669544,
+      "grad_norm": 0.6524068117141724,
+      "learning_rate": 0.0002,
+      "loss": 0.614,
+      "step": 2630
+    },
+    {
+      "epoch": 3.255240443896424,
+      "grad_norm": 1.273668646812439,
+      "learning_rate": 0.0002,
+      "loss": 0.5456,
+      "step": 2640
+    },
+    {
+      "epoch": 3.2675709001233044,
+      "grad_norm": 0.6950451731681824,
+      "learning_rate": 0.0002,
+      "loss": 0.5266,
+      "step": 2650
+    },
+    {
+      "epoch": 3.279901356350185,
+      "grad_norm": 0.8029071688652039,
+      "learning_rate": 0.0002,
+      "loss": 0.5194,
+      "step": 2660
+    },
+    {
+      "epoch": 3.2922318125770653,
+      "grad_norm": 0.7464073896408081,
+      "learning_rate": 0.0002,
+      "loss": 0.5729,
+      "step": 2670
+    },
+    {
+      "epoch": 3.304562268803946,
+      "grad_norm": 0.8342001438140869,
+      "learning_rate": 0.0002,
+      "loss": 0.5366,
+      "step": 2680
+    },
+    {
+      "epoch": 3.316892725030826,
+      "grad_norm": 0.5629868507385254,
+      "learning_rate": 0.0002,
+      "loss": 0.5413,
+      "step": 2690
+    },
+    {
+      "epoch": 3.3292231812577064,
+      "grad_norm": 0.753999650478363,
+      "learning_rate": 0.0002,
+      "loss": 0.633,
+      "step": 2700
+    },
+    {
+      "epoch": 3.341553637484587,
+      "grad_norm": 1.0271371603012085,
+      "learning_rate": 0.0002,
+      "loss": 0.5048,
+      "step": 2710
+    },
+    {
+      "epoch": 3.3538840937114673,
+      "grad_norm": 0.9608535170555115,
+      "learning_rate": 0.0002,
+      "loss": 0.5233,
+      "step": 2720
+    },
+    {
+      "epoch": 3.3662145499383476,
+      "grad_norm": 0.7796488404273987,
+      "learning_rate": 0.0002,
+      "loss": 0.5102,
+      "step": 2730
+    },
+    {
+      "epoch": 3.3785450061652282,
+      "grad_norm": 0.5666437149047852,
+      "learning_rate": 0.0002,
+      "loss": 0.5172,
+      "step": 2740
+    },
+    {
+      "epoch": 3.3908754623921085,
+      "grad_norm": 0.5462956428527832,
+      "learning_rate": 0.0002,
+      "loss": 0.491,
+      "step": 2750
+    },
+    {
+      "epoch": 3.4032059186189887,
+      "grad_norm": 1.289099097251892,
+      "learning_rate": 0.0002,
+      "loss": 0.5855,
+      "step": 2760
+    },
+    {
+      "epoch": 3.4155363748458694,
+      "grad_norm": 0.825566828250885,
+      "learning_rate": 0.0002,
+      "loss": 0.635,
+      "step": 2770
+    },
+    {
+      "epoch": 3.4278668310727496,
+      "grad_norm": 0.8366670608520508,
+      "learning_rate": 0.0002,
+      "loss": 0.4998,
+      "step": 2780
+    },
+    {
+      "epoch": 3.4401972872996303,
+      "grad_norm": 1.0931549072265625,
+      "learning_rate": 0.0002,
+      "loss": 0.5732,
+      "step": 2790
+    },
+    {
+      "epoch": 3.4525277435265105,
+      "grad_norm": 0.9228858351707458,
+      "learning_rate": 0.0002,
+      "loss": 0.6093,
+      "step": 2800
+    },
+    {
+      "epoch": 3.4648581997533907,
+      "grad_norm": 1.3182806968688965,
+      "learning_rate": 0.0002,
+      "loss": 0.6089,
+      "step": 2810
+    },
+    {
+      "epoch": 3.4771886559802714,
+      "grad_norm": 0.8366976380348206,
+      "learning_rate": 0.0002,
+      "loss": 0.5665,
+      "step": 2820
+    },
+    {
+      "epoch": 3.4895191122071516,
+      "grad_norm": 0.8067695498466492,
+      "learning_rate": 0.0002,
+      "loss": 0.5666,
+      "step": 2830
+    },
+    {
+      "epoch": 3.5018495684340323,
+      "grad_norm": 1.1163437366485596,
+      "learning_rate": 0.0002,
+      "loss": 0.579,
+      "step": 2840
+    },
+    {
+      "epoch": 3.5141800246609125,
+      "grad_norm": 1.7196556329727173,
+      "learning_rate": 0.0002,
+      "loss": 0.5785,
+      "step": 2850
+    },
+    {
+      "epoch": 3.5265104808877927,
+      "grad_norm": 1.1267012357711792,
+      "learning_rate": 0.0002,
+      "loss": 0.5346,
+      "step": 2860
+    },
+    {
+      "epoch": 3.5388409371146734,
+      "grad_norm": 0.7220137119293213,
+      "learning_rate": 0.0002,
+      "loss": 0.447,
+      "step": 2870
+    },
+    {
+      "epoch": 3.5511713933415536,
+      "grad_norm": 0.914114773273468,
+      "learning_rate": 0.0002,
+      "loss": 0.6099,
+      "step": 2880
+    },
+    {
+      "epoch": 3.563501849568434,
+      "grad_norm": 0.6193503141403198,
+      "learning_rate": 0.0002,
+      "loss": 0.6143,
+      "step": 2890
+    },
+    {
+      "epoch": 3.5758323057953145,
+      "grad_norm": 0.6060135960578918,
+      "learning_rate": 0.0002,
+      "loss": 0.5171,
+      "step": 2900
+    },
+    {
+      "epoch": 3.5881627620221948,
+      "grad_norm": 1.0177327394485474,
+      "learning_rate": 0.0002,
+      "loss": 0.5659,
+      "step": 2910
+    },
+    {
+      "epoch": 3.600493218249075,
+      "grad_norm": 0.5994468331336975,
+      "learning_rate": 0.0002,
+      "loss": 0.5711,
+      "step": 2920
+    },
+    {
+      "epoch": 3.6128236744759556,
+      "grad_norm": 0.7450457215309143,
+      "learning_rate": 0.0002,
+      "loss": 0.6373,
+      "step": 2930
+    },
+    {
+      "epoch": 3.625154130702836,
+      "grad_norm": 0.5825870037078857,
+      "learning_rate": 0.0002,
+      "loss": 0.4933,
+      "step": 2940
+    },
+    {
+      "epoch": 3.6374845869297165,
+      "grad_norm": 0.6289743781089783,
+      "learning_rate": 0.0002,
+      "loss": 0.6016,
+      "step": 2950
+    },
+    {
+      "epoch": 3.6498150431565968,
+      "grad_norm": 0.7801929116249084,
+      "learning_rate": 0.0002,
+      "loss": 0.5507,
+      "step": 2960
+    },
+    {
+      "epoch": 3.6621454993834774,
+      "grad_norm": 1.1206634044647217,
+      "learning_rate": 0.0002,
+      "loss": 0.5695,
+      "step": 2970
+    },
+    {
+      "epoch": 3.6744759556103577,
+      "grad_norm": 0.6738817691802979,
+      "learning_rate": 0.0002,
+      "loss": 0.4985,
+      "step": 2980
+    },
+    {
+      "epoch": 3.686806411837238,
+      "grad_norm": 1.1917344331741333,
+      "learning_rate": 0.0002,
+      "loss": 0.6209,
+      "step": 2990
+    },
+    {
+      "epoch": 3.6991368680641186,
+      "grad_norm": 1.3738657236099243,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 3000
+    },
+    {
+      "epoch": 3.711467324290999,
+      "grad_norm": 0.6642793416976929,
+      "learning_rate": 0.0002,
+      "loss": 0.5467,
+      "step": 3010
+    },
+    {
+      "epoch": 3.723797780517879,
+      "grad_norm": 0.9030995965003967,
+      "learning_rate": 0.0002,
+      "loss": 0.6243,
+      "step": 3020
+    },
+    {
+      "epoch": 3.7361282367447597,
+      "grad_norm": 1.0203914642333984,
+      "learning_rate": 0.0002,
+      "loss": 0.592,
+      "step": 3030
+    },
+    {
+      "epoch": 3.74845869297164,
+      "grad_norm": 0.648394763469696,
+      "learning_rate": 0.0002,
+      "loss": 0.5453,
+      "step": 3040
+    },
+    {
+      "epoch": 3.76078914919852,
+      "grad_norm": 0.6304570436477661,
+      "learning_rate": 0.0002,
+      "loss": 0.498,
+      "step": 3050
+    },
+    {
+      "epoch": 3.773119605425401,
+      "grad_norm": 0.8286601901054382,
+      "learning_rate": 0.0002,
+      "loss": 0.683,
+      "step": 3060
+    },
+    {
+      "epoch": 3.785450061652281,
+      "grad_norm": 0.906444251537323,
+      "learning_rate": 0.0002,
+      "loss": 0.5302,
+      "step": 3070
+    },
+    {
+      "epoch": 3.7977805178791613,
+      "grad_norm": 1.4212149381637573,
+      "learning_rate": 0.0002,
+      "loss": 0.5345,
+      "step": 3080
+    },
+    {
+      "epoch": 3.810110974106042,
+      "grad_norm": 0.7574319839477539,
+      "learning_rate": 0.0002,
+      "loss": 0.6403,
+      "step": 3090
+    },
+    {
+      "epoch": 3.822441430332922,
+      "grad_norm": 0.6534451246261597,
+      "learning_rate": 0.0002,
+      "loss": 0.5756,
+      "step": 3100
+    },
+    {
+      "epoch": 3.834771886559803,
+      "grad_norm": 0.7525447010993958,
+      "learning_rate": 0.0002,
+      "loss": 0.5306,
+      "step": 3110
+    },
+    {
+      "epoch": 3.847102342786683,
+      "grad_norm": 0.6513990759849548,
+      "learning_rate": 0.0002,
+      "loss": 0.5368,
+      "step": 3120
+    },
+    {
+      "epoch": 3.8594327990135637,
+      "grad_norm": 0.7782694697380066,
+      "learning_rate": 0.0002,
+      "loss": 0.5492,
+      "step": 3130
+    },
+    {
+      "epoch": 3.871763255240444,
+      "grad_norm": 0.7998530268669128,
+      "learning_rate": 0.0002,
+      "loss": 0.5727,
+      "step": 3140
+    },
+    {
+      "epoch": 3.884093711467324,
+      "grad_norm": 0.8045353293418884,
+      "learning_rate": 0.0002,
+      "loss": 0.5156,
+      "step": 3150
+    },
+    {
+      "epoch": 3.896424167694205,
+      "grad_norm": 0.8242645263671875,
+      "learning_rate": 0.0002,
+      "loss": 0.5341,
+      "step": 3160
+    },
+    {
+      "epoch": 3.908754623921085,
+      "grad_norm": 0.8302360773086548,
+      "learning_rate": 0.0002,
+      "loss": 0.5563,
+      "step": 3170
+    },
+    {
+      "epoch": 3.9210850801479653,
+      "grad_norm": 0.8653109073638916,
+      "learning_rate": 0.0002,
+      "loss": 0.5793,
+      "step": 3180
+    },
+    {
+      "epoch": 3.933415536374846,
+      "grad_norm": 0.6461338996887207,
+      "learning_rate": 0.0002,
+      "loss": 0.5219,
+      "step": 3190
+    },
+    {
+      "epoch": 3.945745992601726,
+      "grad_norm": 0.8267415165901184,
+      "learning_rate": 0.0002,
+      "loss": 0.6009,
+      "step": 3200
+    },
+    {
+      "epoch": 3.9580764488286064,
+      "grad_norm": 1.1963194608688354,
+      "learning_rate": 0.0002,
+      "loss": 0.5956,
+      "step": 3210
+    },
+    {
+      "epoch": 3.970406905055487,
+      "grad_norm": 0.7101966142654419,
+      "learning_rate": 0.0002,
+      "loss": 0.5692,
+      "step": 3220
+    },
+    {
+      "epoch": 3.9827373612823673,
+      "grad_norm": 0.5931660532951355,
+      "learning_rate": 0.0002,
+      "loss": 0.5471,
+      "step": 3230
+    },
+    {
+      "epoch": 3.995067817509248,
+      "grad_norm": 0.7465988993644714,
+      "learning_rate": 0.0002,
+      "loss": 0.5619,
+      "step": 3240
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4066498279571533,
+      "eval_runtime": 95.7145,
+      "eval_samples_per_second": 4.555,
+      "eval_steps_per_second": 0.575,
+      "step": 3244
+    },
+    {
+      "epoch": 4.007398273736128,
+      "grad_norm": 0.9478800296783447,
+      "learning_rate": 0.0002,
+      "loss": 0.4948,
+      "step": 3250
+    },
+    {
+      "epoch": 4.019728729963009,
+      "grad_norm": 1.207059621810913,
+      "learning_rate": 0.0002,
+      "loss": 0.4129,
+      "step": 3260
+    },
+    {
+      "epoch": 4.032059186189889,
+      "grad_norm": 0.8984074592590332,
+      "learning_rate": 0.0002,
+      "loss": 0.3577,
+      "step": 3270
+    },
+    {
+      "epoch": 4.044389642416769,
+      "grad_norm": 0.8104140758514404,
+      "learning_rate": 0.0002,
+      "loss": 0.3798,
+      "step": 3280
+    },
+    {
+      "epoch": 4.05672009864365,
+      "grad_norm": 1.0875468254089355,
+      "learning_rate": 0.0002,
+      "loss": 0.3657,
+      "step": 3290
+    },
+    {
+      "epoch": 4.06905055487053,
+      "grad_norm": 0.8520309329032898,
+      "learning_rate": 0.0002,
+      "loss": 0.3703,
+      "step": 3300
+    },
+    {
+      "epoch": 4.0813810110974105,
+      "grad_norm": 1.076735496520996,
+      "learning_rate": 0.0002,
+      "loss": 0.3933,
+      "step": 3310
+    },
+    {
+      "epoch": 4.093711467324291,
+      "grad_norm": 0.7789369821548462,
+      "learning_rate": 0.0002,
+      "loss": 0.4422,
+      "step": 3320
+    },
+    {
+      "epoch": 4.106041923551172,
+      "grad_norm": 0.916862964630127,
+      "learning_rate": 0.0002,
+      "loss": 0.4009,
+      "step": 3330
+    },
+    {
+      "epoch": 4.118372379778052,
+      "grad_norm": 1.1251654624938965,
+      "learning_rate": 0.0002,
+      "loss": 0.3934,
+      "step": 3340
+    },
+    {
+      "epoch": 4.130702836004932,
+      "grad_norm": 0.9373420476913452,
+      "learning_rate": 0.0002,
+      "loss": 0.3651,
+      "step": 3350
+    },
+    {
+      "epoch": 4.143033292231813,
+      "grad_norm": 1.03253972530365,
+      "learning_rate": 0.0002,
+      "loss": 0.384,
+      "step": 3360
+    },
+    {
+      "epoch": 4.155363748458693,
+      "grad_norm": 0.947023332118988,
+      "learning_rate": 0.0002,
+      "loss": 0.372,
+      "step": 3370
+    },
+    {
+      "epoch": 4.167694204685573,
+      "grad_norm": 0.8709157109260559,
+      "learning_rate": 0.0002,
+      "loss": 0.4018,
+      "step": 3380
+    },
+    {
+      "epoch": 4.180024660912454,
+      "grad_norm": 0.930983304977417,
+      "learning_rate": 0.0002,
+      "loss": 0.3754,
+      "step": 3390
+    },
+    {
+      "epoch": 4.192355117139334,
+      "grad_norm": 1.092809796333313,
+      "learning_rate": 0.0002,
+      "loss": 0.4248,
+      "step": 3400
+    },
+    {
+      "epoch": 4.2046855733662145,
+      "grad_norm": 0.8454303741455078,
+      "learning_rate": 0.0002,
+      "loss": 0.4453,
+      "step": 3410
+    },
+    {
+      "epoch": 4.217016029593095,
+      "grad_norm": 0.957210123538971,
+      "learning_rate": 0.0002,
+      "loss": 0.4198,
+      "step": 3420
+    },
+    {
+      "epoch": 4.229346485819975,
+      "grad_norm": 0.854333758354187,
+      "learning_rate": 0.0002,
+      "loss": 0.3743,
+      "step": 3430
+    },
+    {
+      "epoch": 4.241676942046856,
+      "grad_norm": 1.0457639694213867,
+      "learning_rate": 0.0002,
+      "loss": 0.4041,
+      "step": 3440
+    },
+    {
+      "epoch": 4.254007398273736,
+      "grad_norm": 0.8972977995872498,
+      "learning_rate": 0.0002,
+      "loss": 0.3817,
+      "step": 3450
+    },
+    {
+      "epoch": 4.266337854500616,
+      "grad_norm": 1.0438238382339478,
+      "learning_rate": 0.0002,
+      "loss": 0.4445,
+      "step": 3460
+    },
+    {
+      "epoch": 4.278668310727497,
+      "grad_norm": 0.7000405192375183,
+      "learning_rate": 0.0002,
+      "loss": 0.4078,
+      "step": 3470
+    },
+    {
+      "epoch": 4.290998766954377,
+      "grad_norm": 1.0451240539550781,
+      "learning_rate": 0.0002,
+      "loss": 0.3718,
+      "step": 3480
+    },
+    {
+      "epoch": 4.303329223181258,
+      "grad_norm": 1.3339767456054688,
+      "learning_rate": 0.0002,
+      "loss": 0.4506,
+      "step": 3490
+    },
+    {
+      "epoch": 4.315659679408138,
+      "grad_norm": 0.7503946423530579,
+      "learning_rate": 0.0002,
+      "loss": 0.3999,
+      "step": 3500
+    },
+    {
+      "epoch": 4.3279901356350186,
+      "grad_norm": 0.8443584442138672,
+      "learning_rate": 0.0002,
+      "loss": 0.4503,
+      "step": 3510
+    },
+    {
+      "epoch": 4.340320591861899,
+      "grad_norm": 1.1681201457977295,
+      "learning_rate": 0.0002,
+      "loss": 0.3793,
+      "step": 3520
+    },
+    {
+      "epoch": 4.352651048088779,
+      "grad_norm": 1.078883171081543,
+      "learning_rate": 0.0002,
+      "loss": 0.4462,
+      "step": 3530
+    },
+    {
+      "epoch": 4.36498150431566,
+      "grad_norm": 0.6894834041595459,
+      "learning_rate": 0.0002,
+      "loss": 0.4216,
+      "step": 3540
+    },
+    {
+      "epoch": 4.37731196054254,
+      "grad_norm": 0.7059480547904968,
+      "learning_rate": 0.0002,
+      "loss": 0.4315,
+      "step": 3550
+    },
+    {
+      "epoch": 4.38964241676942,
+      "grad_norm": 1.1807256937026978,
+      "learning_rate": 0.0002,
+      "loss": 0.3821,
+      "step": 3560
+    },
+    {
+      "epoch": 4.401972872996301,
+      "grad_norm": 0.8341359496116638,
+      "learning_rate": 0.0002,
+      "loss": 0.4192,
+      "step": 3570
+    },
+    {
+      "epoch": 4.4143033292231815,
+      "grad_norm": 1.0273033380508423,
+      "learning_rate": 0.0002,
+      "loss": 0.4123,
+      "step": 3580
+    },
+    {
+      "epoch": 4.426633785450061,
+      "grad_norm": 0.6916454434394836,
+      "learning_rate": 0.0002,
+      "loss": 0.5018,
+      "step": 3590
+    },
+    {
+      "epoch": 4.438964241676942,
+      "grad_norm": 0.8210113644599915,
+      "learning_rate": 0.0002,
+      "loss": 0.3909,
+      "step": 3600
+    },
+    {
+      "epoch": 4.451294697903823,
+      "grad_norm": 1.0309500694274902,
+      "learning_rate": 0.0002,
+      "loss": 0.3893,
+      "step": 3610
+    },
+    {
+      "epoch": 4.463625154130703,
+      "grad_norm": 0.8847399353981018,
+      "learning_rate": 0.0002,
+      "loss": 0.3902,
+      "step": 3620
+    },
+    {
+      "epoch": 4.475955610357583,
+      "grad_norm": 1.668636679649353,
+      "learning_rate": 0.0002,
+      "loss": 0.4198,
+      "step": 3630
+    },
+    {
+      "epoch": 4.488286066584464,
+      "grad_norm": 1.3087958097457886,
+      "learning_rate": 0.0002,
+      "loss": 0.4075,
+      "step": 3640
+    },
+    {
+      "epoch": 4.500616522811344,
+      "grad_norm": 0.837852418422699,
+      "learning_rate": 0.0002,
+      "loss": 0.4294,
+      "step": 3650
+    },
+    {
+      "epoch": 4.512946979038224,
+      "grad_norm": 9.7662353515625,
+      "learning_rate": 0.0002,
+      "loss": 0.4053,
+      "step": 3660
+    },
+    {
+      "epoch": 4.525277435265105,
+      "grad_norm": 1.125719428062439,
+      "learning_rate": 0.0002,
+      "loss": 0.4033,
+      "step": 3670
+    },
+    {
+      "epoch": 4.5376078914919855,
+      "grad_norm": 0.7755377292633057,
+      "learning_rate": 0.0002,
+      "loss": 0.4566,
+      "step": 3680
+    },
+    {
+      "epoch": 4.549938347718865,
+      "grad_norm": 0.7185089588165283,
+      "learning_rate": 0.0002,
+      "loss": 0.4415,
+      "step": 3690
+    },
+    {
+      "epoch": 4.562268803945746,
+      "grad_norm": 1.182063102722168,
+      "learning_rate": 0.0002,
+      "loss": 0.4616,
+      "step": 3700
+    },
+    {
+      "epoch": 4.574599260172627,
+      "grad_norm": 1.001197338104248,
+      "learning_rate": 0.0002,
+      "loss": 0.4572,
+      "step": 3710
+    },
+    {
+      "epoch": 4.586929716399506,
+      "grad_norm": 0.9705429077148438,
+      "learning_rate": 0.0002,
+      "loss": 0.4493,
+      "step": 3720
+    },
+    {
+      "epoch": 4.599260172626387,
+      "grad_norm": 0.7136746048927307,
+      "learning_rate": 0.0002,
+      "loss": 0.42,
+      "step": 3730
+    },
+    {
+      "epoch": 4.611590628853268,
+      "grad_norm": 1.0004864931106567,
+      "learning_rate": 0.0002,
+      "loss": 0.3757,
+      "step": 3740
+    },
+    {
+      "epoch": 4.623921085080148,
+      "grad_norm": 1.3193715810775757,
+      "learning_rate": 0.0002,
+      "loss": 0.4418,
+      "step": 3750
+    },
+    {
+      "epoch": 4.636251541307028,
+      "grad_norm": 0.6945042014122009,
+      "learning_rate": 0.0002,
+      "loss": 0.4572,
+      "step": 3760
+    },
+    {
+      "epoch": 4.648581997533909,
+      "grad_norm": 0.8903936743736267,
+      "learning_rate": 0.0002,
+      "loss": 0.4255,
+      "step": 3770
+    },
+    {
+      "epoch": 4.660912453760789,
+      "grad_norm": 0.7960889339447021,
+      "learning_rate": 0.0002,
+      "loss": 0.3582,
+      "step": 3780
+    },
+    {
+      "epoch": 4.673242909987669,
+      "grad_norm": 1.0439172983169556,
+      "learning_rate": 0.0002,
+      "loss": 0.3864,
+      "step": 3790
+    },
+    {
+      "epoch": 4.68557336621455,
+      "grad_norm": 1.4546219110488892,
+      "learning_rate": 0.0002,
+      "loss": 0.4378,
+      "step": 3800
+    },
+    {
+      "epoch": 4.697903822441431,
+      "grad_norm": 0.8194343447685242,
+      "learning_rate": 0.0002,
+      "loss": 0.4191,
+      "step": 3810
+    },
+    {
+      "epoch": 4.7102342786683105,
+      "grad_norm": 1.0727602243423462,
+      "learning_rate": 0.0002,
+      "loss": 0.4473,
+      "step": 3820
+    },
+    {
+      "epoch": 4.722564734895191,
+      "grad_norm": 0.7785195708274841,
+      "learning_rate": 0.0002,
+      "loss": 0.4021,
+      "step": 3830
+    },
+    {
+      "epoch": 4.734895191122072,
+      "grad_norm": 0.846783459186554,
+      "learning_rate": 0.0002,
+      "loss": 0.4252,
+      "step": 3840
+    },
+    {
+      "epoch": 4.747225647348952,
+      "grad_norm": 1.0481648445129395,
+      "learning_rate": 0.0002,
+      "loss": 0.4647,
+      "step": 3850
+    },
+    {
+      "epoch": 4.759556103575832,
+      "grad_norm": 0.7324008941650391,
+      "learning_rate": 0.0002,
+      "loss": 0.4944,
+      "step": 3860
+    },
+    {
+      "epoch": 4.771886559802713,
+      "grad_norm": 1.06382417678833,
+      "learning_rate": 0.0002,
+      "loss": 0.3831,
+      "step": 3870
+    },
+    {
+      "epoch": 4.784217016029594,
+      "grad_norm": 0.9851241111755371,
+      "learning_rate": 0.0002,
+      "loss": 0.3934,
+      "step": 3880
+    },
+    {
+      "epoch": 4.796547472256473,
+      "grad_norm": 0.8215277791023254,
+      "learning_rate": 0.0002,
+      "loss": 0.5172,
+      "step": 3890
+    },
+    {
+      "epoch": 4.808877928483354,
+      "grad_norm": 0.9901723861694336,
+      "learning_rate": 0.0002,
+      "loss": 0.4437,
+      "step": 3900
+    },
+    {
+      "epoch": 4.821208384710234,
+      "grad_norm": 0.9149112701416016,
+      "learning_rate": 0.0002,
+      "loss": 0.4673,
+      "step": 3910
+    },
+    {
+      "epoch": 4.8335388409371145,
+      "grad_norm": 0.9772973656654358,
+      "learning_rate": 0.0002,
+      "loss": 0.4295,
+      "step": 3920
+    },
+    {
+      "epoch": 4.845869297163995,
+      "grad_norm": 0.8889636397361755,
+      "learning_rate": 0.0002,
+      "loss": 0.4346,
+      "step": 3930
+    },
+    {
+      "epoch": 4.858199753390876,
+      "grad_norm": 1.3032807111740112,
+      "learning_rate": 0.0002,
+      "loss": 0.421,
+      "step": 3940
+    },
+    {
+      "epoch": 4.870530209617756,
+      "grad_norm": 0.8575899600982666,
+      "learning_rate": 0.0002,
+      "loss": 0.434,
+      "step": 3950
+    },
+    {
+      "epoch": 4.882860665844636,
+      "grad_norm": 1.04326331615448,
+      "learning_rate": 0.0002,
+      "loss": 0.4295,
+      "step": 3960
+    },
+    {
+      "epoch": 4.895191122071517,
+      "grad_norm": 1.041210651397705,
+      "learning_rate": 0.0002,
+      "loss": 0.3633,
+      "step": 3970
+    },
+    {
+      "epoch": 4.907521578298397,
+      "grad_norm": 0.9113056063652039,
+      "learning_rate": 0.0002,
+      "loss": 0.4104,
+      "step": 3980
+    },
+    {
+      "epoch": 4.919852034525277,
+      "grad_norm": 1.019347906112671,
+      "learning_rate": 0.0002,
+      "loss": 0.4496,
+      "step": 3990
+    },
+    {
+      "epoch": 4.932182490752158,
+      "grad_norm": 0.7709218859672546,
+      "learning_rate": 0.0002,
+      "loss": 0.457,
+      "step": 4000
+    },
+    {
+      "epoch": 4.944512946979038,
+      "grad_norm": 0.8891775608062744,
+      "learning_rate": 0.0002,
+      "loss": 0.4697,
+      "step": 4010
+    },
+    {
+      "epoch": 4.9568434032059185,
+      "grad_norm": 1.0396920442581177,
+      "learning_rate": 0.0002,
+      "loss": 0.4436,
+      "step": 4020
+    },
+    {
+      "epoch": 4.969173859432799,
+      "grad_norm": 0.9239833354949951,
+      "learning_rate": 0.0002,
+      "loss": 0.4251,
+      "step": 4030
+    },
+    {
+      "epoch": 4.981504315659679,
+      "grad_norm": 1.801400065422058,
+      "learning_rate": 0.0002,
+      "loss": 0.5049,
+      "step": 4040
+    },
+    {
+      "epoch": 4.99383477188656,
+      "grad_norm": 0.6194164752960205,
+      "learning_rate": 0.0002,
+      "loss": 0.4481,
+      "step": 4050
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.544758915901184,
+      "eval_runtime": 96.2573,
+      "eval_samples_per_second": 4.53,
+      "eval_steps_per_second": 0.571,
+      "step": 4055
+    },
+    {
+      "epoch": 5.00616522811344,
+      "grad_norm": 0.9918256998062134,
+      "learning_rate": 0.0002,
+      "loss": 0.3774,
+      "step": 4060
+    },
+    {
+      "epoch": 5.018495684340321,
+      "grad_norm": 1.4851351976394653,
+      "learning_rate": 0.0002,
+      "loss": 0.2887,
+      "step": 4070
+    },
+    {
+      "epoch": 5.030826140567201,
+      "grad_norm": 0.9237686395645142,
+      "learning_rate": 0.0002,
+      "loss": 0.2454,
+      "step": 4080
+    },
+    {
+      "epoch": 5.0431565967940815,
+      "grad_norm": 1.2180852890014648,
+      "learning_rate": 0.0002,
+      "loss": 0.3072,
+      "step": 4090
+    },
+    {
+      "epoch": 5.055487053020962,
+      "grad_norm": 1.1247979402542114,
+      "learning_rate": 0.0002,
+      "loss": 0.282,
+      "step": 4100
+    },
+    {
+      "epoch": 5.067817509247842,
+      "grad_norm": 1.2969884872436523,
+      "learning_rate": 0.0002,
+      "loss": 0.3108,
+      "step": 4110
+    },
+    {
+      "epoch": 5.080147965474723,
+      "grad_norm": 1.0183063745498657,
+      "learning_rate": 0.0002,
+      "loss": 0.2858,
+      "step": 4120
+    },
+    {
+      "epoch": 5.092478421701603,
+      "grad_norm": 1.121330738067627,
+      "learning_rate": 0.0002,
+      "loss": 0.295,
+      "step": 4130
+    },
+    {
+      "epoch": 5.104808877928483,
+      "grad_norm": 1.0748186111450195,
+      "learning_rate": 0.0002,
+      "loss": 0.2697,
+      "step": 4140
+    },
+    {
+      "epoch": 5.117139334155364,
+      "grad_norm": 1.103474736213684,
+      "learning_rate": 0.0002,
+      "loss": 0.3414,
+      "step": 4150
+    },
+    {
+      "epoch": 5.129469790382244,
+      "grad_norm": 1.2251166105270386,
+      "learning_rate": 0.0002,
+      "loss": 0.305,
+      "step": 4160
+    },
+    {
+      "epoch": 5.141800246609124,
+      "grad_norm": 0.920898973941803,
+      "learning_rate": 0.0002,
+      "loss": 0.3131,
+      "step": 4170
+    },
+    {
+      "epoch": 5.154130702836005,
+      "grad_norm": 1.327542781829834,
+      "learning_rate": 0.0002,
+      "loss": 0.281,
+      "step": 4180
+    },
+    {
+      "epoch": 5.1664611590628855,
+      "grad_norm": 1.0677192211151123,
+      "learning_rate": 0.0002,
+      "loss": 0.3214,
+      "step": 4190
+    },
+    {
+      "epoch": 5.178791615289766,
+      "grad_norm": 0.897241473197937,
+      "learning_rate": 0.0002,
+      "loss": 0.2863,
+      "step": 4200
+    },
+    {
+      "epoch": 5.191122071516646,
+      "grad_norm": 0.977457582950592,
+      "learning_rate": 0.0002,
+      "loss": 0.2967,
+      "step": 4210
+    },
+    {
+      "epoch": 5.203452527743527,
+      "grad_norm": 1.4115267992019653,
+      "learning_rate": 0.0002,
+      "loss": 0.3032,
+      "step": 4220
+    },
+    {
+      "epoch": 5.215782983970407,
+      "grad_norm": 1.097743034362793,
+      "learning_rate": 0.0002,
+      "loss": 0.3279,
+      "step": 4230
+    },
+    {
+      "epoch": 5.228113440197287,
+      "grad_norm": 1.1095269918441772,
+      "learning_rate": 0.0002,
+      "loss": 0.293,
+      "step": 4240
+    },
+    {
+      "epoch": 5.240443896424168,
+      "grad_norm": 1.3785479068756104,
+      "learning_rate": 0.0002,
+      "loss": 0.3544,
+      "step": 4250
+    },
+    {
+      "epoch": 5.252774352651048,
+      "grad_norm": 1.0298776626586914,
+      "learning_rate": 0.0002,
+      "loss": 0.3118,
+      "step": 4260
+    },
+    {
+      "epoch": 5.265104808877928,
+      "grad_norm": 1.1592111587524414,
+      "learning_rate": 0.0002,
+      "loss": 0.296,
+      "step": 4270
+    },
+    {
+      "epoch": 5.277435265104809,
+      "grad_norm": 1.2355743646621704,
+      "learning_rate": 0.0002,
+      "loss": 0.2878,
+      "step": 4280
+    },
+    {
+      "epoch": 5.2897657213316895,
+      "grad_norm": 0.8543112874031067,
+      "learning_rate": 0.0002,
+      "loss": 0.3085,
+      "step": 4290
+    },
+    {
+      "epoch": 5.302096177558569,
+      "grad_norm": 1.2953215837478638,
+      "learning_rate": 0.0002,
+      "loss": 0.3108,
+      "step": 4300
+    },
+    {
+      "epoch": 5.31442663378545,
+      "grad_norm": 1.1001787185668945,
+      "learning_rate": 0.0002,
+      "loss": 0.2912,
+      "step": 4310
+    },
+    {
+      "epoch": 5.326757090012331,
+      "grad_norm": 0.7476816773414612,
+      "learning_rate": 0.0002,
+      "loss": 0.3003,
+      "step": 4320
+    },
+    {
+      "epoch": 5.3390875462392104,
+      "grad_norm": 0.8195574283599854,
+      "learning_rate": 0.0002,
+      "loss": 0.3247,
+      "step": 4330
+    },
+    {
+      "epoch": 5.351418002466091,
+      "grad_norm": 0.9490262866020203,
+      "learning_rate": 0.0002,
+      "loss": 0.3035,
+      "step": 4340
+    },
+    {
+      "epoch": 5.363748458692972,
+      "grad_norm": 1.2201412916183472,
+      "learning_rate": 0.0002,
+      "loss": 0.2846,
+      "step": 4350
+    },
+    {
+      "epoch": 5.376078914919852,
+      "grad_norm": 1.0311479568481445,
+      "learning_rate": 0.0002,
+      "loss": 0.2644,
+      "step": 4360
+    },
+    {
+      "epoch": 5.388409371146732,
+      "grad_norm": 1.2097488641738892,
+      "learning_rate": 0.0002,
+      "loss": 0.3104,
+      "step": 4370
+    },
+    {
+      "epoch": 5.400739827373613,
+      "grad_norm": 1.140942096710205,
+      "learning_rate": 0.0002,
+      "loss": 0.2977,
+      "step": 4380
+    },
+    {
+      "epoch": 5.413070283600494,
+      "grad_norm": 0.8091890811920166,
+      "learning_rate": 0.0002,
+      "loss": 0.2975,
+      "step": 4390
+    },
+    {
+      "epoch": 5.425400739827373,
+      "grad_norm": 1.4467964172363281,
+      "learning_rate": 0.0002,
+      "loss": 0.3727,
+      "step": 4400
+    },
+    {
+      "epoch": 5.437731196054254,
+      "grad_norm": 1.0836058855056763,
+      "learning_rate": 0.0002,
+      "loss": 0.2979,
+      "step": 4410
+    },
+    {
+      "epoch": 5.450061652281135,
+      "grad_norm": 1.0515433549880981,
+      "learning_rate": 0.0002,
+      "loss": 0.2601,
+      "step": 4420
+    },
+    {
+      "epoch": 5.4623921085080145,
+      "grad_norm": 0.9603073000907898,
+      "learning_rate": 0.0002,
+      "loss": 0.315,
+      "step": 4430
+    },
+    {
+      "epoch": 5.474722564734895,
+      "grad_norm": 1.234609842300415,
+      "learning_rate": 0.0002,
+      "loss": 0.3166,
+      "step": 4440
+    },
+    {
+      "epoch": 5.487053020961776,
+      "grad_norm": 0.8881428837776184,
+      "learning_rate": 0.0002,
+      "loss": 0.3142,
+      "step": 4450
+    },
+    {
+      "epoch": 5.499383477188656,
+      "grad_norm": 1.1817275285720825,
+      "learning_rate": 0.0002,
+      "loss": 0.3725,
+      "step": 4460
+    },
+    {
+      "epoch": 5.511713933415536,
+      "grad_norm": 1.213993787765503,
+      "learning_rate": 0.0002,
+      "loss": 0.2944,
+      "step": 4470
+    },
+    {
+      "epoch": 5.524044389642417,
+      "grad_norm": 1.0501725673675537,
+      "learning_rate": 0.0002,
+      "loss": 0.3136,
+      "step": 4480
+    },
+    {
+      "epoch": 5.536374845869297,
+      "grad_norm": 1.5061579942703247,
+      "learning_rate": 0.0002,
+      "loss": 0.306,
+      "step": 4490
+    },
+    {
+      "epoch": 5.548705302096177,
+      "grad_norm": 1.1171475648880005,
+      "learning_rate": 0.0002,
+      "loss": 0.3226,
+      "step": 4500
+    },
+    {
+      "epoch": 5.561035758323058,
+      "grad_norm": 1.1147594451904297,
+      "learning_rate": 0.0002,
+      "loss": 0.3624,
+      "step": 4510
+    },
+    {
+      "epoch": 5.573366214549939,
+      "grad_norm": 1.0600544214248657,
+      "learning_rate": 0.0002,
+      "loss": 0.3435,
+      "step": 4520
+    },
+    {
+      "epoch": 5.5856966707768185,
+      "grad_norm": 1.247870922088623,
+      "learning_rate": 0.0002,
+      "loss": 0.3268,
+      "step": 4530
+    },
+    {
+      "epoch": 5.598027127003699,
+      "grad_norm": 0.9425561428070068,
+      "learning_rate": 0.0002,
+      "loss": 0.3168,
+      "step": 4540
+    },
+    {
+      "epoch": 5.61035758323058,
+      "grad_norm": 1.1111550331115723,
+      "learning_rate": 0.0002,
+      "loss": 0.3119,
+      "step": 4550
+    },
+    {
+      "epoch": 5.62268803945746,
+      "grad_norm": 1.743268609046936,
+      "learning_rate": 0.0002,
+      "loss": 0.3389,
+      "step": 4560
+    },
+    {
+      "epoch": 5.63501849568434,
+      "grad_norm": 1.3522645235061646,
+      "learning_rate": 0.0002,
+      "loss": 0.31,
+      "step": 4570
+    },
+    {
+      "epoch": 5.647348951911221,
+      "grad_norm": 0.7354221343994141,
+      "learning_rate": 0.0002,
+      "loss": 0.3121,
+      "step": 4580
+    },
+    {
+      "epoch": 5.659679408138101,
+      "grad_norm": 1.050743818283081,
+      "learning_rate": 0.0002,
+      "loss": 0.3693,
+      "step": 4590
+    },
+    {
+      "epoch": 5.6720098643649814,
+      "grad_norm": 1.1302396059036255,
+      "learning_rate": 0.0002,
+      "loss": 0.3449,
+      "step": 4600
+    },
+    {
+      "epoch": 5.684340320591862,
+      "grad_norm": 0.8774183392524719,
+      "learning_rate": 0.0002,
+      "loss": 0.3211,
+      "step": 4610
+    },
+    {
+      "epoch": 5.696670776818742,
+      "grad_norm": 1.090781569480896,
+      "learning_rate": 0.0002,
+      "loss": 0.3501,
+      "step": 4620
+    },
+    {
+      "epoch": 5.709001233045623,
+      "grad_norm": 0.9177733063697815,
+      "learning_rate": 0.0002,
+      "loss": 0.3211,
+      "step": 4630
+    },
+    {
+      "epoch": 5.721331689272503,
+      "grad_norm": 0.9985341429710388,
+      "learning_rate": 0.0002,
+      "loss": 0.3439,
+      "step": 4640
+    },
+    {
+      "epoch": 5.733662145499384,
+      "grad_norm": 1.0230613946914673,
+      "learning_rate": 0.0002,
+      "loss": 0.3323,
+      "step": 4650
+    },
+    {
+      "epoch": 5.745992601726264,
+      "grad_norm": 0.944656252861023,
+      "learning_rate": 0.0002,
+      "loss": 0.3525,
+      "step": 4660
+    },
+    {
+      "epoch": 5.758323057953144,
+      "grad_norm": 0.8162471652030945,
+      "learning_rate": 0.0002,
+      "loss": 0.3191,
+      "step": 4670
+    },
+    {
+      "epoch": 5.770653514180025,
+      "grad_norm": 1.0500398874282837,
+      "learning_rate": 0.0002,
+      "loss": 0.4011,
+      "step": 4680
+    },
+    {
+      "epoch": 5.782983970406905,
+      "grad_norm": 0.9487981796264648,
+      "learning_rate": 0.0002,
+      "loss": 0.3452,
+      "step": 4690
+    },
+    {
+      "epoch": 5.7953144266337855,
+      "grad_norm": 1.1856540441513062,
+      "learning_rate": 0.0002,
+      "loss": 0.2942,
+      "step": 4700
+    },
+    {
+      "epoch": 5.807644882860666,
+      "grad_norm": 1.2583396434783936,
+      "learning_rate": 0.0002,
+      "loss": 0.3107,
+      "step": 4710
+    },
+    {
+      "epoch": 5.819975339087546,
+      "grad_norm": 1.2532602548599243,
+      "learning_rate": 0.0002,
+      "loss": 0.3223,
+      "step": 4720
+    },
+    {
+      "epoch": 5.832305795314427,
+      "grad_norm": 1.115236520767212,
+      "learning_rate": 0.0002,
+      "loss": 0.3253,
+      "step": 4730
+    },
+    {
+      "epoch": 5.844636251541307,
+      "grad_norm": 1.2245537042617798,
+      "learning_rate": 0.0002,
+      "loss": 0.3539,
+      "step": 4740
+    },
+    {
+      "epoch": 5.856966707768187,
+      "grad_norm": 1.1964094638824463,
+      "learning_rate": 0.0002,
+      "loss": 0.3171,
+      "step": 4750
+    },
+    {
+      "epoch": 5.869297163995068,
+      "grad_norm": 1.0833805799484253,
+      "learning_rate": 0.0002,
+      "loss": 0.3623,
+      "step": 4760
+    },
+    {
+      "epoch": 5.881627620221948,
+      "grad_norm": 1.0694046020507812,
+      "learning_rate": 0.0002,
+      "loss": 0.3511,
+      "step": 4770
+    },
+    {
+      "epoch": 5.893958076448829,
+      "grad_norm": 0.9947936534881592,
+      "learning_rate": 0.0002,
+      "loss": 0.3266,
+      "step": 4780
+    },
+    {
+      "epoch": 5.906288532675709,
+      "grad_norm": 1.175716519355774,
+      "learning_rate": 0.0002,
+      "loss": 0.316,
+      "step": 4790
+    },
+    {
+      "epoch": 5.9186189889025895,
+      "grad_norm": 0.7717352509498596,
+      "learning_rate": 0.0002,
+      "loss": 0.3609,
+      "step": 4800
+    },
+    {
+      "epoch": 5.930949445129469,
+      "grad_norm": 1.2906442880630493,
+      "learning_rate": 0.0002,
+      "loss": 0.3058,
+      "step": 4810
+    },
+    {
+      "epoch": 5.94327990135635,
+      "grad_norm": 1.2416284084320068,
+      "learning_rate": 0.0002,
+      "loss": 0.3187,
+      "step": 4820
+    },
+    {
+      "epoch": 5.955610357583231,
+      "grad_norm": 1.3066956996917725,
+      "learning_rate": 0.0002,
+      "loss": 0.337,
+      "step": 4830
+    },
+    {
+      "epoch": 5.967940813810111,
+      "grad_norm": 1.0872026681900024,
+      "learning_rate": 0.0002,
+      "loss": 0.3167,
+      "step": 4840
+    },
+    {
+      "epoch": 5.980271270036991,
+      "grad_norm": 1.1941101551055908,
+      "learning_rate": 0.0002,
+      "loss": 0.3262,
+      "step": 4850
+    },
+    {
+      "epoch": 5.992601726263872,
+      "grad_norm": 1.1126095056533813,
+      "learning_rate": 0.0002,
+      "loss": 0.3234,
+      "step": 4860
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.748323917388916,
+      "eval_runtime": 97.7488,
+      "eval_samples_per_second": 4.46,
+      "eval_steps_per_second": 0.563,
+      "step": 4866
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6488,
+  "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": 2.4993598622662656e+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-0.6-num-5885-sd-10000/checkpoint-4866/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-0.6-num-5885-sd-10000/checkpoint-4866/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..459ba5959a39ea126110113c9faed75cda19ffff
--- /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-0.6-num-5885-sd-10000/checkpoint-4866/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05287f447dfde244c1a85dc0f576593b4a9dd61961eb0797da4844688fc48447
+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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e04e4441e0c1b29f69c16b26c142944e440b8076
--- /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-0.6-num-5885-sd-10000/checkpoint-5677/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": [
+    "q_proj",
+    "v_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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..032cd672ebb1fed63311496c2060def719e1aa2f
--- /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-0.6-num-5885-sd-10000/checkpoint-5677/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c1cef35ec572a9817b838d442ed757139ea6c6872cb537a7c44ccd3fd1115d6
+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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..264f0fbd5eb0aa48762c27d57279143860172c86
--- /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-0.6-num-5885-sd-10000/checkpoint-5677/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35ee121268f7b4ba2af88c2f87f9b558e7bd230c7839d55dd4e1ca774a4bbb9a
+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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..36bec44e886dca7704f7ac183f987f04b9fe549a
--- /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-0.6-num-5885-sd-10000/checkpoint-5677/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b665d283293cba13847b5d8e25bd9ac4b7f3658cd54aec8d20689ec4e87cf99b
+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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..92c35a87a729e89be8430721defd697b07ab7118
--- /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-0.6-num-5885-sd-10000/checkpoint-5677/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c63c3119d1e66c8e4572d55ec3986f2909422152daac522b536300baca280f
+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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22
--- /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-0.6-num-5885-sd-10000/checkpoint-5677/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873
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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..4f9fdafa4f1fa0a6fe7c7a7d08374485a95e1c34
--- /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-0.6-num-5885-sd-10000/checkpoint-5677/trainer_state.json
@@ -0,0 +1,4058 @@
+{
+  "best_metric": 1.238026738166809,
+  "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-0.6-num-5885-sd-10000/checkpoint-1622",
+  "epoch": 7.0,
+  "eval_steps": 10,
+  "global_step": 5677,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012330456226880395,
+      "grad_norm": 0.8258164525032043,
+      "learning_rate": 0.0002,
+      "loss": 2.3601,
+      "step": 10
+    },
+    {
+      "epoch": 0.02466091245376079,
+      "grad_norm": 0.4577729105949402,
+      "learning_rate": 0.0002,
+      "loss": 1.7317,
+      "step": 20
+    },
+    {
+      "epoch": 0.036991368680641186,
+      "grad_norm": 0.639807939529419,
+      "learning_rate": 0.0002,
+      "loss": 1.4729,
+      "step": 30
+    },
+    {
+      "epoch": 0.04932182490752158,
+      "grad_norm": 0.5311757922172546,
+      "learning_rate": 0.0002,
+      "loss": 1.2088,
+      "step": 40
+    },
+    {
+      "epoch": 0.06165228113440197,
+      "grad_norm": 0.386595219373703,
+      "learning_rate": 0.0002,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.07398273736128237,
+      "grad_norm": 0.4401357173919678,
+      "learning_rate": 0.0002,
+      "loss": 1.1657,
+      "step": 60
+    },
+    {
+      "epoch": 0.08631319358816276,
+      "grad_norm": 0.3234352171421051,
+      "learning_rate": 0.0002,
+      "loss": 1.1022,
+      "step": 70
+    },
+    {
+      "epoch": 0.09864364981504316,
+      "grad_norm": 0.29643672704696655,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 80
+    },
+    {
+      "epoch": 0.11097410604192355,
+      "grad_norm": 0.2941012382507324,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 90
+    },
+    {
+      "epoch": 0.12330456226880394,
+      "grad_norm": 0.5498173832893372,
+      "learning_rate": 0.0002,
+      "loss": 1.2067,
+      "step": 100
+    },
+    {
+      "epoch": 0.13563501849568435,
+      "grad_norm": 0.2545783519744873,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 110
+    },
+    {
+      "epoch": 0.14796547472256474,
+      "grad_norm": 0.2984241247177124,
+      "learning_rate": 0.0002,
+      "loss": 1.0297,
+      "step": 120
+    },
+    {
+      "epoch": 0.16029593094944514,
+      "grad_norm": 0.2710968852043152,
+      "learning_rate": 0.0002,
+      "loss": 1.1591,
+      "step": 130
+    },
+    {
+      "epoch": 0.17262638717632553,
+      "grad_norm": 0.2817152142524719,
+      "learning_rate": 0.0002,
+      "loss": 1.0427,
+      "step": 140
+    },
+    {
+      "epoch": 0.18495684340320592,
+      "grad_norm": 0.41083765029907227,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 150
+    },
+    {
+      "epoch": 0.19728729963008632,
+      "grad_norm": 0.36536213755607605,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 160
+    },
+    {
+      "epoch": 0.2096177558569667,
+      "grad_norm": 0.2738671600818634,
+      "learning_rate": 0.0002,
+      "loss": 1.0132,
+      "step": 170
+    },
+    {
+      "epoch": 0.2219482120838471,
+      "grad_norm": 0.27403146028518677,
+      "learning_rate": 0.0002,
+      "loss": 0.9555,
+      "step": 180
+    },
+    {
+      "epoch": 0.2342786683107275,
+      "grad_norm": 0.4446810483932495,
+      "learning_rate": 0.0002,
+      "loss": 1.0769,
+      "step": 190
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "grad_norm": 0.5295385718345642,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 200
+    },
+    {
+      "epoch": 0.2589395807644883,
+      "grad_norm": 0.311404824256897,
+      "learning_rate": 0.0002,
+      "loss": 1.0827,
+      "step": 210
+    },
+    {
+      "epoch": 0.2712700369913687,
+      "grad_norm": 0.2448509782552719,
+      "learning_rate": 0.0002,
+      "loss": 1.1455,
+      "step": 220
+    },
+    {
+      "epoch": 0.2836004932182491,
+      "grad_norm": 0.6507014036178589,
+      "learning_rate": 0.0002,
+      "loss": 1.0929,
+      "step": 230
+    },
+    {
+      "epoch": 0.2959309494451295,
+      "grad_norm": 0.2339320331811905,
+      "learning_rate": 0.0002,
+      "loss": 0.9875,
+      "step": 240
+    },
+    {
+      "epoch": 0.3082614056720099,
+      "grad_norm": 0.8210226893424988,
+      "learning_rate": 0.0002,
+      "loss": 0.9211,
+      "step": 250
+    },
+    {
+      "epoch": 0.3205918618988903,
+      "grad_norm": 0.27473965287208557,
+      "learning_rate": 0.0002,
+      "loss": 1.161,
+      "step": 260
+    },
+    {
+      "epoch": 0.33292231812577067,
+      "grad_norm": 0.3051395118236542,
+      "learning_rate": 0.0002,
+      "loss": 1.0218,
+      "step": 270
+    },
+    {
+      "epoch": 0.34525277435265106,
+      "grad_norm": 0.3037777245044708,
+      "learning_rate": 0.0002,
+      "loss": 1.0286,
+      "step": 280
+    },
+    {
+      "epoch": 0.35758323057953145,
+      "grad_norm": 0.2748974859714508,
+      "learning_rate": 0.0002,
+      "loss": 1.144,
+      "step": 290
+    },
+    {
+      "epoch": 0.36991368680641185,
+      "grad_norm": 0.23656068742275238,
+      "learning_rate": 0.0002,
+      "loss": 1.0858,
+      "step": 300
+    },
+    {
+      "epoch": 0.38224414303329224,
+      "grad_norm": 0.2523384094238281,
+      "learning_rate": 0.0002,
+      "loss": 1.0564,
+      "step": 310
+    },
+    {
+      "epoch": 0.39457459926017263,
+      "grad_norm": 0.27848055958747864,
+      "learning_rate": 0.0002,
+      "loss": 1.3091,
+      "step": 320
+    },
+    {
+      "epoch": 0.406905055487053,
+      "grad_norm": 0.3204525411128998,
+      "learning_rate": 0.0002,
+      "loss": 1.0252,
+      "step": 330
+    },
+    {
+      "epoch": 0.4192355117139334,
+      "grad_norm": 0.3459707498550415,
+      "learning_rate": 0.0002,
+      "loss": 0.9855,
+      "step": 340
+    },
+    {
+      "epoch": 0.4315659679408138,
+      "grad_norm": 0.2458430379629135,
+      "learning_rate": 0.0002,
+      "loss": 1.1111,
+      "step": 350
+    },
+    {
+      "epoch": 0.4438964241676942,
+      "grad_norm": 0.5022910237312317,
+      "learning_rate": 0.0002,
+      "loss": 1.1493,
+      "step": 360
+    },
+    {
+      "epoch": 0.4562268803945746,
+      "grad_norm": 0.27076372504234314,
+      "learning_rate": 0.0002,
+      "loss": 1.1272,
+      "step": 370
+    },
+    {
+      "epoch": 0.468557336621455,
+      "grad_norm": 0.6489047408103943,
+      "learning_rate": 0.0002,
+      "loss": 1.1927,
+      "step": 380
+    },
+    {
+      "epoch": 0.4808877928483354,
+      "grad_norm": 0.3324144184589386,
+      "learning_rate": 0.0002,
+      "loss": 0.9501,
+      "step": 390
+    },
+    {
+      "epoch": 0.4932182490752158,
+      "grad_norm": 0.32813116908073425,
+      "learning_rate": 0.0002,
+      "loss": 1.2012,
+      "step": 400
+    },
+    {
+      "epoch": 0.5055487053020962,
+      "grad_norm": 0.25295355916023254,
+      "learning_rate": 0.0002,
+      "loss": 1.1135,
+      "step": 410
+    },
+    {
+      "epoch": 0.5178791615289766,
+      "grad_norm": 0.2912578880786896,
+      "learning_rate": 0.0002,
+      "loss": 0.9477,
+      "step": 420
+    },
+    {
+      "epoch": 0.530209617755857,
+      "grad_norm": 0.34780189394950867,
+      "learning_rate": 0.0002,
+      "loss": 1.0121,
+      "step": 430
+    },
+    {
+      "epoch": 0.5425400739827374,
+      "grad_norm": 0.24604526162147522,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 440
+    },
+    {
+      "epoch": 0.5548705302096177,
+      "grad_norm": 0.32759982347488403,
+      "learning_rate": 0.0002,
+      "loss": 1.253,
+      "step": 450
+    },
+    {
+      "epoch": 0.5672009864364982,
+      "grad_norm": 0.40810221433639526,
+      "learning_rate": 0.0002,
+      "loss": 1.1925,
+      "step": 460
+    },
+    {
+      "epoch": 0.5795314426633785,
+      "grad_norm": 0.3590679466724396,
+      "learning_rate": 0.0002,
+      "loss": 1.174,
+      "step": 470
+    },
+    {
+      "epoch": 0.591861898890259,
+      "grad_norm": 0.5656213760375977,
+      "learning_rate": 0.0002,
+      "loss": 1.2223,
+      "step": 480
+    },
+    {
+      "epoch": 0.6041923551171393,
+      "grad_norm": 0.30830657482147217,
+      "learning_rate": 0.0002,
+      "loss": 1.1936,
+      "step": 490
+    },
+    {
+      "epoch": 0.6165228113440198,
+      "grad_norm": 0.317905455827713,
+      "learning_rate": 0.0002,
+      "loss": 1.1873,
+      "step": 500
+    },
+    {
+      "epoch": 0.6288532675709001,
+      "grad_norm": 0.3254566490650177,
+      "learning_rate": 0.0002,
+      "loss": 0.9805,
+      "step": 510
+    },
+    {
+      "epoch": 0.6411837237977805,
+      "grad_norm": 0.29187721014022827,
+      "learning_rate": 0.0002,
+      "loss": 1.0384,
+      "step": 520
+    },
+    {
+      "epoch": 0.6535141800246609,
+      "grad_norm": 0.3439238965511322,
+      "learning_rate": 0.0002,
+      "loss": 1.2526,
+      "step": 530
+    },
+    {
+      "epoch": 0.6658446362515413,
+      "grad_norm": 0.20970556139945984,
+      "learning_rate": 0.0002,
+      "loss": 1.0698,
+      "step": 540
+    },
+    {
+      "epoch": 0.6781750924784217,
+      "grad_norm": 0.4022853374481201,
+      "learning_rate": 0.0002,
+      "loss": 1.1047,
+      "step": 550
+    },
+    {
+      "epoch": 0.6905055487053021,
+      "grad_norm": 0.2235759049654007,
+      "learning_rate": 0.0002,
+      "loss": 1.0684,
+      "step": 560
+    },
+    {
+      "epoch": 0.7028360049321825,
+      "grad_norm": 0.33849895000457764,
+      "learning_rate": 0.0002,
+      "loss": 1.2339,
+      "step": 570
+    },
+    {
+      "epoch": 0.7151664611590629,
+      "grad_norm": 0.34745967388153076,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 580
+    },
+    {
+      "epoch": 0.7274969173859432,
+      "grad_norm": 0.26041269302368164,
+      "learning_rate": 0.0002,
+      "loss": 1.1158,
+      "step": 590
+    },
+    {
+      "epoch": 0.7398273736128237,
+      "grad_norm": 0.3804777264595032,
+      "learning_rate": 0.0002,
+      "loss": 1.2134,
+      "step": 600
+    },
+    {
+      "epoch": 0.752157829839704,
+      "grad_norm": 0.2456253319978714,
+      "learning_rate": 0.0002,
+      "loss": 1.0606,
+      "step": 610
+    },
+    {
+      "epoch": 0.7644882860665845,
+      "grad_norm": 0.37838423252105713,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 620
+    },
+    {
+      "epoch": 0.7768187422934648,
+      "grad_norm": 0.28105494379997253,
+      "learning_rate": 0.0002,
+      "loss": 1.0556,
+      "step": 630
+    },
+    {
+      "epoch": 0.7891491985203453,
+      "grad_norm": 0.2774018943309784,
+      "learning_rate": 0.0002,
+      "loss": 1.0672,
+      "step": 640
+    },
+    {
+      "epoch": 0.8014796547472256,
+      "grad_norm": 1.8184229135513306,
+      "learning_rate": 0.0002,
+      "loss": 0.9978,
+      "step": 650
+    },
+    {
+      "epoch": 0.813810110974106,
+      "grad_norm": 0.3325096070766449,
+      "learning_rate": 0.0002,
+      "loss": 1.1038,
+      "step": 660
+    },
+    {
+      "epoch": 0.8261405672009864,
+      "grad_norm": 0.2686693072319031,
+      "learning_rate": 0.0002,
+      "loss": 1.083,
+      "step": 670
+    },
+    {
+      "epoch": 0.8384710234278668,
+      "grad_norm": 0.3271431624889374,
+      "learning_rate": 0.0002,
+      "loss": 1.1308,
+      "step": 680
+    },
+    {
+      "epoch": 0.8508014796547472,
+      "grad_norm": 2.359999656677246,
+      "learning_rate": 0.0002,
+      "loss": 1.1116,
+      "step": 690
+    },
+    {
+      "epoch": 0.8631319358816276,
+      "grad_norm": 0.46242964267730713,
+      "learning_rate": 0.0002,
+      "loss": 1.0782,
+      "step": 700
+    },
+    {
+      "epoch": 0.8754623921085081,
+      "grad_norm": 0.34731170535087585,
+      "learning_rate": 0.0002,
+      "loss": 0.95,
+      "step": 710
+    },
+    {
+      "epoch": 0.8877928483353884,
+      "grad_norm": 0.39381715655326843,
+      "learning_rate": 0.0002,
+      "loss": 1.2236,
+      "step": 720
+    },
+    {
+      "epoch": 0.9001233045622689,
+      "grad_norm": 0.43496373295783997,
+      "learning_rate": 0.0002,
+      "loss": 1.1319,
+      "step": 730
+    },
+    {
+      "epoch": 0.9124537607891492,
+      "grad_norm": 0.32243210077285767,
+      "learning_rate": 0.0002,
+      "loss": 1.0979,
+      "step": 740
+    },
+    {
+      "epoch": 0.9247842170160296,
+      "grad_norm": 0.30396756529808044,
+      "learning_rate": 0.0002,
+      "loss": 0.9913,
+      "step": 750
+    },
+    {
+      "epoch": 0.93711467324291,
+      "grad_norm": 0.4461122751235962,
+      "learning_rate": 0.0002,
+      "loss": 1.1141,
+      "step": 760
+    },
+    {
+      "epoch": 0.9494451294697904,
+      "grad_norm": 0.24081681668758392,
+      "learning_rate": 0.0002,
+      "loss": 1.0049,
+      "step": 770
+    },
+    {
+      "epoch": 0.9617755856966708,
+      "grad_norm": 0.27461910247802734,
+      "learning_rate": 0.0002,
+      "loss": 1.0966,
+      "step": 780
+    },
+    {
+      "epoch": 0.9741060419235512,
+      "grad_norm": 0.3325668275356293,
+      "learning_rate": 0.0002,
+      "loss": 0.9942,
+      "step": 790
+    },
+    {
+      "epoch": 0.9864364981504316,
+      "grad_norm": 0.24046339094638824,
+      "learning_rate": 0.0002,
+      "loss": 1.0506,
+      "step": 800
+    },
+    {
+      "epoch": 0.998766954377312,
+      "grad_norm": 0.42950066924095154,
+      "learning_rate": 0.0002,
+      "loss": 0.9989,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.246457576751709,
+      "eval_runtime": 98.7974,
+      "eval_samples_per_second": 4.413,
+      "eval_steps_per_second": 0.557,
+      "step": 811
+    },
+    {
+      "epoch": 1.0110974106041923,
+      "grad_norm": 0.26760655641555786,
+      "learning_rate": 0.0002,
+      "loss": 1.0536,
+      "step": 820
+    },
+    {
+      "epoch": 1.0234278668310728,
+      "grad_norm": 0.4640820026397705,
+      "learning_rate": 0.0002,
+      "loss": 0.9722,
+      "step": 830
+    },
+    {
+      "epoch": 1.0357583230579532,
+      "grad_norm": 0.2699166238307953,
+      "learning_rate": 0.0002,
+      "loss": 0.9392,
+      "step": 840
+    },
+    {
+      "epoch": 1.0480887792848335,
+      "grad_norm": 0.3441709578037262,
+      "learning_rate": 0.0002,
+      "loss": 0.9335,
+      "step": 850
+    },
+    {
+      "epoch": 1.060419235511714,
+      "grad_norm": 0.299934983253479,
+      "learning_rate": 0.0002,
+      "loss": 0.9083,
+      "step": 860
+    },
+    {
+      "epoch": 1.0727496917385944,
+      "grad_norm": 0.2980666160583496,
+      "learning_rate": 0.0002,
+      "loss": 0.9416,
+      "step": 870
+    },
+    {
+      "epoch": 1.0850801479654748,
+      "grad_norm": 0.3131714463233948,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 880
+    },
+    {
+      "epoch": 1.097410604192355,
+      "grad_norm": 0.29881617426872253,
+      "learning_rate": 0.0002,
+      "loss": 0.9288,
+      "step": 890
+    },
+    {
+      "epoch": 1.1097410604192355,
+      "grad_norm": 0.29870888590812683,
+      "learning_rate": 0.0002,
+      "loss": 0.998,
+      "step": 900
+    },
+    {
+      "epoch": 1.122071516646116,
+      "grad_norm": 0.5735140442848206,
+      "learning_rate": 0.0002,
+      "loss": 0.9924,
+      "step": 910
+    },
+    {
+      "epoch": 1.1344019728729964,
+      "grad_norm": 0.33159002661705017,
+      "learning_rate": 0.0002,
+      "loss": 1.0694,
+      "step": 920
+    },
+    {
+      "epoch": 1.1467324290998766,
+      "grad_norm": 1.235399842262268,
+      "learning_rate": 0.0002,
+      "loss": 1.0069,
+      "step": 930
+    },
+    {
+      "epoch": 1.159062885326757,
+      "grad_norm": 0.27469736337661743,
+      "learning_rate": 0.0002,
+      "loss": 1.0315,
+      "step": 940
+    },
+    {
+      "epoch": 1.1713933415536375,
+      "grad_norm": 0.29130664467811584,
+      "learning_rate": 0.0002,
+      "loss": 0.9386,
+      "step": 950
+    },
+    {
+      "epoch": 1.183723797780518,
+      "grad_norm": 0.3730354607105255,
+      "learning_rate": 0.0002,
+      "loss": 0.8919,
+      "step": 960
+    },
+    {
+      "epoch": 1.1960542540073984,
+      "grad_norm": 0.5973590612411499,
+      "learning_rate": 0.0002,
+      "loss": 0.9988,
+      "step": 970
+    },
+    {
+      "epoch": 1.2083847102342786,
+      "grad_norm": 0.39631304144859314,
+      "learning_rate": 0.0002,
+      "loss": 0.9525,
+      "step": 980
+    },
+    {
+      "epoch": 1.220715166461159,
+      "grad_norm": 0.849051296710968,
+      "learning_rate": 0.0002,
+      "loss": 0.9217,
+      "step": 990
+    },
+    {
+      "epoch": 1.2330456226880395,
+      "grad_norm": 0.4390525817871094,
+      "learning_rate": 0.0002,
+      "loss": 1.0903,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2453760789149197,
+      "grad_norm": 0.30423852801322937,
+      "learning_rate": 0.0002,
+      "loss": 0.9018,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2577065351418002,
+      "grad_norm": 0.34736061096191406,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2700369913686806,
+      "grad_norm": 0.3421604037284851,
+      "learning_rate": 0.0002,
+      "loss": 0.9026,
+      "step": 1030
+    },
+    {
+      "epoch": 1.282367447595561,
+      "grad_norm": 0.544170081615448,
+      "learning_rate": 0.0002,
+      "loss": 0.8485,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2946979038224415,
+      "grad_norm": 0.5128790736198425,
+      "learning_rate": 0.0002,
+      "loss": 0.9591,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3070283600493218,
+      "grad_norm": 0.443344384431839,
+      "learning_rate": 0.0002,
+      "loss": 0.9214,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3193588162762022,
+      "grad_norm": 0.6380868554115295,
+      "learning_rate": 0.0002,
+      "loss": 0.9367,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3316892725030827,
+      "grad_norm": 0.4638073146343231,
+      "learning_rate": 0.0002,
+      "loss": 0.9849,
+      "step": 1080
+    },
+    {
+      "epoch": 1.344019728729963,
+      "grad_norm": 0.32406893372535706,
+      "learning_rate": 0.0002,
+      "loss": 0.8645,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3563501849568433,
+      "grad_norm": 0.3955065608024597,
+      "learning_rate": 0.0002,
+      "loss": 0.8278,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3686806411837238,
+      "grad_norm": 0.3489246666431427,
+      "learning_rate": 0.0002,
+      "loss": 0.9306,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3810110974106042,
+      "grad_norm": 0.48451653122901917,
+      "learning_rate": 0.0002,
+      "loss": 1.0138,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3933415536374847,
+      "grad_norm": 0.3652360439300537,
+      "learning_rate": 0.0002,
+      "loss": 0.9165,
+      "step": 1130
+    },
+    {
+      "epoch": 1.405672009864365,
+      "grad_norm": 1.3097436428070068,
+      "learning_rate": 0.0002,
+      "loss": 0.9576,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4180024660912454,
+      "grad_norm": 0.3647715449333191,
+      "learning_rate": 0.0002,
+      "loss": 0.8115,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4303329223181258,
+      "grad_norm": 0.37248560786247253,
+      "learning_rate": 0.0002,
+      "loss": 0.8573,
+      "step": 1160
+    },
+    {
+      "epoch": 1.442663378545006,
+      "grad_norm": 0.4639643430709839,
+      "learning_rate": 0.0002,
+      "loss": 0.936,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4549938347718865,
+      "grad_norm": 0.5455219745635986,
+      "learning_rate": 0.0002,
+      "loss": 0.9511,
+      "step": 1180
+    },
+    {
+      "epoch": 1.467324290998767,
+      "grad_norm": 0.38862571120262146,
+      "learning_rate": 0.0002,
+      "loss": 0.8611,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4796547472256474,
+      "grad_norm": 0.37586215138435364,
+      "learning_rate": 0.0002,
+      "loss": 0.8681,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4919852034525278,
+      "grad_norm": 0.46244436502456665,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1210
+    },
+    {
+      "epoch": 1.504315659679408,
+      "grad_norm": 0.3570359945297241,
+      "learning_rate": 0.0002,
+      "loss": 0.9388,
+      "step": 1220
+    },
+    {
+      "epoch": 1.5166461159062885,
+      "grad_norm": 0.28393083810806274,
+      "learning_rate": 0.0002,
+      "loss": 0.971,
+      "step": 1230
+    },
+    {
+      "epoch": 1.528976572133169,
+      "grad_norm": 0.5672869682312012,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5413070283600492,
+      "grad_norm": 0.41605108976364136,
+      "learning_rate": 0.0002,
+      "loss": 0.8787,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5536374845869299,
+      "grad_norm": 0.40657493472099304,
+      "learning_rate": 0.0002,
+      "loss": 0.8744,
+      "step": 1260
+    },
+    {
+      "epoch": 1.56596794081381,
+      "grad_norm": 0.43672341108322144,
+      "learning_rate": 0.0002,
+      "loss": 0.9046,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5782983970406905,
+      "grad_norm": 0.3065410554409027,
+      "learning_rate": 0.0002,
+      "loss": 0.8586,
+      "step": 1280
+    },
+    {
+      "epoch": 1.590628853267571,
+      "grad_norm": 0.37826645374298096,
+      "learning_rate": 0.0002,
+      "loss": 0.9499,
+      "step": 1290
+    },
+    {
+      "epoch": 1.6029593094944512,
+      "grad_norm": 0.42307335138320923,
+      "learning_rate": 0.0002,
+      "loss": 0.901,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6152897657213316,
+      "grad_norm": 0.3648843467235565,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1310
+    },
+    {
+      "epoch": 1.627620221948212,
+      "grad_norm": 0.8921076059341431,
+      "learning_rate": 0.0002,
+      "loss": 0.9302,
+      "step": 1320
+    },
+    {
+      "epoch": 1.6399506781750923,
+      "grad_norm": 0.37522226572036743,
+      "learning_rate": 0.0002,
+      "loss": 0.9378,
+      "step": 1330
+    },
+    {
+      "epoch": 1.652281134401973,
+      "grad_norm": 0.7489957809448242,
+      "learning_rate": 0.0002,
+      "loss": 0.8921,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6646115906288532,
+      "grad_norm": 0.31733131408691406,
+      "learning_rate": 0.0002,
+      "loss": 0.9297,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6769420468557337,
+      "grad_norm": 0.3249478340148926,
+      "learning_rate": 0.0002,
+      "loss": 0.907,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6892725030826141,
+      "grad_norm": 0.3178001344203949,
+      "learning_rate": 0.0002,
+      "loss": 1.0197,
+      "step": 1370
+    },
+    {
+      "epoch": 1.7016029593094943,
+      "grad_norm": 0.5674093961715698,
+      "learning_rate": 0.0002,
+      "loss": 1.0781,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7139334155363748,
+      "grad_norm": 0.35272449254989624,
+      "learning_rate": 0.0002,
+      "loss": 0.8972,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7262638717632552,
+      "grad_norm": 0.5778217911720276,
+      "learning_rate": 0.0002,
+      "loss": 0.9346,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7385943279901355,
+      "grad_norm": 0.33561450242996216,
+      "learning_rate": 0.0002,
+      "loss": 0.9099,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7509247842170161,
+      "grad_norm": 0.31735464930534363,
+      "learning_rate": 0.0002,
+      "loss": 0.8636,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7632552404438964,
+      "grad_norm": 1.0612670183181763,
+      "learning_rate": 0.0002,
+      "loss": 0.982,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7755856966707768,
+      "grad_norm": 0.5442509651184082,
+      "learning_rate": 0.0002,
+      "loss": 0.8224,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7879161528976573,
+      "grad_norm": 0.7471332550048828,
+      "learning_rate": 0.0002,
+      "loss": 0.9275,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8002466091245375,
+      "grad_norm": 0.4323609173297882,
+      "learning_rate": 0.0002,
+      "loss": 0.9389,
+      "step": 1460
+    },
+    {
+      "epoch": 1.8125770653514182,
+      "grad_norm": 0.47796759009361267,
+      "learning_rate": 0.0002,
+      "loss": 0.8247,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8249075215782984,
+      "grad_norm": 0.3348400592803955,
+      "learning_rate": 0.0002,
+      "loss": 0.9395,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8372379778051788,
+      "grad_norm": 0.3354550898075104,
+      "learning_rate": 0.0002,
+      "loss": 0.9793,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8495684340320593,
+      "grad_norm": 0.5988477468490601,
+      "learning_rate": 0.0002,
+      "loss": 0.8581,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8618988902589395,
+      "grad_norm": 0.5222318172454834,
+      "learning_rate": 0.0002,
+      "loss": 0.9268,
+      "step": 1510
+    },
+    {
+      "epoch": 1.87422934648582,
+      "grad_norm": 0.5246642827987671,
+      "learning_rate": 0.0002,
+      "loss": 0.8846,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8865598027127004,
+      "grad_norm": 0.3164594769477844,
+      "learning_rate": 0.0002,
+      "loss": 0.9317,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8988902589395806,
+      "grad_norm": 0.3496174216270447,
+      "learning_rate": 0.0002,
+      "loss": 0.9961,
+      "step": 1540
+    },
+    {
+      "epoch": 1.9112207151664613,
+      "grad_norm": 0.8863359689712524,
+      "learning_rate": 0.0002,
+      "loss": 0.9057,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9235511713933415,
+      "grad_norm": 0.3587026298046112,
+      "learning_rate": 0.0002,
+      "loss": 0.9405,
+      "step": 1560
+    },
+    {
+      "epoch": 1.935881627620222,
+      "grad_norm": 0.6052881479263306,
+      "learning_rate": 0.0002,
+      "loss": 0.8335,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9482120838471024,
+      "grad_norm": 0.567269504070282,
+      "learning_rate": 0.0002,
+      "loss": 0.8805,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9605425400739827,
+      "grad_norm": 0.45184487104415894,
+      "learning_rate": 0.0002,
+      "loss": 0.9581,
+      "step": 1590
+    },
+    {
+      "epoch": 1.972872996300863,
+      "grad_norm": 0.5028569102287292,
+      "learning_rate": 0.0002,
+      "loss": 0.9147,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9852034525277436,
+      "grad_norm": 0.4677547216415405,
+      "learning_rate": 0.0002,
+      "loss": 0.75,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9975339087546238,
+      "grad_norm": 0.35106056928634644,
+      "learning_rate": 0.0002,
+      "loss": 0.8469,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.238026738166809,
+      "eval_runtime": 95.4287,
+      "eval_samples_per_second": 4.569,
+      "eval_steps_per_second": 0.576,
+      "step": 1622
+    },
+    {
+      "epoch": 2.0098643649815044,
+      "grad_norm": 0.444060355424881,
+      "learning_rate": 0.0002,
+      "loss": 0.7629,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0221948212083847,
+      "grad_norm": 0.627570390701294,
+      "learning_rate": 0.0002,
+      "loss": 0.772,
+      "step": 1640
+    },
+    {
+      "epoch": 2.034525277435265,
+      "grad_norm": 0.38737839460372925,
+      "learning_rate": 0.0002,
+      "loss": 0.6186,
+      "step": 1650
+    },
+    {
+      "epoch": 2.0468557336621456,
+      "grad_norm": 0.4300459623336792,
+      "learning_rate": 0.0002,
+      "loss": 0.7734,
+      "step": 1660
+    },
+    {
+      "epoch": 2.059186189889026,
+      "grad_norm": 0.43037715554237366,
+      "learning_rate": 0.0002,
+      "loss": 0.6943,
+      "step": 1670
+    },
+    {
+      "epoch": 2.0715166461159065,
+      "grad_norm": 0.40772515535354614,
+      "learning_rate": 0.0002,
+      "loss": 0.6588,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0838471023427867,
+      "grad_norm": 0.5295451879501343,
+      "learning_rate": 0.0002,
+      "loss": 0.8105,
+      "step": 1690
+    },
+    {
+      "epoch": 2.096177558569667,
+      "grad_norm": 0.7452750205993652,
+      "learning_rate": 0.0002,
+      "loss": 0.7717,
+      "step": 1700
+    },
+    {
+      "epoch": 2.1085080147965476,
+      "grad_norm": 0.809183657169342,
+      "learning_rate": 0.0002,
+      "loss": 0.7458,
+      "step": 1710
+    },
+    {
+      "epoch": 2.120838471023428,
+      "grad_norm": 0.4597688913345337,
+      "learning_rate": 0.0002,
+      "loss": 0.7398,
+      "step": 1720
+    },
+    {
+      "epoch": 2.133168927250308,
+      "grad_norm": 0.806919276714325,
+      "learning_rate": 0.0002,
+      "loss": 0.6856,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1454993834771887,
+      "grad_norm": 0.3755643665790558,
+      "learning_rate": 0.0002,
+      "loss": 0.679,
+      "step": 1740
+    },
+    {
+      "epoch": 2.157829839704069,
+      "grad_norm": 0.5882734060287476,
+      "learning_rate": 0.0002,
+      "loss": 0.7938,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1701602959309496,
+      "grad_norm": 0.692960798740387,
+      "learning_rate": 0.0002,
+      "loss": 0.6782,
+      "step": 1760
+    },
+    {
+      "epoch": 2.18249075215783,
+      "grad_norm": 0.4737096428871155,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 1770
+    },
+    {
+      "epoch": 2.19482120838471,
+      "grad_norm": 0.6637021899223328,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 1780
+    },
+    {
+      "epoch": 2.2071516646115907,
+      "grad_norm": 0.9109764099121094,
+      "learning_rate": 0.0002,
+      "loss": 0.7139,
+      "step": 1790
+    },
+    {
+      "epoch": 2.219482120838471,
+      "grad_norm": 0.4137539267539978,
+      "learning_rate": 0.0002,
+      "loss": 0.7373,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2318125770653516,
+      "grad_norm": 0.44995415210723877,
+      "learning_rate": 0.0002,
+      "loss": 0.7266,
+      "step": 1810
+    },
+    {
+      "epoch": 2.244143033292232,
+      "grad_norm": 0.5985036492347717,
+      "learning_rate": 0.0002,
+      "loss": 0.7663,
+      "step": 1820
+    },
+    {
+      "epoch": 2.256473489519112,
+      "grad_norm": 0.7549490332603455,
+      "learning_rate": 0.0002,
+      "loss": 0.7502,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2688039457459928,
+      "grad_norm": 0.4490937888622284,
+      "learning_rate": 0.0002,
+      "loss": 0.7452,
+      "step": 1840
+    },
+    {
+      "epoch": 2.281134401972873,
+      "grad_norm": 0.38859808444976807,
+      "learning_rate": 0.0002,
+      "loss": 0.7531,
+      "step": 1850
+    },
+    {
+      "epoch": 2.293464858199753,
+      "grad_norm": 1.0704916715621948,
+      "learning_rate": 0.0002,
+      "loss": 0.7278,
+      "step": 1860
+    },
+    {
+      "epoch": 2.305795314426634,
+      "grad_norm": 0.4647100865840912,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 1870
+    },
+    {
+      "epoch": 2.318125770653514,
+      "grad_norm": 0.6181163787841797,
+      "learning_rate": 0.0002,
+      "loss": 0.7146,
+      "step": 1880
+    },
+    {
+      "epoch": 2.3304562268803943,
+      "grad_norm": 0.9241904020309448,
+      "learning_rate": 0.0002,
+      "loss": 0.7689,
+      "step": 1890
+    },
+    {
+      "epoch": 2.342786683107275,
+      "grad_norm": 0.39101317524909973,
+      "learning_rate": 0.0002,
+      "loss": 0.7294,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3551171393341552,
+      "grad_norm": 0.49442458152770996,
+      "learning_rate": 0.0002,
+      "loss": 0.7079,
+      "step": 1910
+    },
+    {
+      "epoch": 2.367447595561036,
+      "grad_norm": 0.4864824414253235,
+      "learning_rate": 0.0002,
+      "loss": 0.7586,
+      "step": 1920
+    },
+    {
+      "epoch": 2.379778051787916,
+      "grad_norm": 0.5427613854408264,
+      "learning_rate": 0.0002,
+      "loss": 0.7434,
+      "step": 1930
+    },
+    {
+      "epoch": 2.392108508014797,
+      "grad_norm": 0.7164974808692932,
+      "learning_rate": 0.0002,
+      "loss": 0.8423,
+      "step": 1940
+    },
+    {
+      "epoch": 2.404438964241677,
+      "grad_norm": 0.562979519367218,
+      "learning_rate": 0.0002,
+      "loss": 0.6888,
+      "step": 1950
+    },
+    {
+      "epoch": 2.4167694204685573,
+      "grad_norm": 0.5631861090660095,
+      "learning_rate": 0.0002,
+      "loss": 0.7692,
+      "step": 1960
+    },
+    {
+      "epoch": 2.429099876695438,
+      "grad_norm": 0.4895121157169342,
+      "learning_rate": 0.0002,
+      "loss": 0.67,
+      "step": 1970
+    },
+    {
+      "epoch": 2.441430332922318,
+      "grad_norm": 0.45674824714660645,
+      "learning_rate": 0.0002,
+      "loss": 0.7735,
+      "step": 1980
+    },
+    {
+      "epoch": 2.4537607891491984,
+      "grad_norm": 1.1424206495285034,
+      "learning_rate": 0.0002,
+      "loss": 0.685,
+      "step": 1990
+    },
+    {
+      "epoch": 2.466091245376079,
+      "grad_norm": 0.6314579844474792,
+      "learning_rate": 0.0002,
+      "loss": 0.7627,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4784217016029593,
+      "grad_norm": 0.5481605529785156,
+      "learning_rate": 0.0002,
+      "loss": 0.7118,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4907521578298395,
+      "grad_norm": 0.4671579599380493,
+      "learning_rate": 0.0002,
+      "loss": 0.6947,
+      "step": 2020
+    },
+    {
+      "epoch": 2.50308261405672,
+      "grad_norm": 0.7621194124221802,
+      "learning_rate": 0.0002,
+      "loss": 0.7377,
+      "step": 2030
+    },
+    {
+      "epoch": 2.5154130702836004,
+      "grad_norm": 0.38983288407325745,
+      "learning_rate": 0.0002,
+      "loss": 0.69,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5277435265104806,
+      "grad_norm": 0.6341150999069214,
+      "learning_rate": 0.0002,
+      "loss": 0.8381,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5400739827373613,
+      "grad_norm": 0.7151971459388733,
+      "learning_rate": 0.0002,
+      "loss": 0.773,
+      "step": 2060
+    },
+    {
+      "epoch": 2.5524044389642415,
+      "grad_norm": 0.9665895104408264,
+      "learning_rate": 0.0002,
+      "loss": 0.6733,
+      "step": 2070
+    },
+    {
+      "epoch": 2.564734895191122,
+      "grad_norm": 0.9572727680206299,
+      "learning_rate": 0.0002,
+      "loss": 0.7791,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5770653514180024,
+      "grad_norm": 1.1970765590667725,
+      "learning_rate": 0.0002,
+      "loss": 0.7205,
+      "step": 2090
+    },
+    {
+      "epoch": 2.589395807644883,
+      "grad_norm": 0.5505942702293396,
+      "learning_rate": 0.0002,
+      "loss": 0.6736,
+      "step": 2100
+    },
+    {
+      "epoch": 2.6017262638717633,
+      "grad_norm": 0.5903949737548828,
+      "learning_rate": 0.0002,
+      "loss": 0.673,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6140567200986435,
+      "grad_norm": 0.45640307664871216,
+      "learning_rate": 0.0002,
+      "loss": 0.678,
+      "step": 2120
+    },
+    {
+      "epoch": 2.626387176325524,
+      "grad_norm": 0.8763944506645203,
+      "learning_rate": 0.0002,
+      "loss": 0.6562,
+      "step": 2130
+    },
+    {
+      "epoch": 2.6387176325524044,
+      "grad_norm": 0.4472963213920593,
+      "learning_rate": 0.0002,
+      "loss": 0.6484,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6510480887792847,
+      "grad_norm": 0.5335086584091187,
+      "learning_rate": 0.0002,
+      "loss": 0.7702,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6633785450061653,
+      "grad_norm": 0.805263340473175,
+      "learning_rate": 0.0002,
+      "loss": 0.6851,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6757090012330456,
+      "grad_norm": 0.6332727670669556,
+      "learning_rate": 0.0002,
+      "loss": 0.7026,
+      "step": 2170
+    },
+    {
+      "epoch": 2.688039457459926,
+      "grad_norm": 0.8667435646057129,
+      "learning_rate": 0.0002,
+      "loss": 0.7925,
+      "step": 2180
+    },
+    {
+      "epoch": 2.7003699136868065,
+      "grad_norm": 0.5638955235481262,
+      "learning_rate": 0.0002,
+      "loss": 0.8044,
+      "step": 2190
+    },
+    {
+      "epoch": 2.7127003699136867,
+      "grad_norm": 0.4176250696182251,
+      "learning_rate": 0.0002,
+      "loss": 0.7117,
+      "step": 2200
+    },
+    {
+      "epoch": 2.7250308261405674,
+      "grad_norm": 0.6013461351394653,
+      "learning_rate": 0.0002,
+      "loss": 0.6932,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7373612823674476,
+      "grad_norm": 0.553961992263794,
+      "learning_rate": 0.0002,
+      "loss": 0.7843,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7496917385943282,
+      "grad_norm": 0.4710180461406708,
+      "learning_rate": 0.0002,
+      "loss": 0.8633,
+      "step": 2230
+    },
+    {
+      "epoch": 2.7620221948212085,
+      "grad_norm": 0.8141706585884094,
+      "learning_rate": 0.0002,
+      "loss": 0.7469,
+      "step": 2240
+    },
+    {
+      "epoch": 2.7743526510480887,
+      "grad_norm": 0.7449556589126587,
+      "learning_rate": 0.0002,
+      "loss": 0.7086,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7866831072749694,
+      "grad_norm": 0.5366780757904053,
+      "learning_rate": 0.0002,
+      "loss": 0.6933,
+      "step": 2260
+    },
+    {
+      "epoch": 2.7990135635018496,
+      "grad_norm": 0.5316720604896545,
+      "learning_rate": 0.0002,
+      "loss": 0.7192,
+      "step": 2270
+    },
+    {
+      "epoch": 2.81134401972873,
+      "grad_norm": 0.4598459005355835,
+      "learning_rate": 0.0002,
+      "loss": 0.6212,
+      "step": 2280
+    },
+    {
+      "epoch": 2.8236744759556105,
+      "grad_norm": 0.6852091550827026,
+      "learning_rate": 0.0002,
+      "loss": 0.7024,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8360049321824907,
+      "grad_norm": 0.8040902018547058,
+      "learning_rate": 0.0002,
+      "loss": 0.7357,
+      "step": 2300
+    },
+    {
+      "epoch": 2.848335388409371,
+      "grad_norm": 0.46976321935653687,
+      "learning_rate": 0.0002,
+      "loss": 0.7563,
+      "step": 2310
+    },
+    {
+      "epoch": 2.8606658446362516,
+      "grad_norm": 0.5214090347290039,
+      "learning_rate": 0.0002,
+      "loss": 0.731,
+      "step": 2320
+    },
+    {
+      "epoch": 2.872996300863132,
+      "grad_norm": 0.5323054790496826,
+      "learning_rate": 0.0002,
+      "loss": 0.6687,
+      "step": 2330
+    },
+    {
+      "epoch": 2.885326757090012,
+      "grad_norm": 0.6842264533042908,
+      "learning_rate": 0.0002,
+      "loss": 0.7895,
+      "step": 2340
+    },
+    {
+      "epoch": 2.8976572133168927,
+      "grad_norm": 0.9157055616378784,
+      "learning_rate": 0.0002,
+      "loss": 0.7737,
+      "step": 2350
+    },
+    {
+      "epoch": 2.909987669543773,
+      "grad_norm": 0.5253258347511292,
+      "learning_rate": 0.0002,
+      "loss": 0.7217,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9223181257706536,
+      "grad_norm": 0.4937705099582672,
+      "learning_rate": 0.0002,
+      "loss": 0.7162,
+      "step": 2370
+    },
+    {
+      "epoch": 2.934648581997534,
+      "grad_norm": 0.48762989044189453,
+      "learning_rate": 0.0002,
+      "loss": 0.7008,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9469790382244145,
+      "grad_norm": 0.544335126876831,
+      "learning_rate": 0.0002,
+      "loss": 0.8086,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9593094944512948,
+      "grad_norm": 0.4847845435142517,
+      "learning_rate": 0.0002,
+      "loss": 0.643,
+      "step": 2400
+    },
+    {
+      "epoch": 2.971639950678175,
+      "grad_norm": 0.4787445366382599,
+      "learning_rate": 0.0002,
+      "loss": 0.7757,
+      "step": 2410
+    },
+    {
+      "epoch": 2.9839704069050557,
+      "grad_norm": 1.022318959236145,
+      "learning_rate": 0.0002,
+      "loss": 0.7678,
+      "step": 2420
+    },
+    {
+      "epoch": 2.996300863131936,
+      "grad_norm": 0.4987848103046417,
+      "learning_rate": 0.0002,
+      "loss": 0.6548,
+      "step": 2430
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2936296463012695,
+      "eval_runtime": 94.7897,
+      "eval_samples_per_second": 4.6,
+      "eval_steps_per_second": 0.58,
+      "step": 2433
+    },
+    {
+      "epoch": 3.008631319358816,
+      "grad_norm": 0.5562372803688049,
+      "learning_rate": 0.0002,
+      "loss": 0.6073,
+      "step": 2440
+    },
+    {
+      "epoch": 3.020961775585697,
+      "grad_norm": 1.133402705192566,
+      "learning_rate": 0.0002,
+      "loss": 0.5181,
+      "step": 2450
+    },
+    {
+      "epoch": 3.033292231812577,
+      "grad_norm": 0.6480470299720764,
+      "learning_rate": 0.0002,
+      "loss": 0.5333,
+      "step": 2460
+    },
+    {
+      "epoch": 3.0456226880394572,
+      "grad_norm": 0.8989138007164001,
+      "learning_rate": 0.0002,
+      "loss": 0.4828,
+      "step": 2470
+    },
+    {
+      "epoch": 3.057953144266338,
+      "grad_norm": 0.8257461786270142,
+      "learning_rate": 0.0002,
+      "loss": 0.5097,
+      "step": 2480
+    },
+    {
+      "epoch": 3.070283600493218,
+      "grad_norm": 0.6813381910324097,
+      "learning_rate": 0.0002,
+      "loss": 0.6229,
+      "step": 2490
+    },
+    {
+      "epoch": 3.082614056720099,
+      "grad_norm": 0.6989586353302002,
+      "learning_rate": 0.0002,
+      "loss": 0.531,
+      "step": 2500
+    },
+    {
+      "epoch": 3.094944512946979,
+      "grad_norm": 0.7992092967033386,
+      "learning_rate": 0.0002,
+      "loss": 0.54,
+      "step": 2510
+    },
+    {
+      "epoch": 3.1072749691738593,
+      "grad_norm": 0.698077917098999,
+      "learning_rate": 0.0002,
+      "loss": 0.5054,
+      "step": 2520
+    },
+    {
+      "epoch": 3.11960542540074,
+      "grad_norm": 0.5699033141136169,
+      "learning_rate": 0.0002,
+      "loss": 0.5064,
+      "step": 2530
+    },
+    {
+      "epoch": 3.13193588162762,
+      "grad_norm": 0.6142355799674988,
+      "learning_rate": 0.0002,
+      "loss": 0.6088,
+      "step": 2540
+    },
+    {
+      "epoch": 3.144266337854501,
+      "grad_norm": 0.7089933753013611,
+      "learning_rate": 0.0002,
+      "loss": 0.585,
+      "step": 2550
+    },
+    {
+      "epoch": 3.156596794081381,
+      "grad_norm": 1.0107015371322632,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 2560
+    },
+    {
+      "epoch": 3.1689272503082613,
+      "grad_norm": 0.568138837814331,
+      "learning_rate": 0.0002,
+      "loss": 0.5429,
+      "step": 2570
+    },
+    {
+      "epoch": 3.181257706535142,
+      "grad_norm": 0.9960416555404663,
+      "learning_rate": 0.0002,
+      "loss": 0.5897,
+      "step": 2580
+    },
+    {
+      "epoch": 3.193588162762022,
+      "grad_norm": 0.6277595162391663,
+      "learning_rate": 0.0002,
+      "loss": 0.5211,
+      "step": 2590
+    },
+    {
+      "epoch": 3.2059186189889024,
+      "grad_norm": 0.681083619594574,
+      "learning_rate": 0.0002,
+      "loss": 0.5787,
+      "step": 2600
+    },
+    {
+      "epoch": 3.218249075215783,
+      "grad_norm": 0.5816057324409485,
+      "learning_rate": 0.0002,
+      "loss": 0.5166,
+      "step": 2610
+    },
+    {
+      "epoch": 3.2305795314426633,
+      "grad_norm": 0.7197734117507935,
+      "learning_rate": 0.0002,
+      "loss": 0.545,
+      "step": 2620
+    },
+    {
+      "epoch": 3.242909987669544,
+      "grad_norm": 0.6524068117141724,
+      "learning_rate": 0.0002,
+      "loss": 0.614,
+      "step": 2630
+    },
+    {
+      "epoch": 3.255240443896424,
+      "grad_norm": 1.273668646812439,
+      "learning_rate": 0.0002,
+      "loss": 0.5456,
+      "step": 2640
+    },
+    {
+      "epoch": 3.2675709001233044,
+      "grad_norm": 0.6950451731681824,
+      "learning_rate": 0.0002,
+      "loss": 0.5266,
+      "step": 2650
+    },
+    {
+      "epoch": 3.279901356350185,
+      "grad_norm": 0.8029071688652039,
+      "learning_rate": 0.0002,
+      "loss": 0.5194,
+      "step": 2660
+    },
+    {
+      "epoch": 3.2922318125770653,
+      "grad_norm": 0.7464073896408081,
+      "learning_rate": 0.0002,
+      "loss": 0.5729,
+      "step": 2670
+    },
+    {
+      "epoch": 3.304562268803946,
+      "grad_norm": 0.8342001438140869,
+      "learning_rate": 0.0002,
+      "loss": 0.5366,
+      "step": 2680
+    },
+    {
+      "epoch": 3.316892725030826,
+      "grad_norm": 0.5629868507385254,
+      "learning_rate": 0.0002,
+      "loss": 0.5413,
+      "step": 2690
+    },
+    {
+      "epoch": 3.3292231812577064,
+      "grad_norm": 0.753999650478363,
+      "learning_rate": 0.0002,
+      "loss": 0.633,
+      "step": 2700
+    },
+    {
+      "epoch": 3.341553637484587,
+      "grad_norm": 1.0271371603012085,
+      "learning_rate": 0.0002,
+      "loss": 0.5048,
+      "step": 2710
+    },
+    {
+      "epoch": 3.3538840937114673,
+      "grad_norm": 0.9608535170555115,
+      "learning_rate": 0.0002,
+      "loss": 0.5233,
+      "step": 2720
+    },
+    {
+      "epoch": 3.3662145499383476,
+      "grad_norm": 0.7796488404273987,
+      "learning_rate": 0.0002,
+      "loss": 0.5102,
+      "step": 2730
+    },
+    {
+      "epoch": 3.3785450061652282,
+      "grad_norm": 0.5666437149047852,
+      "learning_rate": 0.0002,
+      "loss": 0.5172,
+      "step": 2740
+    },
+    {
+      "epoch": 3.3908754623921085,
+      "grad_norm": 0.5462956428527832,
+      "learning_rate": 0.0002,
+      "loss": 0.491,
+      "step": 2750
+    },
+    {
+      "epoch": 3.4032059186189887,
+      "grad_norm": 1.289099097251892,
+      "learning_rate": 0.0002,
+      "loss": 0.5855,
+      "step": 2760
+    },
+    {
+      "epoch": 3.4155363748458694,
+      "grad_norm": 0.825566828250885,
+      "learning_rate": 0.0002,
+      "loss": 0.635,
+      "step": 2770
+    },
+    {
+      "epoch": 3.4278668310727496,
+      "grad_norm": 0.8366670608520508,
+      "learning_rate": 0.0002,
+      "loss": 0.4998,
+      "step": 2780
+    },
+    {
+      "epoch": 3.4401972872996303,
+      "grad_norm": 1.0931549072265625,
+      "learning_rate": 0.0002,
+      "loss": 0.5732,
+      "step": 2790
+    },
+    {
+      "epoch": 3.4525277435265105,
+      "grad_norm": 0.9228858351707458,
+      "learning_rate": 0.0002,
+      "loss": 0.6093,
+      "step": 2800
+    },
+    {
+      "epoch": 3.4648581997533907,
+      "grad_norm": 1.3182806968688965,
+      "learning_rate": 0.0002,
+      "loss": 0.6089,
+      "step": 2810
+    },
+    {
+      "epoch": 3.4771886559802714,
+      "grad_norm": 0.8366976380348206,
+      "learning_rate": 0.0002,
+      "loss": 0.5665,
+      "step": 2820
+    },
+    {
+      "epoch": 3.4895191122071516,
+      "grad_norm": 0.8067695498466492,
+      "learning_rate": 0.0002,
+      "loss": 0.5666,
+      "step": 2830
+    },
+    {
+      "epoch": 3.5018495684340323,
+      "grad_norm": 1.1163437366485596,
+      "learning_rate": 0.0002,
+      "loss": 0.579,
+      "step": 2840
+    },
+    {
+      "epoch": 3.5141800246609125,
+      "grad_norm": 1.7196556329727173,
+      "learning_rate": 0.0002,
+      "loss": 0.5785,
+      "step": 2850
+    },
+    {
+      "epoch": 3.5265104808877927,
+      "grad_norm": 1.1267012357711792,
+      "learning_rate": 0.0002,
+      "loss": 0.5346,
+      "step": 2860
+    },
+    {
+      "epoch": 3.5388409371146734,
+      "grad_norm": 0.7220137119293213,
+      "learning_rate": 0.0002,
+      "loss": 0.447,
+      "step": 2870
+    },
+    {
+      "epoch": 3.5511713933415536,
+      "grad_norm": 0.914114773273468,
+      "learning_rate": 0.0002,
+      "loss": 0.6099,
+      "step": 2880
+    },
+    {
+      "epoch": 3.563501849568434,
+      "grad_norm": 0.6193503141403198,
+      "learning_rate": 0.0002,
+      "loss": 0.6143,
+      "step": 2890
+    },
+    {
+      "epoch": 3.5758323057953145,
+      "grad_norm": 0.6060135960578918,
+      "learning_rate": 0.0002,
+      "loss": 0.5171,
+      "step": 2900
+    },
+    {
+      "epoch": 3.5881627620221948,
+      "grad_norm": 1.0177327394485474,
+      "learning_rate": 0.0002,
+      "loss": 0.5659,
+      "step": 2910
+    },
+    {
+      "epoch": 3.600493218249075,
+      "grad_norm": 0.5994468331336975,
+      "learning_rate": 0.0002,
+      "loss": 0.5711,
+      "step": 2920
+    },
+    {
+      "epoch": 3.6128236744759556,
+      "grad_norm": 0.7450457215309143,
+      "learning_rate": 0.0002,
+      "loss": 0.6373,
+      "step": 2930
+    },
+    {
+      "epoch": 3.625154130702836,
+      "grad_norm": 0.5825870037078857,
+      "learning_rate": 0.0002,
+      "loss": 0.4933,
+      "step": 2940
+    },
+    {
+      "epoch": 3.6374845869297165,
+      "grad_norm": 0.6289743781089783,
+      "learning_rate": 0.0002,
+      "loss": 0.6016,
+      "step": 2950
+    },
+    {
+      "epoch": 3.6498150431565968,
+      "grad_norm": 0.7801929116249084,
+      "learning_rate": 0.0002,
+      "loss": 0.5507,
+      "step": 2960
+    },
+    {
+      "epoch": 3.6621454993834774,
+      "grad_norm": 1.1206634044647217,
+      "learning_rate": 0.0002,
+      "loss": 0.5695,
+      "step": 2970
+    },
+    {
+      "epoch": 3.6744759556103577,
+      "grad_norm": 0.6738817691802979,
+      "learning_rate": 0.0002,
+      "loss": 0.4985,
+      "step": 2980
+    },
+    {
+      "epoch": 3.686806411837238,
+      "grad_norm": 1.1917344331741333,
+      "learning_rate": 0.0002,
+      "loss": 0.6209,
+      "step": 2990
+    },
+    {
+      "epoch": 3.6991368680641186,
+      "grad_norm": 1.3738657236099243,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 3000
+    },
+    {
+      "epoch": 3.711467324290999,
+      "grad_norm": 0.6642793416976929,
+      "learning_rate": 0.0002,
+      "loss": 0.5467,
+      "step": 3010
+    },
+    {
+      "epoch": 3.723797780517879,
+      "grad_norm": 0.9030995965003967,
+      "learning_rate": 0.0002,
+      "loss": 0.6243,
+      "step": 3020
+    },
+    {
+      "epoch": 3.7361282367447597,
+      "grad_norm": 1.0203914642333984,
+      "learning_rate": 0.0002,
+      "loss": 0.592,
+      "step": 3030
+    },
+    {
+      "epoch": 3.74845869297164,
+      "grad_norm": 0.648394763469696,
+      "learning_rate": 0.0002,
+      "loss": 0.5453,
+      "step": 3040
+    },
+    {
+      "epoch": 3.76078914919852,
+      "grad_norm": 0.6304570436477661,
+      "learning_rate": 0.0002,
+      "loss": 0.498,
+      "step": 3050
+    },
+    {
+      "epoch": 3.773119605425401,
+      "grad_norm": 0.8286601901054382,
+      "learning_rate": 0.0002,
+      "loss": 0.683,
+      "step": 3060
+    },
+    {
+      "epoch": 3.785450061652281,
+      "grad_norm": 0.906444251537323,
+      "learning_rate": 0.0002,
+      "loss": 0.5302,
+      "step": 3070
+    },
+    {
+      "epoch": 3.7977805178791613,
+      "grad_norm": 1.4212149381637573,
+      "learning_rate": 0.0002,
+      "loss": 0.5345,
+      "step": 3080
+    },
+    {
+      "epoch": 3.810110974106042,
+      "grad_norm": 0.7574319839477539,
+      "learning_rate": 0.0002,
+      "loss": 0.6403,
+      "step": 3090
+    },
+    {
+      "epoch": 3.822441430332922,
+      "grad_norm": 0.6534451246261597,
+      "learning_rate": 0.0002,
+      "loss": 0.5756,
+      "step": 3100
+    },
+    {
+      "epoch": 3.834771886559803,
+      "grad_norm": 0.7525447010993958,
+      "learning_rate": 0.0002,
+      "loss": 0.5306,
+      "step": 3110
+    },
+    {
+      "epoch": 3.847102342786683,
+      "grad_norm": 0.6513990759849548,
+      "learning_rate": 0.0002,
+      "loss": 0.5368,
+      "step": 3120
+    },
+    {
+      "epoch": 3.8594327990135637,
+      "grad_norm": 0.7782694697380066,
+      "learning_rate": 0.0002,
+      "loss": 0.5492,
+      "step": 3130
+    },
+    {
+      "epoch": 3.871763255240444,
+      "grad_norm": 0.7998530268669128,
+      "learning_rate": 0.0002,
+      "loss": 0.5727,
+      "step": 3140
+    },
+    {
+      "epoch": 3.884093711467324,
+      "grad_norm": 0.8045353293418884,
+      "learning_rate": 0.0002,
+      "loss": 0.5156,
+      "step": 3150
+    },
+    {
+      "epoch": 3.896424167694205,
+      "grad_norm": 0.8242645263671875,
+      "learning_rate": 0.0002,
+      "loss": 0.5341,
+      "step": 3160
+    },
+    {
+      "epoch": 3.908754623921085,
+      "grad_norm": 0.8302360773086548,
+      "learning_rate": 0.0002,
+      "loss": 0.5563,
+      "step": 3170
+    },
+    {
+      "epoch": 3.9210850801479653,
+      "grad_norm": 0.8653109073638916,
+      "learning_rate": 0.0002,
+      "loss": 0.5793,
+      "step": 3180
+    },
+    {
+      "epoch": 3.933415536374846,
+      "grad_norm": 0.6461338996887207,
+      "learning_rate": 0.0002,
+      "loss": 0.5219,
+      "step": 3190
+    },
+    {
+      "epoch": 3.945745992601726,
+      "grad_norm": 0.8267415165901184,
+      "learning_rate": 0.0002,
+      "loss": 0.6009,
+      "step": 3200
+    },
+    {
+      "epoch": 3.9580764488286064,
+      "grad_norm": 1.1963194608688354,
+      "learning_rate": 0.0002,
+      "loss": 0.5956,
+      "step": 3210
+    },
+    {
+      "epoch": 3.970406905055487,
+      "grad_norm": 0.7101966142654419,
+      "learning_rate": 0.0002,
+      "loss": 0.5692,
+      "step": 3220
+    },
+    {
+      "epoch": 3.9827373612823673,
+      "grad_norm": 0.5931660532951355,
+      "learning_rate": 0.0002,
+      "loss": 0.5471,
+      "step": 3230
+    },
+    {
+      "epoch": 3.995067817509248,
+      "grad_norm": 0.7465988993644714,
+      "learning_rate": 0.0002,
+      "loss": 0.5619,
+      "step": 3240
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4066498279571533,
+      "eval_runtime": 95.7145,
+      "eval_samples_per_second": 4.555,
+      "eval_steps_per_second": 0.575,
+      "step": 3244
+    },
+    {
+      "epoch": 4.007398273736128,
+      "grad_norm": 0.9478800296783447,
+      "learning_rate": 0.0002,
+      "loss": 0.4948,
+      "step": 3250
+    },
+    {
+      "epoch": 4.019728729963009,
+      "grad_norm": 1.207059621810913,
+      "learning_rate": 0.0002,
+      "loss": 0.4129,
+      "step": 3260
+    },
+    {
+      "epoch": 4.032059186189889,
+      "grad_norm": 0.8984074592590332,
+      "learning_rate": 0.0002,
+      "loss": 0.3577,
+      "step": 3270
+    },
+    {
+      "epoch": 4.044389642416769,
+      "grad_norm": 0.8104140758514404,
+      "learning_rate": 0.0002,
+      "loss": 0.3798,
+      "step": 3280
+    },
+    {
+      "epoch": 4.05672009864365,
+      "grad_norm": 1.0875468254089355,
+      "learning_rate": 0.0002,
+      "loss": 0.3657,
+      "step": 3290
+    },
+    {
+      "epoch": 4.06905055487053,
+      "grad_norm": 0.8520309329032898,
+      "learning_rate": 0.0002,
+      "loss": 0.3703,
+      "step": 3300
+    },
+    {
+      "epoch": 4.0813810110974105,
+      "grad_norm": 1.076735496520996,
+      "learning_rate": 0.0002,
+      "loss": 0.3933,
+      "step": 3310
+    },
+    {
+      "epoch": 4.093711467324291,
+      "grad_norm": 0.7789369821548462,
+      "learning_rate": 0.0002,
+      "loss": 0.4422,
+      "step": 3320
+    },
+    {
+      "epoch": 4.106041923551172,
+      "grad_norm": 0.916862964630127,
+      "learning_rate": 0.0002,
+      "loss": 0.4009,
+      "step": 3330
+    },
+    {
+      "epoch": 4.118372379778052,
+      "grad_norm": 1.1251654624938965,
+      "learning_rate": 0.0002,
+      "loss": 0.3934,
+      "step": 3340
+    },
+    {
+      "epoch": 4.130702836004932,
+      "grad_norm": 0.9373420476913452,
+      "learning_rate": 0.0002,
+      "loss": 0.3651,
+      "step": 3350
+    },
+    {
+      "epoch": 4.143033292231813,
+      "grad_norm": 1.03253972530365,
+      "learning_rate": 0.0002,
+      "loss": 0.384,
+      "step": 3360
+    },
+    {
+      "epoch": 4.155363748458693,
+      "grad_norm": 0.947023332118988,
+      "learning_rate": 0.0002,
+      "loss": 0.372,
+      "step": 3370
+    },
+    {
+      "epoch": 4.167694204685573,
+      "grad_norm": 0.8709157109260559,
+      "learning_rate": 0.0002,
+      "loss": 0.4018,
+      "step": 3380
+    },
+    {
+      "epoch": 4.180024660912454,
+      "grad_norm": 0.930983304977417,
+      "learning_rate": 0.0002,
+      "loss": 0.3754,
+      "step": 3390
+    },
+    {
+      "epoch": 4.192355117139334,
+      "grad_norm": 1.092809796333313,
+      "learning_rate": 0.0002,
+      "loss": 0.4248,
+      "step": 3400
+    },
+    {
+      "epoch": 4.2046855733662145,
+      "grad_norm": 0.8454303741455078,
+      "learning_rate": 0.0002,
+      "loss": 0.4453,
+      "step": 3410
+    },
+    {
+      "epoch": 4.217016029593095,
+      "grad_norm": 0.957210123538971,
+      "learning_rate": 0.0002,
+      "loss": 0.4198,
+      "step": 3420
+    },
+    {
+      "epoch": 4.229346485819975,
+      "grad_norm": 0.854333758354187,
+      "learning_rate": 0.0002,
+      "loss": 0.3743,
+      "step": 3430
+    },
+    {
+      "epoch": 4.241676942046856,
+      "grad_norm": 1.0457639694213867,
+      "learning_rate": 0.0002,
+      "loss": 0.4041,
+      "step": 3440
+    },
+    {
+      "epoch": 4.254007398273736,
+      "grad_norm": 0.8972977995872498,
+      "learning_rate": 0.0002,
+      "loss": 0.3817,
+      "step": 3450
+    },
+    {
+      "epoch": 4.266337854500616,
+      "grad_norm": 1.0438238382339478,
+      "learning_rate": 0.0002,
+      "loss": 0.4445,
+      "step": 3460
+    },
+    {
+      "epoch": 4.278668310727497,
+      "grad_norm": 0.7000405192375183,
+      "learning_rate": 0.0002,
+      "loss": 0.4078,
+      "step": 3470
+    },
+    {
+      "epoch": 4.290998766954377,
+      "grad_norm": 1.0451240539550781,
+      "learning_rate": 0.0002,
+      "loss": 0.3718,
+      "step": 3480
+    },
+    {
+      "epoch": 4.303329223181258,
+      "grad_norm": 1.3339767456054688,
+      "learning_rate": 0.0002,
+      "loss": 0.4506,
+      "step": 3490
+    },
+    {
+      "epoch": 4.315659679408138,
+      "grad_norm": 0.7503946423530579,
+      "learning_rate": 0.0002,
+      "loss": 0.3999,
+      "step": 3500
+    },
+    {
+      "epoch": 4.3279901356350186,
+      "grad_norm": 0.8443584442138672,
+      "learning_rate": 0.0002,
+      "loss": 0.4503,
+      "step": 3510
+    },
+    {
+      "epoch": 4.340320591861899,
+      "grad_norm": 1.1681201457977295,
+      "learning_rate": 0.0002,
+      "loss": 0.3793,
+      "step": 3520
+    },
+    {
+      "epoch": 4.352651048088779,
+      "grad_norm": 1.078883171081543,
+      "learning_rate": 0.0002,
+      "loss": 0.4462,
+      "step": 3530
+    },
+    {
+      "epoch": 4.36498150431566,
+      "grad_norm": 0.6894834041595459,
+      "learning_rate": 0.0002,
+      "loss": 0.4216,
+      "step": 3540
+    },
+    {
+      "epoch": 4.37731196054254,
+      "grad_norm": 0.7059480547904968,
+      "learning_rate": 0.0002,
+      "loss": 0.4315,
+      "step": 3550
+    },
+    {
+      "epoch": 4.38964241676942,
+      "grad_norm": 1.1807256937026978,
+      "learning_rate": 0.0002,
+      "loss": 0.3821,
+      "step": 3560
+    },
+    {
+      "epoch": 4.401972872996301,
+      "grad_norm": 0.8341359496116638,
+      "learning_rate": 0.0002,
+      "loss": 0.4192,
+      "step": 3570
+    },
+    {
+      "epoch": 4.4143033292231815,
+      "grad_norm": 1.0273033380508423,
+      "learning_rate": 0.0002,
+      "loss": 0.4123,
+      "step": 3580
+    },
+    {
+      "epoch": 4.426633785450061,
+      "grad_norm": 0.6916454434394836,
+      "learning_rate": 0.0002,
+      "loss": 0.5018,
+      "step": 3590
+    },
+    {
+      "epoch": 4.438964241676942,
+      "grad_norm": 0.8210113644599915,
+      "learning_rate": 0.0002,
+      "loss": 0.3909,
+      "step": 3600
+    },
+    {
+      "epoch": 4.451294697903823,
+      "grad_norm": 1.0309500694274902,
+      "learning_rate": 0.0002,
+      "loss": 0.3893,
+      "step": 3610
+    },
+    {
+      "epoch": 4.463625154130703,
+      "grad_norm": 0.8847399353981018,
+      "learning_rate": 0.0002,
+      "loss": 0.3902,
+      "step": 3620
+    },
+    {
+      "epoch": 4.475955610357583,
+      "grad_norm": 1.668636679649353,
+      "learning_rate": 0.0002,
+      "loss": 0.4198,
+      "step": 3630
+    },
+    {
+      "epoch": 4.488286066584464,
+      "grad_norm": 1.3087958097457886,
+      "learning_rate": 0.0002,
+      "loss": 0.4075,
+      "step": 3640
+    },
+    {
+      "epoch": 4.500616522811344,
+      "grad_norm": 0.837852418422699,
+      "learning_rate": 0.0002,
+      "loss": 0.4294,
+      "step": 3650
+    },
+    {
+      "epoch": 4.512946979038224,
+      "grad_norm": 9.7662353515625,
+      "learning_rate": 0.0002,
+      "loss": 0.4053,
+      "step": 3660
+    },
+    {
+      "epoch": 4.525277435265105,
+      "grad_norm": 1.125719428062439,
+      "learning_rate": 0.0002,
+      "loss": 0.4033,
+      "step": 3670
+    },
+    {
+      "epoch": 4.5376078914919855,
+      "grad_norm": 0.7755377292633057,
+      "learning_rate": 0.0002,
+      "loss": 0.4566,
+      "step": 3680
+    },
+    {
+      "epoch": 4.549938347718865,
+      "grad_norm": 0.7185089588165283,
+      "learning_rate": 0.0002,
+      "loss": 0.4415,
+      "step": 3690
+    },
+    {
+      "epoch": 4.562268803945746,
+      "grad_norm": 1.182063102722168,
+      "learning_rate": 0.0002,
+      "loss": 0.4616,
+      "step": 3700
+    },
+    {
+      "epoch": 4.574599260172627,
+      "grad_norm": 1.001197338104248,
+      "learning_rate": 0.0002,
+      "loss": 0.4572,
+      "step": 3710
+    },
+    {
+      "epoch": 4.586929716399506,
+      "grad_norm": 0.9705429077148438,
+      "learning_rate": 0.0002,
+      "loss": 0.4493,
+      "step": 3720
+    },
+    {
+      "epoch": 4.599260172626387,
+      "grad_norm": 0.7136746048927307,
+      "learning_rate": 0.0002,
+      "loss": 0.42,
+      "step": 3730
+    },
+    {
+      "epoch": 4.611590628853268,
+      "grad_norm": 1.0004864931106567,
+      "learning_rate": 0.0002,
+      "loss": 0.3757,
+      "step": 3740
+    },
+    {
+      "epoch": 4.623921085080148,
+      "grad_norm": 1.3193715810775757,
+      "learning_rate": 0.0002,
+      "loss": 0.4418,
+      "step": 3750
+    },
+    {
+      "epoch": 4.636251541307028,
+      "grad_norm": 0.6945042014122009,
+      "learning_rate": 0.0002,
+      "loss": 0.4572,
+      "step": 3760
+    },
+    {
+      "epoch": 4.648581997533909,
+      "grad_norm": 0.8903936743736267,
+      "learning_rate": 0.0002,
+      "loss": 0.4255,
+      "step": 3770
+    },
+    {
+      "epoch": 4.660912453760789,
+      "grad_norm": 0.7960889339447021,
+      "learning_rate": 0.0002,
+      "loss": 0.3582,
+      "step": 3780
+    },
+    {
+      "epoch": 4.673242909987669,
+      "grad_norm": 1.0439172983169556,
+      "learning_rate": 0.0002,
+      "loss": 0.3864,
+      "step": 3790
+    },
+    {
+      "epoch": 4.68557336621455,
+      "grad_norm": 1.4546219110488892,
+      "learning_rate": 0.0002,
+      "loss": 0.4378,
+      "step": 3800
+    },
+    {
+      "epoch": 4.697903822441431,
+      "grad_norm": 0.8194343447685242,
+      "learning_rate": 0.0002,
+      "loss": 0.4191,
+      "step": 3810
+    },
+    {
+      "epoch": 4.7102342786683105,
+      "grad_norm": 1.0727602243423462,
+      "learning_rate": 0.0002,
+      "loss": 0.4473,
+      "step": 3820
+    },
+    {
+      "epoch": 4.722564734895191,
+      "grad_norm": 0.7785195708274841,
+      "learning_rate": 0.0002,
+      "loss": 0.4021,
+      "step": 3830
+    },
+    {
+      "epoch": 4.734895191122072,
+      "grad_norm": 0.846783459186554,
+      "learning_rate": 0.0002,
+      "loss": 0.4252,
+      "step": 3840
+    },
+    {
+      "epoch": 4.747225647348952,
+      "grad_norm": 1.0481648445129395,
+      "learning_rate": 0.0002,
+      "loss": 0.4647,
+      "step": 3850
+    },
+    {
+      "epoch": 4.759556103575832,
+      "grad_norm": 0.7324008941650391,
+      "learning_rate": 0.0002,
+      "loss": 0.4944,
+      "step": 3860
+    },
+    {
+      "epoch": 4.771886559802713,
+      "grad_norm": 1.06382417678833,
+      "learning_rate": 0.0002,
+      "loss": 0.3831,
+      "step": 3870
+    },
+    {
+      "epoch": 4.784217016029594,
+      "grad_norm": 0.9851241111755371,
+      "learning_rate": 0.0002,
+      "loss": 0.3934,
+      "step": 3880
+    },
+    {
+      "epoch": 4.796547472256473,
+      "grad_norm": 0.8215277791023254,
+      "learning_rate": 0.0002,
+      "loss": 0.5172,
+      "step": 3890
+    },
+    {
+      "epoch": 4.808877928483354,
+      "grad_norm": 0.9901723861694336,
+      "learning_rate": 0.0002,
+      "loss": 0.4437,
+      "step": 3900
+    },
+    {
+      "epoch": 4.821208384710234,
+      "grad_norm": 0.9149112701416016,
+      "learning_rate": 0.0002,
+      "loss": 0.4673,
+      "step": 3910
+    },
+    {
+      "epoch": 4.8335388409371145,
+      "grad_norm": 0.9772973656654358,
+      "learning_rate": 0.0002,
+      "loss": 0.4295,
+      "step": 3920
+    },
+    {
+      "epoch": 4.845869297163995,
+      "grad_norm": 0.8889636397361755,
+      "learning_rate": 0.0002,
+      "loss": 0.4346,
+      "step": 3930
+    },
+    {
+      "epoch": 4.858199753390876,
+      "grad_norm": 1.3032807111740112,
+      "learning_rate": 0.0002,
+      "loss": 0.421,
+      "step": 3940
+    },
+    {
+      "epoch": 4.870530209617756,
+      "grad_norm": 0.8575899600982666,
+      "learning_rate": 0.0002,
+      "loss": 0.434,
+      "step": 3950
+    },
+    {
+      "epoch": 4.882860665844636,
+      "grad_norm": 1.04326331615448,
+      "learning_rate": 0.0002,
+      "loss": 0.4295,
+      "step": 3960
+    },
+    {
+      "epoch": 4.895191122071517,
+      "grad_norm": 1.041210651397705,
+      "learning_rate": 0.0002,
+      "loss": 0.3633,
+      "step": 3970
+    },
+    {
+      "epoch": 4.907521578298397,
+      "grad_norm": 0.9113056063652039,
+      "learning_rate": 0.0002,
+      "loss": 0.4104,
+      "step": 3980
+    },
+    {
+      "epoch": 4.919852034525277,
+      "grad_norm": 1.019347906112671,
+      "learning_rate": 0.0002,
+      "loss": 0.4496,
+      "step": 3990
+    },
+    {
+      "epoch": 4.932182490752158,
+      "grad_norm": 0.7709218859672546,
+      "learning_rate": 0.0002,
+      "loss": 0.457,
+      "step": 4000
+    },
+    {
+      "epoch": 4.944512946979038,
+      "grad_norm": 0.8891775608062744,
+      "learning_rate": 0.0002,
+      "loss": 0.4697,
+      "step": 4010
+    },
+    {
+      "epoch": 4.9568434032059185,
+      "grad_norm": 1.0396920442581177,
+      "learning_rate": 0.0002,
+      "loss": 0.4436,
+      "step": 4020
+    },
+    {
+      "epoch": 4.969173859432799,
+      "grad_norm": 0.9239833354949951,
+      "learning_rate": 0.0002,
+      "loss": 0.4251,
+      "step": 4030
+    },
+    {
+      "epoch": 4.981504315659679,
+      "grad_norm": 1.801400065422058,
+      "learning_rate": 0.0002,
+      "loss": 0.5049,
+      "step": 4040
+    },
+    {
+      "epoch": 4.99383477188656,
+      "grad_norm": 0.6194164752960205,
+      "learning_rate": 0.0002,
+      "loss": 0.4481,
+      "step": 4050
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.544758915901184,
+      "eval_runtime": 96.2573,
+      "eval_samples_per_second": 4.53,
+      "eval_steps_per_second": 0.571,
+      "step": 4055
+    },
+    {
+      "epoch": 5.00616522811344,
+      "grad_norm": 0.9918256998062134,
+      "learning_rate": 0.0002,
+      "loss": 0.3774,
+      "step": 4060
+    },
+    {
+      "epoch": 5.018495684340321,
+      "grad_norm": 1.4851351976394653,
+      "learning_rate": 0.0002,
+      "loss": 0.2887,
+      "step": 4070
+    },
+    {
+      "epoch": 5.030826140567201,
+      "grad_norm": 0.9237686395645142,
+      "learning_rate": 0.0002,
+      "loss": 0.2454,
+      "step": 4080
+    },
+    {
+      "epoch": 5.0431565967940815,
+      "grad_norm": 1.2180852890014648,
+      "learning_rate": 0.0002,
+      "loss": 0.3072,
+      "step": 4090
+    },
+    {
+      "epoch": 5.055487053020962,
+      "grad_norm": 1.1247979402542114,
+      "learning_rate": 0.0002,
+      "loss": 0.282,
+      "step": 4100
+    },
+    {
+      "epoch": 5.067817509247842,
+      "grad_norm": 1.2969884872436523,
+      "learning_rate": 0.0002,
+      "loss": 0.3108,
+      "step": 4110
+    },
+    {
+      "epoch": 5.080147965474723,
+      "grad_norm": 1.0183063745498657,
+      "learning_rate": 0.0002,
+      "loss": 0.2858,
+      "step": 4120
+    },
+    {
+      "epoch": 5.092478421701603,
+      "grad_norm": 1.121330738067627,
+      "learning_rate": 0.0002,
+      "loss": 0.295,
+      "step": 4130
+    },
+    {
+      "epoch": 5.104808877928483,
+      "grad_norm": 1.0748186111450195,
+      "learning_rate": 0.0002,
+      "loss": 0.2697,
+      "step": 4140
+    },
+    {
+      "epoch": 5.117139334155364,
+      "grad_norm": 1.103474736213684,
+      "learning_rate": 0.0002,
+      "loss": 0.3414,
+      "step": 4150
+    },
+    {
+      "epoch": 5.129469790382244,
+      "grad_norm": 1.2251166105270386,
+      "learning_rate": 0.0002,
+      "loss": 0.305,
+      "step": 4160
+    },
+    {
+      "epoch": 5.141800246609124,
+      "grad_norm": 0.920898973941803,
+      "learning_rate": 0.0002,
+      "loss": 0.3131,
+      "step": 4170
+    },
+    {
+      "epoch": 5.154130702836005,
+      "grad_norm": 1.327542781829834,
+      "learning_rate": 0.0002,
+      "loss": 0.281,
+      "step": 4180
+    },
+    {
+      "epoch": 5.1664611590628855,
+      "grad_norm": 1.0677192211151123,
+      "learning_rate": 0.0002,
+      "loss": 0.3214,
+      "step": 4190
+    },
+    {
+      "epoch": 5.178791615289766,
+      "grad_norm": 0.897241473197937,
+      "learning_rate": 0.0002,
+      "loss": 0.2863,
+      "step": 4200
+    },
+    {
+      "epoch": 5.191122071516646,
+      "grad_norm": 0.977457582950592,
+      "learning_rate": 0.0002,
+      "loss": 0.2967,
+      "step": 4210
+    },
+    {
+      "epoch": 5.203452527743527,
+      "grad_norm": 1.4115267992019653,
+      "learning_rate": 0.0002,
+      "loss": 0.3032,
+      "step": 4220
+    },
+    {
+      "epoch": 5.215782983970407,
+      "grad_norm": 1.097743034362793,
+      "learning_rate": 0.0002,
+      "loss": 0.3279,
+      "step": 4230
+    },
+    {
+      "epoch": 5.228113440197287,
+      "grad_norm": 1.1095269918441772,
+      "learning_rate": 0.0002,
+      "loss": 0.293,
+      "step": 4240
+    },
+    {
+      "epoch": 5.240443896424168,
+      "grad_norm": 1.3785479068756104,
+      "learning_rate": 0.0002,
+      "loss": 0.3544,
+      "step": 4250
+    },
+    {
+      "epoch": 5.252774352651048,
+      "grad_norm": 1.0298776626586914,
+      "learning_rate": 0.0002,
+      "loss": 0.3118,
+      "step": 4260
+    },
+    {
+      "epoch": 5.265104808877928,
+      "grad_norm": 1.1592111587524414,
+      "learning_rate": 0.0002,
+      "loss": 0.296,
+      "step": 4270
+    },
+    {
+      "epoch": 5.277435265104809,
+      "grad_norm": 1.2355743646621704,
+      "learning_rate": 0.0002,
+      "loss": 0.2878,
+      "step": 4280
+    },
+    {
+      "epoch": 5.2897657213316895,
+      "grad_norm": 0.8543112874031067,
+      "learning_rate": 0.0002,
+      "loss": 0.3085,
+      "step": 4290
+    },
+    {
+      "epoch": 5.302096177558569,
+      "grad_norm": 1.2953215837478638,
+      "learning_rate": 0.0002,
+      "loss": 0.3108,
+      "step": 4300
+    },
+    {
+      "epoch": 5.31442663378545,
+      "grad_norm": 1.1001787185668945,
+      "learning_rate": 0.0002,
+      "loss": 0.2912,
+      "step": 4310
+    },
+    {
+      "epoch": 5.326757090012331,
+      "grad_norm": 0.7476816773414612,
+      "learning_rate": 0.0002,
+      "loss": 0.3003,
+      "step": 4320
+    },
+    {
+      "epoch": 5.3390875462392104,
+      "grad_norm": 0.8195574283599854,
+      "learning_rate": 0.0002,
+      "loss": 0.3247,
+      "step": 4330
+    },
+    {
+      "epoch": 5.351418002466091,
+      "grad_norm": 0.9490262866020203,
+      "learning_rate": 0.0002,
+      "loss": 0.3035,
+      "step": 4340
+    },
+    {
+      "epoch": 5.363748458692972,
+      "grad_norm": 1.2201412916183472,
+      "learning_rate": 0.0002,
+      "loss": 0.2846,
+      "step": 4350
+    },
+    {
+      "epoch": 5.376078914919852,
+      "grad_norm": 1.0311479568481445,
+      "learning_rate": 0.0002,
+      "loss": 0.2644,
+      "step": 4360
+    },
+    {
+      "epoch": 5.388409371146732,
+      "grad_norm": 1.2097488641738892,
+      "learning_rate": 0.0002,
+      "loss": 0.3104,
+      "step": 4370
+    },
+    {
+      "epoch": 5.400739827373613,
+      "grad_norm": 1.140942096710205,
+      "learning_rate": 0.0002,
+      "loss": 0.2977,
+      "step": 4380
+    },
+    {
+      "epoch": 5.413070283600494,
+      "grad_norm": 0.8091890811920166,
+      "learning_rate": 0.0002,
+      "loss": 0.2975,
+      "step": 4390
+    },
+    {
+      "epoch": 5.425400739827373,
+      "grad_norm": 1.4467964172363281,
+      "learning_rate": 0.0002,
+      "loss": 0.3727,
+      "step": 4400
+    },
+    {
+      "epoch": 5.437731196054254,
+      "grad_norm": 1.0836058855056763,
+      "learning_rate": 0.0002,
+      "loss": 0.2979,
+      "step": 4410
+    },
+    {
+      "epoch": 5.450061652281135,
+      "grad_norm": 1.0515433549880981,
+      "learning_rate": 0.0002,
+      "loss": 0.2601,
+      "step": 4420
+    },
+    {
+      "epoch": 5.4623921085080145,
+      "grad_norm": 0.9603073000907898,
+      "learning_rate": 0.0002,
+      "loss": 0.315,
+      "step": 4430
+    },
+    {
+      "epoch": 5.474722564734895,
+      "grad_norm": 1.234609842300415,
+      "learning_rate": 0.0002,
+      "loss": 0.3166,
+      "step": 4440
+    },
+    {
+      "epoch": 5.487053020961776,
+      "grad_norm": 0.8881428837776184,
+      "learning_rate": 0.0002,
+      "loss": 0.3142,
+      "step": 4450
+    },
+    {
+      "epoch": 5.499383477188656,
+      "grad_norm": 1.1817275285720825,
+      "learning_rate": 0.0002,
+      "loss": 0.3725,
+      "step": 4460
+    },
+    {
+      "epoch": 5.511713933415536,
+      "grad_norm": 1.213993787765503,
+      "learning_rate": 0.0002,
+      "loss": 0.2944,
+      "step": 4470
+    },
+    {
+      "epoch": 5.524044389642417,
+      "grad_norm": 1.0501725673675537,
+      "learning_rate": 0.0002,
+      "loss": 0.3136,
+      "step": 4480
+    },
+    {
+      "epoch": 5.536374845869297,
+      "grad_norm": 1.5061579942703247,
+      "learning_rate": 0.0002,
+      "loss": 0.306,
+      "step": 4490
+    },
+    {
+      "epoch": 5.548705302096177,
+      "grad_norm": 1.1171475648880005,
+      "learning_rate": 0.0002,
+      "loss": 0.3226,
+      "step": 4500
+    },
+    {
+      "epoch": 5.561035758323058,
+      "grad_norm": 1.1147594451904297,
+      "learning_rate": 0.0002,
+      "loss": 0.3624,
+      "step": 4510
+    },
+    {
+      "epoch": 5.573366214549939,
+      "grad_norm": 1.0600544214248657,
+      "learning_rate": 0.0002,
+      "loss": 0.3435,
+      "step": 4520
+    },
+    {
+      "epoch": 5.5856966707768185,
+      "grad_norm": 1.247870922088623,
+      "learning_rate": 0.0002,
+      "loss": 0.3268,
+      "step": 4530
+    },
+    {
+      "epoch": 5.598027127003699,
+      "grad_norm": 0.9425561428070068,
+      "learning_rate": 0.0002,
+      "loss": 0.3168,
+      "step": 4540
+    },
+    {
+      "epoch": 5.61035758323058,
+      "grad_norm": 1.1111550331115723,
+      "learning_rate": 0.0002,
+      "loss": 0.3119,
+      "step": 4550
+    },
+    {
+      "epoch": 5.62268803945746,
+      "grad_norm": 1.743268609046936,
+      "learning_rate": 0.0002,
+      "loss": 0.3389,
+      "step": 4560
+    },
+    {
+      "epoch": 5.63501849568434,
+      "grad_norm": 1.3522645235061646,
+      "learning_rate": 0.0002,
+      "loss": 0.31,
+      "step": 4570
+    },
+    {
+      "epoch": 5.647348951911221,
+      "grad_norm": 0.7354221343994141,
+      "learning_rate": 0.0002,
+      "loss": 0.3121,
+      "step": 4580
+    },
+    {
+      "epoch": 5.659679408138101,
+      "grad_norm": 1.050743818283081,
+      "learning_rate": 0.0002,
+      "loss": 0.3693,
+      "step": 4590
+    },
+    {
+      "epoch": 5.6720098643649814,
+      "grad_norm": 1.1302396059036255,
+      "learning_rate": 0.0002,
+      "loss": 0.3449,
+      "step": 4600
+    },
+    {
+      "epoch": 5.684340320591862,
+      "grad_norm": 0.8774183392524719,
+      "learning_rate": 0.0002,
+      "loss": 0.3211,
+      "step": 4610
+    },
+    {
+      "epoch": 5.696670776818742,
+      "grad_norm": 1.090781569480896,
+      "learning_rate": 0.0002,
+      "loss": 0.3501,
+      "step": 4620
+    },
+    {
+      "epoch": 5.709001233045623,
+      "grad_norm": 0.9177733063697815,
+      "learning_rate": 0.0002,
+      "loss": 0.3211,
+      "step": 4630
+    },
+    {
+      "epoch": 5.721331689272503,
+      "grad_norm": 0.9985341429710388,
+      "learning_rate": 0.0002,
+      "loss": 0.3439,
+      "step": 4640
+    },
+    {
+      "epoch": 5.733662145499384,
+      "grad_norm": 1.0230613946914673,
+      "learning_rate": 0.0002,
+      "loss": 0.3323,
+      "step": 4650
+    },
+    {
+      "epoch": 5.745992601726264,
+      "grad_norm": 0.944656252861023,
+      "learning_rate": 0.0002,
+      "loss": 0.3525,
+      "step": 4660
+    },
+    {
+      "epoch": 5.758323057953144,
+      "grad_norm": 0.8162471652030945,
+      "learning_rate": 0.0002,
+      "loss": 0.3191,
+      "step": 4670
+    },
+    {
+      "epoch": 5.770653514180025,
+      "grad_norm": 1.0500398874282837,
+      "learning_rate": 0.0002,
+      "loss": 0.4011,
+      "step": 4680
+    },
+    {
+      "epoch": 5.782983970406905,
+      "grad_norm": 0.9487981796264648,
+      "learning_rate": 0.0002,
+      "loss": 0.3452,
+      "step": 4690
+    },
+    {
+      "epoch": 5.7953144266337855,
+      "grad_norm": 1.1856540441513062,
+      "learning_rate": 0.0002,
+      "loss": 0.2942,
+      "step": 4700
+    },
+    {
+      "epoch": 5.807644882860666,
+      "grad_norm": 1.2583396434783936,
+      "learning_rate": 0.0002,
+      "loss": 0.3107,
+      "step": 4710
+    },
+    {
+      "epoch": 5.819975339087546,
+      "grad_norm": 1.2532602548599243,
+      "learning_rate": 0.0002,
+      "loss": 0.3223,
+      "step": 4720
+    },
+    {
+      "epoch": 5.832305795314427,
+      "grad_norm": 1.115236520767212,
+      "learning_rate": 0.0002,
+      "loss": 0.3253,
+      "step": 4730
+    },
+    {
+      "epoch": 5.844636251541307,
+      "grad_norm": 1.2245537042617798,
+      "learning_rate": 0.0002,
+      "loss": 0.3539,
+      "step": 4740
+    },
+    {
+      "epoch": 5.856966707768187,
+      "grad_norm": 1.1964094638824463,
+      "learning_rate": 0.0002,
+      "loss": 0.3171,
+      "step": 4750
+    },
+    {
+      "epoch": 5.869297163995068,
+      "grad_norm": 1.0833805799484253,
+      "learning_rate": 0.0002,
+      "loss": 0.3623,
+      "step": 4760
+    },
+    {
+      "epoch": 5.881627620221948,
+      "grad_norm": 1.0694046020507812,
+      "learning_rate": 0.0002,
+      "loss": 0.3511,
+      "step": 4770
+    },
+    {
+      "epoch": 5.893958076448829,
+      "grad_norm": 0.9947936534881592,
+      "learning_rate": 0.0002,
+      "loss": 0.3266,
+      "step": 4780
+    },
+    {
+      "epoch": 5.906288532675709,
+      "grad_norm": 1.175716519355774,
+      "learning_rate": 0.0002,
+      "loss": 0.316,
+      "step": 4790
+    },
+    {
+      "epoch": 5.9186189889025895,
+      "grad_norm": 0.7717352509498596,
+      "learning_rate": 0.0002,
+      "loss": 0.3609,
+      "step": 4800
+    },
+    {
+      "epoch": 5.930949445129469,
+      "grad_norm": 1.2906442880630493,
+      "learning_rate": 0.0002,
+      "loss": 0.3058,
+      "step": 4810
+    },
+    {
+      "epoch": 5.94327990135635,
+      "grad_norm": 1.2416284084320068,
+      "learning_rate": 0.0002,
+      "loss": 0.3187,
+      "step": 4820
+    },
+    {
+      "epoch": 5.955610357583231,
+      "grad_norm": 1.3066956996917725,
+      "learning_rate": 0.0002,
+      "loss": 0.337,
+      "step": 4830
+    },
+    {
+      "epoch": 5.967940813810111,
+      "grad_norm": 1.0872026681900024,
+      "learning_rate": 0.0002,
+      "loss": 0.3167,
+      "step": 4840
+    },
+    {
+      "epoch": 5.980271270036991,
+      "grad_norm": 1.1941101551055908,
+      "learning_rate": 0.0002,
+      "loss": 0.3262,
+      "step": 4850
+    },
+    {
+      "epoch": 5.992601726263872,
+      "grad_norm": 1.1126095056533813,
+      "learning_rate": 0.0002,
+      "loss": 0.3234,
+      "step": 4860
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.748323917388916,
+      "eval_runtime": 97.7488,
+      "eval_samples_per_second": 4.46,
+      "eval_steps_per_second": 0.563,
+      "step": 4866
+    },
+    {
+      "epoch": 6.0049321824907524,
+      "grad_norm": 1.3631165027618408,
+      "learning_rate": 0.0002,
+      "loss": 0.2774,
+      "step": 4870
+    },
+    {
+      "epoch": 6.017262638717632,
+      "grad_norm": 1.2631664276123047,
+      "learning_rate": 0.0002,
+      "loss": 0.2399,
+      "step": 4880
+    },
+    {
+      "epoch": 6.029593094944513,
+      "grad_norm": 0.7073080539703369,
+      "learning_rate": 0.0002,
+      "loss": 0.2177,
+      "step": 4890
+    },
+    {
+      "epoch": 6.041923551171394,
+      "grad_norm": 0.7856091856956482,
+      "learning_rate": 0.0002,
+      "loss": 0.215,
+      "step": 4900
+    },
+    {
+      "epoch": 6.054254007398273,
+      "grad_norm": 1.145540475845337,
+      "learning_rate": 0.0002,
+      "loss": 0.1999,
+      "step": 4910
+    },
+    {
+      "epoch": 6.066584463625154,
+      "grad_norm": 1.1742334365844727,
+      "learning_rate": 0.0002,
+      "loss": 0.2084,
+      "step": 4920
+    },
+    {
+      "epoch": 6.078914919852035,
+      "grad_norm": 0.8043994903564453,
+      "learning_rate": 0.0002,
+      "loss": 0.2342,
+      "step": 4930
+    },
+    {
+      "epoch": 6.0912453760789145,
+      "grad_norm": 1.1877652406692505,
+      "learning_rate": 0.0002,
+      "loss": 0.2454,
+      "step": 4940
+    },
+    {
+      "epoch": 6.103575832305795,
+      "grad_norm": 0.7624953985214233,
+      "learning_rate": 0.0002,
+      "loss": 0.1908,
+      "step": 4950
+    },
+    {
+      "epoch": 6.115906288532676,
+      "grad_norm": 1.0403119325637817,
+      "learning_rate": 0.0002,
+      "loss": 0.2254,
+      "step": 4960
+    },
+    {
+      "epoch": 6.1282367447595565,
+      "grad_norm": 1.2040252685546875,
+      "learning_rate": 0.0002,
+      "loss": 0.2274,
+      "step": 4970
+    },
+    {
+      "epoch": 6.140567200986436,
+      "grad_norm": 0.6242546439170837,
+      "learning_rate": 0.0002,
+      "loss": 0.2199,
+      "step": 4980
+    },
+    {
+      "epoch": 6.152897657213317,
+      "grad_norm": 1.1394767761230469,
+      "learning_rate": 0.0002,
+      "loss": 0.27,
+      "step": 4990
+    },
+    {
+      "epoch": 6.165228113440198,
+      "grad_norm": 1.3760257959365845,
+      "learning_rate": 0.0002,
+      "loss": 0.2377,
+      "step": 5000
+    },
+    {
+      "epoch": 6.177558569667077,
+      "grad_norm": 1.0707697868347168,
+      "learning_rate": 0.0002,
+      "loss": 0.2331,
+      "step": 5010
+    },
+    {
+      "epoch": 6.189889025893958,
+      "grad_norm": 1.288072109222412,
+      "learning_rate": 0.0002,
+      "loss": 0.2311,
+      "step": 5020
+    },
+    {
+      "epoch": 6.202219482120839,
+      "grad_norm": 1.1479463577270508,
+      "learning_rate": 0.0002,
+      "loss": 0.2276,
+      "step": 5030
+    },
+    {
+      "epoch": 6.2145499383477185,
+      "grad_norm": 0.905891478061676,
+      "learning_rate": 0.0002,
+      "loss": 0.2294,
+      "step": 5040
+    },
+    {
+      "epoch": 6.226880394574599,
+      "grad_norm": 1.0354516506195068,
+      "learning_rate": 0.0002,
+      "loss": 0.2575,
+      "step": 5050
+    },
+    {
+      "epoch": 6.23921085080148,
+      "grad_norm": 1.312671184539795,
+      "learning_rate": 0.0002,
+      "loss": 0.2259,
+      "step": 5060
+    },
+    {
+      "epoch": 6.25154130702836,
+      "grad_norm": 1.614709734916687,
+      "learning_rate": 0.0002,
+      "loss": 0.2281,
+      "step": 5070
+    },
+    {
+      "epoch": 6.26387176325524,
+      "grad_norm": 1.0864229202270508,
+      "learning_rate": 0.0002,
+      "loss": 0.2388,
+      "step": 5080
+    },
+    {
+      "epoch": 6.276202219482121,
+      "grad_norm": 1.0401391983032227,
+      "learning_rate": 0.0002,
+      "loss": 0.2014,
+      "step": 5090
+    },
+    {
+      "epoch": 6.288532675709002,
+      "grad_norm": 1.2187728881835938,
+      "learning_rate": 0.0002,
+      "loss": 0.2419,
+      "step": 5100
+    },
+    {
+      "epoch": 6.300863131935881,
+      "grad_norm": 0.9474364519119263,
+      "learning_rate": 0.0002,
+      "loss": 0.2144,
+      "step": 5110
+    },
+    {
+      "epoch": 6.313193588162762,
+      "grad_norm": 1.1228716373443604,
+      "learning_rate": 0.0002,
+      "loss": 0.238,
+      "step": 5120
+    },
+    {
+      "epoch": 6.325524044389643,
+      "grad_norm": 0.9294499754905701,
+      "learning_rate": 0.0002,
+      "loss": 0.2556,
+      "step": 5130
+    },
+    {
+      "epoch": 6.337854500616523,
+      "grad_norm": 1.0521048307418823,
+      "learning_rate": 0.0002,
+      "loss": 0.2384,
+      "step": 5140
+    },
+    {
+      "epoch": 6.350184956843403,
+      "grad_norm": 1.2406890392303467,
+      "learning_rate": 0.0002,
+      "loss": 0.2444,
+      "step": 5150
+    },
+    {
+      "epoch": 6.362515413070284,
+      "grad_norm": 1.2972853183746338,
+      "learning_rate": 0.0002,
+      "loss": 0.2301,
+      "step": 5160
+    },
+    {
+      "epoch": 6.374845869297164,
+      "grad_norm": 0.8772842288017273,
+      "learning_rate": 0.0002,
+      "loss": 0.2574,
+      "step": 5170
+    },
+    {
+      "epoch": 6.387176325524044,
+      "grad_norm": 1.050349473953247,
+      "learning_rate": 0.0002,
+      "loss": 0.2337,
+      "step": 5180
+    },
+    {
+      "epoch": 6.399506781750925,
+      "grad_norm": 0.9432134032249451,
+      "learning_rate": 0.0002,
+      "loss": 0.2593,
+      "step": 5190
+    },
+    {
+      "epoch": 6.411837237977805,
+      "grad_norm": 1.11045241355896,
+      "learning_rate": 0.0002,
+      "loss": 0.2546,
+      "step": 5200
+    },
+    {
+      "epoch": 6.4241676942046855,
+      "grad_norm": 1.117530345916748,
+      "learning_rate": 0.0002,
+      "loss": 0.268,
+      "step": 5210
+    },
+    {
+      "epoch": 6.436498150431566,
+      "grad_norm": 1.4194035530090332,
+      "learning_rate": 0.0002,
+      "loss": 0.25,
+      "step": 5220
+    },
+    {
+      "epoch": 6.448828606658447,
+      "grad_norm": 1.063950777053833,
+      "learning_rate": 0.0002,
+      "loss": 0.2335,
+      "step": 5230
+    },
+    {
+      "epoch": 6.461159062885327,
+      "grad_norm": 1.2946349382400513,
+      "learning_rate": 0.0002,
+      "loss": 0.2299,
+      "step": 5240
+    },
+    {
+      "epoch": 6.473489519112207,
+      "grad_norm": 1.5237880945205688,
+      "learning_rate": 0.0002,
+      "loss": 0.242,
+      "step": 5250
+    },
+    {
+      "epoch": 6.485819975339088,
+      "grad_norm": 1.1915720701217651,
+      "learning_rate": 0.0002,
+      "loss": 0.255,
+      "step": 5260
+    },
+    {
+      "epoch": 6.498150431565968,
+      "grad_norm": 1.0779626369476318,
+      "learning_rate": 0.0002,
+      "loss": 0.2357,
+      "step": 5270
+    },
+    {
+      "epoch": 6.510480887792848,
+      "grad_norm": 0.8255738019943237,
+      "learning_rate": 0.0002,
+      "loss": 0.2476,
+      "step": 5280
+    },
+    {
+      "epoch": 6.522811344019729,
+      "grad_norm": 1.275174856185913,
+      "learning_rate": 0.0002,
+      "loss": 0.267,
+      "step": 5290
+    },
+    {
+      "epoch": 6.535141800246609,
+      "grad_norm": 1.0878815650939941,
+      "learning_rate": 0.0002,
+      "loss": 0.2217,
+      "step": 5300
+    },
+    {
+      "epoch": 6.5474722564734895,
+      "grad_norm": 1.2594236135482788,
+      "learning_rate": 0.0002,
+      "loss": 0.2462,
+      "step": 5310
+    },
+    {
+      "epoch": 6.55980271270037,
+      "grad_norm": 0.9919610619544983,
+      "learning_rate": 0.0002,
+      "loss": 0.2457,
+      "step": 5320
+    },
+    {
+      "epoch": 6.57213316892725,
+      "grad_norm": 1.3703680038452148,
+      "learning_rate": 0.0002,
+      "loss": 0.2933,
+      "step": 5330
+    },
+    {
+      "epoch": 6.584463625154131,
+      "grad_norm": 1.403140902519226,
+      "learning_rate": 0.0002,
+      "loss": 0.2453,
+      "step": 5340
+    },
+    {
+      "epoch": 6.596794081381011,
+      "grad_norm": 1.3477165699005127,
+      "learning_rate": 0.0002,
+      "loss": 0.2584,
+      "step": 5350
+    },
+    {
+      "epoch": 6.609124537607892,
+      "grad_norm": 1.3145594596862793,
+      "learning_rate": 0.0002,
+      "loss": 0.2853,
+      "step": 5360
+    },
+    {
+      "epoch": 6.621454993834772,
+      "grad_norm": 0.9048973321914673,
+      "learning_rate": 0.0002,
+      "loss": 0.246,
+      "step": 5370
+    },
+    {
+      "epoch": 6.633785450061652,
+      "grad_norm": 1.4123972654342651,
+      "learning_rate": 0.0002,
+      "loss": 0.2646,
+      "step": 5380
+    },
+    {
+      "epoch": 6.646115906288532,
+      "grad_norm": 1.3584848642349243,
+      "learning_rate": 0.0002,
+      "loss": 0.272,
+      "step": 5390
+    },
+    {
+      "epoch": 6.658446362515413,
+      "grad_norm": 1.2085801362991333,
+      "learning_rate": 0.0002,
+      "loss": 0.2663,
+      "step": 5400
+    },
+    {
+      "epoch": 6.670776818742294,
+      "grad_norm": 1.9293283224105835,
+      "learning_rate": 0.0002,
+      "loss": 0.2796,
+      "step": 5410
+    },
+    {
+      "epoch": 6.683107274969174,
+      "grad_norm": 1.3658782243728638,
+      "learning_rate": 0.0002,
+      "loss": 0.2412,
+      "step": 5420
+    },
+    {
+      "epoch": 6.695437731196054,
+      "grad_norm": 1.2004997730255127,
+      "learning_rate": 0.0002,
+      "loss": 0.2442,
+      "step": 5430
+    },
+    {
+      "epoch": 6.707768187422935,
+      "grad_norm": 1.0671268701553345,
+      "learning_rate": 0.0002,
+      "loss": 0.2693,
+      "step": 5440
+    },
+    {
+      "epoch": 6.720098643649815,
+      "grad_norm": 0.8877466320991516,
+      "learning_rate": 0.0002,
+      "loss": 0.2216,
+      "step": 5450
+    },
+    {
+      "epoch": 6.732429099876695,
+      "grad_norm": 1.2843106985092163,
+      "learning_rate": 0.0002,
+      "loss": 0.2678,
+      "step": 5460
+    },
+    {
+      "epoch": 6.744759556103576,
+      "grad_norm": 1.0663448572158813,
+      "learning_rate": 0.0002,
+      "loss": 0.2418,
+      "step": 5470
+    },
+    {
+      "epoch": 6.7570900123304565,
+      "grad_norm": 1.3155773878097534,
+      "learning_rate": 0.0002,
+      "loss": 0.2402,
+      "step": 5480
+    },
+    {
+      "epoch": 6.769420468557336,
+      "grad_norm": 1.8862448930740356,
+      "learning_rate": 0.0002,
+      "loss": 0.2559,
+      "step": 5490
+    },
+    {
+      "epoch": 6.781750924784217,
+      "grad_norm": 1.165061116218567,
+      "learning_rate": 0.0002,
+      "loss": 0.2651,
+      "step": 5500
+    },
+    {
+      "epoch": 6.794081381011098,
+      "grad_norm": 1.0968598127365112,
+      "learning_rate": 0.0002,
+      "loss": 0.2342,
+      "step": 5510
+    },
+    {
+      "epoch": 6.806411837237977,
+      "grad_norm": 0.9448091983795166,
+      "learning_rate": 0.0002,
+      "loss": 0.2453,
+      "step": 5520
+    },
+    {
+      "epoch": 6.818742293464858,
+      "grad_norm": 1.400767207145691,
+      "learning_rate": 0.0002,
+      "loss": 0.2609,
+      "step": 5530
+    },
+    {
+      "epoch": 6.831072749691739,
+      "grad_norm": 1.1031112670898438,
+      "learning_rate": 0.0002,
+      "loss": 0.2642,
+      "step": 5540
+    },
+    {
+      "epoch": 6.843403205918619,
+      "grad_norm": 1.2436904907226562,
+      "learning_rate": 0.0002,
+      "loss": 0.2534,
+      "step": 5550
+    },
+    {
+      "epoch": 6.855733662145499,
+      "grad_norm": 1.0987974405288696,
+      "learning_rate": 0.0002,
+      "loss": 0.2601,
+      "step": 5560
+    },
+    {
+      "epoch": 6.86806411837238,
+      "grad_norm": 0.8656415939331055,
+      "learning_rate": 0.0002,
+      "loss": 0.2622,
+      "step": 5570
+    },
+    {
+      "epoch": 6.8803945745992605,
+      "grad_norm": 1.2153927087783813,
+      "learning_rate": 0.0002,
+      "loss": 0.2585,
+      "step": 5580
+    },
+    {
+      "epoch": 6.89272503082614,
+      "grad_norm": 1.111377477645874,
+      "learning_rate": 0.0002,
+      "loss": 0.2888,
+      "step": 5590
+    },
+    {
+      "epoch": 6.905055487053021,
+      "grad_norm": 1.0041896104812622,
+      "learning_rate": 0.0002,
+      "loss": 0.2569,
+      "step": 5600
+    },
+    {
+      "epoch": 6.917385943279902,
+      "grad_norm": 1.0638413429260254,
+      "learning_rate": 0.0002,
+      "loss": 0.2654,
+      "step": 5610
+    },
+    {
+      "epoch": 6.929716399506781,
+      "grad_norm": 0.9756764769554138,
+      "learning_rate": 0.0002,
+      "loss": 0.2364,
+      "step": 5620
+    },
+    {
+      "epoch": 6.942046855733662,
+      "grad_norm": 1.153550624847412,
+      "learning_rate": 0.0002,
+      "loss": 0.2756,
+      "step": 5630
+    },
+    {
+      "epoch": 6.954377311960543,
+      "grad_norm": 1.3393985033035278,
+      "learning_rate": 0.0002,
+      "loss": 0.2732,
+      "step": 5640
+    },
+    {
+      "epoch": 6.9667077681874225,
+      "grad_norm": 1.3233463764190674,
+      "learning_rate": 0.0002,
+      "loss": 0.2793,
+      "step": 5650
+    },
+    {
+      "epoch": 6.979038224414303,
+      "grad_norm": 1.1693105697631836,
+      "learning_rate": 0.0002,
+      "loss": 0.2593,
+      "step": 5660
+    },
+    {
+      "epoch": 6.991368680641184,
+      "grad_norm": 0.7186262607574463,
+      "learning_rate": 0.0002,
+      "loss": 0.278,
+      "step": 5670
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.936746597290039,
+      "eval_runtime": 99.4259,
+      "eval_samples_per_second": 4.385,
+      "eval_steps_per_second": 0.553,
+      "step": 5677
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6488,
+  "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": 2.915919839310643e+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-0.6-num-5885-sd-10000/checkpoint-5677/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-0.6-num-5885-sd-10000/checkpoint-5677/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..459ba5959a39ea126110113c9faed75cda19ffff
--- /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-0.6-num-5885-sd-10000/checkpoint-5677/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05287f447dfde244c1a85dc0f576593b4a9dd61961eb0797da4844688fc48447
+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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e04e4441e0c1b29f69c16b26c142944e440b8076
--- /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-0.6-num-5885-sd-10000/checkpoint-6488/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": [
+    "q_proj",
+    "v_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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b010916a0d0274a90be6d410a100d6c5b321b4b6
--- /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-0.6-num-5885-sd-10000/checkpoint-6488/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13bdf9c4c059a9b32eb35f8009e5aaf6680dd1577a27da3fc53b22bfbd67df9a
+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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e416fe30658f67c4c28d14a269a390854af37b9b
--- /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-0.6-num-5885-sd-10000/checkpoint-6488/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74d8d60430eec12206d1a0c3bd850e504e449bc44f770231a5abefe34f2637c3
+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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..097a3a63abf91df9d6e7c0ad6341796f06509028
--- /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-0.6-num-5885-sd-10000/checkpoint-6488/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ca8bf286917b91590b2f5eaaad41f8787561a71f6a72904069eaf56f09eaeba
+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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6dd2dee8fb0438e02e84ccd773f96e6538cfb5ec
--- /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-0.6-num-5885-sd-10000/checkpoint-6488/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5ed4f10a73a447786a0f9f6c0f576e554f45a4d7edc138e651cdd655c3c7450
+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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22
--- /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-0.6-num-5885-sd-10000/checkpoint-6488/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873
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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..4268b2c2808636a45c3093c9e246e02e9055be97
--- /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-0.6-num-5885-sd-10000/checkpoint-6488/trainer_state.json
@@ -0,0 +1,4633 @@
+{
+  "best_metric": 1.238026738166809,
+  "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-0.6-num-5885-sd-10000/checkpoint-1622",
+  "epoch": 8.0,
+  "eval_steps": 10,
+  "global_step": 6488,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012330456226880395,
+      "grad_norm": 0.8258164525032043,
+      "learning_rate": 0.0002,
+      "loss": 2.3601,
+      "step": 10
+    },
+    {
+      "epoch": 0.02466091245376079,
+      "grad_norm": 0.4577729105949402,
+      "learning_rate": 0.0002,
+      "loss": 1.7317,
+      "step": 20
+    },
+    {
+      "epoch": 0.036991368680641186,
+      "grad_norm": 0.639807939529419,
+      "learning_rate": 0.0002,
+      "loss": 1.4729,
+      "step": 30
+    },
+    {
+      "epoch": 0.04932182490752158,
+      "grad_norm": 0.5311757922172546,
+      "learning_rate": 0.0002,
+      "loss": 1.2088,
+      "step": 40
+    },
+    {
+      "epoch": 0.06165228113440197,
+      "grad_norm": 0.386595219373703,
+      "learning_rate": 0.0002,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.07398273736128237,
+      "grad_norm": 0.4401357173919678,
+      "learning_rate": 0.0002,
+      "loss": 1.1657,
+      "step": 60
+    },
+    {
+      "epoch": 0.08631319358816276,
+      "grad_norm": 0.3234352171421051,
+      "learning_rate": 0.0002,
+      "loss": 1.1022,
+      "step": 70
+    },
+    {
+      "epoch": 0.09864364981504316,
+      "grad_norm": 0.29643672704696655,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 80
+    },
+    {
+      "epoch": 0.11097410604192355,
+      "grad_norm": 0.2941012382507324,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 90
+    },
+    {
+      "epoch": 0.12330456226880394,
+      "grad_norm": 0.5498173832893372,
+      "learning_rate": 0.0002,
+      "loss": 1.2067,
+      "step": 100
+    },
+    {
+      "epoch": 0.13563501849568435,
+      "grad_norm": 0.2545783519744873,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 110
+    },
+    {
+      "epoch": 0.14796547472256474,
+      "grad_norm": 0.2984241247177124,
+      "learning_rate": 0.0002,
+      "loss": 1.0297,
+      "step": 120
+    },
+    {
+      "epoch": 0.16029593094944514,
+      "grad_norm": 0.2710968852043152,
+      "learning_rate": 0.0002,
+      "loss": 1.1591,
+      "step": 130
+    },
+    {
+      "epoch": 0.17262638717632553,
+      "grad_norm": 0.2817152142524719,
+      "learning_rate": 0.0002,
+      "loss": 1.0427,
+      "step": 140
+    },
+    {
+      "epoch": 0.18495684340320592,
+      "grad_norm": 0.41083765029907227,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 150
+    },
+    {
+      "epoch": 0.19728729963008632,
+      "grad_norm": 0.36536213755607605,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 160
+    },
+    {
+      "epoch": 0.2096177558569667,
+      "grad_norm": 0.2738671600818634,
+      "learning_rate": 0.0002,
+      "loss": 1.0132,
+      "step": 170
+    },
+    {
+      "epoch": 0.2219482120838471,
+      "grad_norm": 0.27403146028518677,
+      "learning_rate": 0.0002,
+      "loss": 0.9555,
+      "step": 180
+    },
+    {
+      "epoch": 0.2342786683107275,
+      "grad_norm": 0.4446810483932495,
+      "learning_rate": 0.0002,
+      "loss": 1.0769,
+      "step": 190
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "grad_norm": 0.5295385718345642,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 200
+    },
+    {
+      "epoch": 0.2589395807644883,
+      "grad_norm": 0.311404824256897,
+      "learning_rate": 0.0002,
+      "loss": 1.0827,
+      "step": 210
+    },
+    {
+      "epoch": 0.2712700369913687,
+      "grad_norm": 0.2448509782552719,
+      "learning_rate": 0.0002,
+      "loss": 1.1455,
+      "step": 220
+    },
+    {
+      "epoch": 0.2836004932182491,
+      "grad_norm": 0.6507014036178589,
+      "learning_rate": 0.0002,
+      "loss": 1.0929,
+      "step": 230
+    },
+    {
+      "epoch": 0.2959309494451295,
+      "grad_norm": 0.2339320331811905,
+      "learning_rate": 0.0002,
+      "loss": 0.9875,
+      "step": 240
+    },
+    {
+      "epoch": 0.3082614056720099,
+      "grad_norm": 0.8210226893424988,
+      "learning_rate": 0.0002,
+      "loss": 0.9211,
+      "step": 250
+    },
+    {
+      "epoch": 0.3205918618988903,
+      "grad_norm": 0.27473965287208557,
+      "learning_rate": 0.0002,
+      "loss": 1.161,
+      "step": 260
+    },
+    {
+      "epoch": 0.33292231812577067,
+      "grad_norm": 0.3051395118236542,
+      "learning_rate": 0.0002,
+      "loss": 1.0218,
+      "step": 270
+    },
+    {
+      "epoch": 0.34525277435265106,
+      "grad_norm": 0.3037777245044708,
+      "learning_rate": 0.0002,
+      "loss": 1.0286,
+      "step": 280
+    },
+    {
+      "epoch": 0.35758323057953145,
+      "grad_norm": 0.2748974859714508,
+      "learning_rate": 0.0002,
+      "loss": 1.144,
+      "step": 290
+    },
+    {
+      "epoch": 0.36991368680641185,
+      "grad_norm": 0.23656068742275238,
+      "learning_rate": 0.0002,
+      "loss": 1.0858,
+      "step": 300
+    },
+    {
+      "epoch": 0.38224414303329224,
+      "grad_norm": 0.2523384094238281,
+      "learning_rate": 0.0002,
+      "loss": 1.0564,
+      "step": 310
+    },
+    {
+      "epoch": 0.39457459926017263,
+      "grad_norm": 0.27848055958747864,
+      "learning_rate": 0.0002,
+      "loss": 1.3091,
+      "step": 320
+    },
+    {
+      "epoch": 0.406905055487053,
+      "grad_norm": 0.3204525411128998,
+      "learning_rate": 0.0002,
+      "loss": 1.0252,
+      "step": 330
+    },
+    {
+      "epoch": 0.4192355117139334,
+      "grad_norm": 0.3459707498550415,
+      "learning_rate": 0.0002,
+      "loss": 0.9855,
+      "step": 340
+    },
+    {
+      "epoch": 0.4315659679408138,
+      "grad_norm": 0.2458430379629135,
+      "learning_rate": 0.0002,
+      "loss": 1.1111,
+      "step": 350
+    },
+    {
+      "epoch": 0.4438964241676942,
+      "grad_norm": 0.5022910237312317,
+      "learning_rate": 0.0002,
+      "loss": 1.1493,
+      "step": 360
+    },
+    {
+      "epoch": 0.4562268803945746,
+      "grad_norm": 0.27076372504234314,
+      "learning_rate": 0.0002,
+      "loss": 1.1272,
+      "step": 370
+    },
+    {
+      "epoch": 0.468557336621455,
+      "grad_norm": 0.6489047408103943,
+      "learning_rate": 0.0002,
+      "loss": 1.1927,
+      "step": 380
+    },
+    {
+      "epoch": 0.4808877928483354,
+      "grad_norm": 0.3324144184589386,
+      "learning_rate": 0.0002,
+      "loss": 0.9501,
+      "step": 390
+    },
+    {
+      "epoch": 0.4932182490752158,
+      "grad_norm": 0.32813116908073425,
+      "learning_rate": 0.0002,
+      "loss": 1.2012,
+      "step": 400
+    },
+    {
+      "epoch": 0.5055487053020962,
+      "grad_norm": 0.25295355916023254,
+      "learning_rate": 0.0002,
+      "loss": 1.1135,
+      "step": 410
+    },
+    {
+      "epoch": 0.5178791615289766,
+      "grad_norm": 0.2912578880786896,
+      "learning_rate": 0.0002,
+      "loss": 0.9477,
+      "step": 420
+    },
+    {
+      "epoch": 0.530209617755857,
+      "grad_norm": 0.34780189394950867,
+      "learning_rate": 0.0002,
+      "loss": 1.0121,
+      "step": 430
+    },
+    {
+      "epoch": 0.5425400739827374,
+      "grad_norm": 0.24604526162147522,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 440
+    },
+    {
+      "epoch": 0.5548705302096177,
+      "grad_norm": 0.32759982347488403,
+      "learning_rate": 0.0002,
+      "loss": 1.253,
+      "step": 450
+    },
+    {
+      "epoch": 0.5672009864364982,
+      "grad_norm": 0.40810221433639526,
+      "learning_rate": 0.0002,
+      "loss": 1.1925,
+      "step": 460
+    },
+    {
+      "epoch": 0.5795314426633785,
+      "grad_norm": 0.3590679466724396,
+      "learning_rate": 0.0002,
+      "loss": 1.174,
+      "step": 470
+    },
+    {
+      "epoch": 0.591861898890259,
+      "grad_norm": 0.5656213760375977,
+      "learning_rate": 0.0002,
+      "loss": 1.2223,
+      "step": 480
+    },
+    {
+      "epoch": 0.6041923551171393,
+      "grad_norm": 0.30830657482147217,
+      "learning_rate": 0.0002,
+      "loss": 1.1936,
+      "step": 490
+    },
+    {
+      "epoch": 0.6165228113440198,
+      "grad_norm": 0.317905455827713,
+      "learning_rate": 0.0002,
+      "loss": 1.1873,
+      "step": 500
+    },
+    {
+      "epoch": 0.6288532675709001,
+      "grad_norm": 0.3254566490650177,
+      "learning_rate": 0.0002,
+      "loss": 0.9805,
+      "step": 510
+    },
+    {
+      "epoch": 0.6411837237977805,
+      "grad_norm": 0.29187721014022827,
+      "learning_rate": 0.0002,
+      "loss": 1.0384,
+      "step": 520
+    },
+    {
+      "epoch": 0.6535141800246609,
+      "grad_norm": 0.3439238965511322,
+      "learning_rate": 0.0002,
+      "loss": 1.2526,
+      "step": 530
+    },
+    {
+      "epoch": 0.6658446362515413,
+      "grad_norm": 0.20970556139945984,
+      "learning_rate": 0.0002,
+      "loss": 1.0698,
+      "step": 540
+    },
+    {
+      "epoch": 0.6781750924784217,
+      "grad_norm": 0.4022853374481201,
+      "learning_rate": 0.0002,
+      "loss": 1.1047,
+      "step": 550
+    },
+    {
+      "epoch": 0.6905055487053021,
+      "grad_norm": 0.2235759049654007,
+      "learning_rate": 0.0002,
+      "loss": 1.0684,
+      "step": 560
+    },
+    {
+      "epoch": 0.7028360049321825,
+      "grad_norm": 0.33849895000457764,
+      "learning_rate": 0.0002,
+      "loss": 1.2339,
+      "step": 570
+    },
+    {
+      "epoch": 0.7151664611590629,
+      "grad_norm": 0.34745967388153076,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 580
+    },
+    {
+      "epoch": 0.7274969173859432,
+      "grad_norm": 0.26041269302368164,
+      "learning_rate": 0.0002,
+      "loss": 1.1158,
+      "step": 590
+    },
+    {
+      "epoch": 0.7398273736128237,
+      "grad_norm": 0.3804777264595032,
+      "learning_rate": 0.0002,
+      "loss": 1.2134,
+      "step": 600
+    },
+    {
+      "epoch": 0.752157829839704,
+      "grad_norm": 0.2456253319978714,
+      "learning_rate": 0.0002,
+      "loss": 1.0606,
+      "step": 610
+    },
+    {
+      "epoch": 0.7644882860665845,
+      "grad_norm": 0.37838423252105713,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 620
+    },
+    {
+      "epoch": 0.7768187422934648,
+      "grad_norm": 0.28105494379997253,
+      "learning_rate": 0.0002,
+      "loss": 1.0556,
+      "step": 630
+    },
+    {
+      "epoch": 0.7891491985203453,
+      "grad_norm": 0.2774018943309784,
+      "learning_rate": 0.0002,
+      "loss": 1.0672,
+      "step": 640
+    },
+    {
+      "epoch": 0.8014796547472256,
+      "grad_norm": 1.8184229135513306,
+      "learning_rate": 0.0002,
+      "loss": 0.9978,
+      "step": 650
+    },
+    {
+      "epoch": 0.813810110974106,
+      "grad_norm": 0.3325096070766449,
+      "learning_rate": 0.0002,
+      "loss": 1.1038,
+      "step": 660
+    },
+    {
+      "epoch": 0.8261405672009864,
+      "grad_norm": 0.2686693072319031,
+      "learning_rate": 0.0002,
+      "loss": 1.083,
+      "step": 670
+    },
+    {
+      "epoch": 0.8384710234278668,
+      "grad_norm": 0.3271431624889374,
+      "learning_rate": 0.0002,
+      "loss": 1.1308,
+      "step": 680
+    },
+    {
+      "epoch": 0.8508014796547472,
+      "grad_norm": 2.359999656677246,
+      "learning_rate": 0.0002,
+      "loss": 1.1116,
+      "step": 690
+    },
+    {
+      "epoch": 0.8631319358816276,
+      "grad_norm": 0.46242964267730713,
+      "learning_rate": 0.0002,
+      "loss": 1.0782,
+      "step": 700
+    },
+    {
+      "epoch": 0.8754623921085081,
+      "grad_norm": 0.34731170535087585,
+      "learning_rate": 0.0002,
+      "loss": 0.95,
+      "step": 710
+    },
+    {
+      "epoch": 0.8877928483353884,
+      "grad_norm": 0.39381715655326843,
+      "learning_rate": 0.0002,
+      "loss": 1.2236,
+      "step": 720
+    },
+    {
+      "epoch": 0.9001233045622689,
+      "grad_norm": 0.43496373295783997,
+      "learning_rate": 0.0002,
+      "loss": 1.1319,
+      "step": 730
+    },
+    {
+      "epoch": 0.9124537607891492,
+      "grad_norm": 0.32243210077285767,
+      "learning_rate": 0.0002,
+      "loss": 1.0979,
+      "step": 740
+    },
+    {
+      "epoch": 0.9247842170160296,
+      "grad_norm": 0.30396756529808044,
+      "learning_rate": 0.0002,
+      "loss": 0.9913,
+      "step": 750
+    },
+    {
+      "epoch": 0.93711467324291,
+      "grad_norm": 0.4461122751235962,
+      "learning_rate": 0.0002,
+      "loss": 1.1141,
+      "step": 760
+    },
+    {
+      "epoch": 0.9494451294697904,
+      "grad_norm": 0.24081681668758392,
+      "learning_rate": 0.0002,
+      "loss": 1.0049,
+      "step": 770
+    },
+    {
+      "epoch": 0.9617755856966708,
+      "grad_norm": 0.27461910247802734,
+      "learning_rate": 0.0002,
+      "loss": 1.0966,
+      "step": 780
+    },
+    {
+      "epoch": 0.9741060419235512,
+      "grad_norm": 0.3325668275356293,
+      "learning_rate": 0.0002,
+      "loss": 0.9942,
+      "step": 790
+    },
+    {
+      "epoch": 0.9864364981504316,
+      "grad_norm": 0.24046339094638824,
+      "learning_rate": 0.0002,
+      "loss": 1.0506,
+      "step": 800
+    },
+    {
+      "epoch": 0.998766954377312,
+      "grad_norm": 0.42950066924095154,
+      "learning_rate": 0.0002,
+      "loss": 0.9989,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.246457576751709,
+      "eval_runtime": 98.7974,
+      "eval_samples_per_second": 4.413,
+      "eval_steps_per_second": 0.557,
+      "step": 811
+    },
+    {
+      "epoch": 1.0110974106041923,
+      "grad_norm": 0.26760655641555786,
+      "learning_rate": 0.0002,
+      "loss": 1.0536,
+      "step": 820
+    },
+    {
+      "epoch": 1.0234278668310728,
+      "grad_norm": 0.4640820026397705,
+      "learning_rate": 0.0002,
+      "loss": 0.9722,
+      "step": 830
+    },
+    {
+      "epoch": 1.0357583230579532,
+      "grad_norm": 0.2699166238307953,
+      "learning_rate": 0.0002,
+      "loss": 0.9392,
+      "step": 840
+    },
+    {
+      "epoch": 1.0480887792848335,
+      "grad_norm": 0.3441709578037262,
+      "learning_rate": 0.0002,
+      "loss": 0.9335,
+      "step": 850
+    },
+    {
+      "epoch": 1.060419235511714,
+      "grad_norm": 0.299934983253479,
+      "learning_rate": 0.0002,
+      "loss": 0.9083,
+      "step": 860
+    },
+    {
+      "epoch": 1.0727496917385944,
+      "grad_norm": 0.2980666160583496,
+      "learning_rate": 0.0002,
+      "loss": 0.9416,
+      "step": 870
+    },
+    {
+      "epoch": 1.0850801479654748,
+      "grad_norm": 0.3131714463233948,
+      "learning_rate": 0.0002,
+      "loss": 0.94,
+      "step": 880
+    },
+    {
+      "epoch": 1.097410604192355,
+      "grad_norm": 0.29881617426872253,
+      "learning_rate": 0.0002,
+      "loss": 0.9288,
+      "step": 890
+    },
+    {
+      "epoch": 1.1097410604192355,
+      "grad_norm": 0.29870888590812683,
+      "learning_rate": 0.0002,
+      "loss": 0.998,
+      "step": 900
+    },
+    {
+      "epoch": 1.122071516646116,
+      "grad_norm": 0.5735140442848206,
+      "learning_rate": 0.0002,
+      "loss": 0.9924,
+      "step": 910
+    },
+    {
+      "epoch": 1.1344019728729964,
+      "grad_norm": 0.33159002661705017,
+      "learning_rate": 0.0002,
+      "loss": 1.0694,
+      "step": 920
+    },
+    {
+      "epoch": 1.1467324290998766,
+      "grad_norm": 1.235399842262268,
+      "learning_rate": 0.0002,
+      "loss": 1.0069,
+      "step": 930
+    },
+    {
+      "epoch": 1.159062885326757,
+      "grad_norm": 0.27469736337661743,
+      "learning_rate": 0.0002,
+      "loss": 1.0315,
+      "step": 940
+    },
+    {
+      "epoch": 1.1713933415536375,
+      "grad_norm": 0.29130664467811584,
+      "learning_rate": 0.0002,
+      "loss": 0.9386,
+      "step": 950
+    },
+    {
+      "epoch": 1.183723797780518,
+      "grad_norm": 0.3730354607105255,
+      "learning_rate": 0.0002,
+      "loss": 0.8919,
+      "step": 960
+    },
+    {
+      "epoch": 1.1960542540073984,
+      "grad_norm": 0.5973590612411499,
+      "learning_rate": 0.0002,
+      "loss": 0.9988,
+      "step": 970
+    },
+    {
+      "epoch": 1.2083847102342786,
+      "grad_norm": 0.39631304144859314,
+      "learning_rate": 0.0002,
+      "loss": 0.9525,
+      "step": 980
+    },
+    {
+      "epoch": 1.220715166461159,
+      "grad_norm": 0.849051296710968,
+      "learning_rate": 0.0002,
+      "loss": 0.9217,
+      "step": 990
+    },
+    {
+      "epoch": 1.2330456226880395,
+      "grad_norm": 0.4390525817871094,
+      "learning_rate": 0.0002,
+      "loss": 1.0903,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2453760789149197,
+      "grad_norm": 0.30423852801322937,
+      "learning_rate": 0.0002,
+      "loss": 0.9018,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2577065351418002,
+      "grad_norm": 0.34736061096191406,
+      "learning_rate": 0.0002,
+      "loss": 1.0128,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2700369913686806,
+      "grad_norm": 0.3421604037284851,
+      "learning_rate": 0.0002,
+      "loss": 0.9026,
+      "step": 1030
+    },
+    {
+      "epoch": 1.282367447595561,
+      "grad_norm": 0.544170081615448,
+      "learning_rate": 0.0002,
+      "loss": 0.8485,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2946979038224415,
+      "grad_norm": 0.5128790736198425,
+      "learning_rate": 0.0002,
+      "loss": 0.9591,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3070283600493218,
+      "grad_norm": 0.443344384431839,
+      "learning_rate": 0.0002,
+      "loss": 0.9214,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3193588162762022,
+      "grad_norm": 0.6380868554115295,
+      "learning_rate": 0.0002,
+      "loss": 0.9367,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3316892725030827,
+      "grad_norm": 0.4638073146343231,
+      "learning_rate": 0.0002,
+      "loss": 0.9849,
+      "step": 1080
+    },
+    {
+      "epoch": 1.344019728729963,
+      "grad_norm": 0.32406893372535706,
+      "learning_rate": 0.0002,
+      "loss": 0.8645,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3563501849568433,
+      "grad_norm": 0.3955065608024597,
+      "learning_rate": 0.0002,
+      "loss": 0.8278,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3686806411837238,
+      "grad_norm": 0.3489246666431427,
+      "learning_rate": 0.0002,
+      "loss": 0.9306,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3810110974106042,
+      "grad_norm": 0.48451653122901917,
+      "learning_rate": 0.0002,
+      "loss": 1.0138,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3933415536374847,
+      "grad_norm": 0.3652360439300537,
+      "learning_rate": 0.0002,
+      "loss": 0.9165,
+      "step": 1130
+    },
+    {
+      "epoch": 1.405672009864365,
+      "grad_norm": 1.3097436428070068,
+      "learning_rate": 0.0002,
+      "loss": 0.9576,
+      "step": 1140
+    },
+    {
+      "epoch": 1.4180024660912454,
+      "grad_norm": 0.3647715449333191,
+      "learning_rate": 0.0002,
+      "loss": 0.8115,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4303329223181258,
+      "grad_norm": 0.37248560786247253,
+      "learning_rate": 0.0002,
+      "loss": 0.8573,
+      "step": 1160
+    },
+    {
+      "epoch": 1.442663378545006,
+      "grad_norm": 0.4639643430709839,
+      "learning_rate": 0.0002,
+      "loss": 0.936,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4549938347718865,
+      "grad_norm": 0.5455219745635986,
+      "learning_rate": 0.0002,
+      "loss": 0.9511,
+      "step": 1180
+    },
+    {
+      "epoch": 1.467324290998767,
+      "grad_norm": 0.38862571120262146,
+      "learning_rate": 0.0002,
+      "loss": 0.8611,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4796547472256474,
+      "grad_norm": 0.37586215138435364,
+      "learning_rate": 0.0002,
+      "loss": 0.8681,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4919852034525278,
+      "grad_norm": 0.46244436502456665,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1210
+    },
+    {
+      "epoch": 1.504315659679408,
+      "grad_norm": 0.3570359945297241,
+      "learning_rate": 0.0002,
+      "loss": 0.9388,
+      "step": 1220
+    },
+    {
+      "epoch": 1.5166461159062885,
+      "grad_norm": 0.28393083810806274,
+      "learning_rate": 0.0002,
+      "loss": 0.971,
+      "step": 1230
+    },
+    {
+      "epoch": 1.528976572133169,
+      "grad_norm": 0.5672869682312012,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5413070283600492,
+      "grad_norm": 0.41605108976364136,
+      "learning_rate": 0.0002,
+      "loss": 0.8787,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5536374845869299,
+      "grad_norm": 0.40657493472099304,
+      "learning_rate": 0.0002,
+      "loss": 0.8744,
+      "step": 1260
+    },
+    {
+      "epoch": 1.56596794081381,
+      "grad_norm": 0.43672341108322144,
+      "learning_rate": 0.0002,
+      "loss": 0.9046,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5782983970406905,
+      "grad_norm": 0.3065410554409027,
+      "learning_rate": 0.0002,
+      "loss": 0.8586,
+      "step": 1280
+    },
+    {
+      "epoch": 1.590628853267571,
+      "grad_norm": 0.37826645374298096,
+      "learning_rate": 0.0002,
+      "loss": 0.9499,
+      "step": 1290
+    },
+    {
+      "epoch": 1.6029593094944512,
+      "grad_norm": 0.42307335138320923,
+      "learning_rate": 0.0002,
+      "loss": 0.901,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6152897657213316,
+      "grad_norm": 0.3648843467235565,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
+      "step": 1310
+    },
+    {
+      "epoch": 1.627620221948212,
+      "grad_norm": 0.8921076059341431,
+      "learning_rate": 0.0002,
+      "loss": 0.9302,
+      "step": 1320
+    },
+    {
+      "epoch": 1.6399506781750923,
+      "grad_norm": 0.37522226572036743,
+      "learning_rate": 0.0002,
+      "loss": 0.9378,
+      "step": 1330
+    },
+    {
+      "epoch": 1.652281134401973,
+      "grad_norm": 0.7489957809448242,
+      "learning_rate": 0.0002,
+      "loss": 0.8921,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6646115906288532,
+      "grad_norm": 0.31733131408691406,
+      "learning_rate": 0.0002,
+      "loss": 0.9297,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6769420468557337,
+      "grad_norm": 0.3249478340148926,
+      "learning_rate": 0.0002,
+      "loss": 0.907,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6892725030826141,
+      "grad_norm": 0.3178001344203949,
+      "learning_rate": 0.0002,
+      "loss": 1.0197,
+      "step": 1370
+    },
+    {
+      "epoch": 1.7016029593094943,
+      "grad_norm": 0.5674093961715698,
+      "learning_rate": 0.0002,
+      "loss": 1.0781,
+      "step": 1380
+    },
+    {
+      "epoch": 1.7139334155363748,
+      "grad_norm": 0.35272449254989624,
+      "learning_rate": 0.0002,
+      "loss": 0.8972,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7262638717632552,
+      "grad_norm": 0.5778217911720276,
+      "learning_rate": 0.0002,
+      "loss": 0.9346,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7385943279901355,
+      "grad_norm": 0.33561450242996216,
+      "learning_rate": 0.0002,
+      "loss": 0.9099,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7509247842170161,
+      "grad_norm": 0.31735464930534363,
+      "learning_rate": 0.0002,
+      "loss": 0.8636,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7632552404438964,
+      "grad_norm": 1.0612670183181763,
+      "learning_rate": 0.0002,
+      "loss": 0.982,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7755856966707768,
+      "grad_norm": 0.5442509651184082,
+      "learning_rate": 0.0002,
+      "loss": 0.8224,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7879161528976573,
+      "grad_norm": 0.7471332550048828,
+      "learning_rate": 0.0002,
+      "loss": 0.9275,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8002466091245375,
+      "grad_norm": 0.4323609173297882,
+      "learning_rate": 0.0002,
+      "loss": 0.9389,
+      "step": 1460
+    },
+    {
+      "epoch": 1.8125770653514182,
+      "grad_norm": 0.47796759009361267,
+      "learning_rate": 0.0002,
+      "loss": 0.8247,
+      "step": 1470
+    },
+    {
+      "epoch": 1.8249075215782984,
+      "grad_norm": 0.3348400592803955,
+      "learning_rate": 0.0002,
+      "loss": 0.9395,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8372379778051788,
+      "grad_norm": 0.3354550898075104,
+      "learning_rate": 0.0002,
+      "loss": 0.9793,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8495684340320593,
+      "grad_norm": 0.5988477468490601,
+      "learning_rate": 0.0002,
+      "loss": 0.8581,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8618988902589395,
+      "grad_norm": 0.5222318172454834,
+      "learning_rate": 0.0002,
+      "loss": 0.9268,
+      "step": 1510
+    },
+    {
+      "epoch": 1.87422934648582,
+      "grad_norm": 0.5246642827987671,
+      "learning_rate": 0.0002,
+      "loss": 0.8846,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8865598027127004,
+      "grad_norm": 0.3164594769477844,
+      "learning_rate": 0.0002,
+      "loss": 0.9317,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8988902589395806,
+      "grad_norm": 0.3496174216270447,
+      "learning_rate": 0.0002,
+      "loss": 0.9961,
+      "step": 1540
+    },
+    {
+      "epoch": 1.9112207151664613,
+      "grad_norm": 0.8863359689712524,
+      "learning_rate": 0.0002,
+      "loss": 0.9057,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9235511713933415,
+      "grad_norm": 0.3587026298046112,
+      "learning_rate": 0.0002,
+      "loss": 0.9405,
+      "step": 1560
+    },
+    {
+      "epoch": 1.935881627620222,
+      "grad_norm": 0.6052881479263306,
+      "learning_rate": 0.0002,
+      "loss": 0.8335,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9482120838471024,
+      "grad_norm": 0.567269504070282,
+      "learning_rate": 0.0002,
+      "loss": 0.8805,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9605425400739827,
+      "grad_norm": 0.45184487104415894,
+      "learning_rate": 0.0002,
+      "loss": 0.9581,
+      "step": 1590
+    },
+    {
+      "epoch": 1.972872996300863,
+      "grad_norm": 0.5028569102287292,
+      "learning_rate": 0.0002,
+      "loss": 0.9147,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9852034525277436,
+      "grad_norm": 0.4677547216415405,
+      "learning_rate": 0.0002,
+      "loss": 0.75,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9975339087546238,
+      "grad_norm": 0.35106056928634644,
+      "learning_rate": 0.0002,
+      "loss": 0.8469,
+      "step": 1620
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.238026738166809,
+      "eval_runtime": 95.4287,
+      "eval_samples_per_second": 4.569,
+      "eval_steps_per_second": 0.576,
+      "step": 1622
+    },
+    {
+      "epoch": 2.0098643649815044,
+      "grad_norm": 0.444060355424881,
+      "learning_rate": 0.0002,
+      "loss": 0.7629,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0221948212083847,
+      "grad_norm": 0.627570390701294,
+      "learning_rate": 0.0002,
+      "loss": 0.772,
+      "step": 1640
+    },
+    {
+      "epoch": 2.034525277435265,
+      "grad_norm": 0.38737839460372925,
+      "learning_rate": 0.0002,
+      "loss": 0.6186,
+      "step": 1650
+    },
+    {
+      "epoch": 2.0468557336621456,
+      "grad_norm": 0.4300459623336792,
+      "learning_rate": 0.0002,
+      "loss": 0.7734,
+      "step": 1660
+    },
+    {
+      "epoch": 2.059186189889026,
+      "grad_norm": 0.43037715554237366,
+      "learning_rate": 0.0002,
+      "loss": 0.6943,
+      "step": 1670
+    },
+    {
+      "epoch": 2.0715166461159065,
+      "grad_norm": 0.40772515535354614,
+      "learning_rate": 0.0002,
+      "loss": 0.6588,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0838471023427867,
+      "grad_norm": 0.5295451879501343,
+      "learning_rate": 0.0002,
+      "loss": 0.8105,
+      "step": 1690
+    },
+    {
+      "epoch": 2.096177558569667,
+      "grad_norm": 0.7452750205993652,
+      "learning_rate": 0.0002,
+      "loss": 0.7717,
+      "step": 1700
+    },
+    {
+      "epoch": 2.1085080147965476,
+      "grad_norm": 0.809183657169342,
+      "learning_rate": 0.0002,
+      "loss": 0.7458,
+      "step": 1710
+    },
+    {
+      "epoch": 2.120838471023428,
+      "grad_norm": 0.4597688913345337,
+      "learning_rate": 0.0002,
+      "loss": 0.7398,
+      "step": 1720
+    },
+    {
+      "epoch": 2.133168927250308,
+      "grad_norm": 0.806919276714325,
+      "learning_rate": 0.0002,
+      "loss": 0.6856,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1454993834771887,
+      "grad_norm": 0.3755643665790558,
+      "learning_rate": 0.0002,
+      "loss": 0.679,
+      "step": 1740
+    },
+    {
+      "epoch": 2.157829839704069,
+      "grad_norm": 0.5882734060287476,
+      "learning_rate": 0.0002,
+      "loss": 0.7938,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1701602959309496,
+      "grad_norm": 0.692960798740387,
+      "learning_rate": 0.0002,
+      "loss": 0.6782,
+      "step": 1760
+    },
+    {
+      "epoch": 2.18249075215783,
+      "grad_norm": 0.4737096428871155,
+      "learning_rate": 0.0002,
+      "loss": 0.7195,
+      "step": 1770
+    },
+    {
+      "epoch": 2.19482120838471,
+      "grad_norm": 0.6637021899223328,
+      "learning_rate": 0.0002,
+      "loss": 0.758,
+      "step": 1780
+    },
+    {
+      "epoch": 2.2071516646115907,
+      "grad_norm": 0.9109764099121094,
+      "learning_rate": 0.0002,
+      "loss": 0.7139,
+      "step": 1790
+    },
+    {
+      "epoch": 2.219482120838471,
+      "grad_norm": 0.4137539267539978,
+      "learning_rate": 0.0002,
+      "loss": 0.7373,
+      "step": 1800
+    },
+    {
+      "epoch": 2.2318125770653516,
+      "grad_norm": 0.44995415210723877,
+      "learning_rate": 0.0002,
+      "loss": 0.7266,
+      "step": 1810
+    },
+    {
+      "epoch": 2.244143033292232,
+      "grad_norm": 0.5985036492347717,
+      "learning_rate": 0.0002,
+      "loss": 0.7663,
+      "step": 1820
+    },
+    {
+      "epoch": 2.256473489519112,
+      "grad_norm": 0.7549490332603455,
+      "learning_rate": 0.0002,
+      "loss": 0.7502,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2688039457459928,
+      "grad_norm": 0.4490937888622284,
+      "learning_rate": 0.0002,
+      "loss": 0.7452,
+      "step": 1840
+    },
+    {
+      "epoch": 2.281134401972873,
+      "grad_norm": 0.38859808444976807,
+      "learning_rate": 0.0002,
+      "loss": 0.7531,
+      "step": 1850
+    },
+    {
+      "epoch": 2.293464858199753,
+      "grad_norm": 1.0704916715621948,
+      "learning_rate": 0.0002,
+      "loss": 0.7278,
+      "step": 1860
+    },
+    {
+      "epoch": 2.305795314426634,
+      "grad_norm": 0.4647100865840912,
+      "learning_rate": 0.0002,
+      "loss": 0.7143,
+      "step": 1870
+    },
+    {
+      "epoch": 2.318125770653514,
+      "grad_norm": 0.6181163787841797,
+      "learning_rate": 0.0002,
+      "loss": 0.7146,
+      "step": 1880
+    },
+    {
+      "epoch": 2.3304562268803943,
+      "grad_norm": 0.9241904020309448,
+      "learning_rate": 0.0002,
+      "loss": 0.7689,
+      "step": 1890
+    },
+    {
+      "epoch": 2.342786683107275,
+      "grad_norm": 0.39101317524909973,
+      "learning_rate": 0.0002,
+      "loss": 0.7294,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3551171393341552,
+      "grad_norm": 0.49442458152770996,
+      "learning_rate": 0.0002,
+      "loss": 0.7079,
+      "step": 1910
+    },
+    {
+      "epoch": 2.367447595561036,
+      "grad_norm": 0.4864824414253235,
+      "learning_rate": 0.0002,
+      "loss": 0.7586,
+      "step": 1920
+    },
+    {
+      "epoch": 2.379778051787916,
+      "grad_norm": 0.5427613854408264,
+      "learning_rate": 0.0002,
+      "loss": 0.7434,
+      "step": 1930
+    },
+    {
+      "epoch": 2.392108508014797,
+      "grad_norm": 0.7164974808692932,
+      "learning_rate": 0.0002,
+      "loss": 0.8423,
+      "step": 1940
+    },
+    {
+      "epoch": 2.404438964241677,
+      "grad_norm": 0.562979519367218,
+      "learning_rate": 0.0002,
+      "loss": 0.6888,
+      "step": 1950
+    },
+    {
+      "epoch": 2.4167694204685573,
+      "grad_norm": 0.5631861090660095,
+      "learning_rate": 0.0002,
+      "loss": 0.7692,
+      "step": 1960
+    },
+    {
+      "epoch": 2.429099876695438,
+      "grad_norm": 0.4895121157169342,
+      "learning_rate": 0.0002,
+      "loss": 0.67,
+      "step": 1970
+    },
+    {
+      "epoch": 2.441430332922318,
+      "grad_norm": 0.45674824714660645,
+      "learning_rate": 0.0002,
+      "loss": 0.7735,
+      "step": 1980
+    },
+    {
+      "epoch": 2.4537607891491984,
+      "grad_norm": 1.1424206495285034,
+      "learning_rate": 0.0002,
+      "loss": 0.685,
+      "step": 1990
+    },
+    {
+      "epoch": 2.466091245376079,
+      "grad_norm": 0.6314579844474792,
+      "learning_rate": 0.0002,
+      "loss": 0.7627,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4784217016029593,
+      "grad_norm": 0.5481605529785156,
+      "learning_rate": 0.0002,
+      "loss": 0.7118,
+      "step": 2010
+    },
+    {
+      "epoch": 2.4907521578298395,
+      "grad_norm": 0.4671579599380493,
+      "learning_rate": 0.0002,
+      "loss": 0.6947,
+      "step": 2020
+    },
+    {
+      "epoch": 2.50308261405672,
+      "grad_norm": 0.7621194124221802,
+      "learning_rate": 0.0002,
+      "loss": 0.7377,
+      "step": 2030
+    },
+    {
+      "epoch": 2.5154130702836004,
+      "grad_norm": 0.38983288407325745,
+      "learning_rate": 0.0002,
+      "loss": 0.69,
+      "step": 2040
+    },
+    {
+      "epoch": 2.5277435265104806,
+      "grad_norm": 0.6341150999069214,
+      "learning_rate": 0.0002,
+      "loss": 0.8381,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5400739827373613,
+      "grad_norm": 0.7151971459388733,
+      "learning_rate": 0.0002,
+      "loss": 0.773,
+      "step": 2060
+    },
+    {
+      "epoch": 2.5524044389642415,
+      "grad_norm": 0.9665895104408264,
+      "learning_rate": 0.0002,
+      "loss": 0.6733,
+      "step": 2070
+    },
+    {
+      "epoch": 2.564734895191122,
+      "grad_norm": 0.9572727680206299,
+      "learning_rate": 0.0002,
+      "loss": 0.7791,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5770653514180024,
+      "grad_norm": 1.1970765590667725,
+      "learning_rate": 0.0002,
+      "loss": 0.7205,
+      "step": 2090
+    },
+    {
+      "epoch": 2.589395807644883,
+      "grad_norm": 0.5505942702293396,
+      "learning_rate": 0.0002,
+      "loss": 0.6736,
+      "step": 2100
+    },
+    {
+      "epoch": 2.6017262638717633,
+      "grad_norm": 0.5903949737548828,
+      "learning_rate": 0.0002,
+      "loss": 0.673,
+      "step": 2110
+    },
+    {
+      "epoch": 2.6140567200986435,
+      "grad_norm": 0.45640307664871216,
+      "learning_rate": 0.0002,
+      "loss": 0.678,
+      "step": 2120
+    },
+    {
+      "epoch": 2.626387176325524,
+      "grad_norm": 0.8763944506645203,
+      "learning_rate": 0.0002,
+      "loss": 0.6562,
+      "step": 2130
+    },
+    {
+      "epoch": 2.6387176325524044,
+      "grad_norm": 0.4472963213920593,
+      "learning_rate": 0.0002,
+      "loss": 0.6484,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6510480887792847,
+      "grad_norm": 0.5335086584091187,
+      "learning_rate": 0.0002,
+      "loss": 0.7702,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6633785450061653,
+      "grad_norm": 0.805263340473175,
+      "learning_rate": 0.0002,
+      "loss": 0.6851,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6757090012330456,
+      "grad_norm": 0.6332727670669556,
+      "learning_rate": 0.0002,
+      "loss": 0.7026,
+      "step": 2170
+    },
+    {
+      "epoch": 2.688039457459926,
+      "grad_norm": 0.8667435646057129,
+      "learning_rate": 0.0002,
+      "loss": 0.7925,
+      "step": 2180
+    },
+    {
+      "epoch": 2.7003699136868065,
+      "grad_norm": 0.5638955235481262,
+      "learning_rate": 0.0002,
+      "loss": 0.8044,
+      "step": 2190
+    },
+    {
+      "epoch": 2.7127003699136867,
+      "grad_norm": 0.4176250696182251,
+      "learning_rate": 0.0002,
+      "loss": 0.7117,
+      "step": 2200
+    },
+    {
+      "epoch": 2.7250308261405674,
+      "grad_norm": 0.6013461351394653,
+      "learning_rate": 0.0002,
+      "loss": 0.6932,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7373612823674476,
+      "grad_norm": 0.553961992263794,
+      "learning_rate": 0.0002,
+      "loss": 0.7843,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7496917385943282,
+      "grad_norm": 0.4710180461406708,
+      "learning_rate": 0.0002,
+      "loss": 0.8633,
+      "step": 2230
+    },
+    {
+      "epoch": 2.7620221948212085,
+      "grad_norm": 0.8141706585884094,
+      "learning_rate": 0.0002,
+      "loss": 0.7469,
+      "step": 2240
+    },
+    {
+      "epoch": 2.7743526510480887,
+      "grad_norm": 0.7449556589126587,
+      "learning_rate": 0.0002,
+      "loss": 0.7086,
+      "step": 2250
+    },
+    {
+      "epoch": 2.7866831072749694,
+      "grad_norm": 0.5366780757904053,
+      "learning_rate": 0.0002,
+      "loss": 0.6933,
+      "step": 2260
+    },
+    {
+      "epoch": 2.7990135635018496,
+      "grad_norm": 0.5316720604896545,
+      "learning_rate": 0.0002,
+      "loss": 0.7192,
+      "step": 2270
+    },
+    {
+      "epoch": 2.81134401972873,
+      "grad_norm": 0.4598459005355835,
+      "learning_rate": 0.0002,
+      "loss": 0.6212,
+      "step": 2280
+    },
+    {
+      "epoch": 2.8236744759556105,
+      "grad_norm": 0.6852091550827026,
+      "learning_rate": 0.0002,
+      "loss": 0.7024,
+      "step": 2290
+    },
+    {
+      "epoch": 2.8360049321824907,
+      "grad_norm": 0.8040902018547058,
+      "learning_rate": 0.0002,
+      "loss": 0.7357,
+      "step": 2300
+    },
+    {
+      "epoch": 2.848335388409371,
+      "grad_norm": 0.46976321935653687,
+      "learning_rate": 0.0002,
+      "loss": 0.7563,
+      "step": 2310
+    },
+    {
+      "epoch": 2.8606658446362516,
+      "grad_norm": 0.5214090347290039,
+      "learning_rate": 0.0002,
+      "loss": 0.731,
+      "step": 2320
+    },
+    {
+      "epoch": 2.872996300863132,
+      "grad_norm": 0.5323054790496826,
+      "learning_rate": 0.0002,
+      "loss": 0.6687,
+      "step": 2330
+    },
+    {
+      "epoch": 2.885326757090012,
+      "grad_norm": 0.6842264533042908,
+      "learning_rate": 0.0002,
+      "loss": 0.7895,
+      "step": 2340
+    },
+    {
+      "epoch": 2.8976572133168927,
+      "grad_norm": 0.9157055616378784,
+      "learning_rate": 0.0002,
+      "loss": 0.7737,
+      "step": 2350
+    },
+    {
+      "epoch": 2.909987669543773,
+      "grad_norm": 0.5253258347511292,
+      "learning_rate": 0.0002,
+      "loss": 0.7217,
+      "step": 2360
+    },
+    {
+      "epoch": 2.9223181257706536,
+      "grad_norm": 0.4937705099582672,
+      "learning_rate": 0.0002,
+      "loss": 0.7162,
+      "step": 2370
+    },
+    {
+      "epoch": 2.934648581997534,
+      "grad_norm": 0.48762989044189453,
+      "learning_rate": 0.0002,
+      "loss": 0.7008,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9469790382244145,
+      "grad_norm": 0.544335126876831,
+      "learning_rate": 0.0002,
+      "loss": 0.8086,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9593094944512948,
+      "grad_norm": 0.4847845435142517,
+      "learning_rate": 0.0002,
+      "loss": 0.643,
+      "step": 2400
+    },
+    {
+      "epoch": 2.971639950678175,
+      "grad_norm": 0.4787445366382599,
+      "learning_rate": 0.0002,
+      "loss": 0.7757,
+      "step": 2410
+    },
+    {
+      "epoch": 2.9839704069050557,
+      "grad_norm": 1.022318959236145,
+      "learning_rate": 0.0002,
+      "loss": 0.7678,
+      "step": 2420
+    },
+    {
+      "epoch": 2.996300863131936,
+      "grad_norm": 0.4987848103046417,
+      "learning_rate": 0.0002,
+      "loss": 0.6548,
+      "step": 2430
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2936296463012695,
+      "eval_runtime": 94.7897,
+      "eval_samples_per_second": 4.6,
+      "eval_steps_per_second": 0.58,
+      "step": 2433
+    },
+    {
+      "epoch": 3.008631319358816,
+      "grad_norm": 0.5562372803688049,
+      "learning_rate": 0.0002,
+      "loss": 0.6073,
+      "step": 2440
+    },
+    {
+      "epoch": 3.020961775585697,
+      "grad_norm": 1.133402705192566,
+      "learning_rate": 0.0002,
+      "loss": 0.5181,
+      "step": 2450
+    },
+    {
+      "epoch": 3.033292231812577,
+      "grad_norm": 0.6480470299720764,
+      "learning_rate": 0.0002,
+      "loss": 0.5333,
+      "step": 2460
+    },
+    {
+      "epoch": 3.0456226880394572,
+      "grad_norm": 0.8989138007164001,
+      "learning_rate": 0.0002,
+      "loss": 0.4828,
+      "step": 2470
+    },
+    {
+      "epoch": 3.057953144266338,
+      "grad_norm": 0.8257461786270142,
+      "learning_rate": 0.0002,
+      "loss": 0.5097,
+      "step": 2480
+    },
+    {
+      "epoch": 3.070283600493218,
+      "grad_norm": 0.6813381910324097,
+      "learning_rate": 0.0002,
+      "loss": 0.6229,
+      "step": 2490
+    },
+    {
+      "epoch": 3.082614056720099,
+      "grad_norm": 0.6989586353302002,
+      "learning_rate": 0.0002,
+      "loss": 0.531,
+      "step": 2500
+    },
+    {
+      "epoch": 3.094944512946979,
+      "grad_norm": 0.7992092967033386,
+      "learning_rate": 0.0002,
+      "loss": 0.54,
+      "step": 2510
+    },
+    {
+      "epoch": 3.1072749691738593,
+      "grad_norm": 0.698077917098999,
+      "learning_rate": 0.0002,
+      "loss": 0.5054,
+      "step": 2520
+    },
+    {
+      "epoch": 3.11960542540074,
+      "grad_norm": 0.5699033141136169,
+      "learning_rate": 0.0002,
+      "loss": 0.5064,
+      "step": 2530
+    },
+    {
+      "epoch": 3.13193588162762,
+      "grad_norm": 0.6142355799674988,
+      "learning_rate": 0.0002,
+      "loss": 0.6088,
+      "step": 2540
+    },
+    {
+      "epoch": 3.144266337854501,
+      "grad_norm": 0.7089933753013611,
+      "learning_rate": 0.0002,
+      "loss": 0.585,
+      "step": 2550
+    },
+    {
+      "epoch": 3.156596794081381,
+      "grad_norm": 1.0107015371322632,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 2560
+    },
+    {
+      "epoch": 3.1689272503082613,
+      "grad_norm": 0.568138837814331,
+      "learning_rate": 0.0002,
+      "loss": 0.5429,
+      "step": 2570
+    },
+    {
+      "epoch": 3.181257706535142,
+      "grad_norm": 0.9960416555404663,
+      "learning_rate": 0.0002,
+      "loss": 0.5897,
+      "step": 2580
+    },
+    {
+      "epoch": 3.193588162762022,
+      "grad_norm": 0.6277595162391663,
+      "learning_rate": 0.0002,
+      "loss": 0.5211,
+      "step": 2590
+    },
+    {
+      "epoch": 3.2059186189889024,
+      "grad_norm": 0.681083619594574,
+      "learning_rate": 0.0002,
+      "loss": 0.5787,
+      "step": 2600
+    },
+    {
+      "epoch": 3.218249075215783,
+      "grad_norm": 0.5816057324409485,
+      "learning_rate": 0.0002,
+      "loss": 0.5166,
+      "step": 2610
+    },
+    {
+      "epoch": 3.2305795314426633,
+      "grad_norm": 0.7197734117507935,
+      "learning_rate": 0.0002,
+      "loss": 0.545,
+      "step": 2620
+    },
+    {
+      "epoch": 3.242909987669544,
+      "grad_norm": 0.6524068117141724,
+      "learning_rate": 0.0002,
+      "loss": 0.614,
+      "step": 2630
+    },
+    {
+      "epoch": 3.255240443896424,
+      "grad_norm": 1.273668646812439,
+      "learning_rate": 0.0002,
+      "loss": 0.5456,
+      "step": 2640
+    },
+    {
+      "epoch": 3.2675709001233044,
+      "grad_norm": 0.6950451731681824,
+      "learning_rate": 0.0002,
+      "loss": 0.5266,
+      "step": 2650
+    },
+    {
+      "epoch": 3.279901356350185,
+      "grad_norm": 0.8029071688652039,
+      "learning_rate": 0.0002,
+      "loss": 0.5194,
+      "step": 2660
+    },
+    {
+      "epoch": 3.2922318125770653,
+      "grad_norm": 0.7464073896408081,
+      "learning_rate": 0.0002,
+      "loss": 0.5729,
+      "step": 2670
+    },
+    {
+      "epoch": 3.304562268803946,
+      "grad_norm": 0.8342001438140869,
+      "learning_rate": 0.0002,
+      "loss": 0.5366,
+      "step": 2680
+    },
+    {
+      "epoch": 3.316892725030826,
+      "grad_norm": 0.5629868507385254,
+      "learning_rate": 0.0002,
+      "loss": 0.5413,
+      "step": 2690
+    },
+    {
+      "epoch": 3.3292231812577064,
+      "grad_norm": 0.753999650478363,
+      "learning_rate": 0.0002,
+      "loss": 0.633,
+      "step": 2700
+    },
+    {
+      "epoch": 3.341553637484587,
+      "grad_norm": 1.0271371603012085,
+      "learning_rate": 0.0002,
+      "loss": 0.5048,
+      "step": 2710
+    },
+    {
+      "epoch": 3.3538840937114673,
+      "grad_norm": 0.9608535170555115,
+      "learning_rate": 0.0002,
+      "loss": 0.5233,
+      "step": 2720
+    },
+    {
+      "epoch": 3.3662145499383476,
+      "grad_norm": 0.7796488404273987,
+      "learning_rate": 0.0002,
+      "loss": 0.5102,
+      "step": 2730
+    },
+    {
+      "epoch": 3.3785450061652282,
+      "grad_norm": 0.5666437149047852,
+      "learning_rate": 0.0002,
+      "loss": 0.5172,
+      "step": 2740
+    },
+    {
+      "epoch": 3.3908754623921085,
+      "grad_norm": 0.5462956428527832,
+      "learning_rate": 0.0002,
+      "loss": 0.491,
+      "step": 2750
+    },
+    {
+      "epoch": 3.4032059186189887,
+      "grad_norm": 1.289099097251892,
+      "learning_rate": 0.0002,
+      "loss": 0.5855,
+      "step": 2760
+    },
+    {
+      "epoch": 3.4155363748458694,
+      "grad_norm": 0.825566828250885,
+      "learning_rate": 0.0002,
+      "loss": 0.635,
+      "step": 2770
+    },
+    {
+      "epoch": 3.4278668310727496,
+      "grad_norm": 0.8366670608520508,
+      "learning_rate": 0.0002,
+      "loss": 0.4998,
+      "step": 2780
+    },
+    {
+      "epoch": 3.4401972872996303,
+      "grad_norm": 1.0931549072265625,
+      "learning_rate": 0.0002,
+      "loss": 0.5732,
+      "step": 2790
+    },
+    {
+      "epoch": 3.4525277435265105,
+      "grad_norm": 0.9228858351707458,
+      "learning_rate": 0.0002,
+      "loss": 0.6093,
+      "step": 2800
+    },
+    {
+      "epoch": 3.4648581997533907,
+      "grad_norm": 1.3182806968688965,
+      "learning_rate": 0.0002,
+      "loss": 0.6089,
+      "step": 2810
+    },
+    {
+      "epoch": 3.4771886559802714,
+      "grad_norm": 0.8366976380348206,
+      "learning_rate": 0.0002,
+      "loss": 0.5665,
+      "step": 2820
+    },
+    {
+      "epoch": 3.4895191122071516,
+      "grad_norm": 0.8067695498466492,
+      "learning_rate": 0.0002,
+      "loss": 0.5666,
+      "step": 2830
+    },
+    {
+      "epoch": 3.5018495684340323,
+      "grad_norm": 1.1163437366485596,
+      "learning_rate": 0.0002,
+      "loss": 0.579,
+      "step": 2840
+    },
+    {
+      "epoch": 3.5141800246609125,
+      "grad_norm": 1.7196556329727173,
+      "learning_rate": 0.0002,
+      "loss": 0.5785,
+      "step": 2850
+    },
+    {
+      "epoch": 3.5265104808877927,
+      "grad_norm": 1.1267012357711792,
+      "learning_rate": 0.0002,
+      "loss": 0.5346,
+      "step": 2860
+    },
+    {
+      "epoch": 3.5388409371146734,
+      "grad_norm": 0.7220137119293213,
+      "learning_rate": 0.0002,
+      "loss": 0.447,
+      "step": 2870
+    },
+    {
+      "epoch": 3.5511713933415536,
+      "grad_norm": 0.914114773273468,
+      "learning_rate": 0.0002,
+      "loss": 0.6099,
+      "step": 2880
+    },
+    {
+      "epoch": 3.563501849568434,
+      "grad_norm": 0.6193503141403198,
+      "learning_rate": 0.0002,
+      "loss": 0.6143,
+      "step": 2890
+    },
+    {
+      "epoch": 3.5758323057953145,
+      "grad_norm": 0.6060135960578918,
+      "learning_rate": 0.0002,
+      "loss": 0.5171,
+      "step": 2900
+    },
+    {
+      "epoch": 3.5881627620221948,
+      "grad_norm": 1.0177327394485474,
+      "learning_rate": 0.0002,
+      "loss": 0.5659,
+      "step": 2910
+    },
+    {
+      "epoch": 3.600493218249075,
+      "grad_norm": 0.5994468331336975,
+      "learning_rate": 0.0002,
+      "loss": 0.5711,
+      "step": 2920
+    },
+    {
+      "epoch": 3.6128236744759556,
+      "grad_norm": 0.7450457215309143,
+      "learning_rate": 0.0002,
+      "loss": 0.6373,
+      "step": 2930
+    },
+    {
+      "epoch": 3.625154130702836,
+      "grad_norm": 0.5825870037078857,
+      "learning_rate": 0.0002,
+      "loss": 0.4933,
+      "step": 2940
+    },
+    {
+      "epoch": 3.6374845869297165,
+      "grad_norm": 0.6289743781089783,
+      "learning_rate": 0.0002,
+      "loss": 0.6016,
+      "step": 2950
+    },
+    {
+      "epoch": 3.6498150431565968,
+      "grad_norm": 0.7801929116249084,
+      "learning_rate": 0.0002,
+      "loss": 0.5507,
+      "step": 2960
+    },
+    {
+      "epoch": 3.6621454993834774,
+      "grad_norm": 1.1206634044647217,
+      "learning_rate": 0.0002,
+      "loss": 0.5695,
+      "step": 2970
+    },
+    {
+      "epoch": 3.6744759556103577,
+      "grad_norm": 0.6738817691802979,
+      "learning_rate": 0.0002,
+      "loss": 0.4985,
+      "step": 2980
+    },
+    {
+      "epoch": 3.686806411837238,
+      "grad_norm": 1.1917344331741333,
+      "learning_rate": 0.0002,
+      "loss": 0.6209,
+      "step": 2990
+    },
+    {
+      "epoch": 3.6991368680641186,
+      "grad_norm": 1.3738657236099243,
+      "learning_rate": 0.0002,
+      "loss": 0.5373,
+      "step": 3000
+    },
+    {
+      "epoch": 3.711467324290999,
+      "grad_norm": 0.6642793416976929,
+      "learning_rate": 0.0002,
+      "loss": 0.5467,
+      "step": 3010
+    },
+    {
+      "epoch": 3.723797780517879,
+      "grad_norm": 0.9030995965003967,
+      "learning_rate": 0.0002,
+      "loss": 0.6243,
+      "step": 3020
+    },
+    {
+      "epoch": 3.7361282367447597,
+      "grad_norm": 1.0203914642333984,
+      "learning_rate": 0.0002,
+      "loss": 0.592,
+      "step": 3030
+    },
+    {
+      "epoch": 3.74845869297164,
+      "grad_norm": 0.648394763469696,
+      "learning_rate": 0.0002,
+      "loss": 0.5453,
+      "step": 3040
+    },
+    {
+      "epoch": 3.76078914919852,
+      "grad_norm": 0.6304570436477661,
+      "learning_rate": 0.0002,
+      "loss": 0.498,
+      "step": 3050
+    },
+    {
+      "epoch": 3.773119605425401,
+      "grad_norm": 0.8286601901054382,
+      "learning_rate": 0.0002,
+      "loss": 0.683,
+      "step": 3060
+    },
+    {
+      "epoch": 3.785450061652281,
+      "grad_norm": 0.906444251537323,
+      "learning_rate": 0.0002,
+      "loss": 0.5302,
+      "step": 3070
+    },
+    {
+      "epoch": 3.7977805178791613,
+      "grad_norm": 1.4212149381637573,
+      "learning_rate": 0.0002,
+      "loss": 0.5345,
+      "step": 3080
+    },
+    {
+      "epoch": 3.810110974106042,
+      "grad_norm": 0.7574319839477539,
+      "learning_rate": 0.0002,
+      "loss": 0.6403,
+      "step": 3090
+    },
+    {
+      "epoch": 3.822441430332922,
+      "grad_norm": 0.6534451246261597,
+      "learning_rate": 0.0002,
+      "loss": 0.5756,
+      "step": 3100
+    },
+    {
+      "epoch": 3.834771886559803,
+      "grad_norm": 0.7525447010993958,
+      "learning_rate": 0.0002,
+      "loss": 0.5306,
+      "step": 3110
+    },
+    {
+      "epoch": 3.847102342786683,
+      "grad_norm": 0.6513990759849548,
+      "learning_rate": 0.0002,
+      "loss": 0.5368,
+      "step": 3120
+    },
+    {
+      "epoch": 3.8594327990135637,
+      "grad_norm": 0.7782694697380066,
+      "learning_rate": 0.0002,
+      "loss": 0.5492,
+      "step": 3130
+    },
+    {
+      "epoch": 3.871763255240444,
+      "grad_norm": 0.7998530268669128,
+      "learning_rate": 0.0002,
+      "loss": 0.5727,
+      "step": 3140
+    },
+    {
+      "epoch": 3.884093711467324,
+      "grad_norm": 0.8045353293418884,
+      "learning_rate": 0.0002,
+      "loss": 0.5156,
+      "step": 3150
+    },
+    {
+      "epoch": 3.896424167694205,
+      "grad_norm": 0.8242645263671875,
+      "learning_rate": 0.0002,
+      "loss": 0.5341,
+      "step": 3160
+    },
+    {
+      "epoch": 3.908754623921085,
+      "grad_norm": 0.8302360773086548,
+      "learning_rate": 0.0002,
+      "loss": 0.5563,
+      "step": 3170
+    },
+    {
+      "epoch": 3.9210850801479653,
+      "grad_norm": 0.8653109073638916,
+      "learning_rate": 0.0002,
+      "loss": 0.5793,
+      "step": 3180
+    },
+    {
+      "epoch": 3.933415536374846,
+      "grad_norm": 0.6461338996887207,
+      "learning_rate": 0.0002,
+      "loss": 0.5219,
+      "step": 3190
+    },
+    {
+      "epoch": 3.945745992601726,
+      "grad_norm": 0.8267415165901184,
+      "learning_rate": 0.0002,
+      "loss": 0.6009,
+      "step": 3200
+    },
+    {
+      "epoch": 3.9580764488286064,
+      "grad_norm": 1.1963194608688354,
+      "learning_rate": 0.0002,
+      "loss": 0.5956,
+      "step": 3210
+    },
+    {
+      "epoch": 3.970406905055487,
+      "grad_norm": 0.7101966142654419,
+      "learning_rate": 0.0002,
+      "loss": 0.5692,
+      "step": 3220
+    },
+    {
+      "epoch": 3.9827373612823673,
+      "grad_norm": 0.5931660532951355,
+      "learning_rate": 0.0002,
+      "loss": 0.5471,
+      "step": 3230
+    },
+    {
+      "epoch": 3.995067817509248,
+      "grad_norm": 0.7465988993644714,
+      "learning_rate": 0.0002,
+      "loss": 0.5619,
+      "step": 3240
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4066498279571533,
+      "eval_runtime": 95.7145,
+      "eval_samples_per_second": 4.555,
+      "eval_steps_per_second": 0.575,
+      "step": 3244
+    },
+    {
+      "epoch": 4.007398273736128,
+      "grad_norm": 0.9478800296783447,
+      "learning_rate": 0.0002,
+      "loss": 0.4948,
+      "step": 3250
+    },
+    {
+      "epoch": 4.019728729963009,
+      "grad_norm": 1.207059621810913,
+      "learning_rate": 0.0002,
+      "loss": 0.4129,
+      "step": 3260
+    },
+    {
+      "epoch": 4.032059186189889,
+      "grad_norm": 0.8984074592590332,
+      "learning_rate": 0.0002,
+      "loss": 0.3577,
+      "step": 3270
+    },
+    {
+      "epoch": 4.044389642416769,
+      "grad_norm": 0.8104140758514404,
+      "learning_rate": 0.0002,
+      "loss": 0.3798,
+      "step": 3280
+    },
+    {
+      "epoch": 4.05672009864365,
+      "grad_norm": 1.0875468254089355,
+      "learning_rate": 0.0002,
+      "loss": 0.3657,
+      "step": 3290
+    },
+    {
+      "epoch": 4.06905055487053,
+      "grad_norm": 0.8520309329032898,
+      "learning_rate": 0.0002,
+      "loss": 0.3703,
+      "step": 3300
+    },
+    {
+      "epoch": 4.0813810110974105,
+      "grad_norm": 1.076735496520996,
+      "learning_rate": 0.0002,
+      "loss": 0.3933,
+      "step": 3310
+    },
+    {
+      "epoch": 4.093711467324291,
+      "grad_norm": 0.7789369821548462,
+      "learning_rate": 0.0002,
+      "loss": 0.4422,
+      "step": 3320
+    },
+    {
+      "epoch": 4.106041923551172,
+      "grad_norm": 0.916862964630127,
+      "learning_rate": 0.0002,
+      "loss": 0.4009,
+      "step": 3330
+    },
+    {
+      "epoch": 4.118372379778052,
+      "grad_norm": 1.1251654624938965,
+      "learning_rate": 0.0002,
+      "loss": 0.3934,
+      "step": 3340
+    },
+    {
+      "epoch": 4.130702836004932,
+      "grad_norm": 0.9373420476913452,
+      "learning_rate": 0.0002,
+      "loss": 0.3651,
+      "step": 3350
+    },
+    {
+      "epoch": 4.143033292231813,
+      "grad_norm": 1.03253972530365,
+      "learning_rate": 0.0002,
+      "loss": 0.384,
+      "step": 3360
+    },
+    {
+      "epoch": 4.155363748458693,
+      "grad_norm": 0.947023332118988,
+      "learning_rate": 0.0002,
+      "loss": 0.372,
+      "step": 3370
+    },
+    {
+      "epoch": 4.167694204685573,
+      "grad_norm": 0.8709157109260559,
+      "learning_rate": 0.0002,
+      "loss": 0.4018,
+      "step": 3380
+    },
+    {
+      "epoch": 4.180024660912454,
+      "grad_norm": 0.930983304977417,
+      "learning_rate": 0.0002,
+      "loss": 0.3754,
+      "step": 3390
+    },
+    {
+      "epoch": 4.192355117139334,
+      "grad_norm": 1.092809796333313,
+      "learning_rate": 0.0002,
+      "loss": 0.4248,
+      "step": 3400
+    },
+    {
+      "epoch": 4.2046855733662145,
+      "grad_norm": 0.8454303741455078,
+      "learning_rate": 0.0002,
+      "loss": 0.4453,
+      "step": 3410
+    },
+    {
+      "epoch": 4.217016029593095,
+      "grad_norm": 0.957210123538971,
+      "learning_rate": 0.0002,
+      "loss": 0.4198,
+      "step": 3420
+    },
+    {
+      "epoch": 4.229346485819975,
+      "grad_norm": 0.854333758354187,
+      "learning_rate": 0.0002,
+      "loss": 0.3743,
+      "step": 3430
+    },
+    {
+      "epoch": 4.241676942046856,
+      "grad_norm": 1.0457639694213867,
+      "learning_rate": 0.0002,
+      "loss": 0.4041,
+      "step": 3440
+    },
+    {
+      "epoch": 4.254007398273736,
+      "grad_norm": 0.8972977995872498,
+      "learning_rate": 0.0002,
+      "loss": 0.3817,
+      "step": 3450
+    },
+    {
+      "epoch": 4.266337854500616,
+      "grad_norm": 1.0438238382339478,
+      "learning_rate": 0.0002,
+      "loss": 0.4445,
+      "step": 3460
+    },
+    {
+      "epoch": 4.278668310727497,
+      "grad_norm": 0.7000405192375183,
+      "learning_rate": 0.0002,
+      "loss": 0.4078,
+      "step": 3470
+    },
+    {
+      "epoch": 4.290998766954377,
+      "grad_norm": 1.0451240539550781,
+      "learning_rate": 0.0002,
+      "loss": 0.3718,
+      "step": 3480
+    },
+    {
+      "epoch": 4.303329223181258,
+      "grad_norm": 1.3339767456054688,
+      "learning_rate": 0.0002,
+      "loss": 0.4506,
+      "step": 3490
+    },
+    {
+      "epoch": 4.315659679408138,
+      "grad_norm": 0.7503946423530579,
+      "learning_rate": 0.0002,
+      "loss": 0.3999,
+      "step": 3500
+    },
+    {
+      "epoch": 4.3279901356350186,
+      "grad_norm": 0.8443584442138672,
+      "learning_rate": 0.0002,
+      "loss": 0.4503,
+      "step": 3510
+    },
+    {
+      "epoch": 4.340320591861899,
+      "grad_norm": 1.1681201457977295,
+      "learning_rate": 0.0002,
+      "loss": 0.3793,
+      "step": 3520
+    },
+    {
+      "epoch": 4.352651048088779,
+      "grad_norm": 1.078883171081543,
+      "learning_rate": 0.0002,
+      "loss": 0.4462,
+      "step": 3530
+    },
+    {
+      "epoch": 4.36498150431566,
+      "grad_norm": 0.6894834041595459,
+      "learning_rate": 0.0002,
+      "loss": 0.4216,
+      "step": 3540
+    },
+    {
+      "epoch": 4.37731196054254,
+      "grad_norm": 0.7059480547904968,
+      "learning_rate": 0.0002,
+      "loss": 0.4315,
+      "step": 3550
+    },
+    {
+      "epoch": 4.38964241676942,
+      "grad_norm": 1.1807256937026978,
+      "learning_rate": 0.0002,
+      "loss": 0.3821,
+      "step": 3560
+    },
+    {
+      "epoch": 4.401972872996301,
+      "grad_norm": 0.8341359496116638,
+      "learning_rate": 0.0002,
+      "loss": 0.4192,
+      "step": 3570
+    },
+    {
+      "epoch": 4.4143033292231815,
+      "grad_norm": 1.0273033380508423,
+      "learning_rate": 0.0002,
+      "loss": 0.4123,
+      "step": 3580
+    },
+    {
+      "epoch": 4.426633785450061,
+      "grad_norm": 0.6916454434394836,
+      "learning_rate": 0.0002,
+      "loss": 0.5018,
+      "step": 3590
+    },
+    {
+      "epoch": 4.438964241676942,
+      "grad_norm": 0.8210113644599915,
+      "learning_rate": 0.0002,
+      "loss": 0.3909,
+      "step": 3600
+    },
+    {
+      "epoch": 4.451294697903823,
+      "grad_norm": 1.0309500694274902,
+      "learning_rate": 0.0002,
+      "loss": 0.3893,
+      "step": 3610
+    },
+    {
+      "epoch": 4.463625154130703,
+      "grad_norm": 0.8847399353981018,
+      "learning_rate": 0.0002,
+      "loss": 0.3902,
+      "step": 3620
+    },
+    {
+      "epoch": 4.475955610357583,
+      "grad_norm": 1.668636679649353,
+      "learning_rate": 0.0002,
+      "loss": 0.4198,
+      "step": 3630
+    },
+    {
+      "epoch": 4.488286066584464,
+      "grad_norm": 1.3087958097457886,
+      "learning_rate": 0.0002,
+      "loss": 0.4075,
+      "step": 3640
+    },
+    {
+      "epoch": 4.500616522811344,
+      "grad_norm": 0.837852418422699,
+      "learning_rate": 0.0002,
+      "loss": 0.4294,
+      "step": 3650
+    },
+    {
+      "epoch": 4.512946979038224,
+      "grad_norm": 9.7662353515625,
+      "learning_rate": 0.0002,
+      "loss": 0.4053,
+      "step": 3660
+    },
+    {
+      "epoch": 4.525277435265105,
+      "grad_norm": 1.125719428062439,
+      "learning_rate": 0.0002,
+      "loss": 0.4033,
+      "step": 3670
+    },
+    {
+      "epoch": 4.5376078914919855,
+      "grad_norm": 0.7755377292633057,
+      "learning_rate": 0.0002,
+      "loss": 0.4566,
+      "step": 3680
+    },
+    {
+      "epoch": 4.549938347718865,
+      "grad_norm": 0.7185089588165283,
+      "learning_rate": 0.0002,
+      "loss": 0.4415,
+      "step": 3690
+    },
+    {
+      "epoch": 4.562268803945746,
+      "grad_norm": 1.182063102722168,
+      "learning_rate": 0.0002,
+      "loss": 0.4616,
+      "step": 3700
+    },
+    {
+      "epoch": 4.574599260172627,
+      "grad_norm": 1.001197338104248,
+      "learning_rate": 0.0002,
+      "loss": 0.4572,
+      "step": 3710
+    },
+    {
+      "epoch": 4.586929716399506,
+      "grad_norm": 0.9705429077148438,
+      "learning_rate": 0.0002,
+      "loss": 0.4493,
+      "step": 3720
+    },
+    {
+      "epoch": 4.599260172626387,
+      "grad_norm": 0.7136746048927307,
+      "learning_rate": 0.0002,
+      "loss": 0.42,
+      "step": 3730
+    },
+    {
+      "epoch": 4.611590628853268,
+      "grad_norm": 1.0004864931106567,
+      "learning_rate": 0.0002,
+      "loss": 0.3757,
+      "step": 3740
+    },
+    {
+      "epoch": 4.623921085080148,
+      "grad_norm": 1.3193715810775757,
+      "learning_rate": 0.0002,
+      "loss": 0.4418,
+      "step": 3750
+    },
+    {
+      "epoch": 4.636251541307028,
+      "grad_norm": 0.6945042014122009,
+      "learning_rate": 0.0002,
+      "loss": 0.4572,
+      "step": 3760
+    },
+    {
+      "epoch": 4.648581997533909,
+      "grad_norm": 0.8903936743736267,
+      "learning_rate": 0.0002,
+      "loss": 0.4255,
+      "step": 3770
+    },
+    {
+      "epoch": 4.660912453760789,
+      "grad_norm": 0.7960889339447021,
+      "learning_rate": 0.0002,
+      "loss": 0.3582,
+      "step": 3780
+    },
+    {
+      "epoch": 4.673242909987669,
+      "grad_norm": 1.0439172983169556,
+      "learning_rate": 0.0002,
+      "loss": 0.3864,
+      "step": 3790
+    },
+    {
+      "epoch": 4.68557336621455,
+      "grad_norm": 1.4546219110488892,
+      "learning_rate": 0.0002,
+      "loss": 0.4378,
+      "step": 3800
+    },
+    {
+      "epoch": 4.697903822441431,
+      "grad_norm": 0.8194343447685242,
+      "learning_rate": 0.0002,
+      "loss": 0.4191,
+      "step": 3810
+    },
+    {
+      "epoch": 4.7102342786683105,
+      "grad_norm": 1.0727602243423462,
+      "learning_rate": 0.0002,
+      "loss": 0.4473,
+      "step": 3820
+    },
+    {
+      "epoch": 4.722564734895191,
+      "grad_norm": 0.7785195708274841,
+      "learning_rate": 0.0002,
+      "loss": 0.4021,
+      "step": 3830
+    },
+    {
+      "epoch": 4.734895191122072,
+      "grad_norm": 0.846783459186554,
+      "learning_rate": 0.0002,
+      "loss": 0.4252,
+      "step": 3840
+    },
+    {
+      "epoch": 4.747225647348952,
+      "grad_norm": 1.0481648445129395,
+      "learning_rate": 0.0002,
+      "loss": 0.4647,
+      "step": 3850
+    },
+    {
+      "epoch": 4.759556103575832,
+      "grad_norm": 0.7324008941650391,
+      "learning_rate": 0.0002,
+      "loss": 0.4944,
+      "step": 3860
+    },
+    {
+      "epoch": 4.771886559802713,
+      "grad_norm": 1.06382417678833,
+      "learning_rate": 0.0002,
+      "loss": 0.3831,
+      "step": 3870
+    },
+    {
+      "epoch": 4.784217016029594,
+      "grad_norm": 0.9851241111755371,
+      "learning_rate": 0.0002,
+      "loss": 0.3934,
+      "step": 3880
+    },
+    {
+      "epoch": 4.796547472256473,
+      "grad_norm": 0.8215277791023254,
+      "learning_rate": 0.0002,
+      "loss": 0.5172,
+      "step": 3890
+    },
+    {
+      "epoch": 4.808877928483354,
+      "grad_norm": 0.9901723861694336,
+      "learning_rate": 0.0002,
+      "loss": 0.4437,
+      "step": 3900
+    },
+    {
+      "epoch": 4.821208384710234,
+      "grad_norm": 0.9149112701416016,
+      "learning_rate": 0.0002,
+      "loss": 0.4673,
+      "step": 3910
+    },
+    {
+      "epoch": 4.8335388409371145,
+      "grad_norm": 0.9772973656654358,
+      "learning_rate": 0.0002,
+      "loss": 0.4295,
+      "step": 3920
+    },
+    {
+      "epoch": 4.845869297163995,
+      "grad_norm": 0.8889636397361755,
+      "learning_rate": 0.0002,
+      "loss": 0.4346,
+      "step": 3930
+    },
+    {
+      "epoch": 4.858199753390876,
+      "grad_norm": 1.3032807111740112,
+      "learning_rate": 0.0002,
+      "loss": 0.421,
+      "step": 3940
+    },
+    {
+      "epoch": 4.870530209617756,
+      "grad_norm": 0.8575899600982666,
+      "learning_rate": 0.0002,
+      "loss": 0.434,
+      "step": 3950
+    },
+    {
+      "epoch": 4.882860665844636,
+      "grad_norm": 1.04326331615448,
+      "learning_rate": 0.0002,
+      "loss": 0.4295,
+      "step": 3960
+    },
+    {
+      "epoch": 4.895191122071517,
+      "grad_norm": 1.041210651397705,
+      "learning_rate": 0.0002,
+      "loss": 0.3633,
+      "step": 3970
+    },
+    {
+      "epoch": 4.907521578298397,
+      "grad_norm": 0.9113056063652039,
+      "learning_rate": 0.0002,
+      "loss": 0.4104,
+      "step": 3980
+    },
+    {
+      "epoch": 4.919852034525277,
+      "grad_norm": 1.019347906112671,
+      "learning_rate": 0.0002,
+      "loss": 0.4496,
+      "step": 3990
+    },
+    {
+      "epoch": 4.932182490752158,
+      "grad_norm": 0.7709218859672546,
+      "learning_rate": 0.0002,
+      "loss": 0.457,
+      "step": 4000
+    },
+    {
+      "epoch": 4.944512946979038,
+      "grad_norm": 0.8891775608062744,
+      "learning_rate": 0.0002,
+      "loss": 0.4697,
+      "step": 4010
+    },
+    {
+      "epoch": 4.9568434032059185,
+      "grad_norm": 1.0396920442581177,
+      "learning_rate": 0.0002,
+      "loss": 0.4436,
+      "step": 4020
+    },
+    {
+      "epoch": 4.969173859432799,
+      "grad_norm": 0.9239833354949951,
+      "learning_rate": 0.0002,
+      "loss": 0.4251,
+      "step": 4030
+    },
+    {
+      "epoch": 4.981504315659679,
+      "grad_norm": 1.801400065422058,
+      "learning_rate": 0.0002,
+      "loss": 0.5049,
+      "step": 4040
+    },
+    {
+      "epoch": 4.99383477188656,
+      "grad_norm": 0.6194164752960205,
+      "learning_rate": 0.0002,
+      "loss": 0.4481,
+      "step": 4050
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.544758915901184,
+      "eval_runtime": 96.2573,
+      "eval_samples_per_second": 4.53,
+      "eval_steps_per_second": 0.571,
+      "step": 4055
+    },
+    {
+      "epoch": 5.00616522811344,
+      "grad_norm": 0.9918256998062134,
+      "learning_rate": 0.0002,
+      "loss": 0.3774,
+      "step": 4060
+    },
+    {
+      "epoch": 5.018495684340321,
+      "grad_norm": 1.4851351976394653,
+      "learning_rate": 0.0002,
+      "loss": 0.2887,
+      "step": 4070
+    },
+    {
+      "epoch": 5.030826140567201,
+      "grad_norm": 0.9237686395645142,
+      "learning_rate": 0.0002,
+      "loss": 0.2454,
+      "step": 4080
+    },
+    {
+      "epoch": 5.0431565967940815,
+      "grad_norm": 1.2180852890014648,
+      "learning_rate": 0.0002,
+      "loss": 0.3072,
+      "step": 4090
+    },
+    {
+      "epoch": 5.055487053020962,
+      "grad_norm": 1.1247979402542114,
+      "learning_rate": 0.0002,
+      "loss": 0.282,
+      "step": 4100
+    },
+    {
+      "epoch": 5.067817509247842,
+      "grad_norm": 1.2969884872436523,
+      "learning_rate": 0.0002,
+      "loss": 0.3108,
+      "step": 4110
+    },
+    {
+      "epoch": 5.080147965474723,
+      "grad_norm": 1.0183063745498657,
+      "learning_rate": 0.0002,
+      "loss": 0.2858,
+      "step": 4120
+    },
+    {
+      "epoch": 5.092478421701603,
+      "grad_norm": 1.121330738067627,
+      "learning_rate": 0.0002,
+      "loss": 0.295,
+      "step": 4130
+    },
+    {
+      "epoch": 5.104808877928483,
+      "grad_norm": 1.0748186111450195,
+      "learning_rate": 0.0002,
+      "loss": 0.2697,
+      "step": 4140
+    },
+    {
+      "epoch": 5.117139334155364,
+      "grad_norm": 1.103474736213684,
+      "learning_rate": 0.0002,
+      "loss": 0.3414,
+      "step": 4150
+    },
+    {
+      "epoch": 5.129469790382244,
+      "grad_norm": 1.2251166105270386,
+      "learning_rate": 0.0002,
+      "loss": 0.305,
+      "step": 4160
+    },
+    {
+      "epoch": 5.141800246609124,
+      "grad_norm": 0.920898973941803,
+      "learning_rate": 0.0002,
+      "loss": 0.3131,
+      "step": 4170
+    },
+    {
+      "epoch": 5.154130702836005,
+      "grad_norm": 1.327542781829834,
+      "learning_rate": 0.0002,
+      "loss": 0.281,
+      "step": 4180
+    },
+    {
+      "epoch": 5.1664611590628855,
+      "grad_norm": 1.0677192211151123,
+      "learning_rate": 0.0002,
+      "loss": 0.3214,
+      "step": 4190
+    },
+    {
+      "epoch": 5.178791615289766,
+      "grad_norm": 0.897241473197937,
+      "learning_rate": 0.0002,
+      "loss": 0.2863,
+      "step": 4200
+    },
+    {
+      "epoch": 5.191122071516646,
+      "grad_norm": 0.977457582950592,
+      "learning_rate": 0.0002,
+      "loss": 0.2967,
+      "step": 4210
+    },
+    {
+      "epoch": 5.203452527743527,
+      "grad_norm": 1.4115267992019653,
+      "learning_rate": 0.0002,
+      "loss": 0.3032,
+      "step": 4220
+    },
+    {
+      "epoch": 5.215782983970407,
+      "grad_norm": 1.097743034362793,
+      "learning_rate": 0.0002,
+      "loss": 0.3279,
+      "step": 4230
+    },
+    {
+      "epoch": 5.228113440197287,
+      "grad_norm": 1.1095269918441772,
+      "learning_rate": 0.0002,
+      "loss": 0.293,
+      "step": 4240
+    },
+    {
+      "epoch": 5.240443896424168,
+      "grad_norm": 1.3785479068756104,
+      "learning_rate": 0.0002,
+      "loss": 0.3544,
+      "step": 4250
+    },
+    {
+      "epoch": 5.252774352651048,
+      "grad_norm": 1.0298776626586914,
+      "learning_rate": 0.0002,
+      "loss": 0.3118,
+      "step": 4260
+    },
+    {
+      "epoch": 5.265104808877928,
+      "grad_norm": 1.1592111587524414,
+      "learning_rate": 0.0002,
+      "loss": 0.296,
+      "step": 4270
+    },
+    {
+      "epoch": 5.277435265104809,
+      "grad_norm": 1.2355743646621704,
+      "learning_rate": 0.0002,
+      "loss": 0.2878,
+      "step": 4280
+    },
+    {
+      "epoch": 5.2897657213316895,
+      "grad_norm": 0.8543112874031067,
+      "learning_rate": 0.0002,
+      "loss": 0.3085,
+      "step": 4290
+    },
+    {
+      "epoch": 5.302096177558569,
+      "grad_norm": 1.2953215837478638,
+      "learning_rate": 0.0002,
+      "loss": 0.3108,
+      "step": 4300
+    },
+    {
+      "epoch": 5.31442663378545,
+      "grad_norm": 1.1001787185668945,
+      "learning_rate": 0.0002,
+      "loss": 0.2912,
+      "step": 4310
+    },
+    {
+      "epoch": 5.326757090012331,
+      "grad_norm": 0.7476816773414612,
+      "learning_rate": 0.0002,
+      "loss": 0.3003,
+      "step": 4320
+    },
+    {
+      "epoch": 5.3390875462392104,
+      "grad_norm": 0.8195574283599854,
+      "learning_rate": 0.0002,
+      "loss": 0.3247,
+      "step": 4330
+    },
+    {
+      "epoch": 5.351418002466091,
+      "grad_norm": 0.9490262866020203,
+      "learning_rate": 0.0002,
+      "loss": 0.3035,
+      "step": 4340
+    },
+    {
+      "epoch": 5.363748458692972,
+      "grad_norm": 1.2201412916183472,
+      "learning_rate": 0.0002,
+      "loss": 0.2846,
+      "step": 4350
+    },
+    {
+      "epoch": 5.376078914919852,
+      "grad_norm": 1.0311479568481445,
+      "learning_rate": 0.0002,
+      "loss": 0.2644,
+      "step": 4360
+    },
+    {
+      "epoch": 5.388409371146732,
+      "grad_norm": 1.2097488641738892,
+      "learning_rate": 0.0002,
+      "loss": 0.3104,
+      "step": 4370
+    },
+    {
+      "epoch": 5.400739827373613,
+      "grad_norm": 1.140942096710205,
+      "learning_rate": 0.0002,
+      "loss": 0.2977,
+      "step": 4380
+    },
+    {
+      "epoch": 5.413070283600494,
+      "grad_norm": 0.8091890811920166,
+      "learning_rate": 0.0002,
+      "loss": 0.2975,
+      "step": 4390
+    },
+    {
+      "epoch": 5.425400739827373,
+      "grad_norm": 1.4467964172363281,
+      "learning_rate": 0.0002,
+      "loss": 0.3727,
+      "step": 4400
+    },
+    {
+      "epoch": 5.437731196054254,
+      "grad_norm": 1.0836058855056763,
+      "learning_rate": 0.0002,
+      "loss": 0.2979,
+      "step": 4410
+    },
+    {
+      "epoch": 5.450061652281135,
+      "grad_norm": 1.0515433549880981,
+      "learning_rate": 0.0002,
+      "loss": 0.2601,
+      "step": 4420
+    },
+    {
+      "epoch": 5.4623921085080145,
+      "grad_norm": 0.9603073000907898,
+      "learning_rate": 0.0002,
+      "loss": 0.315,
+      "step": 4430
+    },
+    {
+      "epoch": 5.474722564734895,
+      "grad_norm": 1.234609842300415,
+      "learning_rate": 0.0002,
+      "loss": 0.3166,
+      "step": 4440
+    },
+    {
+      "epoch": 5.487053020961776,
+      "grad_norm": 0.8881428837776184,
+      "learning_rate": 0.0002,
+      "loss": 0.3142,
+      "step": 4450
+    },
+    {
+      "epoch": 5.499383477188656,
+      "grad_norm": 1.1817275285720825,
+      "learning_rate": 0.0002,
+      "loss": 0.3725,
+      "step": 4460
+    },
+    {
+      "epoch": 5.511713933415536,
+      "grad_norm": 1.213993787765503,
+      "learning_rate": 0.0002,
+      "loss": 0.2944,
+      "step": 4470
+    },
+    {
+      "epoch": 5.524044389642417,
+      "grad_norm": 1.0501725673675537,
+      "learning_rate": 0.0002,
+      "loss": 0.3136,
+      "step": 4480
+    },
+    {
+      "epoch": 5.536374845869297,
+      "grad_norm": 1.5061579942703247,
+      "learning_rate": 0.0002,
+      "loss": 0.306,
+      "step": 4490
+    },
+    {
+      "epoch": 5.548705302096177,
+      "grad_norm": 1.1171475648880005,
+      "learning_rate": 0.0002,
+      "loss": 0.3226,
+      "step": 4500
+    },
+    {
+      "epoch": 5.561035758323058,
+      "grad_norm": 1.1147594451904297,
+      "learning_rate": 0.0002,
+      "loss": 0.3624,
+      "step": 4510
+    },
+    {
+      "epoch": 5.573366214549939,
+      "grad_norm": 1.0600544214248657,
+      "learning_rate": 0.0002,
+      "loss": 0.3435,
+      "step": 4520
+    },
+    {
+      "epoch": 5.5856966707768185,
+      "grad_norm": 1.247870922088623,
+      "learning_rate": 0.0002,
+      "loss": 0.3268,
+      "step": 4530
+    },
+    {
+      "epoch": 5.598027127003699,
+      "grad_norm": 0.9425561428070068,
+      "learning_rate": 0.0002,
+      "loss": 0.3168,
+      "step": 4540
+    },
+    {
+      "epoch": 5.61035758323058,
+      "grad_norm": 1.1111550331115723,
+      "learning_rate": 0.0002,
+      "loss": 0.3119,
+      "step": 4550
+    },
+    {
+      "epoch": 5.62268803945746,
+      "grad_norm": 1.743268609046936,
+      "learning_rate": 0.0002,
+      "loss": 0.3389,
+      "step": 4560
+    },
+    {
+      "epoch": 5.63501849568434,
+      "grad_norm": 1.3522645235061646,
+      "learning_rate": 0.0002,
+      "loss": 0.31,
+      "step": 4570
+    },
+    {
+      "epoch": 5.647348951911221,
+      "grad_norm": 0.7354221343994141,
+      "learning_rate": 0.0002,
+      "loss": 0.3121,
+      "step": 4580
+    },
+    {
+      "epoch": 5.659679408138101,
+      "grad_norm": 1.050743818283081,
+      "learning_rate": 0.0002,
+      "loss": 0.3693,
+      "step": 4590
+    },
+    {
+      "epoch": 5.6720098643649814,
+      "grad_norm": 1.1302396059036255,
+      "learning_rate": 0.0002,
+      "loss": 0.3449,
+      "step": 4600
+    },
+    {
+      "epoch": 5.684340320591862,
+      "grad_norm": 0.8774183392524719,
+      "learning_rate": 0.0002,
+      "loss": 0.3211,
+      "step": 4610
+    },
+    {
+      "epoch": 5.696670776818742,
+      "grad_norm": 1.090781569480896,
+      "learning_rate": 0.0002,
+      "loss": 0.3501,
+      "step": 4620
+    },
+    {
+      "epoch": 5.709001233045623,
+      "grad_norm": 0.9177733063697815,
+      "learning_rate": 0.0002,
+      "loss": 0.3211,
+      "step": 4630
+    },
+    {
+      "epoch": 5.721331689272503,
+      "grad_norm": 0.9985341429710388,
+      "learning_rate": 0.0002,
+      "loss": 0.3439,
+      "step": 4640
+    },
+    {
+      "epoch": 5.733662145499384,
+      "grad_norm": 1.0230613946914673,
+      "learning_rate": 0.0002,
+      "loss": 0.3323,
+      "step": 4650
+    },
+    {
+      "epoch": 5.745992601726264,
+      "grad_norm": 0.944656252861023,
+      "learning_rate": 0.0002,
+      "loss": 0.3525,
+      "step": 4660
+    },
+    {
+      "epoch": 5.758323057953144,
+      "grad_norm": 0.8162471652030945,
+      "learning_rate": 0.0002,
+      "loss": 0.3191,
+      "step": 4670
+    },
+    {
+      "epoch": 5.770653514180025,
+      "grad_norm": 1.0500398874282837,
+      "learning_rate": 0.0002,
+      "loss": 0.4011,
+      "step": 4680
+    },
+    {
+      "epoch": 5.782983970406905,
+      "grad_norm": 0.9487981796264648,
+      "learning_rate": 0.0002,
+      "loss": 0.3452,
+      "step": 4690
+    },
+    {
+      "epoch": 5.7953144266337855,
+      "grad_norm": 1.1856540441513062,
+      "learning_rate": 0.0002,
+      "loss": 0.2942,
+      "step": 4700
+    },
+    {
+      "epoch": 5.807644882860666,
+      "grad_norm": 1.2583396434783936,
+      "learning_rate": 0.0002,
+      "loss": 0.3107,
+      "step": 4710
+    },
+    {
+      "epoch": 5.819975339087546,
+      "grad_norm": 1.2532602548599243,
+      "learning_rate": 0.0002,
+      "loss": 0.3223,
+      "step": 4720
+    },
+    {
+      "epoch": 5.832305795314427,
+      "grad_norm": 1.115236520767212,
+      "learning_rate": 0.0002,
+      "loss": 0.3253,
+      "step": 4730
+    },
+    {
+      "epoch": 5.844636251541307,
+      "grad_norm": 1.2245537042617798,
+      "learning_rate": 0.0002,
+      "loss": 0.3539,
+      "step": 4740
+    },
+    {
+      "epoch": 5.856966707768187,
+      "grad_norm": 1.1964094638824463,
+      "learning_rate": 0.0002,
+      "loss": 0.3171,
+      "step": 4750
+    },
+    {
+      "epoch": 5.869297163995068,
+      "grad_norm": 1.0833805799484253,
+      "learning_rate": 0.0002,
+      "loss": 0.3623,
+      "step": 4760
+    },
+    {
+      "epoch": 5.881627620221948,
+      "grad_norm": 1.0694046020507812,
+      "learning_rate": 0.0002,
+      "loss": 0.3511,
+      "step": 4770
+    },
+    {
+      "epoch": 5.893958076448829,
+      "grad_norm": 0.9947936534881592,
+      "learning_rate": 0.0002,
+      "loss": 0.3266,
+      "step": 4780
+    },
+    {
+      "epoch": 5.906288532675709,
+      "grad_norm": 1.175716519355774,
+      "learning_rate": 0.0002,
+      "loss": 0.316,
+      "step": 4790
+    },
+    {
+      "epoch": 5.9186189889025895,
+      "grad_norm": 0.7717352509498596,
+      "learning_rate": 0.0002,
+      "loss": 0.3609,
+      "step": 4800
+    },
+    {
+      "epoch": 5.930949445129469,
+      "grad_norm": 1.2906442880630493,
+      "learning_rate": 0.0002,
+      "loss": 0.3058,
+      "step": 4810
+    },
+    {
+      "epoch": 5.94327990135635,
+      "grad_norm": 1.2416284084320068,
+      "learning_rate": 0.0002,
+      "loss": 0.3187,
+      "step": 4820
+    },
+    {
+      "epoch": 5.955610357583231,
+      "grad_norm": 1.3066956996917725,
+      "learning_rate": 0.0002,
+      "loss": 0.337,
+      "step": 4830
+    },
+    {
+      "epoch": 5.967940813810111,
+      "grad_norm": 1.0872026681900024,
+      "learning_rate": 0.0002,
+      "loss": 0.3167,
+      "step": 4840
+    },
+    {
+      "epoch": 5.980271270036991,
+      "grad_norm": 1.1941101551055908,
+      "learning_rate": 0.0002,
+      "loss": 0.3262,
+      "step": 4850
+    },
+    {
+      "epoch": 5.992601726263872,
+      "grad_norm": 1.1126095056533813,
+      "learning_rate": 0.0002,
+      "loss": 0.3234,
+      "step": 4860
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.748323917388916,
+      "eval_runtime": 97.7488,
+      "eval_samples_per_second": 4.46,
+      "eval_steps_per_second": 0.563,
+      "step": 4866
+    },
+    {
+      "epoch": 6.0049321824907524,
+      "grad_norm": 1.3631165027618408,
+      "learning_rate": 0.0002,
+      "loss": 0.2774,
+      "step": 4870
+    },
+    {
+      "epoch": 6.017262638717632,
+      "grad_norm": 1.2631664276123047,
+      "learning_rate": 0.0002,
+      "loss": 0.2399,
+      "step": 4880
+    },
+    {
+      "epoch": 6.029593094944513,
+      "grad_norm": 0.7073080539703369,
+      "learning_rate": 0.0002,
+      "loss": 0.2177,
+      "step": 4890
+    },
+    {
+      "epoch": 6.041923551171394,
+      "grad_norm": 0.7856091856956482,
+      "learning_rate": 0.0002,
+      "loss": 0.215,
+      "step": 4900
+    },
+    {
+      "epoch": 6.054254007398273,
+      "grad_norm": 1.145540475845337,
+      "learning_rate": 0.0002,
+      "loss": 0.1999,
+      "step": 4910
+    },
+    {
+      "epoch": 6.066584463625154,
+      "grad_norm": 1.1742334365844727,
+      "learning_rate": 0.0002,
+      "loss": 0.2084,
+      "step": 4920
+    },
+    {
+      "epoch": 6.078914919852035,
+      "grad_norm": 0.8043994903564453,
+      "learning_rate": 0.0002,
+      "loss": 0.2342,
+      "step": 4930
+    },
+    {
+      "epoch": 6.0912453760789145,
+      "grad_norm": 1.1877652406692505,
+      "learning_rate": 0.0002,
+      "loss": 0.2454,
+      "step": 4940
+    },
+    {
+      "epoch": 6.103575832305795,
+      "grad_norm": 0.7624953985214233,
+      "learning_rate": 0.0002,
+      "loss": 0.1908,
+      "step": 4950
+    },
+    {
+      "epoch": 6.115906288532676,
+      "grad_norm": 1.0403119325637817,
+      "learning_rate": 0.0002,
+      "loss": 0.2254,
+      "step": 4960
+    },
+    {
+      "epoch": 6.1282367447595565,
+      "grad_norm": 1.2040252685546875,
+      "learning_rate": 0.0002,
+      "loss": 0.2274,
+      "step": 4970
+    },
+    {
+      "epoch": 6.140567200986436,
+      "grad_norm": 0.6242546439170837,
+      "learning_rate": 0.0002,
+      "loss": 0.2199,
+      "step": 4980
+    },
+    {
+      "epoch": 6.152897657213317,
+      "grad_norm": 1.1394767761230469,
+      "learning_rate": 0.0002,
+      "loss": 0.27,
+      "step": 4990
+    },
+    {
+      "epoch": 6.165228113440198,
+      "grad_norm": 1.3760257959365845,
+      "learning_rate": 0.0002,
+      "loss": 0.2377,
+      "step": 5000
+    },
+    {
+      "epoch": 6.177558569667077,
+      "grad_norm": 1.0707697868347168,
+      "learning_rate": 0.0002,
+      "loss": 0.2331,
+      "step": 5010
+    },
+    {
+      "epoch": 6.189889025893958,
+      "grad_norm": 1.288072109222412,
+      "learning_rate": 0.0002,
+      "loss": 0.2311,
+      "step": 5020
+    },
+    {
+      "epoch": 6.202219482120839,
+      "grad_norm": 1.1479463577270508,
+      "learning_rate": 0.0002,
+      "loss": 0.2276,
+      "step": 5030
+    },
+    {
+      "epoch": 6.2145499383477185,
+      "grad_norm": 0.905891478061676,
+      "learning_rate": 0.0002,
+      "loss": 0.2294,
+      "step": 5040
+    },
+    {
+      "epoch": 6.226880394574599,
+      "grad_norm": 1.0354516506195068,
+      "learning_rate": 0.0002,
+      "loss": 0.2575,
+      "step": 5050
+    },
+    {
+      "epoch": 6.23921085080148,
+      "grad_norm": 1.312671184539795,
+      "learning_rate": 0.0002,
+      "loss": 0.2259,
+      "step": 5060
+    },
+    {
+      "epoch": 6.25154130702836,
+      "grad_norm": 1.614709734916687,
+      "learning_rate": 0.0002,
+      "loss": 0.2281,
+      "step": 5070
+    },
+    {
+      "epoch": 6.26387176325524,
+      "grad_norm": 1.0864229202270508,
+      "learning_rate": 0.0002,
+      "loss": 0.2388,
+      "step": 5080
+    },
+    {
+      "epoch": 6.276202219482121,
+      "grad_norm": 1.0401391983032227,
+      "learning_rate": 0.0002,
+      "loss": 0.2014,
+      "step": 5090
+    },
+    {
+      "epoch": 6.288532675709002,
+      "grad_norm": 1.2187728881835938,
+      "learning_rate": 0.0002,
+      "loss": 0.2419,
+      "step": 5100
+    },
+    {
+      "epoch": 6.300863131935881,
+      "grad_norm": 0.9474364519119263,
+      "learning_rate": 0.0002,
+      "loss": 0.2144,
+      "step": 5110
+    },
+    {
+      "epoch": 6.313193588162762,
+      "grad_norm": 1.1228716373443604,
+      "learning_rate": 0.0002,
+      "loss": 0.238,
+      "step": 5120
+    },
+    {
+      "epoch": 6.325524044389643,
+      "grad_norm": 0.9294499754905701,
+      "learning_rate": 0.0002,
+      "loss": 0.2556,
+      "step": 5130
+    },
+    {
+      "epoch": 6.337854500616523,
+      "grad_norm": 1.0521048307418823,
+      "learning_rate": 0.0002,
+      "loss": 0.2384,
+      "step": 5140
+    },
+    {
+      "epoch": 6.350184956843403,
+      "grad_norm": 1.2406890392303467,
+      "learning_rate": 0.0002,
+      "loss": 0.2444,
+      "step": 5150
+    },
+    {
+      "epoch": 6.362515413070284,
+      "grad_norm": 1.2972853183746338,
+      "learning_rate": 0.0002,
+      "loss": 0.2301,
+      "step": 5160
+    },
+    {
+      "epoch": 6.374845869297164,
+      "grad_norm": 0.8772842288017273,
+      "learning_rate": 0.0002,
+      "loss": 0.2574,
+      "step": 5170
+    },
+    {
+      "epoch": 6.387176325524044,
+      "grad_norm": 1.050349473953247,
+      "learning_rate": 0.0002,
+      "loss": 0.2337,
+      "step": 5180
+    },
+    {
+      "epoch": 6.399506781750925,
+      "grad_norm": 0.9432134032249451,
+      "learning_rate": 0.0002,
+      "loss": 0.2593,
+      "step": 5190
+    },
+    {
+      "epoch": 6.411837237977805,
+      "grad_norm": 1.11045241355896,
+      "learning_rate": 0.0002,
+      "loss": 0.2546,
+      "step": 5200
+    },
+    {
+      "epoch": 6.4241676942046855,
+      "grad_norm": 1.117530345916748,
+      "learning_rate": 0.0002,
+      "loss": 0.268,
+      "step": 5210
+    },
+    {
+      "epoch": 6.436498150431566,
+      "grad_norm": 1.4194035530090332,
+      "learning_rate": 0.0002,
+      "loss": 0.25,
+      "step": 5220
+    },
+    {
+      "epoch": 6.448828606658447,
+      "grad_norm": 1.063950777053833,
+      "learning_rate": 0.0002,
+      "loss": 0.2335,
+      "step": 5230
+    },
+    {
+      "epoch": 6.461159062885327,
+      "grad_norm": 1.2946349382400513,
+      "learning_rate": 0.0002,
+      "loss": 0.2299,
+      "step": 5240
+    },
+    {
+      "epoch": 6.473489519112207,
+      "grad_norm": 1.5237880945205688,
+      "learning_rate": 0.0002,
+      "loss": 0.242,
+      "step": 5250
+    },
+    {
+      "epoch": 6.485819975339088,
+      "grad_norm": 1.1915720701217651,
+      "learning_rate": 0.0002,
+      "loss": 0.255,
+      "step": 5260
+    },
+    {
+      "epoch": 6.498150431565968,
+      "grad_norm": 1.0779626369476318,
+      "learning_rate": 0.0002,
+      "loss": 0.2357,
+      "step": 5270
+    },
+    {
+      "epoch": 6.510480887792848,
+      "grad_norm": 0.8255738019943237,
+      "learning_rate": 0.0002,
+      "loss": 0.2476,
+      "step": 5280
+    },
+    {
+      "epoch": 6.522811344019729,
+      "grad_norm": 1.275174856185913,
+      "learning_rate": 0.0002,
+      "loss": 0.267,
+      "step": 5290
+    },
+    {
+      "epoch": 6.535141800246609,
+      "grad_norm": 1.0878815650939941,
+      "learning_rate": 0.0002,
+      "loss": 0.2217,
+      "step": 5300
+    },
+    {
+      "epoch": 6.5474722564734895,
+      "grad_norm": 1.2594236135482788,
+      "learning_rate": 0.0002,
+      "loss": 0.2462,
+      "step": 5310
+    },
+    {
+      "epoch": 6.55980271270037,
+      "grad_norm": 0.9919610619544983,
+      "learning_rate": 0.0002,
+      "loss": 0.2457,
+      "step": 5320
+    },
+    {
+      "epoch": 6.57213316892725,
+      "grad_norm": 1.3703680038452148,
+      "learning_rate": 0.0002,
+      "loss": 0.2933,
+      "step": 5330
+    },
+    {
+      "epoch": 6.584463625154131,
+      "grad_norm": 1.403140902519226,
+      "learning_rate": 0.0002,
+      "loss": 0.2453,
+      "step": 5340
+    },
+    {
+      "epoch": 6.596794081381011,
+      "grad_norm": 1.3477165699005127,
+      "learning_rate": 0.0002,
+      "loss": 0.2584,
+      "step": 5350
+    },
+    {
+      "epoch": 6.609124537607892,
+      "grad_norm": 1.3145594596862793,
+      "learning_rate": 0.0002,
+      "loss": 0.2853,
+      "step": 5360
+    },
+    {
+      "epoch": 6.621454993834772,
+      "grad_norm": 0.9048973321914673,
+      "learning_rate": 0.0002,
+      "loss": 0.246,
+      "step": 5370
+    },
+    {
+      "epoch": 6.633785450061652,
+      "grad_norm": 1.4123972654342651,
+      "learning_rate": 0.0002,
+      "loss": 0.2646,
+      "step": 5380
+    },
+    {
+      "epoch": 6.646115906288532,
+      "grad_norm": 1.3584848642349243,
+      "learning_rate": 0.0002,
+      "loss": 0.272,
+      "step": 5390
+    },
+    {
+      "epoch": 6.658446362515413,
+      "grad_norm": 1.2085801362991333,
+      "learning_rate": 0.0002,
+      "loss": 0.2663,
+      "step": 5400
+    },
+    {
+      "epoch": 6.670776818742294,
+      "grad_norm": 1.9293283224105835,
+      "learning_rate": 0.0002,
+      "loss": 0.2796,
+      "step": 5410
+    },
+    {
+      "epoch": 6.683107274969174,
+      "grad_norm": 1.3658782243728638,
+      "learning_rate": 0.0002,
+      "loss": 0.2412,
+      "step": 5420
+    },
+    {
+      "epoch": 6.695437731196054,
+      "grad_norm": 1.2004997730255127,
+      "learning_rate": 0.0002,
+      "loss": 0.2442,
+      "step": 5430
+    },
+    {
+      "epoch": 6.707768187422935,
+      "grad_norm": 1.0671268701553345,
+      "learning_rate": 0.0002,
+      "loss": 0.2693,
+      "step": 5440
+    },
+    {
+      "epoch": 6.720098643649815,
+      "grad_norm": 0.8877466320991516,
+      "learning_rate": 0.0002,
+      "loss": 0.2216,
+      "step": 5450
+    },
+    {
+      "epoch": 6.732429099876695,
+      "grad_norm": 1.2843106985092163,
+      "learning_rate": 0.0002,
+      "loss": 0.2678,
+      "step": 5460
+    },
+    {
+      "epoch": 6.744759556103576,
+      "grad_norm": 1.0663448572158813,
+      "learning_rate": 0.0002,
+      "loss": 0.2418,
+      "step": 5470
+    },
+    {
+      "epoch": 6.7570900123304565,
+      "grad_norm": 1.3155773878097534,
+      "learning_rate": 0.0002,
+      "loss": 0.2402,
+      "step": 5480
+    },
+    {
+      "epoch": 6.769420468557336,
+      "grad_norm": 1.8862448930740356,
+      "learning_rate": 0.0002,
+      "loss": 0.2559,
+      "step": 5490
+    },
+    {
+      "epoch": 6.781750924784217,
+      "grad_norm": 1.165061116218567,
+      "learning_rate": 0.0002,
+      "loss": 0.2651,
+      "step": 5500
+    },
+    {
+      "epoch": 6.794081381011098,
+      "grad_norm": 1.0968598127365112,
+      "learning_rate": 0.0002,
+      "loss": 0.2342,
+      "step": 5510
+    },
+    {
+      "epoch": 6.806411837237977,
+      "grad_norm": 0.9448091983795166,
+      "learning_rate": 0.0002,
+      "loss": 0.2453,
+      "step": 5520
+    },
+    {
+      "epoch": 6.818742293464858,
+      "grad_norm": 1.400767207145691,
+      "learning_rate": 0.0002,
+      "loss": 0.2609,
+      "step": 5530
+    },
+    {
+      "epoch": 6.831072749691739,
+      "grad_norm": 1.1031112670898438,
+      "learning_rate": 0.0002,
+      "loss": 0.2642,
+      "step": 5540
+    },
+    {
+      "epoch": 6.843403205918619,
+      "grad_norm": 1.2436904907226562,
+      "learning_rate": 0.0002,
+      "loss": 0.2534,
+      "step": 5550
+    },
+    {
+      "epoch": 6.855733662145499,
+      "grad_norm": 1.0987974405288696,
+      "learning_rate": 0.0002,
+      "loss": 0.2601,
+      "step": 5560
+    },
+    {
+      "epoch": 6.86806411837238,
+      "grad_norm": 0.8656415939331055,
+      "learning_rate": 0.0002,
+      "loss": 0.2622,
+      "step": 5570
+    },
+    {
+      "epoch": 6.8803945745992605,
+      "grad_norm": 1.2153927087783813,
+      "learning_rate": 0.0002,
+      "loss": 0.2585,
+      "step": 5580
+    },
+    {
+      "epoch": 6.89272503082614,
+      "grad_norm": 1.111377477645874,
+      "learning_rate": 0.0002,
+      "loss": 0.2888,
+      "step": 5590
+    },
+    {
+      "epoch": 6.905055487053021,
+      "grad_norm": 1.0041896104812622,
+      "learning_rate": 0.0002,
+      "loss": 0.2569,
+      "step": 5600
+    },
+    {
+      "epoch": 6.917385943279902,
+      "grad_norm": 1.0638413429260254,
+      "learning_rate": 0.0002,
+      "loss": 0.2654,
+      "step": 5610
+    },
+    {
+      "epoch": 6.929716399506781,
+      "grad_norm": 0.9756764769554138,
+      "learning_rate": 0.0002,
+      "loss": 0.2364,
+      "step": 5620
+    },
+    {
+      "epoch": 6.942046855733662,
+      "grad_norm": 1.153550624847412,
+      "learning_rate": 0.0002,
+      "loss": 0.2756,
+      "step": 5630
+    },
+    {
+      "epoch": 6.954377311960543,
+      "grad_norm": 1.3393985033035278,
+      "learning_rate": 0.0002,
+      "loss": 0.2732,
+      "step": 5640
+    },
+    {
+      "epoch": 6.9667077681874225,
+      "grad_norm": 1.3233463764190674,
+      "learning_rate": 0.0002,
+      "loss": 0.2793,
+      "step": 5650
+    },
+    {
+      "epoch": 6.979038224414303,
+      "grad_norm": 1.1693105697631836,
+      "learning_rate": 0.0002,
+      "loss": 0.2593,
+      "step": 5660
+    },
+    {
+      "epoch": 6.991368680641184,
+      "grad_norm": 0.7186262607574463,
+      "learning_rate": 0.0002,
+      "loss": 0.278,
+      "step": 5670
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.936746597290039,
+      "eval_runtime": 99.4259,
+      "eval_samples_per_second": 4.385,
+      "eval_steps_per_second": 0.553,
+      "step": 5677
+    },
+    {
+      "epoch": 7.003699136868065,
+      "grad_norm": 0.9832284450531006,
+      "learning_rate": 0.0002,
+      "loss": 0.2573,
+      "step": 5680
+    },
+    {
+      "epoch": 7.016029593094944,
+      "grad_norm": 1.6794530153274536,
+      "learning_rate": 0.0002,
+      "loss": 0.1879,
+      "step": 5690
+    },
+    {
+      "epoch": 7.028360049321825,
+      "grad_norm": 1.0405313968658447,
+      "learning_rate": 0.0002,
+      "loss": 0.1612,
+      "step": 5700
+    },
+    {
+      "epoch": 7.040690505548706,
+      "grad_norm": 0.8833287954330444,
+      "learning_rate": 0.0002,
+      "loss": 0.1623,
+      "step": 5710
+    },
+    {
+      "epoch": 7.0530209617755855,
+      "grad_norm": 1.081743597984314,
+      "learning_rate": 0.0002,
+      "loss": 0.1666,
+      "step": 5720
+    },
+    {
+      "epoch": 7.065351418002466,
+      "grad_norm": 1.1786993741989136,
+      "learning_rate": 0.0002,
+      "loss": 0.1952,
+      "step": 5730
+    },
+    {
+      "epoch": 7.077681874229347,
+      "grad_norm": 1.219215989112854,
+      "learning_rate": 0.0002,
+      "loss": 0.1618,
+      "step": 5740
+    },
+    {
+      "epoch": 7.090012330456227,
+      "grad_norm": 0.882033109664917,
+      "learning_rate": 0.0002,
+      "loss": 0.165,
+      "step": 5750
+    },
+    {
+      "epoch": 7.102342786683107,
+      "grad_norm": 1.0919346809387207,
+      "learning_rate": 0.0002,
+      "loss": 0.1801,
+      "step": 5760
+    },
+    {
+      "epoch": 7.114673242909988,
+      "grad_norm": 1.2448198795318604,
+      "learning_rate": 0.0002,
+      "loss": 0.1914,
+      "step": 5770
+    },
+    {
+      "epoch": 7.127003699136868,
+      "grad_norm": 0.8977628350257874,
+      "learning_rate": 0.0002,
+      "loss": 0.1826,
+      "step": 5780
+    },
+    {
+      "epoch": 7.139334155363748,
+      "grad_norm": 1.1030590534210205,
+      "learning_rate": 0.0002,
+      "loss": 0.2119,
+      "step": 5790
+    },
+    {
+      "epoch": 7.151664611590629,
+      "grad_norm": 0.9050454497337341,
+      "learning_rate": 0.0002,
+      "loss": 0.1841,
+      "step": 5800
+    },
+    {
+      "epoch": 7.163995067817509,
+      "grad_norm": 1.2709665298461914,
+      "learning_rate": 0.0002,
+      "loss": 0.1765,
+      "step": 5810
+    },
+    {
+      "epoch": 7.1763255240443895,
+      "grad_norm": 1.7741143703460693,
+      "learning_rate": 0.0002,
+      "loss": 0.2069,
+      "step": 5820
+    },
+    {
+      "epoch": 7.18865598027127,
+      "grad_norm": 1.040995478630066,
+      "learning_rate": 0.0002,
+      "loss": 0.2189,
+      "step": 5830
+    },
+    {
+      "epoch": 7.200986436498151,
+      "grad_norm": 0.995246171951294,
+      "learning_rate": 0.0002,
+      "loss": 0.1869,
+      "step": 5840
+    },
+    {
+      "epoch": 7.213316892725031,
+      "grad_norm": 0.962523341178894,
+      "learning_rate": 0.0002,
+      "loss": 0.1727,
+      "step": 5850
+    },
+    {
+      "epoch": 7.225647348951911,
+      "grad_norm": 1.2010393142700195,
+      "learning_rate": 0.0002,
+      "loss": 0.2051,
+      "step": 5860
+    },
+    {
+      "epoch": 7.237977805178792,
+      "grad_norm": 1.1749597787857056,
+      "learning_rate": 0.0002,
+      "loss": 0.19,
+      "step": 5870
+    },
+    {
+      "epoch": 7.250308261405672,
+      "grad_norm": 1.0654889345169067,
+      "learning_rate": 0.0002,
+      "loss": 0.1799,
+      "step": 5880
+    },
+    {
+      "epoch": 7.262638717632552,
+      "grad_norm": 0.761138379573822,
+      "learning_rate": 0.0002,
+      "loss": 0.2184,
+      "step": 5890
+    },
+    {
+      "epoch": 7.274969173859433,
+      "grad_norm": 0.9512502551078796,
+      "learning_rate": 0.0002,
+      "loss": 0.1828,
+      "step": 5900
+    },
+    {
+      "epoch": 7.287299630086313,
+      "grad_norm": 0.7542949318885803,
+      "learning_rate": 0.0002,
+      "loss": 0.1655,
+      "step": 5910
+    },
+    {
+      "epoch": 7.2996300863131935,
+      "grad_norm": 0.7638646364212036,
+      "learning_rate": 0.0002,
+      "loss": 0.1985,
+      "step": 5920
+    },
+    {
+      "epoch": 7.311960542540074,
+      "grad_norm": 1.162330985069275,
+      "learning_rate": 0.0002,
+      "loss": 0.1953,
+      "step": 5930
+    },
+    {
+      "epoch": 7.324290998766954,
+      "grad_norm": 1.5835925340652466,
+      "learning_rate": 0.0002,
+      "loss": 0.204,
+      "step": 5940
+    },
+    {
+      "epoch": 7.336621454993835,
+      "grad_norm": 1.0043281316757202,
+      "learning_rate": 0.0002,
+      "loss": 0.178,
+      "step": 5950
+    },
+    {
+      "epoch": 7.348951911220715,
+      "grad_norm": 1.2750244140625,
+      "learning_rate": 0.0002,
+      "loss": 0.1819,
+      "step": 5960
+    },
+    {
+      "epoch": 7.361282367447595,
+      "grad_norm": 0.8582083582878113,
+      "learning_rate": 0.0002,
+      "loss": 0.1917,
+      "step": 5970
+    },
+    {
+      "epoch": 7.373612823674476,
+      "grad_norm": 1.0025495290756226,
+      "learning_rate": 0.0002,
+      "loss": 0.2022,
+      "step": 5980
+    },
+    {
+      "epoch": 7.3859432799013565,
+      "grad_norm": 1.030452847480774,
+      "learning_rate": 0.0002,
+      "loss": 0.1971,
+      "step": 5990
+    },
+    {
+      "epoch": 7.398273736128237,
+      "grad_norm": 0.9436936378479004,
+      "learning_rate": 0.0002,
+      "loss": 0.2026,
+      "step": 6000
+    },
+    {
+      "epoch": 7.410604192355117,
+      "grad_norm": 1.3259925842285156,
+      "learning_rate": 0.0002,
+      "loss": 0.1847,
+      "step": 6010
+    },
+    {
+      "epoch": 7.422934648581998,
+      "grad_norm": 0.884767472743988,
+      "learning_rate": 0.0002,
+      "loss": 0.1794,
+      "step": 6020
+    },
+    {
+      "epoch": 7.435265104808878,
+      "grad_norm": 0.8467209339141846,
+      "learning_rate": 0.0002,
+      "loss": 0.1712,
+      "step": 6030
+    },
+    {
+      "epoch": 7.447595561035758,
+      "grad_norm": 0.9294904470443726,
+      "learning_rate": 0.0002,
+      "loss": 0.2025,
+      "step": 6040
+    },
+    {
+      "epoch": 7.459926017262639,
+      "grad_norm": 1.2054014205932617,
+      "learning_rate": 0.0002,
+      "loss": 0.1808,
+      "step": 6050
+    },
+    {
+      "epoch": 7.472256473489519,
+      "grad_norm": 0.9458960294723511,
+      "learning_rate": 0.0002,
+      "loss": 0.193,
+      "step": 6060
+    },
+    {
+      "epoch": 7.484586929716399,
+      "grad_norm": 1.0876508951187134,
+      "learning_rate": 0.0002,
+      "loss": 0.1762,
+      "step": 6070
+    },
+    {
+      "epoch": 7.49691738594328,
+      "grad_norm": 1.110326886177063,
+      "learning_rate": 0.0002,
+      "loss": 0.1999,
+      "step": 6080
+    },
+    {
+      "epoch": 7.5092478421701605,
+      "grad_norm": 1.1584968566894531,
+      "learning_rate": 0.0002,
+      "loss": 0.1854,
+      "step": 6090
+    },
+    {
+      "epoch": 7.52157829839704,
+      "grad_norm": 1.0806410312652588,
+      "learning_rate": 0.0002,
+      "loss": 0.2059,
+      "step": 6100
+    },
+    {
+      "epoch": 7.533908754623921,
+      "grad_norm": 0.9162251353263855,
+      "learning_rate": 0.0002,
+      "loss": 0.2042,
+      "step": 6110
+    },
+    {
+      "epoch": 7.546239210850802,
+      "grad_norm": 1.044049620628357,
+      "learning_rate": 0.0002,
+      "loss": 0.1981,
+      "step": 6120
+    },
+    {
+      "epoch": 7.558569667077682,
+      "grad_norm": 0.9524619579315186,
+      "learning_rate": 0.0002,
+      "loss": 0.1857,
+      "step": 6130
+    },
+    {
+      "epoch": 7.570900123304562,
+      "grad_norm": 1.0031976699829102,
+      "learning_rate": 0.0002,
+      "loss": 0.2113,
+      "step": 6140
+    },
+    {
+      "epoch": 7.583230579531443,
+      "grad_norm": 1.342751383781433,
+      "learning_rate": 0.0002,
+      "loss": 0.2008,
+      "step": 6150
+    },
+    {
+      "epoch": 7.595561035758323,
+      "grad_norm": 1.4278815984725952,
+      "learning_rate": 0.0002,
+      "loss": 0.1895,
+      "step": 6160
+    },
+    {
+      "epoch": 7.607891491985203,
+      "grad_norm": 1.6231565475463867,
+      "learning_rate": 0.0002,
+      "loss": 0.2473,
+      "step": 6170
+    },
+    {
+      "epoch": 7.620221948212084,
+      "grad_norm": 1.0082448720932007,
+      "learning_rate": 0.0002,
+      "loss": 0.1861,
+      "step": 6180
+    },
+    {
+      "epoch": 7.6325524044389645,
+      "grad_norm": 1.1605384349822998,
+      "learning_rate": 0.0002,
+      "loss": 0.1945,
+      "step": 6190
+    },
+    {
+      "epoch": 7.644882860665844,
+      "grad_norm": 1.3302881717681885,
+      "learning_rate": 0.0002,
+      "loss": 0.196,
+      "step": 6200
+    },
+    {
+      "epoch": 7.657213316892725,
+      "grad_norm": 1.3318504095077515,
+      "learning_rate": 0.0002,
+      "loss": 0.2169,
+      "step": 6210
+    },
+    {
+      "epoch": 7.669543773119606,
+      "grad_norm": 1.265977144241333,
+      "learning_rate": 0.0002,
+      "loss": 0.1872,
+      "step": 6220
+    },
+    {
+      "epoch": 7.6818742293464854,
+      "grad_norm": 1.3964512348175049,
+      "learning_rate": 0.0002,
+      "loss": 0.1917,
+      "step": 6230
+    },
+    {
+      "epoch": 7.694204685573366,
+      "grad_norm": 1.148972988128662,
+      "learning_rate": 0.0002,
+      "loss": 0.2244,
+      "step": 6240
+    },
+    {
+      "epoch": 7.706535141800247,
+      "grad_norm": 0.8778917193412781,
+      "learning_rate": 0.0002,
+      "loss": 0.2038,
+      "step": 6250
+    },
+    {
+      "epoch": 7.7188655980271275,
+      "grad_norm": 1.3537850379943848,
+      "learning_rate": 0.0002,
+      "loss": 0.2399,
+      "step": 6260
+    },
+    {
+      "epoch": 7.731196054254007,
+      "grad_norm": 0.8741335868835449,
+      "learning_rate": 0.0002,
+      "loss": 0.194,
+      "step": 6270
+    },
+    {
+      "epoch": 7.743526510480888,
+      "grad_norm": 0.9642979502677917,
+      "learning_rate": 0.0002,
+      "loss": 0.2178,
+      "step": 6280
+    },
+    {
+      "epoch": 7.755856966707768,
+      "grad_norm": 1.4556978940963745,
+      "learning_rate": 0.0002,
+      "loss": 0.2328,
+      "step": 6290
+    },
+    {
+      "epoch": 7.768187422934648,
+      "grad_norm": 1.1485596895217896,
+      "learning_rate": 0.0002,
+      "loss": 0.2309,
+      "step": 6300
+    },
+    {
+      "epoch": 7.780517879161529,
+      "grad_norm": 1.2361459732055664,
+      "learning_rate": 0.0002,
+      "loss": 0.2178,
+      "step": 6310
+    },
+    {
+      "epoch": 7.79284833538841,
+      "grad_norm": 1.0271167755126953,
+      "learning_rate": 0.0002,
+      "loss": 0.2291,
+      "step": 6320
+    },
+    {
+      "epoch": 7.8051787916152895,
+      "grad_norm": 1.2584497928619385,
+      "learning_rate": 0.0002,
+      "loss": 0.2112,
+      "step": 6330
+    },
+    {
+      "epoch": 7.81750924784217,
+      "grad_norm": 0.9013339877128601,
+      "learning_rate": 0.0002,
+      "loss": 0.2098,
+      "step": 6340
+    },
+    {
+      "epoch": 7.829839704069051,
+      "grad_norm": 1.1033759117126465,
+      "learning_rate": 0.0002,
+      "loss": 0.1927,
+      "step": 6350
+    },
+    {
+      "epoch": 7.842170160295931,
+      "grad_norm": 1.4669054746627808,
+      "learning_rate": 0.0002,
+      "loss": 0.2294,
+      "step": 6360
+    },
+    {
+      "epoch": 7.854500616522811,
+      "grad_norm": 1.3915599584579468,
+      "learning_rate": 0.0002,
+      "loss": 0.2176,
+      "step": 6370
+    },
+    {
+      "epoch": 7.866831072749692,
+      "grad_norm": 1.6034538745880127,
+      "learning_rate": 0.0002,
+      "loss": 0.2294,
+      "step": 6380
+    },
+    {
+      "epoch": 7.879161528976573,
+      "grad_norm": 1.3022582530975342,
+      "learning_rate": 0.0002,
+      "loss": 0.2244,
+      "step": 6390
+    },
+    {
+      "epoch": 7.891491985203452,
+      "grad_norm": 1.0695449113845825,
+      "learning_rate": 0.0002,
+      "loss": 0.2316,
+      "step": 6400
+    },
+    {
+      "epoch": 7.903822441430333,
+      "grad_norm": 1.1082428693771362,
+      "learning_rate": 0.0002,
+      "loss": 0.2203,
+      "step": 6410
+    },
+    {
+      "epoch": 7.916152897657213,
+      "grad_norm": 0.9848728775978088,
+      "learning_rate": 0.0002,
+      "loss": 0.2102,
+      "step": 6420
+    },
+    {
+      "epoch": 7.9284833538840935,
+      "grad_norm": 0.8668254017829895,
+      "learning_rate": 0.0002,
+      "loss": 0.2049,
+      "step": 6430
+    },
+    {
+      "epoch": 7.940813810110974,
+      "grad_norm": 0.9431440234184265,
+      "learning_rate": 0.0002,
+      "loss": 0.2054,
+      "step": 6440
+    },
+    {
+      "epoch": 7.953144266337855,
+      "grad_norm": 1.3903534412384033,
+      "learning_rate": 0.0002,
+      "loss": 0.2364,
+      "step": 6450
+    },
+    {
+      "epoch": 7.965474722564735,
+      "grad_norm": 1.111591100692749,
+      "learning_rate": 0.0002,
+      "loss": 0.2193,
+      "step": 6460
+    },
+    {
+      "epoch": 7.977805178791615,
+      "grad_norm": 0.9858004450798035,
+      "learning_rate": 0.0002,
+      "loss": 0.2178,
+      "step": 6470
+    },
+    {
+      "epoch": 7.990135635018496,
+      "grad_norm": 0.9721771478652954,
+      "learning_rate": 0.0002,
+      "loss": 0.208,
+      "step": 6480
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.145089626312256,
+      "eval_runtime": 99.6883,
+      "eval_samples_per_second": 4.374,
+      "eval_steps_per_second": 0.552,
+      "step": 6488
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6488,
+  "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": 3.332479816355021e+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-0.6-num-5885-sd-10000/checkpoint-6488/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-0.6-num-5885-sd-10000/checkpoint-6488/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..459ba5959a39ea126110113c9faed75cda19ffff
--- /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-0.6-num-5885-sd-10000/checkpoint-6488/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05287f447dfde244c1a85dc0f576593b4a9dd61961eb0797da4844688fc48447
+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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e04e4441e0c1b29f69c16b26c142944e440b8076
--- /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-0.6-num-5885-sd-10000/checkpoint-811/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": [
+    "q_proj",
+    "v_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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fd97101b620c486ae09c1735cab9e0cb876bdc77
--- /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-0.6-num-5885-sd-10000/checkpoint-811/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84c76a07108de4d52d6d1ca3b590035cdfa1622b60c85d1ee5ddba7d62c3e28
+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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b1d11f1649a351743b24536f6e96451d3f17bab5
--- /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-0.6-num-5885-sd-10000/checkpoint-811/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58806af7af359649b5ade476b1a76eca6a37e287f030753631c1b49fd4aec36c
+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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4208fa1bcd526248f36011b20dd074140a212b21
--- /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-0.6-num-5885-sd-10000/checkpoint-811/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd9be0ee08bddb5f8e1c772ef94e9744bd61e8f63e50db22874917c2bfb606e6
+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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8308ca551eb626f5b968d9e93641d1bd18e6b06c
--- /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-0.6-num-5885-sd-10000/checkpoint-811/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c6112a460bf71ffe48986a0a5d8e7d7f2fd904b4345f25e28a23a413c344c70
+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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22
--- /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-0.6-num-5885-sd-10000/checkpoint-811/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873
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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..4ffd629a71352759af56f5c650811f25735d7f4b
--- /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-0.6-num-5885-sd-10000/checkpoint-811/trainer_state.json
@@ -0,0 +1,608 @@
+{
+  "best_metric": 1.246457576751709,
+  "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-0.6-num-5885-sd-10000/checkpoint-811",
+  "epoch": 1.0,
+  "eval_steps": 10,
+  "global_step": 811,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012330456226880395,
+      "grad_norm": 0.8258164525032043,
+      "learning_rate": 0.0002,
+      "loss": 2.3601,
+      "step": 10
+    },
+    {
+      "epoch": 0.02466091245376079,
+      "grad_norm": 0.4577729105949402,
+      "learning_rate": 0.0002,
+      "loss": 1.7317,
+      "step": 20
+    },
+    {
+      "epoch": 0.036991368680641186,
+      "grad_norm": 0.639807939529419,
+      "learning_rate": 0.0002,
+      "loss": 1.4729,
+      "step": 30
+    },
+    {
+      "epoch": 0.04932182490752158,
+      "grad_norm": 0.5311757922172546,
+      "learning_rate": 0.0002,
+      "loss": 1.2088,
+      "step": 40
+    },
+    {
+      "epoch": 0.06165228113440197,
+      "grad_norm": 0.386595219373703,
+      "learning_rate": 0.0002,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.07398273736128237,
+      "grad_norm": 0.4401357173919678,
+      "learning_rate": 0.0002,
+      "loss": 1.1657,
+      "step": 60
+    },
+    {
+      "epoch": 0.08631319358816276,
+      "grad_norm": 0.3234352171421051,
+      "learning_rate": 0.0002,
+      "loss": 1.1022,
+      "step": 70
+    },
+    {
+      "epoch": 0.09864364981504316,
+      "grad_norm": 0.29643672704696655,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 80
+    },
+    {
+      "epoch": 0.11097410604192355,
+      "grad_norm": 0.2941012382507324,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 90
+    },
+    {
+      "epoch": 0.12330456226880394,
+      "grad_norm": 0.5498173832893372,
+      "learning_rate": 0.0002,
+      "loss": 1.2067,
+      "step": 100
+    },
+    {
+      "epoch": 0.13563501849568435,
+      "grad_norm": 0.2545783519744873,
+      "learning_rate": 0.0002,
+      "loss": 1.142,
+      "step": 110
+    },
+    {
+      "epoch": 0.14796547472256474,
+      "grad_norm": 0.2984241247177124,
+      "learning_rate": 0.0002,
+      "loss": 1.0297,
+      "step": 120
+    },
+    {
+      "epoch": 0.16029593094944514,
+      "grad_norm": 0.2710968852043152,
+      "learning_rate": 0.0002,
+      "loss": 1.1591,
+      "step": 130
+    },
+    {
+      "epoch": 0.17262638717632553,
+      "grad_norm": 0.2817152142524719,
+      "learning_rate": 0.0002,
+      "loss": 1.0427,
+      "step": 140
+    },
+    {
+      "epoch": 0.18495684340320592,
+      "grad_norm": 0.41083765029907227,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 150
+    },
+    {
+      "epoch": 0.19728729963008632,
+      "grad_norm": 0.36536213755607605,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 160
+    },
+    {
+      "epoch": 0.2096177558569667,
+      "grad_norm": 0.2738671600818634,
+      "learning_rate": 0.0002,
+      "loss": 1.0132,
+      "step": 170
+    },
+    {
+      "epoch": 0.2219482120838471,
+      "grad_norm": 0.27403146028518677,
+      "learning_rate": 0.0002,
+      "loss": 0.9555,
+      "step": 180
+    },
+    {
+      "epoch": 0.2342786683107275,
+      "grad_norm": 0.4446810483932495,
+      "learning_rate": 0.0002,
+      "loss": 1.0769,
+      "step": 190
+    },
+    {
+      "epoch": 0.2466091245376079,
+      "grad_norm": 0.5295385718345642,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 200
+    },
+    {
+      "epoch": 0.2589395807644883,
+      "grad_norm": 0.311404824256897,
+      "learning_rate": 0.0002,
+      "loss": 1.0827,
+      "step": 210
+    },
+    {
+      "epoch": 0.2712700369913687,
+      "grad_norm": 0.2448509782552719,
+      "learning_rate": 0.0002,
+      "loss": 1.1455,
+      "step": 220
+    },
+    {
+      "epoch": 0.2836004932182491,
+      "grad_norm": 0.6507014036178589,
+      "learning_rate": 0.0002,
+      "loss": 1.0929,
+      "step": 230
+    },
+    {
+      "epoch": 0.2959309494451295,
+      "grad_norm": 0.2339320331811905,
+      "learning_rate": 0.0002,
+      "loss": 0.9875,
+      "step": 240
+    },
+    {
+      "epoch": 0.3082614056720099,
+      "grad_norm": 0.8210226893424988,
+      "learning_rate": 0.0002,
+      "loss": 0.9211,
+      "step": 250
+    },
+    {
+      "epoch": 0.3205918618988903,
+      "grad_norm": 0.27473965287208557,
+      "learning_rate": 0.0002,
+      "loss": 1.161,
+      "step": 260
+    },
+    {
+      "epoch": 0.33292231812577067,
+      "grad_norm": 0.3051395118236542,
+      "learning_rate": 0.0002,
+      "loss": 1.0218,
+      "step": 270
+    },
+    {
+      "epoch": 0.34525277435265106,
+      "grad_norm": 0.3037777245044708,
+      "learning_rate": 0.0002,
+      "loss": 1.0286,
+      "step": 280
+    },
+    {
+      "epoch": 0.35758323057953145,
+      "grad_norm": 0.2748974859714508,
+      "learning_rate": 0.0002,
+      "loss": 1.144,
+      "step": 290
+    },
+    {
+      "epoch": 0.36991368680641185,
+      "grad_norm": 0.23656068742275238,
+      "learning_rate": 0.0002,
+      "loss": 1.0858,
+      "step": 300
+    },
+    {
+      "epoch": 0.38224414303329224,
+      "grad_norm": 0.2523384094238281,
+      "learning_rate": 0.0002,
+      "loss": 1.0564,
+      "step": 310
+    },
+    {
+      "epoch": 0.39457459926017263,
+      "grad_norm": 0.27848055958747864,
+      "learning_rate": 0.0002,
+      "loss": 1.3091,
+      "step": 320
+    },
+    {
+      "epoch": 0.406905055487053,
+      "grad_norm": 0.3204525411128998,
+      "learning_rate": 0.0002,
+      "loss": 1.0252,
+      "step": 330
+    },
+    {
+      "epoch": 0.4192355117139334,
+      "grad_norm": 0.3459707498550415,
+      "learning_rate": 0.0002,
+      "loss": 0.9855,
+      "step": 340
+    },
+    {
+      "epoch": 0.4315659679408138,
+      "grad_norm": 0.2458430379629135,
+      "learning_rate": 0.0002,
+      "loss": 1.1111,
+      "step": 350
+    },
+    {
+      "epoch": 0.4438964241676942,
+      "grad_norm": 0.5022910237312317,
+      "learning_rate": 0.0002,
+      "loss": 1.1493,
+      "step": 360
+    },
+    {
+      "epoch": 0.4562268803945746,
+      "grad_norm": 0.27076372504234314,
+      "learning_rate": 0.0002,
+      "loss": 1.1272,
+      "step": 370
+    },
+    {
+      "epoch": 0.468557336621455,
+      "grad_norm": 0.6489047408103943,
+      "learning_rate": 0.0002,
+      "loss": 1.1927,
+      "step": 380
+    },
+    {
+      "epoch": 0.4808877928483354,
+      "grad_norm": 0.3324144184589386,
+      "learning_rate": 0.0002,
+      "loss": 0.9501,
+      "step": 390
+    },
+    {
+      "epoch": 0.4932182490752158,
+      "grad_norm": 0.32813116908073425,
+      "learning_rate": 0.0002,
+      "loss": 1.2012,
+      "step": 400
+    },
+    {
+      "epoch": 0.5055487053020962,
+      "grad_norm": 0.25295355916023254,
+      "learning_rate": 0.0002,
+      "loss": 1.1135,
+      "step": 410
+    },
+    {
+      "epoch": 0.5178791615289766,
+      "grad_norm": 0.2912578880786896,
+      "learning_rate": 0.0002,
+      "loss": 0.9477,
+      "step": 420
+    },
+    {
+      "epoch": 0.530209617755857,
+      "grad_norm": 0.34780189394950867,
+      "learning_rate": 0.0002,
+      "loss": 1.0121,
+      "step": 430
+    },
+    {
+      "epoch": 0.5425400739827374,
+      "grad_norm": 0.24604526162147522,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 440
+    },
+    {
+      "epoch": 0.5548705302096177,
+      "grad_norm": 0.32759982347488403,
+      "learning_rate": 0.0002,
+      "loss": 1.253,
+      "step": 450
+    },
+    {
+      "epoch": 0.5672009864364982,
+      "grad_norm": 0.40810221433639526,
+      "learning_rate": 0.0002,
+      "loss": 1.1925,
+      "step": 460
+    },
+    {
+      "epoch": 0.5795314426633785,
+      "grad_norm": 0.3590679466724396,
+      "learning_rate": 0.0002,
+      "loss": 1.174,
+      "step": 470
+    },
+    {
+      "epoch": 0.591861898890259,
+      "grad_norm": 0.5656213760375977,
+      "learning_rate": 0.0002,
+      "loss": 1.2223,
+      "step": 480
+    },
+    {
+      "epoch": 0.6041923551171393,
+      "grad_norm": 0.30830657482147217,
+      "learning_rate": 0.0002,
+      "loss": 1.1936,
+      "step": 490
+    },
+    {
+      "epoch": 0.6165228113440198,
+      "grad_norm": 0.317905455827713,
+      "learning_rate": 0.0002,
+      "loss": 1.1873,
+      "step": 500
+    },
+    {
+      "epoch": 0.6288532675709001,
+      "grad_norm": 0.3254566490650177,
+      "learning_rate": 0.0002,
+      "loss": 0.9805,
+      "step": 510
+    },
+    {
+      "epoch": 0.6411837237977805,
+      "grad_norm": 0.29187721014022827,
+      "learning_rate": 0.0002,
+      "loss": 1.0384,
+      "step": 520
+    },
+    {
+      "epoch": 0.6535141800246609,
+      "grad_norm": 0.3439238965511322,
+      "learning_rate": 0.0002,
+      "loss": 1.2526,
+      "step": 530
+    },
+    {
+      "epoch": 0.6658446362515413,
+      "grad_norm": 0.20970556139945984,
+      "learning_rate": 0.0002,
+      "loss": 1.0698,
+      "step": 540
+    },
+    {
+      "epoch": 0.6781750924784217,
+      "grad_norm": 0.4022853374481201,
+      "learning_rate": 0.0002,
+      "loss": 1.1047,
+      "step": 550
+    },
+    {
+      "epoch": 0.6905055487053021,
+      "grad_norm": 0.2235759049654007,
+      "learning_rate": 0.0002,
+      "loss": 1.0684,
+      "step": 560
+    },
+    {
+      "epoch": 0.7028360049321825,
+      "grad_norm": 0.33849895000457764,
+      "learning_rate": 0.0002,
+      "loss": 1.2339,
+      "step": 570
+    },
+    {
+      "epoch": 0.7151664611590629,
+      "grad_norm": 0.34745967388153076,
+      "learning_rate": 0.0002,
+      "loss": 1.1929,
+      "step": 580
+    },
+    {
+      "epoch": 0.7274969173859432,
+      "grad_norm": 0.26041269302368164,
+      "learning_rate": 0.0002,
+      "loss": 1.1158,
+      "step": 590
+    },
+    {
+      "epoch": 0.7398273736128237,
+      "grad_norm": 0.3804777264595032,
+      "learning_rate": 0.0002,
+      "loss": 1.2134,
+      "step": 600
+    },
+    {
+      "epoch": 0.752157829839704,
+      "grad_norm": 0.2456253319978714,
+      "learning_rate": 0.0002,
+      "loss": 1.0606,
+      "step": 610
+    },
+    {
+      "epoch": 0.7644882860665845,
+      "grad_norm": 0.37838423252105713,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 620
+    },
+    {
+      "epoch": 0.7768187422934648,
+      "grad_norm": 0.28105494379997253,
+      "learning_rate": 0.0002,
+      "loss": 1.0556,
+      "step": 630
+    },
+    {
+      "epoch": 0.7891491985203453,
+      "grad_norm": 0.2774018943309784,
+      "learning_rate": 0.0002,
+      "loss": 1.0672,
+      "step": 640
+    },
+    {
+      "epoch": 0.8014796547472256,
+      "grad_norm": 1.8184229135513306,
+      "learning_rate": 0.0002,
+      "loss": 0.9978,
+      "step": 650
+    },
+    {
+      "epoch": 0.813810110974106,
+      "grad_norm": 0.3325096070766449,
+      "learning_rate": 0.0002,
+      "loss": 1.1038,
+      "step": 660
+    },
+    {
+      "epoch": 0.8261405672009864,
+      "grad_norm": 0.2686693072319031,
+      "learning_rate": 0.0002,
+      "loss": 1.083,
+      "step": 670
+    },
+    {
+      "epoch": 0.8384710234278668,
+      "grad_norm": 0.3271431624889374,
+      "learning_rate": 0.0002,
+      "loss": 1.1308,
+      "step": 680
+    },
+    {
+      "epoch": 0.8508014796547472,
+      "grad_norm": 2.359999656677246,
+      "learning_rate": 0.0002,
+      "loss": 1.1116,
+      "step": 690
+    },
+    {
+      "epoch": 0.8631319358816276,
+      "grad_norm": 0.46242964267730713,
+      "learning_rate": 0.0002,
+      "loss": 1.0782,
+      "step": 700
+    },
+    {
+      "epoch": 0.8754623921085081,
+      "grad_norm": 0.34731170535087585,
+      "learning_rate": 0.0002,
+      "loss": 0.95,
+      "step": 710
+    },
+    {
+      "epoch": 0.8877928483353884,
+      "grad_norm": 0.39381715655326843,
+      "learning_rate": 0.0002,
+      "loss": 1.2236,
+      "step": 720
+    },
+    {
+      "epoch": 0.9001233045622689,
+      "grad_norm": 0.43496373295783997,
+      "learning_rate": 0.0002,
+      "loss": 1.1319,
+      "step": 730
+    },
+    {
+      "epoch": 0.9124537607891492,
+      "grad_norm": 0.32243210077285767,
+      "learning_rate": 0.0002,
+      "loss": 1.0979,
+      "step": 740
+    },
+    {
+      "epoch": 0.9247842170160296,
+      "grad_norm": 0.30396756529808044,
+      "learning_rate": 0.0002,
+      "loss": 0.9913,
+      "step": 750
+    },
+    {
+      "epoch": 0.93711467324291,
+      "grad_norm": 0.4461122751235962,
+      "learning_rate": 0.0002,
+      "loss": 1.1141,
+      "step": 760
+    },
+    {
+      "epoch": 0.9494451294697904,
+      "grad_norm": 0.24081681668758392,
+      "learning_rate": 0.0002,
+      "loss": 1.0049,
+      "step": 770
+    },
+    {
+      "epoch": 0.9617755856966708,
+      "grad_norm": 0.27461910247802734,
+      "learning_rate": 0.0002,
+      "loss": 1.0966,
+      "step": 780
+    },
+    {
+      "epoch": 0.9741060419235512,
+      "grad_norm": 0.3325668275356293,
+      "learning_rate": 0.0002,
+      "loss": 0.9942,
+      "step": 790
+    },
+    {
+      "epoch": 0.9864364981504316,
+      "grad_norm": 0.24046339094638824,
+      "learning_rate": 0.0002,
+      "loss": 1.0506,
+      "step": 800
+    },
+    {
+      "epoch": 0.998766954377312,
+      "grad_norm": 0.42950066924095154,
+      "learning_rate": 0.0002,
+      "loss": 0.9989,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.246457576751709,
+      "eval_runtime": 98.7974,
+      "eval_samples_per_second": 4.413,
+      "eval_steps_per_second": 0.557,
+      "step": 811
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6488,
+  "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": 4.165599770443776e+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-0.6-num-5885-sd-10000/checkpoint-811/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-0.6-num-5885-sd-10000/checkpoint-811/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..459ba5959a39ea126110113c9faed75cda19ffff
--- /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-0.6-num-5885-sd-10000/checkpoint-811/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05287f447dfde244c1a85dc0f576593b4a9dd61961eb0797da4844688fc48447
+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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22
--- /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-0.6-num-5885-sd-10000/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873
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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..459ba5959a39ea126110113c9faed75cda19ffff
--- /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-0.6-num-5885-sd-10000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05287f447dfde244c1a85dc0f576593b4a9dd61961eb0797da4844688fc48447
+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-0.6-num-5885-sd-10000/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-0.6-num-5885-sd-10000/training_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..bae6098617f67718b80fe759fa31675595f31ded
--- /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-0.6-num-5885-sd-10000/training_log.jsonl
@@ -0,0 +1,8 @@
+{"epoch": 1.0, "step": 811, "epoch_duration": 2476.3049235343933, "total_accumulated_duration": 2476.3049235343933, "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": 12786.0}, "peak_memory_reserved": {"GPU_0": 12786.0}, "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": 2.3601, "grad_norm": 0.8258164525032043, "learning_rate": 0.0002, "epoch": 0.012330456226880395, "step": 10}, {"loss": 1.7317, "grad_norm": 0.4577729105949402, "learning_rate": 0.0002, "epoch": 0.02466091245376079, "step": 20}, {"loss": 1.4729, "grad_norm": 0.639807939529419, "learning_rate": 0.0002, "epoch": 0.036991368680641186, "step": 30}, {"loss": 1.2088, "grad_norm": 0.5311757922172546, "learning_rate": 0.0002, "epoch": 0.04932182490752158, "step": 40}, {"loss": 1.3149, "grad_norm": 0.386595219373703, "learning_rate": 0.0002, "epoch": 0.06165228113440197, "step": 50}, {"loss": 1.1657, "grad_norm": 0.4401357173919678, "learning_rate": 0.0002, "epoch": 0.07398273736128237, "step": 60}, {"loss": 1.1022, "grad_norm": 0.3234352171421051, "learning_rate": 0.0002, "epoch": 0.08631319358816276, "step": 70}, {"loss": 1.3738, "grad_norm": 0.29643672704696655, "learning_rate": 0.0002, "epoch": 0.09864364981504316, "step": 80}, {"loss": 1.1929, "grad_norm": 0.2941012382507324, "learning_rate": 0.0002, "epoch": 0.11097410604192355, "step": 90}, {"loss": 1.2067, "grad_norm": 0.5498173832893372, "learning_rate": 0.0002, "epoch": 0.12330456226880394, "step": 100}, {"loss": 1.142, "grad_norm": 0.2545783519744873, "learning_rate": 0.0002, "epoch": 0.13563501849568435, "step": 110}, {"loss": 1.0297, "grad_norm": 0.2984241247177124, "learning_rate": 0.0002, "epoch": 0.14796547472256474, "step": 120}, {"loss": 1.1591, "grad_norm": 0.2710968852043152, "learning_rate": 0.0002, "epoch": 0.16029593094944514, "step": 130}, {"loss": 1.0427, "grad_norm": 0.2817152142524719, "learning_rate": 0.0002, "epoch": 0.17262638717632553, "step": 140}, {"loss": 1.0638, "grad_norm": 0.41083765029907227, "learning_rate": 0.0002, "epoch": 0.18495684340320592, "step": 150}, {"loss": 1.3537, "grad_norm": 0.36536213755607605, "learning_rate": 0.0002, "epoch": 0.19728729963008632, "step": 160}, {"loss": 1.0132, "grad_norm": 0.2738671600818634, "learning_rate": 0.0002, "epoch": 0.2096177558569667, "step": 170}, {"loss": 0.9555, "grad_norm": 0.27403146028518677, "learning_rate": 0.0002, "epoch": 0.2219482120838471, "step": 180}, {"loss": 1.0769, "grad_norm": 0.4446810483932495, "learning_rate": 0.0002, "epoch": 0.2342786683107275, "step": 190}, {"loss": 1.0588, "grad_norm": 0.5295385718345642, "learning_rate": 0.0002, "epoch": 0.2466091245376079, "step": 200}, {"loss": 1.0827, "grad_norm": 0.311404824256897, "learning_rate": 0.0002, "epoch": 0.2589395807644883, "step": 210}, {"loss": 1.1455, "grad_norm": 0.2448509782552719, "learning_rate": 0.0002, "epoch": 0.2712700369913687, "step": 220}, {"loss": 1.0929, "grad_norm": 0.6507014036178589, "learning_rate": 0.0002, "epoch": 0.2836004932182491, "step": 230}, {"loss": 0.9875, "grad_norm": 0.2339320331811905, "learning_rate": 0.0002, "epoch": 0.2959309494451295, "step": 240}, {"loss": 0.9211, "grad_norm": 0.8210226893424988, "learning_rate": 0.0002, "epoch": 0.3082614056720099, "step": 250}, {"loss": 1.161, "grad_norm": 0.27473965287208557, "learning_rate": 0.0002, "epoch": 0.3205918618988903, "step": 260}, {"loss": 1.0218, "grad_norm": 0.3051395118236542, "learning_rate": 0.0002, "epoch": 0.33292231812577067, "step": 270}, {"loss": 1.0286, "grad_norm": 0.3037777245044708, "learning_rate": 0.0002, "epoch": 0.34525277435265106, "step": 280}, {"loss": 1.144, "grad_norm": 0.2748974859714508, "learning_rate": 0.0002, "epoch": 0.35758323057953145, "step": 290}, {"loss": 1.0858, "grad_norm": 0.23656068742275238, "learning_rate": 0.0002, "epoch": 0.36991368680641185, "step": 300}, {"loss": 1.0564, "grad_norm": 0.2523384094238281, "learning_rate": 0.0002, "epoch": 0.38224414303329224, "step": 310}, {"loss": 1.3091, "grad_norm": 0.27848055958747864, "learning_rate": 0.0002, "epoch": 0.39457459926017263, "step": 320}, {"loss": 1.0252, "grad_norm": 0.3204525411128998, "learning_rate": 0.0002, "epoch": 0.406905055487053, "step": 330}, {"loss": 0.9855, "grad_norm": 0.3459707498550415, "learning_rate": 0.0002, "epoch": 0.4192355117139334, "step": 340}, {"loss": 1.1111, "grad_norm": 0.2458430379629135, "learning_rate": 0.0002, "epoch": 0.4315659679408138, "step": 350}, {"loss": 1.1493, "grad_norm": 0.5022910237312317, "learning_rate": 0.0002, "epoch": 0.4438964241676942, "step": 360}, {"loss": 1.1272, "grad_norm": 0.27076372504234314, "learning_rate": 0.0002, "epoch": 0.4562268803945746, "step": 370}, {"loss": 1.1927, "grad_norm": 0.6489047408103943, "learning_rate": 0.0002, "epoch": 0.468557336621455, "step": 380}, {"loss": 0.9501, "grad_norm": 0.3324144184589386, "learning_rate": 0.0002, "epoch": 0.4808877928483354, "step": 390}, {"loss": 1.2012, "grad_norm": 0.32813116908073425, "learning_rate": 0.0002, "epoch": 0.4932182490752158, "step": 400}, {"loss": 1.1135, "grad_norm": 0.25295355916023254, "learning_rate": 0.0002, "epoch": 0.5055487053020962, "step": 410}, {"loss": 0.9477, "grad_norm": 0.2912578880786896, "learning_rate": 0.0002, "epoch": 0.5178791615289766, "step": 420}, {"loss": 1.0121, "grad_norm": 0.34780189394950867, "learning_rate": 0.0002, "epoch": 0.530209617755857, "step": 430}, {"loss": 0.9296, "grad_norm": 0.24604526162147522, "learning_rate": 0.0002, "epoch": 0.5425400739827374, "step": 440}, {"loss": 1.253, "grad_norm": 0.32759982347488403, "learning_rate": 0.0002, "epoch": 0.5548705302096177, "step": 450}, {"loss": 1.1925, "grad_norm": 0.40810221433639526, "learning_rate": 0.0002, "epoch": 0.5672009864364982, "step": 460}, {"loss": 1.174, "grad_norm": 0.3590679466724396, "learning_rate": 0.0002, "epoch": 0.5795314426633785, "step": 470}, {"loss": 1.2223, "grad_norm": 0.5656213760375977, "learning_rate": 0.0002, "epoch": 0.591861898890259, "step": 480}, {"loss": 1.1936, "grad_norm": 0.30830657482147217, "learning_rate": 0.0002, "epoch": 0.6041923551171393, "step": 490}, {"loss": 1.1873, "grad_norm": 0.317905455827713, "learning_rate": 0.0002, "epoch": 0.6165228113440198, "step": 500}, {"loss": 0.9805, "grad_norm": 0.3254566490650177, "learning_rate": 0.0002, "epoch": 0.6288532675709001, "step": 510}, {"loss": 1.0384, "grad_norm": 0.29187721014022827, "learning_rate": 0.0002, "epoch": 0.6411837237977805, "step": 520}, {"loss": 1.2526, "grad_norm": 0.3439238965511322, "learning_rate": 0.0002, "epoch": 0.6535141800246609, "step": 530}, {"loss": 1.0698, "grad_norm": 0.20970556139945984, "learning_rate": 0.0002, "epoch": 0.6658446362515413, "step": 540}, {"loss": 1.1047, "grad_norm": 0.4022853374481201, "learning_rate": 0.0002, "epoch": 0.6781750924784217, "step": 550}, {"loss": 1.0684, "grad_norm": 0.2235759049654007, "learning_rate": 0.0002, "epoch": 0.6905055487053021, "step": 560}, {"loss": 1.2339, "grad_norm": 0.33849895000457764, "learning_rate": 0.0002, "epoch": 0.7028360049321825, "step": 570}, {"loss": 1.1929, "grad_norm": 0.34745967388153076, "learning_rate": 0.0002, "epoch": 0.7151664611590629, "step": 580}, {"loss": 1.1158, "grad_norm": 0.26041269302368164, "learning_rate": 0.0002, "epoch": 0.7274969173859432, "step": 590}, {"loss": 1.2134, "grad_norm": 0.3804777264595032, "learning_rate": 0.0002, "epoch": 0.7398273736128237, "step": 600}, {"loss": 1.0606, "grad_norm": 0.2456253319978714, "learning_rate": 0.0002, "epoch": 0.752157829839704, "step": 610}, {"loss": 1.0638, "grad_norm": 0.37838423252105713, "learning_rate": 0.0002, "epoch": 0.7644882860665845, "step": 620}, {"loss": 1.0556, "grad_norm": 0.28105494379997253, "learning_rate": 0.0002, "epoch": 0.7768187422934648, "step": 630}, {"loss": 1.0672, "grad_norm": 0.2774018943309784, "learning_rate": 0.0002, "epoch": 0.7891491985203453, "step": 640}, {"loss": 0.9978, "grad_norm": 1.8184229135513306, "learning_rate": 0.0002, "epoch": 0.8014796547472256, "step": 650}, {"loss": 1.1038, "grad_norm": 0.3325096070766449, "learning_rate": 0.0002, "epoch": 0.813810110974106, "step": 660}, {"loss": 1.083, "grad_norm": 0.2686693072319031, "learning_rate": 0.0002, "epoch": 0.8261405672009864, "step": 670}, {"loss": 1.1308, "grad_norm": 0.3271431624889374, "learning_rate": 0.0002, "epoch": 0.8384710234278668, "step": 680}, {"loss": 1.1116, "grad_norm": 2.359999656677246, "learning_rate": 0.0002, "epoch": 0.8508014796547472, "step": 690}, {"loss": 1.0782, "grad_norm": 0.46242964267730713, "learning_rate": 0.0002, "epoch": 0.8631319358816276, "step": 700}, {"loss": 0.95, "grad_norm": 0.34731170535087585, "learning_rate": 0.0002, "epoch": 0.8754623921085081, "step": 710}, {"loss": 1.2236, "grad_norm": 0.39381715655326843, "learning_rate": 0.0002, "epoch": 0.8877928483353884, "step": 720}, {"loss": 1.1319, "grad_norm": 0.43496373295783997, "learning_rate": 0.0002, "epoch": 0.9001233045622689, "step": 730}, {"loss": 1.0979, "grad_norm": 0.32243210077285767, "learning_rate": 0.0002, "epoch": 0.9124537607891492, "step": 740}, {"loss": 0.9913, "grad_norm": 0.30396756529808044, "learning_rate": 0.0002, "epoch": 0.9247842170160296, "step": 750}, {"loss": 1.1141, "grad_norm": 0.4461122751235962, "learning_rate": 0.0002, "epoch": 0.93711467324291, "step": 760}, {"loss": 1.0049, "grad_norm": 0.24081681668758392, "learning_rate": 0.0002, "epoch": 0.9494451294697904, "step": 770}, {"loss": 1.0966, "grad_norm": 0.27461910247802734, "learning_rate": 0.0002, "epoch": 0.9617755856966708, "step": 780}, {"loss": 0.9942, "grad_norm": 0.3325668275356293, "learning_rate": 0.0002, "epoch": 0.9741060419235512, "step": 790}, {"loss": 1.0506, "grad_norm": 0.24046339094638824, "learning_rate": 0.0002, "epoch": 0.9864364981504316, "step": 800}, {"loss": 0.9989, "grad_norm": 0.42950066924095154, "learning_rate": 0.0002, "epoch": 0.998766954377312, "step": 810}]}
+{"epoch": 2.0, "step": 1622, "epoch_duration": 2439.8832573890686, "total_accumulated_duration": 4916.188180923462, "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": 28774.0}, "peak_memory_reserved": {"GPU_0": 28774.0}, "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-0.6-num-5885-sd-10000/checkpoint-811", "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": 2.3601, "grad_norm": 0.8258164525032043, "learning_rate": 0.0002, "epoch": 0.012330456226880395, "step": 10}, {"loss": 1.7317, "grad_norm": 0.4577729105949402, "learning_rate": 0.0002, "epoch": 0.02466091245376079, "step": 20}, {"loss": 1.4729, "grad_norm": 0.639807939529419, "learning_rate": 0.0002, "epoch": 0.036991368680641186, "step": 30}, {"loss": 1.2088, "grad_norm": 0.5311757922172546, "learning_rate": 0.0002, "epoch": 0.04932182490752158, "step": 40}, {"loss": 1.3149, "grad_norm": 0.386595219373703, "learning_rate": 0.0002, "epoch": 0.06165228113440197, "step": 50}, {"loss": 1.1657, "grad_norm": 0.4401357173919678, "learning_rate": 0.0002, "epoch": 0.07398273736128237, "step": 60}, {"loss": 1.1022, "grad_norm": 0.3234352171421051, "learning_rate": 0.0002, "epoch": 0.08631319358816276, "step": 70}, {"loss": 1.3738, "grad_norm": 0.29643672704696655, "learning_rate": 0.0002, "epoch": 0.09864364981504316, "step": 80}, {"loss": 1.1929, "grad_norm": 0.2941012382507324, "learning_rate": 0.0002, "epoch": 0.11097410604192355, "step": 90}, {"loss": 1.2067, "grad_norm": 0.5498173832893372, "learning_rate": 0.0002, "epoch": 0.12330456226880394, "step": 100}, {"loss": 1.142, "grad_norm": 0.2545783519744873, "learning_rate": 0.0002, "epoch": 0.13563501849568435, "step": 110}, {"loss": 1.0297, "grad_norm": 0.2984241247177124, "learning_rate": 0.0002, "epoch": 0.14796547472256474, "step": 120}, {"loss": 1.1591, "grad_norm": 0.2710968852043152, "learning_rate": 0.0002, "epoch": 0.16029593094944514, "step": 130}, {"loss": 1.0427, "grad_norm": 0.2817152142524719, "learning_rate": 0.0002, "epoch": 0.17262638717632553, "step": 140}, {"loss": 1.0638, "grad_norm": 0.41083765029907227, "learning_rate": 0.0002, "epoch": 0.18495684340320592, "step": 150}, {"loss": 1.3537, "grad_norm": 0.36536213755607605, "learning_rate": 0.0002, "epoch": 0.19728729963008632, "step": 160}, {"loss": 1.0132, "grad_norm": 0.2738671600818634, "learning_rate": 0.0002, "epoch": 0.2096177558569667, "step": 170}, {"loss": 0.9555, "grad_norm": 0.27403146028518677, "learning_rate": 0.0002, "epoch": 0.2219482120838471, "step": 180}, {"loss": 1.0769, "grad_norm": 0.4446810483932495, "learning_rate": 0.0002, "epoch": 0.2342786683107275, "step": 190}, {"loss": 1.0588, "grad_norm": 0.5295385718345642, "learning_rate": 0.0002, "epoch": 0.2466091245376079, "step": 200}, {"loss": 1.0827, "grad_norm": 0.311404824256897, "learning_rate": 0.0002, "epoch": 0.2589395807644883, "step": 210}, {"loss": 1.1455, "grad_norm": 0.2448509782552719, "learning_rate": 0.0002, "epoch": 0.2712700369913687, "step": 220}, {"loss": 1.0929, "grad_norm": 0.6507014036178589, "learning_rate": 0.0002, "epoch": 0.2836004932182491, "step": 230}, {"loss": 0.9875, "grad_norm": 0.2339320331811905, "learning_rate": 0.0002, "epoch": 0.2959309494451295, "step": 240}, {"loss": 0.9211, "grad_norm": 0.8210226893424988, "learning_rate": 0.0002, "epoch": 0.3082614056720099, "step": 250}, {"loss": 1.161, "grad_norm": 0.27473965287208557, "learning_rate": 0.0002, "epoch": 0.3205918618988903, "step": 260}, {"loss": 1.0218, "grad_norm": 0.3051395118236542, "learning_rate": 0.0002, "epoch": 0.33292231812577067, "step": 270}, {"loss": 1.0286, "grad_norm": 0.3037777245044708, "learning_rate": 0.0002, "epoch": 0.34525277435265106, "step": 280}, {"loss": 1.144, "grad_norm": 0.2748974859714508, "learning_rate": 0.0002, "epoch": 0.35758323057953145, "step": 290}, {"loss": 1.0858, "grad_norm": 0.23656068742275238, "learning_rate": 0.0002, "epoch": 0.36991368680641185, "step": 300}, {"loss": 1.0564, "grad_norm": 0.2523384094238281, "learning_rate": 0.0002, "epoch": 0.38224414303329224, "step": 310}, {"loss": 1.3091, "grad_norm": 0.27848055958747864, "learning_rate": 0.0002, "epoch": 0.39457459926017263, "step": 320}, {"loss": 1.0252, "grad_norm": 0.3204525411128998, "learning_rate": 0.0002, "epoch": 0.406905055487053, "step": 330}, {"loss": 0.9855, "grad_norm": 0.3459707498550415, "learning_rate": 0.0002, "epoch": 0.4192355117139334, "step": 340}, {"loss": 1.1111, "grad_norm": 0.2458430379629135, "learning_rate": 0.0002, "epoch": 0.4315659679408138, "step": 350}, {"loss": 1.1493, "grad_norm": 0.5022910237312317, "learning_rate": 0.0002, "epoch": 0.4438964241676942, "step": 360}, {"loss": 1.1272, "grad_norm": 0.27076372504234314, "learning_rate": 0.0002, "epoch": 0.4562268803945746, "step": 370}, {"loss": 1.1927, "grad_norm": 0.6489047408103943, "learning_rate": 0.0002, "epoch": 0.468557336621455, "step": 380}, {"loss": 0.9501, "grad_norm": 0.3324144184589386, "learning_rate": 0.0002, "epoch": 0.4808877928483354, "step": 390}, {"loss": 1.2012, "grad_norm": 0.32813116908073425, "learning_rate": 0.0002, "epoch": 0.4932182490752158, "step": 400}, {"loss": 1.1135, "grad_norm": 0.25295355916023254, "learning_rate": 0.0002, "epoch": 0.5055487053020962, "step": 410}, {"loss": 0.9477, "grad_norm": 0.2912578880786896, "learning_rate": 0.0002, "epoch": 0.5178791615289766, "step": 420}, {"loss": 1.0121, "grad_norm": 0.34780189394950867, "learning_rate": 0.0002, "epoch": 0.530209617755857, "step": 430}, {"loss": 0.9296, "grad_norm": 0.24604526162147522, "learning_rate": 0.0002, "epoch": 0.5425400739827374, "step": 440}, {"loss": 1.253, "grad_norm": 0.32759982347488403, "learning_rate": 0.0002, "epoch": 0.5548705302096177, "step": 450}, {"loss": 1.1925, "grad_norm": 0.40810221433639526, "learning_rate": 0.0002, "epoch": 0.5672009864364982, "step": 460}, {"loss": 1.174, "grad_norm": 0.3590679466724396, "learning_rate": 0.0002, "epoch": 0.5795314426633785, "step": 470}, {"loss": 1.2223, "grad_norm": 0.5656213760375977, "learning_rate": 0.0002, "epoch": 0.591861898890259, "step": 480}, {"loss": 1.1936, "grad_norm": 0.30830657482147217, "learning_rate": 0.0002, "epoch": 0.6041923551171393, "step": 490}, {"loss": 1.1873, "grad_norm": 0.317905455827713, "learning_rate": 0.0002, "epoch": 0.6165228113440198, "step": 500}, {"loss": 0.9805, "grad_norm": 0.3254566490650177, "learning_rate": 0.0002, "epoch": 0.6288532675709001, "step": 510}, {"loss": 1.0384, "grad_norm": 0.29187721014022827, "learning_rate": 0.0002, "epoch": 0.6411837237977805, "step": 520}, {"loss": 1.2526, "grad_norm": 0.3439238965511322, "learning_rate": 0.0002, "epoch": 0.6535141800246609, "step": 530}, {"loss": 1.0698, "grad_norm": 0.20970556139945984, "learning_rate": 0.0002, "epoch": 0.6658446362515413, "step": 540}, {"loss": 1.1047, "grad_norm": 0.4022853374481201, "learning_rate": 0.0002, "epoch": 0.6781750924784217, "step": 550}, {"loss": 1.0684, "grad_norm": 0.2235759049654007, "learning_rate": 0.0002, "epoch": 0.6905055487053021, "step": 560}, {"loss": 1.2339, "grad_norm": 0.33849895000457764, "learning_rate": 0.0002, "epoch": 0.7028360049321825, "step": 570}, {"loss": 1.1929, "grad_norm": 0.34745967388153076, "learning_rate": 0.0002, "epoch": 0.7151664611590629, "step": 580}, {"loss": 1.1158, "grad_norm": 0.26041269302368164, "learning_rate": 0.0002, "epoch": 0.7274969173859432, "step": 590}, {"loss": 1.2134, "grad_norm": 0.3804777264595032, "learning_rate": 0.0002, "epoch": 0.7398273736128237, "step": 600}, {"loss": 1.0606, "grad_norm": 0.2456253319978714, "learning_rate": 0.0002, "epoch": 0.752157829839704, "step": 610}, {"loss": 1.0638, "grad_norm": 0.37838423252105713, "learning_rate": 0.0002, "epoch": 0.7644882860665845, "step": 620}, {"loss": 1.0556, "grad_norm": 0.28105494379997253, "learning_rate": 0.0002, "epoch": 0.7768187422934648, "step": 630}, {"loss": 1.0672, "grad_norm": 0.2774018943309784, "learning_rate": 0.0002, "epoch": 0.7891491985203453, "step": 640}, {"loss": 0.9978, "grad_norm": 1.8184229135513306, "learning_rate": 0.0002, "epoch": 0.8014796547472256, "step": 650}, {"loss": 1.1038, "grad_norm": 0.3325096070766449, "learning_rate": 0.0002, "epoch": 0.813810110974106, "step": 660}, {"loss": 1.083, "grad_norm": 0.2686693072319031, "learning_rate": 0.0002, "epoch": 0.8261405672009864, "step": 670}, {"loss": 1.1308, "grad_norm": 0.3271431624889374, "learning_rate": 0.0002, "epoch": 0.8384710234278668, "step": 680}, {"loss": 1.1116, "grad_norm": 2.359999656677246, "learning_rate": 0.0002, "epoch": 0.8508014796547472, "step": 690}, {"loss": 1.0782, "grad_norm": 0.46242964267730713, "learning_rate": 0.0002, "epoch": 0.8631319358816276, "step": 700}, {"loss": 0.95, "grad_norm": 0.34731170535087585, "learning_rate": 0.0002, "epoch": 0.8754623921085081, "step": 710}, {"loss": 1.2236, "grad_norm": 0.39381715655326843, "learning_rate": 0.0002, "epoch": 0.8877928483353884, "step": 720}, {"loss": 1.1319, "grad_norm": 0.43496373295783997, "learning_rate": 0.0002, "epoch": 0.9001233045622689, "step": 730}, {"loss": 1.0979, "grad_norm": 0.32243210077285767, "learning_rate": 0.0002, "epoch": 0.9124537607891492, "step": 740}, {"loss": 0.9913, "grad_norm": 0.30396756529808044, "learning_rate": 0.0002, "epoch": 0.9247842170160296, "step": 750}, {"loss": 1.1141, "grad_norm": 0.4461122751235962, "learning_rate": 0.0002, "epoch": 0.93711467324291, "step": 760}, {"loss": 1.0049, "grad_norm": 0.24081681668758392, "learning_rate": 0.0002, "epoch": 0.9494451294697904, "step": 770}, {"loss": 1.0966, "grad_norm": 0.27461910247802734, "learning_rate": 0.0002, "epoch": 0.9617755856966708, "step": 780}, {"loss": 0.9942, "grad_norm": 0.3325668275356293, "learning_rate": 0.0002, "epoch": 0.9741060419235512, "step": 790}, {"loss": 1.0506, "grad_norm": 0.24046339094638824, "learning_rate": 0.0002, "epoch": 0.9864364981504316, "step": 800}, {"loss": 0.9989, "grad_norm": 0.42950066924095154, "learning_rate": 0.0002, "epoch": 0.998766954377312, "step": 810}, {"eval_loss": 1.246457576751709, "eval_runtime": 98.7974, "eval_samples_per_second": 4.413, "eval_steps_per_second": 0.557, "epoch": 1.0, "step": 811}, {"loss": 1.0536, "grad_norm": 0.26760655641555786, "learning_rate": 0.0002, "epoch": 1.0110974106041923, "step": 820}, {"loss": 0.9722, "grad_norm": 0.4640820026397705, "learning_rate": 0.0002, "epoch": 1.0234278668310728, "step": 830}, {"loss": 0.9392, "grad_norm": 0.2699166238307953, "learning_rate": 0.0002, "epoch": 1.0357583230579532, "step": 840}, {"loss": 0.9335, "grad_norm": 0.3441709578037262, "learning_rate": 0.0002, "epoch": 1.0480887792848335, "step": 850}, {"loss": 0.9083, "grad_norm": 0.299934983253479, "learning_rate": 0.0002, "epoch": 1.060419235511714, "step": 860}, {"loss": 0.9416, "grad_norm": 0.2980666160583496, "learning_rate": 0.0002, "epoch": 1.0727496917385944, "step": 870}, {"loss": 0.94, "grad_norm": 0.3131714463233948, "learning_rate": 0.0002, "epoch": 1.0850801479654748, "step": 880}, {"loss": 0.9288, "grad_norm": 0.29881617426872253, "learning_rate": 0.0002, "epoch": 1.097410604192355, "step": 890}, {"loss": 0.998, "grad_norm": 0.29870888590812683, "learning_rate": 0.0002, "epoch": 1.1097410604192355, "step": 900}, {"loss": 0.9924, "grad_norm": 0.5735140442848206, "learning_rate": 0.0002, "epoch": 1.122071516646116, "step": 910}, {"loss": 1.0694, "grad_norm": 0.33159002661705017, "learning_rate": 0.0002, "epoch": 1.1344019728729964, "step": 920}, {"loss": 1.0069, "grad_norm": 1.235399842262268, "learning_rate": 0.0002, "epoch": 1.1467324290998766, "step": 930}, {"loss": 1.0315, "grad_norm": 0.27469736337661743, "learning_rate": 0.0002, "epoch": 1.159062885326757, "step": 940}, {"loss": 0.9386, "grad_norm": 0.29130664467811584, "learning_rate": 0.0002, "epoch": 1.1713933415536375, "step": 950}, {"loss": 0.8919, "grad_norm": 0.3730354607105255, "learning_rate": 0.0002, "epoch": 1.183723797780518, "step": 960}, {"loss": 0.9988, "grad_norm": 0.5973590612411499, "learning_rate": 0.0002, "epoch": 1.1960542540073984, "step": 970}, {"loss": 0.9525, "grad_norm": 0.39631304144859314, "learning_rate": 0.0002, "epoch": 1.2083847102342786, "step": 980}, {"loss": 0.9217, "grad_norm": 0.849051296710968, "learning_rate": 0.0002, "epoch": 1.220715166461159, "step": 990}, {"loss": 1.0903, "grad_norm": 0.4390525817871094, "learning_rate": 0.0002, "epoch": 1.2330456226880395, "step": 1000}, {"loss": 0.9018, "grad_norm": 0.30423852801322937, "learning_rate": 0.0002, "epoch": 1.2453760789149197, "step": 1010}, {"loss": 1.0128, "grad_norm": 0.34736061096191406, "learning_rate": 0.0002, "epoch": 1.2577065351418002, "step": 1020}, {"loss": 0.9026, "grad_norm": 0.3421604037284851, "learning_rate": 0.0002, "epoch": 1.2700369913686806, "step": 1030}, {"loss": 0.8485, "grad_norm": 0.544170081615448, "learning_rate": 0.0002, "epoch": 1.282367447595561, "step": 1040}, {"loss": 0.9591, "grad_norm": 0.5128790736198425, "learning_rate": 0.0002, "epoch": 1.2946979038224415, "step": 1050}, {"loss": 0.9214, "grad_norm": 0.443344384431839, "learning_rate": 0.0002, "epoch": 1.3070283600493218, "step": 1060}, {"loss": 0.9367, "grad_norm": 0.6380868554115295, "learning_rate": 0.0002, "epoch": 1.3193588162762022, "step": 1070}, {"loss": 0.9849, "grad_norm": 0.4638073146343231, "learning_rate": 0.0002, "epoch": 1.3316892725030827, "step": 1080}, {"loss": 0.8645, "grad_norm": 0.32406893372535706, "learning_rate": 0.0002, "epoch": 1.344019728729963, "step": 1090}, {"loss": 0.8278, "grad_norm": 0.3955065608024597, "learning_rate": 0.0002, "epoch": 1.3563501849568433, "step": 1100}, {"loss": 0.9306, "grad_norm": 0.3489246666431427, "learning_rate": 0.0002, "epoch": 1.3686806411837238, "step": 1110}, {"loss": 1.0138, "grad_norm": 0.48451653122901917, "learning_rate": 0.0002, "epoch": 1.3810110974106042, "step": 1120}, {"loss": 0.9165, "grad_norm": 0.3652360439300537, "learning_rate": 0.0002, "epoch": 1.3933415536374847, "step": 1130}, {"loss": 0.9576, "grad_norm": 1.3097436428070068, "learning_rate": 0.0002, "epoch": 1.405672009864365, "step": 1140}, {"loss": 0.8115, "grad_norm": 0.3647715449333191, "learning_rate": 0.0002, "epoch": 1.4180024660912454, "step": 1150}, {"loss": 0.8573, "grad_norm": 0.37248560786247253, "learning_rate": 0.0002, "epoch": 1.4303329223181258, "step": 1160}, {"loss": 0.936, "grad_norm": 0.4639643430709839, "learning_rate": 0.0002, "epoch": 1.442663378545006, "step": 1170}, {"loss": 0.9511, "grad_norm": 0.5455219745635986, "learning_rate": 0.0002, "epoch": 1.4549938347718865, "step": 1180}, {"loss": 0.8611, "grad_norm": 0.38862571120262146, "learning_rate": 0.0002, "epoch": 1.467324290998767, "step": 1190}, {"loss": 0.8681, "grad_norm": 0.37586215138435364, "learning_rate": 0.0002, "epoch": 1.4796547472256474, "step": 1200}, {"loss": 0.8673, "grad_norm": 0.46244436502456665, "learning_rate": 0.0002, "epoch": 1.4919852034525278, "step": 1210}, {"loss": 0.9388, "grad_norm": 0.3570359945297241, "learning_rate": 0.0002, "epoch": 1.504315659679408, "step": 1220}, {"loss": 0.971, "grad_norm": 0.28393083810806274, "learning_rate": 0.0002, "epoch": 1.5166461159062885, "step": 1230}, {"loss": 0.9296, "grad_norm": 0.5672869682312012, "learning_rate": 0.0002, "epoch": 1.528976572133169, "step": 1240}, {"loss": 0.8787, "grad_norm": 0.41605108976364136, "learning_rate": 0.0002, "epoch": 1.5413070283600492, "step": 1250}, {"loss": 0.8744, "grad_norm": 0.40657493472099304, "learning_rate": 0.0002, "epoch": 1.5536374845869299, "step": 1260}, {"loss": 0.9046, "grad_norm": 0.43672341108322144, "learning_rate": 0.0002, "epoch": 1.56596794081381, "step": 1270}, {"loss": 0.8586, "grad_norm": 0.3065410554409027, "learning_rate": 0.0002, "epoch": 1.5782983970406905, "step": 1280}, {"loss": 0.9499, "grad_norm": 0.37826645374298096, "learning_rate": 0.0002, "epoch": 1.590628853267571, "step": 1290}, {"loss": 0.901, "grad_norm": 0.42307335138320923, "learning_rate": 0.0002, "epoch": 1.6029593094944512, "step": 1300}, {"loss": 0.8673, "grad_norm": 0.3648843467235565, "learning_rate": 0.0002, "epoch": 1.6152897657213316, "step": 1310}, {"loss": 0.9302, "grad_norm": 0.8921076059341431, "learning_rate": 0.0002, "epoch": 1.627620221948212, "step": 1320}, {"loss": 0.9378, "grad_norm": 0.37522226572036743, "learning_rate": 0.0002, "epoch": 1.6399506781750923, "step": 1330}, {"loss": 0.8921, "grad_norm": 0.7489957809448242, "learning_rate": 0.0002, "epoch": 1.652281134401973, "step": 1340}, {"loss": 0.9297, "grad_norm": 0.31733131408691406, "learning_rate": 0.0002, "epoch": 1.6646115906288532, "step": 1350}, {"loss": 0.907, "grad_norm": 0.3249478340148926, "learning_rate": 0.0002, "epoch": 1.6769420468557337, "step": 1360}, {"loss": 1.0197, "grad_norm": 0.3178001344203949, "learning_rate": 0.0002, "epoch": 1.6892725030826141, "step": 1370}, {"loss": 1.0781, "grad_norm": 0.5674093961715698, "learning_rate": 0.0002, "epoch": 1.7016029593094943, "step": 1380}, {"loss": 0.8972, "grad_norm": 0.35272449254989624, "learning_rate": 0.0002, "epoch": 1.7139334155363748, "step": 1390}, {"loss": 0.9346, "grad_norm": 0.5778217911720276, "learning_rate": 0.0002, "epoch": 1.7262638717632552, "step": 1400}, {"loss": 0.9099, "grad_norm": 0.33561450242996216, "learning_rate": 0.0002, "epoch": 1.7385943279901355, "step": 1410}, {"loss": 0.8636, "grad_norm": 0.31735464930534363, "learning_rate": 0.0002, "epoch": 1.7509247842170161, "step": 1420}, {"loss": 0.982, "grad_norm": 1.0612670183181763, "learning_rate": 0.0002, "epoch": 1.7632552404438964, "step": 1430}, {"loss": 0.8224, "grad_norm": 0.5442509651184082, "learning_rate": 0.0002, "epoch": 1.7755856966707768, "step": 1440}, {"loss": 0.9275, "grad_norm": 0.7471332550048828, "learning_rate": 0.0002, "epoch": 1.7879161528976573, "step": 1450}, {"loss": 0.9389, "grad_norm": 0.4323609173297882, "learning_rate": 0.0002, "epoch": 1.8002466091245375, "step": 1460}, {"loss": 0.8247, "grad_norm": 0.47796759009361267, "learning_rate": 0.0002, "epoch": 1.8125770653514182, "step": 1470}, {"loss": 0.9395, "grad_norm": 0.3348400592803955, "learning_rate": 0.0002, "epoch": 1.8249075215782984, "step": 1480}, {"loss": 0.9793, "grad_norm": 0.3354550898075104, "learning_rate": 0.0002, "epoch": 1.8372379778051788, "step": 1490}, {"loss": 0.8581, "grad_norm": 0.5988477468490601, "learning_rate": 0.0002, "epoch": 1.8495684340320593, "step": 1500}, {"loss": 0.9268, "grad_norm": 0.5222318172454834, "learning_rate": 0.0002, "epoch": 1.8618988902589395, "step": 1510}, {"loss": 0.8846, "grad_norm": 0.5246642827987671, "learning_rate": 0.0002, "epoch": 1.87422934648582, "step": 1520}, {"loss": 0.9317, "grad_norm": 0.3164594769477844, "learning_rate": 0.0002, "epoch": 1.8865598027127004, "step": 1530}, {"loss": 0.9961, "grad_norm": 0.3496174216270447, "learning_rate": 0.0002, "epoch": 1.8988902589395806, "step": 1540}, {"loss": 0.9057, "grad_norm": 0.8863359689712524, "learning_rate": 0.0002, "epoch": 1.9112207151664613, "step": 1550}, {"loss": 0.9405, "grad_norm": 0.3587026298046112, "learning_rate": 0.0002, "epoch": 1.9235511713933415, "step": 1560}, {"loss": 0.8335, "grad_norm": 0.6052881479263306, "learning_rate": 0.0002, "epoch": 1.935881627620222, "step": 1570}, {"loss": 0.8805, "grad_norm": 0.567269504070282, "learning_rate": 0.0002, "epoch": 1.9482120838471024, "step": 1580}, {"loss": 0.9581, "grad_norm": 0.45184487104415894, "learning_rate": 0.0002, "epoch": 1.9605425400739827, "step": 1590}, {"loss": 0.9147, "grad_norm": 0.5028569102287292, "learning_rate": 0.0002, "epoch": 1.972872996300863, "step": 1600}, {"loss": 0.75, "grad_norm": 0.4677547216415405, "learning_rate": 0.0002, "epoch": 1.9852034525277436, "step": 1610}, {"loss": 0.8469, "grad_norm": 0.35106056928634644, "learning_rate": 0.0002, "epoch": 1.9975339087546238, "step": 1620}]}
+{"epoch": 3.0, "step": 2433, "epoch_duration": 2425.9265751838684, "total_accumulated_duration": 7342.11475610733, "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": 28774.0}, "peak_memory_reserved": {"GPU_0": 28774.0}, "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-0.6-num-5885-sd-10000/checkpoint-1622", "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": 2.3601, "grad_norm": 0.8258164525032043, "learning_rate": 0.0002, "epoch": 0.012330456226880395, "step": 10}, {"loss": 1.7317, "grad_norm": 0.4577729105949402, "learning_rate": 0.0002, "epoch": 0.02466091245376079, "step": 20}, {"loss": 1.4729, "grad_norm": 0.639807939529419, "learning_rate": 0.0002, "epoch": 0.036991368680641186, "step": 30}, {"loss": 1.2088, "grad_norm": 0.5311757922172546, "learning_rate": 0.0002, "epoch": 0.04932182490752158, "step": 40}, {"loss": 1.3149, "grad_norm": 0.386595219373703, "learning_rate": 0.0002, "epoch": 0.06165228113440197, "step": 50}, {"loss": 1.1657, "grad_norm": 0.4401357173919678, "learning_rate": 0.0002, "epoch": 0.07398273736128237, "step": 60}, {"loss": 1.1022, "grad_norm": 0.3234352171421051, "learning_rate": 0.0002, "epoch": 0.08631319358816276, "step": 70}, {"loss": 1.3738, "grad_norm": 0.29643672704696655, "learning_rate": 0.0002, "epoch": 0.09864364981504316, "step": 80}, {"loss": 1.1929, "grad_norm": 0.2941012382507324, "learning_rate": 0.0002, "epoch": 0.11097410604192355, "step": 90}, {"loss": 1.2067, "grad_norm": 0.5498173832893372, "learning_rate": 0.0002, "epoch": 0.12330456226880394, "step": 100}, {"loss": 1.142, "grad_norm": 0.2545783519744873, "learning_rate": 0.0002, "epoch": 0.13563501849568435, "step": 110}, {"loss": 1.0297, "grad_norm": 0.2984241247177124, "learning_rate": 0.0002, "epoch": 0.14796547472256474, "step": 120}, {"loss": 1.1591, "grad_norm": 0.2710968852043152, "learning_rate": 0.0002, "epoch": 0.16029593094944514, "step": 130}, {"loss": 1.0427, "grad_norm": 0.2817152142524719, "learning_rate": 0.0002, "epoch": 0.17262638717632553, "step": 140}, {"loss": 1.0638, "grad_norm": 0.41083765029907227, "learning_rate": 0.0002, "epoch": 0.18495684340320592, "step": 150}, {"loss": 1.3537, "grad_norm": 0.36536213755607605, "learning_rate": 0.0002, "epoch": 0.19728729963008632, "step": 160}, {"loss": 1.0132, "grad_norm": 0.2738671600818634, "learning_rate": 0.0002, "epoch": 0.2096177558569667, "step": 170}, {"loss": 0.9555, "grad_norm": 0.27403146028518677, "learning_rate": 0.0002, "epoch": 0.2219482120838471, "step": 180}, {"loss": 1.0769, "grad_norm": 0.4446810483932495, "learning_rate": 0.0002, "epoch": 0.2342786683107275, "step": 190}, {"loss": 1.0588, "grad_norm": 0.5295385718345642, "learning_rate": 0.0002, "epoch": 0.2466091245376079, "step": 200}, {"loss": 1.0827, "grad_norm": 0.311404824256897, "learning_rate": 0.0002, "epoch": 0.2589395807644883, "step": 210}, {"loss": 1.1455, "grad_norm": 0.2448509782552719, "learning_rate": 0.0002, "epoch": 0.2712700369913687, "step": 220}, {"loss": 1.0929, "grad_norm": 0.6507014036178589, "learning_rate": 0.0002, "epoch": 0.2836004932182491, "step": 230}, {"loss": 0.9875, "grad_norm": 0.2339320331811905, "learning_rate": 0.0002, "epoch": 0.2959309494451295, "step": 240}, {"loss": 0.9211, "grad_norm": 0.8210226893424988, "learning_rate": 0.0002, "epoch": 0.3082614056720099, "step": 250}, {"loss": 1.161, "grad_norm": 0.27473965287208557, "learning_rate": 0.0002, "epoch": 0.3205918618988903, "step": 260}, {"loss": 1.0218, "grad_norm": 0.3051395118236542, "learning_rate": 0.0002, "epoch": 0.33292231812577067, "step": 270}, {"loss": 1.0286, "grad_norm": 0.3037777245044708, "learning_rate": 0.0002, "epoch": 0.34525277435265106, "step": 280}, {"loss": 1.144, "grad_norm": 0.2748974859714508, "learning_rate": 0.0002, "epoch": 0.35758323057953145, "step": 290}, {"loss": 1.0858, "grad_norm": 0.23656068742275238, "learning_rate": 0.0002, "epoch": 0.36991368680641185, "step": 300}, {"loss": 1.0564, "grad_norm": 0.2523384094238281, "learning_rate": 0.0002, "epoch": 0.38224414303329224, "step": 310}, {"loss": 1.3091, "grad_norm": 0.27848055958747864, "learning_rate": 0.0002, "epoch": 0.39457459926017263, "step": 320}, {"loss": 1.0252, "grad_norm": 0.3204525411128998, "learning_rate": 0.0002, "epoch": 0.406905055487053, "step": 330}, {"loss": 0.9855, "grad_norm": 0.3459707498550415, "learning_rate": 0.0002, "epoch": 0.4192355117139334, "step": 340}, {"loss": 1.1111, "grad_norm": 0.2458430379629135, "learning_rate": 0.0002, "epoch": 0.4315659679408138, "step": 350}, {"loss": 1.1493, "grad_norm": 0.5022910237312317, "learning_rate": 0.0002, "epoch": 0.4438964241676942, "step": 360}, {"loss": 1.1272, "grad_norm": 0.27076372504234314, "learning_rate": 0.0002, "epoch": 0.4562268803945746, "step": 370}, {"loss": 1.1927, "grad_norm": 0.6489047408103943, "learning_rate": 0.0002, "epoch": 0.468557336621455, "step": 380}, {"loss": 0.9501, "grad_norm": 0.3324144184589386, "learning_rate": 0.0002, "epoch": 0.4808877928483354, "step": 390}, {"loss": 1.2012, "grad_norm": 0.32813116908073425, "learning_rate": 0.0002, "epoch": 0.4932182490752158, "step": 400}, {"loss": 1.1135, "grad_norm": 0.25295355916023254, "learning_rate": 0.0002, "epoch": 0.5055487053020962, "step": 410}, {"loss": 0.9477, "grad_norm": 0.2912578880786896, "learning_rate": 0.0002, "epoch": 0.5178791615289766, "step": 420}, {"loss": 1.0121, "grad_norm": 0.34780189394950867, "learning_rate": 0.0002, "epoch": 0.530209617755857, "step": 430}, {"loss": 0.9296, "grad_norm": 0.24604526162147522, "learning_rate": 0.0002, "epoch": 0.5425400739827374, "step": 440}, {"loss": 1.253, "grad_norm": 0.32759982347488403, "learning_rate": 0.0002, "epoch": 0.5548705302096177, "step": 450}, {"loss": 1.1925, "grad_norm": 0.40810221433639526, "learning_rate": 0.0002, "epoch": 0.5672009864364982, "step": 460}, {"loss": 1.174, "grad_norm": 0.3590679466724396, "learning_rate": 0.0002, "epoch": 0.5795314426633785, "step": 470}, {"loss": 1.2223, "grad_norm": 0.5656213760375977, "learning_rate": 0.0002, "epoch": 0.591861898890259, "step": 480}, {"loss": 1.1936, "grad_norm": 0.30830657482147217, "learning_rate": 0.0002, "epoch": 0.6041923551171393, "step": 490}, {"loss": 1.1873, "grad_norm": 0.317905455827713, "learning_rate": 0.0002, "epoch": 0.6165228113440198, "step": 500}, {"loss": 0.9805, "grad_norm": 0.3254566490650177, "learning_rate": 0.0002, "epoch": 0.6288532675709001, "step": 510}, {"loss": 1.0384, "grad_norm": 0.29187721014022827, "learning_rate": 0.0002, "epoch": 0.6411837237977805, "step": 520}, {"loss": 1.2526, "grad_norm": 0.3439238965511322, "learning_rate": 0.0002, "epoch": 0.6535141800246609, "step": 530}, {"loss": 1.0698, "grad_norm": 0.20970556139945984, "learning_rate": 0.0002, "epoch": 0.6658446362515413, "step": 540}, {"loss": 1.1047, "grad_norm": 0.4022853374481201, "learning_rate": 0.0002, "epoch": 0.6781750924784217, "step": 550}, {"loss": 1.0684, "grad_norm": 0.2235759049654007, "learning_rate": 0.0002, "epoch": 0.6905055487053021, "step": 560}, {"loss": 1.2339, "grad_norm": 0.33849895000457764, "learning_rate": 0.0002, "epoch": 0.7028360049321825, "step": 570}, {"loss": 1.1929, "grad_norm": 0.34745967388153076, "learning_rate": 0.0002, "epoch": 0.7151664611590629, "step": 580}, {"loss": 1.1158, "grad_norm": 0.26041269302368164, "learning_rate": 0.0002, "epoch": 0.7274969173859432, "step": 590}, {"loss": 1.2134, "grad_norm": 0.3804777264595032, "learning_rate": 0.0002, "epoch": 0.7398273736128237, "step": 600}, {"loss": 1.0606, "grad_norm": 0.2456253319978714, "learning_rate": 0.0002, "epoch": 0.752157829839704, "step": 610}, {"loss": 1.0638, "grad_norm": 0.37838423252105713, "learning_rate": 0.0002, "epoch": 0.7644882860665845, "step": 620}, {"loss": 1.0556, "grad_norm": 0.28105494379997253, "learning_rate": 0.0002, "epoch": 0.7768187422934648, "step": 630}, {"loss": 1.0672, "grad_norm": 0.2774018943309784, "learning_rate": 0.0002, "epoch": 0.7891491985203453, "step": 640}, {"loss": 0.9978, "grad_norm": 1.8184229135513306, "learning_rate": 0.0002, "epoch": 0.8014796547472256, "step": 650}, {"loss": 1.1038, "grad_norm": 0.3325096070766449, "learning_rate": 0.0002, "epoch": 0.813810110974106, "step": 660}, {"loss": 1.083, "grad_norm": 0.2686693072319031, "learning_rate": 0.0002, "epoch": 0.8261405672009864, "step": 670}, {"loss": 1.1308, "grad_norm": 0.3271431624889374, "learning_rate": 0.0002, "epoch": 0.8384710234278668, "step": 680}, {"loss": 1.1116, "grad_norm": 2.359999656677246, "learning_rate": 0.0002, "epoch": 0.8508014796547472, "step": 690}, {"loss": 1.0782, "grad_norm": 0.46242964267730713, "learning_rate": 0.0002, "epoch": 0.8631319358816276, "step": 700}, {"loss": 0.95, "grad_norm": 0.34731170535087585, "learning_rate": 0.0002, "epoch": 0.8754623921085081, "step": 710}, {"loss": 1.2236, "grad_norm": 0.39381715655326843, "learning_rate": 0.0002, "epoch": 0.8877928483353884, "step": 720}, {"loss": 1.1319, "grad_norm": 0.43496373295783997, "learning_rate": 0.0002, "epoch": 0.9001233045622689, "step": 730}, {"loss": 1.0979, "grad_norm": 0.32243210077285767, "learning_rate": 0.0002, "epoch": 0.9124537607891492, "step": 740}, {"loss": 0.9913, "grad_norm": 0.30396756529808044, "learning_rate": 0.0002, "epoch": 0.9247842170160296, "step": 750}, {"loss": 1.1141, "grad_norm": 0.4461122751235962, "learning_rate": 0.0002, "epoch": 0.93711467324291, "step": 760}, {"loss": 1.0049, "grad_norm": 0.24081681668758392, "learning_rate": 0.0002, "epoch": 0.9494451294697904, "step": 770}, {"loss": 1.0966, "grad_norm": 0.27461910247802734, "learning_rate": 0.0002, "epoch": 0.9617755856966708, "step": 780}, {"loss": 0.9942, "grad_norm": 0.3325668275356293, "learning_rate": 0.0002, "epoch": 0.9741060419235512, "step": 790}, {"loss": 1.0506, "grad_norm": 0.24046339094638824, "learning_rate": 0.0002, "epoch": 0.9864364981504316, "step": 800}, {"loss": 0.9989, "grad_norm": 0.42950066924095154, "learning_rate": 0.0002, "epoch": 0.998766954377312, "step": 810}, {"eval_loss": 1.246457576751709, "eval_runtime": 98.7974, "eval_samples_per_second": 4.413, "eval_steps_per_second": 0.557, "epoch": 1.0, "step": 811}, {"loss": 1.0536, "grad_norm": 0.26760655641555786, "learning_rate": 0.0002, "epoch": 1.0110974106041923, "step": 820}, {"loss": 0.9722, "grad_norm": 0.4640820026397705, "learning_rate": 0.0002, "epoch": 1.0234278668310728, "step": 830}, {"loss": 0.9392, "grad_norm": 0.2699166238307953, "learning_rate": 0.0002, "epoch": 1.0357583230579532, "step": 840}, {"loss": 0.9335, "grad_norm": 0.3441709578037262, "learning_rate": 0.0002, "epoch": 1.0480887792848335, "step": 850}, {"loss": 0.9083, "grad_norm": 0.299934983253479, "learning_rate": 0.0002, "epoch": 1.060419235511714, "step": 860}, {"loss": 0.9416, "grad_norm": 0.2980666160583496, "learning_rate": 0.0002, "epoch": 1.0727496917385944, "step": 870}, {"loss": 0.94, "grad_norm": 0.3131714463233948, "learning_rate": 0.0002, "epoch": 1.0850801479654748, "step": 880}, {"loss": 0.9288, "grad_norm": 0.29881617426872253, "learning_rate": 0.0002, "epoch": 1.097410604192355, "step": 890}, {"loss": 0.998, "grad_norm": 0.29870888590812683, "learning_rate": 0.0002, "epoch": 1.1097410604192355, "step": 900}, {"loss": 0.9924, "grad_norm": 0.5735140442848206, "learning_rate": 0.0002, "epoch": 1.122071516646116, "step": 910}, {"loss": 1.0694, "grad_norm": 0.33159002661705017, "learning_rate": 0.0002, "epoch": 1.1344019728729964, "step": 920}, {"loss": 1.0069, "grad_norm": 1.235399842262268, "learning_rate": 0.0002, "epoch": 1.1467324290998766, "step": 930}, {"loss": 1.0315, "grad_norm": 0.27469736337661743, "learning_rate": 0.0002, "epoch": 1.159062885326757, "step": 940}, {"loss": 0.9386, "grad_norm": 0.29130664467811584, "learning_rate": 0.0002, "epoch": 1.1713933415536375, "step": 950}, {"loss": 0.8919, "grad_norm": 0.3730354607105255, "learning_rate": 0.0002, "epoch": 1.183723797780518, "step": 960}, {"loss": 0.9988, "grad_norm": 0.5973590612411499, "learning_rate": 0.0002, "epoch": 1.1960542540073984, "step": 970}, {"loss": 0.9525, "grad_norm": 0.39631304144859314, "learning_rate": 0.0002, "epoch": 1.2083847102342786, "step": 980}, {"loss": 0.9217, "grad_norm": 0.849051296710968, "learning_rate": 0.0002, "epoch": 1.220715166461159, "step": 990}, {"loss": 1.0903, "grad_norm": 0.4390525817871094, "learning_rate": 0.0002, "epoch": 1.2330456226880395, "step": 1000}, {"loss": 0.9018, "grad_norm": 0.30423852801322937, "learning_rate": 0.0002, "epoch": 1.2453760789149197, "step": 1010}, {"loss": 1.0128, "grad_norm": 0.34736061096191406, "learning_rate": 0.0002, "epoch": 1.2577065351418002, "step": 1020}, {"loss": 0.9026, "grad_norm": 0.3421604037284851, "learning_rate": 0.0002, "epoch": 1.2700369913686806, "step": 1030}, {"loss": 0.8485, "grad_norm": 0.544170081615448, "learning_rate": 0.0002, "epoch": 1.282367447595561, "step": 1040}, {"loss": 0.9591, "grad_norm": 0.5128790736198425, "learning_rate": 0.0002, "epoch": 1.2946979038224415, "step": 1050}, {"loss": 0.9214, "grad_norm": 0.443344384431839, "learning_rate": 0.0002, "epoch": 1.3070283600493218, "step": 1060}, {"loss": 0.9367, "grad_norm": 0.6380868554115295, "learning_rate": 0.0002, "epoch": 1.3193588162762022, "step": 1070}, {"loss": 0.9849, "grad_norm": 0.4638073146343231, "learning_rate": 0.0002, "epoch": 1.3316892725030827, "step": 1080}, {"loss": 0.8645, "grad_norm": 0.32406893372535706, "learning_rate": 0.0002, "epoch": 1.344019728729963, "step": 1090}, {"loss": 0.8278, "grad_norm": 0.3955065608024597, "learning_rate": 0.0002, "epoch": 1.3563501849568433, "step": 1100}, {"loss": 0.9306, "grad_norm": 0.3489246666431427, "learning_rate": 0.0002, "epoch": 1.3686806411837238, "step": 1110}, {"loss": 1.0138, "grad_norm": 0.48451653122901917, "learning_rate": 0.0002, "epoch": 1.3810110974106042, "step": 1120}, {"loss": 0.9165, "grad_norm": 0.3652360439300537, "learning_rate": 0.0002, "epoch": 1.3933415536374847, "step": 1130}, {"loss": 0.9576, "grad_norm": 1.3097436428070068, "learning_rate": 0.0002, "epoch": 1.405672009864365, "step": 1140}, {"loss": 0.8115, "grad_norm": 0.3647715449333191, "learning_rate": 0.0002, "epoch": 1.4180024660912454, "step": 1150}, {"loss": 0.8573, "grad_norm": 0.37248560786247253, "learning_rate": 0.0002, "epoch": 1.4303329223181258, "step": 1160}, {"loss": 0.936, "grad_norm": 0.4639643430709839, "learning_rate": 0.0002, "epoch": 1.442663378545006, "step": 1170}, {"loss": 0.9511, "grad_norm": 0.5455219745635986, "learning_rate": 0.0002, "epoch": 1.4549938347718865, "step": 1180}, {"loss": 0.8611, "grad_norm": 0.38862571120262146, "learning_rate": 0.0002, "epoch": 1.467324290998767, "step": 1190}, {"loss": 0.8681, "grad_norm": 0.37586215138435364, "learning_rate": 0.0002, "epoch": 1.4796547472256474, "step": 1200}, {"loss": 0.8673, "grad_norm": 0.46244436502456665, "learning_rate": 0.0002, "epoch": 1.4919852034525278, "step": 1210}, {"loss": 0.9388, "grad_norm": 0.3570359945297241, "learning_rate": 0.0002, "epoch": 1.504315659679408, "step": 1220}, {"loss": 0.971, "grad_norm": 0.28393083810806274, "learning_rate": 0.0002, "epoch": 1.5166461159062885, "step": 1230}, {"loss": 0.9296, "grad_norm": 0.5672869682312012, "learning_rate": 0.0002, "epoch": 1.528976572133169, "step": 1240}, {"loss": 0.8787, "grad_norm": 0.41605108976364136, "learning_rate": 0.0002, "epoch": 1.5413070283600492, "step": 1250}, {"loss": 0.8744, "grad_norm": 0.40657493472099304, "learning_rate": 0.0002, "epoch": 1.5536374845869299, "step": 1260}, {"loss": 0.9046, "grad_norm": 0.43672341108322144, "learning_rate": 0.0002, "epoch": 1.56596794081381, "step": 1270}, {"loss": 0.8586, "grad_norm": 0.3065410554409027, "learning_rate": 0.0002, "epoch": 1.5782983970406905, "step": 1280}, {"loss": 0.9499, "grad_norm": 0.37826645374298096, "learning_rate": 0.0002, "epoch": 1.590628853267571, "step": 1290}, {"loss": 0.901, "grad_norm": 0.42307335138320923, "learning_rate": 0.0002, "epoch": 1.6029593094944512, "step": 1300}, {"loss": 0.8673, "grad_norm": 0.3648843467235565, "learning_rate": 0.0002, "epoch": 1.6152897657213316, "step": 1310}, {"loss": 0.9302, "grad_norm": 0.8921076059341431, "learning_rate": 0.0002, "epoch": 1.627620221948212, "step": 1320}, {"loss": 0.9378, "grad_norm": 0.37522226572036743, "learning_rate": 0.0002, "epoch": 1.6399506781750923, "step": 1330}, {"loss": 0.8921, "grad_norm": 0.7489957809448242, "learning_rate": 0.0002, "epoch": 1.652281134401973, "step": 1340}, {"loss": 0.9297, "grad_norm": 0.31733131408691406, "learning_rate": 0.0002, "epoch": 1.6646115906288532, "step": 1350}, {"loss": 0.907, "grad_norm": 0.3249478340148926, "learning_rate": 0.0002, "epoch": 1.6769420468557337, "step": 1360}, {"loss": 1.0197, "grad_norm": 0.3178001344203949, "learning_rate": 0.0002, "epoch": 1.6892725030826141, "step": 1370}, {"loss": 1.0781, "grad_norm": 0.5674093961715698, "learning_rate": 0.0002, "epoch": 1.7016029593094943, "step": 1380}, {"loss": 0.8972, "grad_norm": 0.35272449254989624, "learning_rate": 0.0002, "epoch": 1.7139334155363748, "step": 1390}, {"loss": 0.9346, "grad_norm": 0.5778217911720276, "learning_rate": 0.0002, "epoch": 1.7262638717632552, "step": 1400}, {"loss": 0.9099, "grad_norm": 0.33561450242996216, "learning_rate": 0.0002, "epoch": 1.7385943279901355, "step": 1410}, {"loss": 0.8636, "grad_norm": 0.31735464930534363, "learning_rate": 0.0002, "epoch": 1.7509247842170161, "step": 1420}, {"loss": 0.982, "grad_norm": 1.0612670183181763, "learning_rate": 0.0002, "epoch": 1.7632552404438964, "step": 1430}, {"loss": 0.8224, "grad_norm": 0.5442509651184082, "learning_rate": 0.0002, "epoch": 1.7755856966707768, "step": 1440}, {"loss": 0.9275, "grad_norm": 0.7471332550048828, "learning_rate": 0.0002, "epoch": 1.7879161528976573, "step": 1450}, {"loss": 0.9389, "grad_norm": 0.4323609173297882, "learning_rate": 0.0002, "epoch": 1.8002466091245375, "step": 1460}, {"loss": 0.8247, "grad_norm": 0.47796759009361267, "learning_rate": 0.0002, "epoch": 1.8125770653514182, "step": 1470}, {"loss": 0.9395, "grad_norm": 0.3348400592803955, "learning_rate": 0.0002, "epoch": 1.8249075215782984, "step": 1480}, {"loss": 0.9793, "grad_norm": 0.3354550898075104, "learning_rate": 0.0002, "epoch": 1.8372379778051788, "step": 1490}, {"loss": 0.8581, "grad_norm": 0.5988477468490601, "learning_rate": 0.0002, "epoch": 1.8495684340320593, "step": 1500}, {"loss": 0.9268, "grad_norm": 0.5222318172454834, "learning_rate": 0.0002, "epoch": 1.8618988902589395, "step": 1510}, {"loss": 0.8846, "grad_norm": 0.5246642827987671, "learning_rate": 0.0002, "epoch": 1.87422934648582, "step": 1520}, {"loss": 0.9317, "grad_norm": 0.3164594769477844, "learning_rate": 0.0002, "epoch": 1.8865598027127004, "step": 1530}, {"loss": 0.9961, "grad_norm": 0.3496174216270447, "learning_rate": 0.0002, "epoch": 1.8988902589395806, "step": 1540}, {"loss": 0.9057, "grad_norm": 0.8863359689712524, "learning_rate": 0.0002, "epoch": 1.9112207151664613, "step": 1550}, {"loss": 0.9405, "grad_norm": 0.3587026298046112, "learning_rate": 0.0002, "epoch": 1.9235511713933415, "step": 1560}, {"loss": 0.8335, "grad_norm": 0.6052881479263306, "learning_rate": 0.0002, "epoch": 1.935881627620222, "step": 1570}, {"loss": 0.8805, "grad_norm": 0.567269504070282, "learning_rate": 0.0002, "epoch": 1.9482120838471024, "step": 1580}, {"loss": 0.9581, "grad_norm": 0.45184487104415894, "learning_rate": 0.0002, "epoch": 1.9605425400739827, "step": 1590}, {"loss": 0.9147, "grad_norm": 0.5028569102287292, "learning_rate": 0.0002, "epoch": 1.972872996300863, "step": 1600}, {"loss": 0.75, "grad_norm": 0.4677547216415405, "learning_rate": 0.0002, "epoch": 1.9852034525277436, "step": 1610}, {"loss": 0.8469, "grad_norm": 0.35106056928634644, "learning_rate": 0.0002, "epoch": 1.9975339087546238, "step": 1620}, {"eval_loss": 1.238026738166809, "eval_runtime": 95.4287, "eval_samples_per_second": 4.569, "eval_steps_per_second": 0.576, "epoch": 2.0, "step": 1622}, {"loss": 0.7629, "grad_norm": 0.444060355424881, "learning_rate": 0.0002, "epoch": 2.0098643649815044, "step": 1630}, {"loss": 0.772, "grad_norm": 0.627570390701294, "learning_rate": 0.0002, "epoch": 2.0221948212083847, "step": 1640}, {"loss": 0.6186, "grad_norm": 0.38737839460372925, "learning_rate": 0.0002, "epoch": 2.034525277435265, "step": 1650}, {"loss": 0.7734, "grad_norm": 0.4300459623336792, "learning_rate": 0.0002, "epoch": 2.0468557336621456, "step": 1660}, {"loss": 0.6943, "grad_norm": 0.43037715554237366, "learning_rate": 0.0002, "epoch": 2.059186189889026, "step": 1670}, {"loss": 0.6588, "grad_norm": 0.40772515535354614, "learning_rate": 0.0002, "epoch": 2.0715166461159065, "step": 1680}, {"loss": 0.8105, "grad_norm": 0.5295451879501343, "learning_rate": 0.0002, "epoch": 2.0838471023427867, "step": 1690}, {"loss": 0.7717, "grad_norm": 0.7452750205993652, "learning_rate": 0.0002, "epoch": 2.096177558569667, "step": 1700}, {"loss": 0.7458, "grad_norm": 0.809183657169342, "learning_rate": 0.0002, "epoch": 2.1085080147965476, "step": 1710}, {"loss": 0.7398, "grad_norm": 0.4597688913345337, "learning_rate": 0.0002, "epoch": 2.120838471023428, "step": 1720}, {"loss": 0.6856, "grad_norm": 0.806919276714325, "learning_rate": 0.0002, "epoch": 2.133168927250308, "step": 1730}, {"loss": 0.679, "grad_norm": 0.3755643665790558, "learning_rate": 0.0002, "epoch": 2.1454993834771887, "step": 1740}, {"loss": 0.7938, "grad_norm": 0.5882734060287476, "learning_rate": 0.0002, "epoch": 2.157829839704069, "step": 1750}, {"loss": 0.6782, "grad_norm": 0.692960798740387, "learning_rate": 0.0002, "epoch": 2.1701602959309496, "step": 1760}, {"loss": 0.7195, "grad_norm": 0.4737096428871155, "learning_rate": 0.0002, "epoch": 2.18249075215783, "step": 1770}, {"loss": 0.758, "grad_norm": 0.6637021899223328, "learning_rate": 0.0002, "epoch": 2.19482120838471, "step": 1780}, {"loss": 0.7139, "grad_norm": 0.9109764099121094, "learning_rate": 0.0002, "epoch": 2.2071516646115907, "step": 1790}, {"loss": 0.7373, "grad_norm": 0.4137539267539978, "learning_rate": 0.0002, "epoch": 2.219482120838471, "step": 1800}, {"loss": 0.7266, "grad_norm": 0.44995415210723877, "learning_rate": 0.0002, "epoch": 2.2318125770653516, "step": 1810}, {"loss": 0.7663, "grad_norm": 0.5985036492347717, "learning_rate": 0.0002, "epoch": 2.244143033292232, "step": 1820}, {"loss": 0.7502, "grad_norm": 0.7549490332603455, "learning_rate": 0.0002, "epoch": 2.256473489519112, "step": 1830}, {"loss": 0.7452, "grad_norm": 0.4490937888622284, "learning_rate": 0.0002, "epoch": 2.2688039457459928, "step": 1840}, {"loss": 0.7531, "grad_norm": 0.38859808444976807, "learning_rate": 0.0002, "epoch": 2.281134401972873, "step": 1850}, {"loss": 0.7278, "grad_norm": 1.0704916715621948, "learning_rate": 0.0002, "epoch": 2.293464858199753, "step": 1860}, {"loss": 0.7143, "grad_norm": 0.4647100865840912, "learning_rate": 0.0002, "epoch": 2.305795314426634, "step": 1870}, {"loss": 0.7146, "grad_norm": 0.6181163787841797, "learning_rate": 0.0002, "epoch": 2.318125770653514, "step": 1880}, {"loss": 0.7689, "grad_norm": 0.9241904020309448, "learning_rate": 0.0002, "epoch": 2.3304562268803943, "step": 1890}, {"loss": 0.7294, "grad_norm": 0.39101317524909973, "learning_rate": 0.0002, "epoch": 2.342786683107275, "step": 1900}, {"loss": 0.7079, "grad_norm": 0.49442458152770996, "learning_rate": 0.0002, "epoch": 2.3551171393341552, "step": 1910}, {"loss": 0.7586, "grad_norm": 0.4864824414253235, "learning_rate": 0.0002, "epoch": 2.367447595561036, "step": 1920}, {"loss": 0.7434, "grad_norm": 0.5427613854408264, "learning_rate": 0.0002, "epoch": 2.379778051787916, "step": 1930}, {"loss": 0.8423, "grad_norm": 0.7164974808692932, "learning_rate": 0.0002, "epoch": 2.392108508014797, "step": 1940}, {"loss": 0.6888, "grad_norm": 0.562979519367218, "learning_rate": 0.0002, "epoch": 2.404438964241677, "step": 1950}, {"loss": 0.7692, "grad_norm": 0.5631861090660095, "learning_rate": 0.0002, "epoch": 2.4167694204685573, "step": 1960}, {"loss": 0.67, "grad_norm": 0.4895121157169342, "learning_rate": 0.0002, "epoch": 2.429099876695438, "step": 1970}, {"loss": 0.7735, "grad_norm": 0.45674824714660645, "learning_rate": 0.0002, "epoch": 2.441430332922318, "step": 1980}, {"loss": 0.685, "grad_norm": 1.1424206495285034, "learning_rate": 0.0002, "epoch": 2.4537607891491984, "step": 1990}, {"loss": 0.7627, "grad_norm": 0.6314579844474792, "learning_rate": 0.0002, "epoch": 2.466091245376079, "step": 2000}, {"loss": 0.7118, "grad_norm": 0.5481605529785156, "learning_rate": 0.0002, "epoch": 2.4784217016029593, "step": 2010}, {"loss": 0.6947, "grad_norm": 0.4671579599380493, "learning_rate": 0.0002, "epoch": 2.4907521578298395, "step": 2020}, {"loss": 0.7377, "grad_norm": 0.7621194124221802, "learning_rate": 0.0002, "epoch": 2.50308261405672, "step": 2030}, {"loss": 0.69, "grad_norm": 0.38983288407325745, "learning_rate": 0.0002, "epoch": 2.5154130702836004, "step": 2040}, {"loss": 0.8381, "grad_norm": 0.6341150999069214, "learning_rate": 0.0002, "epoch": 2.5277435265104806, "step": 2050}, {"loss": 0.773, "grad_norm": 0.7151971459388733, "learning_rate": 0.0002, "epoch": 2.5400739827373613, "step": 2060}, {"loss": 0.6733, "grad_norm": 0.9665895104408264, "learning_rate": 0.0002, "epoch": 2.5524044389642415, "step": 2070}, {"loss": 0.7791, "grad_norm": 0.9572727680206299, "learning_rate": 0.0002, "epoch": 2.564734895191122, "step": 2080}, {"loss": 0.7205, "grad_norm": 1.1970765590667725, "learning_rate": 0.0002, "epoch": 2.5770653514180024, "step": 2090}, {"loss": 0.6736, "grad_norm": 0.5505942702293396, "learning_rate": 0.0002, "epoch": 2.589395807644883, "step": 2100}, {"loss": 0.673, "grad_norm": 0.5903949737548828, "learning_rate": 0.0002, "epoch": 2.6017262638717633, "step": 2110}, {"loss": 0.678, "grad_norm": 0.45640307664871216, "learning_rate": 0.0002, "epoch": 2.6140567200986435, "step": 2120}, {"loss": 0.6562, "grad_norm": 0.8763944506645203, "learning_rate": 0.0002, "epoch": 2.626387176325524, "step": 2130}, {"loss": 0.6484, "grad_norm": 0.4472963213920593, "learning_rate": 0.0002, "epoch": 2.6387176325524044, "step": 2140}, {"loss": 0.7702, "grad_norm": 0.5335086584091187, "learning_rate": 0.0002, "epoch": 2.6510480887792847, "step": 2150}, {"loss": 0.6851, "grad_norm": 0.805263340473175, "learning_rate": 0.0002, "epoch": 2.6633785450061653, "step": 2160}, {"loss": 0.7026, "grad_norm": 0.6332727670669556, "learning_rate": 0.0002, "epoch": 2.6757090012330456, "step": 2170}, {"loss": 0.7925, "grad_norm": 0.8667435646057129, "learning_rate": 0.0002, "epoch": 2.688039457459926, "step": 2180}, {"loss": 0.8044, "grad_norm": 0.5638955235481262, "learning_rate": 0.0002, "epoch": 2.7003699136868065, "step": 2190}, {"loss": 0.7117, "grad_norm": 0.4176250696182251, "learning_rate": 0.0002, "epoch": 2.7127003699136867, "step": 2200}, {"loss": 0.6932, "grad_norm": 0.6013461351394653, "learning_rate": 0.0002, "epoch": 2.7250308261405674, "step": 2210}, {"loss": 0.7843, "grad_norm": 0.553961992263794, "learning_rate": 0.0002, "epoch": 2.7373612823674476, "step": 2220}, {"loss": 0.8633, "grad_norm": 0.4710180461406708, "learning_rate": 0.0002, "epoch": 2.7496917385943282, "step": 2230}, {"loss": 0.7469, "grad_norm": 0.8141706585884094, "learning_rate": 0.0002, "epoch": 2.7620221948212085, "step": 2240}, {"loss": 0.7086, "grad_norm": 0.7449556589126587, "learning_rate": 0.0002, "epoch": 2.7743526510480887, "step": 2250}, {"loss": 0.6933, "grad_norm": 0.5366780757904053, "learning_rate": 0.0002, "epoch": 2.7866831072749694, "step": 2260}, {"loss": 0.7192, "grad_norm": 0.5316720604896545, "learning_rate": 0.0002, "epoch": 2.7990135635018496, "step": 2270}, {"loss": 0.6212, "grad_norm": 0.4598459005355835, "learning_rate": 0.0002, "epoch": 2.81134401972873, "step": 2280}, {"loss": 0.7024, "grad_norm": 0.6852091550827026, "learning_rate": 0.0002, "epoch": 2.8236744759556105, "step": 2290}, {"loss": 0.7357, "grad_norm": 0.8040902018547058, "learning_rate": 0.0002, "epoch": 2.8360049321824907, "step": 2300}, {"loss": 0.7563, "grad_norm": 0.46976321935653687, "learning_rate": 0.0002, "epoch": 2.848335388409371, "step": 2310}, {"loss": 0.731, "grad_norm": 0.5214090347290039, "learning_rate": 0.0002, "epoch": 2.8606658446362516, "step": 2320}, {"loss": 0.6687, "grad_norm": 0.5323054790496826, "learning_rate": 0.0002, "epoch": 2.872996300863132, "step": 2330}, {"loss": 0.7895, "grad_norm": 0.6842264533042908, "learning_rate": 0.0002, "epoch": 2.885326757090012, "step": 2340}, {"loss": 0.7737, "grad_norm": 0.9157055616378784, "learning_rate": 0.0002, "epoch": 2.8976572133168927, "step": 2350}, {"loss": 0.7217, "grad_norm": 0.5253258347511292, "learning_rate": 0.0002, "epoch": 2.909987669543773, "step": 2360}, {"loss": 0.7162, "grad_norm": 0.4937705099582672, "learning_rate": 0.0002, "epoch": 2.9223181257706536, "step": 2370}, {"loss": 0.7008, "grad_norm": 0.48762989044189453, "learning_rate": 0.0002, "epoch": 2.934648581997534, "step": 2380}, {"loss": 0.8086, "grad_norm": 0.544335126876831, "learning_rate": 0.0002, "epoch": 2.9469790382244145, "step": 2390}, {"loss": 0.643, "grad_norm": 0.4847845435142517, "learning_rate": 0.0002, "epoch": 2.9593094944512948, "step": 2400}, {"loss": 0.7757, "grad_norm": 0.4787445366382599, "learning_rate": 0.0002, "epoch": 2.971639950678175, "step": 2410}, {"loss": 0.7678, "grad_norm": 1.022318959236145, "learning_rate": 0.0002, "epoch": 2.9839704069050557, "step": 2420}, {"loss": 0.6548, "grad_norm": 0.4987848103046417, "learning_rate": 0.0002, "epoch": 2.996300863131936, "step": 2430}]}
+{"epoch": 4.0, "step": 3244, "epoch_duration": 2421.7602109909058, "total_accumulated_duration": 9763.874967098236, "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": 28774.0}, "peak_memory_reserved": {"GPU_0": 28774.0}, "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-0.6-num-5885-sd-10000/checkpoint-1622", "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": 2.3601, "grad_norm": 0.8258164525032043, "learning_rate": 0.0002, "epoch": 0.012330456226880395, "step": 10}, {"loss": 1.7317, "grad_norm": 0.4577729105949402, "learning_rate": 0.0002, "epoch": 0.02466091245376079, "step": 20}, {"loss": 1.4729, "grad_norm": 0.639807939529419, "learning_rate": 0.0002, "epoch": 0.036991368680641186, "step": 30}, {"loss": 1.2088, "grad_norm": 0.5311757922172546, "learning_rate": 0.0002, "epoch": 0.04932182490752158, "step": 40}, {"loss": 1.3149, "grad_norm": 0.386595219373703, "learning_rate": 0.0002, "epoch": 0.06165228113440197, "step": 50}, {"loss": 1.1657, "grad_norm": 0.4401357173919678, "learning_rate": 0.0002, "epoch": 0.07398273736128237, "step": 60}, {"loss": 1.1022, "grad_norm": 0.3234352171421051, "learning_rate": 0.0002, "epoch": 0.08631319358816276, "step": 70}, {"loss": 1.3738, "grad_norm": 0.29643672704696655, "learning_rate": 0.0002, "epoch": 0.09864364981504316, "step": 80}, {"loss": 1.1929, "grad_norm": 0.2941012382507324, "learning_rate": 0.0002, "epoch": 0.11097410604192355, "step": 90}, {"loss": 1.2067, "grad_norm": 0.5498173832893372, "learning_rate": 0.0002, "epoch": 0.12330456226880394, "step": 100}, {"loss": 1.142, "grad_norm": 0.2545783519744873, "learning_rate": 0.0002, "epoch": 0.13563501849568435, "step": 110}, {"loss": 1.0297, "grad_norm": 0.2984241247177124, "learning_rate": 0.0002, "epoch": 0.14796547472256474, "step": 120}, {"loss": 1.1591, "grad_norm": 0.2710968852043152, "learning_rate": 0.0002, "epoch": 0.16029593094944514, "step": 130}, {"loss": 1.0427, "grad_norm": 0.2817152142524719, "learning_rate": 0.0002, "epoch": 0.17262638717632553, "step": 140}, {"loss": 1.0638, "grad_norm": 0.41083765029907227, "learning_rate": 0.0002, "epoch": 0.18495684340320592, "step": 150}, {"loss": 1.3537, "grad_norm": 0.36536213755607605, "learning_rate": 0.0002, "epoch": 0.19728729963008632, "step": 160}, {"loss": 1.0132, "grad_norm": 0.2738671600818634, "learning_rate": 0.0002, "epoch": 0.2096177558569667, "step": 170}, {"loss": 0.9555, "grad_norm": 0.27403146028518677, "learning_rate": 0.0002, "epoch": 0.2219482120838471, "step": 180}, {"loss": 1.0769, "grad_norm": 0.4446810483932495, "learning_rate": 0.0002, "epoch": 0.2342786683107275, "step": 190}, {"loss": 1.0588, "grad_norm": 0.5295385718345642, "learning_rate": 0.0002, "epoch": 0.2466091245376079, "step": 200}, {"loss": 1.0827, "grad_norm": 0.311404824256897, "learning_rate": 0.0002, "epoch": 0.2589395807644883, "step": 210}, {"loss": 1.1455, "grad_norm": 0.2448509782552719, "learning_rate": 0.0002, "epoch": 0.2712700369913687, "step": 220}, {"loss": 1.0929, "grad_norm": 0.6507014036178589, "learning_rate": 0.0002, "epoch": 0.2836004932182491, "step": 230}, {"loss": 0.9875, "grad_norm": 0.2339320331811905, "learning_rate": 0.0002, "epoch": 0.2959309494451295, "step": 240}, {"loss": 0.9211, "grad_norm": 0.8210226893424988, "learning_rate": 0.0002, "epoch": 0.3082614056720099, "step": 250}, {"loss": 1.161, "grad_norm": 0.27473965287208557, "learning_rate": 0.0002, "epoch": 0.3205918618988903, "step": 260}, {"loss": 1.0218, "grad_norm": 0.3051395118236542, "learning_rate": 0.0002, "epoch": 0.33292231812577067, "step": 270}, {"loss": 1.0286, "grad_norm": 0.3037777245044708, "learning_rate": 0.0002, "epoch": 0.34525277435265106, "step": 280}, {"loss": 1.144, "grad_norm": 0.2748974859714508, "learning_rate": 0.0002, "epoch": 0.35758323057953145, "step": 290}, {"loss": 1.0858, "grad_norm": 0.23656068742275238, "learning_rate": 0.0002, "epoch": 0.36991368680641185, "step": 300}, {"loss": 1.0564, "grad_norm": 0.2523384094238281, "learning_rate": 0.0002, "epoch": 0.38224414303329224, "step": 310}, {"loss": 1.3091, "grad_norm": 0.27848055958747864, "learning_rate": 0.0002, "epoch": 0.39457459926017263, "step": 320}, {"loss": 1.0252, "grad_norm": 0.3204525411128998, "learning_rate": 0.0002, "epoch": 0.406905055487053, "step": 330}, {"loss": 0.9855, "grad_norm": 0.3459707498550415, "learning_rate": 0.0002, "epoch": 0.4192355117139334, "step": 340}, {"loss": 1.1111, "grad_norm": 0.2458430379629135, "learning_rate": 0.0002, "epoch": 0.4315659679408138, "step": 350}, {"loss": 1.1493, "grad_norm": 0.5022910237312317, "learning_rate": 0.0002, "epoch": 0.4438964241676942, "step": 360}, {"loss": 1.1272, "grad_norm": 0.27076372504234314, "learning_rate": 0.0002, "epoch": 0.4562268803945746, "step": 370}, {"loss": 1.1927, "grad_norm": 0.6489047408103943, "learning_rate": 0.0002, "epoch": 0.468557336621455, "step": 380}, {"loss": 0.9501, "grad_norm": 0.3324144184589386, "learning_rate": 0.0002, "epoch": 0.4808877928483354, "step": 390}, {"loss": 1.2012, "grad_norm": 0.32813116908073425, "learning_rate": 0.0002, "epoch": 0.4932182490752158, "step": 400}, {"loss": 1.1135, "grad_norm": 0.25295355916023254, "learning_rate": 0.0002, "epoch": 0.5055487053020962, "step": 410}, {"loss": 0.9477, "grad_norm": 0.2912578880786896, "learning_rate": 0.0002, "epoch": 0.5178791615289766, "step": 420}, {"loss": 1.0121, "grad_norm": 0.34780189394950867, "learning_rate": 0.0002, "epoch": 0.530209617755857, "step": 430}, {"loss": 0.9296, "grad_norm": 0.24604526162147522, "learning_rate": 0.0002, "epoch": 0.5425400739827374, "step": 440}, {"loss": 1.253, "grad_norm": 0.32759982347488403, "learning_rate": 0.0002, "epoch": 0.5548705302096177, "step": 450}, {"loss": 1.1925, "grad_norm": 0.40810221433639526, "learning_rate": 0.0002, "epoch": 0.5672009864364982, "step": 460}, {"loss": 1.174, "grad_norm": 0.3590679466724396, "learning_rate": 0.0002, "epoch": 0.5795314426633785, "step": 470}, {"loss": 1.2223, "grad_norm": 0.5656213760375977, "learning_rate": 0.0002, "epoch": 0.591861898890259, "step": 480}, {"loss": 1.1936, "grad_norm": 0.30830657482147217, "learning_rate": 0.0002, "epoch": 0.6041923551171393, "step": 490}, {"loss": 1.1873, "grad_norm": 0.317905455827713, "learning_rate": 0.0002, "epoch": 0.6165228113440198, "step": 500}, {"loss": 0.9805, "grad_norm": 0.3254566490650177, "learning_rate": 0.0002, "epoch": 0.6288532675709001, "step": 510}, {"loss": 1.0384, "grad_norm": 0.29187721014022827, "learning_rate": 0.0002, "epoch": 0.6411837237977805, "step": 520}, {"loss": 1.2526, "grad_norm": 0.3439238965511322, "learning_rate": 0.0002, "epoch": 0.6535141800246609, "step": 530}, {"loss": 1.0698, "grad_norm": 0.20970556139945984, "learning_rate": 0.0002, "epoch": 0.6658446362515413, "step": 540}, {"loss": 1.1047, "grad_norm": 0.4022853374481201, "learning_rate": 0.0002, "epoch": 0.6781750924784217, "step": 550}, {"loss": 1.0684, "grad_norm": 0.2235759049654007, "learning_rate": 0.0002, "epoch": 0.6905055487053021, "step": 560}, {"loss": 1.2339, "grad_norm": 0.33849895000457764, "learning_rate": 0.0002, "epoch": 0.7028360049321825, "step": 570}, {"loss": 1.1929, "grad_norm": 0.34745967388153076, "learning_rate": 0.0002, "epoch": 0.7151664611590629, "step": 580}, {"loss": 1.1158, "grad_norm": 0.26041269302368164, "learning_rate": 0.0002, "epoch": 0.7274969173859432, "step": 590}, {"loss": 1.2134, "grad_norm": 0.3804777264595032, "learning_rate": 0.0002, "epoch": 0.7398273736128237, "step": 600}, {"loss": 1.0606, "grad_norm": 0.2456253319978714, "learning_rate": 0.0002, "epoch": 0.752157829839704, "step": 610}, {"loss": 1.0638, "grad_norm": 0.37838423252105713, "learning_rate": 0.0002, "epoch": 0.7644882860665845, "step": 620}, {"loss": 1.0556, "grad_norm": 0.28105494379997253, "learning_rate": 0.0002, "epoch": 0.7768187422934648, "step": 630}, {"loss": 1.0672, "grad_norm": 0.2774018943309784, "learning_rate": 0.0002, "epoch": 0.7891491985203453, "step": 640}, {"loss": 0.9978, "grad_norm": 1.8184229135513306, "learning_rate": 0.0002, "epoch": 0.8014796547472256, "step": 650}, {"loss": 1.1038, "grad_norm": 0.3325096070766449, "learning_rate": 0.0002, "epoch": 0.813810110974106, "step": 660}, {"loss": 1.083, "grad_norm": 0.2686693072319031, "learning_rate": 0.0002, "epoch": 0.8261405672009864, "step": 670}, {"loss": 1.1308, "grad_norm": 0.3271431624889374, "learning_rate": 0.0002, "epoch": 0.8384710234278668, "step": 680}, {"loss": 1.1116, "grad_norm": 2.359999656677246, "learning_rate": 0.0002, "epoch": 0.8508014796547472, "step": 690}, {"loss": 1.0782, "grad_norm": 0.46242964267730713, "learning_rate": 0.0002, "epoch": 0.8631319358816276, "step": 700}, {"loss": 0.95, "grad_norm": 0.34731170535087585, "learning_rate": 0.0002, "epoch": 0.8754623921085081, "step": 710}, {"loss": 1.2236, "grad_norm": 0.39381715655326843, "learning_rate": 0.0002, "epoch": 0.8877928483353884, "step": 720}, {"loss": 1.1319, "grad_norm": 0.43496373295783997, "learning_rate": 0.0002, "epoch": 0.9001233045622689, "step": 730}, {"loss": 1.0979, "grad_norm": 0.32243210077285767, "learning_rate": 0.0002, "epoch": 0.9124537607891492, "step": 740}, {"loss": 0.9913, "grad_norm": 0.30396756529808044, "learning_rate": 0.0002, "epoch": 0.9247842170160296, "step": 750}, {"loss": 1.1141, "grad_norm": 0.4461122751235962, "learning_rate": 0.0002, "epoch": 0.93711467324291, "step": 760}, {"loss": 1.0049, "grad_norm": 0.24081681668758392, "learning_rate": 0.0002, "epoch": 0.9494451294697904, "step": 770}, {"loss": 1.0966, "grad_norm": 0.27461910247802734, "learning_rate": 0.0002, "epoch": 0.9617755856966708, "step": 780}, {"loss": 0.9942, "grad_norm": 0.3325668275356293, "learning_rate": 0.0002, "epoch": 0.9741060419235512, "step": 790}, {"loss": 1.0506, "grad_norm": 0.24046339094638824, "learning_rate": 0.0002, "epoch": 0.9864364981504316, "step": 800}, {"loss": 0.9989, "grad_norm": 0.42950066924095154, "learning_rate": 0.0002, "epoch": 0.998766954377312, "step": 810}, {"eval_loss": 1.246457576751709, "eval_runtime": 98.7974, "eval_samples_per_second": 4.413, "eval_steps_per_second": 0.557, "epoch": 1.0, "step": 811}, {"loss": 1.0536, "grad_norm": 0.26760655641555786, "learning_rate": 0.0002, "epoch": 1.0110974106041923, "step": 820}, {"loss": 0.9722, "grad_norm": 0.4640820026397705, "learning_rate": 0.0002, "epoch": 1.0234278668310728, "step": 830}, {"loss": 0.9392, "grad_norm": 0.2699166238307953, "learning_rate": 0.0002, "epoch": 1.0357583230579532, "step": 840}, {"loss": 0.9335, "grad_norm": 0.3441709578037262, "learning_rate": 0.0002, "epoch": 1.0480887792848335, "step": 850}, {"loss": 0.9083, "grad_norm": 0.299934983253479, "learning_rate": 0.0002, "epoch": 1.060419235511714, "step": 860}, {"loss": 0.9416, "grad_norm": 0.2980666160583496, "learning_rate": 0.0002, "epoch": 1.0727496917385944, "step": 870}, {"loss": 0.94, "grad_norm": 0.3131714463233948, "learning_rate": 0.0002, "epoch": 1.0850801479654748, "step": 880}, {"loss": 0.9288, "grad_norm": 0.29881617426872253, "learning_rate": 0.0002, "epoch": 1.097410604192355, "step": 890}, {"loss": 0.998, "grad_norm": 0.29870888590812683, "learning_rate": 0.0002, "epoch": 1.1097410604192355, "step": 900}, {"loss": 0.9924, "grad_norm": 0.5735140442848206, "learning_rate": 0.0002, "epoch": 1.122071516646116, "step": 910}, {"loss": 1.0694, "grad_norm": 0.33159002661705017, "learning_rate": 0.0002, "epoch": 1.1344019728729964, "step": 920}, {"loss": 1.0069, "grad_norm": 1.235399842262268, "learning_rate": 0.0002, "epoch": 1.1467324290998766, "step": 930}, {"loss": 1.0315, "grad_norm": 0.27469736337661743, "learning_rate": 0.0002, "epoch": 1.159062885326757, "step": 940}, {"loss": 0.9386, "grad_norm": 0.29130664467811584, "learning_rate": 0.0002, "epoch": 1.1713933415536375, "step": 950}, {"loss": 0.8919, "grad_norm": 0.3730354607105255, "learning_rate": 0.0002, "epoch": 1.183723797780518, "step": 960}, {"loss": 0.9988, "grad_norm": 0.5973590612411499, "learning_rate": 0.0002, "epoch": 1.1960542540073984, "step": 970}, {"loss": 0.9525, "grad_norm": 0.39631304144859314, "learning_rate": 0.0002, "epoch": 1.2083847102342786, "step": 980}, {"loss": 0.9217, "grad_norm": 0.849051296710968, "learning_rate": 0.0002, "epoch": 1.220715166461159, "step": 990}, {"loss": 1.0903, "grad_norm": 0.4390525817871094, "learning_rate": 0.0002, "epoch": 1.2330456226880395, "step": 1000}, {"loss": 0.9018, "grad_norm": 0.30423852801322937, "learning_rate": 0.0002, "epoch": 1.2453760789149197, "step": 1010}, {"loss": 1.0128, "grad_norm": 0.34736061096191406, "learning_rate": 0.0002, "epoch": 1.2577065351418002, "step": 1020}, {"loss": 0.9026, "grad_norm": 0.3421604037284851, "learning_rate": 0.0002, "epoch": 1.2700369913686806, "step": 1030}, {"loss": 0.8485, "grad_norm": 0.544170081615448, "learning_rate": 0.0002, "epoch": 1.282367447595561, "step": 1040}, {"loss": 0.9591, "grad_norm": 0.5128790736198425, "learning_rate": 0.0002, "epoch": 1.2946979038224415, "step": 1050}, {"loss": 0.9214, "grad_norm": 0.443344384431839, "learning_rate": 0.0002, "epoch": 1.3070283600493218, "step": 1060}, {"loss": 0.9367, "grad_norm": 0.6380868554115295, "learning_rate": 0.0002, "epoch": 1.3193588162762022, "step": 1070}, {"loss": 0.9849, "grad_norm": 0.4638073146343231, "learning_rate": 0.0002, "epoch": 1.3316892725030827, "step": 1080}, {"loss": 0.8645, "grad_norm": 0.32406893372535706, "learning_rate": 0.0002, "epoch": 1.344019728729963, "step": 1090}, {"loss": 0.8278, "grad_norm": 0.3955065608024597, "learning_rate": 0.0002, "epoch": 1.3563501849568433, "step": 1100}, {"loss": 0.9306, "grad_norm": 0.3489246666431427, "learning_rate": 0.0002, "epoch": 1.3686806411837238, "step": 1110}, {"loss": 1.0138, "grad_norm": 0.48451653122901917, "learning_rate": 0.0002, "epoch": 1.3810110974106042, "step": 1120}, {"loss": 0.9165, "grad_norm": 0.3652360439300537, "learning_rate": 0.0002, "epoch": 1.3933415536374847, "step": 1130}, {"loss": 0.9576, "grad_norm": 1.3097436428070068, "learning_rate": 0.0002, "epoch": 1.405672009864365, "step": 1140}, {"loss": 0.8115, "grad_norm": 0.3647715449333191, "learning_rate": 0.0002, "epoch": 1.4180024660912454, "step": 1150}, {"loss": 0.8573, "grad_norm": 0.37248560786247253, "learning_rate": 0.0002, "epoch": 1.4303329223181258, "step": 1160}, {"loss": 0.936, "grad_norm": 0.4639643430709839, "learning_rate": 0.0002, "epoch": 1.442663378545006, "step": 1170}, {"loss": 0.9511, "grad_norm": 0.5455219745635986, "learning_rate": 0.0002, "epoch": 1.4549938347718865, "step": 1180}, {"loss": 0.8611, "grad_norm": 0.38862571120262146, "learning_rate": 0.0002, "epoch": 1.467324290998767, "step": 1190}, {"loss": 0.8681, "grad_norm": 0.37586215138435364, "learning_rate": 0.0002, "epoch": 1.4796547472256474, "step": 1200}, {"loss": 0.8673, "grad_norm": 0.46244436502456665, "learning_rate": 0.0002, "epoch": 1.4919852034525278, "step": 1210}, {"loss": 0.9388, "grad_norm": 0.3570359945297241, "learning_rate": 0.0002, "epoch": 1.504315659679408, "step": 1220}, {"loss": 0.971, "grad_norm": 0.28393083810806274, "learning_rate": 0.0002, "epoch": 1.5166461159062885, "step": 1230}, {"loss": 0.9296, "grad_norm": 0.5672869682312012, "learning_rate": 0.0002, "epoch": 1.528976572133169, "step": 1240}, {"loss": 0.8787, "grad_norm": 0.41605108976364136, "learning_rate": 0.0002, "epoch": 1.5413070283600492, "step": 1250}, {"loss": 0.8744, "grad_norm": 0.40657493472099304, "learning_rate": 0.0002, "epoch": 1.5536374845869299, "step": 1260}, {"loss": 0.9046, "grad_norm": 0.43672341108322144, "learning_rate": 0.0002, "epoch": 1.56596794081381, "step": 1270}, {"loss": 0.8586, "grad_norm": 0.3065410554409027, "learning_rate": 0.0002, "epoch": 1.5782983970406905, "step": 1280}, {"loss": 0.9499, "grad_norm": 0.37826645374298096, "learning_rate": 0.0002, "epoch": 1.590628853267571, "step": 1290}, {"loss": 0.901, "grad_norm": 0.42307335138320923, "learning_rate": 0.0002, "epoch": 1.6029593094944512, "step": 1300}, {"loss": 0.8673, "grad_norm": 0.3648843467235565, "learning_rate": 0.0002, "epoch": 1.6152897657213316, "step": 1310}, {"loss": 0.9302, "grad_norm": 0.8921076059341431, "learning_rate": 0.0002, "epoch": 1.627620221948212, "step": 1320}, {"loss": 0.9378, "grad_norm": 0.37522226572036743, "learning_rate": 0.0002, "epoch": 1.6399506781750923, "step": 1330}, {"loss": 0.8921, "grad_norm": 0.7489957809448242, "learning_rate": 0.0002, "epoch": 1.652281134401973, "step": 1340}, {"loss": 0.9297, "grad_norm": 0.31733131408691406, "learning_rate": 0.0002, "epoch": 1.6646115906288532, "step": 1350}, {"loss": 0.907, "grad_norm": 0.3249478340148926, "learning_rate": 0.0002, "epoch": 1.6769420468557337, "step": 1360}, {"loss": 1.0197, "grad_norm": 0.3178001344203949, "learning_rate": 0.0002, "epoch": 1.6892725030826141, "step": 1370}, {"loss": 1.0781, "grad_norm": 0.5674093961715698, "learning_rate": 0.0002, "epoch": 1.7016029593094943, "step": 1380}, {"loss": 0.8972, "grad_norm": 0.35272449254989624, "learning_rate": 0.0002, "epoch": 1.7139334155363748, "step": 1390}, {"loss": 0.9346, "grad_norm": 0.5778217911720276, "learning_rate": 0.0002, "epoch": 1.7262638717632552, "step": 1400}, {"loss": 0.9099, "grad_norm": 0.33561450242996216, "learning_rate": 0.0002, "epoch": 1.7385943279901355, "step": 1410}, {"loss": 0.8636, "grad_norm": 0.31735464930534363, "learning_rate": 0.0002, "epoch": 1.7509247842170161, "step": 1420}, {"loss": 0.982, "grad_norm": 1.0612670183181763, "learning_rate": 0.0002, "epoch": 1.7632552404438964, "step": 1430}, {"loss": 0.8224, "grad_norm": 0.5442509651184082, "learning_rate": 0.0002, "epoch": 1.7755856966707768, "step": 1440}, {"loss": 0.9275, "grad_norm": 0.7471332550048828, "learning_rate": 0.0002, "epoch": 1.7879161528976573, "step": 1450}, {"loss": 0.9389, "grad_norm": 0.4323609173297882, "learning_rate": 0.0002, "epoch": 1.8002466091245375, "step": 1460}, {"loss": 0.8247, "grad_norm": 0.47796759009361267, "learning_rate": 0.0002, "epoch": 1.8125770653514182, "step": 1470}, {"loss": 0.9395, "grad_norm": 0.3348400592803955, "learning_rate": 0.0002, "epoch": 1.8249075215782984, "step": 1480}, {"loss": 0.9793, "grad_norm": 0.3354550898075104, "learning_rate": 0.0002, "epoch": 1.8372379778051788, "step": 1490}, {"loss": 0.8581, "grad_norm": 0.5988477468490601, "learning_rate": 0.0002, "epoch": 1.8495684340320593, "step": 1500}, {"loss": 0.9268, "grad_norm": 0.5222318172454834, "learning_rate": 0.0002, "epoch": 1.8618988902589395, "step": 1510}, {"loss": 0.8846, "grad_norm": 0.5246642827987671, "learning_rate": 0.0002, "epoch": 1.87422934648582, "step": 1520}, {"loss": 0.9317, "grad_norm": 0.3164594769477844, "learning_rate": 0.0002, "epoch": 1.8865598027127004, "step": 1530}, {"loss": 0.9961, "grad_norm": 0.3496174216270447, "learning_rate": 0.0002, "epoch": 1.8988902589395806, "step": 1540}, {"loss": 0.9057, "grad_norm": 0.8863359689712524, "learning_rate": 0.0002, "epoch": 1.9112207151664613, "step": 1550}, {"loss": 0.9405, "grad_norm": 0.3587026298046112, "learning_rate": 0.0002, "epoch": 1.9235511713933415, "step": 1560}, {"loss": 0.8335, "grad_norm": 0.6052881479263306, "learning_rate": 0.0002, "epoch": 1.935881627620222, "step": 1570}, {"loss": 0.8805, "grad_norm": 0.567269504070282, "learning_rate": 0.0002, "epoch": 1.9482120838471024, "step": 1580}, {"loss": 0.9581, "grad_norm": 0.45184487104415894, "learning_rate": 0.0002, "epoch": 1.9605425400739827, "step": 1590}, {"loss": 0.9147, "grad_norm": 0.5028569102287292, "learning_rate": 0.0002, "epoch": 1.972872996300863, "step": 1600}, {"loss": 0.75, "grad_norm": 0.4677547216415405, "learning_rate": 0.0002, "epoch": 1.9852034525277436, "step": 1610}, {"loss": 0.8469, "grad_norm": 0.35106056928634644, "learning_rate": 0.0002, "epoch": 1.9975339087546238, "step": 1620}, {"eval_loss": 1.238026738166809, "eval_runtime": 95.4287, "eval_samples_per_second": 4.569, "eval_steps_per_second": 0.576, "epoch": 2.0, "step": 1622}, {"loss": 0.7629, "grad_norm": 0.444060355424881, "learning_rate": 0.0002, "epoch": 2.0098643649815044, "step": 1630}, {"loss": 0.772, "grad_norm": 0.627570390701294, "learning_rate": 0.0002, "epoch": 2.0221948212083847, "step": 1640}, {"loss": 0.6186, "grad_norm": 0.38737839460372925, "learning_rate": 0.0002, "epoch": 2.034525277435265, "step": 1650}, {"loss": 0.7734, "grad_norm": 0.4300459623336792, "learning_rate": 0.0002, "epoch": 2.0468557336621456, "step": 1660}, {"loss": 0.6943, "grad_norm": 0.43037715554237366, "learning_rate": 0.0002, "epoch": 2.059186189889026, "step": 1670}, {"loss": 0.6588, "grad_norm": 0.40772515535354614, "learning_rate": 0.0002, "epoch": 2.0715166461159065, "step": 1680}, {"loss": 0.8105, "grad_norm": 0.5295451879501343, "learning_rate": 0.0002, "epoch": 2.0838471023427867, "step": 1690}, {"loss": 0.7717, "grad_norm": 0.7452750205993652, "learning_rate": 0.0002, "epoch": 2.096177558569667, "step": 1700}, {"loss": 0.7458, "grad_norm": 0.809183657169342, "learning_rate": 0.0002, "epoch": 2.1085080147965476, "step": 1710}, {"loss": 0.7398, "grad_norm": 0.4597688913345337, "learning_rate": 0.0002, "epoch": 2.120838471023428, "step": 1720}, {"loss": 0.6856, "grad_norm": 0.806919276714325, "learning_rate": 0.0002, "epoch": 2.133168927250308, "step": 1730}, {"loss": 0.679, "grad_norm": 0.3755643665790558, "learning_rate": 0.0002, "epoch": 2.1454993834771887, "step": 1740}, {"loss": 0.7938, "grad_norm": 0.5882734060287476, "learning_rate": 0.0002, "epoch": 2.157829839704069, "step": 1750}, {"loss": 0.6782, "grad_norm": 0.692960798740387, "learning_rate": 0.0002, "epoch": 2.1701602959309496, "step": 1760}, {"loss": 0.7195, "grad_norm": 0.4737096428871155, "learning_rate": 0.0002, "epoch": 2.18249075215783, "step": 1770}, {"loss": 0.758, "grad_norm": 0.6637021899223328, "learning_rate": 0.0002, "epoch": 2.19482120838471, "step": 1780}, {"loss": 0.7139, "grad_norm": 0.9109764099121094, "learning_rate": 0.0002, "epoch": 2.2071516646115907, "step": 1790}, {"loss": 0.7373, "grad_norm": 0.4137539267539978, "learning_rate": 0.0002, "epoch": 2.219482120838471, "step": 1800}, {"loss": 0.7266, "grad_norm": 0.44995415210723877, "learning_rate": 0.0002, "epoch": 2.2318125770653516, "step": 1810}, {"loss": 0.7663, "grad_norm": 0.5985036492347717, "learning_rate": 0.0002, "epoch": 2.244143033292232, "step": 1820}, {"loss": 0.7502, "grad_norm": 0.7549490332603455, "learning_rate": 0.0002, "epoch": 2.256473489519112, "step": 1830}, {"loss": 0.7452, "grad_norm": 0.4490937888622284, "learning_rate": 0.0002, "epoch": 2.2688039457459928, "step": 1840}, {"loss": 0.7531, "grad_norm": 0.38859808444976807, "learning_rate": 0.0002, "epoch": 2.281134401972873, "step": 1850}, {"loss": 0.7278, "grad_norm": 1.0704916715621948, "learning_rate": 0.0002, "epoch": 2.293464858199753, "step": 1860}, {"loss": 0.7143, "grad_norm": 0.4647100865840912, "learning_rate": 0.0002, "epoch": 2.305795314426634, "step": 1870}, {"loss": 0.7146, "grad_norm": 0.6181163787841797, "learning_rate": 0.0002, "epoch": 2.318125770653514, "step": 1880}, {"loss": 0.7689, "grad_norm": 0.9241904020309448, "learning_rate": 0.0002, "epoch": 2.3304562268803943, "step": 1890}, {"loss": 0.7294, "grad_norm": 0.39101317524909973, "learning_rate": 0.0002, "epoch": 2.342786683107275, "step": 1900}, {"loss": 0.7079, "grad_norm": 0.49442458152770996, "learning_rate": 0.0002, "epoch": 2.3551171393341552, "step": 1910}, {"loss": 0.7586, "grad_norm": 0.4864824414253235, "learning_rate": 0.0002, "epoch": 2.367447595561036, "step": 1920}, {"loss": 0.7434, "grad_norm": 0.5427613854408264, "learning_rate": 0.0002, "epoch": 2.379778051787916, "step": 1930}, {"loss": 0.8423, "grad_norm": 0.7164974808692932, "learning_rate": 0.0002, "epoch": 2.392108508014797, "step": 1940}, {"loss": 0.6888, "grad_norm": 0.562979519367218, "learning_rate": 0.0002, "epoch": 2.404438964241677, "step": 1950}, {"loss": 0.7692, "grad_norm": 0.5631861090660095, "learning_rate": 0.0002, "epoch": 2.4167694204685573, "step": 1960}, {"loss": 0.67, "grad_norm": 0.4895121157169342, "learning_rate": 0.0002, "epoch": 2.429099876695438, "step": 1970}, {"loss": 0.7735, "grad_norm": 0.45674824714660645, "learning_rate": 0.0002, "epoch": 2.441430332922318, "step": 1980}, {"loss": 0.685, "grad_norm": 1.1424206495285034, "learning_rate": 0.0002, "epoch": 2.4537607891491984, "step": 1990}, {"loss": 0.7627, "grad_norm": 0.6314579844474792, "learning_rate": 0.0002, "epoch": 2.466091245376079, "step": 2000}, {"loss": 0.7118, "grad_norm": 0.5481605529785156, "learning_rate": 0.0002, "epoch": 2.4784217016029593, "step": 2010}, {"loss": 0.6947, "grad_norm": 0.4671579599380493, "learning_rate": 0.0002, "epoch": 2.4907521578298395, "step": 2020}, {"loss": 0.7377, "grad_norm": 0.7621194124221802, "learning_rate": 0.0002, "epoch": 2.50308261405672, "step": 2030}, {"loss": 0.69, "grad_norm": 0.38983288407325745, "learning_rate": 0.0002, "epoch": 2.5154130702836004, "step": 2040}, {"loss": 0.8381, "grad_norm": 0.6341150999069214, "learning_rate": 0.0002, "epoch": 2.5277435265104806, "step": 2050}, {"loss": 0.773, "grad_norm": 0.7151971459388733, "learning_rate": 0.0002, "epoch": 2.5400739827373613, "step": 2060}, {"loss": 0.6733, "grad_norm": 0.9665895104408264, "learning_rate": 0.0002, "epoch": 2.5524044389642415, "step": 2070}, {"loss": 0.7791, "grad_norm": 0.9572727680206299, "learning_rate": 0.0002, "epoch": 2.564734895191122, "step": 2080}, {"loss": 0.7205, "grad_norm": 1.1970765590667725, "learning_rate": 0.0002, "epoch": 2.5770653514180024, "step": 2090}, {"loss": 0.6736, "grad_norm": 0.5505942702293396, "learning_rate": 0.0002, "epoch": 2.589395807644883, "step": 2100}, {"loss": 0.673, "grad_norm": 0.5903949737548828, "learning_rate": 0.0002, "epoch": 2.6017262638717633, "step": 2110}, {"loss": 0.678, "grad_norm": 0.45640307664871216, "learning_rate": 0.0002, "epoch": 2.6140567200986435, "step": 2120}, {"loss": 0.6562, "grad_norm": 0.8763944506645203, "learning_rate": 0.0002, "epoch": 2.626387176325524, "step": 2130}, {"loss": 0.6484, "grad_norm": 0.4472963213920593, "learning_rate": 0.0002, "epoch": 2.6387176325524044, "step": 2140}, {"loss": 0.7702, "grad_norm": 0.5335086584091187, "learning_rate": 0.0002, "epoch": 2.6510480887792847, "step": 2150}, {"loss": 0.6851, "grad_norm": 0.805263340473175, "learning_rate": 0.0002, "epoch": 2.6633785450061653, "step": 2160}, {"loss": 0.7026, "grad_norm": 0.6332727670669556, "learning_rate": 0.0002, "epoch": 2.6757090012330456, "step": 2170}, {"loss": 0.7925, "grad_norm": 0.8667435646057129, "learning_rate": 0.0002, "epoch": 2.688039457459926, "step": 2180}, {"loss": 0.8044, "grad_norm": 0.5638955235481262, "learning_rate": 0.0002, "epoch": 2.7003699136868065, "step": 2190}, {"loss": 0.7117, "grad_norm": 0.4176250696182251, "learning_rate": 0.0002, "epoch": 2.7127003699136867, "step": 2200}, {"loss": 0.6932, "grad_norm": 0.6013461351394653, "learning_rate": 0.0002, "epoch": 2.7250308261405674, "step": 2210}, {"loss": 0.7843, "grad_norm": 0.553961992263794, "learning_rate": 0.0002, "epoch": 2.7373612823674476, "step": 2220}, {"loss": 0.8633, "grad_norm": 0.4710180461406708, "learning_rate": 0.0002, "epoch": 2.7496917385943282, "step": 2230}, {"loss": 0.7469, "grad_norm": 0.8141706585884094, "learning_rate": 0.0002, "epoch": 2.7620221948212085, "step": 2240}, {"loss": 0.7086, "grad_norm": 0.7449556589126587, "learning_rate": 0.0002, "epoch": 2.7743526510480887, "step": 2250}, {"loss": 0.6933, "grad_norm": 0.5366780757904053, "learning_rate": 0.0002, "epoch": 2.7866831072749694, "step": 2260}, {"loss": 0.7192, "grad_norm": 0.5316720604896545, "learning_rate": 0.0002, "epoch": 2.7990135635018496, "step": 2270}, {"loss": 0.6212, "grad_norm": 0.4598459005355835, "learning_rate": 0.0002, "epoch": 2.81134401972873, "step": 2280}, {"loss": 0.7024, "grad_norm": 0.6852091550827026, "learning_rate": 0.0002, "epoch": 2.8236744759556105, "step": 2290}, {"loss": 0.7357, "grad_norm": 0.8040902018547058, "learning_rate": 0.0002, "epoch": 2.8360049321824907, "step": 2300}, {"loss": 0.7563, "grad_norm": 0.46976321935653687, "learning_rate": 0.0002, "epoch": 2.848335388409371, "step": 2310}, {"loss": 0.731, "grad_norm": 0.5214090347290039, "learning_rate": 0.0002, "epoch": 2.8606658446362516, "step": 2320}, {"loss": 0.6687, "grad_norm": 0.5323054790496826, "learning_rate": 0.0002, "epoch": 2.872996300863132, "step": 2330}, {"loss": 0.7895, "grad_norm": 0.6842264533042908, "learning_rate": 0.0002, "epoch": 2.885326757090012, "step": 2340}, {"loss": 0.7737, "grad_norm": 0.9157055616378784, "learning_rate": 0.0002, "epoch": 2.8976572133168927, "step": 2350}, {"loss": 0.7217, "grad_norm": 0.5253258347511292, "learning_rate": 0.0002, "epoch": 2.909987669543773, "step": 2360}, {"loss": 0.7162, "grad_norm": 0.4937705099582672, "learning_rate": 0.0002, "epoch": 2.9223181257706536, "step": 2370}, {"loss": 0.7008, "grad_norm": 0.48762989044189453, "learning_rate": 0.0002, "epoch": 2.934648581997534, "step": 2380}, {"loss": 0.8086, "grad_norm": 0.544335126876831, "learning_rate": 0.0002, "epoch": 2.9469790382244145, "step": 2390}, {"loss": 0.643, "grad_norm": 0.4847845435142517, "learning_rate": 0.0002, "epoch": 2.9593094944512948, "step": 2400}, {"loss": 0.7757, "grad_norm": 0.4787445366382599, "learning_rate": 0.0002, "epoch": 2.971639950678175, "step": 2410}, {"loss": 0.7678, "grad_norm": 1.022318959236145, "learning_rate": 0.0002, "epoch": 2.9839704069050557, "step": 2420}, {"loss": 0.6548, "grad_norm": 0.4987848103046417, "learning_rate": 0.0002, "epoch": 2.996300863131936, "step": 2430}, {"eval_loss": 1.2936296463012695, "eval_runtime": 94.7897, "eval_samples_per_second": 4.6, "eval_steps_per_second": 0.58, "epoch": 3.0, "step": 2433}, {"loss": 0.6073, "grad_norm": 0.5562372803688049, "learning_rate": 0.0002, "epoch": 3.008631319358816, "step": 2440}, {"loss": 0.5181, "grad_norm": 1.133402705192566, "learning_rate": 0.0002, "epoch": 3.020961775585697, "step": 2450}, {"loss": 0.5333, "grad_norm": 0.6480470299720764, "learning_rate": 0.0002, "epoch": 3.033292231812577, "step": 2460}, {"loss": 0.4828, "grad_norm": 0.8989138007164001, "learning_rate": 0.0002, "epoch": 3.0456226880394572, "step": 2470}, {"loss": 0.5097, "grad_norm": 0.8257461786270142, "learning_rate": 0.0002, "epoch": 3.057953144266338, "step": 2480}, {"loss": 0.6229, "grad_norm": 0.6813381910324097, "learning_rate": 0.0002, "epoch": 3.070283600493218, "step": 2490}, {"loss": 0.531, "grad_norm": 0.6989586353302002, "learning_rate": 0.0002, "epoch": 3.082614056720099, "step": 2500}, {"loss": 0.54, "grad_norm": 0.7992092967033386, "learning_rate": 0.0002, "epoch": 3.094944512946979, "step": 2510}, {"loss": 0.5054, "grad_norm": 0.698077917098999, "learning_rate": 0.0002, "epoch": 3.1072749691738593, "step": 2520}, {"loss": 0.5064, "grad_norm": 0.5699033141136169, "learning_rate": 0.0002, "epoch": 3.11960542540074, "step": 2530}, {"loss": 0.6088, "grad_norm": 0.6142355799674988, "learning_rate": 0.0002, "epoch": 3.13193588162762, "step": 2540}, {"loss": 0.585, "grad_norm": 0.7089933753013611, "learning_rate": 0.0002, "epoch": 3.144266337854501, "step": 2550}, {"loss": 0.5373, "grad_norm": 1.0107015371322632, "learning_rate": 0.0002, "epoch": 3.156596794081381, "step": 2560}, {"loss": 0.5429, "grad_norm": 0.568138837814331, "learning_rate": 0.0002, "epoch": 3.1689272503082613, "step": 2570}, {"loss": 0.5897, "grad_norm": 0.9960416555404663, "learning_rate": 0.0002, "epoch": 3.181257706535142, "step": 2580}, {"loss": 0.5211, "grad_norm": 0.6277595162391663, "learning_rate": 0.0002, "epoch": 3.193588162762022, "step": 2590}, {"loss": 0.5787, "grad_norm": 0.681083619594574, "learning_rate": 0.0002, "epoch": 3.2059186189889024, "step": 2600}, {"loss": 0.5166, "grad_norm": 0.5816057324409485, "learning_rate": 0.0002, "epoch": 3.218249075215783, "step": 2610}, {"loss": 0.545, "grad_norm": 0.7197734117507935, "learning_rate": 0.0002, "epoch": 3.2305795314426633, "step": 2620}, {"loss": 0.614, "grad_norm": 0.6524068117141724, "learning_rate": 0.0002, "epoch": 3.242909987669544, "step": 2630}, {"loss": 0.5456, "grad_norm": 1.273668646812439, "learning_rate": 0.0002, "epoch": 3.255240443896424, "step": 2640}, {"loss": 0.5266, "grad_norm": 0.6950451731681824, "learning_rate": 0.0002, "epoch": 3.2675709001233044, "step": 2650}, {"loss": 0.5194, "grad_norm": 0.8029071688652039, "learning_rate": 0.0002, "epoch": 3.279901356350185, "step": 2660}, {"loss": 0.5729, "grad_norm": 0.7464073896408081, "learning_rate": 0.0002, "epoch": 3.2922318125770653, "step": 2670}, {"loss": 0.5366, "grad_norm": 0.8342001438140869, "learning_rate": 0.0002, "epoch": 3.304562268803946, "step": 2680}, {"loss": 0.5413, "grad_norm": 0.5629868507385254, "learning_rate": 0.0002, "epoch": 3.316892725030826, "step": 2690}, {"loss": 0.633, "grad_norm": 0.753999650478363, "learning_rate": 0.0002, "epoch": 3.3292231812577064, "step": 2700}, {"loss": 0.5048, "grad_norm": 1.0271371603012085, "learning_rate": 0.0002, "epoch": 3.341553637484587, "step": 2710}, {"loss": 0.5233, "grad_norm": 0.9608535170555115, "learning_rate": 0.0002, "epoch": 3.3538840937114673, "step": 2720}, {"loss": 0.5102, "grad_norm": 0.7796488404273987, "learning_rate": 0.0002, "epoch": 3.3662145499383476, "step": 2730}, {"loss": 0.5172, "grad_norm": 0.5666437149047852, "learning_rate": 0.0002, "epoch": 3.3785450061652282, "step": 2740}, {"loss": 0.491, "grad_norm": 0.5462956428527832, "learning_rate": 0.0002, "epoch": 3.3908754623921085, "step": 2750}, {"loss": 0.5855, "grad_norm": 1.289099097251892, "learning_rate": 0.0002, "epoch": 3.4032059186189887, "step": 2760}, {"loss": 0.635, "grad_norm": 0.825566828250885, "learning_rate": 0.0002, "epoch": 3.4155363748458694, "step": 2770}, {"loss": 0.4998, "grad_norm": 0.8366670608520508, "learning_rate": 0.0002, "epoch": 3.4278668310727496, "step": 2780}, {"loss": 0.5732, "grad_norm": 1.0931549072265625, "learning_rate": 0.0002, "epoch": 3.4401972872996303, "step": 2790}, {"loss": 0.6093, "grad_norm": 0.9228858351707458, "learning_rate": 0.0002, "epoch": 3.4525277435265105, "step": 2800}, {"loss": 0.6089, "grad_norm": 1.3182806968688965, "learning_rate": 0.0002, "epoch": 3.4648581997533907, "step": 2810}, {"loss": 0.5665, "grad_norm": 0.8366976380348206, "learning_rate": 0.0002, "epoch": 3.4771886559802714, "step": 2820}, {"loss": 0.5666, "grad_norm": 0.8067695498466492, "learning_rate": 0.0002, "epoch": 3.4895191122071516, "step": 2830}, {"loss": 0.579, "grad_norm": 1.1163437366485596, "learning_rate": 0.0002, "epoch": 3.5018495684340323, "step": 2840}, {"loss": 0.5785, "grad_norm": 1.7196556329727173, "learning_rate": 0.0002, "epoch": 3.5141800246609125, "step": 2850}, {"loss": 0.5346, "grad_norm": 1.1267012357711792, "learning_rate": 0.0002, "epoch": 3.5265104808877927, "step": 2860}, {"loss": 0.447, "grad_norm": 0.7220137119293213, "learning_rate": 0.0002, "epoch": 3.5388409371146734, "step": 2870}, {"loss": 0.6099, "grad_norm": 0.914114773273468, "learning_rate": 0.0002, "epoch": 3.5511713933415536, "step": 2880}, {"loss": 0.6143, "grad_norm": 0.6193503141403198, "learning_rate": 0.0002, "epoch": 3.563501849568434, "step": 2890}, {"loss": 0.5171, "grad_norm": 0.6060135960578918, "learning_rate": 0.0002, "epoch": 3.5758323057953145, "step": 2900}, {"loss": 0.5659, "grad_norm": 1.0177327394485474, "learning_rate": 0.0002, "epoch": 3.5881627620221948, "step": 2910}, {"loss": 0.5711, "grad_norm": 0.5994468331336975, "learning_rate": 0.0002, "epoch": 3.600493218249075, "step": 2920}, {"loss": 0.6373, "grad_norm": 0.7450457215309143, "learning_rate": 0.0002, "epoch": 3.6128236744759556, "step": 2930}, {"loss": 0.4933, "grad_norm": 0.5825870037078857, "learning_rate": 0.0002, "epoch": 3.625154130702836, "step": 2940}, {"loss": 0.6016, "grad_norm": 0.6289743781089783, "learning_rate": 0.0002, "epoch": 3.6374845869297165, "step": 2950}, {"loss": 0.5507, "grad_norm": 0.7801929116249084, "learning_rate": 0.0002, "epoch": 3.6498150431565968, "step": 2960}, {"loss": 0.5695, "grad_norm": 1.1206634044647217, "learning_rate": 0.0002, "epoch": 3.6621454993834774, "step": 2970}, {"loss": 0.4985, "grad_norm": 0.6738817691802979, "learning_rate": 0.0002, "epoch": 3.6744759556103577, "step": 2980}, {"loss": 0.6209, "grad_norm": 1.1917344331741333, "learning_rate": 0.0002, "epoch": 3.686806411837238, "step": 2990}, {"loss": 0.5373, "grad_norm": 1.3738657236099243, "learning_rate": 0.0002, "epoch": 3.6991368680641186, "step": 3000}, {"loss": 0.5467, "grad_norm": 0.6642793416976929, "learning_rate": 0.0002, "epoch": 3.711467324290999, "step": 3010}, {"loss": 0.6243, "grad_norm": 0.9030995965003967, "learning_rate": 0.0002, "epoch": 3.723797780517879, "step": 3020}, {"loss": 0.592, "grad_norm": 1.0203914642333984, "learning_rate": 0.0002, "epoch": 3.7361282367447597, "step": 3030}, {"loss": 0.5453, "grad_norm": 0.648394763469696, "learning_rate": 0.0002, "epoch": 3.74845869297164, "step": 3040}, {"loss": 0.498, "grad_norm": 0.6304570436477661, "learning_rate": 0.0002, "epoch": 3.76078914919852, "step": 3050}, {"loss": 0.683, "grad_norm": 0.8286601901054382, "learning_rate": 0.0002, "epoch": 3.773119605425401, "step": 3060}, {"loss": 0.5302, "grad_norm": 0.906444251537323, "learning_rate": 0.0002, "epoch": 3.785450061652281, "step": 3070}, {"loss": 0.5345, "grad_norm": 1.4212149381637573, "learning_rate": 0.0002, "epoch": 3.7977805178791613, "step": 3080}, {"loss": 0.6403, "grad_norm": 0.7574319839477539, "learning_rate": 0.0002, "epoch": 3.810110974106042, "step": 3090}, {"loss": 0.5756, "grad_norm": 0.6534451246261597, "learning_rate": 0.0002, "epoch": 3.822441430332922, "step": 3100}, {"loss": 0.5306, "grad_norm": 0.7525447010993958, "learning_rate": 0.0002, "epoch": 3.834771886559803, "step": 3110}, {"loss": 0.5368, "grad_norm": 0.6513990759849548, "learning_rate": 0.0002, "epoch": 3.847102342786683, "step": 3120}, {"loss": 0.5492, "grad_norm": 0.7782694697380066, "learning_rate": 0.0002, "epoch": 3.8594327990135637, "step": 3130}, {"loss": 0.5727, "grad_norm": 0.7998530268669128, "learning_rate": 0.0002, "epoch": 3.871763255240444, "step": 3140}, {"loss": 0.5156, "grad_norm": 0.8045353293418884, "learning_rate": 0.0002, "epoch": 3.884093711467324, "step": 3150}, {"loss": 0.5341, "grad_norm": 0.8242645263671875, "learning_rate": 0.0002, "epoch": 3.896424167694205, "step": 3160}, {"loss": 0.5563, "grad_norm": 0.8302360773086548, "learning_rate": 0.0002, "epoch": 3.908754623921085, "step": 3170}, {"loss": 0.5793, "grad_norm": 0.8653109073638916, "learning_rate": 0.0002, "epoch": 3.9210850801479653, "step": 3180}, {"loss": 0.5219, "grad_norm": 0.6461338996887207, "learning_rate": 0.0002, "epoch": 3.933415536374846, "step": 3190}, {"loss": 0.6009, "grad_norm": 0.8267415165901184, "learning_rate": 0.0002, "epoch": 3.945745992601726, "step": 3200}, {"loss": 0.5956, "grad_norm": 1.1963194608688354, "learning_rate": 0.0002, "epoch": 3.9580764488286064, "step": 3210}, {"loss": 0.5692, "grad_norm": 0.7101966142654419, "learning_rate": 0.0002, "epoch": 3.970406905055487, "step": 3220}, {"loss": 0.5471, "grad_norm": 0.5931660532951355, "learning_rate": 0.0002, "epoch": 3.9827373612823673, "step": 3230}, {"loss": 0.5619, "grad_norm": 0.7465988993644714, "learning_rate": 0.0002, "epoch": 3.995067817509248, "step": 3240}]}
+{"epoch": 5.0, "step": 4055, "epoch_duration": 2417.7227470874786, "total_accumulated_duration": 12181.597714185715, "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": 28774.0}, "peak_memory_reserved": {"GPU_0": 28774.0}, "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-0.6-num-5885-sd-10000/checkpoint-1622", "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": 2.3601, "grad_norm": 0.8258164525032043, "learning_rate": 0.0002, "epoch": 0.012330456226880395, "step": 10}, {"loss": 1.7317, "grad_norm": 0.4577729105949402, "learning_rate": 0.0002, "epoch": 0.02466091245376079, "step": 20}, {"loss": 1.4729, "grad_norm": 0.639807939529419, "learning_rate": 0.0002, "epoch": 0.036991368680641186, "step": 30}, {"loss": 1.2088, "grad_norm": 0.5311757922172546, "learning_rate": 0.0002, "epoch": 0.04932182490752158, "step": 40}, {"loss": 1.3149, "grad_norm": 0.386595219373703, "learning_rate": 0.0002, "epoch": 0.06165228113440197, "step": 50}, {"loss": 1.1657, "grad_norm": 0.4401357173919678, "learning_rate": 0.0002, "epoch": 0.07398273736128237, "step": 60}, {"loss": 1.1022, "grad_norm": 0.3234352171421051, "learning_rate": 0.0002, "epoch": 0.08631319358816276, "step": 70}, {"loss": 1.3738, "grad_norm": 0.29643672704696655, "learning_rate": 0.0002, "epoch": 0.09864364981504316, "step": 80}, {"loss": 1.1929, "grad_norm": 0.2941012382507324, "learning_rate": 0.0002, "epoch": 0.11097410604192355, "step": 90}, {"loss": 1.2067, "grad_norm": 0.5498173832893372, "learning_rate": 0.0002, "epoch": 0.12330456226880394, "step": 100}, {"loss": 1.142, "grad_norm": 0.2545783519744873, "learning_rate": 0.0002, "epoch": 0.13563501849568435, "step": 110}, {"loss": 1.0297, "grad_norm": 0.2984241247177124, "learning_rate": 0.0002, "epoch": 0.14796547472256474, "step": 120}, {"loss": 1.1591, "grad_norm": 0.2710968852043152, "learning_rate": 0.0002, "epoch": 0.16029593094944514, "step": 130}, {"loss": 1.0427, "grad_norm": 0.2817152142524719, "learning_rate": 0.0002, "epoch": 0.17262638717632553, "step": 140}, {"loss": 1.0638, "grad_norm": 0.41083765029907227, "learning_rate": 0.0002, "epoch": 0.18495684340320592, "step": 150}, {"loss": 1.3537, "grad_norm": 0.36536213755607605, "learning_rate": 0.0002, "epoch": 0.19728729963008632, "step": 160}, {"loss": 1.0132, "grad_norm": 0.2738671600818634, "learning_rate": 0.0002, "epoch": 0.2096177558569667, "step": 170}, {"loss": 0.9555, "grad_norm": 0.27403146028518677, "learning_rate": 0.0002, "epoch": 0.2219482120838471, "step": 180}, {"loss": 1.0769, "grad_norm": 0.4446810483932495, "learning_rate": 0.0002, "epoch": 0.2342786683107275, "step": 190}, {"loss": 1.0588, "grad_norm": 0.5295385718345642, "learning_rate": 0.0002, "epoch": 0.2466091245376079, "step": 200}, {"loss": 1.0827, "grad_norm": 0.311404824256897, "learning_rate": 0.0002, "epoch": 0.2589395807644883, "step": 210}, {"loss": 1.1455, "grad_norm": 0.2448509782552719, "learning_rate": 0.0002, "epoch": 0.2712700369913687, "step": 220}, {"loss": 1.0929, "grad_norm": 0.6507014036178589, "learning_rate": 0.0002, "epoch": 0.2836004932182491, "step": 230}, {"loss": 0.9875, "grad_norm": 0.2339320331811905, "learning_rate": 0.0002, "epoch": 0.2959309494451295, "step": 240}, {"loss": 0.9211, "grad_norm": 0.8210226893424988, "learning_rate": 0.0002, "epoch": 0.3082614056720099, "step": 250}, {"loss": 1.161, "grad_norm": 0.27473965287208557, "learning_rate": 0.0002, "epoch": 0.3205918618988903, "step": 260}, {"loss": 1.0218, "grad_norm": 0.3051395118236542, "learning_rate": 0.0002, "epoch": 0.33292231812577067, "step": 270}, {"loss": 1.0286, "grad_norm": 0.3037777245044708, "learning_rate": 0.0002, "epoch": 0.34525277435265106, "step": 280}, {"loss": 1.144, "grad_norm": 0.2748974859714508, "learning_rate": 0.0002, "epoch": 0.35758323057953145, "step": 290}, {"loss": 1.0858, "grad_norm": 0.23656068742275238, "learning_rate": 0.0002, "epoch": 0.36991368680641185, "step": 300}, {"loss": 1.0564, "grad_norm": 0.2523384094238281, "learning_rate": 0.0002, "epoch": 0.38224414303329224, "step": 310}, {"loss": 1.3091, "grad_norm": 0.27848055958747864, "learning_rate": 0.0002, "epoch": 0.39457459926017263, "step": 320}, {"loss": 1.0252, "grad_norm": 0.3204525411128998, "learning_rate": 0.0002, "epoch": 0.406905055487053, "step": 330}, {"loss": 0.9855, "grad_norm": 0.3459707498550415, "learning_rate": 0.0002, "epoch": 0.4192355117139334, "step": 340}, {"loss": 1.1111, "grad_norm": 0.2458430379629135, "learning_rate": 0.0002, "epoch": 0.4315659679408138, "step": 350}, {"loss": 1.1493, "grad_norm": 0.5022910237312317, "learning_rate": 0.0002, "epoch": 0.4438964241676942, "step": 360}, {"loss": 1.1272, "grad_norm": 0.27076372504234314, "learning_rate": 0.0002, "epoch": 0.4562268803945746, "step": 370}, {"loss": 1.1927, "grad_norm": 0.6489047408103943, "learning_rate": 0.0002, "epoch": 0.468557336621455, "step": 380}, {"loss": 0.9501, "grad_norm": 0.3324144184589386, "learning_rate": 0.0002, "epoch": 0.4808877928483354, "step": 390}, {"loss": 1.2012, "grad_norm": 0.32813116908073425, "learning_rate": 0.0002, "epoch": 0.4932182490752158, "step": 400}, {"loss": 1.1135, "grad_norm": 0.25295355916023254, "learning_rate": 0.0002, "epoch": 0.5055487053020962, "step": 410}, {"loss": 0.9477, "grad_norm": 0.2912578880786896, "learning_rate": 0.0002, "epoch": 0.5178791615289766, "step": 420}, {"loss": 1.0121, "grad_norm": 0.34780189394950867, "learning_rate": 0.0002, "epoch": 0.530209617755857, "step": 430}, {"loss": 0.9296, "grad_norm": 0.24604526162147522, "learning_rate": 0.0002, "epoch": 0.5425400739827374, "step": 440}, {"loss": 1.253, "grad_norm": 0.32759982347488403, "learning_rate": 0.0002, "epoch": 0.5548705302096177, "step": 450}, {"loss": 1.1925, "grad_norm": 0.40810221433639526, "learning_rate": 0.0002, "epoch": 0.5672009864364982, "step": 460}, {"loss": 1.174, "grad_norm": 0.3590679466724396, "learning_rate": 0.0002, "epoch": 0.5795314426633785, "step": 470}, {"loss": 1.2223, "grad_norm": 0.5656213760375977, "learning_rate": 0.0002, "epoch": 0.591861898890259, "step": 480}, {"loss": 1.1936, "grad_norm": 0.30830657482147217, "learning_rate": 0.0002, "epoch": 0.6041923551171393, "step": 490}, {"loss": 1.1873, "grad_norm": 0.317905455827713, "learning_rate": 0.0002, "epoch": 0.6165228113440198, "step": 500}, {"loss": 0.9805, "grad_norm": 0.3254566490650177, "learning_rate": 0.0002, "epoch": 0.6288532675709001, "step": 510}, {"loss": 1.0384, "grad_norm": 0.29187721014022827, "learning_rate": 0.0002, "epoch": 0.6411837237977805, "step": 520}, {"loss": 1.2526, "grad_norm": 0.3439238965511322, "learning_rate": 0.0002, "epoch": 0.6535141800246609, "step": 530}, {"loss": 1.0698, "grad_norm": 0.20970556139945984, "learning_rate": 0.0002, "epoch": 0.6658446362515413, "step": 540}, {"loss": 1.1047, "grad_norm": 0.4022853374481201, "learning_rate": 0.0002, "epoch": 0.6781750924784217, "step": 550}, {"loss": 1.0684, "grad_norm": 0.2235759049654007, "learning_rate": 0.0002, "epoch": 0.6905055487053021, "step": 560}, {"loss": 1.2339, "grad_norm": 0.33849895000457764, "learning_rate": 0.0002, "epoch": 0.7028360049321825, "step": 570}, {"loss": 1.1929, "grad_norm": 0.34745967388153076, "learning_rate": 0.0002, "epoch": 0.7151664611590629, "step": 580}, {"loss": 1.1158, "grad_norm": 0.26041269302368164, "learning_rate": 0.0002, "epoch": 0.7274969173859432, "step": 590}, {"loss": 1.2134, "grad_norm": 0.3804777264595032, "learning_rate": 0.0002, "epoch": 0.7398273736128237, "step": 600}, {"loss": 1.0606, "grad_norm": 0.2456253319978714, "learning_rate": 0.0002, "epoch": 0.752157829839704, "step": 610}, {"loss": 1.0638, "grad_norm": 0.37838423252105713, "learning_rate": 0.0002, "epoch": 0.7644882860665845, "step": 620}, {"loss": 1.0556, "grad_norm": 0.28105494379997253, "learning_rate": 0.0002, "epoch": 0.7768187422934648, "step": 630}, {"loss": 1.0672, "grad_norm": 0.2774018943309784, "learning_rate": 0.0002, "epoch": 0.7891491985203453, "step": 640}, {"loss": 0.9978, "grad_norm": 1.8184229135513306, "learning_rate": 0.0002, "epoch": 0.8014796547472256, "step": 650}, {"loss": 1.1038, "grad_norm": 0.3325096070766449, "learning_rate": 0.0002, "epoch": 0.813810110974106, "step": 660}, {"loss": 1.083, "grad_norm": 0.2686693072319031, "learning_rate": 0.0002, "epoch": 0.8261405672009864, "step": 670}, {"loss": 1.1308, "grad_norm": 0.3271431624889374, "learning_rate": 0.0002, "epoch": 0.8384710234278668, "step": 680}, {"loss": 1.1116, "grad_norm": 2.359999656677246, "learning_rate": 0.0002, "epoch": 0.8508014796547472, "step": 690}, {"loss": 1.0782, "grad_norm": 0.46242964267730713, "learning_rate": 0.0002, "epoch": 0.8631319358816276, "step": 700}, {"loss": 0.95, "grad_norm": 0.34731170535087585, "learning_rate": 0.0002, "epoch": 0.8754623921085081, "step": 710}, {"loss": 1.2236, "grad_norm": 0.39381715655326843, "learning_rate": 0.0002, "epoch": 0.8877928483353884, "step": 720}, {"loss": 1.1319, "grad_norm": 0.43496373295783997, "learning_rate": 0.0002, "epoch": 0.9001233045622689, "step": 730}, {"loss": 1.0979, "grad_norm": 0.32243210077285767, "learning_rate": 0.0002, "epoch": 0.9124537607891492, "step": 740}, {"loss": 0.9913, "grad_norm": 0.30396756529808044, "learning_rate": 0.0002, "epoch": 0.9247842170160296, "step": 750}, {"loss": 1.1141, "grad_norm": 0.4461122751235962, "learning_rate": 0.0002, "epoch": 0.93711467324291, "step": 760}, {"loss": 1.0049, "grad_norm": 0.24081681668758392, "learning_rate": 0.0002, "epoch": 0.9494451294697904, "step": 770}, {"loss": 1.0966, "grad_norm": 0.27461910247802734, "learning_rate": 0.0002, "epoch": 0.9617755856966708, "step": 780}, {"loss": 0.9942, "grad_norm": 0.3325668275356293, "learning_rate": 0.0002, "epoch": 0.9741060419235512, "step": 790}, {"loss": 1.0506, "grad_norm": 0.24046339094638824, "learning_rate": 0.0002, "epoch": 0.9864364981504316, "step": 800}, {"loss": 0.9989, "grad_norm": 0.42950066924095154, "learning_rate": 0.0002, "epoch": 0.998766954377312, "step": 810}, {"eval_loss": 1.246457576751709, "eval_runtime": 98.7974, "eval_samples_per_second": 4.413, "eval_steps_per_second": 0.557, "epoch": 1.0, "step": 811}, {"loss": 1.0536, "grad_norm": 0.26760655641555786, "learning_rate": 0.0002, "epoch": 1.0110974106041923, "step": 820}, {"loss": 0.9722, "grad_norm": 0.4640820026397705, "learning_rate": 0.0002, "epoch": 1.0234278668310728, "step": 830}, {"loss": 0.9392, "grad_norm": 0.2699166238307953, "learning_rate": 0.0002, "epoch": 1.0357583230579532, "step": 840}, {"loss": 0.9335, "grad_norm": 0.3441709578037262, "learning_rate": 0.0002, "epoch": 1.0480887792848335, "step": 850}, {"loss": 0.9083, "grad_norm": 0.299934983253479, "learning_rate": 0.0002, "epoch": 1.060419235511714, "step": 860}, {"loss": 0.9416, "grad_norm": 0.2980666160583496, "learning_rate": 0.0002, "epoch": 1.0727496917385944, "step": 870}, {"loss": 0.94, "grad_norm": 0.3131714463233948, "learning_rate": 0.0002, "epoch": 1.0850801479654748, "step": 880}, {"loss": 0.9288, "grad_norm": 0.29881617426872253, "learning_rate": 0.0002, "epoch": 1.097410604192355, "step": 890}, {"loss": 0.998, "grad_norm": 0.29870888590812683, "learning_rate": 0.0002, "epoch": 1.1097410604192355, "step": 900}, {"loss": 0.9924, "grad_norm": 0.5735140442848206, "learning_rate": 0.0002, "epoch": 1.122071516646116, "step": 910}, {"loss": 1.0694, "grad_norm": 0.33159002661705017, "learning_rate": 0.0002, "epoch": 1.1344019728729964, "step": 920}, {"loss": 1.0069, "grad_norm": 1.235399842262268, "learning_rate": 0.0002, "epoch": 1.1467324290998766, "step": 930}, {"loss": 1.0315, "grad_norm": 0.27469736337661743, "learning_rate": 0.0002, "epoch": 1.159062885326757, "step": 940}, {"loss": 0.9386, "grad_norm": 0.29130664467811584, "learning_rate": 0.0002, "epoch": 1.1713933415536375, "step": 950}, {"loss": 0.8919, "grad_norm": 0.3730354607105255, "learning_rate": 0.0002, "epoch": 1.183723797780518, "step": 960}, {"loss": 0.9988, "grad_norm": 0.5973590612411499, "learning_rate": 0.0002, "epoch": 1.1960542540073984, "step": 970}, {"loss": 0.9525, "grad_norm": 0.39631304144859314, "learning_rate": 0.0002, "epoch": 1.2083847102342786, "step": 980}, {"loss": 0.9217, "grad_norm": 0.849051296710968, "learning_rate": 0.0002, "epoch": 1.220715166461159, "step": 990}, {"loss": 1.0903, "grad_norm": 0.4390525817871094, "learning_rate": 0.0002, "epoch": 1.2330456226880395, "step": 1000}, {"loss": 0.9018, "grad_norm": 0.30423852801322937, "learning_rate": 0.0002, "epoch": 1.2453760789149197, "step": 1010}, {"loss": 1.0128, "grad_norm": 0.34736061096191406, "learning_rate": 0.0002, "epoch": 1.2577065351418002, "step": 1020}, {"loss": 0.9026, "grad_norm": 0.3421604037284851, "learning_rate": 0.0002, "epoch": 1.2700369913686806, "step": 1030}, {"loss": 0.8485, "grad_norm": 0.544170081615448, "learning_rate": 0.0002, "epoch": 1.282367447595561, "step": 1040}, {"loss": 0.9591, "grad_norm": 0.5128790736198425, "learning_rate": 0.0002, "epoch": 1.2946979038224415, "step": 1050}, {"loss": 0.9214, "grad_norm": 0.443344384431839, "learning_rate": 0.0002, "epoch": 1.3070283600493218, "step": 1060}, {"loss": 0.9367, "grad_norm": 0.6380868554115295, "learning_rate": 0.0002, "epoch": 1.3193588162762022, "step": 1070}, {"loss": 0.9849, "grad_norm": 0.4638073146343231, "learning_rate": 0.0002, "epoch": 1.3316892725030827, "step": 1080}, {"loss": 0.8645, "grad_norm": 0.32406893372535706, "learning_rate": 0.0002, "epoch": 1.344019728729963, "step": 1090}, {"loss": 0.8278, "grad_norm": 0.3955065608024597, "learning_rate": 0.0002, "epoch": 1.3563501849568433, "step": 1100}, {"loss": 0.9306, "grad_norm": 0.3489246666431427, "learning_rate": 0.0002, "epoch": 1.3686806411837238, "step": 1110}, {"loss": 1.0138, "grad_norm": 0.48451653122901917, "learning_rate": 0.0002, "epoch": 1.3810110974106042, "step": 1120}, {"loss": 0.9165, "grad_norm": 0.3652360439300537, "learning_rate": 0.0002, "epoch": 1.3933415536374847, "step": 1130}, {"loss": 0.9576, "grad_norm": 1.3097436428070068, "learning_rate": 0.0002, "epoch": 1.405672009864365, "step": 1140}, {"loss": 0.8115, "grad_norm": 0.3647715449333191, "learning_rate": 0.0002, "epoch": 1.4180024660912454, "step": 1150}, {"loss": 0.8573, "grad_norm": 0.37248560786247253, "learning_rate": 0.0002, "epoch": 1.4303329223181258, "step": 1160}, {"loss": 0.936, "grad_norm": 0.4639643430709839, "learning_rate": 0.0002, "epoch": 1.442663378545006, "step": 1170}, {"loss": 0.9511, "grad_norm": 0.5455219745635986, "learning_rate": 0.0002, "epoch": 1.4549938347718865, "step": 1180}, {"loss": 0.8611, "grad_norm": 0.38862571120262146, "learning_rate": 0.0002, "epoch": 1.467324290998767, "step": 1190}, {"loss": 0.8681, "grad_norm": 0.37586215138435364, "learning_rate": 0.0002, "epoch": 1.4796547472256474, "step": 1200}, {"loss": 0.8673, "grad_norm": 0.46244436502456665, "learning_rate": 0.0002, "epoch": 1.4919852034525278, "step": 1210}, {"loss": 0.9388, "grad_norm": 0.3570359945297241, "learning_rate": 0.0002, "epoch": 1.504315659679408, "step": 1220}, {"loss": 0.971, "grad_norm": 0.28393083810806274, "learning_rate": 0.0002, "epoch": 1.5166461159062885, "step": 1230}, {"loss": 0.9296, "grad_norm": 0.5672869682312012, "learning_rate": 0.0002, "epoch": 1.528976572133169, "step": 1240}, {"loss": 0.8787, "grad_norm": 0.41605108976364136, "learning_rate": 0.0002, "epoch": 1.5413070283600492, "step": 1250}, {"loss": 0.8744, "grad_norm": 0.40657493472099304, "learning_rate": 0.0002, "epoch": 1.5536374845869299, "step": 1260}, {"loss": 0.9046, "grad_norm": 0.43672341108322144, "learning_rate": 0.0002, "epoch": 1.56596794081381, "step": 1270}, {"loss": 0.8586, "grad_norm": 0.3065410554409027, "learning_rate": 0.0002, "epoch": 1.5782983970406905, "step": 1280}, {"loss": 0.9499, "grad_norm": 0.37826645374298096, "learning_rate": 0.0002, "epoch": 1.590628853267571, "step": 1290}, {"loss": 0.901, "grad_norm": 0.42307335138320923, "learning_rate": 0.0002, "epoch": 1.6029593094944512, "step": 1300}, {"loss": 0.8673, "grad_norm": 0.3648843467235565, "learning_rate": 0.0002, "epoch": 1.6152897657213316, "step": 1310}, {"loss": 0.9302, "grad_norm": 0.8921076059341431, "learning_rate": 0.0002, "epoch": 1.627620221948212, "step": 1320}, {"loss": 0.9378, "grad_norm": 0.37522226572036743, "learning_rate": 0.0002, "epoch": 1.6399506781750923, "step": 1330}, {"loss": 0.8921, "grad_norm": 0.7489957809448242, "learning_rate": 0.0002, "epoch": 1.652281134401973, "step": 1340}, {"loss": 0.9297, "grad_norm": 0.31733131408691406, "learning_rate": 0.0002, "epoch": 1.6646115906288532, "step": 1350}, {"loss": 0.907, "grad_norm": 0.3249478340148926, "learning_rate": 0.0002, "epoch": 1.6769420468557337, "step": 1360}, {"loss": 1.0197, "grad_norm": 0.3178001344203949, "learning_rate": 0.0002, "epoch": 1.6892725030826141, "step": 1370}, {"loss": 1.0781, "grad_norm": 0.5674093961715698, "learning_rate": 0.0002, "epoch": 1.7016029593094943, "step": 1380}, {"loss": 0.8972, "grad_norm": 0.35272449254989624, "learning_rate": 0.0002, "epoch": 1.7139334155363748, "step": 1390}, {"loss": 0.9346, "grad_norm": 0.5778217911720276, "learning_rate": 0.0002, "epoch": 1.7262638717632552, "step": 1400}, {"loss": 0.9099, "grad_norm": 0.33561450242996216, "learning_rate": 0.0002, "epoch": 1.7385943279901355, "step": 1410}, {"loss": 0.8636, "grad_norm": 0.31735464930534363, "learning_rate": 0.0002, "epoch": 1.7509247842170161, "step": 1420}, {"loss": 0.982, "grad_norm": 1.0612670183181763, "learning_rate": 0.0002, "epoch": 1.7632552404438964, "step": 1430}, {"loss": 0.8224, "grad_norm": 0.5442509651184082, "learning_rate": 0.0002, "epoch": 1.7755856966707768, "step": 1440}, {"loss": 0.9275, "grad_norm": 0.7471332550048828, "learning_rate": 0.0002, "epoch": 1.7879161528976573, "step": 1450}, {"loss": 0.9389, "grad_norm": 0.4323609173297882, "learning_rate": 0.0002, "epoch": 1.8002466091245375, "step": 1460}, {"loss": 0.8247, "grad_norm": 0.47796759009361267, "learning_rate": 0.0002, "epoch": 1.8125770653514182, "step": 1470}, {"loss": 0.9395, "grad_norm": 0.3348400592803955, "learning_rate": 0.0002, "epoch": 1.8249075215782984, "step": 1480}, {"loss": 0.9793, "grad_norm": 0.3354550898075104, "learning_rate": 0.0002, "epoch": 1.8372379778051788, "step": 1490}, {"loss": 0.8581, "grad_norm": 0.5988477468490601, "learning_rate": 0.0002, "epoch": 1.8495684340320593, "step": 1500}, {"loss": 0.9268, "grad_norm": 0.5222318172454834, "learning_rate": 0.0002, "epoch": 1.8618988902589395, "step": 1510}, {"loss": 0.8846, "grad_norm": 0.5246642827987671, "learning_rate": 0.0002, "epoch": 1.87422934648582, "step": 1520}, {"loss": 0.9317, "grad_norm": 0.3164594769477844, "learning_rate": 0.0002, "epoch": 1.8865598027127004, "step": 1530}, {"loss": 0.9961, "grad_norm": 0.3496174216270447, "learning_rate": 0.0002, "epoch": 1.8988902589395806, "step": 1540}, {"loss": 0.9057, "grad_norm": 0.8863359689712524, "learning_rate": 0.0002, "epoch": 1.9112207151664613, "step": 1550}, {"loss": 0.9405, "grad_norm": 0.3587026298046112, "learning_rate": 0.0002, "epoch": 1.9235511713933415, "step": 1560}, {"loss": 0.8335, "grad_norm": 0.6052881479263306, "learning_rate": 0.0002, "epoch": 1.935881627620222, "step": 1570}, {"loss": 0.8805, "grad_norm": 0.567269504070282, "learning_rate": 0.0002, "epoch": 1.9482120838471024, "step": 1580}, {"loss": 0.9581, "grad_norm": 0.45184487104415894, "learning_rate": 0.0002, "epoch": 1.9605425400739827, "step": 1590}, {"loss": 0.9147, "grad_norm": 0.5028569102287292, "learning_rate": 0.0002, "epoch": 1.972872996300863, "step": 1600}, {"loss": 0.75, "grad_norm": 0.4677547216415405, "learning_rate": 0.0002, "epoch": 1.9852034525277436, "step": 1610}, {"loss": 0.8469, "grad_norm": 0.35106056928634644, "learning_rate": 0.0002, "epoch": 1.9975339087546238, "step": 1620}, {"eval_loss": 1.238026738166809, "eval_runtime": 95.4287, "eval_samples_per_second": 4.569, "eval_steps_per_second": 0.576, "epoch": 2.0, "step": 1622}, {"loss": 0.7629, "grad_norm": 0.444060355424881, "learning_rate": 0.0002, "epoch": 2.0098643649815044, "step": 1630}, {"loss": 0.772, "grad_norm": 0.627570390701294, "learning_rate": 0.0002, "epoch": 2.0221948212083847, "step": 1640}, {"loss": 0.6186, "grad_norm": 0.38737839460372925, "learning_rate": 0.0002, "epoch": 2.034525277435265, "step": 1650}, {"loss": 0.7734, "grad_norm": 0.4300459623336792, "learning_rate": 0.0002, "epoch": 2.0468557336621456, "step": 1660}, {"loss": 0.6943, "grad_norm": 0.43037715554237366, "learning_rate": 0.0002, "epoch": 2.059186189889026, "step": 1670}, {"loss": 0.6588, "grad_norm": 0.40772515535354614, "learning_rate": 0.0002, "epoch": 2.0715166461159065, "step": 1680}, {"loss": 0.8105, "grad_norm": 0.5295451879501343, "learning_rate": 0.0002, "epoch": 2.0838471023427867, "step": 1690}, {"loss": 0.7717, "grad_norm": 0.7452750205993652, "learning_rate": 0.0002, "epoch": 2.096177558569667, "step": 1700}, {"loss": 0.7458, "grad_norm": 0.809183657169342, "learning_rate": 0.0002, "epoch": 2.1085080147965476, "step": 1710}, {"loss": 0.7398, "grad_norm": 0.4597688913345337, "learning_rate": 0.0002, "epoch": 2.120838471023428, "step": 1720}, {"loss": 0.6856, "grad_norm": 0.806919276714325, "learning_rate": 0.0002, "epoch": 2.133168927250308, "step": 1730}, {"loss": 0.679, "grad_norm": 0.3755643665790558, "learning_rate": 0.0002, "epoch": 2.1454993834771887, "step": 1740}, {"loss": 0.7938, "grad_norm": 0.5882734060287476, "learning_rate": 0.0002, "epoch": 2.157829839704069, "step": 1750}, {"loss": 0.6782, "grad_norm": 0.692960798740387, "learning_rate": 0.0002, "epoch": 2.1701602959309496, "step": 1760}, {"loss": 0.7195, "grad_norm": 0.4737096428871155, "learning_rate": 0.0002, "epoch": 2.18249075215783, "step": 1770}, {"loss": 0.758, "grad_norm": 0.6637021899223328, "learning_rate": 0.0002, "epoch": 2.19482120838471, "step": 1780}, {"loss": 0.7139, "grad_norm": 0.9109764099121094, "learning_rate": 0.0002, "epoch": 2.2071516646115907, "step": 1790}, {"loss": 0.7373, "grad_norm": 0.4137539267539978, "learning_rate": 0.0002, "epoch": 2.219482120838471, "step": 1800}, {"loss": 0.7266, "grad_norm": 0.44995415210723877, "learning_rate": 0.0002, "epoch": 2.2318125770653516, "step": 1810}, {"loss": 0.7663, "grad_norm": 0.5985036492347717, "learning_rate": 0.0002, "epoch": 2.244143033292232, "step": 1820}, {"loss": 0.7502, "grad_norm": 0.7549490332603455, "learning_rate": 0.0002, "epoch": 2.256473489519112, "step": 1830}, {"loss": 0.7452, "grad_norm": 0.4490937888622284, "learning_rate": 0.0002, "epoch": 2.2688039457459928, "step": 1840}, {"loss": 0.7531, "grad_norm": 0.38859808444976807, "learning_rate": 0.0002, "epoch": 2.281134401972873, "step": 1850}, {"loss": 0.7278, "grad_norm": 1.0704916715621948, "learning_rate": 0.0002, "epoch": 2.293464858199753, "step": 1860}, {"loss": 0.7143, "grad_norm": 0.4647100865840912, "learning_rate": 0.0002, "epoch": 2.305795314426634, "step": 1870}, {"loss": 0.7146, "grad_norm": 0.6181163787841797, "learning_rate": 0.0002, "epoch": 2.318125770653514, "step": 1880}, {"loss": 0.7689, "grad_norm": 0.9241904020309448, "learning_rate": 0.0002, "epoch": 2.3304562268803943, "step": 1890}, {"loss": 0.7294, "grad_norm": 0.39101317524909973, "learning_rate": 0.0002, "epoch": 2.342786683107275, "step": 1900}, {"loss": 0.7079, "grad_norm": 0.49442458152770996, "learning_rate": 0.0002, "epoch": 2.3551171393341552, "step": 1910}, {"loss": 0.7586, "grad_norm": 0.4864824414253235, "learning_rate": 0.0002, "epoch": 2.367447595561036, "step": 1920}, {"loss": 0.7434, "grad_norm": 0.5427613854408264, "learning_rate": 0.0002, "epoch": 2.379778051787916, "step": 1930}, {"loss": 0.8423, "grad_norm": 0.7164974808692932, "learning_rate": 0.0002, "epoch": 2.392108508014797, "step": 1940}, {"loss": 0.6888, "grad_norm": 0.562979519367218, "learning_rate": 0.0002, "epoch": 2.404438964241677, "step": 1950}, {"loss": 0.7692, "grad_norm": 0.5631861090660095, "learning_rate": 0.0002, "epoch": 2.4167694204685573, "step": 1960}, {"loss": 0.67, "grad_norm": 0.4895121157169342, "learning_rate": 0.0002, "epoch": 2.429099876695438, "step": 1970}, {"loss": 0.7735, "grad_norm": 0.45674824714660645, "learning_rate": 0.0002, "epoch": 2.441430332922318, "step": 1980}, {"loss": 0.685, "grad_norm": 1.1424206495285034, "learning_rate": 0.0002, "epoch": 2.4537607891491984, "step": 1990}, {"loss": 0.7627, "grad_norm": 0.6314579844474792, "learning_rate": 0.0002, "epoch": 2.466091245376079, "step": 2000}, {"loss": 0.7118, "grad_norm": 0.5481605529785156, "learning_rate": 0.0002, "epoch": 2.4784217016029593, "step": 2010}, {"loss": 0.6947, "grad_norm": 0.4671579599380493, "learning_rate": 0.0002, "epoch": 2.4907521578298395, "step": 2020}, {"loss": 0.7377, "grad_norm": 0.7621194124221802, "learning_rate": 0.0002, "epoch": 2.50308261405672, "step": 2030}, {"loss": 0.69, "grad_norm": 0.38983288407325745, "learning_rate": 0.0002, "epoch": 2.5154130702836004, "step": 2040}, {"loss": 0.8381, "grad_norm": 0.6341150999069214, "learning_rate": 0.0002, "epoch": 2.5277435265104806, "step": 2050}, {"loss": 0.773, "grad_norm": 0.7151971459388733, "learning_rate": 0.0002, "epoch": 2.5400739827373613, "step": 2060}, {"loss": 0.6733, "grad_norm": 0.9665895104408264, "learning_rate": 0.0002, "epoch": 2.5524044389642415, "step": 2070}, {"loss": 0.7791, "grad_norm": 0.9572727680206299, "learning_rate": 0.0002, "epoch": 2.564734895191122, "step": 2080}, {"loss": 0.7205, "grad_norm": 1.1970765590667725, "learning_rate": 0.0002, "epoch": 2.5770653514180024, "step": 2090}, {"loss": 0.6736, "grad_norm": 0.5505942702293396, "learning_rate": 0.0002, "epoch": 2.589395807644883, "step": 2100}, {"loss": 0.673, "grad_norm": 0.5903949737548828, "learning_rate": 0.0002, "epoch": 2.6017262638717633, "step": 2110}, {"loss": 0.678, "grad_norm": 0.45640307664871216, "learning_rate": 0.0002, "epoch": 2.6140567200986435, "step": 2120}, {"loss": 0.6562, "grad_norm": 0.8763944506645203, "learning_rate": 0.0002, "epoch": 2.626387176325524, "step": 2130}, {"loss": 0.6484, "grad_norm": 0.4472963213920593, "learning_rate": 0.0002, "epoch": 2.6387176325524044, "step": 2140}, {"loss": 0.7702, "grad_norm": 0.5335086584091187, "learning_rate": 0.0002, "epoch": 2.6510480887792847, "step": 2150}, {"loss": 0.6851, "grad_norm": 0.805263340473175, "learning_rate": 0.0002, "epoch": 2.6633785450061653, "step": 2160}, {"loss": 0.7026, "grad_norm": 0.6332727670669556, "learning_rate": 0.0002, "epoch": 2.6757090012330456, "step": 2170}, {"loss": 0.7925, "grad_norm": 0.8667435646057129, "learning_rate": 0.0002, "epoch": 2.688039457459926, "step": 2180}, {"loss": 0.8044, "grad_norm": 0.5638955235481262, "learning_rate": 0.0002, "epoch": 2.7003699136868065, "step": 2190}, {"loss": 0.7117, "grad_norm": 0.4176250696182251, "learning_rate": 0.0002, "epoch": 2.7127003699136867, "step": 2200}, {"loss": 0.6932, "grad_norm": 0.6013461351394653, "learning_rate": 0.0002, "epoch": 2.7250308261405674, "step": 2210}, {"loss": 0.7843, "grad_norm": 0.553961992263794, "learning_rate": 0.0002, "epoch": 2.7373612823674476, "step": 2220}, {"loss": 0.8633, "grad_norm": 0.4710180461406708, "learning_rate": 0.0002, "epoch": 2.7496917385943282, "step": 2230}, {"loss": 0.7469, "grad_norm": 0.8141706585884094, "learning_rate": 0.0002, "epoch": 2.7620221948212085, "step": 2240}, {"loss": 0.7086, "grad_norm": 0.7449556589126587, "learning_rate": 0.0002, "epoch": 2.7743526510480887, "step": 2250}, {"loss": 0.6933, "grad_norm": 0.5366780757904053, "learning_rate": 0.0002, "epoch": 2.7866831072749694, "step": 2260}, {"loss": 0.7192, "grad_norm": 0.5316720604896545, "learning_rate": 0.0002, "epoch": 2.7990135635018496, "step": 2270}, {"loss": 0.6212, "grad_norm": 0.4598459005355835, "learning_rate": 0.0002, "epoch": 2.81134401972873, "step": 2280}, {"loss": 0.7024, "grad_norm": 0.6852091550827026, "learning_rate": 0.0002, "epoch": 2.8236744759556105, "step": 2290}, {"loss": 0.7357, "grad_norm": 0.8040902018547058, "learning_rate": 0.0002, "epoch": 2.8360049321824907, "step": 2300}, {"loss": 0.7563, "grad_norm": 0.46976321935653687, "learning_rate": 0.0002, "epoch": 2.848335388409371, "step": 2310}, {"loss": 0.731, "grad_norm": 0.5214090347290039, "learning_rate": 0.0002, "epoch": 2.8606658446362516, "step": 2320}, {"loss": 0.6687, "grad_norm": 0.5323054790496826, "learning_rate": 0.0002, "epoch": 2.872996300863132, "step": 2330}, {"loss": 0.7895, "grad_norm": 0.6842264533042908, "learning_rate": 0.0002, "epoch": 2.885326757090012, "step": 2340}, {"loss": 0.7737, "grad_norm": 0.9157055616378784, "learning_rate": 0.0002, "epoch": 2.8976572133168927, "step": 2350}, {"loss": 0.7217, "grad_norm": 0.5253258347511292, "learning_rate": 0.0002, "epoch": 2.909987669543773, "step": 2360}, {"loss": 0.7162, "grad_norm": 0.4937705099582672, "learning_rate": 0.0002, "epoch": 2.9223181257706536, "step": 2370}, {"loss": 0.7008, "grad_norm": 0.48762989044189453, "learning_rate": 0.0002, "epoch": 2.934648581997534, "step": 2380}, {"loss": 0.8086, "grad_norm": 0.544335126876831, "learning_rate": 0.0002, "epoch": 2.9469790382244145, "step": 2390}, {"loss": 0.643, "grad_norm": 0.4847845435142517, "learning_rate": 0.0002, "epoch": 2.9593094944512948, "step": 2400}, {"loss": 0.7757, "grad_norm": 0.4787445366382599, "learning_rate": 0.0002, "epoch": 2.971639950678175, "step": 2410}, {"loss": 0.7678, "grad_norm": 1.022318959236145, "learning_rate": 0.0002, "epoch": 2.9839704069050557, "step": 2420}, {"loss": 0.6548, "grad_norm": 0.4987848103046417, "learning_rate": 0.0002, "epoch": 2.996300863131936, "step": 2430}, {"eval_loss": 1.2936296463012695, "eval_runtime": 94.7897, "eval_samples_per_second": 4.6, "eval_steps_per_second": 0.58, "epoch": 3.0, "step": 2433}, {"loss": 0.6073, "grad_norm": 0.5562372803688049, "learning_rate": 0.0002, "epoch": 3.008631319358816, "step": 2440}, {"loss": 0.5181, "grad_norm": 1.133402705192566, "learning_rate": 0.0002, "epoch": 3.020961775585697, "step": 2450}, {"loss": 0.5333, "grad_norm": 0.6480470299720764, "learning_rate": 0.0002, "epoch": 3.033292231812577, "step": 2460}, {"loss": 0.4828, "grad_norm": 0.8989138007164001, "learning_rate": 0.0002, "epoch": 3.0456226880394572, "step": 2470}, {"loss": 0.5097, "grad_norm": 0.8257461786270142, "learning_rate": 0.0002, "epoch": 3.057953144266338, "step": 2480}, {"loss": 0.6229, "grad_norm": 0.6813381910324097, "learning_rate": 0.0002, "epoch": 3.070283600493218, "step": 2490}, {"loss": 0.531, "grad_norm": 0.6989586353302002, "learning_rate": 0.0002, "epoch": 3.082614056720099, "step": 2500}, {"loss": 0.54, "grad_norm": 0.7992092967033386, "learning_rate": 0.0002, "epoch": 3.094944512946979, "step": 2510}, {"loss": 0.5054, "grad_norm": 0.698077917098999, "learning_rate": 0.0002, "epoch": 3.1072749691738593, "step": 2520}, {"loss": 0.5064, "grad_norm": 0.5699033141136169, "learning_rate": 0.0002, "epoch": 3.11960542540074, "step": 2530}, {"loss": 0.6088, "grad_norm": 0.6142355799674988, "learning_rate": 0.0002, "epoch": 3.13193588162762, "step": 2540}, {"loss": 0.585, "grad_norm": 0.7089933753013611, "learning_rate": 0.0002, "epoch": 3.144266337854501, "step": 2550}, {"loss": 0.5373, "grad_norm": 1.0107015371322632, "learning_rate": 0.0002, "epoch": 3.156596794081381, "step": 2560}, {"loss": 0.5429, "grad_norm": 0.568138837814331, "learning_rate": 0.0002, "epoch": 3.1689272503082613, "step": 2570}, {"loss": 0.5897, "grad_norm": 0.9960416555404663, "learning_rate": 0.0002, "epoch": 3.181257706535142, "step": 2580}, {"loss": 0.5211, "grad_norm": 0.6277595162391663, "learning_rate": 0.0002, "epoch": 3.193588162762022, "step": 2590}, {"loss": 0.5787, "grad_norm": 0.681083619594574, "learning_rate": 0.0002, "epoch": 3.2059186189889024, "step": 2600}, {"loss": 0.5166, "grad_norm": 0.5816057324409485, "learning_rate": 0.0002, "epoch": 3.218249075215783, "step": 2610}, {"loss": 0.545, "grad_norm": 0.7197734117507935, "learning_rate": 0.0002, "epoch": 3.2305795314426633, "step": 2620}, {"loss": 0.614, "grad_norm": 0.6524068117141724, "learning_rate": 0.0002, "epoch": 3.242909987669544, "step": 2630}, {"loss": 0.5456, "grad_norm": 1.273668646812439, "learning_rate": 0.0002, "epoch": 3.255240443896424, "step": 2640}, {"loss": 0.5266, "grad_norm": 0.6950451731681824, "learning_rate": 0.0002, "epoch": 3.2675709001233044, "step": 2650}, {"loss": 0.5194, "grad_norm": 0.8029071688652039, "learning_rate": 0.0002, "epoch": 3.279901356350185, "step": 2660}, {"loss": 0.5729, "grad_norm": 0.7464073896408081, "learning_rate": 0.0002, "epoch": 3.2922318125770653, "step": 2670}, {"loss": 0.5366, "grad_norm": 0.8342001438140869, "learning_rate": 0.0002, "epoch": 3.304562268803946, "step": 2680}, {"loss": 0.5413, "grad_norm": 0.5629868507385254, "learning_rate": 0.0002, "epoch": 3.316892725030826, "step": 2690}, {"loss": 0.633, "grad_norm": 0.753999650478363, "learning_rate": 0.0002, "epoch": 3.3292231812577064, "step": 2700}, {"loss": 0.5048, "grad_norm": 1.0271371603012085, "learning_rate": 0.0002, "epoch": 3.341553637484587, "step": 2710}, {"loss": 0.5233, "grad_norm": 0.9608535170555115, "learning_rate": 0.0002, "epoch": 3.3538840937114673, "step": 2720}, {"loss": 0.5102, "grad_norm": 0.7796488404273987, "learning_rate": 0.0002, "epoch": 3.3662145499383476, "step": 2730}, {"loss": 0.5172, "grad_norm": 0.5666437149047852, "learning_rate": 0.0002, "epoch": 3.3785450061652282, "step": 2740}, {"loss": 0.491, "grad_norm": 0.5462956428527832, "learning_rate": 0.0002, "epoch": 3.3908754623921085, "step": 2750}, {"loss": 0.5855, "grad_norm": 1.289099097251892, "learning_rate": 0.0002, "epoch": 3.4032059186189887, "step": 2760}, {"loss": 0.635, "grad_norm": 0.825566828250885, "learning_rate": 0.0002, "epoch": 3.4155363748458694, "step": 2770}, {"loss": 0.4998, "grad_norm": 0.8366670608520508, "learning_rate": 0.0002, "epoch": 3.4278668310727496, "step": 2780}, {"loss": 0.5732, "grad_norm": 1.0931549072265625, "learning_rate": 0.0002, "epoch": 3.4401972872996303, "step": 2790}, {"loss": 0.6093, "grad_norm": 0.9228858351707458, "learning_rate": 0.0002, "epoch": 3.4525277435265105, "step": 2800}, {"loss": 0.6089, "grad_norm": 1.3182806968688965, "learning_rate": 0.0002, "epoch": 3.4648581997533907, "step": 2810}, {"loss": 0.5665, "grad_norm": 0.8366976380348206, "learning_rate": 0.0002, "epoch": 3.4771886559802714, "step": 2820}, {"loss": 0.5666, "grad_norm": 0.8067695498466492, "learning_rate": 0.0002, "epoch": 3.4895191122071516, "step": 2830}, {"loss": 0.579, "grad_norm": 1.1163437366485596, "learning_rate": 0.0002, "epoch": 3.5018495684340323, "step": 2840}, {"loss": 0.5785, "grad_norm": 1.7196556329727173, "learning_rate": 0.0002, "epoch": 3.5141800246609125, "step": 2850}, {"loss": 0.5346, "grad_norm": 1.1267012357711792, "learning_rate": 0.0002, "epoch": 3.5265104808877927, "step": 2860}, {"loss": 0.447, "grad_norm": 0.7220137119293213, "learning_rate": 0.0002, "epoch": 3.5388409371146734, "step": 2870}, {"loss": 0.6099, "grad_norm": 0.914114773273468, "learning_rate": 0.0002, "epoch": 3.5511713933415536, "step": 2880}, {"loss": 0.6143, "grad_norm": 0.6193503141403198, "learning_rate": 0.0002, "epoch": 3.563501849568434, "step": 2890}, {"loss": 0.5171, "grad_norm": 0.6060135960578918, "learning_rate": 0.0002, "epoch": 3.5758323057953145, "step": 2900}, {"loss": 0.5659, "grad_norm": 1.0177327394485474, "learning_rate": 0.0002, "epoch": 3.5881627620221948, "step": 2910}, {"loss": 0.5711, "grad_norm": 0.5994468331336975, "learning_rate": 0.0002, "epoch": 3.600493218249075, "step": 2920}, {"loss": 0.6373, "grad_norm": 0.7450457215309143, "learning_rate": 0.0002, "epoch": 3.6128236744759556, "step": 2930}, {"loss": 0.4933, "grad_norm": 0.5825870037078857, "learning_rate": 0.0002, "epoch": 3.625154130702836, "step": 2940}, {"loss": 0.6016, "grad_norm": 0.6289743781089783, "learning_rate": 0.0002, "epoch": 3.6374845869297165, "step": 2950}, {"loss": 0.5507, "grad_norm": 0.7801929116249084, "learning_rate": 0.0002, "epoch": 3.6498150431565968, "step": 2960}, {"loss": 0.5695, "grad_norm": 1.1206634044647217, "learning_rate": 0.0002, "epoch": 3.6621454993834774, "step": 2970}, {"loss": 0.4985, "grad_norm": 0.6738817691802979, "learning_rate": 0.0002, "epoch": 3.6744759556103577, "step": 2980}, {"loss": 0.6209, "grad_norm": 1.1917344331741333, "learning_rate": 0.0002, "epoch": 3.686806411837238, "step": 2990}, {"loss": 0.5373, "grad_norm": 1.3738657236099243, "learning_rate": 0.0002, "epoch": 3.6991368680641186, "step": 3000}, {"loss": 0.5467, "grad_norm": 0.6642793416976929, "learning_rate": 0.0002, "epoch": 3.711467324290999, "step": 3010}, {"loss": 0.6243, "grad_norm": 0.9030995965003967, "learning_rate": 0.0002, "epoch": 3.723797780517879, "step": 3020}, {"loss": 0.592, "grad_norm": 1.0203914642333984, "learning_rate": 0.0002, "epoch": 3.7361282367447597, "step": 3030}, {"loss": 0.5453, "grad_norm": 0.648394763469696, "learning_rate": 0.0002, "epoch": 3.74845869297164, "step": 3040}, {"loss": 0.498, "grad_norm": 0.6304570436477661, "learning_rate": 0.0002, "epoch": 3.76078914919852, "step": 3050}, {"loss": 0.683, "grad_norm": 0.8286601901054382, "learning_rate": 0.0002, "epoch": 3.773119605425401, "step": 3060}, {"loss": 0.5302, "grad_norm": 0.906444251537323, "learning_rate": 0.0002, "epoch": 3.785450061652281, "step": 3070}, {"loss": 0.5345, "grad_norm": 1.4212149381637573, "learning_rate": 0.0002, "epoch": 3.7977805178791613, "step": 3080}, {"loss": 0.6403, "grad_norm": 0.7574319839477539, "learning_rate": 0.0002, "epoch": 3.810110974106042, "step": 3090}, {"loss": 0.5756, "grad_norm": 0.6534451246261597, "learning_rate": 0.0002, "epoch": 3.822441430332922, "step": 3100}, {"loss": 0.5306, "grad_norm": 0.7525447010993958, "learning_rate": 0.0002, "epoch": 3.834771886559803, "step": 3110}, {"loss": 0.5368, "grad_norm": 0.6513990759849548, "learning_rate": 0.0002, "epoch": 3.847102342786683, "step": 3120}, {"loss": 0.5492, "grad_norm": 0.7782694697380066, "learning_rate": 0.0002, "epoch": 3.8594327990135637, "step": 3130}, {"loss": 0.5727, "grad_norm": 0.7998530268669128, "learning_rate": 0.0002, "epoch": 3.871763255240444, "step": 3140}, {"loss": 0.5156, "grad_norm": 0.8045353293418884, "learning_rate": 0.0002, "epoch": 3.884093711467324, "step": 3150}, {"loss": 0.5341, "grad_norm": 0.8242645263671875, "learning_rate": 0.0002, "epoch": 3.896424167694205, "step": 3160}, {"loss": 0.5563, "grad_norm": 0.8302360773086548, "learning_rate": 0.0002, "epoch": 3.908754623921085, "step": 3170}, {"loss": 0.5793, "grad_norm": 0.8653109073638916, "learning_rate": 0.0002, "epoch": 3.9210850801479653, "step": 3180}, {"loss": 0.5219, "grad_norm": 0.6461338996887207, "learning_rate": 0.0002, "epoch": 3.933415536374846, "step": 3190}, {"loss": 0.6009, "grad_norm": 0.8267415165901184, "learning_rate": 0.0002, "epoch": 3.945745992601726, "step": 3200}, {"loss": 0.5956, "grad_norm": 1.1963194608688354, "learning_rate": 0.0002, "epoch": 3.9580764488286064, "step": 3210}, {"loss": 0.5692, "grad_norm": 0.7101966142654419, "learning_rate": 0.0002, "epoch": 3.970406905055487, "step": 3220}, {"loss": 0.5471, "grad_norm": 0.5931660532951355, "learning_rate": 0.0002, "epoch": 3.9827373612823673, "step": 3230}, {"loss": 0.5619, "grad_norm": 0.7465988993644714, "learning_rate": 0.0002, "epoch": 3.995067817509248, "step": 3240}, {"eval_loss": 1.4066498279571533, "eval_runtime": 95.7145, "eval_samples_per_second": 4.555, "eval_steps_per_second": 0.575, "epoch": 4.0, "step": 3244}, {"loss": 0.4948, "grad_norm": 0.9478800296783447, "learning_rate": 0.0002, "epoch": 4.007398273736128, "step": 3250}, {"loss": 0.4129, "grad_norm": 1.207059621810913, "learning_rate": 0.0002, "epoch": 4.019728729963009, "step": 3260}, {"loss": 0.3577, "grad_norm": 0.8984074592590332, "learning_rate": 0.0002, "epoch": 4.032059186189889, "step": 3270}, {"loss": 0.3798, "grad_norm": 0.8104140758514404, "learning_rate": 0.0002, "epoch": 4.044389642416769, "step": 3280}, {"loss": 0.3657, "grad_norm": 1.0875468254089355, "learning_rate": 0.0002, "epoch": 4.05672009864365, "step": 3290}, {"loss": 0.3703, "grad_norm": 0.8520309329032898, "learning_rate": 0.0002, "epoch": 4.06905055487053, "step": 3300}, {"loss": 0.3933, "grad_norm": 1.076735496520996, "learning_rate": 0.0002, "epoch": 4.0813810110974105, "step": 3310}, {"loss": 0.4422, "grad_norm": 0.7789369821548462, "learning_rate": 0.0002, "epoch": 4.093711467324291, "step": 3320}, {"loss": 0.4009, "grad_norm": 0.916862964630127, "learning_rate": 0.0002, "epoch": 4.106041923551172, "step": 3330}, {"loss": 0.3934, "grad_norm": 1.1251654624938965, "learning_rate": 0.0002, "epoch": 4.118372379778052, "step": 3340}, {"loss": 0.3651, "grad_norm": 0.9373420476913452, "learning_rate": 0.0002, "epoch": 4.130702836004932, "step": 3350}, {"loss": 0.384, "grad_norm": 1.03253972530365, "learning_rate": 0.0002, "epoch": 4.143033292231813, "step": 3360}, {"loss": 0.372, "grad_norm": 0.947023332118988, "learning_rate": 0.0002, "epoch": 4.155363748458693, "step": 3370}, {"loss": 0.4018, "grad_norm": 0.8709157109260559, "learning_rate": 0.0002, "epoch": 4.167694204685573, "step": 3380}, {"loss": 0.3754, "grad_norm": 0.930983304977417, "learning_rate": 0.0002, "epoch": 4.180024660912454, "step": 3390}, {"loss": 0.4248, "grad_norm": 1.092809796333313, "learning_rate": 0.0002, "epoch": 4.192355117139334, "step": 3400}, {"loss": 0.4453, "grad_norm": 0.8454303741455078, "learning_rate": 0.0002, "epoch": 4.2046855733662145, "step": 3410}, {"loss": 0.4198, "grad_norm": 0.957210123538971, "learning_rate": 0.0002, "epoch": 4.217016029593095, "step": 3420}, {"loss": 0.3743, "grad_norm": 0.854333758354187, "learning_rate": 0.0002, "epoch": 4.229346485819975, "step": 3430}, {"loss": 0.4041, "grad_norm": 1.0457639694213867, "learning_rate": 0.0002, "epoch": 4.241676942046856, "step": 3440}, {"loss": 0.3817, "grad_norm": 0.8972977995872498, "learning_rate": 0.0002, "epoch": 4.254007398273736, "step": 3450}, {"loss": 0.4445, "grad_norm": 1.0438238382339478, "learning_rate": 0.0002, "epoch": 4.266337854500616, "step": 3460}, {"loss": 0.4078, "grad_norm": 0.7000405192375183, "learning_rate": 0.0002, "epoch": 4.278668310727497, "step": 3470}, {"loss": 0.3718, "grad_norm": 1.0451240539550781, "learning_rate": 0.0002, "epoch": 4.290998766954377, "step": 3480}, {"loss": 0.4506, "grad_norm": 1.3339767456054688, "learning_rate": 0.0002, "epoch": 4.303329223181258, "step": 3490}, {"loss": 0.3999, "grad_norm": 0.7503946423530579, "learning_rate": 0.0002, "epoch": 4.315659679408138, "step": 3500}, {"loss": 0.4503, "grad_norm": 0.8443584442138672, "learning_rate": 0.0002, "epoch": 4.3279901356350186, "step": 3510}, {"loss": 0.3793, "grad_norm": 1.1681201457977295, "learning_rate": 0.0002, "epoch": 4.340320591861899, "step": 3520}, {"loss": 0.4462, "grad_norm": 1.078883171081543, "learning_rate": 0.0002, "epoch": 4.352651048088779, "step": 3530}, {"loss": 0.4216, "grad_norm": 0.6894834041595459, "learning_rate": 0.0002, "epoch": 4.36498150431566, "step": 3540}, {"loss": 0.4315, "grad_norm": 0.7059480547904968, "learning_rate": 0.0002, "epoch": 4.37731196054254, "step": 3550}, {"loss": 0.3821, "grad_norm": 1.1807256937026978, "learning_rate": 0.0002, "epoch": 4.38964241676942, "step": 3560}, {"loss": 0.4192, "grad_norm": 0.8341359496116638, "learning_rate": 0.0002, "epoch": 4.401972872996301, "step": 3570}, {"loss": 0.4123, "grad_norm": 1.0273033380508423, "learning_rate": 0.0002, "epoch": 4.4143033292231815, "step": 3580}, {"loss": 0.5018, "grad_norm": 0.6916454434394836, "learning_rate": 0.0002, "epoch": 4.426633785450061, "step": 3590}, {"loss": 0.3909, "grad_norm": 0.8210113644599915, "learning_rate": 0.0002, "epoch": 4.438964241676942, "step": 3600}, {"loss": 0.3893, "grad_norm": 1.0309500694274902, "learning_rate": 0.0002, "epoch": 4.451294697903823, "step": 3610}, {"loss": 0.3902, "grad_norm": 0.8847399353981018, "learning_rate": 0.0002, "epoch": 4.463625154130703, "step": 3620}, {"loss": 0.4198, "grad_norm": 1.668636679649353, "learning_rate": 0.0002, "epoch": 4.475955610357583, "step": 3630}, {"loss": 0.4075, "grad_norm": 1.3087958097457886, "learning_rate": 0.0002, "epoch": 4.488286066584464, "step": 3640}, {"loss": 0.4294, "grad_norm": 0.837852418422699, "learning_rate": 0.0002, "epoch": 4.500616522811344, "step": 3650}, {"loss": 0.4053, "grad_norm": 9.7662353515625, "learning_rate": 0.0002, "epoch": 4.512946979038224, "step": 3660}, {"loss": 0.4033, "grad_norm": 1.125719428062439, "learning_rate": 0.0002, "epoch": 4.525277435265105, "step": 3670}, {"loss": 0.4566, "grad_norm": 0.7755377292633057, "learning_rate": 0.0002, "epoch": 4.5376078914919855, "step": 3680}, {"loss": 0.4415, "grad_norm": 0.7185089588165283, "learning_rate": 0.0002, "epoch": 4.549938347718865, "step": 3690}, {"loss": 0.4616, "grad_norm": 1.182063102722168, "learning_rate": 0.0002, "epoch": 4.562268803945746, "step": 3700}, {"loss": 0.4572, "grad_norm": 1.001197338104248, "learning_rate": 0.0002, "epoch": 4.574599260172627, "step": 3710}, {"loss": 0.4493, "grad_norm": 0.9705429077148438, "learning_rate": 0.0002, "epoch": 4.586929716399506, "step": 3720}, {"loss": 0.42, "grad_norm": 0.7136746048927307, "learning_rate": 0.0002, "epoch": 4.599260172626387, "step": 3730}, {"loss": 0.3757, "grad_norm": 1.0004864931106567, "learning_rate": 0.0002, "epoch": 4.611590628853268, "step": 3740}, {"loss": 0.4418, "grad_norm": 1.3193715810775757, "learning_rate": 0.0002, "epoch": 4.623921085080148, "step": 3750}, {"loss": 0.4572, "grad_norm": 0.6945042014122009, "learning_rate": 0.0002, "epoch": 4.636251541307028, "step": 3760}, {"loss": 0.4255, "grad_norm": 0.8903936743736267, "learning_rate": 0.0002, "epoch": 4.648581997533909, "step": 3770}, {"loss": 0.3582, "grad_norm": 0.7960889339447021, "learning_rate": 0.0002, "epoch": 4.660912453760789, "step": 3780}, {"loss": 0.3864, "grad_norm": 1.0439172983169556, "learning_rate": 0.0002, "epoch": 4.673242909987669, "step": 3790}, {"loss": 0.4378, "grad_norm": 1.4546219110488892, "learning_rate": 0.0002, "epoch": 4.68557336621455, "step": 3800}, {"loss": 0.4191, "grad_norm": 0.8194343447685242, "learning_rate": 0.0002, "epoch": 4.697903822441431, "step": 3810}, {"loss": 0.4473, "grad_norm": 1.0727602243423462, "learning_rate": 0.0002, "epoch": 4.7102342786683105, "step": 3820}, {"loss": 0.4021, "grad_norm": 0.7785195708274841, "learning_rate": 0.0002, "epoch": 4.722564734895191, "step": 3830}, {"loss": 0.4252, "grad_norm": 0.846783459186554, "learning_rate": 0.0002, "epoch": 4.734895191122072, "step": 3840}, {"loss": 0.4647, "grad_norm": 1.0481648445129395, "learning_rate": 0.0002, "epoch": 4.747225647348952, "step": 3850}, {"loss": 0.4944, "grad_norm": 0.7324008941650391, "learning_rate": 0.0002, "epoch": 4.759556103575832, "step": 3860}, {"loss": 0.3831, "grad_norm": 1.06382417678833, "learning_rate": 0.0002, "epoch": 4.771886559802713, "step": 3870}, {"loss": 0.3934, "grad_norm": 0.9851241111755371, "learning_rate": 0.0002, "epoch": 4.784217016029594, "step": 3880}, {"loss": 0.5172, "grad_norm": 0.8215277791023254, "learning_rate": 0.0002, "epoch": 4.796547472256473, "step": 3890}, {"loss": 0.4437, "grad_norm": 0.9901723861694336, "learning_rate": 0.0002, "epoch": 4.808877928483354, "step": 3900}, {"loss": 0.4673, "grad_norm": 0.9149112701416016, "learning_rate": 0.0002, "epoch": 4.821208384710234, "step": 3910}, {"loss": 0.4295, "grad_norm": 0.9772973656654358, "learning_rate": 0.0002, "epoch": 4.8335388409371145, "step": 3920}, {"loss": 0.4346, "grad_norm": 0.8889636397361755, "learning_rate": 0.0002, "epoch": 4.845869297163995, "step": 3930}, {"loss": 0.421, "grad_norm": 1.3032807111740112, "learning_rate": 0.0002, "epoch": 4.858199753390876, "step": 3940}, {"loss": 0.434, "grad_norm": 0.8575899600982666, "learning_rate": 0.0002, "epoch": 4.870530209617756, "step": 3950}, {"loss": 0.4295, "grad_norm": 1.04326331615448, "learning_rate": 0.0002, "epoch": 4.882860665844636, "step": 3960}, {"loss": 0.3633, "grad_norm": 1.041210651397705, "learning_rate": 0.0002, "epoch": 4.895191122071517, "step": 3970}, {"loss": 0.4104, "grad_norm": 0.9113056063652039, "learning_rate": 0.0002, "epoch": 4.907521578298397, "step": 3980}, {"loss": 0.4496, "grad_norm": 1.019347906112671, "learning_rate": 0.0002, "epoch": 4.919852034525277, "step": 3990}, {"loss": 0.457, "grad_norm": 0.7709218859672546, "learning_rate": 0.0002, "epoch": 4.932182490752158, "step": 4000}, {"loss": 0.4697, "grad_norm": 0.8891775608062744, "learning_rate": 0.0002, "epoch": 4.944512946979038, "step": 4010}, {"loss": 0.4436, "grad_norm": 1.0396920442581177, "learning_rate": 0.0002, "epoch": 4.9568434032059185, "step": 4020}, {"loss": 0.4251, "grad_norm": 0.9239833354949951, "learning_rate": 0.0002, "epoch": 4.969173859432799, "step": 4030}, {"loss": 0.5049, "grad_norm": 1.801400065422058, "learning_rate": 0.0002, "epoch": 4.981504315659679, "step": 4040}, {"loss": 0.4481, "grad_norm": 0.6194164752960205, "learning_rate": 0.0002, "epoch": 4.99383477188656, "step": 4050}]}
+{"epoch": 6.0, "step": 4866, "epoch_duration": 2412.182984352112, "total_accumulated_duration": 14593.780698537827, "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": 28774.0}, "peak_memory_reserved": {"GPU_0": 28774.0}, "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-0.6-num-5885-sd-10000/checkpoint-1622", "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": 2.3601, "grad_norm": 0.8258164525032043, "learning_rate": 0.0002, "epoch": 0.012330456226880395, "step": 10}, {"loss": 1.7317, "grad_norm": 0.4577729105949402, "learning_rate": 0.0002, "epoch": 0.02466091245376079, "step": 20}, {"loss": 1.4729, "grad_norm": 0.639807939529419, "learning_rate": 0.0002, "epoch": 0.036991368680641186, "step": 30}, {"loss": 1.2088, "grad_norm": 0.5311757922172546, "learning_rate": 0.0002, "epoch": 0.04932182490752158, "step": 40}, {"loss": 1.3149, "grad_norm": 0.386595219373703, "learning_rate": 0.0002, "epoch": 0.06165228113440197, "step": 50}, {"loss": 1.1657, "grad_norm": 0.4401357173919678, "learning_rate": 0.0002, "epoch": 0.07398273736128237, "step": 60}, {"loss": 1.1022, "grad_norm": 0.3234352171421051, "learning_rate": 0.0002, "epoch": 0.08631319358816276, "step": 70}, {"loss": 1.3738, "grad_norm": 0.29643672704696655, "learning_rate": 0.0002, "epoch": 0.09864364981504316, "step": 80}, {"loss": 1.1929, "grad_norm": 0.2941012382507324, "learning_rate": 0.0002, "epoch": 0.11097410604192355, "step": 90}, {"loss": 1.2067, "grad_norm": 0.5498173832893372, "learning_rate": 0.0002, "epoch": 0.12330456226880394, "step": 100}, {"loss": 1.142, "grad_norm": 0.2545783519744873, "learning_rate": 0.0002, "epoch": 0.13563501849568435, "step": 110}, {"loss": 1.0297, "grad_norm": 0.2984241247177124, "learning_rate": 0.0002, "epoch": 0.14796547472256474, "step": 120}, {"loss": 1.1591, "grad_norm": 0.2710968852043152, "learning_rate": 0.0002, "epoch": 0.16029593094944514, "step": 130}, {"loss": 1.0427, "grad_norm": 0.2817152142524719, "learning_rate": 0.0002, "epoch": 0.17262638717632553, "step": 140}, {"loss": 1.0638, "grad_norm": 0.41083765029907227, "learning_rate": 0.0002, "epoch": 0.18495684340320592, "step": 150}, {"loss": 1.3537, "grad_norm": 0.36536213755607605, "learning_rate": 0.0002, "epoch": 0.19728729963008632, "step": 160}, {"loss": 1.0132, "grad_norm": 0.2738671600818634, "learning_rate": 0.0002, "epoch": 0.2096177558569667, "step": 170}, {"loss": 0.9555, "grad_norm": 0.27403146028518677, "learning_rate": 0.0002, "epoch": 0.2219482120838471, "step": 180}, {"loss": 1.0769, "grad_norm": 0.4446810483932495, "learning_rate": 0.0002, "epoch": 0.2342786683107275, "step": 190}, {"loss": 1.0588, "grad_norm": 0.5295385718345642, "learning_rate": 0.0002, "epoch": 0.2466091245376079, "step": 200}, {"loss": 1.0827, "grad_norm": 0.311404824256897, "learning_rate": 0.0002, "epoch": 0.2589395807644883, "step": 210}, {"loss": 1.1455, "grad_norm": 0.2448509782552719, "learning_rate": 0.0002, "epoch": 0.2712700369913687, "step": 220}, {"loss": 1.0929, "grad_norm": 0.6507014036178589, "learning_rate": 0.0002, "epoch": 0.2836004932182491, "step": 230}, {"loss": 0.9875, "grad_norm": 0.2339320331811905, "learning_rate": 0.0002, "epoch": 0.2959309494451295, "step": 240}, {"loss": 0.9211, "grad_norm": 0.8210226893424988, "learning_rate": 0.0002, "epoch": 0.3082614056720099, "step": 250}, {"loss": 1.161, "grad_norm": 0.27473965287208557, "learning_rate": 0.0002, "epoch": 0.3205918618988903, "step": 260}, {"loss": 1.0218, "grad_norm": 0.3051395118236542, "learning_rate": 0.0002, "epoch": 0.33292231812577067, "step": 270}, {"loss": 1.0286, "grad_norm": 0.3037777245044708, "learning_rate": 0.0002, "epoch": 0.34525277435265106, "step": 280}, {"loss": 1.144, "grad_norm": 0.2748974859714508, "learning_rate": 0.0002, "epoch": 0.35758323057953145, "step": 290}, {"loss": 1.0858, "grad_norm": 0.23656068742275238, "learning_rate": 0.0002, "epoch": 0.36991368680641185, "step": 300}, {"loss": 1.0564, "grad_norm": 0.2523384094238281, "learning_rate": 0.0002, "epoch": 0.38224414303329224, "step": 310}, {"loss": 1.3091, "grad_norm": 0.27848055958747864, "learning_rate": 0.0002, "epoch": 0.39457459926017263, "step": 320}, {"loss": 1.0252, "grad_norm": 0.3204525411128998, "learning_rate": 0.0002, "epoch": 0.406905055487053, "step": 330}, {"loss": 0.9855, "grad_norm": 0.3459707498550415, "learning_rate": 0.0002, "epoch": 0.4192355117139334, "step": 340}, {"loss": 1.1111, "grad_norm": 0.2458430379629135, "learning_rate": 0.0002, "epoch": 0.4315659679408138, "step": 350}, {"loss": 1.1493, "grad_norm": 0.5022910237312317, "learning_rate": 0.0002, "epoch": 0.4438964241676942, "step": 360}, {"loss": 1.1272, "grad_norm": 0.27076372504234314, "learning_rate": 0.0002, "epoch": 0.4562268803945746, "step": 370}, {"loss": 1.1927, "grad_norm": 0.6489047408103943, "learning_rate": 0.0002, "epoch": 0.468557336621455, "step": 380}, {"loss": 0.9501, "grad_norm": 0.3324144184589386, "learning_rate": 0.0002, "epoch": 0.4808877928483354, "step": 390}, {"loss": 1.2012, "grad_norm": 0.32813116908073425, "learning_rate": 0.0002, "epoch": 0.4932182490752158, "step": 400}, {"loss": 1.1135, "grad_norm": 0.25295355916023254, "learning_rate": 0.0002, "epoch": 0.5055487053020962, "step": 410}, {"loss": 0.9477, "grad_norm": 0.2912578880786896, "learning_rate": 0.0002, "epoch": 0.5178791615289766, "step": 420}, {"loss": 1.0121, "grad_norm": 0.34780189394950867, "learning_rate": 0.0002, "epoch": 0.530209617755857, "step": 430}, {"loss": 0.9296, "grad_norm": 0.24604526162147522, "learning_rate": 0.0002, "epoch": 0.5425400739827374, "step": 440}, {"loss": 1.253, "grad_norm": 0.32759982347488403, "learning_rate": 0.0002, "epoch": 0.5548705302096177, "step": 450}, {"loss": 1.1925, "grad_norm": 0.40810221433639526, "learning_rate": 0.0002, "epoch": 0.5672009864364982, "step": 460}, {"loss": 1.174, "grad_norm": 0.3590679466724396, "learning_rate": 0.0002, "epoch": 0.5795314426633785, "step": 470}, {"loss": 1.2223, "grad_norm": 0.5656213760375977, "learning_rate": 0.0002, "epoch": 0.591861898890259, "step": 480}, {"loss": 1.1936, "grad_norm": 0.30830657482147217, "learning_rate": 0.0002, "epoch": 0.6041923551171393, "step": 490}, {"loss": 1.1873, "grad_norm": 0.317905455827713, "learning_rate": 0.0002, "epoch": 0.6165228113440198, "step": 500}, {"loss": 0.9805, "grad_norm": 0.3254566490650177, "learning_rate": 0.0002, "epoch": 0.6288532675709001, "step": 510}, {"loss": 1.0384, "grad_norm": 0.29187721014022827, "learning_rate": 0.0002, "epoch": 0.6411837237977805, "step": 520}, {"loss": 1.2526, "grad_norm": 0.3439238965511322, "learning_rate": 0.0002, "epoch": 0.6535141800246609, "step": 530}, {"loss": 1.0698, "grad_norm": 0.20970556139945984, "learning_rate": 0.0002, "epoch": 0.6658446362515413, "step": 540}, {"loss": 1.1047, "grad_norm": 0.4022853374481201, "learning_rate": 0.0002, "epoch": 0.6781750924784217, "step": 550}, {"loss": 1.0684, "grad_norm": 0.2235759049654007, "learning_rate": 0.0002, "epoch": 0.6905055487053021, "step": 560}, {"loss": 1.2339, "grad_norm": 0.33849895000457764, "learning_rate": 0.0002, "epoch": 0.7028360049321825, "step": 570}, {"loss": 1.1929, "grad_norm": 0.34745967388153076, "learning_rate": 0.0002, "epoch": 0.7151664611590629, "step": 580}, {"loss": 1.1158, "grad_norm": 0.26041269302368164, "learning_rate": 0.0002, "epoch": 0.7274969173859432, "step": 590}, {"loss": 1.2134, "grad_norm": 0.3804777264595032, "learning_rate": 0.0002, "epoch": 0.7398273736128237, "step": 600}, {"loss": 1.0606, "grad_norm": 0.2456253319978714, "learning_rate": 0.0002, "epoch": 0.752157829839704, "step": 610}, {"loss": 1.0638, "grad_norm": 0.37838423252105713, "learning_rate": 0.0002, "epoch": 0.7644882860665845, "step": 620}, {"loss": 1.0556, "grad_norm": 0.28105494379997253, "learning_rate": 0.0002, "epoch": 0.7768187422934648, "step": 630}, {"loss": 1.0672, "grad_norm": 0.2774018943309784, "learning_rate": 0.0002, "epoch": 0.7891491985203453, "step": 640}, {"loss": 0.9978, "grad_norm": 1.8184229135513306, "learning_rate": 0.0002, "epoch": 0.8014796547472256, "step": 650}, {"loss": 1.1038, "grad_norm": 0.3325096070766449, "learning_rate": 0.0002, "epoch": 0.813810110974106, "step": 660}, {"loss": 1.083, "grad_norm": 0.2686693072319031, "learning_rate": 0.0002, "epoch": 0.8261405672009864, "step": 670}, {"loss": 1.1308, "grad_norm": 0.3271431624889374, "learning_rate": 0.0002, "epoch": 0.8384710234278668, "step": 680}, {"loss": 1.1116, "grad_norm": 2.359999656677246, "learning_rate": 0.0002, "epoch": 0.8508014796547472, "step": 690}, {"loss": 1.0782, "grad_norm": 0.46242964267730713, "learning_rate": 0.0002, "epoch": 0.8631319358816276, "step": 700}, {"loss": 0.95, "grad_norm": 0.34731170535087585, "learning_rate": 0.0002, "epoch": 0.8754623921085081, "step": 710}, {"loss": 1.2236, "grad_norm": 0.39381715655326843, "learning_rate": 0.0002, "epoch": 0.8877928483353884, "step": 720}, {"loss": 1.1319, "grad_norm": 0.43496373295783997, "learning_rate": 0.0002, "epoch": 0.9001233045622689, "step": 730}, {"loss": 1.0979, "grad_norm": 0.32243210077285767, "learning_rate": 0.0002, "epoch": 0.9124537607891492, "step": 740}, {"loss": 0.9913, "grad_norm": 0.30396756529808044, "learning_rate": 0.0002, "epoch": 0.9247842170160296, "step": 750}, {"loss": 1.1141, "grad_norm": 0.4461122751235962, "learning_rate": 0.0002, "epoch": 0.93711467324291, "step": 760}, {"loss": 1.0049, "grad_norm": 0.24081681668758392, "learning_rate": 0.0002, "epoch": 0.9494451294697904, "step": 770}, {"loss": 1.0966, "grad_norm": 0.27461910247802734, "learning_rate": 0.0002, "epoch": 0.9617755856966708, "step": 780}, {"loss": 0.9942, "grad_norm": 0.3325668275356293, "learning_rate": 0.0002, "epoch": 0.9741060419235512, "step": 790}, {"loss": 1.0506, "grad_norm": 0.24046339094638824, "learning_rate": 0.0002, "epoch": 0.9864364981504316, "step": 800}, {"loss": 0.9989, "grad_norm": 0.42950066924095154, "learning_rate": 0.0002, "epoch": 0.998766954377312, "step": 810}, {"eval_loss": 1.246457576751709, "eval_runtime": 98.7974, "eval_samples_per_second": 4.413, "eval_steps_per_second": 0.557, "epoch": 1.0, "step": 811}, {"loss": 1.0536, "grad_norm": 0.26760655641555786, "learning_rate": 0.0002, "epoch": 1.0110974106041923, "step": 820}, {"loss": 0.9722, "grad_norm": 0.4640820026397705, "learning_rate": 0.0002, "epoch": 1.0234278668310728, "step": 830}, {"loss": 0.9392, "grad_norm": 0.2699166238307953, "learning_rate": 0.0002, "epoch": 1.0357583230579532, "step": 840}, {"loss": 0.9335, "grad_norm": 0.3441709578037262, "learning_rate": 0.0002, "epoch": 1.0480887792848335, "step": 850}, {"loss": 0.9083, "grad_norm": 0.299934983253479, "learning_rate": 0.0002, "epoch": 1.060419235511714, "step": 860}, {"loss": 0.9416, "grad_norm": 0.2980666160583496, "learning_rate": 0.0002, "epoch": 1.0727496917385944, "step": 870}, {"loss": 0.94, "grad_norm": 0.3131714463233948, "learning_rate": 0.0002, "epoch": 1.0850801479654748, "step": 880}, {"loss": 0.9288, "grad_norm": 0.29881617426872253, "learning_rate": 0.0002, "epoch": 1.097410604192355, "step": 890}, {"loss": 0.998, "grad_norm": 0.29870888590812683, "learning_rate": 0.0002, "epoch": 1.1097410604192355, "step": 900}, {"loss": 0.9924, "grad_norm": 0.5735140442848206, "learning_rate": 0.0002, "epoch": 1.122071516646116, "step": 910}, {"loss": 1.0694, "grad_norm": 0.33159002661705017, "learning_rate": 0.0002, "epoch": 1.1344019728729964, "step": 920}, {"loss": 1.0069, "grad_norm": 1.235399842262268, "learning_rate": 0.0002, "epoch": 1.1467324290998766, "step": 930}, {"loss": 1.0315, "grad_norm": 0.27469736337661743, "learning_rate": 0.0002, "epoch": 1.159062885326757, "step": 940}, {"loss": 0.9386, "grad_norm": 0.29130664467811584, "learning_rate": 0.0002, "epoch": 1.1713933415536375, "step": 950}, {"loss": 0.8919, "grad_norm": 0.3730354607105255, "learning_rate": 0.0002, "epoch": 1.183723797780518, "step": 960}, {"loss": 0.9988, "grad_norm": 0.5973590612411499, "learning_rate": 0.0002, "epoch": 1.1960542540073984, "step": 970}, {"loss": 0.9525, "grad_norm": 0.39631304144859314, "learning_rate": 0.0002, "epoch": 1.2083847102342786, "step": 980}, {"loss": 0.9217, "grad_norm": 0.849051296710968, "learning_rate": 0.0002, "epoch": 1.220715166461159, "step": 990}, {"loss": 1.0903, "grad_norm": 0.4390525817871094, "learning_rate": 0.0002, "epoch": 1.2330456226880395, "step": 1000}, {"loss": 0.9018, "grad_norm": 0.30423852801322937, "learning_rate": 0.0002, "epoch": 1.2453760789149197, "step": 1010}, {"loss": 1.0128, "grad_norm": 0.34736061096191406, "learning_rate": 0.0002, "epoch": 1.2577065351418002, "step": 1020}, {"loss": 0.9026, "grad_norm": 0.3421604037284851, "learning_rate": 0.0002, "epoch": 1.2700369913686806, "step": 1030}, {"loss": 0.8485, "grad_norm": 0.544170081615448, "learning_rate": 0.0002, "epoch": 1.282367447595561, "step": 1040}, {"loss": 0.9591, "grad_norm": 0.5128790736198425, "learning_rate": 0.0002, "epoch": 1.2946979038224415, "step": 1050}, {"loss": 0.9214, "grad_norm": 0.443344384431839, "learning_rate": 0.0002, "epoch": 1.3070283600493218, "step": 1060}, {"loss": 0.9367, "grad_norm": 0.6380868554115295, "learning_rate": 0.0002, "epoch": 1.3193588162762022, "step": 1070}, {"loss": 0.9849, "grad_norm": 0.4638073146343231, "learning_rate": 0.0002, "epoch": 1.3316892725030827, "step": 1080}, {"loss": 0.8645, "grad_norm": 0.32406893372535706, "learning_rate": 0.0002, "epoch": 1.344019728729963, "step": 1090}, {"loss": 0.8278, "grad_norm": 0.3955065608024597, "learning_rate": 0.0002, "epoch": 1.3563501849568433, "step": 1100}, {"loss": 0.9306, "grad_norm": 0.3489246666431427, "learning_rate": 0.0002, "epoch": 1.3686806411837238, "step": 1110}, {"loss": 1.0138, "grad_norm": 0.48451653122901917, "learning_rate": 0.0002, "epoch": 1.3810110974106042, "step": 1120}, {"loss": 0.9165, "grad_norm": 0.3652360439300537, "learning_rate": 0.0002, "epoch": 1.3933415536374847, "step": 1130}, {"loss": 0.9576, "grad_norm": 1.3097436428070068, "learning_rate": 0.0002, "epoch": 1.405672009864365, "step": 1140}, {"loss": 0.8115, "grad_norm": 0.3647715449333191, "learning_rate": 0.0002, "epoch": 1.4180024660912454, "step": 1150}, {"loss": 0.8573, "grad_norm": 0.37248560786247253, "learning_rate": 0.0002, "epoch": 1.4303329223181258, "step": 1160}, {"loss": 0.936, "grad_norm": 0.4639643430709839, "learning_rate": 0.0002, "epoch": 1.442663378545006, "step": 1170}, {"loss": 0.9511, "grad_norm": 0.5455219745635986, "learning_rate": 0.0002, "epoch": 1.4549938347718865, "step": 1180}, {"loss": 0.8611, "grad_norm": 0.38862571120262146, "learning_rate": 0.0002, "epoch": 1.467324290998767, "step": 1190}, {"loss": 0.8681, "grad_norm": 0.37586215138435364, "learning_rate": 0.0002, "epoch": 1.4796547472256474, "step": 1200}, {"loss": 0.8673, "grad_norm": 0.46244436502456665, "learning_rate": 0.0002, "epoch": 1.4919852034525278, "step": 1210}, {"loss": 0.9388, "grad_norm": 0.3570359945297241, "learning_rate": 0.0002, "epoch": 1.504315659679408, "step": 1220}, {"loss": 0.971, "grad_norm": 0.28393083810806274, "learning_rate": 0.0002, "epoch": 1.5166461159062885, "step": 1230}, {"loss": 0.9296, "grad_norm": 0.5672869682312012, "learning_rate": 0.0002, "epoch": 1.528976572133169, "step": 1240}, {"loss": 0.8787, "grad_norm": 0.41605108976364136, "learning_rate": 0.0002, "epoch": 1.5413070283600492, "step": 1250}, {"loss": 0.8744, "grad_norm": 0.40657493472099304, "learning_rate": 0.0002, "epoch": 1.5536374845869299, "step": 1260}, {"loss": 0.9046, "grad_norm": 0.43672341108322144, "learning_rate": 0.0002, "epoch": 1.56596794081381, "step": 1270}, {"loss": 0.8586, "grad_norm": 0.3065410554409027, "learning_rate": 0.0002, "epoch": 1.5782983970406905, "step": 1280}, {"loss": 0.9499, "grad_norm": 0.37826645374298096, "learning_rate": 0.0002, "epoch": 1.590628853267571, "step": 1290}, {"loss": 0.901, "grad_norm": 0.42307335138320923, "learning_rate": 0.0002, "epoch": 1.6029593094944512, "step": 1300}, {"loss": 0.8673, "grad_norm": 0.3648843467235565, "learning_rate": 0.0002, "epoch": 1.6152897657213316, "step": 1310}, {"loss": 0.9302, "grad_norm": 0.8921076059341431, "learning_rate": 0.0002, "epoch": 1.627620221948212, "step": 1320}, {"loss": 0.9378, "grad_norm": 0.37522226572036743, "learning_rate": 0.0002, "epoch": 1.6399506781750923, "step": 1330}, {"loss": 0.8921, "grad_norm": 0.7489957809448242, "learning_rate": 0.0002, "epoch": 1.652281134401973, "step": 1340}, {"loss": 0.9297, "grad_norm": 0.31733131408691406, "learning_rate": 0.0002, "epoch": 1.6646115906288532, "step": 1350}, {"loss": 0.907, "grad_norm": 0.3249478340148926, "learning_rate": 0.0002, "epoch": 1.6769420468557337, "step": 1360}, {"loss": 1.0197, "grad_norm": 0.3178001344203949, "learning_rate": 0.0002, "epoch": 1.6892725030826141, "step": 1370}, {"loss": 1.0781, "grad_norm": 0.5674093961715698, "learning_rate": 0.0002, "epoch": 1.7016029593094943, "step": 1380}, {"loss": 0.8972, "grad_norm": 0.35272449254989624, "learning_rate": 0.0002, "epoch": 1.7139334155363748, "step": 1390}, {"loss": 0.9346, "grad_norm": 0.5778217911720276, "learning_rate": 0.0002, "epoch": 1.7262638717632552, "step": 1400}, {"loss": 0.9099, "grad_norm": 0.33561450242996216, "learning_rate": 0.0002, "epoch": 1.7385943279901355, "step": 1410}, {"loss": 0.8636, "grad_norm": 0.31735464930534363, "learning_rate": 0.0002, "epoch": 1.7509247842170161, "step": 1420}, {"loss": 0.982, "grad_norm": 1.0612670183181763, "learning_rate": 0.0002, "epoch": 1.7632552404438964, "step": 1430}, {"loss": 0.8224, "grad_norm": 0.5442509651184082, "learning_rate": 0.0002, "epoch": 1.7755856966707768, "step": 1440}, {"loss": 0.9275, "grad_norm": 0.7471332550048828, "learning_rate": 0.0002, "epoch": 1.7879161528976573, "step": 1450}, {"loss": 0.9389, "grad_norm": 0.4323609173297882, "learning_rate": 0.0002, "epoch": 1.8002466091245375, "step": 1460}, {"loss": 0.8247, "grad_norm": 0.47796759009361267, "learning_rate": 0.0002, "epoch": 1.8125770653514182, "step": 1470}, {"loss": 0.9395, "grad_norm": 0.3348400592803955, "learning_rate": 0.0002, "epoch": 1.8249075215782984, "step": 1480}, {"loss": 0.9793, "grad_norm": 0.3354550898075104, "learning_rate": 0.0002, "epoch": 1.8372379778051788, "step": 1490}, {"loss": 0.8581, "grad_norm": 0.5988477468490601, "learning_rate": 0.0002, "epoch": 1.8495684340320593, "step": 1500}, {"loss": 0.9268, "grad_norm": 0.5222318172454834, "learning_rate": 0.0002, "epoch": 1.8618988902589395, "step": 1510}, {"loss": 0.8846, "grad_norm": 0.5246642827987671, "learning_rate": 0.0002, "epoch": 1.87422934648582, "step": 1520}, {"loss": 0.9317, "grad_norm": 0.3164594769477844, "learning_rate": 0.0002, "epoch": 1.8865598027127004, "step": 1530}, {"loss": 0.9961, "grad_norm": 0.3496174216270447, "learning_rate": 0.0002, "epoch": 1.8988902589395806, "step": 1540}, {"loss": 0.9057, "grad_norm": 0.8863359689712524, "learning_rate": 0.0002, "epoch": 1.9112207151664613, "step": 1550}, {"loss": 0.9405, "grad_norm": 0.3587026298046112, "learning_rate": 0.0002, "epoch": 1.9235511713933415, "step": 1560}, {"loss": 0.8335, "grad_norm": 0.6052881479263306, "learning_rate": 0.0002, "epoch": 1.935881627620222, "step": 1570}, {"loss": 0.8805, "grad_norm": 0.567269504070282, "learning_rate": 0.0002, "epoch": 1.9482120838471024, "step": 1580}, {"loss": 0.9581, "grad_norm": 0.45184487104415894, "learning_rate": 0.0002, "epoch": 1.9605425400739827, "step": 1590}, {"loss": 0.9147, "grad_norm": 0.5028569102287292, "learning_rate": 0.0002, "epoch": 1.972872996300863, "step": 1600}, {"loss": 0.75, "grad_norm": 0.4677547216415405, "learning_rate": 0.0002, "epoch": 1.9852034525277436, "step": 1610}, {"loss": 0.8469, "grad_norm": 0.35106056928634644, "learning_rate": 0.0002, "epoch": 1.9975339087546238, "step": 1620}, {"eval_loss": 1.238026738166809, "eval_runtime": 95.4287, "eval_samples_per_second": 4.569, "eval_steps_per_second": 0.576, "epoch": 2.0, "step": 1622}, {"loss": 0.7629, "grad_norm": 0.444060355424881, "learning_rate": 0.0002, "epoch": 2.0098643649815044, "step": 1630}, {"loss": 0.772, "grad_norm": 0.627570390701294, "learning_rate": 0.0002, "epoch": 2.0221948212083847, "step": 1640}, {"loss": 0.6186, "grad_norm": 0.38737839460372925, "learning_rate": 0.0002, "epoch": 2.034525277435265, "step": 1650}, {"loss": 0.7734, "grad_norm": 0.4300459623336792, "learning_rate": 0.0002, "epoch": 2.0468557336621456, "step": 1660}, {"loss": 0.6943, "grad_norm": 0.43037715554237366, "learning_rate": 0.0002, "epoch": 2.059186189889026, "step": 1670}, {"loss": 0.6588, "grad_norm": 0.40772515535354614, "learning_rate": 0.0002, "epoch": 2.0715166461159065, "step": 1680}, {"loss": 0.8105, "grad_norm": 0.5295451879501343, "learning_rate": 0.0002, "epoch": 2.0838471023427867, "step": 1690}, {"loss": 0.7717, "grad_norm": 0.7452750205993652, "learning_rate": 0.0002, "epoch": 2.096177558569667, "step": 1700}, {"loss": 0.7458, "grad_norm": 0.809183657169342, "learning_rate": 0.0002, "epoch": 2.1085080147965476, "step": 1710}, {"loss": 0.7398, "grad_norm": 0.4597688913345337, "learning_rate": 0.0002, "epoch": 2.120838471023428, "step": 1720}, {"loss": 0.6856, "grad_norm": 0.806919276714325, "learning_rate": 0.0002, "epoch": 2.133168927250308, "step": 1730}, {"loss": 0.679, "grad_norm": 0.3755643665790558, "learning_rate": 0.0002, "epoch": 2.1454993834771887, "step": 1740}, {"loss": 0.7938, "grad_norm": 0.5882734060287476, "learning_rate": 0.0002, "epoch": 2.157829839704069, "step": 1750}, {"loss": 0.6782, "grad_norm": 0.692960798740387, "learning_rate": 0.0002, "epoch": 2.1701602959309496, "step": 1760}, {"loss": 0.7195, "grad_norm": 0.4737096428871155, "learning_rate": 0.0002, "epoch": 2.18249075215783, "step": 1770}, {"loss": 0.758, "grad_norm": 0.6637021899223328, "learning_rate": 0.0002, "epoch": 2.19482120838471, "step": 1780}, {"loss": 0.7139, "grad_norm": 0.9109764099121094, "learning_rate": 0.0002, "epoch": 2.2071516646115907, "step": 1790}, {"loss": 0.7373, "grad_norm": 0.4137539267539978, "learning_rate": 0.0002, "epoch": 2.219482120838471, "step": 1800}, {"loss": 0.7266, "grad_norm": 0.44995415210723877, "learning_rate": 0.0002, "epoch": 2.2318125770653516, "step": 1810}, {"loss": 0.7663, "grad_norm": 0.5985036492347717, "learning_rate": 0.0002, "epoch": 2.244143033292232, "step": 1820}, {"loss": 0.7502, "grad_norm": 0.7549490332603455, "learning_rate": 0.0002, "epoch": 2.256473489519112, "step": 1830}, {"loss": 0.7452, "grad_norm": 0.4490937888622284, "learning_rate": 0.0002, "epoch": 2.2688039457459928, "step": 1840}, {"loss": 0.7531, "grad_norm": 0.38859808444976807, "learning_rate": 0.0002, "epoch": 2.281134401972873, "step": 1850}, {"loss": 0.7278, "grad_norm": 1.0704916715621948, "learning_rate": 0.0002, "epoch": 2.293464858199753, "step": 1860}, {"loss": 0.7143, "grad_norm": 0.4647100865840912, "learning_rate": 0.0002, "epoch": 2.305795314426634, "step": 1870}, {"loss": 0.7146, "grad_norm": 0.6181163787841797, "learning_rate": 0.0002, "epoch": 2.318125770653514, "step": 1880}, {"loss": 0.7689, "grad_norm": 0.9241904020309448, "learning_rate": 0.0002, "epoch": 2.3304562268803943, "step": 1890}, {"loss": 0.7294, "grad_norm": 0.39101317524909973, "learning_rate": 0.0002, "epoch": 2.342786683107275, "step": 1900}, {"loss": 0.7079, "grad_norm": 0.49442458152770996, "learning_rate": 0.0002, "epoch": 2.3551171393341552, "step": 1910}, {"loss": 0.7586, "grad_norm": 0.4864824414253235, "learning_rate": 0.0002, "epoch": 2.367447595561036, "step": 1920}, {"loss": 0.7434, "grad_norm": 0.5427613854408264, "learning_rate": 0.0002, "epoch": 2.379778051787916, "step": 1930}, {"loss": 0.8423, "grad_norm": 0.7164974808692932, "learning_rate": 0.0002, "epoch": 2.392108508014797, "step": 1940}, {"loss": 0.6888, "grad_norm": 0.562979519367218, "learning_rate": 0.0002, "epoch": 2.404438964241677, "step": 1950}, {"loss": 0.7692, "grad_norm": 0.5631861090660095, "learning_rate": 0.0002, "epoch": 2.4167694204685573, "step": 1960}, {"loss": 0.67, "grad_norm": 0.4895121157169342, "learning_rate": 0.0002, "epoch": 2.429099876695438, "step": 1970}, {"loss": 0.7735, "grad_norm": 0.45674824714660645, "learning_rate": 0.0002, "epoch": 2.441430332922318, "step": 1980}, {"loss": 0.685, "grad_norm": 1.1424206495285034, "learning_rate": 0.0002, "epoch": 2.4537607891491984, "step": 1990}, {"loss": 0.7627, "grad_norm": 0.6314579844474792, "learning_rate": 0.0002, "epoch": 2.466091245376079, "step": 2000}, {"loss": 0.7118, "grad_norm": 0.5481605529785156, "learning_rate": 0.0002, "epoch": 2.4784217016029593, "step": 2010}, {"loss": 0.6947, "grad_norm": 0.4671579599380493, "learning_rate": 0.0002, "epoch": 2.4907521578298395, "step": 2020}, {"loss": 0.7377, "grad_norm": 0.7621194124221802, "learning_rate": 0.0002, "epoch": 2.50308261405672, "step": 2030}, {"loss": 0.69, "grad_norm": 0.38983288407325745, "learning_rate": 0.0002, "epoch": 2.5154130702836004, "step": 2040}, {"loss": 0.8381, "grad_norm": 0.6341150999069214, "learning_rate": 0.0002, "epoch": 2.5277435265104806, "step": 2050}, {"loss": 0.773, "grad_norm": 0.7151971459388733, "learning_rate": 0.0002, "epoch": 2.5400739827373613, "step": 2060}, {"loss": 0.6733, "grad_norm": 0.9665895104408264, "learning_rate": 0.0002, "epoch": 2.5524044389642415, "step": 2070}, {"loss": 0.7791, "grad_norm": 0.9572727680206299, "learning_rate": 0.0002, "epoch": 2.564734895191122, "step": 2080}, {"loss": 0.7205, "grad_norm": 1.1970765590667725, "learning_rate": 0.0002, "epoch": 2.5770653514180024, "step": 2090}, {"loss": 0.6736, "grad_norm": 0.5505942702293396, "learning_rate": 0.0002, "epoch": 2.589395807644883, "step": 2100}, {"loss": 0.673, "grad_norm": 0.5903949737548828, "learning_rate": 0.0002, "epoch": 2.6017262638717633, "step": 2110}, {"loss": 0.678, "grad_norm": 0.45640307664871216, "learning_rate": 0.0002, "epoch": 2.6140567200986435, "step": 2120}, {"loss": 0.6562, "grad_norm": 0.8763944506645203, "learning_rate": 0.0002, "epoch": 2.626387176325524, "step": 2130}, {"loss": 0.6484, "grad_norm": 0.4472963213920593, "learning_rate": 0.0002, "epoch": 2.6387176325524044, "step": 2140}, {"loss": 0.7702, "grad_norm": 0.5335086584091187, "learning_rate": 0.0002, "epoch": 2.6510480887792847, "step": 2150}, {"loss": 0.6851, "grad_norm": 0.805263340473175, "learning_rate": 0.0002, "epoch": 2.6633785450061653, "step": 2160}, {"loss": 0.7026, "grad_norm": 0.6332727670669556, "learning_rate": 0.0002, "epoch": 2.6757090012330456, "step": 2170}, {"loss": 0.7925, "grad_norm": 0.8667435646057129, "learning_rate": 0.0002, "epoch": 2.688039457459926, "step": 2180}, {"loss": 0.8044, "grad_norm": 0.5638955235481262, "learning_rate": 0.0002, "epoch": 2.7003699136868065, "step": 2190}, {"loss": 0.7117, "grad_norm": 0.4176250696182251, "learning_rate": 0.0002, "epoch": 2.7127003699136867, "step": 2200}, {"loss": 0.6932, "grad_norm": 0.6013461351394653, "learning_rate": 0.0002, "epoch": 2.7250308261405674, "step": 2210}, {"loss": 0.7843, "grad_norm": 0.553961992263794, "learning_rate": 0.0002, "epoch": 2.7373612823674476, "step": 2220}, {"loss": 0.8633, "grad_norm": 0.4710180461406708, "learning_rate": 0.0002, "epoch": 2.7496917385943282, "step": 2230}, {"loss": 0.7469, "grad_norm": 0.8141706585884094, "learning_rate": 0.0002, "epoch": 2.7620221948212085, "step": 2240}, {"loss": 0.7086, "grad_norm": 0.7449556589126587, "learning_rate": 0.0002, "epoch": 2.7743526510480887, "step": 2250}, {"loss": 0.6933, "grad_norm": 0.5366780757904053, "learning_rate": 0.0002, "epoch": 2.7866831072749694, "step": 2260}, {"loss": 0.7192, "grad_norm": 0.5316720604896545, "learning_rate": 0.0002, "epoch": 2.7990135635018496, "step": 2270}, {"loss": 0.6212, "grad_norm": 0.4598459005355835, "learning_rate": 0.0002, "epoch": 2.81134401972873, "step": 2280}, {"loss": 0.7024, "grad_norm": 0.6852091550827026, "learning_rate": 0.0002, "epoch": 2.8236744759556105, "step": 2290}, {"loss": 0.7357, "grad_norm": 0.8040902018547058, "learning_rate": 0.0002, "epoch": 2.8360049321824907, "step": 2300}, {"loss": 0.7563, "grad_norm": 0.46976321935653687, "learning_rate": 0.0002, "epoch": 2.848335388409371, "step": 2310}, {"loss": 0.731, "grad_norm": 0.5214090347290039, "learning_rate": 0.0002, "epoch": 2.8606658446362516, "step": 2320}, {"loss": 0.6687, "grad_norm": 0.5323054790496826, "learning_rate": 0.0002, "epoch": 2.872996300863132, "step": 2330}, {"loss": 0.7895, "grad_norm": 0.6842264533042908, "learning_rate": 0.0002, "epoch": 2.885326757090012, "step": 2340}, {"loss": 0.7737, "grad_norm": 0.9157055616378784, "learning_rate": 0.0002, "epoch": 2.8976572133168927, "step": 2350}, {"loss": 0.7217, "grad_norm": 0.5253258347511292, "learning_rate": 0.0002, "epoch": 2.909987669543773, "step": 2360}, {"loss": 0.7162, "grad_norm": 0.4937705099582672, "learning_rate": 0.0002, "epoch": 2.9223181257706536, "step": 2370}, {"loss": 0.7008, "grad_norm": 0.48762989044189453, "learning_rate": 0.0002, "epoch": 2.934648581997534, "step": 2380}, {"loss": 0.8086, "grad_norm": 0.544335126876831, "learning_rate": 0.0002, "epoch": 2.9469790382244145, "step": 2390}, {"loss": 0.643, "grad_norm": 0.4847845435142517, "learning_rate": 0.0002, "epoch": 2.9593094944512948, "step": 2400}, {"loss": 0.7757, "grad_norm": 0.4787445366382599, "learning_rate": 0.0002, "epoch": 2.971639950678175, "step": 2410}, {"loss": 0.7678, "grad_norm": 1.022318959236145, "learning_rate": 0.0002, "epoch": 2.9839704069050557, "step": 2420}, {"loss": 0.6548, "grad_norm": 0.4987848103046417, "learning_rate": 0.0002, "epoch": 2.996300863131936, "step": 2430}, {"eval_loss": 1.2936296463012695, "eval_runtime": 94.7897, "eval_samples_per_second": 4.6, "eval_steps_per_second": 0.58, "epoch": 3.0, "step": 2433}, {"loss": 0.6073, "grad_norm": 0.5562372803688049, "learning_rate": 0.0002, "epoch": 3.008631319358816, "step": 2440}, {"loss": 0.5181, "grad_norm": 1.133402705192566, "learning_rate": 0.0002, "epoch": 3.020961775585697, "step": 2450}, {"loss": 0.5333, "grad_norm": 0.6480470299720764, "learning_rate": 0.0002, "epoch": 3.033292231812577, "step": 2460}, {"loss": 0.4828, "grad_norm": 0.8989138007164001, "learning_rate": 0.0002, "epoch": 3.0456226880394572, "step": 2470}, {"loss": 0.5097, "grad_norm": 0.8257461786270142, "learning_rate": 0.0002, "epoch": 3.057953144266338, "step": 2480}, {"loss": 0.6229, "grad_norm": 0.6813381910324097, "learning_rate": 0.0002, "epoch": 3.070283600493218, "step": 2490}, {"loss": 0.531, "grad_norm": 0.6989586353302002, "learning_rate": 0.0002, "epoch": 3.082614056720099, "step": 2500}, {"loss": 0.54, "grad_norm": 0.7992092967033386, "learning_rate": 0.0002, "epoch": 3.094944512946979, "step": 2510}, {"loss": 0.5054, "grad_norm": 0.698077917098999, "learning_rate": 0.0002, "epoch": 3.1072749691738593, "step": 2520}, {"loss": 0.5064, "grad_norm": 0.5699033141136169, "learning_rate": 0.0002, "epoch": 3.11960542540074, "step": 2530}, {"loss": 0.6088, "grad_norm": 0.6142355799674988, "learning_rate": 0.0002, "epoch": 3.13193588162762, "step": 2540}, {"loss": 0.585, "grad_norm": 0.7089933753013611, "learning_rate": 0.0002, "epoch": 3.144266337854501, "step": 2550}, {"loss": 0.5373, "grad_norm": 1.0107015371322632, "learning_rate": 0.0002, "epoch": 3.156596794081381, "step": 2560}, {"loss": 0.5429, "grad_norm": 0.568138837814331, "learning_rate": 0.0002, "epoch": 3.1689272503082613, "step": 2570}, {"loss": 0.5897, "grad_norm": 0.9960416555404663, "learning_rate": 0.0002, "epoch": 3.181257706535142, "step": 2580}, {"loss": 0.5211, "grad_norm": 0.6277595162391663, "learning_rate": 0.0002, "epoch": 3.193588162762022, "step": 2590}, {"loss": 0.5787, "grad_norm": 0.681083619594574, "learning_rate": 0.0002, "epoch": 3.2059186189889024, "step": 2600}, {"loss": 0.5166, "grad_norm": 0.5816057324409485, "learning_rate": 0.0002, "epoch": 3.218249075215783, "step": 2610}, {"loss": 0.545, "grad_norm": 0.7197734117507935, "learning_rate": 0.0002, "epoch": 3.2305795314426633, "step": 2620}, {"loss": 0.614, "grad_norm": 0.6524068117141724, "learning_rate": 0.0002, "epoch": 3.242909987669544, "step": 2630}, {"loss": 0.5456, "grad_norm": 1.273668646812439, "learning_rate": 0.0002, "epoch": 3.255240443896424, "step": 2640}, {"loss": 0.5266, "grad_norm": 0.6950451731681824, "learning_rate": 0.0002, "epoch": 3.2675709001233044, "step": 2650}, {"loss": 0.5194, "grad_norm": 0.8029071688652039, "learning_rate": 0.0002, "epoch": 3.279901356350185, "step": 2660}, {"loss": 0.5729, "grad_norm": 0.7464073896408081, "learning_rate": 0.0002, "epoch": 3.2922318125770653, "step": 2670}, {"loss": 0.5366, "grad_norm": 0.8342001438140869, "learning_rate": 0.0002, "epoch": 3.304562268803946, "step": 2680}, {"loss": 0.5413, "grad_norm": 0.5629868507385254, "learning_rate": 0.0002, "epoch": 3.316892725030826, "step": 2690}, {"loss": 0.633, "grad_norm": 0.753999650478363, "learning_rate": 0.0002, "epoch": 3.3292231812577064, "step": 2700}, {"loss": 0.5048, "grad_norm": 1.0271371603012085, "learning_rate": 0.0002, "epoch": 3.341553637484587, "step": 2710}, {"loss": 0.5233, "grad_norm": 0.9608535170555115, "learning_rate": 0.0002, "epoch": 3.3538840937114673, "step": 2720}, {"loss": 0.5102, "grad_norm": 0.7796488404273987, "learning_rate": 0.0002, "epoch": 3.3662145499383476, "step": 2730}, {"loss": 0.5172, "grad_norm": 0.5666437149047852, "learning_rate": 0.0002, "epoch": 3.3785450061652282, "step": 2740}, {"loss": 0.491, "grad_norm": 0.5462956428527832, "learning_rate": 0.0002, "epoch": 3.3908754623921085, "step": 2750}, {"loss": 0.5855, "grad_norm": 1.289099097251892, "learning_rate": 0.0002, "epoch": 3.4032059186189887, "step": 2760}, {"loss": 0.635, "grad_norm": 0.825566828250885, "learning_rate": 0.0002, "epoch": 3.4155363748458694, "step": 2770}, {"loss": 0.4998, "grad_norm": 0.8366670608520508, "learning_rate": 0.0002, "epoch": 3.4278668310727496, "step": 2780}, {"loss": 0.5732, "grad_norm": 1.0931549072265625, "learning_rate": 0.0002, "epoch": 3.4401972872996303, "step": 2790}, {"loss": 0.6093, "grad_norm": 0.9228858351707458, "learning_rate": 0.0002, "epoch": 3.4525277435265105, "step": 2800}, {"loss": 0.6089, "grad_norm": 1.3182806968688965, "learning_rate": 0.0002, "epoch": 3.4648581997533907, "step": 2810}, {"loss": 0.5665, "grad_norm": 0.8366976380348206, "learning_rate": 0.0002, "epoch": 3.4771886559802714, "step": 2820}, {"loss": 0.5666, "grad_norm": 0.8067695498466492, "learning_rate": 0.0002, "epoch": 3.4895191122071516, "step": 2830}, {"loss": 0.579, "grad_norm": 1.1163437366485596, "learning_rate": 0.0002, "epoch": 3.5018495684340323, "step": 2840}, {"loss": 0.5785, "grad_norm": 1.7196556329727173, "learning_rate": 0.0002, "epoch": 3.5141800246609125, "step": 2850}, {"loss": 0.5346, "grad_norm": 1.1267012357711792, "learning_rate": 0.0002, "epoch": 3.5265104808877927, "step": 2860}, {"loss": 0.447, "grad_norm": 0.7220137119293213, "learning_rate": 0.0002, "epoch": 3.5388409371146734, "step": 2870}, {"loss": 0.6099, "grad_norm": 0.914114773273468, "learning_rate": 0.0002, "epoch": 3.5511713933415536, "step": 2880}, {"loss": 0.6143, "grad_norm": 0.6193503141403198, "learning_rate": 0.0002, "epoch": 3.563501849568434, "step": 2890}, {"loss": 0.5171, "grad_norm": 0.6060135960578918, "learning_rate": 0.0002, "epoch": 3.5758323057953145, "step": 2900}, {"loss": 0.5659, "grad_norm": 1.0177327394485474, "learning_rate": 0.0002, "epoch": 3.5881627620221948, "step": 2910}, {"loss": 0.5711, "grad_norm": 0.5994468331336975, "learning_rate": 0.0002, "epoch": 3.600493218249075, "step": 2920}, {"loss": 0.6373, "grad_norm": 0.7450457215309143, "learning_rate": 0.0002, "epoch": 3.6128236744759556, "step": 2930}, {"loss": 0.4933, "grad_norm": 0.5825870037078857, "learning_rate": 0.0002, "epoch": 3.625154130702836, "step": 2940}, {"loss": 0.6016, "grad_norm": 0.6289743781089783, "learning_rate": 0.0002, "epoch": 3.6374845869297165, "step": 2950}, {"loss": 0.5507, "grad_norm": 0.7801929116249084, "learning_rate": 0.0002, "epoch": 3.6498150431565968, "step": 2960}, {"loss": 0.5695, "grad_norm": 1.1206634044647217, "learning_rate": 0.0002, "epoch": 3.6621454993834774, "step": 2970}, {"loss": 0.4985, "grad_norm": 0.6738817691802979, "learning_rate": 0.0002, "epoch": 3.6744759556103577, "step": 2980}, {"loss": 0.6209, "grad_norm": 1.1917344331741333, "learning_rate": 0.0002, "epoch": 3.686806411837238, "step": 2990}, {"loss": 0.5373, "grad_norm": 1.3738657236099243, "learning_rate": 0.0002, "epoch": 3.6991368680641186, "step": 3000}, {"loss": 0.5467, "grad_norm": 0.6642793416976929, "learning_rate": 0.0002, "epoch": 3.711467324290999, "step": 3010}, {"loss": 0.6243, "grad_norm": 0.9030995965003967, "learning_rate": 0.0002, "epoch": 3.723797780517879, "step": 3020}, {"loss": 0.592, "grad_norm": 1.0203914642333984, "learning_rate": 0.0002, "epoch": 3.7361282367447597, "step": 3030}, {"loss": 0.5453, "grad_norm": 0.648394763469696, "learning_rate": 0.0002, "epoch": 3.74845869297164, "step": 3040}, {"loss": 0.498, "grad_norm": 0.6304570436477661, "learning_rate": 0.0002, "epoch": 3.76078914919852, "step": 3050}, {"loss": 0.683, "grad_norm": 0.8286601901054382, "learning_rate": 0.0002, "epoch": 3.773119605425401, "step": 3060}, {"loss": 0.5302, "grad_norm": 0.906444251537323, "learning_rate": 0.0002, "epoch": 3.785450061652281, "step": 3070}, {"loss": 0.5345, "grad_norm": 1.4212149381637573, "learning_rate": 0.0002, "epoch": 3.7977805178791613, "step": 3080}, {"loss": 0.6403, "grad_norm": 0.7574319839477539, "learning_rate": 0.0002, "epoch": 3.810110974106042, "step": 3090}, {"loss": 0.5756, "grad_norm": 0.6534451246261597, "learning_rate": 0.0002, "epoch": 3.822441430332922, "step": 3100}, {"loss": 0.5306, "grad_norm": 0.7525447010993958, "learning_rate": 0.0002, "epoch": 3.834771886559803, "step": 3110}, {"loss": 0.5368, "grad_norm": 0.6513990759849548, "learning_rate": 0.0002, "epoch": 3.847102342786683, "step": 3120}, {"loss": 0.5492, "grad_norm": 0.7782694697380066, "learning_rate": 0.0002, "epoch": 3.8594327990135637, "step": 3130}, {"loss": 0.5727, "grad_norm": 0.7998530268669128, "learning_rate": 0.0002, "epoch": 3.871763255240444, "step": 3140}, {"loss": 0.5156, "grad_norm": 0.8045353293418884, "learning_rate": 0.0002, "epoch": 3.884093711467324, "step": 3150}, {"loss": 0.5341, "grad_norm": 0.8242645263671875, "learning_rate": 0.0002, "epoch": 3.896424167694205, "step": 3160}, {"loss": 0.5563, "grad_norm": 0.8302360773086548, "learning_rate": 0.0002, "epoch": 3.908754623921085, "step": 3170}, {"loss": 0.5793, "grad_norm": 0.8653109073638916, "learning_rate": 0.0002, "epoch": 3.9210850801479653, "step": 3180}, {"loss": 0.5219, "grad_norm": 0.6461338996887207, "learning_rate": 0.0002, "epoch": 3.933415536374846, "step": 3190}, {"loss": 0.6009, "grad_norm": 0.8267415165901184, "learning_rate": 0.0002, "epoch": 3.945745992601726, "step": 3200}, {"loss": 0.5956, "grad_norm": 1.1963194608688354, "learning_rate": 0.0002, "epoch": 3.9580764488286064, "step": 3210}, {"loss": 0.5692, "grad_norm": 0.7101966142654419, "learning_rate": 0.0002, "epoch": 3.970406905055487, "step": 3220}, {"loss": 0.5471, "grad_norm": 0.5931660532951355, "learning_rate": 0.0002, "epoch": 3.9827373612823673, "step": 3230}, {"loss": 0.5619, "grad_norm": 0.7465988993644714, "learning_rate": 0.0002, "epoch": 3.995067817509248, "step": 3240}, {"eval_loss": 1.4066498279571533, "eval_runtime": 95.7145, "eval_samples_per_second": 4.555, "eval_steps_per_second": 0.575, "epoch": 4.0, "step": 3244}, {"loss": 0.4948, "grad_norm": 0.9478800296783447, "learning_rate": 0.0002, "epoch": 4.007398273736128, "step": 3250}, {"loss": 0.4129, "grad_norm": 1.207059621810913, "learning_rate": 0.0002, "epoch": 4.019728729963009, "step": 3260}, {"loss": 0.3577, "grad_norm": 0.8984074592590332, "learning_rate": 0.0002, "epoch": 4.032059186189889, "step": 3270}, {"loss": 0.3798, "grad_norm": 0.8104140758514404, "learning_rate": 0.0002, "epoch": 4.044389642416769, "step": 3280}, {"loss": 0.3657, "grad_norm": 1.0875468254089355, "learning_rate": 0.0002, "epoch": 4.05672009864365, "step": 3290}, {"loss": 0.3703, "grad_norm": 0.8520309329032898, "learning_rate": 0.0002, "epoch": 4.06905055487053, "step": 3300}, {"loss": 0.3933, "grad_norm": 1.076735496520996, "learning_rate": 0.0002, "epoch": 4.0813810110974105, "step": 3310}, {"loss": 0.4422, "grad_norm": 0.7789369821548462, "learning_rate": 0.0002, "epoch": 4.093711467324291, "step": 3320}, {"loss": 0.4009, "grad_norm": 0.916862964630127, "learning_rate": 0.0002, "epoch": 4.106041923551172, "step": 3330}, {"loss": 0.3934, "grad_norm": 1.1251654624938965, "learning_rate": 0.0002, "epoch": 4.118372379778052, "step": 3340}, {"loss": 0.3651, "grad_norm": 0.9373420476913452, "learning_rate": 0.0002, "epoch": 4.130702836004932, "step": 3350}, {"loss": 0.384, "grad_norm": 1.03253972530365, "learning_rate": 0.0002, "epoch": 4.143033292231813, "step": 3360}, {"loss": 0.372, "grad_norm": 0.947023332118988, "learning_rate": 0.0002, "epoch": 4.155363748458693, "step": 3370}, {"loss": 0.4018, "grad_norm": 0.8709157109260559, "learning_rate": 0.0002, "epoch": 4.167694204685573, "step": 3380}, {"loss": 0.3754, "grad_norm": 0.930983304977417, "learning_rate": 0.0002, "epoch": 4.180024660912454, "step": 3390}, {"loss": 0.4248, "grad_norm": 1.092809796333313, "learning_rate": 0.0002, "epoch": 4.192355117139334, "step": 3400}, {"loss": 0.4453, "grad_norm": 0.8454303741455078, "learning_rate": 0.0002, "epoch": 4.2046855733662145, "step": 3410}, {"loss": 0.4198, "grad_norm": 0.957210123538971, "learning_rate": 0.0002, "epoch": 4.217016029593095, "step": 3420}, {"loss": 0.3743, "grad_norm": 0.854333758354187, "learning_rate": 0.0002, "epoch": 4.229346485819975, "step": 3430}, {"loss": 0.4041, "grad_norm": 1.0457639694213867, "learning_rate": 0.0002, "epoch": 4.241676942046856, "step": 3440}, {"loss": 0.3817, "grad_norm": 0.8972977995872498, "learning_rate": 0.0002, "epoch": 4.254007398273736, "step": 3450}, {"loss": 0.4445, "grad_norm": 1.0438238382339478, "learning_rate": 0.0002, "epoch": 4.266337854500616, "step": 3460}, {"loss": 0.4078, "grad_norm": 0.7000405192375183, "learning_rate": 0.0002, "epoch": 4.278668310727497, "step": 3470}, {"loss": 0.3718, "grad_norm": 1.0451240539550781, "learning_rate": 0.0002, "epoch": 4.290998766954377, "step": 3480}, {"loss": 0.4506, "grad_norm": 1.3339767456054688, "learning_rate": 0.0002, "epoch": 4.303329223181258, "step": 3490}, {"loss": 0.3999, "grad_norm": 0.7503946423530579, "learning_rate": 0.0002, "epoch": 4.315659679408138, "step": 3500}, {"loss": 0.4503, "grad_norm": 0.8443584442138672, "learning_rate": 0.0002, "epoch": 4.3279901356350186, "step": 3510}, {"loss": 0.3793, "grad_norm": 1.1681201457977295, "learning_rate": 0.0002, "epoch": 4.340320591861899, "step": 3520}, {"loss": 0.4462, "grad_norm": 1.078883171081543, "learning_rate": 0.0002, "epoch": 4.352651048088779, "step": 3530}, {"loss": 0.4216, "grad_norm": 0.6894834041595459, "learning_rate": 0.0002, "epoch": 4.36498150431566, "step": 3540}, {"loss": 0.4315, "grad_norm": 0.7059480547904968, "learning_rate": 0.0002, "epoch": 4.37731196054254, "step": 3550}, {"loss": 0.3821, "grad_norm": 1.1807256937026978, "learning_rate": 0.0002, "epoch": 4.38964241676942, "step": 3560}, {"loss": 0.4192, "grad_norm": 0.8341359496116638, "learning_rate": 0.0002, "epoch": 4.401972872996301, "step": 3570}, {"loss": 0.4123, "grad_norm": 1.0273033380508423, "learning_rate": 0.0002, "epoch": 4.4143033292231815, "step": 3580}, {"loss": 0.5018, "grad_norm": 0.6916454434394836, "learning_rate": 0.0002, "epoch": 4.426633785450061, "step": 3590}, {"loss": 0.3909, "grad_norm": 0.8210113644599915, "learning_rate": 0.0002, "epoch": 4.438964241676942, "step": 3600}, {"loss": 0.3893, "grad_norm": 1.0309500694274902, "learning_rate": 0.0002, "epoch": 4.451294697903823, "step": 3610}, {"loss": 0.3902, "grad_norm": 0.8847399353981018, "learning_rate": 0.0002, "epoch": 4.463625154130703, "step": 3620}, {"loss": 0.4198, "grad_norm": 1.668636679649353, "learning_rate": 0.0002, "epoch": 4.475955610357583, "step": 3630}, {"loss": 0.4075, "grad_norm": 1.3087958097457886, "learning_rate": 0.0002, "epoch": 4.488286066584464, "step": 3640}, {"loss": 0.4294, "grad_norm": 0.837852418422699, "learning_rate": 0.0002, "epoch": 4.500616522811344, "step": 3650}, {"loss": 0.4053, "grad_norm": 9.7662353515625, "learning_rate": 0.0002, "epoch": 4.512946979038224, "step": 3660}, {"loss": 0.4033, "grad_norm": 1.125719428062439, "learning_rate": 0.0002, "epoch": 4.525277435265105, "step": 3670}, {"loss": 0.4566, "grad_norm": 0.7755377292633057, "learning_rate": 0.0002, "epoch": 4.5376078914919855, "step": 3680}, {"loss": 0.4415, "grad_norm": 0.7185089588165283, "learning_rate": 0.0002, "epoch": 4.549938347718865, "step": 3690}, {"loss": 0.4616, "grad_norm": 1.182063102722168, "learning_rate": 0.0002, "epoch": 4.562268803945746, "step": 3700}, {"loss": 0.4572, "grad_norm": 1.001197338104248, "learning_rate": 0.0002, "epoch": 4.574599260172627, "step": 3710}, {"loss": 0.4493, "grad_norm": 0.9705429077148438, "learning_rate": 0.0002, "epoch": 4.586929716399506, "step": 3720}, {"loss": 0.42, "grad_norm": 0.7136746048927307, "learning_rate": 0.0002, "epoch": 4.599260172626387, "step": 3730}, {"loss": 0.3757, "grad_norm": 1.0004864931106567, "learning_rate": 0.0002, "epoch": 4.611590628853268, "step": 3740}, {"loss": 0.4418, "grad_norm": 1.3193715810775757, "learning_rate": 0.0002, "epoch": 4.623921085080148, "step": 3750}, {"loss": 0.4572, "grad_norm": 0.6945042014122009, "learning_rate": 0.0002, "epoch": 4.636251541307028, "step": 3760}, {"loss": 0.4255, "grad_norm": 0.8903936743736267, "learning_rate": 0.0002, "epoch": 4.648581997533909, "step": 3770}, {"loss": 0.3582, "grad_norm": 0.7960889339447021, "learning_rate": 0.0002, "epoch": 4.660912453760789, "step": 3780}, {"loss": 0.3864, "grad_norm": 1.0439172983169556, "learning_rate": 0.0002, "epoch": 4.673242909987669, "step": 3790}, {"loss": 0.4378, "grad_norm": 1.4546219110488892, "learning_rate": 0.0002, "epoch": 4.68557336621455, "step": 3800}, {"loss": 0.4191, "grad_norm": 0.8194343447685242, "learning_rate": 0.0002, "epoch": 4.697903822441431, "step": 3810}, {"loss": 0.4473, "grad_norm": 1.0727602243423462, "learning_rate": 0.0002, "epoch": 4.7102342786683105, "step": 3820}, {"loss": 0.4021, "grad_norm": 0.7785195708274841, "learning_rate": 0.0002, "epoch": 4.722564734895191, "step": 3830}, {"loss": 0.4252, "grad_norm": 0.846783459186554, "learning_rate": 0.0002, "epoch": 4.734895191122072, "step": 3840}, {"loss": 0.4647, "grad_norm": 1.0481648445129395, "learning_rate": 0.0002, "epoch": 4.747225647348952, "step": 3850}, {"loss": 0.4944, "grad_norm": 0.7324008941650391, "learning_rate": 0.0002, "epoch": 4.759556103575832, "step": 3860}, {"loss": 0.3831, "grad_norm": 1.06382417678833, "learning_rate": 0.0002, "epoch": 4.771886559802713, "step": 3870}, {"loss": 0.3934, "grad_norm": 0.9851241111755371, "learning_rate": 0.0002, "epoch": 4.784217016029594, "step": 3880}, {"loss": 0.5172, "grad_norm": 0.8215277791023254, "learning_rate": 0.0002, "epoch": 4.796547472256473, "step": 3890}, {"loss": 0.4437, "grad_norm": 0.9901723861694336, "learning_rate": 0.0002, "epoch": 4.808877928483354, "step": 3900}, {"loss": 0.4673, "grad_norm": 0.9149112701416016, "learning_rate": 0.0002, "epoch": 4.821208384710234, "step": 3910}, {"loss": 0.4295, "grad_norm": 0.9772973656654358, "learning_rate": 0.0002, "epoch": 4.8335388409371145, "step": 3920}, {"loss": 0.4346, "grad_norm": 0.8889636397361755, "learning_rate": 0.0002, "epoch": 4.845869297163995, "step": 3930}, {"loss": 0.421, "grad_norm": 1.3032807111740112, "learning_rate": 0.0002, "epoch": 4.858199753390876, "step": 3940}, {"loss": 0.434, "grad_norm": 0.8575899600982666, "learning_rate": 0.0002, "epoch": 4.870530209617756, "step": 3950}, {"loss": 0.4295, "grad_norm": 1.04326331615448, "learning_rate": 0.0002, "epoch": 4.882860665844636, "step": 3960}, {"loss": 0.3633, "grad_norm": 1.041210651397705, "learning_rate": 0.0002, "epoch": 4.895191122071517, "step": 3970}, {"loss": 0.4104, "grad_norm": 0.9113056063652039, "learning_rate": 0.0002, "epoch": 4.907521578298397, "step": 3980}, {"loss": 0.4496, "grad_norm": 1.019347906112671, "learning_rate": 0.0002, "epoch": 4.919852034525277, "step": 3990}, {"loss": 0.457, "grad_norm": 0.7709218859672546, "learning_rate": 0.0002, "epoch": 4.932182490752158, "step": 4000}, {"loss": 0.4697, "grad_norm": 0.8891775608062744, "learning_rate": 0.0002, "epoch": 4.944512946979038, "step": 4010}, {"loss": 0.4436, "grad_norm": 1.0396920442581177, "learning_rate": 0.0002, "epoch": 4.9568434032059185, "step": 4020}, {"loss": 0.4251, "grad_norm": 0.9239833354949951, "learning_rate": 0.0002, "epoch": 4.969173859432799, "step": 4030}, {"loss": 0.5049, "grad_norm": 1.801400065422058, "learning_rate": 0.0002, "epoch": 4.981504315659679, "step": 4040}, {"loss": 0.4481, "grad_norm": 0.6194164752960205, "learning_rate": 0.0002, "epoch": 4.99383477188656, "step": 4050}, {"eval_loss": 1.544758915901184, "eval_runtime": 96.2573, "eval_samples_per_second": 4.53, "eval_steps_per_second": 0.571, "epoch": 5.0, "step": 4055}, {"loss": 0.3774, "grad_norm": 0.9918256998062134, "learning_rate": 0.0002, "epoch": 5.00616522811344, "step": 4060}, {"loss": 0.2887, "grad_norm": 1.4851351976394653, "learning_rate": 0.0002, "epoch": 5.018495684340321, "step": 4070}, {"loss": 0.2454, "grad_norm": 0.9237686395645142, "learning_rate": 0.0002, "epoch": 5.030826140567201, "step": 4080}, {"loss": 0.3072, "grad_norm": 1.2180852890014648, "learning_rate": 0.0002, "epoch": 5.0431565967940815, "step": 4090}, {"loss": 0.282, "grad_norm": 1.1247979402542114, "learning_rate": 0.0002, "epoch": 5.055487053020962, "step": 4100}, {"loss": 0.3108, "grad_norm": 1.2969884872436523, "learning_rate": 0.0002, "epoch": 5.067817509247842, "step": 4110}, {"loss": 0.2858, "grad_norm": 1.0183063745498657, "learning_rate": 0.0002, "epoch": 5.080147965474723, "step": 4120}, {"loss": 0.295, "grad_norm": 1.121330738067627, "learning_rate": 0.0002, "epoch": 5.092478421701603, "step": 4130}, {"loss": 0.2697, "grad_norm": 1.0748186111450195, "learning_rate": 0.0002, "epoch": 5.104808877928483, "step": 4140}, {"loss": 0.3414, "grad_norm": 1.103474736213684, "learning_rate": 0.0002, "epoch": 5.117139334155364, "step": 4150}, {"loss": 0.305, "grad_norm": 1.2251166105270386, "learning_rate": 0.0002, "epoch": 5.129469790382244, "step": 4160}, {"loss": 0.3131, "grad_norm": 0.920898973941803, "learning_rate": 0.0002, "epoch": 5.141800246609124, "step": 4170}, {"loss": 0.281, "grad_norm": 1.327542781829834, "learning_rate": 0.0002, "epoch": 5.154130702836005, "step": 4180}, {"loss": 0.3214, "grad_norm": 1.0677192211151123, "learning_rate": 0.0002, "epoch": 5.1664611590628855, "step": 4190}, {"loss": 0.2863, "grad_norm": 0.897241473197937, "learning_rate": 0.0002, "epoch": 5.178791615289766, "step": 4200}, {"loss": 0.2967, "grad_norm": 0.977457582950592, "learning_rate": 0.0002, "epoch": 5.191122071516646, "step": 4210}, {"loss": 0.3032, "grad_norm": 1.4115267992019653, "learning_rate": 0.0002, "epoch": 5.203452527743527, "step": 4220}, {"loss": 0.3279, "grad_norm": 1.097743034362793, "learning_rate": 0.0002, "epoch": 5.215782983970407, "step": 4230}, {"loss": 0.293, "grad_norm": 1.1095269918441772, "learning_rate": 0.0002, "epoch": 5.228113440197287, "step": 4240}, {"loss": 0.3544, "grad_norm": 1.3785479068756104, "learning_rate": 0.0002, "epoch": 5.240443896424168, "step": 4250}, {"loss": 0.3118, "grad_norm": 1.0298776626586914, "learning_rate": 0.0002, "epoch": 5.252774352651048, "step": 4260}, {"loss": 0.296, "grad_norm": 1.1592111587524414, "learning_rate": 0.0002, "epoch": 5.265104808877928, "step": 4270}, {"loss": 0.2878, "grad_norm": 1.2355743646621704, "learning_rate": 0.0002, "epoch": 5.277435265104809, "step": 4280}, {"loss": 0.3085, "grad_norm": 0.8543112874031067, "learning_rate": 0.0002, "epoch": 5.2897657213316895, "step": 4290}, {"loss": 0.3108, "grad_norm": 1.2953215837478638, "learning_rate": 0.0002, "epoch": 5.302096177558569, "step": 4300}, {"loss": 0.2912, "grad_norm": 1.1001787185668945, "learning_rate": 0.0002, "epoch": 5.31442663378545, "step": 4310}, {"loss": 0.3003, "grad_norm": 0.7476816773414612, "learning_rate": 0.0002, "epoch": 5.326757090012331, "step": 4320}, {"loss": 0.3247, "grad_norm": 0.8195574283599854, "learning_rate": 0.0002, "epoch": 5.3390875462392104, "step": 4330}, {"loss": 0.3035, "grad_norm": 0.9490262866020203, "learning_rate": 0.0002, "epoch": 5.351418002466091, "step": 4340}, {"loss": 0.2846, "grad_norm": 1.2201412916183472, "learning_rate": 0.0002, "epoch": 5.363748458692972, "step": 4350}, {"loss": 0.2644, "grad_norm": 1.0311479568481445, "learning_rate": 0.0002, "epoch": 5.376078914919852, "step": 4360}, {"loss": 0.3104, "grad_norm": 1.2097488641738892, "learning_rate": 0.0002, "epoch": 5.388409371146732, "step": 4370}, {"loss": 0.2977, "grad_norm": 1.140942096710205, "learning_rate": 0.0002, "epoch": 5.400739827373613, "step": 4380}, {"loss": 0.2975, "grad_norm": 0.8091890811920166, "learning_rate": 0.0002, "epoch": 5.413070283600494, "step": 4390}, {"loss": 0.3727, "grad_norm": 1.4467964172363281, "learning_rate": 0.0002, "epoch": 5.425400739827373, "step": 4400}, {"loss": 0.2979, "grad_norm": 1.0836058855056763, "learning_rate": 0.0002, "epoch": 5.437731196054254, "step": 4410}, {"loss": 0.2601, "grad_norm": 1.0515433549880981, "learning_rate": 0.0002, "epoch": 5.450061652281135, "step": 4420}, {"loss": 0.315, "grad_norm": 0.9603073000907898, "learning_rate": 0.0002, "epoch": 5.4623921085080145, "step": 4430}, {"loss": 0.3166, "grad_norm": 1.234609842300415, "learning_rate": 0.0002, "epoch": 5.474722564734895, "step": 4440}, {"loss": 0.3142, "grad_norm": 0.8881428837776184, "learning_rate": 0.0002, "epoch": 5.487053020961776, "step": 4450}, {"loss": 0.3725, "grad_norm": 1.1817275285720825, "learning_rate": 0.0002, "epoch": 5.499383477188656, "step": 4460}, {"loss": 0.2944, "grad_norm": 1.213993787765503, "learning_rate": 0.0002, "epoch": 5.511713933415536, "step": 4470}, {"loss": 0.3136, "grad_norm": 1.0501725673675537, "learning_rate": 0.0002, "epoch": 5.524044389642417, "step": 4480}, {"loss": 0.306, "grad_norm": 1.5061579942703247, "learning_rate": 0.0002, "epoch": 5.536374845869297, "step": 4490}, {"loss": 0.3226, "grad_norm": 1.1171475648880005, "learning_rate": 0.0002, "epoch": 5.548705302096177, "step": 4500}, {"loss": 0.3624, "grad_norm": 1.1147594451904297, "learning_rate": 0.0002, "epoch": 5.561035758323058, "step": 4510}, {"loss": 0.3435, "grad_norm": 1.0600544214248657, "learning_rate": 0.0002, "epoch": 5.573366214549939, "step": 4520}, {"loss": 0.3268, "grad_norm": 1.247870922088623, "learning_rate": 0.0002, "epoch": 5.5856966707768185, "step": 4530}, {"loss": 0.3168, "grad_norm": 0.9425561428070068, "learning_rate": 0.0002, "epoch": 5.598027127003699, "step": 4540}, {"loss": 0.3119, "grad_norm": 1.1111550331115723, "learning_rate": 0.0002, "epoch": 5.61035758323058, "step": 4550}, {"loss": 0.3389, "grad_norm": 1.743268609046936, "learning_rate": 0.0002, "epoch": 5.62268803945746, "step": 4560}, {"loss": 0.31, "grad_norm": 1.3522645235061646, "learning_rate": 0.0002, "epoch": 5.63501849568434, "step": 4570}, {"loss": 0.3121, "grad_norm": 0.7354221343994141, "learning_rate": 0.0002, "epoch": 5.647348951911221, "step": 4580}, {"loss": 0.3693, "grad_norm": 1.050743818283081, "learning_rate": 0.0002, "epoch": 5.659679408138101, "step": 4590}, {"loss": 0.3449, "grad_norm": 1.1302396059036255, "learning_rate": 0.0002, "epoch": 5.6720098643649814, "step": 4600}, {"loss": 0.3211, "grad_norm": 0.8774183392524719, "learning_rate": 0.0002, "epoch": 5.684340320591862, "step": 4610}, {"loss": 0.3501, "grad_norm": 1.090781569480896, "learning_rate": 0.0002, "epoch": 5.696670776818742, "step": 4620}, {"loss": 0.3211, "grad_norm": 0.9177733063697815, "learning_rate": 0.0002, "epoch": 5.709001233045623, "step": 4630}, {"loss": 0.3439, "grad_norm": 0.9985341429710388, "learning_rate": 0.0002, "epoch": 5.721331689272503, "step": 4640}, {"loss": 0.3323, "grad_norm": 1.0230613946914673, "learning_rate": 0.0002, "epoch": 5.733662145499384, "step": 4650}, {"loss": 0.3525, "grad_norm": 0.944656252861023, "learning_rate": 0.0002, "epoch": 5.745992601726264, "step": 4660}, {"loss": 0.3191, "grad_norm": 0.8162471652030945, "learning_rate": 0.0002, "epoch": 5.758323057953144, "step": 4670}, {"loss": 0.4011, "grad_norm": 1.0500398874282837, "learning_rate": 0.0002, "epoch": 5.770653514180025, "step": 4680}, {"loss": 0.3452, "grad_norm": 0.9487981796264648, "learning_rate": 0.0002, "epoch": 5.782983970406905, "step": 4690}, {"loss": 0.2942, "grad_norm": 1.1856540441513062, "learning_rate": 0.0002, "epoch": 5.7953144266337855, "step": 4700}, {"loss": 0.3107, "grad_norm": 1.2583396434783936, "learning_rate": 0.0002, "epoch": 5.807644882860666, "step": 4710}, {"loss": 0.3223, "grad_norm": 1.2532602548599243, "learning_rate": 0.0002, "epoch": 5.819975339087546, "step": 4720}, {"loss": 0.3253, "grad_norm": 1.115236520767212, "learning_rate": 0.0002, "epoch": 5.832305795314427, "step": 4730}, {"loss": 0.3539, "grad_norm": 1.2245537042617798, "learning_rate": 0.0002, "epoch": 5.844636251541307, "step": 4740}, {"loss": 0.3171, "grad_norm": 1.1964094638824463, "learning_rate": 0.0002, "epoch": 5.856966707768187, "step": 4750}, {"loss": 0.3623, "grad_norm": 1.0833805799484253, "learning_rate": 0.0002, "epoch": 5.869297163995068, "step": 4760}, {"loss": 0.3511, "grad_norm": 1.0694046020507812, "learning_rate": 0.0002, "epoch": 5.881627620221948, "step": 4770}, {"loss": 0.3266, "grad_norm": 0.9947936534881592, "learning_rate": 0.0002, "epoch": 5.893958076448829, "step": 4780}, {"loss": 0.316, "grad_norm": 1.175716519355774, "learning_rate": 0.0002, "epoch": 5.906288532675709, "step": 4790}, {"loss": 0.3609, "grad_norm": 0.7717352509498596, "learning_rate": 0.0002, "epoch": 5.9186189889025895, "step": 4800}, {"loss": 0.3058, "grad_norm": 1.2906442880630493, "learning_rate": 0.0002, "epoch": 5.930949445129469, "step": 4810}, {"loss": 0.3187, "grad_norm": 1.2416284084320068, "learning_rate": 0.0002, "epoch": 5.94327990135635, "step": 4820}, {"loss": 0.337, "grad_norm": 1.3066956996917725, "learning_rate": 0.0002, "epoch": 5.955610357583231, "step": 4830}, {"loss": 0.3167, "grad_norm": 1.0872026681900024, "learning_rate": 0.0002, "epoch": 5.967940813810111, "step": 4840}, {"loss": 0.3262, "grad_norm": 1.1941101551055908, "learning_rate": 0.0002, "epoch": 5.980271270036991, "step": 4850}, {"loss": 0.3234, "grad_norm": 1.1126095056533813, "learning_rate": 0.0002, "epoch": 5.992601726263872, "step": 4860}]}
+{"epoch": 7.0, "step": 5677, "epoch_duration": 2505.4287343025208, "total_accumulated_duration": 17099.209432840347, "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": 28774.0}, "peak_memory_reserved": {"GPU_0": 28774.0}, "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-0.6-num-5885-sd-10000/checkpoint-1622", "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": 2.3601, "grad_norm": 0.8258164525032043, "learning_rate": 0.0002, "epoch": 0.012330456226880395, "step": 10}, {"loss": 1.7317, "grad_norm": 0.4577729105949402, "learning_rate": 0.0002, "epoch": 0.02466091245376079, "step": 20}, {"loss": 1.4729, "grad_norm": 0.639807939529419, "learning_rate": 0.0002, "epoch": 0.036991368680641186, "step": 30}, {"loss": 1.2088, "grad_norm": 0.5311757922172546, "learning_rate": 0.0002, "epoch": 0.04932182490752158, "step": 40}, {"loss": 1.3149, "grad_norm": 0.386595219373703, "learning_rate": 0.0002, "epoch": 0.06165228113440197, "step": 50}, {"loss": 1.1657, "grad_norm": 0.4401357173919678, "learning_rate": 0.0002, "epoch": 0.07398273736128237, "step": 60}, {"loss": 1.1022, "grad_norm": 0.3234352171421051, "learning_rate": 0.0002, "epoch": 0.08631319358816276, "step": 70}, {"loss": 1.3738, "grad_norm": 0.29643672704696655, "learning_rate": 0.0002, "epoch": 0.09864364981504316, "step": 80}, {"loss": 1.1929, "grad_norm": 0.2941012382507324, "learning_rate": 0.0002, "epoch": 0.11097410604192355, "step": 90}, {"loss": 1.2067, "grad_norm": 0.5498173832893372, "learning_rate": 0.0002, "epoch": 0.12330456226880394, "step": 100}, {"loss": 1.142, "grad_norm": 0.2545783519744873, "learning_rate": 0.0002, "epoch": 0.13563501849568435, "step": 110}, {"loss": 1.0297, "grad_norm": 0.2984241247177124, "learning_rate": 0.0002, "epoch": 0.14796547472256474, "step": 120}, {"loss": 1.1591, "grad_norm": 0.2710968852043152, "learning_rate": 0.0002, "epoch": 0.16029593094944514, "step": 130}, {"loss": 1.0427, "grad_norm": 0.2817152142524719, "learning_rate": 0.0002, "epoch": 0.17262638717632553, "step": 140}, {"loss": 1.0638, "grad_norm": 0.41083765029907227, "learning_rate": 0.0002, "epoch": 0.18495684340320592, "step": 150}, {"loss": 1.3537, "grad_norm": 0.36536213755607605, "learning_rate": 0.0002, "epoch": 0.19728729963008632, "step": 160}, {"loss": 1.0132, "grad_norm": 0.2738671600818634, "learning_rate": 0.0002, "epoch": 0.2096177558569667, "step": 170}, {"loss": 0.9555, "grad_norm": 0.27403146028518677, "learning_rate": 0.0002, "epoch": 0.2219482120838471, "step": 180}, {"loss": 1.0769, "grad_norm": 0.4446810483932495, "learning_rate": 0.0002, "epoch": 0.2342786683107275, "step": 190}, {"loss": 1.0588, "grad_norm": 0.5295385718345642, "learning_rate": 0.0002, "epoch": 0.2466091245376079, "step": 200}, {"loss": 1.0827, "grad_norm": 0.311404824256897, "learning_rate": 0.0002, "epoch": 0.2589395807644883, "step": 210}, {"loss": 1.1455, "grad_norm": 0.2448509782552719, "learning_rate": 0.0002, "epoch": 0.2712700369913687, "step": 220}, {"loss": 1.0929, "grad_norm": 0.6507014036178589, "learning_rate": 0.0002, "epoch": 0.2836004932182491, "step": 230}, {"loss": 0.9875, "grad_norm": 0.2339320331811905, "learning_rate": 0.0002, "epoch": 0.2959309494451295, "step": 240}, {"loss": 0.9211, "grad_norm": 0.8210226893424988, "learning_rate": 0.0002, "epoch": 0.3082614056720099, "step": 250}, {"loss": 1.161, "grad_norm": 0.27473965287208557, "learning_rate": 0.0002, "epoch": 0.3205918618988903, "step": 260}, {"loss": 1.0218, "grad_norm": 0.3051395118236542, "learning_rate": 0.0002, "epoch": 0.33292231812577067, "step": 270}, {"loss": 1.0286, "grad_norm": 0.3037777245044708, "learning_rate": 0.0002, "epoch": 0.34525277435265106, "step": 280}, {"loss": 1.144, "grad_norm": 0.2748974859714508, "learning_rate": 0.0002, "epoch": 0.35758323057953145, "step": 290}, {"loss": 1.0858, "grad_norm": 0.23656068742275238, "learning_rate": 0.0002, "epoch": 0.36991368680641185, "step": 300}, {"loss": 1.0564, "grad_norm": 0.2523384094238281, "learning_rate": 0.0002, "epoch": 0.38224414303329224, "step": 310}, {"loss": 1.3091, "grad_norm": 0.27848055958747864, "learning_rate": 0.0002, "epoch": 0.39457459926017263, "step": 320}, {"loss": 1.0252, "grad_norm": 0.3204525411128998, "learning_rate": 0.0002, "epoch": 0.406905055487053, "step": 330}, {"loss": 0.9855, "grad_norm": 0.3459707498550415, "learning_rate": 0.0002, "epoch": 0.4192355117139334, "step": 340}, {"loss": 1.1111, "grad_norm": 0.2458430379629135, "learning_rate": 0.0002, "epoch": 0.4315659679408138, "step": 350}, {"loss": 1.1493, "grad_norm": 0.5022910237312317, "learning_rate": 0.0002, "epoch": 0.4438964241676942, "step": 360}, {"loss": 1.1272, "grad_norm": 0.27076372504234314, "learning_rate": 0.0002, "epoch": 0.4562268803945746, "step": 370}, {"loss": 1.1927, "grad_norm": 0.6489047408103943, "learning_rate": 0.0002, "epoch": 0.468557336621455, "step": 380}, {"loss": 0.9501, "grad_norm": 0.3324144184589386, "learning_rate": 0.0002, "epoch": 0.4808877928483354, "step": 390}, {"loss": 1.2012, "grad_norm": 0.32813116908073425, "learning_rate": 0.0002, "epoch": 0.4932182490752158, "step": 400}, {"loss": 1.1135, "grad_norm": 0.25295355916023254, "learning_rate": 0.0002, "epoch": 0.5055487053020962, "step": 410}, {"loss": 0.9477, "grad_norm": 0.2912578880786896, "learning_rate": 0.0002, "epoch": 0.5178791615289766, "step": 420}, {"loss": 1.0121, "grad_norm": 0.34780189394950867, "learning_rate": 0.0002, "epoch": 0.530209617755857, "step": 430}, {"loss": 0.9296, "grad_norm": 0.24604526162147522, "learning_rate": 0.0002, "epoch": 0.5425400739827374, "step": 440}, {"loss": 1.253, "grad_norm": 0.32759982347488403, "learning_rate": 0.0002, "epoch": 0.5548705302096177, "step": 450}, {"loss": 1.1925, "grad_norm": 0.40810221433639526, "learning_rate": 0.0002, "epoch": 0.5672009864364982, "step": 460}, {"loss": 1.174, "grad_norm": 0.3590679466724396, "learning_rate": 0.0002, "epoch": 0.5795314426633785, "step": 470}, {"loss": 1.2223, "grad_norm": 0.5656213760375977, "learning_rate": 0.0002, "epoch": 0.591861898890259, "step": 480}, {"loss": 1.1936, "grad_norm": 0.30830657482147217, "learning_rate": 0.0002, "epoch": 0.6041923551171393, "step": 490}, {"loss": 1.1873, "grad_norm": 0.317905455827713, "learning_rate": 0.0002, "epoch": 0.6165228113440198, "step": 500}, {"loss": 0.9805, "grad_norm": 0.3254566490650177, "learning_rate": 0.0002, "epoch": 0.6288532675709001, "step": 510}, {"loss": 1.0384, "grad_norm": 0.29187721014022827, "learning_rate": 0.0002, "epoch": 0.6411837237977805, "step": 520}, {"loss": 1.2526, "grad_norm": 0.3439238965511322, "learning_rate": 0.0002, "epoch": 0.6535141800246609, "step": 530}, {"loss": 1.0698, "grad_norm": 0.20970556139945984, "learning_rate": 0.0002, "epoch": 0.6658446362515413, "step": 540}, {"loss": 1.1047, "grad_norm": 0.4022853374481201, "learning_rate": 0.0002, "epoch": 0.6781750924784217, "step": 550}, {"loss": 1.0684, "grad_norm": 0.2235759049654007, "learning_rate": 0.0002, "epoch": 0.6905055487053021, "step": 560}, {"loss": 1.2339, "grad_norm": 0.33849895000457764, "learning_rate": 0.0002, "epoch": 0.7028360049321825, "step": 570}, {"loss": 1.1929, "grad_norm": 0.34745967388153076, "learning_rate": 0.0002, "epoch": 0.7151664611590629, "step": 580}, {"loss": 1.1158, "grad_norm": 0.26041269302368164, "learning_rate": 0.0002, "epoch": 0.7274969173859432, "step": 590}, {"loss": 1.2134, "grad_norm": 0.3804777264595032, "learning_rate": 0.0002, "epoch": 0.7398273736128237, "step": 600}, {"loss": 1.0606, "grad_norm": 0.2456253319978714, "learning_rate": 0.0002, "epoch": 0.752157829839704, "step": 610}, {"loss": 1.0638, "grad_norm": 0.37838423252105713, "learning_rate": 0.0002, "epoch": 0.7644882860665845, "step": 620}, {"loss": 1.0556, "grad_norm": 0.28105494379997253, "learning_rate": 0.0002, "epoch": 0.7768187422934648, "step": 630}, {"loss": 1.0672, "grad_norm": 0.2774018943309784, "learning_rate": 0.0002, "epoch": 0.7891491985203453, "step": 640}, {"loss": 0.9978, "grad_norm": 1.8184229135513306, "learning_rate": 0.0002, "epoch": 0.8014796547472256, "step": 650}, {"loss": 1.1038, "grad_norm": 0.3325096070766449, "learning_rate": 0.0002, "epoch": 0.813810110974106, "step": 660}, {"loss": 1.083, "grad_norm": 0.2686693072319031, "learning_rate": 0.0002, "epoch": 0.8261405672009864, "step": 670}, {"loss": 1.1308, "grad_norm": 0.3271431624889374, "learning_rate": 0.0002, "epoch": 0.8384710234278668, "step": 680}, {"loss": 1.1116, "grad_norm": 2.359999656677246, "learning_rate": 0.0002, "epoch": 0.8508014796547472, "step": 690}, {"loss": 1.0782, "grad_norm": 0.46242964267730713, "learning_rate": 0.0002, "epoch": 0.8631319358816276, "step": 700}, {"loss": 0.95, "grad_norm": 0.34731170535087585, "learning_rate": 0.0002, "epoch": 0.8754623921085081, "step": 710}, {"loss": 1.2236, "grad_norm": 0.39381715655326843, "learning_rate": 0.0002, "epoch": 0.8877928483353884, "step": 720}, {"loss": 1.1319, "grad_norm": 0.43496373295783997, "learning_rate": 0.0002, "epoch": 0.9001233045622689, "step": 730}, {"loss": 1.0979, "grad_norm": 0.32243210077285767, "learning_rate": 0.0002, "epoch": 0.9124537607891492, "step": 740}, {"loss": 0.9913, "grad_norm": 0.30396756529808044, "learning_rate": 0.0002, "epoch": 0.9247842170160296, "step": 750}, {"loss": 1.1141, "grad_norm": 0.4461122751235962, "learning_rate": 0.0002, "epoch": 0.93711467324291, "step": 760}, {"loss": 1.0049, "grad_norm": 0.24081681668758392, "learning_rate": 0.0002, "epoch": 0.9494451294697904, "step": 770}, {"loss": 1.0966, "grad_norm": 0.27461910247802734, "learning_rate": 0.0002, "epoch": 0.9617755856966708, "step": 780}, {"loss": 0.9942, "grad_norm": 0.3325668275356293, "learning_rate": 0.0002, "epoch": 0.9741060419235512, "step": 790}, {"loss": 1.0506, "grad_norm": 0.24046339094638824, "learning_rate": 0.0002, "epoch": 0.9864364981504316, "step": 800}, {"loss": 0.9989, "grad_norm": 0.42950066924095154, "learning_rate": 0.0002, "epoch": 0.998766954377312, "step": 810}, {"eval_loss": 1.246457576751709, "eval_runtime": 98.7974, "eval_samples_per_second": 4.413, "eval_steps_per_second": 0.557, "epoch": 1.0, "step": 811}, {"loss": 1.0536, "grad_norm": 0.26760655641555786, "learning_rate": 0.0002, "epoch": 1.0110974106041923, "step": 820}, {"loss": 0.9722, "grad_norm": 0.4640820026397705, "learning_rate": 0.0002, "epoch": 1.0234278668310728, "step": 830}, {"loss": 0.9392, "grad_norm": 0.2699166238307953, "learning_rate": 0.0002, "epoch": 1.0357583230579532, "step": 840}, {"loss": 0.9335, "grad_norm": 0.3441709578037262, "learning_rate": 0.0002, "epoch": 1.0480887792848335, "step": 850}, {"loss": 0.9083, "grad_norm": 0.299934983253479, "learning_rate": 0.0002, "epoch": 1.060419235511714, "step": 860}, {"loss": 0.9416, "grad_norm": 0.2980666160583496, "learning_rate": 0.0002, "epoch": 1.0727496917385944, "step": 870}, {"loss": 0.94, "grad_norm": 0.3131714463233948, "learning_rate": 0.0002, "epoch": 1.0850801479654748, "step": 880}, {"loss": 0.9288, "grad_norm": 0.29881617426872253, "learning_rate": 0.0002, "epoch": 1.097410604192355, "step": 890}, {"loss": 0.998, "grad_norm": 0.29870888590812683, "learning_rate": 0.0002, "epoch": 1.1097410604192355, "step": 900}, {"loss": 0.9924, "grad_norm": 0.5735140442848206, "learning_rate": 0.0002, "epoch": 1.122071516646116, "step": 910}, {"loss": 1.0694, "grad_norm": 0.33159002661705017, "learning_rate": 0.0002, "epoch": 1.1344019728729964, "step": 920}, {"loss": 1.0069, "grad_norm": 1.235399842262268, "learning_rate": 0.0002, "epoch": 1.1467324290998766, "step": 930}, {"loss": 1.0315, "grad_norm": 0.27469736337661743, "learning_rate": 0.0002, "epoch": 1.159062885326757, "step": 940}, {"loss": 0.9386, "grad_norm": 0.29130664467811584, "learning_rate": 0.0002, "epoch": 1.1713933415536375, "step": 950}, {"loss": 0.8919, "grad_norm": 0.3730354607105255, "learning_rate": 0.0002, "epoch": 1.183723797780518, "step": 960}, {"loss": 0.9988, "grad_norm": 0.5973590612411499, "learning_rate": 0.0002, "epoch": 1.1960542540073984, "step": 970}, {"loss": 0.9525, "grad_norm": 0.39631304144859314, "learning_rate": 0.0002, "epoch": 1.2083847102342786, "step": 980}, {"loss": 0.9217, "grad_norm": 0.849051296710968, "learning_rate": 0.0002, "epoch": 1.220715166461159, "step": 990}, {"loss": 1.0903, "grad_norm": 0.4390525817871094, "learning_rate": 0.0002, "epoch": 1.2330456226880395, "step": 1000}, {"loss": 0.9018, "grad_norm": 0.30423852801322937, "learning_rate": 0.0002, "epoch": 1.2453760789149197, "step": 1010}, {"loss": 1.0128, "grad_norm": 0.34736061096191406, "learning_rate": 0.0002, "epoch": 1.2577065351418002, "step": 1020}, {"loss": 0.9026, "grad_norm": 0.3421604037284851, "learning_rate": 0.0002, "epoch": 1.2700369913686806, "step": 1030}, {"loss": 0.8485, "grad_norm": 0.544170081615448, "learning_rate": 0.0002, "epoch": 1.282367447595561, "step": 1040}, {"loss": 0.9591, "grad_norm": 0.5128790736198425, "learning_rate": 0.0002, "epoch": 1.2946979038224415, "step": 1050}, {"loss": 0.9214, "grad_norm": 0.443344384431839, "learning_rate": 0.0002, "epoch": 1.3070283600493218, "step": 1060}, {"loss": 0.9367, "grad_norm": 0.6380868554115295, "learning_rate": 0.0002, "epoch": 1.3193588162762022, "step": 1070}, {"loss": 0.9849, "grad_norm": 0.4638073146343231, "learning_rate": 0.0002, "epoch": 1.3316892725030827, "step": 1080}, {"loss": 0.8645, "grad_norm": 0.32406893372535706, "learning_rate": 0.0002, "epoch": 1.344019728729963, "step": 1090}, {"loss": 0.8278, "grad_norm": 0.3955065608024597, "learning_rate": 0.0002, "epoch": 1.3563501849568433, "step": 1100}, {"loss": 0.9306, "grad_norm": 0.3489246666431427, "learning_rate": 0.0002, "epoch": 1.3686806411837238, "step": 1110}, {"loss": 1.0138, "grad_norm": 0.48451653122901917, "learning_rate": 0.0002, "epoch": 1.3810110974106042, "step": 1120}, {"loss": 0.9165, "grad_norm": 0.3652360439300537, "learning_rate": 0.0002, "epoch": 1.3933415536374847, "step": 1130}, {"loss": 0.9576, "grad_norm": 1.3097436428070068, "learning_rate": 0.0002, "epoch": 1.405672009864365, "step": 1140}, {"loss": 0.8115, "grad_norm": 0.3647715449333191, "learning_rate": 0.0002, "epoch": 1.4180024660912454, "step": 1150}, {"loss": 0.8573, "grad_norm": 0.37248560786247253, "learning_rate": 0.0002, "epoch": 1.4303329223181258, "step": 1160}, {"loss": 0.936, "grad_norm": 0.4639643430709839, "learning_rate": 0.0002, "epoch": 1.442663378545006, "step": 1170}, {"loss": 0.9511, "grad_norm": 0.5455219745635986, "learning_rate": 0.0002, "epoch": 1.4549938347718865, "step": 1180}, {"loss": 0.8611, "grad_norm": 0.38862571120262146, "learning_rate": 0.0002, "epoch": 1.467324290998767, "step": 1190}, {"loss": 0.8681, "grad_norm": 0.37586215138435364, "learning_rate": 0.0002, "epoch": 1.4796547472256474, "step": 1200}, {"loss": 0.8673, "grad_norm": 0.46244436502456665, "learning_rate": 0.0002, "epoch": 1.4919852034525278, "step": 1210}, {"loss": 0.9388, "grad_norm": 0.3570359945297241, "learning_rate": 0.0002, "epoch": 1.504315659679408, "step": 1220}, {"loss": 0.971, "grad_norm": 0.28393083810806274, "learning_rate": 0.0002, "epoch": 1.5166461159062885, "step": 1230}, {"loss": 0.9296, "grad_norm": 0.5672869682312012, "learning_rate": 0.0002, "epoch": 1.528976572133169, "step": 1240}, {"loss": 0.8787, "grad_norm": 0.41605108976364136, "learning_rate": 0.0002, "epoch": 1.5413070283600492, "step": 1250}, {"loss": 0.8744, "grad_norm": 0.40657493472099304, "learning_rate": 0.0002, "epoch": 1.5536374845869299, "step": 1260}, {"loss": 0.9046, "grad_norm": 0.43672341108322144, "learning_rate": 0.0002, "epoch": 1.56596794081381, "step": 1270}, {"loss": 0.8586, "grad_norm": 0.3065410554409027, "learning_rate": 0.0002, "epoch": 1.5782983970406905, "step": 1280}, {"loss": 0.9499, "grad_norm": 0.37826645374298096, "learning_rate": 0.0002, "epoch": 1.590628853267571, "step": 1290}, {"loss": 0.901, "grad_norm": 0.42307335138320923, "learning_rate": 0.0002, "epoch": 1.6029593094944512, "step": 1300}, {"loss": 0.8673, "grad_norm": 0.3648843467235565, "learning_rate": 0.0002, "epoch": 1.6152897657213316, "step": 1310}, {"loss": 0.9302, "grad_norm": 0.8921076059341431, "learning_rate": 0.0002, "epoch": 1.627620221948212, "step": 1320}, {"loss": 0.9378, "grad_norm": 0.37522226572036743, "learning_rate": 0.0002, "epoch": 1.6399506781750923, "step": 1330}, {"loss": 0.8921, "grad_norm": 0.7489957809448242, "learning_rate": 0.0002, "epoch": 1.652281134401973, "step": 1340}, {"loss": 0.9297, "grad_norm": 0.31733131408691406, "learning_rate": 0.0002, "epoch": 1.6646115906288532, "step": 1350}, {"loss": 0.907, "grad_norm": 0.3249478340148926, "learning_rate": 0.0002, "epoch": 1.6769420468557337, "step": 1360}, {"loss": 1.0197, "grad_norm": 0.3178001344203949, "learning_rate": 0.0002, "epoch": 1.6892725030826141, "step": 1370}, {"loss": 1.0781, "grad_norm": 0.5674093961715698, "learning_rate": 0.0002, "epoch": 1.7016029593094943, "step": 1380}, {"loss": 0.8972, "grad_norm": 0.35272449254989624, "learning_rate": 0.0002, "epoch": 1.7139334155363748, "step": 1390}, {"loss": 0.9346, "grad_norm": 0.5778217911720276, "learning_rate": 0.0002, "epoch": 1.7262638717632552, "step": 1400}, {"loss": 0.9099, "grad_norm": 0.33561450242996216, "learning_rate": 0.0002, "epoch": 1.7385943279901355, "step": 1410}, {"loss": 0.8636, "grad_norm": 0.31735464930534363, "learning_rate": 0.0002, "epoch": 1.7509247842170161, "step": 1420}, {"loss": 0.982, "grad_norm": 1.0612670183181763, "learning_rate": 0.0002, "epoch": 1.7632552404438964, "step": 1430}, {"loss": 0.8224, "grad_norm": 0.5442509651184082, "learning_rate": 0.0002, "epoch": 1.7755856966707768, "step": 1440}, {"loss": 0.9275, "grad_norm": 0.7471332550048828, "learning_rate": 0.0002, "epoch": 1.7879161528976573, "step": 1450}, {"loss": 0.9389, "grad_norm": 0.4323609173297882, "learning_rate": 0.0002, "epoch": 1.8002466091245375, "step": 1460}, {"loss": 0.8247, "grad_norm": 0.47796759009361267, "learning_rate": 0.0002, "epoch": 1.8125770653514182, "step": 1470}, {"loss": 0.9395, "grad_norm": 0.3348400592803955, "learning_rate": 0.0002, "epoch": 1.8249075215782984, "step": 1480}, {"loss": 0.9793, "grad_norm": 0.3354550898075104, "learning_rate": 0.0002, "epoch": 1.8372379778051788, "step": 1490}, {"loss": 0.8581, "grad_norm": 0.5988477468490601, "learning_rate": 0.0002, "epoch": 1.8495684340320593, "step": 1500}, {"loss": 0.9268, "grad_norm": 0.5222318172454834, "learning_rate": 0.0002, "epoch": 1.8618988902589395, "step": 1510}, {"loss": 0.8846, "grad_norm": 0.5246642827987671, "learning_rate": 0.0002, "epoch": 1.87422934648582, "step": 1520}, {"loss": 0.9317, "grad_norm": 0.3164594769477844, "learning_rate": 0.0002, "epoch": 1.8865598027127004, "step": 1530}, {"loss": 0.9961, "grad_norm": 0.3496174216270447, "learning_rate": 0.0002, "epoch": 1.8988902589395806, "step": 1540}, {"loss": 0.9057, "grad_norm": 0.8863359689712524, "learning_rate": 0.0002, "epoch": 1.9112207151664613, "step": 1550}, {"loss": 0.9405, "grad_norm": 0.3587026298046112, "learning_rate": 0.0002, "epoch": 1.9235511713933415, "step": 1560}, {"loss": 0.8335, "grad_norm": 0.6052881479263306, "learning_rate": 0.0002, "epoch": 1.935881627620222, "step": 1570}, {"loss": 0.8805, "grad_norm": 0.567269504070282, "learning_rate": 0.0002, "epoch": 1.9482120838471024, "step": 1580}, {"loss": 0.9581, "grad_norm": 0.45184487104415894, "learning_rate": 0.0002, "epoch": 1.9605425400739827, "step": 1590}, {"loss": 0.9147, "grad_norm": 0.5028569102287292, "learning_rate": 0.0002, "epoch": 1.972872996300863, "step": 1600}, {"loss": 0.75, "grad_norm": 0.4677547216415405, "learning_rate": 0.0002, "epoch": 1.9852034525277436, "step": 1610}, {"loss": 0.8469, "grad_norm": 0.35106056928634644, "learning_rate": 0.0002, "epoch": 1.9975339087546238, "step": 1620}, {"eval_loss": 1.238026738166809, "eval_runtime": 95.4287, "eval_samples_per_second": 4.569, "eval_steps_per_second": 0.576, "epoch": 2.0, "step": 1622}, {"loss": 0.7629, "grad_norm": 0.444060355424881, "learning_rate": 0.0002, "epoch": 2.0098643649815044, "step": 1630}, {"loss": 0.772, "grad_norm": 0.627570390701294, "learning_rate": 0.0002, "epoch": 2.0221948212083847, "step": 1640}, {"loss": 0.6186, "grad_norm": 0.38737839460372925, "learning_rate": 0.0002, "epoch": 2.034525277435265, "step": 1650}, {"loss": 0.7734, "grad_norm": 0.4300459623336792, "learning_rate": 0.0002, "epoch": 2.0468557336621456, "step": 1660}, {"loss": 0.6943, "grad_norm": 0.43037715554237366, "learning_rate": 0.0002, "epoch": 2.059186189889026, "step": 1670}, {"loss": 0.6588, "grad_norm": 0.40772515535354614, "learning_rate": 0.0002, "epoch": 2.0715166461159065, "step": 1680}, {"loss": 0.8105, "grad_norm": 0.5295451879501343, "learning_rate": 0.0002, "epoch": 2.0838471023427867, "step": 1690}, {"loss": 0.7717, "grad_norm": 0.7452750205993652, "learning_rate": 0.0002, "epoch": 2.096177558569667, "step": 1700}, {"loss": 0.7458, "grad_norm": 0.809183657169342, "learning_rate": 0.0002, "epoch": 2.1085080147965476, "step": 1710}, {"loss": 0.7398, "grad_norm": 0.4597688913345337, "learning_rate": 0.0002, "epoch": 2.120838471023428, "step": 1720}, {"loss": 0.6856, "grad_norm": 0.806919276714325, "learning_rate": 0.0002, "epoch": 2.133168927250308, "step": 1730}, {"loss": 0.679, "grad_norm": 0.3755643665790558, "learning_rate": 0.0002, "epoch": 2.1454993834771887, "step": 1740}, {"loss": 0.7938, "grad_norm": 0.5882734060287476, "learning_rate": 0.0002, "epoch": 2.157829839704069, "step": 1750}, {"loss": 0.6782, "grad_norm": 0.692960798740387, "learning_rate": 0.0002, "epoch": 2.1701602959309496, "step": 1760}, {"loss": 0.7195, "grad_norm": 0.4737096428871155, "learning_rate": 0.0002, "epoch": 2.18249075215783, "step": 1770}, {"loss": 0.758, "grad_norm": 0.6637021899223328, "learning_rate": 0.0002, "epoch": 2.19482120838471, "step": 1780}, {"loss": 0.7139, "grad_norm": 0.9109764099121094, "learning_rate": 0.0002, "epoch": 2.2071516646115907, "step": 1790}, {"loss": 0.7373, "grad_norm": 0.4137539267539978, "learning_rate": 0.0002, "epoch": 2.219482120838471, "step": 1800}, {"loss": 0.7266, "grad_norm": 0.44995415210723877, "learning_rate": 0.0002, "epoch": 2.2318125770653516, "step": 1810}, {"loss": 0.7663, "grad_norm": 0.5985036492347717, "learning_rate": 0.0002, "epoch": 2.244143033292232, "step": 1820}, {"loss": 0.7502, "grad_norm": 0.7549490332603455, "learning_rate": 0.0002, "epoch": 2.256473489519112, "step": 1830}, {"loss": 0.7452, "grad_norm": 0.4490937888622284, "learning_rate": 0.0002, "epoch": 2.2688039457459928, "step": 1840}, {"loss": 0.7531, "grad_norm": 0.38859808444976807, "learning_rate": 0.0002, "epoch": 2.281134401972873, "step": 1850}, {"loss": 0.7278, "grad_norm": 1.0704916715621948, "learning_rate": 0.0002, "epoch": 2.293464858199753, "step": 1860}, {"loss": 0.7143, "grad_norm": 0.4647100865840912, "learning_rate": 0.0002, "epoch": 2.305795314426634, "step": 1870}, {"loss": 0.7146, "grad_norm": 0.6181163787841797, "learning_rate": 0.0002, "epoch": 2.318125770653514, "step": 1880}, {"loss": 0.7689, "grad_norm": 0.9241904020309448, "learning_rate": 0.0002, "epoch": 2.3304562268803943, "step": 1890}, {"loss": 0.7294, "grad_norm": 0.39101317524909973, "learning_rate": 0.0002, "epoch": 2.342786683107275, "step": 1900}, {"loss": 0.7079, "grad_norm": 0.49442458152770996, "learning_rate": 0.0002, "epoch": 2.3551171393341552, "step": 1910}, {"loss": 0.7586, "grad_norm": 0.4864824414253235, "learning_rate": 0.0002, "epoch": 2.367447595561036, "step": 1920}, {"loss": 0.7434, "grad_norm": 0.5427613854408264, "learning_rate": 0.0002, "epoch": 2.379778051787916, "step": 1930}, {"loss": 0.8423, "grad_norm": 0.7164974808692932, "learning_rate": 0.0002, "epoch": 2.392108508014797, "step": 1940}, {"loss": 0.6888, "grad_norm": 0.562979519367218, "learning_rate": 0.0002, "epoch": 2.404438964241677, "step": 1950}, {"loss": 0.7692, "grad_norm": 0.5631861090660095, "learning_rate": 0.0002, "epoch": 2.4167694204685573, "step": 1960}, {"loss": 0.67, "grad_norm": 0.4895121157169342, "learning_rate": 0.0002, "epoch": 2.429099876695438, "step": 1970}, {"loss": 0.7735, "grad_norm": 0.45674824714660645, "learning_rate": 0.0002, "epoch": 2.441430332922318, "step": 1980}, {"loss": 0.685, "grad_norm": 1.1424206495285034, "learning_rate": 0.0002, "epoch": 2.4537607891491984, "step": 1990}, {"loss": 0.7627, "grad_norm": 0.6314579844474792, "learning_rate": 0.0002, "epoch": 2.466091245376079, "step": 2000}, {"loss": 0.7118, "grad_norm": 0.5481605529785156, "learning_rate": 0.0002, "epoch": 2.4784217016029593, "step": 2010}, {"loss": 0.6947, "grad_norm": 0.4671579599380493, "learning_rate": 0.0002, "epoch": 2.4907521578298395, "step": 2020}, {"loss": 0.7377, "grad_norm": 0.7621194124221802, "learning_rate": 0.0002, "epoch": 2.50308261405672, "step": 2030}, {"loss": 0.69, "grad_norm": 0.38983288407325745, "learning_rate": 0.0002, "epoch": 2.5154130702836004, "step": 2040}, {"loss": 0.8381, "grad_norm": 0.6341150999069214, "learning_rate": 0.0002, "epoch": 2.5277435265104806, "step": 2050}, {"loss": 0.773, "grad_norm": 0.7151971459388733, "learning_rate": 0.0002, "epoch": 2.5400739827373613, "step": 2060}, {"loss": 0.6733, "grad_norm": 0.9665895104408264, "learning_rate": 0.0002, "epoch": 2.5524044389642415, "step": 2070}, {"loss": 0.7791, "grad_norm": 0.9572727680206299, "learning_rate": 0.0002, "epoch": 2.564734895191122, "step": 2080}, {"loss": 0.7205, "grad_norm": 1.1970765590667725, "learning_rate": 0.0002, "epoch": 2.5770653514180024, "step": 2090}, {"loss": 0.6736, "grad_norm": 0.5505942702293396, "learning_rate": 0.0002, "epoch": 2.589395807644883, "step": 2100}, {"loss": 0.673, "grad_norm": 0.5903949737548828, "learning_rate": 0.0002, "epoch": 2.6017262638717633, "step": 2110}, {"loss": 0.678, "grad_norm": 0.45640307664871216, "learning_rate": 0.0002, "epoch": 2.6140567200986435, "step": 2120}, {"loss": 0.6562, "grad_norm": 0.8763944506645203, "learning_rate": 0.0002, "epoch": 2.626387176325524, "step": 2130}, {"loss": 0.6484, "grad_norm": 0.4472963213920593, "learning_rate": 0.0002, "epoch": 2.6387176325524044, "step": 2140}, {"loss": 0.7702, "grad_norm": 0.5335086584091187, "learning_rate": 0.0002, "epoch": 2.6510480887792847, "step": 2150}, {"loss": 0.6851, "grad_norm": 0.805263340473175, "learning_rate": 0.0002, "epoch": 2.6633785450061653, "step": 2160}, {"loss": 0.7026, "grad_norm": 0.6332727670669556, "learning_rate": 0.0002, "epoch": 2.6757090012330456, "step": 2170}, {"loss": 0.7925, "grad_norm": 0.8667435646057129, "learning_rate": 0.0002, "epoch": 2.688039457459926, "step": 2180}, {"loss": 0.8044, "grad_norm": 0.5638955235481262, "learning_rate": 0.0002, "epoch": 2.7003699136868065, "step": 2190}, {"loss": 0.7117, "grad_norm": 0.4176250696182251, "learning_rate": 0.0002, "epoch": 2.7127003699136867, "step": 2200}, {"loss": 0.6932, "grad_norm": 0.6013461351394653, "learning_rate": 0.0002, "epoch": 2.7250308261405674, "step": 2210}, {"loss": 0.7843, "grad_norm": 0.553961992263794, "learning_rate": 0.0002, "epoch": 2.7373612823674476, "step": 2220}, {"loss": 0.8633, "grad_norm": 0.4710180461406708, "learning_rate": 0.0002, "epoch": 2.7496917385943282, "step": 2230}, {"loss": 0.7469, "grad_norm": 0.8141706585884094, "learning_rate": 0.0002, "epoch": 2.7620221948212085, "step": 2240}, {"loss": 0.7086, "grad_norm": 0.7449556589126587, "learning_rate": 0.0002, "epoch": 2.7743526510480887, "step": 2250}, {"loss": 0.6933, "grad_norm": 0.5366780757904053, "learning_rate": 0.0002, "epoch": 2.7866831072749694, "step": 2260}, {"loss": 0.7192, "grad_norm": 0.5316720604896545, "learning_rate": 0.0002, "epoch": 2.7990135635018496, "step": 2270}, {"loss": 0.6212, "grad_norm": 0.4598459005355835, "learning_rate": 0.0002, "epoch": 2.81134401972873, "step": 2280}, {"loss": 0.7024, "grad_norm": 0.6852091550827026, "learning_rate": 0.0002, "epoch": 2.8236744759556105, "step": 2290}, {"loss": 0.7357, "grad_norm": 0.8040902018547058, "learning_rate": 0.0002, "epoch": 2.8360049321824907, "step": 2300}, {"loss": 0.7563, "grad_norm": 0.46976321935653687, "learning_rate": 0.0002, "epoch": 2.848335388409371, "step": 2310}, {"loss": 0.731, "grad_norm": 0.5214090347290039, "learning_rate": 0.0002, "epoch": 2.8606658446362516, "step": 2320}, {"loss": 0.6687, "grad_norm": 0.5323054790496826, "learning_rate": 0.0002, "epoch": 2.872996300863132, "step": 2330}, {"loss": 0.7895, "grad_norm": 0.6842264533042908, "learning_rate": 0.0002, "epoch": 2.885326757090012, "step": 2340}, {"loss": 0.7737, "grad_norm": 0.9157055616378784, "learning_rate": 0.0002, "epoch": 2.8976572133168927, "step": 2350}, {"loss": 0.7217, "grad_norm": 0.5253258347511292, "learning_rate": 0.0002, "epoch": 2.909987669543773, "step": 2360}, {"loss": 0.7162, "grad_norm": 0.4937705099582672, "learning_rate": 0.0002, "epoch": 2.9223181257706536, "step": 2370}, {"loss": 0.7008, "grad_norm": 0.48762989044189453, "learning_rate": 0.0002, "epoch": 2.934648581997534, "step": 2380}, {"loss": 0.8086, "grad_norm": 0.544335126876831, "learning_rate": 0.0002, "epoch": 2.9469790382244145, "step": 2390}, {"loss": 0.643, "grad_norm": 0.4847845435142517, "learning_rate": 0.0002, "epoch": 2.9593094944512948, "step": 2400}, {"loss": 0.7757, "grad_norm": 0.4787445366382599, "learning_rate": 0.0002, "epoch": 2.971639950678175, "step": 2410}, {"loss": 0.7678, "grad_norm": 1.022318959236145, "learning_rate": 0.0002, "epoch": 2.9839704069050557, "step": 2420}, {"loss": 0.6548, "grad_norm": 0.4987848103046417, "learning_rate": 0.0002, "epoch": 2.996300863131936, "step": 2430}, {"eval_loss": 1.2936296463012695, "eval_runtime": 94.7897, "eval_samples_per_second": 4.6, "eval_steps_per_second": 0.58, "epoch": 3.0, "step": 2433}, {"loss": 0.6073, "grad_norm": 0.5562372803688049, "learning_rate": 0.0002, "epoch": 3.008631319358816, "step": 2440}, {"loss": 0.5181, "grad_norm": 1.133402705192566, "learning_rate": 0.0002, "epoch": 3.020961775585697, "step": 2450}, {"loss": 0.5333, "grad_norm": 0.6480470299720764, "learning_rate": 0.0002, "epoch": 3.033292231812577, "step": 2460}, {"loss": 0.4828, "grad_norm": 0.8989138007164001, "learning_rate": 0.0002, "epoch": 3.0456226880394572, "step": 2470}, {"loss": 0.5097, "grad_norm": 0.8257461786270142, "learning_rate": 0.0002, "epoch": 3.057953144266338, "step": 2480}, {"loss": 0.6229, "grad_norm": 0.6813381910324097, "learning_rate": 0.0002, "epoch": 3.070283600493218, "step": 2490}, {"loss": 0.531, "grad_norm": 0.6989586353302002, "learning_rate": 0.0002, "epoch": 3.082614056720099, "step": 2500}, {"loss": 0.54, "grad_norm": 0.7992092967033386, "learning_rate": 0.0002, "epoch": 3.094944512946979, "step": 2510}, {"loss": 0.5054, "grad_norm": 0.698077917098999, "learning_rate": 0.0002, "epoch": 3.1072749691738593, "step": 2520}, {"loss": 0.5064, "grad_norm": 0.5699033141136169, "learning_rate": 0.0002, "epoch": 3.11960542540074, "step": 2530}, {"loss": 0.6088, "grad_norm": 0.6142355799674988, "learning_rate": 0.0002, "epoch": 3.13193588162762, "step": 2540}, {"loss": 0.585, "grad_norm": 0.7089933753013611, "learning_rate": 0.0002, "epoch": 3.144266337854501, "step": 2550}, {"loss": 0.5373, "grad_norm": 1.0107015371322632, "learning_rate": 0.0002, "epoch": 3.156596794081381, "step": 2560}, {"loss": 0.5429, "grad_norm": 0.568138837814331, "learning_rate": 0.0002, "epoch": 3.1689272503082613, "step": 2570}, {"loss": 0.5897, "grad_norm": 0.9960416555404663, "learning_rate": 0.0002, "epoch": 3.181257706535142, "step": 2580}, {"loss": 0.5211, "grad_norm": 0.6277595162391663, "learning_rate": 0.0002, "epoch": 3.193588162762022, "step": 2590}, {"loss": 0.5787, "grad_norm": 0.681083619594574, "learning_rate": 0.0002, "epoch": 3.2059186189889024, "step": 2600}, {"loss": 0.5166, "grad_norm": 0.5816057324409485, "learning_rate": 0.0002, "epoch": 3.218249075215783, "step": 2610}, {"loss": 0.545, "grad_norm": 0.7197734117507935, "learning_rate": 0.0002, "epoch": 3.2305795314426633, "step": 2620}, {"loss": 0.614, "grad_norm": 0.6524068117141724, "learning_rate": 0.0002, "epoch": 3.242909987669544, "step": 2630}, {"loss": 0.5456, "grad_norm": 1.273668646812439, "learning_rate": 0.0002, "epoch": 3.255240443896424, "step": 2640}, {"loss": 0.5266, "grad_norm": 0.6950451731681824, "learning_rate": 0.0002, "epoch": 3.2675709001233044, "step": 2650}, {"loss": 0.5194, "grad_norm": 0.8029071688652039, "learning_rate": 0.0002, "epoch": 3.279901356350185, "step": 2660}, {"loss": 0.5729, "grad_norm": 0.7464073896408081, "learning_rate": 0.0002, "epoch": 3.2922318125770653, "step": 2670}, {"loss": 0.5366, "grad_norm": 0.8342001438140869, "learning_rate": 0.0002, "epoch": 3.304562268803946, "step": 2680}, {"loss": 0.5413, "grad_norm": 0.5629868507385254, "learning_rate": 0.0002, "epoch": 3.316892725030826, "step": 2690}, {"loss": 0.633, "grad_norm": 0.753999650478363, "learning_rate": 0.0002, "epoch": 3.3292231812577064, "step": 2700}, {"loss": 0.5048, "grad_norm": 1.0271371603012085, "learning_rate": 0.0002, "epoch": 3.341553637484587, "step": 2710}, {"loss": 0.5233, "grad_norm": 0.9608535170555115, "learning_rate": 0.0002, "epoch": 3.3538840937114673, "step": 2720}, {"loss": 0.5102, "grad_norm": 0.7796488404273987, "learning_rate": 0.0002, "epoch": 3.3662145499383476, "step": 2730}, {"loss": 0.5172, "grad_norm": 0.5666437149047852, "learning_rate": 0.0002, "epoch": 3.3785450061652282, "step": 2740}, {"loss": 0.491, "grad_norm": 0.5462956428527832, "learning_rate": 0.0002, "epoch": 3.3908754623921085, "step": 2750}, {"loss": 0.5855, "grad_norm": 1.289099097251892, "learning_rate": 0.0002, "epoch": 3.4032059186189887, "step": 2760}, {"loss": 0.635, "grad_norm": 0.825566828250885, "learning_rate": 0.0002, "epoch": 3.4155363748458694, "step": 2770}, {"loss": 0.4998, "grad_norm": 0.8366670608520508, "learning_rate": 0.0002, "epoch": 3.4278668310727496, "step": 2780}, {"loss": 0.5732, "grad_norm": 1.0931549072265625, "learning_rate": 0.0002, "epoch": 3.4401972872996303, "step": 2790}, {"loss": 0.6093, "grad_norm": 0.9228858351707458, "learning_rate": 0.0002, "epoch": 3.4525277435265105, "step": 2800}, {"loss": 0.6089, "grad_norm": 1.3182806968688965, "learning_rate": 0.0002, "epoch": 3.4648581997533907, "step": 2810}, {"loss": 0.5665, "grad_norm": 0.8366976380348206, "learning_rate": 0.0002, "epoch": 3.4771886559802714, "step": 2820}, {"loss": 0.5666, "grad_norm": 0.8067695498466492, "learning_rate": 0.0002, "epoch": 3.4895191122071516, "step": 2830}, {"loss": 0.579, "grad_norm": 1.1163437366485596, "learning_rate": 0.0002, "epoch": 3.5018495684340323, "step": 2840}, {"loss": 0.5785, "grad_norm": 1.7196556329727173, "learning_rate": 0.0002, "epoch": 3.5141800246609125, "step": 2850}, {"loss": 0.5346, "grad_norm": 1.1267012357711792, "learning_rate": 0.0002, "epoch": 3.5265104808877927, "step": 2860}, {"loss": 0.447, "grad_norm": 0.7220137119293213, "learning_rate": 0.0002, "epoch": 3.5388409371146734, "step": 2870}, {"loss": 0.6099, "grad_norm": 0.914114773273468, "learning_rate": 0.0002, "epoch": 3.5511713933415536, "step": 2880}, {"loss": 0.6143, "grad_norm": 0.6193503141403198, "learning_rate": 0.0002, "epoch": 3.563501849568434, "step": 2890}, {"loss": 0.5171, "grad_norm": 0.6060135960578918, "learning_rate": 0.0002, "epoch": 3.5758323057953145, "step": 2900}, {"loss": 0.5659, "grad_norm": 1.0177327394485474, "learning_rate": 0.0002, "epoch": 3.5881627620221948, "step": 2910}, {"loss": 0.5711, "grad_norm": 0.5994468331336975, "learning_rate": 0.0002, "epoch": 3.600493218249075, "step": 2920}, {"loss": 0.6373, "grad_norm": 0.7450457215309143, "learning_rate": 0.0002, "epoch": 3.6128236744759556, "step": 2930}, {"loss": 0.4933, "grad_norm": 0.5825870037078857, "learning_rate": 0.0002, "epoch": 3.625154130702836, "step": 2940}, {"loss": 0.6016, "grad_norm": 0.6289743781089783, "learning_rate": 0.0002, "epoch": 3.6374845869297165, "step": 2950}, {"loss": 0.5507, "grad_norm": 0.7801929116249084, "learning_rate": 0.0002, "epoch": 3.6498150431565968, "step": 2960}, {"loss": 0.5695, "grad_norm": 1.1206634044647217, "learning_rate": 0.0002, "epoch": 3.6621454993834774, "step": 2970}, {"loss": 0.4985, "grad_norm": 0.6738817691802979, "learning_rate": 0.0002, "epoch": 3.6744759556103577, "step": 2980}, {"loss": 0.6209, "grad_norm": 1.1917344331741333, "learning_rate": 0.0002, "epoch": 3.686806411837238, "step": 2990}, {"loss": 0.5373, "grad_norm": 1.3738657236099243, "learning_rate": 0.0002, "epoch": 3.6991368680641186, "step": 3000}, {"loss": 0.5467, "grad_norm": 0.6642793416976929, "learning_rate": 0.0002, "epoch": 3.711467324290999, "step": 3010}, {"loss": 0.6243, "grad_norm": 0.9030995965003967, "learning_rate": 0.0002, "epoch": 3.723797780517879, "step": 3020}, {"loss": 0.592, "grad_norm": 1.0203914642333984, "learning_rate": 0.0002, "epoch": 3.7361282367447597, "step": 3030}, {"loss": 0.5453, "grad_norm": 0.648394763469696, "learning_rate": 0.0002, "epoch": 3.74845869297164, "step": 3040}, {"loss": 0.498, "grad_norm": 0.6304570436477661, "learning_rate": 0.0002, "epoch": 3.76078914919852, "step": 3050}, {"loss": 0.683, "grad_norm": 0.8286601901054382, "learning_rate": 0.0002, "epoch": 3.773119605425401, "step": 3060}, {"loss": 0.5302, "grad_norm": 0.906444251537323, "learning_rate": 0.0002, "epoch": 3.785450061652281, "step": 3070}, {"loss": 0.5345, "grad_norm": 1.4212149381637573, "learning_rate": 0.0002, "epoch": 3.7977805178791613, "step": 3080}, {"loss": 0.6403, "grad_norm": 0.7574319839477539, "learning_rate": 0.0002, "epoch": 3.810110974106042, "step": 3090}, {"loss": 0.5756, "grad_norm": 0.6534451246261597, "learning_rate": 0.0002, "epoch": 3.822441430332922, "step": 3100}, {"loss": 0.5306, "grad_norm": 0.7525447010993958, "learning_rate": 0.0002, "epoch": 3.834771886559803, "step": 3110}, {"loss": 0.5368, "grad_norm": 0.6513990759849548, "learning_rate": 0.0002, "epoch": 3.847102342786683, "step": 3120}, {"loss": 0.5492, "grad_norm": 0.7782694697380066, "learning_rate": 0.0002, "epoch": 3.8594327990135637, "step": 3130}, {"loss": 0.5727, "grad_norm": 0.7998530268669128, "learning_rate": 0.0002, "epoch": 3.871763255240444, "step": 3140}, {"loss": 0.5156, "grad_norm": 0.8045353293418884, "learning_rate": 0.0002, "epoch": 3.884093711467324, "step": 3150}, {"loss": 0.5341, "grad_norm": 0.8242645263671875, "learning_rate": 0.0002, "epoch": 3.896424167694205, "step": 3160}, {"loss": 0.5563, "grad_norm": 0.8302360773086548, "learning_rate": 0.0002, "epoch": 3.908754623921085, "step": 3170}, {"loss": 0.5793, "grad_norm": 0.8653109073638916, "learning_rate": 0.0002, "epoch": 3.9210850801479653, "step": 3180}, {"loss": 0.5219, "grad_norm": 0.6461338996887207, "learning_rate": 0.0002, "epoch": 3.933415536374846, "step": 3190}, {"loss": 0.6009, "grad_norm": 0.8267415165901184, "learning_rate": 0.0002, "epoch": 3.945745992601726, "step": 3200}, {"loss": 0.5956, "grad_norm": 1.1963194608688354, "learning_rate": 0.0002, "epoch": 3.9580764488286064, "step": 3210}, {"loss": 0.5692, "grad_norm": 0.7101966142654419, "learning_rate": 0.0002, "epoch": 3.970406905055487, "step": 3220}, {"loss": 0.5471, "grad_norm": 0.5931660532951355, "learning_rate": 0.0002, "epoch": 3.9827373612823673, "step": 3230}, {"loss": 0.5619, "grad_norm": 0.7465988993644714, "learning_rate": 0.0002, "epoch": 3.995067817509248, "step": 3240}, {"eval_loss": 1.4066498279571533, "eval_runtime": 95.7145, "eval_samples_per_second": 4.555, "eval_steps_per_second": 0.575, "epoch": 4.0, "step": 3244}, {"loss": 0.4948, "grad_norm": 0.9478800296783447, "learning_rate": 0.0002, "epoch": 4.007398273736128, "step": 3250}, {"loss": 0.4129, "grad_norm": 1.207059621810913, "learning_rate": 0.0002, "epoch": 4.019728729963009, "step": 3260}, {"loss": 0.3577, "grad_norm": 0.8984074592590332, "learning_rate": 0.0002, "epoch": 4.032059186189889, "step": 3270}, {"loss": 0.3798, "grad_norm": 0.8104140758514404, "learning_rate": 0.0002, "epoch": 4.044389642416769, "step": 3280}, {"loss": 0.3657, "grad_norm": 1.0875468254089355, "learning_rate": 0.0002, "epoch": 4.05672009864365, "step": 3290}, {"loss": 0.3703, "grad_norm": 0.8520309329032898, "learning_rate": 0.0002, "epoch": 4.06905055487053, "step": 3300}, {"loss": 0.3933, "grad_norm": 1.076735496520996, "learning_rate": 0.0002, "epoch": 4.0813810110974105, "step": 3310}, {"loss": 0.4422, "grad_norm": 0.7789369821548462, "learning_rate": 0.0002, "epoch": 4.093711467324291, "step": 3320}, {"loss": 0.4009, "grad_norm": 0.916862964630127, "learning_rate": 0.0002, "epoch": 4.106041923551172, "step": 3330}, {"loss": 0.3934, "grad_norm": 1.1251654624938965, "learning_rate": 0.0002, "epoch": 4.118372379778052, "step": 3340}, {"loss": 0.3651, "grad_norm": 0.9373420476913452, "learning_rate": 0.0002, "epoch": 4.130702836004932, "step": 3350}, {"loss": 0.384, "grad_norm": 1.03253972530365, "learning_rate": 0.0002, "epoch": 4.143033292231813, "step": 3360}, {"loss": 0.372, "grad_norm": 0.947023332118988, "learning_rate": 0.0002, "epoch": 4.155363748458693, "step": 3370}, {"loss": 0.4018, "grad_norm": 0.8709157109260559, "learning_rate": 0.0002, "epoch": 4.167694204685573, "step": 3380}, {"loss": 0.3754, "grad_norm": 0.930983304977417, "learning_rate": 0.0002, "epoch": 4.180024660912454, "step": 3390}, {"loss": 0.4248, "grad_norm": 1.092809796333313, "learning_rate": 0.0002, "epoch": 4.192355117139334, "step": 3400}, {"loss": 0.4453, "grad_norm": 0.8454303741455078, "learning_rate": 0.0002, "epoch": 4.2046855733662145, "step": 3410}, {"loss": 0.4198, "grad_norm": 0.957210123538971, "learning_rate": 0.0002, "epoch": 4.217016029593095, "step": 3420}, {"loss": 0.3743, "grad_norm": 0.854333758354187, "learning_rate": 0.0002, "epoch": 4.229346485819975, "step": 3430}, {"loss": 0.4041, "grad_norm": 1.0457639694213867, "learning_rate": 0.0002, "epoch": 4.241676942046856, "step": 3440}, {"loss": 0.3817, "grad_norm": 0.8972977995872498, "learning_rate": 0.0002, "epoch": 4.254007398273736, "step": 3450}, {"loss": 0.4445, "grad_norm": 1.0438238382339478, "learning_rate": 0.0002, "epoch": 4.266337854500616, "step": 3460}, {"loss": 0.4078, "grad_norm": 0.7000405192375183, "learning_rate": 0.0002, "epoch": 4.278668310727497, "step": 3470}, {"loss": 0.3718, "grad_norm": 1.0451240539550781, "learning_rate": 0.0002, "epoch": 4.290998766954377, "step": 3480}, {"loss": 0.4506, "grad_norm": 1.3339767456054688, "learning_rate": 0.0002, "epoch": 4.303329223181258, "step": 3490}, {"loss": 0.3999, "grad_norm": 0.7503946423530579, "learning_rate": 0.0002, "epoch": 4.315659679408138, "step": 3500}, {"loss": 0.4503, "grad_norm": 0.8443584442138672, "learning_rate": 0.0002, "epoch": 4.3279901356350186, "step": 3510}, {"loss": 0.3793, "grad_norm": 1.1681201457977295, "learning_rate": 0.0002, "epoch": 4.340320591861899, "step": 3520}, {"loss": 0.4462, "grad_norm": 1.078883171081543, "learning_rate": 0.0002, "epoch": 4.352651048088779, "step": 3530}, {"loss": 0.4216, "grad_norm": 0.6894834041595459, "learning_rate": 0.0002, "epoch": 4.36498150431566, "step": 3540}, {"loss": 0.4315, "grad_norm": 0.7059480547904968, "learning_rate": 0.0002, "epoch": 4.37731196054254, "step": 3550}, {"loss": 0.3821, "grad_norm": 1.1807256937026978, "learning_rate": 0.0002, "epoch": 4.38964241676942, "step": 3560}, {"loss": 0.4192, "grad_norm": 0.8341359496116638, "learning_rate": 0.0002, "epoch": 4.401972872996301, "step": 3570}, {"loss": 0.4123, "grad_norm": 1.0273033380508423, "learning_rate": 0.0002, "epoch": 4.4143033292231815, "step": 3580}, {"loss": 0.5018, "grad_norm": 0.6916454434394836, "learning_rate": 0.0002, "epoch": 4.426633785450061, "step": 3590}, {"loss": 0.3909, "grad_norm": 0.8210113644599915, "learning_rate": 0.0002, "epoch": 4.438964241676942, "step": 3600}, {"loss": 0.3893, "grad_norm": 1.0309500694274902, "learning_rate": 0.0002, "epoch": 4.451294697903823, "step": 3610}, {"loss": 0.3902, "grad_norm": 0.8847399353981018, "learning_rate": 0.0002, "epoch": 4.463625154130703, "step": 3620}, {"loss": 0.4198, "grad_norm": 1.668636679649353, "learning_rate": 0.0002, "epoch": 4.475955610357583, "step": 3630}, {"loss": 0.4075, "grad_norm": 1.3087958097457886, "learning_rate": 0.0002, "epoch": 4.488286066584464, "step": 3640}, {"loss": 0.4294, "grad_norm": 0.837852418422699, "learning_rate": 0.0002, "epoch": 4.500616522811344, "step": 3650}, {"loss": 0.4053, "grad_norm": 9.7662353515625, "learning_rate": 0.0002, "epoch": 4.512946979038224, "step": 3660}, {"loss": 0.4033, "grad_norm": 1.125719428062439, "learning_rate": 0.0002, "epoch": 4.525277435265105, "step": 3670}, {"loss": 0.4566, "grad_norm": 0.7755377292633057, "learning_rate": 0.0002, "epoch": 4.5376078914919855, "step": 3680}, {"loss": 0.4415, "grad_norm": 0.7185089588165283, "learning_rate": 0.0002, "epoch": 4.549938347718865, "step": 3690}, {"loss": 0.4616, "grad_norm": 1.182063102722168, "learning_rate": 0.0002, "epoch": 4.562268803945746, "step": 3700}, {"loss": 0.4572, "grad_norm": 1.001197338104248, "learning_rate": 0.0002, "epoch": 4.574599260172627, "step": 3710}, {"loss": 0.4493, "grad_norm": 0.9705429077148438, "learning_rate": 0.0002, "epoch": 4.586929716399506, "step": 3720}, {"loss": 0.42, "grad_norm": 0.7136746048927307, "learning_rate": 0.0002, "epoch": 4.599260172626387, "step": 3730}, {"loss": 0.3757, "grad_norm": 1.0004864931106567, "learning_rate": 0.0002, "epoch": 4.611590628853268, "step": 3740}, {"loss": 0.4418, "grad_norm": 1.3193715810775757, "learning_rate": 0.0002, "epoch": 4.623921085080148, "step": 3750}, {"loss": 0.4572, "grad_norm": 0.6945042014122009, "learning_rate": 0.0002, "epoch": 4.636251541307028, "step": 3760}, {"loss": 0.4255, "grad_norm": 0.8903936743736267, "learning_rate": 0.0002, "epoch": 4.648581997533909, "step": 3770}, {"loss": 0.3582, "grad_norm": 0.7960889339447021, "learning_rate": 0.0002, "epoch": 4.660912453760789, "step": 3780}, {"loss": 0.3864, "grad_norm": 1.0439172983169556, "learning_rate": 0.0002, "epoch": 4.673242909987669, "step": 3790}, {"loss": 0.4378, "grad_norm": 1.4546219110488892, "learning_rate": 0.0002, "epoch": 4.68557336621455, "step": 3800}, {"loss": 0.4191, "grad_norm": 0.8194343447685242, "learning_rate": 0.0002, "epoch": 4.697903822441431, "step": 3810}, {"loss": 0.4473, "grad_norm": 1.0727602243423462, "learning_rate": 0.0002, "epoch": 4.7102342786683105, "step": 3820}, {"loss": 0.4021, "grad_norm": 0.7785195708274841, "learning_rate": 0.0002, "epoch": 4.722564734895191, "step": 3830}, {"loss": 0.4252, "grad_norm": 0.846783459186554, "learning_rate": 0.0002, "epoch": 4.734895191122072, "step": 3840}, {"loss": 0.4647, "grad_norm": 1.0481648445129395, "learning_rate": 0.0002, "epoch": 4.747225647348952, "step": 3850}, {"loss": 0.4944, "grad_norm": 0.7324008941650391, "learning_rate": 0.0002, "epoch": 4.759556103575832, "step": 3860}, {"loss": 0.3831, "grad_norm": 1.06382417678833, "learning_rate": 0.0002, "epoch": 4.771886559802713, "step": 3870}, {"loss": 0.3934, "grad_norm": 0.9851241111755371, "learning_rate": 0.0002, "epoch": 4.784217016029594, "step": 3880}, {"loss": 0.5172, "grad_norm": 0.8215277791023254, "learning_rate": 0.0002, "epoch": 4.796547472256473, "step": 3890}, {"loss": 0.4437, "grad_norm": 0.9901723861694336, "learning_rate": 0.0002, "epoch": 4.808877928483354, "step": 3900}, {"loss": 0.4673, "grad_norm": 0.9149112701416016, "learning_rate": 0.0002, "epoch": 4.821208384710234, "step": 3910}, {"loss": 0.4295, "grad_norm": 0.9772973656654358, "learning_rate": 0.0002, "epoch": 4.8335388409371145, "step": 3920}, {"loss": 0.4346, "grad_norm": 0.8889636397361755, "learning_rate": 0.0002, "epoch": 4.845869297163995, "step": 3930}, {"loss": 0.421, "grad_norm": 1.3032807111740112, "learning_rate": 0.0002, "epoch": 4.858199753390876, "step": 3940}, {"loss": 0.434, "grad_norm": 0.8575899600982666, "learning_rate": 0.0002, "epoch": 4.870530209617756, "step": 3950}, {"loss": 0.4295, "grad_norm": 1.04326331615448, "learning_rate": 0.0002, "epoch": 4.882860665844636, "step": 3960}, {"loss": 0.3633, "grad_norm": 1.041210651397705, "learning_rate": 0.0002, "epoch": 4.895191122071517, "step": 3970}, {"loss": 0.4104, "grad_norm": 0.9113056063652039, "learning_rate": 0.0002, "epoch": 4.907521578298397, "step": 3980}, {"loss": 0.4496, "grad_norm": 1.019347906112671, "learning_rate": 0.0002, "epoch": 4.919852034525277, "step": 3990}, {"loss": 0.457, "grad_norm": 0.7709218859672546, "learning_rate": 0.0002, "epoch": 4.932182490752158, "step": 4000}, {"loss": 0.4697, "grad_norm": 0.8891775608062744, "learning_rate": 0.0002, "epoch": 4.944512946979038, "step": 4010}, {"loss": 0.4436, "grad_norm": 1.0396920442581177, "learning_rate": 0.0002, "epoch": 4.9568434032059185, "step": 4020}, {"loss": 0.4251, "grad_norm": 0.9239833354949951, "learning_rate": 0.0002, "epoch": 4.969173859432799, "step": 4030}, {"loss": 0.5049, "grad_norm": 1.801400065422058, "learning_rate": 0.0002, "epoch": 4.981504315659679, "step": 4040}, {"loss": 0.4481, "grad_norm": 0.6194164752960205, "learning_rate": 0.0002, "epoch": 4.99383477188656, "step": 4050}, {"eval_loss": 1.544758915901184, "eval_runtime": 96.2573, "eval_samples_per_second": 4.53, "eval_steps_per_second": 0.571, "epoch": 5.0, "step": 4055}, {"loss": 0.3774, "grad_norm": 0.9918256998062134, "learning_rate": 0.0002, "epoch": 5.00616522811344, "step": 4060}, {"loss": 0.2887, "grad_norm": 1.4851351976394653, "learning_rate": 0.0002, "epoch": 5.018495684340321, "step": 4070}, {"loss": 0.2454, "grad_norm": 0.9237686395645142, "learning_rate": 0.0002, "epoch": 5.030826140567201, "step": 4080}, {"loss": 0.3072, "grad_norm": 1.2180852890014648, "learning_rate": 0.0002, "epoch": 5.0431565967940815, "step": 4090}, {"loss": 0.282, "grad_norm": 1.1247979402542114, "learning_rate": 0.0002, "epoch": 5.055487053020962, "step": 4100}, {"loss": 0.3108, "grad_norm": 1.2969884872436523, "learning_rate": 0.0002, "epoch": 5.067817509247842, "step": 4110}, {"loss": 0.2858, "grad_norm": 1.0183063745498657, "learning_rate": 0.0002, "epoch": 5.080147965474723, "step": 4120}, {"loss": 0.295, "grad_norm": 1.121330738067627, "learning_rate": 0.0002, "epoch": 5.092478421701603, "step": 4130}, {"loss": 0.2697, "grad_norm": 1.0748186111450195, "learning_rate": 0.0002, "epoch": 5.104808877928483, "step": 4140}, {"loss": 0.3414, "grad_norm": 1.103474736213684, "learning_rate": 0.0002, "epoch": 5.117139334155364, "step": 4150}, {"loss": 0.305, "grad_norm": 1.2251166105270386, "learning_rate": 0.0002, "epoch": 5.129469790382244, "step": 4160}, {"loss": 0.3131, "grad_norm": 0.920898973941803, "learning_rate": 0.0002, "epoch": 5.141800246609124, "step": 4170}, {"loss": 0.281, "grad_norm": 1.327542781829834, "learning_rate": 0.0002, "epoch": 5.154130702836005, "step": 4180}, {"loss": 0.3214, "grad_norm": 1.0677192211151123, "learning_rate": 0.0002, "epoch": 5.1664611590628855, "step": 4190}, {"loss": 0.2863, "grad_norm": 0.897241473197937, "learning_rate": 0.0002, "epoch": 5.178791615289766, "step": 4200}, {"loss": 0.2967, "grad_norm": 0.977457582950592, "learning_rate": 0.0002, "epoch": 5.191122071516646, "step": 4210}, {"loss": 0.3032, "grad_norm": 1.4115267992019653, "learning_rate": 0.0002, "epoch": 5.203452527743527, "step": 4220}, {"loss": 0.3279, "grad_norm": 1.097743034362793, "learning_rate": 0.0002, "epoch": 5.215782983970407, "step": 4230}, {"loss": 0.293, "grad_norm": 1.1095269918441772, "learning_rate": 0.0002, "epoch": 5.228113440197287, "step": 4240}, {"loss": 0.3544, "grad_norm": 1.3785479068756104, "learning_rate": 0.0002, "epoch": 5.240443896424168, "step": 4250}, {"loss": 0.3118, "grad_norm": 1.0298776626586914, "learning_rate": 0.0002, "epoch": 5.252774352651048, "step": 4260}, {"loss": 0.296, "grad_norm": 1.1592111587524414, "learning_rate": 0.0002, "epoch": 5.265104808877928, "step": 4270}, {"loss": 0.2878, "grad_norm": 1.2355743646621704, "learning_rate": 0.0002, "epoch": 5.277435265104809, "step": 4280}, {"loss": 0.3085, "grad_norm": 0.8543112874031067, "learning_rate": 0.0002, "epoch": 5.2897657213316895, "step": 4290}, {"loss": 0.3108, "grad_norm": 1.2953215837478638, "learning_rate": 0.0002, "epoch": 5.302096177558569, "step": 4300}, {"loss": 0.2912, "grad_norm": 1.1001787185668945, "learning_rate": 0.0002, "epoch": 5.31442663378545, "step": 4310}, {"loss": 0.3003, "grad_norm": 0.7476816773414612, "learning_rate": 0.0002, "epoch": 5.326757090012331, "step": 4320}, {"loss": 0.3247, "grad_norm": 0.8195574283599854, "learning_rate": 0.0002, "epoch": 5.3390875462392104, "step": 4330}, {"loss": 0.3035, "grad_norm": 0.9490262866020203, "learning_rate": 0.0002, "epoch": 5.351418002466091, "step": 4340}, {"loss": 0.2846, "grad_norm": 1.2201412916183472, "learning_rate": 0.0002, "epoch": 5.363748458692972, "step": 4350}, {"loss": 0.2644, "grad_norm": 1.0311479568481445, "learning_rate": 0.0002, "epoch": 5.376078914919852, "step": 4360}, {"loss": 0.3104, "grad_norm": 1.2097488641738892, "learning_rate": 0.0002, "epoch": 5.388409371146732, "step": 4370}, {"loss": 0.2977, "grad_norm": 1.140942096710205, "learning_rate": 0.0002, "epoch": 5.400739827373613, "step": 4380}, {"loss": 0.2975, "grad_norm": 0.8091890811920166, "learning_rate": 0.0002, "epoch": 5.413070283600494, "step": 4390}, {"loss": 0.3727, "grad_norm": 1.4467964172363281, "learning_rate": 0.0002, "epoch": 5.425400739827373, "step": 4400}, {"loss": 0.2979, "grad_norm": 1.0836058855056763, "learning_rate": 0.0002, "epoch": 5.437731196054254, "step": 4410}, {"loss": 0.2601, "grad_norm": 1.0515433549880981, "learning_rate": 0.0002, "epoch": 5.450061652281135, "step": 4420}, {"loss": 0.315, "grad_norm": 0.9603073000907898, "learning_rate": 0.0002, "epoch": 5.4623921085080145, "step": 4430}, {"loss": 0.3166, "grad_norm": 1.234609842300415, "learning_rate": 0.0002, "epoch": 5.474722564734895, "step": 4440}, {"loss": 0.3142, "grad_norm": 0.8881428837776184, "learning_rate": 0.0002, "epoch": 5.487053020961776, "step": 4450}, {"loss": 0.3725, "grad_norm": 1.1817275285720825, "learning_rate": 0.0002, "epoch": 5.499383477188656, "step": 4460}, {"loss": 0.2944, "grad_norm": 1.213993787765503, "learning_rate": 0.0002, "epoch": 5.511713933415536, "step": 4470}, {"loss": 0.3136, "grad_norm": 1.0501725673675537, "learning_rate": 0.0002, "epoch": 5.524044389642417, "step": 4480}, {"loss": 0.306, "grad_norm": 1.5061579942703247, "learning_rate": 0.0002, "epoch": 5.536374845869297, "step": 4490}, {"loss": 0.3226, "grad_norm": 1.1171475648880005, "learning_rate": 0.0002, "epoch": 5.548705302096177, "step": 4500}, {"loss": 0.3624, "grad_norm": 1.1147594451904297, "learning_rate": 0.0002, "epoch": 5.561035758323058, "step": 4510}, {"loss": 0.3435, "grad_norm": 1.0600544214248657, "learning_rate": 0.0002, "epoch": 5.573366214549939, "step": 4520}, {"loss": 0.3268, "grad_norm": 1.247870922088623, "learning_rate": 0.0002, "epoch": 5.5856966707768185, "step": 4530}, {"loss": 0.3168, "grad_norm": 0.9425561428070068, "learning_rate": 0.0002, "epoch": 5.598027127003699, "step": 4540}, {"loss": 0.3119, "grad_norm": 1.1111550331115723, "learning_rate": 0.0002, "epoch": 5.61035758323058, "step": 4550}, {"loss": 0.3389, "grad_norm": 1.743268609046936, "learning_rate": 0.0002, "epoch": 5.62268803945746, "step": 4560}, {"loss": 0.31, "grad_norm": 1.3522645235061646, "learning_rate": 0.0002, "epoch": 5.63501849568434, "step": 4570}, {"loss": 0.3121, "grad_norm": 0.7354221343994141, "learning_rate": 0.0002, "epoch": 5.647348951911221, "step": 4580}, {"loss": 0.3693, "grad_norm": 1.050743818283081, "learning_rate": 0.0002, "epoch": 5.659679408138101, "step": 4590}, {"loss": 0.3449, "grad_norm": 1.1302396059036255, "learning_rate": 0.0002, "epoch": 5.6720098643649814, "step": 4600}, {"loss": 0.3211, "grad_norm": 0.8774183392524719, "learning_rate": 0.0002, "epoch": 5.684340320591862, "step": 4610}, {"loss": 0.3501, "grad_norm": 1.090781569480896, "learning_rate": 0.0002, "epoch": 5.696670776818742, "step": 4620}, {"loss": 0.3211, "grad_norm": 0.9177733063697815, "learning_rate": 0.0002, "epoch": 5.709001233045623, "step": 4630}, {"loss": 0.3439, "grad_norm": 0.9985341429710388, "learning_rate": 0.0002, "epoch": 5.721331689272503, "step": 4640}, {"loss": 0.3323, "grad_norm": 1.0230613946914673, "learning_rate": 0.0002, "epoch": 5.733662145499384, "step": 4650}, {"loss": 0.3525, "grad_norm": 0.944656252861023, "learning_rate": 0.0002, "epoch": 5.745992601726264, "step": 4660}, {"loss": 0.3191, "grad_norm": 0.8162471652030945, "learning_rate": 0.0002, "epoch": 5.758323057953144, "step": 4670}, {"loss": 0.4011, "grad_norm": 1.0500398874282837, "learning_rate": 0.0002, "epoch": 5.770653514180025, "step": 4680}, {"loss": 0.3452, "grad_norm": 0.9487981796264648, "learning_rate": 0.0002, "epoch": 5.782983970406905, "step": 4690}, {"loss": 0.2942, "grad_norm": 1.1856540441513062, "learning_rate": 0.0002, "epoch": 5.7953144266337855, "step": 4700}, {"loss": 0.3107, "grad_norm": 1.2583396434783936, "learning_rate": 0.0002, "epoch": 5.807644882860666, "step": 4710}, {"loss": 0.3223, "grad_norm": 1.2532602548599243, "learning_rate": 0.0002, "epoch": 5.819975339087546, "step": 4720}, {"loss": 0.3253, "grad_norm": 1.115236520767212, "learning_rate": 0.0002, "epoch": 5.832305795314427, "step": 4730}, {"loss": 0.3539, "grad_norm": 1.2245537042617798, "learning_rate": 0.0002, "epoch": 5.844636251541307, "step": 4740}, {"loss": 0.3171, "grad_norm": 1.1964094638824463, "learning_rate": 0.0002, "epoch": 5.856966707768187, "step": 4750}, {"loss": 0.3623, "grad_norm": 1.0833805799484253, "learning_rate": 0.0002, "epoch": 5.869297163995068, "step": 4760}, {"loss": 0.3511, "grad_norm": 1.0694046020507812, "learning_rate": 0.0002, "epoch": 5.881627620221948, "step": 4770}, {"loss": 0.3266, "grad_norm": 0.9947936534881592, "learning_rate": 0.0002, "epoch": 5.893958076448829, "step": 4780}, {"loss": 0.316, "grad_norm": 1.175716519355774, "learning_rate": 0.0002, "epoch": 5.906288532675709, "step": 4790}, {"loss": 0.3609, "grad_norm": 0.7717352509498596, "learning_rate": 0.0002, "epoch": 5.9186189889025895, "step": 4800}, {"loss": 0.3058, "grad_norm": 1.2906442880630493, "learning_rate": 0.0002, "epoch": 5.930949445129469, "step": 4810}, {"loss": 0.3187, "grad_norm": 1.2416284084320068, "learning_rate": 0.0002, "epoch": 5.94327990135635, "step": 4820}, {"loss": 0.337, "grad_norm": 1.3066956996917725, "learning_rate": 0.0002, "epoch": 5.955610357583231, "step": 4830}, {"loss": 0.3167, "grad_norm": 1.0872026681900024, "learning_rate": 0.0002, "epoch": 5.967940813810111, "step": 4840}, {"loss": 0.3262, "grad_norm": 1.1941101551055908, "learning_rate": 0.0002, "epoch": 5.980271270036991, "step": 4850}, {"loss": 0.3234, "grad_norm": 1.1126095056533813, "learning_rate": 0.0002, "epoch": 5.992601726263872, "step": 4860}, {"eval_loss": 1.748323917388916, "eval_runtime": 97.7488, "eval_samples_per_second": 4.46, "eval_steps_per_second": 0.563, "epoch": 6.0, "step": 4866}, {"loss": 0.2774, "grad_norm": 1.3631165027618408, "learning_rate": 0.0002, "epoch": 6.0049321824907524, "step": 4870}, {"loss": 0.2399, "grad_norm": 1.2631664276123047, "learning_rate": 0.0002, "epoch": 6.017262638717632, "step": 4880}, {"loss": 0.2177, "grad_norm": 0.7073080539703369, "learning_rate": 0.0002, "epoch": 6.029593094944513, "step": 4890}, {"loss": 0.215, "grad_norm": 0.7856091856956482, "learning_rate": 0.0002, "epoch": 6.041923551171394, "step": 4900}, {"loss": 0.1999, "grad_norm": 1.145540475845337, "learning_rate": 0.0002, "epoch": 6.054254007398273, "step": 4910}, {"loss": 0.2084, "grad_norm": 1.1742334365844727, "learning_rate": 0.0002, "epoch": 6.066584463625154, "step": 4920}, {"loss": 0.2342, "grad_norm": 0.8043994903564453, "learning_rate": 0.0002, "epoch": 6.078914919852035, "step": 4930}, {"loss": 0.2454, "grad_norm": 1.1877652406692505, "learning_rate": 0.0002, "epoch": 6.0912453760789145, "step": 4940}, {"loss": 0.1908, "grad_norm": 0.7624953985214233, "learning_rate": 0.0002, "epoch": 6.103575832305795, "step": 4950}, {"loss": 0.2254, "grad_norm": 1.0403119325637817, "learning_rate": 0.0002, "epoch": 6.115906288532676, "step": 4960}, {"loss": 0.2274, "grad_norm": 1.2040252685546875, "learning_rate": 0.0002, "epoch": 6.1282367447595565, "step": 4970}, {"loss": 0.2199, "grad_norm": 0.6242546439170837, "learning_rate": 0.0002, "epoch": 6.140567200986436, "step": 4980}, {"loss": 0.27, "grad_norm": 1.1394767761230469, "learning_rate": 0.0002, "epoch": 6.152897657213317, "step": 4990}, {"loss": 0.2377, "grad_norm": 1.3760257959365845, "learning_rate": 0.0002, "epoch": 6.165228113440198, "step": 5000}, {"loss": 0.2331, "grad_norm": 1.0707697868347168, "learning_rate": 0.0002, "epoch": 6.177558569667077, "step": 5010}, {"loss": 0.2311, "grad_norm": 1.288072109222412, "learning_rate": 0.0002, "epoch": 6.189889025893958, "step": 5020}, {"loss": 0.2276, "grad_norm": 1.1479463577270508, "learning_rate": 0.0002, "epoch": 6.202219482120839, "step": 5030}, {"loss": 0.2294, "grad_norm": 0.905891478061676, "learning_rate": 0.0002, "epoch": 6.2145499383477185, "step": 5040}, {"loss": 0.2575, "grad_norm": 1.0354516506195068, "learning_rate": 0.0002, "epoch": 6.226880394574599, "step": 5050}, {"loss": 0.2259, "grad_norm": 1.312671184539795, "learning_rate": 0.0002, "epoch": 6.23921085080148, "step": 5060}, {"loss": 0.2281, "grad_norm": 1.614709734916687, "learning_rate": 0.0002, "epoch": 6.25154130702836, "step": 5070}, {"loss": 0.2388, "grad_norm": 1.0864229202270508, "learning_rate": 0.0002, "epoch": 6.26387176325524, "step": 5080}, {"loss": 0.2014, "grad_norm": 1.0401391983032227, "learning_rate": 0.0002, "epoch": 6.276202219482121, "step": 5090}, {"loss": 0.2419, "grad_norm": 1.2187728881835938, "learning_rate": 0.0002, "epoch": 6.288532675709002, "step": 5100}, {"loss": 0.2144, "grad_norm": 0.9474364519119263, "learning_rate": 0.0002, "epoch": 6.300863131935881, "step": 5110}, {"loss": 0.238, "grad_norm": 1.1228716373443604, "learning_rate": 0.0002, "epoch": 6.313193588162762, "step": 5120}, {"loss": 0.2556, "grad_norm": 0.9294499754905701, "learning_rate": 0.0002, "epoch": 6.325524044389643, "step": 5130}, {"loss": 0.2384, "grad_norm": 1.0521048307418823, "learning_rate": 0.0002, "epoch": 6.337854500616523, "step": 5140}, {"loss": 0.2444, "grad_norm": 1.2406890392303467, "learning_rate": 0.0002, "epoch": 6.350184956843403, "step": 5150}, {"loss": 0.2301, "grad_norm": 1.2972853183746338, "learning_rate": 0.0002, "epoch": 6.362515413070284, "step": 5160}, {"loss": 0.2574, "grad_norm": 0.8772842288017273, "learning_rate": 0.0002, "epoch": 6.374845869297164, "step": 5170}, {"loss": 0.2337, "grad_norm": 1.050349473953247, "learning_rate": 0.0002, "epoch": 6.387176325524044, "step": 5180}, {"loss": 0.2593, "grad_norm": 0.9432134032249451, "learning_rate": 0.0002, "epoch": 6.399506781750925, "step": 5190}, {"loss": 0.2546, "grad_norm": 1.11045241355896, "learning_rate": 0.0002, "epoch": 6.411837237977805, "step": 5200}, {"loss": 0.268, "grad_norm": 1.117530345916748, "learning_rate": 0.0002, "epoch": 6.4241676942046855, "step": 5210}, {"loss": 0.25, "grad_norm": 1.4194035530090332, "learning_rate": 0.0002, "epoch": 6.436498150431566, "step": 5220}, {"loss": 0.2335, "grad_norm": 1.063950777053833, "learning_rate": 0.0002, "epoch": 6.448828606658447, "step": 5230}, {"loss": 0.2299, "grad_norm": 1.2946349382400513, "learning_rate": 0.0002, "epoch": 6.461159062885327, "step": 5240}, {"loss": 0.242, "grad_norm": 1.5237880945205688, "learning_rate": 0.0002, "epoch": 6.473489519112207, "step": 5250}, {"loss": 0.255, "grad_norm": 1.1915720701217651, "learning_rate": 0.0002, "epoch": 6.485819975339088, "step": 5260}, {"loss": 0.2357, "grad_norm": 1.0779626369476318, "learning_rate": 0.0002, "epoch": 6.498150431565968, "step": 5270}, {"loss": 0.2476, "grad_norm": 0.8255738019943237, "learning_rate": 0.0002, "epoch": 6.510480887792848, "step": 5280}, {"loss": 0.267, "grad_norm": 1.275174856185913, "learning_rate": 0.0002, "epoch": 6.522811344019729, "step": 5290}, {"loss": 0.2217, "grad_norm": 1.0878815650939941, "learning_rate": 0.0002, "epoch": 6.535141800246609, "step": 5300}, {"loss": 0.2462, "grad_norm": 1.2594236135482788, "learning_rate": 0.0002, "epoch": 6.5474722564734895, "step": 5310}, {"loss": 0.2457, "grad_norm": 0.9919610619544983, "learning_rate": 0.0002, "epoch": 6.55980271270037, "step": 5320}, {"loss": 0.2933, "grad_norm": 1.3703680038452148, "learning_rate": 0.0002, "epoch": 6.57213316892725, "step": 5330}, {"loss": 0.2453, "grad_norm": 1.403140902519226, "learning_rate": 0.0002, "epoch": 6.584463625154131, "step": 5340}, {"loss": 0.2584, "grad_norm": 1.3477165699005127, "learning_rate": 0.0002, "epoch": 6.596794081381011, "step": 5350}, {"loss": 0.2853, "grad_norm": 1.3145594596862793, "learning_rate": 0.0002, "epoch": 6.609124537607892, "step": 5360}, {"loss": 0.246, "grad_norm": 0.9048973321914673, "learning_rate": 0.0002, "epoch": 6.621454993834772, "step": 5370}, {"loss": 0.2646, "grad_norm": 1.4123972654342651, "learning_rate": 0.0002, "epoch": 6.633785450061652, "step": 5380}, {"loss": 0.272, "grad_norm": 1.3584848642349243, "learning_rate": 0.0002, "epoch": 6.646115906288532, "step": 5390}, {"loss": 0.2663, "grad_norm": 1.2085801362991333, "learning_rate": 0.0002, "epoch": 6.658446362515413, "step": 5400}, {"loss": 0.2796, "grad_norm": 1.9293283224105835, "learning_rate": 0.0002, "epoch": 6.670776818742294, "step": 5410}, {"loss": 0.2412, "grad_norm": 1.3658782243728638, "learning_rate": 0.0002, "epoch": 6.683107274969174, "step": 5420}, {"loss": 0.2442, "grad_norm": 1.2004997730255127, "learning_rate": 0.0002, "epoch": 6.695437731196054, "step": 5430}, {"loss": 0.2693, "grad_norm": 1.0671268701553345, "learning_rate": 0.0002, "epoch": 6.707768187422935, "step": 5440}, {"loss": 0.2216, "grad_norm": 0.8877466320991516, "learning_rate": 0.0002, "epoch": 6.720098643649815, "step": 5450}, {"loss": 0.2678, "grad_norm": 1.2843106985092163, "learning_rate": 0.0002, "epoch": 6.732429099876695, "step": 5460}, {"loss": 0.2418, "grad_norm": 1.0663448572158813, "learning_rate": 0.0002, "epoch": 6.744759556103576, "step": 5470}, {"loss": 0.2402, "grad_norm": 1.3155773878097534, "learning_rate": 0.0002, "epoch": 6.7570900123304565, "step": 5480}, {"loss": 0.2559, "grad_norm": 1.8862448930740356, "learning_rate": 0.0002, "epoch": 6.769420468557336, "step": 5490}, {"loss": 0.2651, "grad_norm": 1.165061116218567, "learning_rate": 0.0002, "epoch": 6.781750924784217, "step": 5500}, {"loss": 0.2342, "grad_norm": 1.0968598127365112, "learning_rate": 0.0002, "epoch": 6.794081381011098, "step": 5510}, {"loss": 0.2453, "grad_norm": 0.9448091983795166, "learning_rate": 0.0002, "epoch": 6.806411837237977, "step": 5520}, {"loss": 0.2609, "grad_norm": 1.400767207145691, "learning_rate": 0.0002, "epoch": 6.818742293464858, "step": 5530}, {"loss": 0.2642, "grad_norm": 1.1031112670898438, "learning_rate": 0.0002, "epoch": 6.831072749691739, "step": 5540}, {"loss": 0.2534, "grad_norm": 1.2436904907226562, "learning_rate": 0.0002, "epoch": 6.843403205918619, "step": 5550}, {"loss": 0.2601, "grad_norm": 1.0987974405288696, "learning_rate": 0.0002, "epoch": 6.855733662145499, "step": 5560}, {"loss": 0.2622, "grad_norm": 0.8656415939331055, "learning_rate": 0.0002, "epoch": 6.86806411837238, "step": 5570}, {"loss": 0.2585, "grad_norm": 1.2153927087783813, "learning_rate": 0.0002, "epoch": 6.8803945745992605, "step": 5580}, {"loss": 0.2888, "grad_norm": 1.111377477645874, "learning_rate": 0.0002, "epoch": 6.89272503082614, "step": 5590}, {"loss": 0.2569, "grad_norm": 1.0041896104812622, "learning_rate": 0.0002, "epoch": 6.905055487053021, "step": 5600}, {"loss": 0.2654, "grad_norm": 1.0638413429260254, "learning_rate": 0.0002, "epoch": 6.917385943279902, "step": 5610}, {"loss": 0.2364, "grad_norm": 0.9756764769554138, "learning_rate": 0.0002, "epoch": 6.929716399506781, "step": 5620}, {"loss": 0.2756, "grad_norm": 1.153550624847412, "learning_rate": 0.0002, "epoch": 6.942046855733662, "step": 5630}, {"loss": 0.2732, "grad_norm": 1.3393985033035278, "learning_rate": 0.0002, "epoch": 6.954377311960543, "step": 5640}, {"loss": 0.2793, "grad_norm": 1.3233463764190674, "learning_rate": 0.0002, "epoch": 6.9667077681874225, "step": 5650}, {"loss": 0.2593, "grad_norm": 1.1693105697631836, "learning_rate": 0.0002, "epoch": 6.979038224414303, "step": 5660}, {"loss": 0.278, "grad_norm": 0.7186262607574463, "learning_rate": 0.0002, "epoch": 6.991368680641184, "step": 5670}]}
+{"epoch": 8.0, "step": 6488, "epoch_duration": 2527.4715588092804, "total_accumulated_duration": 19626.680991649628, "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": 28774.0}, "peak_memory_reserved": {"GPU_0": 28774.0}, "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-0.6-num-5885-sd-10000/checkpoint-1622", "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": 2.3601, "grad_norm": 0.8258164525032043, "learning_rate": 0.0002, "epoch": 0.012330456226880395, "step": 10}, {"loss": 1.7317, "grad_norm": 0.4577729105949402, "learning_rate": 0.0002, "epoch": 0.02466091245376079, "step": 20}, {"loss": 1.4729, "grad_norm": 0.639807939529419, "learning_rate": 0.0002, "epoch": 0.036991368680641186, "step": 30}, {"loss": 1.2088, "grad_norm": 0.5311757922172546, "learning_rate": 0.0002, "epoch": 0.04932182490752158, "step": 40}, {"loss": 1.3149, "grad_norm": 0.386595219373703, "learning_rate": 0.0002, "epoch": 0.06165228113440197, "step": 50}, {"loss": 1.1657, "grad_norm": 0.4401357173919678, "learning_rate": 0.0002, "epoch": 0.07398273736128237, "step": 60}, {"loss": 1.1022, "grad_norm": 0.3234352171421051, "learning_rate": 0.0002, "epoch": 0.08631319358816276, "step": 70}, {"loss": 1.3738, "grad_norm": 0.29643672704696655, "learning_rate": 0.0002, "epoch": 0.09864364981504316, "step": 80}, {"loss": 1.1929, "grad_norm": 0.2941012382507324, "learning_rate": 0.0002, "epoch": 0.11097410604192355, "step": 90}, {"loss": 1.2067, "grad_norm": 0.5498173832893372, "learning_rate": 0.0002, "epoch": 0.12330456226880394, "step": 100}, {"loss": 1.142, "grad_norm": 0.2545783519744873, "learning_rate": 0.0002, "epoch": 0.13563501849568435, "step": 110}, {"loss": 1.0297, "grad_norm": 0.2984241247177124, "learning_rate": 0.0002, "epoch": 0.14796547472256474, "step": 120}, {"loss": 1.1591, "grad_norm": 0.2710968852043152, "learning_rate": 0.0002, "epoch": 0.16029593094944514, "step": 130}, {"loss": 1.0427, "grad_norm": 0.2817152142524719, "learning_rate": 0.0002, "epoch": 0.17262638717632553, "step": 140}, {"loss": 1.0638, "grad_norm": 0.41083765029907227, "learning_rate": 0.0002, "epoch": 0.18495684340320592, "step": 150}, {"loss": 1.3537, "grad_norm": 0.36536213755607605, "learning_rate": 0.0002, "epoch": 0.19728729963008632, "step": 160}, {"loss": 1.0132, "grad_norm": 0.2738671600818634, "learning_rate": 0.0002, "epoch": 0.2096177558569667, "step": 170}, {"loss": 0.9555, "grad_norm": 0.27403146028518677, "learning_rate": 0.0002, "epoch": 0.2219482120838471, "step": 180}, {"loss": 1.0769, "grad_norm": 0.4446810483932495, "learning_rate": 0.0002, "epoch": 0.2342786683107275, "step": 190}, {"loss": 1.0588, "grad_norm": 0.5295385718345642, "learning_rate": 0.0002, "epoch": 0.2466091245376079, "step": 200}, {"loss": 1.0827, "grad_norm": 0.311404824256897, "learning_rate": 0.0002, "epoch": 0.2589395807644883, "step": 210}, {"loss": 1.1455, "grad_norm": 0.2448509782552719, "learning_rate": 0.0002, "epoch": 0.2712700369913687, "step": 220}, {"loss": 1.0929, "grad_norm": 0.6507014036178589, "learning_rate": 0.0002, "epoch": 0.2836004932182491, "step": 230}, {"loss": 0.9875, "grad_norm": 0.2339320331811905, "learning_rate": 0.0002, "epoch": 0.2959309494451295, "step": 240}, {"loss": 0.9211, "grad_norm": 0.8210226893424988, "learning_rate": 0.0002, "epoch": 0.3082614056720099, "step": 250}, {"loss": 1.161, "grad_norm": 0.27473965287208557, "learning_rate": 0.0002, "epoch": 0.3205918618988903, "step": 260}, {"loss": 1.0218, "grad_norm": 0.3051395118236542, "learning_rate": 0.0002, "epoch": 0.33292231812577067, "step": 270}, {"loss": 1.0286, "grad_norm": 0.3037777245044708, "learning_rate": 0.0002, "epoch": 0.34525277435265106, "step": 280}, {"loss": 1.144, "grad_norm": 0.2748974859714508, "learning_rate": 0.0002, "epoch": 0.35758323057953145, "step": 290}, {"loss": 1.0858, "grad_norm": 0.23656068742275238, "learning_rate": 0.0002, "epoch": 0.36991368680641185, "step": 300}, {"loss": 1.0564, "grad_norm": 0.2523384094238281, "learning_rate": 0.0002, "epoch": 0.38224414303329224, "step": 310}, {"loss": 1.3091, "grad_norm": 0.27848055958747864, "learning_rate": 0.0002, "epoch": 0.39457459926017263, "step": 320}, {"loss": 1.0252, "grad_norm": 0.3204525411128998, "learning_rate": 0.0002, "epoch": 0.406905055487053, "step": 330}, {"loss": 0.9855, "grad_norm": 0.3459707498550415, "learning_rate": 0.0002, "epoch": 0.4192355117139334, "step": 340}, {"loss": 1.1111, "grad_norm": 0.2458430379629135, "learning_rate": 0.0002, "epoch": 0.4315659679408138, "step": 350}, {"loss": 1.1493, "grad_norm": 0.5022910237312317, "learning_rate": 0.0002, "epoch": 0.4438964241676942, "step": 360}, {"loss": 1.1272, "grad_norm": 0.27076372504234314, "learning_rate": 0.0002, "epoch": 0.4562268803945746, "step": 370}, {"loss": 1.1927, "grad_norm": 0.6489047408103943, "learning_rate": 0.0002, "epoch": 0.468557336621455, "step": 380}, {"loss": 0.9501, "grad_norm": 0.3324144184589386, "learning_rate": 0.0002, "epoch": 0.4808877928483354, "step": 390}, {"loss": 1.2012, "grad_norm": 0.32813116908073425, "learning_rate": 0.0002, "epoch": 0.4932182490752158, "step": 400}, {"loss": 1.1135, "grad_norm": 0.25295355916023254, "learning_rate": 0.0002, "epoch": 0.5055487053020962, "step": 410}, {"loss": 0.9477, "grad_norm": 0.2912578880786896, "learning_rate": 0.0002, "epoch": 0.5178791615289766, "step": 420}, {"loss": 1.0121, "grad_norm": 0.34780189394950867, "learning_rate": 0.0002, "epoch": 0.530209617755857, "step": 430}, {"loss": 0.9296, "grad_norm": 0.24604526162147522, "learning_rate": 0.0002, "epoch": 0.5425400739827374, "step": 440}, {"loss": 1.253, "grad_norm": 0.32759982347488403, "learning_rate": 0.0002, "epoch": 0.5548705302096177, "step": 450}, {"loss": 1.1925, "grad_norm": 0.40810221433639526, "learning_rate": 0.0002, "epoch": 0.5672009864364982, "step": 460}, {"loss": 1.174, "grad_norm": 0.3590679466724396, "learning_rate": 0.0002, "epoch": 0.5795314426633785, "step": 470}, {"loss": 1.2223, "grad_norm": 0.5656213760375977, "learning_rate": 0.0002, "epoch": 0.591861898890259, "step": 480}, {"loss": 1.1936, "grad_norm": 0.30830657482147217, "learning_rate": 0.0002, "epoch": 0.6041923551171393, "step": 490}, {"loss": 1.1873, "grad_norm": 0.317905455827713, "learning_rate": 0.0002, "epoch": 0.6165228113440198, "step": 500}, {"loss": 0.9805, "grad_norm": 0.3254566490650177, "learning_rate": 0.0002, "epoch": 0.6288532675709001, "step": 510}, {"loss": 1.0384, "grad_norm": 0.29187721014022827, "learning_rate": 0.0002, "epoch": 0.6411837237977805, "step": 520}, {"loss": 1.2526, "grad_norm": 0.3439238965511322, "learning_rate": 0.0002, "epoch": 0.6535141800246609, "step": 530}, {"loss": 1.0698, "grad_norm": 0.20970556139945984, "learning_rate": 0.0002, "epoch": 0.6658446362515413, "step": 540}, {"loss": 1.1047, "grad_norm": 0.4022853374481201, "learning_rate": 0.0002, "epoch": 0.6781750924784217, "step": 550}, {"loss": 1.0684, "grad_norm": 0.2235759049654007, "learning_rate": 0.0002, "epoch": 0.6905055487053021, "step": 560}, {"loss": 1.2339, "grad_norm": 0.33849895000457764, "learning_rate": 0.0002, "epoch": 0.7028360049321825, "step": 570}, {"loss": 1.1929, "grad_norm": 0.34745967388153076, "learning_rate": 0.0002, "epoch": 0.7151664611590629, "step": 580}, {"loss": 1.1158, "grad_norm": 0.26041269302368164, "learning_rate": 0.0002, "epoch": 0.7274969173859432, "step": 590}, {"loss": 1.2134, "grad_norm": 0.3804777264595032, "learning_rate": 0.0002, "epoch": 0.7398273736128237, "step": 600}, {"loss": 1.0606, "grad_norm": 0.2456253319978714, "learning_rate": 0.0002, "epoch": 0.752157829839704, "step": 610}, {"loss": 1.0638, "grad_norm": 0.37838423252105713, "learning_rate": 0.0002, "epoch": 0.7644882860665845, "step": 620}, {"loss": 1.0556, "grad_norm": 0.28105494379997253, "learning_rate": 0.0002, "epoch": 0.7768187422934648, "step": 630}, {"loss": 1.0672, "grad_norm": 0.2774018943309784, "learning_rate": 0.0002, "epoch": 0.7891491985203453, "step": 640}, {"loss": 0.9978, "grad_norm": 1.8184229135513306, "learning_rate": 0.0002, "epoch": 0.8014796547472256, "step": 650}, {"loss": 1.1038, "grad_norm": 0.3325096070766449, "learning_rate": 0.0002, "epoch": 0.813810110974106, "step": 660}, {"loss": 1.083, "grad_norm": 0.2686693072319031, "learning_rate": 0.0002, "epoch": 0.8261405672009864, "step": 670}, {"loss": 1.1308, "grad_norm": 0.3271431624889374, "learning_rate": 0.0002, "epoch": 0.8384710234278668, "step": 680}, {"loss": 1.1116, "grad_norm": 2.359999656677246, "learning_rate": 0.0002, "epoch": 0.8508014796547472, "step": 690}, {"loss": 1.0782, "grad_norm": 0.46242964267730713, "learning_rate": 0.0002, "epoch": 0.8631319358816276, "step": 700}, {"loss": 0.95, "grad_norm": 0.34731170535087585, "learning_rate": 0.0002, "epoch": 0.8754623921085081, "step": 710}, {"loss": 1.2236, "grad_norm": 0.39381715655326843, "learning_rate": 0.0002, "epoch": 0.8877928483353884, "step": 720}, {"loss": 1.1319, "grad_norm": 0.43496373295783997, "learning_rate": 0.0002, "epoch": 0.9001233045622689, "step": 730}, {"loss": 1.0979, "grad_norm": 0.32243210077285767, "learning_rate": 0.0002, "epoch": 0.9124537607891492, "step": 740}, {"loss": 0.9913, "grad_norm": 0.30396756529808044, "learning_rate": 0.0002, "epoch": 0.9247842170160296, "step": 750}, {"loss": 1.1141, "grad_norm": 0.4461122751235962, "learning_rate": 0.0002, "epoch": 0.93711467324291, "step": 760}, {"loss": 1.0049, "grad_norm": 0.24081681668758392, "learning_rate": 0.0002, "epoch": 0.9494451294697904, "step": 770}, {"loss": 1.0966, "grad_norm": 0.27461910247802734, "learning_rate": 0.0002, "epoch": 0.9617755856966708, "step": 780}, {"loss": 0.9942, "grad_norm": 0.3325668275356293, "learning_rate": 0.0002, "epoch": 0.9741060419235512, "step": 790}, {"loss": 1.0506, "grad_norm": 0.24046339094638824, "learning_rate": 0.0002, "epoch": 0.9864364981504316, "step": 800}, {"loss": 0.9989, "grad_norm": 0.42950066924095154, "learning_rate": 0.0002, "epoch": 0.998766954377312, "step": 810}, {"eval_loss": 1.246457576751709, "eval_runtime": 98.7974, "eval_samples_per_second": 4.413, "eval_steps_per_second": 0.557, "epoch": 1.0, "step": 811}, {"loss": 1.0536, "grad_norm": 0.26760655641555786, "learning_rate": 0.0002, "epoch": 1.0110974106041923, "step": 820}, {"loss": 0.9722, "grad_norm": 0.4640820026397705, "learning_rate": 0.0002, "epoch": 1.0234278668310728, "step": 830}, {"loss": 0.9392, "grad_norm": 0.2699166238307953, "learning_rate": 0.0002, "epoch": 1.0357583230579532, "step": 840}, {"loss": 0.9335, "grad_norm": 0.3441709578037262, "learning_rate": 0.0002, "epoch": 1.0480887792848335, "step": 850}, {"loss": 0.9083, "grad_norm": 0.299934983253479, "learning_rate": 0.0002, "epoch": 1.060419235511714, "step": 860}, {"loss": 0.9416, "grad_norm": 0.2980666160583496, "learning_rate": 0.0002, "epoch": 1.0727496917385944, "step": 870}, {"loss": 0.94, "grad_norm": 0.3131714463233948, "learning_rate": 0.0002, "epoch": 1.0850801479654748, "step": 880}, {"loss": 0.9288, "grad_norm": 0.29881617426872253, "learning_rate": 0.0002, "epoch": 1.097410604192355, "step": 890}, {"loss": 0.998, "grad_norm": 0.29870888590812683, "learning_rate": 0.0002, "epoch": 1.1097410604192355, "step": 900}, {"loss": 0.9924, "grad_norm": 0.5735140442848206, "learning_rate": 0.0002, "epoch": 1.122071516646116, "step": 910}, {"loss": 1.0694, "grad_norm": 0.33159002661705017, "learning_rate": 0.0002, "epoch": 1.1344019728729964, "step": 920}, {"loss": 1.0069, "grad_norm": 1.235399842262268, "learning_rate": 0.0002, "epoch": 1.1467324290998766, "step": 930}, {"loss": 1.0315, "grad_norm": 0.27469736337661743, "learning_rate": 0.0002, "epoch": 1.159062885326757, "step": 940}, {"loss": 0.9386, "grad_norm": 0.29130664467811584, "learning_rate": 0.0002, "epoch": 1.1713933415536375, "step": 950}, {"loss": 0.8919, "grad_norm": 0.3730354607105255, "learning_rate": 0.0002, "epoch": 1.183723797780518, "step": 960}, {"loss": 0.9988, "grad_norm": 0.5973590612411499, "learning_rate": 0.0002, "epoch": 1.1960542540073984, "step": 970}, {"loss": 0.9525, "grad_norm": 0.39631304144859314, "learning_rate": 0.0002, "epoch": 1.2083847102342786, "step": 980}, {"loss": 0.9217, "grad_norm": 0.849051296710968, "learning_rate": 0.0002, "epoch": 1.220715166461159, "step": 990}, {"loss": 1.0903, "grad_norm": 0.4390525817871094, "learning_rate": 0.0002, "epoch": 1.2330456226880395, "step": 1000}, {"loss": 0.9018, "grad_norm": 0.30423852801322937, "learning_rate": 0.0002, "epoch": 1.2453760789149197, "step": 1010}, {"loss": 1.0128, "grad_norm": 0.34736061096191406, "learning_rate": 0.0002, "epoch": 1.2577065351418002, "step": 1020}, {"loss": 0.9026, "grad_norm": 0.3421604037284851, "learning_rate": 0.0002, "epoch": 1.2700369913686806, "step": 1030}, {"loss": 0.8485, "grad_norm": 0.544170081615448, "learning_rate": 0.0002, "epoch": 1.282367447595561, "step": 1040}, {"loss": 0.9591, "grad_norm": 0.5128790736198425, "learning_rate": 0.0002, "epoch": 1.2946979038224415, "step": 1050}, {"loss": 0.9214, "grad_norm": 0.443344384431839, "learning_rate": 0.0002, "epoch": 1.3070283600493218, "step": 1060}, {"loss": 0.9367, "grad_norm": 0.6380868554115295, "learning_rate": 0.0002, "epoch": 1.3193588162762022, "step": 1070}, {"loss": 0.9849, "grad_norm": 0.4638073146343231, "learning_rate": 0.0002, "epoch": 1.3316892725030827, "step": 1080}, {"loss": 0.8645, "grad_norm": 0.32406893372535706, "learning_rate": 0.0002, "epoch": 1.344019728729963, "step": 1090}, {"loss": 0.8278, "grad_norm": 0.3955065608024597, "learning_rate": 0.0002, "epoch": 1.3563501849568433, "step": 1100}, {"loss": 0.9306, "grad_norm": 0.3489246666431427, "learning_rate": 0.0002, "epoch": 1.3686806411837238, "step": 1110}, {"loss": 1.0138, "grad_norm": 0.48451653122901917, "learning_rate": 0.0002, "epoch": 1.3810110974106042, "step": 1120}, {"loss": 0.9165, "grad_norm": 0.3652360439300537, "learning_rate": 0.0002, "epoch": 1.3933415536374847, "step": 1130}, {"loss": 0.9576, "grad_norm": 1.3097436428070068, "learning_rate": 0.0002, "epoch": 1.405672009864365, "step": 1140}, {"loss": 0.8115, "grad_norm": 0.3647715449333191, "learning_rate": 0.0002, "epoch": 1.4180024660912454, "step": 1150}, {"loss": 0.8573, "grad_norm": 0.37248560786247253, "learning_rate": 0.0002, "epoch": 1.4303329223181258, "step": 1160}, {"loss": 0.936, "grad_norm": 0.4639643430709839, "learning_rate": 0.0002, "epoch": 1.442663378545006, "step": 1170}, {"loss": 0.9511, "grad_norm": 0.5455219745635986, "learning_rate": 0.0002, "epoch": 1.4549938347718865, "step": 1180}, {"loss": 0.8611, "grad_norm": 0.38862571120262146, "learning_rate": 0.0002, "epoch": 1.467324290998767, "step": 1190}, {"loss": 0.8681, "grad_norm": 0.37586215138435364, "learning_rate": 0.0002, "epoch": 1.4796547472256474, "step": 1200}, {"loss": 0.8673, "grad_norm": 0.46244436502456665, "learning_rate": 0.0002, "epoch": 1.4919852034525278, "step": 1210}, {"loss": 0.9388, "grad_norm": 0.3570359945297241, "learning_rate": 0.0002, "epoch": 1.504315659679408, "step": 1220}, {"loss": 0.971, "grad_norm": 0.28393083810806274, "learning_rate": 0.0002, "epoch": 1.5166461159062885, "step": 1230}, {"loss": 0.9296, "grad_norm": 0.5672869682312012, "learning_rate": 0.0002, "epoch": 1.528976572133169, "step": 1240}, {"loss": 0.8787, "grad_norm": 0.41605108976364136, "learning_rate": 0.0002, "epoch": 1.5413070283600492, "step": 1250}, {"loss": 0.8744, "grad_norm": 0.40657493472099304, "learning_rate": 0.0002, "epoch": 1.5536374845869299, "step": 1260}, {"loss": 0.9046, "grad_norm": 0.43672341108322144, "learning_rate": 0.0002, "epoch": 1.56596794081381, "step": 1270}, {"loss": 0.8586, "grad_norm": 0.3065410554409027, "learning_rate": 0.0002, "epoch": 1.5782983970406905, "step": 1280}, {"loss": 0.9499, "grad_norm": 0.37826645374298096, "learning_rate": 0.0002, "epoch": 1.590628853267571, "step": 1290}, {"loss": 0.901, "grad_norm": 0.42307335138320923, "learning_rate": 0.0002, "epoch": 1.6029593094944512, "step": 1300}, {"loss": 0.8673, "grad_norm": 0.3648843467235565, "learning_rate": 0.0002, "epoch": 1.6152897657213316, "step": 1310}, {"loss": 0.9302, "grad_norm": 0.8921076059341431, "learning_rate": 0.0002, "epoch": 1.627620221948212, "step": 1320}, {"loss": 0.9378, "grad_norm": 0.37522226572036743, "learning_rate": 0.0002, "epoch": 1.6399506781750923, "step": 1330}, {"loss": 0.8921, "grad_norm": 0.7489957809448242, "learning_rate": 0.0002, "epoch": 1.652281134401973, "step": 1340}, {"loss": 0.9297, "grad_norm": 0.31733131408691406, "learning_rate": 0.0002, "epoch": 1.6646115906288532, "step": 1350}, {"loss": 0.907, "grad_norm": 0.3249478340148926, "learning_rate": 0.0002, "epoch": 1.6769420468557337, "step": 1360}, {"loss": 1.0197, "grad_norm": 0.3178001344203949, "learning_rate": 0.0002, "epoch": 1.6892725030826141, "step": 1370}, {"loss": 1.0781, "grad_norm": 0.5674093961715698, "learning_rate": 0.0002, "epoch": 1.7016029593094943, "step": 1380}, {"loss": 0.8972, "grad_norm": 0.35272449254989624, "learning_rate": 0.0002, "epoch": 1.7139334155363748, "step": 1390}, {"loss": 0.9346, "grad_norm": 0.5778217911720276, "learning_rate": 0.0002, "epoch": 1.7262638717632552, "step": 1400}, {"loss": 0.9099, "grad_norm": 0.33561450242996216, "learning_rate": 0.0002, "epoch": 1.7385943279901355, "step": 1410}, {"loss": 0.8636, "grad_norm": 0.31735464930534363, "learning_rate": 0.0002, "epoch": 1.7509247842170161, "step": 1420}, {"loss": 0.982, "grad_norm": 1.0612670183181763, "learning_rate": 0.0002, "epoch": 1.7632552404438964, "step": 1430}, {"loss": 0.8224, "grad_norm": 0.5442509651184082, "learning_rate": 0.0002, "epoch": 1.7755856966707768, "step": 1440}, {"loss": 0.9275, "grad_norm": 0.7471332550048828, "learning_rate": 0.0002, "epoch": 1.7879161528976573, "step": 1450}, {"loss": 0.9389, "grad_norm": 0.4323609173297882, "learning_rate": 0.0002, "epoch": 1.8002466091245375, "step": 1460}, {"loss": 0.8247, "grad_norm": 0.47796759009361267, "learning_rate": 0.0002, "epoch": 1.8125770653514182, "step": 1470}, {"loss": 0.9395, "grad_norm": 0.3348400592803955, "learning_rate": 0.0002, "epoch": 1.8249075215782984, "step": 1480}, {"loss": 0.9793, "grad_norm": 0.3354550898075104, "learning_rate": 0.0002, "epoch": 1.8372379778051788, "step": 1490}, {"loss": 0.8581, "grad_norm": 0.5988477468490601, "learning_rate": 0.0002, "epoch": 1.8495684340320593, "step": 1500}, {"loss": 0.9268, "grad_norm": 0.5222318172454834, "learning_rate": 0.0002, "epoch": 1.8618988902589395, "step": 1510}, {"loss": 0.8846, "grad_norm": 0.5246642827987671, "learning_rate": 0.0002, "epoch": 1.87422934648582, "step": 1520}, {"loss": 0.9317, "grad_norm": 0.3164594769477844, "learning_rate": 0.0002, "epoch": 1.8865598027127004, "step": 1530}, {"loss": 0.9961, "grad_norm": 0.3496174216270447, "learning_rate": 0.0002, "epoch": 1.8988902589395806, "step": 1540}, {"loss": 0.9057, "grad_norm": 0.8863359689712524, "learning_rate": 0.0002, "epoch": 1.9112207151664613, "step": 1550}, {"loss": 0.9405, "grad_norm": 0.3587026298046112, "learning_rate": 0.0002, "epoch": 1.9235511713933415, "step": 1560}, {"loss": 0.8335, "grad_norm": 0.6052881479263306, "learning_rate": 0.0002, "epoch": 1.935881627620222, "step": 1570}, {"loss": 0.8805, "grad_norm": 0.567269504070282, "learning_rate": 0.0002, "epoch": 1.9482120838471024, "step": 1580}, {"loss": 0.9581, "grad_norm": 0.45184487104415894, "learning_rate": 0.0002, "epoch": 1.9605425400739827, "step": 1590}, {"loss": 0.9147, "grad_norm": 0.5028569102287292, "learning_rate": 0.0002, "epoch": 1.972872996300863, "step": 1600}, {"loss": 0.75, "grad_norm": 0.4677547216415405, "learning_rate": 0.0002, "epoch": 1.9852034525277436, "step": 1610}, {"loss": 0.8469, "grad_norm": 0.35106056928634644, "learning_rate": 0.0002, "epoch": 1.9975339087546238, "step": 1620}, {"eval_loss": 1.238026738166809, "eval_runtime": 95.4287, "eval_samples_per_second": 4.569, "eval_steps_per_second": 0.576, "epoch": 2.0, "step": 1622}, {"loss": 0.7629, "grad_norm": 0.444060355424881, "learning_rate": 0.0002, "epoch": 2.0098643649815044, "step": 1630}, {"loss": 0.772, "grad_norm": 0.627570390701294, "learning_rate": 0.0002, "epoch": 2.0221948212083847, "step": 1640}, {"loss": 0.6186, "grad_norm": 0.38737839460372925, "learning_rate": 0.0002, "epoch": 2.034525277435265, "step": 1650}, {"loss": 0.7734, "grad_norm": 0.4300459623336792, "learning_rate": 0.0002, "epoch": 2.0468557336621456, "step": 1660}, {"loss": 0.6943, "grad_norm": 0.43037715554237366, "learning_rate": 0.0002, "epoch": 2.059186189889026, "step": 1670}, {"loss": 0.6588, "grad_norm": 0.40772515535354614, "learning_rate": 0.0002, "epoch": 2.0715166461159065, "step": 1680}, {"loss": 0.8105, "grad_norm": 0.5295451879501343, "learning_rate": 0.0002, "epoch": 2.0838471023427867, "step": 1690}, {"loss": 0.7717, "grad_norm": 0.7452750205993652, "learning_rate": 0.0002, "epoch": 2.096177558569667, "step": 1700}, {"loss": 0.7458, "grad_norm": 0.809183657169342, "learning_rate": 0.0002, "epoch": 2.1085080147965476, "step": 1710}, {"loss": 0.7398, "grad_norm": 0.4597688913345337, "learning_rate": 0.0002, "epoch": 2.120838471023428, "step": 1720}, {"loss": 0.6856, "grad_norm": 0.806919276714325, "learning_rate": 0.0002, "epoch": 2.133168927250308, "step": 1730}, {"loss": 0.679, "grad_norm": 0.3755643665790558, "learning_rate": 0.0002, "epoch": 2.1454993834771887, "step": 1740}, {"loss": 0.7938, "grad_norm": 0.5882734060287476, "learning_rate": 0.0002, "epoch": 2.157829839704069, "step": 1750}, {"loss": 0.6782, "grad_norm": 0.692960798740387, "learning_rate": 0.0002, "epoch": 2.1701602959309496, "step": 1760}, {"loss": 0.7195, "grad_norm": 0.4737096428871155, "learning_rate": 0.0002, "epoch": 2.18249075215783, "step": 1770}, {"loss": 0.758, "grad_norm": 0.6637021899223328, "learning_rate": 0.0002, "epoch": 2.19482120838471, "step": 1780}, {"loss": 0.7139, "grad_norm": 0.9109764099121094, "learning_rate": 0.0002, "epoch": 2.2071516646115907, "step": 1790}, {"loss": 0.7373, "grad_norm": 0.4137539267539978, "learning_rate": 0.0002, "epoch": 2.219482120838471, "step": 1800}, {"loss": 0.7266, "grad_norm": 0.44995415210723877, "learning_rate": 0.0002, "epoch": 2.2318125770653516, "step": 1810}, {"loss": 0.7663, "grad_norm": 0.5985036492347717, "learning_rate": 0.0002, "epoch": 2.244143033292232, "step": 1820}, {"loss": 0.7502, "grad_norm": 0.7549490332603455, "learning_rate": 0.0002, "epoch": 2.256473489519112, "step": 1830}, {"loss": 0.7452, "grad_norm": 0.4490937888622284, "learning_rate": 0.0002, "epoch": 2.2688039457459928, "step": 1840}, {"loss": 0.7531, "grad_norm": 0.38859808444976807, "learning_rate": 0.0002, "epoch": 2.281134401972873, "step": 1850}, {"loss": 0.7278, "grad_norm": 1.0704916715621948, "learning_rate": 0.0002, "epoch": 2.293464858199753, "step": 1860}, {"loss": 0.7143, "grad_norm": 0.4647100865840912, "learning_rate": 0.0002, "epoch": 2.305795314426634, "step": 1870}, {"loss": 0.7146, "grad_norm": 0.6181163787841797, "learning_rate": 0.0002, "epoch": 2.318125770653514, "step": 1880}, {"loss": 0.7689, "grad_norm": 0.9241904020309448, "learning_rate": 0.0002, "epoch": 2.3304562268803943, "step": 1890}, {"loss": 0.7294, "grad_norm": 0.39101317524909973, "learning_rate": 0.0002, "epoch": 2.342786683107275, "step": 1900}, {"loss": 0.7079, "grad_norm": 0.49442458152770996, "learning_rate": 0.0002, "epoch": 2.3551171393341552, "step": 1910}, {"loss": 0.7586, "grad_norm": 0.4864824414253235, "learning_rate": 0.0002, "epoch": 2.367447595561036, "step": 1920}, {"loss": 0.7434, "grad_norm": 0.5427613854408264, "learning_rate": 0.0002, "epoch": 2.379778051787916, "step": 1930}, {"loss": 0.8423, "grad_norm": 0.7164974808692932, "learning_rate": 0.0002, "epoch": 2.392108508014797, "step": 1940}, {"loss": 0.6888, "grad_norm": 0.562979519367218, "learning_rate": 0.0002, "epoch": 2.404438964241677, "step": 1950}, {"loss": 0.7692, "grad_norm": 0.5631861090660095, "learning_rate": 0.0002, "epoch": 2.4167694204685573, "step": 1960}, {"loss": 0.67, "grad_norm": 0.4895121157169342, "learning_rate": 0.0002, "epoch": 2.429099876695438, "step": 1970}, {"loss": 0.7735, "grad_norm": 0.45674824714660645, "learning_rate": 0.0002, "epoch": 2.441430332922318, "step": 1980}, {"loss": 0.685, "grad_norm": 1.1424206495285034, "learning_rate": 0.0002, "epoch": 2.4537607891491984, "step": 1990}, {"loss": 0.7627, "grad_norm": 0.6314579844474792, "learning_rate": 0.0002, "epoch": 2.466091245376079, "step": 2000}, {"loss": 0.7118, "grad_norm": 0.5481605529785156, "learning_rate": 0.0002, "epoch": 2.4784217016029593, "step": 2010}, {"loss": 0.6947, "grad_norm": 0.4671579599380493, "learning_rate": 0.0002, "epoch": 2.4907521578298395, "step": 2020}, {"loss": 0.7377, "grad_norm": 0.7621194124221802, "learning_rate": 0.0002, "epoch": 2.50308261405672, "step": 2030}, {"loss": 0.69, "grad_norm": 0.38983288407325745, "learning_rate": 0.0002, "epoch": 2.5154130702836004, "step": 2040}, {"loss": 0.8381, "grad_norm": 0.6341150999069214, "learning_rate": 0.0002, "epoch": 2.5277435265104806, "step": 2050}, {"loss": 0.773, "grad_norm": 0.7151971459388733, "learning_rate": 0.0002, "epoch": 2.5400739827373613, "step": 2060}, {"loss": 0.6733, "grad_norm": 0.9665895104408264, "learning_rate": 0.0002, "epoch": 2.5524044389642415, "step": 2070}, {"loss": 0.7791, "grad_norm": 0.9572727680206299, "learning_rate": 0.0002, "epoch": 2.564734895191122, "step": 2080}, {"loss": 0.7205, "grad_norm": 1.1970765590667725, "learning_rate": 0.0002, "epoch": 2.5770653514180024, "step": 2090}, {"loss": 0.6736, "grad_norm": 0.5505942702293396, "learning_rate": 0.0002, "epoch": 2.589395807644883, "step": 2100}, {"loss": 0.673, "grad_norm": 0.5903949737548828, "learning_rate": 0.0002, "epoch": 2.6017262638717633, "step": 2110}, {"loss": 0.678, "grad_norm": 0.45640307664871216, "learning_rate": 0.0002, "epoch": 2.6140567200986435, "step": 2120}, {"loss": 0.6562, "grad_norm": 0.8763944506645203, "learning_rate": 0.0002, "epoch": 2.626387176325524, "step": 2130}, {"loss": 0.6484, "grad_norm": 0.4472963213920593, "learning_rate": 0.0002, "epoch": 2.6387176325524044, "step": 2140}, {"loss": 0.7702, "grad_norm": 0.5335086584091187, "learning_rate": 0.0002, "epoch": 2.6510480887792847, "step": 2150}, {"loss": 0.6851, "grad_norm": 0.805263340473175, "learning_rate": 0.0002, "epoch": 2.6633785450061653, "step": 2160}, {"loss": 0.7026, "grad_norm": 0.6332727670669556, "learning_rate": 0.0002, "epoch": 2.6757090012330456, "step": 2170}, {"loss": 0.7925, "grad_norm": 0.8667435646057129, "learning_rate": 0.0002, "epoch": 2.688039457459926, "step": 2180}, {"loss": 0.8044, "grad_norm": 0.5638955235481262, "learning_rate": 0.0002, "epoch": 2.7003699136868065, "step": 2190}, {"loss": 0.7117, "grad_norm": 0.4176250696182251, "learning_rate": 0.0002, "epoch": 2.7127003699136867, "step": 2200}, {"loss": 0.6932, "grad_norm": 0.6013461351394653, "learning_rate": 0.0002, "epoch": 2.7250308261405674, "step": 2210}, {"loss": 0.7843, "grad_norm": 0.553961992263794, "learning_rate": 0.0002, "epoch": 2.7373612823674476, "step": 2220}, {"loss": 0.8633, "grad_norm": 0.4710180461406708, "learning_rate": 0.0002, "epoch": 2.7496917385943282, "step": 2230}, {"loss": 0.7469, "grad_norm": 0.8141706585884094, "learning_rate": 0.0002, "epoch": 2.7620221948212085, "step": 2240}, {"loss": 0.7086, "grad_norm": 0.7449556589126587, "learning_rate": 0.0002, "epoch": 2.7743526510480887, "step": 2250}, {"loss": 0.6933, "grad_norm": 0.5366780757904053, "learning_rate": 0.0002, "epoch": 2.7866831072749694, "step": 2260}, {"loss": 0.7192, "grad_norm": 0.5316720604896545, "learning_rate": 0.0002, "epoch": 2.7990135635018496, "step": 2270}, {"loss": 0.6212, "grad_norm": 0.4598459005355835, "learning_rate": 0.0002, "epoch": 2.81134401972873, "step": 2280}, {"loss": 0.7024, "grad_norm": 0.6852091550827026, "learning_rate": 0.0002, "epoch": 2.8236744759556105, "step": 2290}, {"loss": 0.7357, "grad_norm": 0.8040902018547058, "learning_rate": 0.0002, "epoch": 2.8360049321824907, "step": 2300}, {"loss": 0.7563, "grad_norm": 0.46976321935653687, "learning_rate": 0.0002, "epoch": 2.848335388409371, "step": 2310}, {"loss": 0.731, "grad_norm": 0.5214090347290039, "learning_rate": 0.0002, "epoch": 2.8606658446362516, "step": 2320}, {"loss": 0.6687, "grad_norm": 0.5323054790496826, "learning_rate": 0.0002, "epoch": 2.872996300863132, "step": 2330}, {"loss": 0.7895, "grad_norm": 0.6842264533042908, "learning_rate": 0.0002, "epoch": 2.885326757090012, "step": 2340}, {"loss": 0.7737, "grad_norm": 0.9157055616378784, "learning_rate": 0.0002, "epoch": 2.8976572133168927, "step": 2350}, {"loss": 0.7217, "grad_norm": 0.5253258347511292, "learning_rate": 0.0002, "epoch": 2.909987669543773, "step": 2360}, {"loss": 0.7162, "grad_norm": 0.4937705099582672, "learning_rate": 0.0002, "epoch": 2.9223181257706536, "step": 2370}, {"loss": 0.7008, "grad_norm": 0.48762989044189453, "learning_rate": 0.0002, "epoch": 2.934648581997534, "step": 2380}, {"loss": 0.8086, "grad_norm": 0.544335126876831, "learning_rate": 0.0002, "epoch": 2.9469790382244145, "step": 2390}, {"loss": 0.643, "grad_norm": 0.4847845435142517, "learning_rate": 0.0002, "epoch": 2.9593094944512948, "step": 2400}, {"loss": 0.7757, "grad_norm": 0.4787445366382599, "learning_rate": 0.0002, "epoch": 2.971639950678175, "step": 2410}, {"loss": 0.7678, "grad_norm": 1.022318959236145, "learning_rate": 0.0002, "epoch": 2.9839704069050557, "step": 2420}, {"loss": 0.6548, "grad_norm": 0.4987848103046417, "learning_rate": 0.0002, "epoch": 2.996300863131936, "step": 2430}, {"eval_loss": 1.2936296463012695, "eval_runtime": 94.7897, "eval_samples_per_second": 4.6, "eval_steps_per_second": 0.58, "epoch": 3.0, "step": 2433}, {"loss": 0.6073, "grad_norm": 0.5562372803688049, "learning_rate": 0.0002, "epoch": 3.008631319358816, "step": 2440}, {"loss": 0.5181, "grad_norm": 1.133402705192566, "learning_rate": 0.0002, "epoch": 3.020961775585697, "step": 2450}, {"loss": 0.5333, "grad_norm": 0.6480470299720764, "learning_rate": 0.0002, "epoch": 3.033292231812577, "step": 2460}, {"loss": 0.4828, "grad_norm": 0.8989138007164001, "learning_rate": 0.0002, "epoch": 3.0456226880394572, "step": 2470}, {"loss": 0.5097, "grad_norm": 0.8257461786270142, "learning_rate": 0.0002, "epoch": 3.057953144266338, "step": 2480}, {"loss": 0.6229, "grad_norm": 0.6813381910324097, "learning_rate": 0.0002, "epoch": 3.070283600493218, "step": 2490}, {"loss": 0.531, "grad_norm": 0.6989586353302002, "learning_rate": 0.0002, "epoch": 3.082614056720099, "step": 2500}, {"loss": 0.54, "grad_norm": 0.7992092967033386, "learning_rate": 0.0002, "epoch": 3.094944512946979, "step": 2510}, {"loss": 0.5054, "grad_norm": 0.698077917098999, "learning_rate": 0.0002, "epoch": 3.1072749691738593, "step": 2520}, {"loss": 0.5064, "grad_norm": 0.5699033141136169, "learning_rate": 0.0002, "epoch": 3.11960542540074, "step": 2530}, {"loss": 0.6088, "grad_norm": 0.6142355799674988, "learning_rate": 0.0002, "epoch": 3.13193588162762, "step": 2540}, {"loss": 0.585, "grad_norm": 0.7089933753013611, "learning_rate": 0.0002, "epoch": 3.144266337854501, "step": 2550}, {"loss": 0.5373, "grad_norm": 1.0107015371322632, "learning_rate": 0.0002, "epoch": 3.156596794081381, "step": 2560}, {"loss": 0.5429, "grad_norm": 0.568138837814331, "learning_rate": 0.0002, "epoch": 3.1689272503082613, "step": 2570}, {"loss": 0.5897, "grad_norm": 0.9960416555404663, "learning_rate": 0.0002, "epoch": 3.181257706535142, "step": 2580}, {"loss": 0.5211, "grad_norm": 0.6277595162391663, "learning_rate": 0.0002, "epoch": 3.193588162762022, "step": 2590}, {"loss": 0.5787, "grad_norm": 0.681083619594574, "learning_rate": 0.0002, "epoch": 3.2059186189889024, "step": 2600}, {"loss": 0.5166, "grad_norm": 0.5816057324409485, "learning_rate": 0.0002, "epoch": 3.218249075215783, "step": 2610}, {"loss": 0.545, "grad_norm": 0.7197734117507935, "learning_rate": 0.0002, "epoch": 3.2305795314426633, "step": 2620}, {"loss": 0.614, "grad_norm": 0.6524068117141724, "learning_rate": 0.0002, "epoch": 3.242909987669544, "step": 2630}, {"loss": 0.5456, "grad_norm": 1.273668646812439, "learning_rate": 0.0002, "epoch": 3.255240443896424, "step": 2640}, {"loss": 0.5266, "grad_norm": 0.6950451731681824, "learning_rate": 0.0002, "epoch": 3.2675709001233044, "step": 2650}, {"loss": 0.5194, "grad_norm": 0.8029071688652039, "learning_rate": 0.0002, "epoch": 3.279901356350185, "step": 2660}, {"loss": 0.5729, "grad_norm": 0.7464073896408081, "learning_rate": 0.0002, "epoch": 3.2922318125770653, "step": 2670}, {"loss": 0.5366, "grad_norm": 0.8342001438140869, "learning_rate": 0.0002, "epoch": 3.304562268803946, "step": 2680}, {"loss": 0.5413, "grad_norm": 0.5629868507385254, "learning_rate": 0.0002, "epoch": 3.316892725030826, "step": 2690}, {"loss": 0.633, "grad_norm": 0.753999650478363, "learning_rate": 0.0002, "epoch": 3.3292231812577064, "step": 2700}, {"loss": 0.5048, "grad_norm": 1.0271371603012085, "learning_rate": 0.0002, "epoch": 3.341553637484587, "step": 2710}, {"loss": 0.5233, "grad_norm": 0.9608535170555115, "learning_rate": 0.0002, "epoch": 3.3538840937114673, "step": 2720}, {"loss": 0.5102, "grad_norm": 0.7796488404273987, "learning_rate": 0.0002, "epoch": 3.3662145499383476, "step": 2730}, {"loss": 0.5172, "grad_norm": 0.5666437149047852, "learning_rate": 0.0002, "epoch": 3.3785450061652282, "step": 2740}, {"loss": 0.491, "grad_norm": 0.5462956428527832, "learning_rate": 0.0002, "epoch": 3.3908754623921085, "step": 2750}, {"loss": 0.5855, "grad_norm": 1.289099097251892, "learning_rate": 0.0002, "epoch": 3.4032059186189887, "step": 2760}, {"loss": 0.635, "grad_norm": 0.825566828250885, "learning_rate": 0.0002, "epoch": 3.4155363748458694, "step": 2770}, {"loss": 0.4998, "grad_norm": 0.8366670608520508, "learning_rate": 0.0002, "epoch": 3.4278668310727496, "step": 2780}, {"loss": 0.5732, "grad_norm": 1.0931549072265625, "learning_rate": 0.0002, "epoch": 3.4401972872996303, "step": 2790}, {"loss": 0.6093, "grad_norm": 0.9228858351707458, "learning_rate": 0.0002, "epoch": 3.4525277435265105, "step": 2800}, {"loss": 0.6089, "grad_norm": 1.3182806968688965, "learning_rate": 0.0002, "epoch": 3.4648581997533907, "step": 2810}, {"loss": 0.5665, "grad_norm": 0.8366976380348206, "learning_rate": 0.0002, "epoch": 3.4771886559802714, "step": 2820}, {"loss": 0.5666, "grad_norm": 0.8067695498466492, "learning_rate": 0.0002, "epoch": 3.4895191122071516, "step": 2830}, {"loss": 0.579, "grad_norm": 1.1163437366485596, "learning_rate": 0.0002, "epoch": 3.5018495684340323, "step": 2840}, {"loss": 0.5785, "grad_norm": 1.7196556329727173, "learning_rate": 0.0002, "epoch": 3.5141800246609125, "step": 2850}, {"loss": 0.5346, "grad_norm": 1.1267012357711792, "learning_rate": 0.0002, "epoch": 3.5265104808877927, "step": 2860}, {"loss": 0.447, "grad_norm": 0.7220137119293213, "learning_rate": 0.0002, "epoch": 3.5388409371146734, "step": 2870}, {"loss": 0.6099, "grad_norm": 0.914114773273468, "learning_rate": 0.0002, "epoch": 3.5511713933415536, "step": 2880}, {"loss": 0.6143, "grad_norm": 0.6193503141403198, "learning_rate": 0.0002, "epoch": 3.563501849568434, "step": 2890}, {"loss": 0.5171, "grad_norm": 0.6060135960578918, "learning_rate": 0.0002, "epoch": 3.5758323057953145, "step": 2900}, {"loss": 0.5659, "grad_norm": 1.0177327394485474, "learning_rate": 0.0002, "epoch": 3.5881627620221948, "step": 2910}, {"loss": 0.5711, "grad_norm": 0.5994468331336975, "learning_rate": 0.0002, "epoch": 3.600493218249075, "step": 2920}, {"loss": 0.6373, "grad_norm": 0.7450457215309143, "learning_rate": 0.0002, "epoch": 3.6128236744759556, "step": 2930}, {"loss": 0.4933, "grad_norm": 0.5825870037078857, "learning_rate": 0.0002, "epoch": 3.625154130702836, "step": 2940}, {"loss": 0.6016, "grad_norm": 0.6289743781089783, "learning_rate": 0.0002, "epoch": 3.6374845869297165, "step": 2950}, {"loss": 0.5507, "grad_norm": 0.7801929116249084, "learning_rate": 0.0002, "epoch": 3.6498150431565968, "step": 2960}, {"loss": 0.5695, "grad_norm": 1.1206634044647217, "learning_rate": 0.0002, "epoch": 3.6621454993834774, "step": 2970}, {"loss": 0.4985, "grad_norm": 0.6738817691802979, "learning_rate": 0.0002, "epoch": 3.6744759556103577, "step": 2980}, {"loss": 0.6209, "grad_norm": 1.1917344331741333, "learning_rate": 0.0002, "epoch": 3.686806411837238, "step": 2990}, {"loss": 0.5373, "grad_norm": 1.3738657236099243, "learning_rate": 0.0002, "epoch": 3.6991368680641186, "step": 3000}, {"loss": 0.5467, "grad_norm": 0.6642793416976929, "learning_rate": 0.0002, "epoch": 3.711467324290999, "step": 3010}, {"loss": 0.6243, "grad_norm": 0.9030995965003967, "learning_rate": 0.0002, "epoch": 3.723797780517879, "step": 3020}, {"loss": 0.592, "grad_norm": 1.0203914642333984, "learning_rate": 0.0002, "epoch": 3.7361282367447597, "step": 3030}, {"loss": 0.5453, "grad_norm": 0.648394763469696, "learning_rate": 0.0002, "epoch": 3.74845869297164, "step": 3040}, {"loss": 0.498, "grad_norm": 0.6304570436477661, "learning_rate": 0.0002, "epoch": 3.76078914919852, "step": 3050}, {"loss": 0.683, "grad_norm": 0.8286601901054382, "learning_rate": 0.0002, "epoch": 3.773119605425401, "step": 3060}, {"loss": 0.5302, "grad_norm": 0.906444251537323, "learning_rate": 0.0002, "epoch": 3.785450061652281, "step": 3070}, {"loss": 0.5345, "grad_norm": 1.4212149381637573, "learning_rate": 0.0002, "epoch": 3.7977805178791613, "step": 3080}, {"loss": 0.6403, "grad_norm": 0.7574319839477539, "learning_rate": 0.0002, "epoch": 3.810110974106042, "step": 3090}, {"loss": 0.5756, "grad_norm": 0.6534451246261597, "learning_rate": 0.0002, "epoch": 3.822441430332922, "step": 3100}, {"loss": 0.5306, "grad_norm": 0.7525447010993958, "learning_rate": 0.0002, "epoch": 3.834771886559803, "step": 3110}, {"loss": 0.5368, "grad_norm": 0.6513990759849548, "learning_rate": 0.0002, "epoch": 3.847102342786683, "step": 3120}, {"loss": 0.5492, "grad_norm": 0.7782694697380066, "learning_rate": 0.0002, "epoch": 3.8594327990135637, "step": 3130}, {"loss": 0.5727, "grad_norm": 0.7998530268669128, "learning_rate": 0.0002, "epoch": 3.871763255240444, "step": 3140}, {"loss": 0.5156, "grad_norm": 0.8045353293418884, "learning_rate": 0.0002, "epoch": 3.884093711467324, "step": 3150}, {"loss": 0.5341, "grad_norm": 0.8242645263671875, "learning_rate": 0.0002, "epoch": 3.896424167694205, "step": 3160}, {"loss": 0.5563, "grad_norm": 0.8302360773086548, "learning_rate": 0.0002, "epoch": 3.908754623921085, "step": 3170}, {"loss": 0.5793, "grad_norm": 0.8653109073638916, "learning_rate": 0.0002, "epoch": 3.9210850801479653, "step": 3180}, {"loss": 0.5219, "grad_norm": 0.6461338996887207, "learning_rate": 0.0002, "epoch": 3.933415536374846, "step": 3190}, {"loss": 0.6009, "grad_norm": 0.8267415165901184, "learning_rate": 0.0002, "epoch": 3.945745992601726, "step": 3200}, {"loss": 0.5956, "grad_norm": 1.1963194608688354, "learning_rate": 0.0002, "epoch": 3.9580764488286064, "step": 3210}, {"loss": 0.5692, "grad_norm": 0.7101966142654419, "learning_rate": 0.0002, "epoch": 3.970406905055487, "step": 3220}, {"loss": 0.5471, "grad_norm": 0.5931660532951355, "learning_rate": 0.0002, "epoch": 3.9827373612823673, "step": 3230}, {"loss": 0.5619, "grad_norm": 0.7465988993644714, "learning_rate": 0.0002, "epoch": 3.995067817509248, "step": 3240}, {"eval_loss": 1.4066498279571533, "eval_runtime": 95.7145, "eval_samples_per_second": 4.555, "eval_steps_per_second": 0.575, "epoch": 4.0, "step": 3244}, {"loss": 0.4948, "grad_norm": 0.9478800296783447, "learning_rate": 0.0002, "epoch": 4.007398273736128, "step": 3250}, {"loss": 0.4129, "grad_norm": 1.207059621810913, "learning_rate": 0.0002, "epoch": 4.019728729963009, "step": 3260}, {"loss": 0.3577, "grad_norm": 0.8984074592590332, "learning_rate": 0.0002, "epoch": 4.032059186189889, "step": 3270}, {"loss": 0.3798, "grad_norm": 0.8104140758514404, "learning_rate": 0.0002, "epoch": 4.044389642416769, "step": 3280}, {"loss": 0.3657, "grad_norm": 1.0875468254089355, "learning_rate": 0.0002, "epoch": 4.05672009864365, "step": 3290}, {"loss": 0.3703, "grad_norm": 0.8520309329032898, "learning_rate": 0.0002, "epoch": 4.06905055487053, "step": 3300}, {"loss": 0.3933, "grad_norm": 1.076735496520996, "learning_rate": 0.0002, "epoch": 4.0813810110974105, "step": 3310}, {"loss": 0.4422, "grad_norm": 0.7789369821548462, "learning_rate": 0.0002, "epoch": 4.093711467324291, "step": 3320}, {"loss": 0.4009, "grad_norm": 0.916862964630127, "learning_rate": 0.0002, "epoch": 4.106041923551172, "step": 3330}, {"loss": 0.3934, "grad_norm": 1.1251654624938965, "learning_rate": 0.0002, "epoch": 4.118372379778052, "step": 3340}, {"loss": 0.3651, "grad_norm": 0.9373420476913452, "learning_rate": 0.0002, "epoch": 4.130702836004932, "step": 3350}, {"loss": 0.384, "grad_norm": 1.03253972530365, "learning_rate": 0.0002, "epoch": 4.143033292231813, "step": 3360}, {"loss": 0.372, "grad_norm": 0.947023332118988, "learning_rate": 0.0002, "epoch": 4.155363748458693, "step": 3370}, {"loss": 0.4018, "grad_norm": 0.8709157109260559, "learning_rate": 0.0002, "epoch": 4.167694204685573, "step": 3380}, {"loss": 0.3754, "grad_norm": 0.930983304977417, "learning_rate": 0.0002, "epoch": 4.180024660912454, "step": 3390}, {"loss": 0.4248, "grad_norm": 1.092809796333313, "learning_rate": 0.0002, "epoch": 4.192355117139334, "step": 3400}, {"loss": 0.4453, "grad_norm": 0.8454303741455078, "learning_rate": 0.0002, "epoch": 4.2046855733662145, "step": 3410}, {"loss": 0.4198, "grad_norm": 0.957210123538971, "learning_rate": 0.0002, "epoch": 4.217016029593095, "step": 3420}, {"loss": 0.3743, "grad_norm": 0.854333758354187, "learning_rate": 0.0002, "epoch": 4.229346485819975, "step": 3430}, {"loss": 0.4041, "grad_norm": 1.0457639694213867, "learning_rate": 0.0002, "epoch": 4.241676942046856, "step": 3440}, {"loss": 0.3817, "grad_norm": 0.8972977995872498, "learning_rate": 0.0002, "epoch": 4.254007398273736, "step": 3450}, {"loss": 0.4445, "grad_norm": 1.0438238382339478, "learning_rate": 0.0002, "epoch": 4.266337854500616, "step": 3460}, {"loss": 0.4078, "grad_norm": 0.7000405192375183, "learning_rate": 0.0002, "epoch": 4.278668310727497, "step": 3470}, {"loss": 0.3718, "grad_norm": 1.0451240539550781, "learning_rate": 0.0002, "epoch": 4.290998766954377, "step": 3480}, {"loss": 0.4506, "grad_norm": 1.3339767456054688, "learning_rate": 0.0002, "epoch": 4.303329223181258, "step": 3490}, {"loss": 0.3999, "grad_norm": 0.7503946423530579, "learning_rate": 0.0002, "epoch": 4.315659679408138, "step": 3500}, {"loss": 0.4503, "grad_norm": 0.8443584442138672, "learning_rate": 0.0002, "epoch": 4.3279901356350186, "step": 3510}, {"loss": 0.3793, "grad_norm": 1.1681201457977295, "learning_rate": 0.0002, "epoch": 4.340320591861899, "step": 3520}, {"loss": 0.4462, "grad_norm": 1.078883171081543, "learning_rate": 0.0002, "epoch": 4.352651048088779, "step": 3530}, {"loss": 0.4216, "grad_norm": 0.6894834041595459, "learning_rate": 0.0002, "epoch": 4.36498150431566, "step": 3540}, {"loss": 0.4315, "grad_norm": 0.7059480547904968, "learning_rate": 0.0002, "epoch": 4.37731196054254, "step": 3550}, {"loss": 0.3821, "grad_norm": 1.1807256937026978, "learning_rate": 0.0002, "epoch": 4.38964241676942, "step": 3560}, {"loss": 0.4192, "grad_norm": 0.8341359496116638, "learning_rate": 0.0002, "epoch": 4.401972872996301, "step": 3570}, {"loss": 0.4123, "grad_norm": 1.0273033380508423, "learning_rate": 0.0002, "epoch": 4.4143033292231815, "step": 3580}, {"loss": 0.5018, "grad_norm": 0.6916454434394836, "learning_rate": 0.0002, "epoch": 4.426633785450061, "step": 3590}, {"loss": 0.3909, "grad_norm": 0.8210113644599915, "learning_rate": 0.0002, "epoch": 4.438964241676942, "step": 3600}, {"loss": 0.3893, "grad_norm": 1.0309500694274902, "learning_rate": 0.0002, "epoch": 4.451294697903823, "step": 3610}, {"loss": 0.3902, "grad_norm": 0.8847399353981018, "learning_rate": 0.0002, "epoch": 4.463625154130703, "step": 3620}, {"loss": 0.4198, "grad_norm": 1.668636679649353, "learning_rate": 0.0002, "epoch": 4.475955610357583, "step": 3630}, {"loss": 0.4075, "grad_norm": 1.3087958097457886, "learning_rate": 0.0002, "epoch": 4.488286066584464, "step": 3640}, {"loss": 0.4294, "grad_norm": 0.837852418422699, "learning_rate": 0.0002, "epoch": 4.500616522811344, "step": 3650}, {"loss": 0.4053, "grad_norm": 9.7662353515625, "learning_rate": 0.0002, "epoch": 4.512946979038224, "step": 3660}, {"loss": 0.4033, "grad_norm": 1.125719428062439, "learning_rate": 0.0002, "epoch": 4.525277435265105, "step": 3670}, {"loss": 0.4566, "grad_norm": 0.7755377292633057, "learning_rate": 0.0002, "epoch": 4.5376078914919855, "step": 3680}, {"loss": 0.4415, "grad_norm": 0.7185089588165283, "learning_rate": 0.0002, "epoch": 4.549938347718865, "step": 3690}, {"loss": 0.4616, "grad_norm": 1.182063102722168, "learning_rate": 0.0002, "epoch": 4.562268803945746, "step": 3700}, {"loss": 0.4572, "grad_norm": 1.001197338104248, "learning_rate": 0.0002, "epoch": 4.574599260172627, "step": 3710}, {"loss": 0.4493, "grad_norm": 0.9705429077148438, "learning_rate": 0.0002, "epoch": 4.586929716399506, "step": 3720}, {"loss": 0.42, "grad_norm": 0.7136746048927307, "learning_rate": 0.0002, "epoch": 4.599260172626387, "step": 3730}, {"loss": 0.3757, "grad_norm": 1.0004864931106567, "learning_rate": 0.0002, "epoch": 4.611590628853268, "step": 3740}, {"loss": 0.4418, "grad_norm": 1.3193715810775757, "learning_rate": 0.0002, "epoch": 4.623921085080148, "step": 3750}, {"loss": 0.4572, "grad_norm": 0.6945042014122009, "learning_rate": 0.0002, "epoch": 4.636251541307028, "step": 3760}, {"loss": 0.4255, "grad_norm": 0.8903936743736267, "learning_rate": 0.0002, "epoch": 4.648581997533909, "step": 3770}, {"loss": 0.3582, "grad_norm": 0.7960889339447021, "learning_rate": 0.0002, "epoch": 4.660912453760789, "step": 3780}, {"loss": 0.3864, "grad_norm": 1.0439172983169556, "learning_rate": 0.0002, "epoch": 4.673242909987669, "step": 3790}, {"loss": 0.4378, "grad_norm": 1.4546219110488892, "learning_rate": 0.0002, "epoch": 4.68557336621455, "step": 3800}, {"loss": 0.4191, "grad_norm": 0.8194343447685242, "learning_rate": 0.0002, "epoch": 4.697903822441431, "step": 3810}, {"loss": 0.4473, "grad_norm": 1.0727602243423462, "learning_rate": 0.0002, "epoch": 4.7102342786683105, "step": 3820}, {"loss": 0.4021, "grad_norm": 0.7785195708274841, "learning_rate": 0.0002, "epoch": 4.722564734895191, "step": 3830}, {"loss": 0.4252, "grad_norm": 0.846783459186554, "learning_rate": 0.0002, "epoch": 4.734895191122072, "step": 3840}, {"loss": 0.4647, "grad_norm": 1.0481648445129395, "learning_rate": 0.0002, "epoch": 4.747225647348952, "step": 3850}, {"loss": 0.4944, "grad_norm": 0.7324008941650391, "learning_rate": 0.0002, "epoch": 4.759556103575832, "step": 3860}, {"loss": 0.3831, "grad_norm": 1.06382417678833, "learning_rate": 0.0002, "epoch": 4.771886559802713, "step": 3870}, {"loss": 0.3934, "grad_norm": 0.9851241111755371, "learning_rate": 0.0002, "epoch": 4.784217016029594, "step": 3880}, {"loss": 0.5172, "grad_norm": 0.8215277791023254, "learning_rate": 0.0002, "epoch": 4.796547472256473, "step": 3890}, {"loss": 0.4437, "grad_norm": 0.9901723861694336, "learning_rate": 0.0002, "epoch": 4.808877928483354, "step": 3900}, {"loss": 0.4673, "grad_norm": 0.9149112701416016, "learning_rate": 0.0002, "epoch": 4.821208384710234, "step": 3910}, {"loss": 0.4295, "grad_norm": 0.9772973656654358, "learning_rate": 0.0002, "epoch": 4.8335388409371145, "step": 3920}, {"loss": 0.4346, "grad_norm": 0.8889636397361755, "learning_rate": 0.0002, "epoch": 4.845869297163995, "step": 3930}, {"loss": 0.421, "grad_norm": 1.3032807111740112, "learning_rate": 0.0002, "epoch": 4.858199753390876, "step": 3940}, {"loss": 0.434, "grad_norm": 0.8575899600982666, "learning_rate": 0.0002, "epoch": 4.870530209617756, "step": 3950}, {"loss": 0.4295, "grad_norm": 1.04326331615448, "learning_rate": 0.0002, "epoch": 4.882860665844636, "step": 3960}, {"loss": 0.3633, "grad_norm": 1.041210651397705, "learning_rate": 0.0002, "epoch": 4.895191122071517, "step": 3970}, {"loss": 0.4104, "grad_norm": 0.9113056063652039, "learning_rate": 0.0002, "epoch": 4.907521578298397, "step": 3980}, {"loss": 0.4496, "grad_norm": 1.019347906112671, "learning_rate": 0.0002, "epoch": 4.919852034525277, "step": 3990}, {"loss": 0.457, "grad_norm": 0.7709218859672546, "learning_rate": 0.0002, "epoch": 4.932182490752158, "step": 4000}, {"loss": 0.4697, "grad_norm": 0.8891775608062744, "learning_rate": 0.0002, "epoch": 4.944512946979038, "step": 4010}, {"loss": 0.4436, "grad_norm": 1.0396920442581177, "learning_rate": 0.0002, "epoch": 4.9568434032059185, "step": 4020}, {"loss": 0.4251, "grad_norm": 0.9239833354949951, "learning_rate": 0.0002, "epoch": 4.969173859432799, "step": 4030}, {"loss": 0.5049, "grad_norm": 1.801400065422058, "learning_rate": 0.0002, "epoch": 4.981504315659679, "step": 4040}, {"loss": 0.4481, "grad_norm": 0.6194164752960205, "learning_rate": 0.0002, "epoch": 4.99383477188656, "step": 4050}, {"eval_loss": 1.544758915901184, "eval_runtime": 96.2573, "eval_samples_per_second": 4.53, "eval_steps_per_second": 0.571, "epoch": 5.0, "step": 4055}, {"loss": 0.3774, "grad_norm": 0.9918256998062134, "learning_rate": 0.0002, "epoch": 5.00616522811344, "step": 4060}, {"loss": 0.2887, "grad_norm": 1.4851351976394653, "learning_rate": 0.0002, "epoch": 5.018495684340321, "step": 4070}, {"loss": 0.2454, "grad_norm": 0.9237686395645142, "learning_rate": 0.0002, "epoch": 5.030826140567201, "step": 4080}, {"loss": 0.3072, "grad_norm": 1.2180852890014648, "learning_rate": 0.0002, "epoch": 5.0431565967940815, "step": 4090}, {"loss": 0.282, "grad_norm": 1.1247979402542114, "learning_rate": 0.0002, "epoch": 5.055487053020962, "step": 4100}, {"loss": 0.3108, "grad_norm": 1.2969884872436523, "learning_rate": 0.0002, "epoch": 5.067817509247842, "step": 4110}, {"loss": 0.2858, "grad_norm": 1.0183063745498657, "learning_rate": 0.0002, "epoch": 5.080147965474723, "step": 4120}, {"loss": 0.295, "grad_norm": 1.121330738067627, "learning_rate": 0.0002, "epoch": 5.092478421701603, "step": 4130}, {"loss": 0.2697, "grad_norm": 1.0748186111450195, "learning_rate": 0.0002, "epoch": 5.104808877928483, "step": 4140}, {"loss": 0.3414, "grad_norm": 1.103474736213684, "learning_rate": 0.0002, "epoch": 5.117139334155364, "step": 4150}, {"loss": 0.305, "grad_norm": 1.2251166105270386, "learning_rate": 0.0002, "epoch": 5.129469790382244, "step": 4160}, {"loss": 0.3131, "grad_norm": 0.920898973941803, "learning_rate": 0.0002, "epoch": 5.141800246609124, "step": 4170}, {"loss": 0.281, "grad_norm": 1.327542781829834, "learning_rate": 0.0002, "epoch": 5.154130702836005, "step": 4180}, {"loss": 0.3214, "grad_norm": 1.0677192211151123, "learning_rate": 0.0002, "epoch": 5.1664611590628855, "step": 4190}, {"loss": 0.2863, "grad_norm": 0.897241473197937, "learning_rate": 0.0002, "epoch": 5.178791615289766, "step": 4200}, {"loss": 0.2967, "grad_norm": 0.977457582950592, "learning_rate": 0.0002, "epoch": 5.191122071516646, "step": 4210}, {"loss": 0.3032, "grad_norm": 1.4115267992019653, "learning_rate": 0.0002, "epoch": 5.203452527743527, "step": 4220}, {"loss": 0.3279, "grad_norm": 1.097743034362793, "learning_rate": 0.0002, "epoch": 5.215782983970407, "step": 4230}, {"loss": 0.293, "grad_norm": 1.1095269918441772, "learning_rate": 0.0002, "epoch": 5.228113440197287, "step": 4240}, {"loss": 0.3544, "grad_norm": 1.3785479068756104, "learning_rate": 0.0002, "epoch": 5.240443896424168, "step": 4250}, {"loss": 0.3118, "grad_norm": 1.0298776626586914, "learning_rate": 0.0002, "epoch": 5.252774352651048, "step": 4260}, {"loss": 0.296, "grad_norm": 1.1592111587524414, "learning_rate": 0.0002, "epoch": 5.265104808877928, "step": 4270}, {"loss": 0.2878, "grad_norm": 1.2355743646621704, "learning_rate": 0.0002, "epoch": 5.277435265104809, "step": 4280}, {"loss": 0.3085, "grad_norm": 0.8543112874031067, "learning_rate": 0.0002, "epoch": 5.2897657213316895, "step": 4290}, {"loss": 0.3108, "grad_norm": 1.2953215837478638, "learning_rate": 0.0002, "epoch": 5.302096177558569, "step": 4300}, {"loss": 0.2912, "grad_norm": 1.1001787185668945, "learning_rate": 0.0002, "epoch": 5.31442663378545, "step": 4310}, {"loss": 0.3003, "grad_norm": 0.7476816773414612, "learning_rate": 0.0002, "epoch": 5.326757090012331, "step": 4320}, {"loss": 0.3247, "grad_norm": 0.8195574283599854, "learning_rate": 0.0002, "epoch": 5.3390875462392104, "step": 4330}, {"loss": 0.3035, "grad_norm": 0.9490262866020203, "learning_rate": 0.0002, "epoch": 5.351418002466091, "step": 4340}, {"loss": 0.2846, "grad_norm": 1.2201412916183472, "learning_rate": 0.0002, "epoch": 5.363748458692972, "step": 4350}, {"loss": 0.2644, "grad_norm": 1.0311479568481445, "learning_rate": 0.0002, "epoch": 5.376078914919852, "step": 4360}, {"loss": 0.3104, "grad_norm": 1.2097488641738892, "learning_rate": 0.0002, "epoch": 5.388409371146732, "step": 4370}, {"loss": 0.2977, "grad_norm": 1.140942096710205, "learning_rate": 0.0002, "epoch": 5.400739827373613, "step": 4380}, {"loss": 0.2975, "grad_norm": 0.8091890811920166, "learning_rate": 0.0002, "epoch": 5.413070283600494, "step": 4390}, {"loss": 0.3727, "grad_norm": 1.4467964172363281, "learning_rate": 0.0002, "epoch": 5.425400739827373, "step": 4400}, {"loss": 0.2979, "grad_norm": 1.0836058855056763, "learning_rate": 0.0002, "epoch": 5.437731196054254, "step": 4410}, {"loss": 0.2601, "grad_norm": 1.0515433549880981, "learning_rate": 0.0002, "epoch": 5.450061652281135, "step": 4420}, {"loss": 0.315, "grad_norm": 0.9603073000907898, "learning_rate": 0.0002, "epoch": 5.4623921085080145, "step": 4430}, {"loss": 0.3166, "grad_norm": 1.234609842300415, "learning_rate": 0.0002, "epoch": 5.474722564734895, "step": 4440}, {"loss": 0.3142, "grad_norm": 0.8881428837776184, "learning_rate": 0.0002, "epoch": 5.487053020961776, "step": 4450}, {"loss": 0.3725, "grad_norm": 1.1817275285720825, "learning_rate": 0.0002, "epoch": 5.499383477188656, "step": 4460}, {"loss": 0.2944, "grad_norm": 1.213993787765503, "learning_rate": 0.0002, "epoch": 5.511713933415536, "step": 4470}, {"loss": 0.3136, "grad_norm": 1.0501725673675537, "learning_rate": 0.0002, "epoch": 5.524044389642417, "step": 4480}, {"loss": 0.306, "grad_norm": 1.5061579942703247, "learning_rate": 0.0002, "epoch": 5.536374845869297, "step": 4490}, {"loss": 0.3226, "grad_norm": 1.1171475648880005, "learning_rate": 0.0002, "epoch": 5.548705302096177, "step": 4500}, {"loss": 0.3624, "grad_norm": 1.1147594451904297, "learning_rate": 0.0002, "epoch": 5.561035758323058, "step": 4510}, {"loss": 0.3435, "grad_norm": 1.0600544214248657, "learning_rate": 0.0002, "epoch": 5.573366214549939, "step": 4520}, {"loss": 0.3268, "grad_norm": 1.247870922088623, "learning_rate": 0.0002, "epoch": 5.5856966707768185, "step": 4530}, {"loss": 0.3168, "grad_norm": 0.9425561428070068, "learning_rate": 0.0002, "epoch": 5.598027127003699, "step": 4540}, {"loss": 0.3119, "grad_norm": 1.1111550331115723, "learning_rate": 0.0002, "epoch": 5.61035758323058, "step": 4550}, {"loss": 0.3389, "grad_norm": 1.743268609046936, "learning_rate": 0.0002, "epoch": 5.62268803945746, "step": 4560}, {"loss": 0.31, "grad_norm": 1.3522645235061646, "learning_rate": 0.0002, "epoch": 5.63501849568434, "step": 4570}, {"loss": 0.3121, "grad_norm": 0.7354221343994141, "learning_rate": 0.0002, "epoch": 5.647348951911221, "step": 4580}, {"loss": 0.3693, "grad_norm": 1.050743818283081, "learning_rate": 0.0002, "epoch": 5.659679408138101, "step": 4590}, {"loss": 0.3449, "grad_norm": 1.1302396059036255, "learning_rate": 0.0002, "epoch": 5.6720098643649814, "step": 4600}, {"loss": 0.3211, "grad_norm": 0.8774183392524719, "learning_rate": 0.0002, "epoch": 5.684340320591862, "step": 4610}, {"loss": 0.3501, "grad_norm": 1.090781569480896, "learning_rate": 0.0002, "epoch": 5.696670776818742, "step": 4620}, {"loss": 0.3211, "grad_norm": 0.9177733063697815, "learning_rate": 0.0002, "epoch": 5.709001233045623, "step": 4630}, {"loss": 0.3439, "grad_norm": 0.9985341429710388, "learning_rate": 0.0002, "epoch": 5.721331689272503, "step": 4640}, {"loss": 0.3323, "grad_norm": 1.0230613946914673, "learning_rate": 0.0002, "epoch": 5.733662145499384, "step": 4650}, {"loss": 0.3525, "grad_norm": 0.944656252861023, "learning_rate": 0.0002, "epoch": 5.745992601726264, "step": 4660}, {"loss": 0.3191, "grad_norm": 0.8162471652030945, "learning_rate": 0.0002, "epoch": 5.758323057953144, "step": 4670}, {"loss": 0.4011, "grad_norm": 1.0500398874282837, "learning_rate": 0.0002, "epoch": 5.770653514180025, "step": 4680}, {"loss": 0.3452, "grad_norm": 0.9487981796264648, "learning_rate": 0.0002, "epoch": 5.782983970406905, "step": 4690}, {"loss": 0.2942, "grad_norm": 1.1856540441513062, "learning_rate": 0.0002, "epoch": 5.7953144266337855, "step": 4700}, {"loss": 0.3107, "grad_norm": 1.2583396434783936, "learning_rate": 0.0002, "epoch": 5.807644882860666, "step": 4710}, {"loss": 0.3223, "grad_norm": 1.2532602548599243, "learning_rate": 0.0002, "epoch": 5.819975339087546, "step": 4720}, {"loss": 0.3253, "grad_norm": 1.115236520767212, "learning_rate": 0.0002, "epoch": 5.832305795314427, "step": 4730}, {"loss": 0.3539, "grad_norm": 1.2245537042617798, "learning_rate": 0.0002, "epoch": 5.844636251541307, "step": 4740}, {"loss": 0.3171, "grad_norm": 1.1964094638824463, "learning_rate": 0.0002, "epoch": 5.856966707768187, "step": 4750}, {"loss": 0.3623, "grad_norm": 1.0833805799484253, "learning_rate": 0.0002, "epoch": 5.869297163995068, "step": 4760}, {"loss": 0.3511, "grad_norm": 1.0694046020507812, "learning_rate": 0.0002, "epoch": 5.881627620221948, "step": 4770}, {"loss": 0.3266, "grad_norm": 0.9947936534881592, "learning_rate": 0.0002, "epoch": 5.893958076448829, "step": 4780}, {"loss": 0.316, "grad_norm": 1.175716519355774, "learning_rate": 0.0002, "epoch": 5.906288532675709, "step": 4790}, {"loss": 0.3609, "grad_norm": 0.7717352509498596, "learning_rate": 0.0002, "epoch": 5.9186189889025895, "step": 4800}, {"loss": 0.3058, "grad_norm": 1.2906442880630493, "learning_rate": 0.0002, "epoch": 5.930949445129469, "step": 4810}, {"loss": 0.3187, "grad_norm": 1.2416284084320068, "learning_rate": 0.0002, "epoch": 5.94327990135635, "step": 4820}, {"loss": 0.337, "grad_norm": 1.3066956996917725, "learning_rate": 0.0002, "epoch": 5.955610357583231, "step": 4830}, {"loss": 0.3167, "grad_norm": 1.0872026681900024, "learning_rate": 0.0002, "epoch": 5.967940813810111, "step": 4840}, {"loss": 0.3262, "grad_norm": 1.1941101551055908, "learning_rate": 0.0002, "epoch": 5.980271270036991, "step": 4850}, {"loss": 0.3234, "grad_norm": 1.1126095056533813, "learning_rate": 0.0002, "epoch": 5.992601726263872, "step": 4860}, {"eval_loss": 1.748323917388916, "eval_runtime": 97.7488, "eval_samples_per_second": 4.46, "eval_steps_per_second": 0.563, "epoch": 6.0, "step": 4866}, {"loss": 0.2774, "grad_norm": 1.3631165027618408, "learning_rate": 0.0002, "epoch": 6.0049321824907524, "step": 4870}, {"loss": 0.2399, "grad_norm": 1.2631664276123047, "learning_rate": 0.0002, "epoch": 6.017262638717632, "step": 4880}, {"loss": 0.2177, "grad_norm": 0.7073080539703369, "learning_rate": 0.0002, "epoch": 6.029593094944513, "step": 4890}, {"loss": 0.215, "grad_norm": 0.7856091856956482, "learning_rate": 0.0002, "epoch": 6.041923551171394, "step": 4900}, {"loss": 0.1999, "grad_norm": 1.145540475845337, "learning_rate": 0.0002, "epoch": 6.054254007398273, "step": 4910}, {"loss": 0.2084, "grad_norm": 1.1742334365844727, "learning_rate": 0.0002, "epoch": 6.066584463625154, "step": 4920}, {"loss": 0.2342, "grad_norm": 0.8043994903564453, "learning_rate": 0.0002, "epoch": 6.078914919852035, "step": 4930}, {"loss": 0.2454, "grad_norm": 1.1877652406692505, "learning_rate": 0.0002, "epoch": 6.0912453760789145, "step": 4940}, {"loss": 0.1908, "grad_norm": 0.7624953985214233, "learning_rate": 0.0002, "epoch": 6.103575832305795, "step": 4950}, {"loss": 0.2254, "grad_norm": 1.0403119325637817, "learning_rate": 0.0002, "epoch": 6.115906288532676, "step": 4960}, {"loss": 0.2274, "grad_norm": 1.2040252685546875, "learning_rate": 0.0002, "epoch": 6.1282367447595565, "step": 4970}, {"loss": 0.2199, "grad_norm": 0.6242546439170837, "learning_rate": 0.0002, "epoch": 6.140567200986436, "step": 4980}, {"loss": 0.27, "grad_norm": 1.1394767761230469, "learning_rate": 0.0002, "epoch": 6.152897657213317, "step": 4990}, {"loss": 0.2377, "grad_norm": 1.3760257959365845, "learning_rate": 0.0002, "epoch": 6.165228113440198, "step": 5000}, {"loss": 0.2331, "grad_norm": 1.0707697868347168, "learning_rate": 0.0002, "epoch": 6.177558569667077, "step": 5010}, {"loss": 0.2311, "grad_norm": 1.288072109222412, "learning_rate": 0.0002, "epoch": 6.189889025893958, "step": 5020}, {"loss": 0.2276, "grad_norm": 1.1479463577270508, "learning_rate": 0.0002, "epoch": 6.202219482120839, "step": 5030}, {"loss": 0.2294, "grad_norm": 0.905891478061676, "learning_rate": 0.0002, "epoch": 6.2145499383477185, "step": 5040}, {"loss": 0.2575, "grad_norm": 1.0354516506195068, "learning_rate": 0.0002, "epoch": 6.226880394574599, "step": 5050}, {"loss": 0.2259, "grad_norm": 1.312671184539795, "learning_rate": 0.0002, "epoch": 6.23921085080148, "step": 5060}, {"loss": 0.2281, "grad_norm": 1.614709734916687, "learning_rate": 0.0002, "epoch": 6.25154130702836, "step": 5070}, {"loss": 0.2388, "grad_norm": 1.0864229202270508, "learning_rate": 0.0002, "epoch": 6.26387176325524, "step": 5080}, {"loss": 0.2014, "grad_norm": 1.0401391983032227, "learning_rate": 0.0002, "epoch": 6.276202219482121, "step": 5090}, {"loss": 0.2419, "grad_norm": 1.2187728881835938, "learning_rate": 0.0002, "epoch": 6.288532675709002, "step": 5100}, {"loss": 0.2144, "grad_norm": 0.9474364519119263, "learning_rate": 0.0002, "epoch": 6.300863131935881, "step": 5110}, {"loss": 0.238, "grad_norm": 1.1228716373443604, "learning_rate": 0.0002, "epoch": 6.313193588162762, "step": 5120}, {"loss": 0.2556, "grad_norm": 0.9294499754905701, "learning_rate": 0.0002, "epoch": 6.325524044389643, "step": 5130}, {"loss": 0.2384, "grad_norm": 1.0521048307418823, "learning_rate": 0.0002, "epoch": 6.337854500616523, "step": 5140}, {"loss": 0.2444, "grad_norm": 1.2406890392303467, "learning_rate": 0.0002, "epoch": 6.350184956843403, "step": 5150}, {"loss": 0.2301, "grad_norm": 1.2972853183746338, "learning_rate": 0.0002, "epoch": 6.362515413070284, "step": 5160}, {"loss": 0.2574, "grad_norm": 0.8772842288017273, "learning_rate": 0.0002, "epoch": 6.374845869297164, "step": 5170}, {"loss": 0.2337, "grad_norm": 1.050349473953247, "learning_rate": 0.0002, "epoch": 6.387176325524044, "step": 5180}, {"loss": 0.2593, "grad_norm": 0.9432134032249451, "learning_rate": 0.0002, "epoch": 6.399506781750925, "step": 5190}, {"loss": 0.2546, "grad_norm": 1.11045241355896, "learning_rate": 0.0002, "epoch": 6.411837237977805, "step": 5200}, {"loss": 0.268, "grad_norm": 1.117530345916748, "learning_rate": 0.0002, "epoch": 6.4241676942046855, "step": 5210}, {"loss": 0.25, "grad_norm": 1.4194035530090332, "learning_rate": 0.0002, "epoch": 6.436498150431566, "step": 5220}, {"loss": 0.2335, "grad_norm": 1.063950777053833, "learning_rate": 0.0002, "epoch": 6.448828606658447, "step": 5230}, {"loss": 0.2299, "grad_norm": 1.2946349382400513, "learning_rate": 0.0002, "epoch": 6.461159062885327, "step": 5240}, {"loss": 0.242, "grad_norm": 1.5237880945205688, "learning_rate": 0.0002, "epoch": 6.473489519112207, "step": 5250}, {"loss": 0.255, "grad_norm": 1.1915720701217651, "learning_rate": 0.0002, "epoch": 6.485819975339088, "step": 5260}, {"loss": 0.2357, "grad_norm": 1.0779626369476318, "learning_rate": 0.0002, "epoch": 6.498150431565968, "step": 5270}, {"loss": 0.2476, "grad_norm": 0.8255738019943237, "learning_rate": 0.0002, "epoch": 6.510480887792848, "step": 5280}, {"loss": 0.267, "grad_norm": 1.275174856185913, "learning_rate": 0.0002, "epoch": 6.522811344019729, "step": 5290}, {"loss": 0.2217, "grad_norm": 1.0878815650939941, "learning_rate": 0.0002, "epoch": 6.535141800246609, "step": 5300}, {"loss": 0.2462, "grad_norm": 1.2594236135482788, "learning_rate": 0.0002, "epoch": 6.5474722564734895, "step": 5310}, {"loss": 0.2457, "grad_norm": 0.9919610619544983, "learning_rate": 0.0002, "epoch": 6.55980271270037, "step": 5320}, {"loss": 0.2933, "grad_norm": 1.3703680038452148, "learning_rate": 0.0002, "epoch": 6.57213316892725, "step": 5330}, {"loss": 0.2453, "grad_norm": 1.403140902519226, "learning_rate": 0.0002, "epoch": 6.584463625154131, "step": 5340}, {"loss": 0.2584, "grad_norm": 1.3477165699005127, "learning_rate": 0.0002, "epoch": 6.596794081381011, "step": 5350}, {"loss": 0.2853, "grad_norm": 1.3145594596862793, "learning_rate": 0.0002, "epoch": 6.609124537607892, "step": 5360}, {"loss": 0.246, "grad_norm": 0.9048973321914673, "learning_rate": 0.0002, "epoch": 6.621454993834772, "step": 5370}, {"loss": 0.2646, "grad_norm": 1.4123972654342651, "learning_rate": 0.0002, "epoch": 6.633785450061652, "step": 5380}, {"loss": 0.272, "grad_norm": 1.3584848642349243, "learning_rate": 0.0002, "epoch": 6.646115906288532, "step": 5390}, {"loss": 0.2663, "grad_norm": 1.2085801362991333, "learning_rate": 0.0002, "epoch": 6.658446362515413, "step": 5400}, {"loss": 0.2796, "grad_norm": 1.9293283224105835, "learning_rate": 0.0002, "epoch": 6.670776818742294, "step": 5410}, {"loss": 0.2412, "grad_norm": 1.3658782243728638, "learning_rate": 0.0002, "epoch": 6.683107274969174, "step": 5420}, {"loss": 0.2442, "grad_norm": 1.2004997730255127, "learning_rate": 0.0002, "epoch": 6.695437731196054, "step": 5430}, {"loss": 0.2693, "grad_norm": 1.0671268701553345, "learning_rate": 0.0002, "epoch": 6.707768187422935, "step": 5440}, {"loss": 0.2216, "grad_norm": 0.8877466320991516, "learning_rate": 0.0002, "epoch": 6.720098643649815, "step": 5450}, {"loss": 0.2678, "grad_norm": 1.2843106985092163, "learning_rate": 0.0002, "epoch": 6.732429099876695, "step": 5460}, {"loss": 0.2418, "grad_norm": 1.0663448572158813, "learning_rate": 0.0002, "epoch": 6.744759556103576, "step": 5470}, {"loss": 0.2402, "grad_norm": 1.3155773878097534, "learning_rate": 0.0002, "epoch": 6.7570900123304565, "step": 5480}, {"loss": 0.2559, "grad_norm": 1.8862448930740356, "learning_rate": 0.0002, "epoch": 6.769420468557336, "step": 5490}, {"loss": 0.2651, "grad_norm": 1.165061116218567, "learning_rate": 0.0002, "epoch": 6.781750924784217, "step": 5500}, {"loss": 0.2342, "grad_norm": 1.0968598127365112, "learning_rate": 0.0002, "epoch": 6.794081381011098, "step": 5510}, {"loss": 0.2453, "grad_norm": 0.9448091983795166, "learning_rate": 0.0002, "epoch": 6.806411837237977, "step": 5520}, {"loss": 0.2609, "grad_norm": 1.400767207145691, "learning_rate": 0.0002, "epoch": 6.818742293464858, "step": 5530}, {"loss": 0.2642, "grad_norm": 1.1031112670898438, "learning_rate": 0.0002, "epoch": 6.831072749691739, "step": 5540}, {"loss": 0.2534, "grad_norm": 1.2436904907226562, "learning_rate": 0.0002, "epoch": 6.843403205918619, "step": 5550}, {"loss": 0.2601, "grad_norm": 1.0987974405288696, "learning_rate": 0.0002, "epoch": 6.855733662145499, "step": 5560}, {"loss": 0.2622, "grad_norm": 0.8656415939331055, "learning_rate": 0.0002, "epoch": 6.86806411837238, "step": 5570}, {"loss": 0.2585, "grad_norm": 1.2153927087783813, "learning_rate": 0.0002, "epoch": 6.8803945745992605, "step": 5580}, {"loss": 0.2888, "grad_norm": 1.111377477645874, "learning_rate": 0.0002, "epoch": 6.89272503082614, "step": 5590}, {"loss": 0.2569, "grad_norm": 1.0041896104812622, "learning_rate": 0.0002, "epoch": 6.905055487053021, "step": 5600}, {"loss": 0.2654, "grad_norm": 1.0638413429260254, "learning_rate": 0.0002, "epoch": 6.917385943279902, "step": 5610}, {"loss": 0.2364, "grad_norm": 0.9756764769554138, "learning_rate": 0.0002, "epoch": 6.929716399506781, "step": 5620}, {"loss": 0.2756, "grad_norm": 1.153550624847412, "learning_rate": 0.0002, "epoch": 6.942046855733662, "step": 5630}, {"loss": 0.2732, "grad_norm": 1.3393985033035278, "learning_rate": 0.0002, "epoch": 6.954377311960543, "step": 5640}, {"loss": 0.2793, "grad_norm": 1.3233463764190674, "learning_rate": 0.0002, "epoch": 6.9667077681874225, "step": 5650}, {"loss": 0.2593, "grad_norm": 1.1693105697631836, "learning_rate": 0.0002, "epoch": 6.979038224414303, "step": 5660}, {"loss": 0.278, "grad_norm": 0.7186262607574463, "learning_rate": 0.0002, "epoch": 6.991368680641184, "step": 5670}, {"eval_loss": 1.936746597290039, "eval_runtime": 99.4259, "eval_samples_per_second": 4.385, "eval_steps_per_second": 0.553, "epoch": 7.0, "step": 5677}, {"loss": 0.2573, "grad_norm": 0.9832284450531006, "learning_rate": 0.0002, "epoch": 7.003699136868065, "step": 5680}, {"loss": 0.1879, "grad_norm": 1.6794530153274536, "learning_rate": 0.0002, "epoch": 7.016029593094944, "step": 5690}, {"loss": 0.1612, "grad_norm": 1.0405313968658447, "learning_rate": 0.0002, "epoch": 7.028360049321825, "step": 5700}, {"loss": 0.1623, "grad_norm": 0.8833287954330444, "learning_rate": 0.0002, "epoch": 7.040690505548706, "step": 5710}, {"loss": 0.1666, "grad_norm": 1.081743597984314, "learning_rate": 0.0002, "epoch": 7.0530209617755855, "step": 5720}, {"loss": 0.1952, "grad_norm": 1.1786993741989136, "learning_rate": 0.0002, "epoch": 7.065351418002466, "step": 5730}, {"loss": 0.1618, "grad_norm": 1.219215989112854, "learning_rate": 0.0002, "epoch": 7.077681874229347, "step": 5740}, {"loss": 0.165, "grad_norm": 0.882033109664917, "learning_rate": 0.0002, "epoch": 7.090012330456227, "step": 5750}, {"loss": 0.1801, "grad_norm": 1.0919346809387207, "learning_rate": 0.0002, "epoch": 7.102342786683107, "step": 5760}, {"loss": 0.1914, "grad_norm": 1.2448198795318604, "learning_rate": 0.0002, "epoch": 7.114673242909988, "step": 5770}, {"loss": 0.1826, "grad_norm": 0.8977628350257874, "learning_rate": 0.0002, "epoch": 7.127003699136868, "step": 5780}, {"loss": 0.2119, "grad_norm": 1.1030590534210205, "learning_rate": 0.0002, "epoch": 7.139334155363748, "step": 5790}, {"loss": 0.1841, "grad_norm": 0.9050454497337341, "learning_rate": 0.0002, "epoch": 7.151664611590629, "step": 5800}, {"loss": 0.1765, "grad_norm": 1.2709665298461914, "learning_rate": 0.0002, "epoch": 7.163995067817509, "step": 5810}, {"loss": 0.2069, "grad_norm": 1.7741143703460693, "learning_rate": 0.0002, "epoch": 7.1763255240443895, "step": 5820}, {"loss": 0.2189, "grad_norm": 1.040995478630066, "learning_rate": 0.0002, "epoch": 7.18865598027127, "step": 5830}, {"loss": 0.1869, "grad_norm": 0.995246171951294, "learning_rate": 0.0002, "epoch": 7.200986436498151, "step": 5840}, {"loss": 0.1727, "grad_norm": 0.962523341178894, "learning_rate": 0.0002, "epoch": 7.213316892725031, "step": 5850}, {"loss": 0.2051, "grad_norm": 1.2010393142700195, "learning_rate": 0.0002, "epoch": 7.225647348951911, "step": 5860}, {"loss": 0.19, "grad_norm": 1.1749597787857056, "learning_rate": 0.0002, "epoch": 7.237977805178792, "step": 5870}, {"loss": 0.1799, "grad_norm": 1.0654889345169067, "learning_rate": 0.0002, "epoch": 7.250308261405672, "step": 5880}, {"loss": 0.2184, "grad_norm": 0.761138379573822, "learning_rate": 0.0002, "epoch": 7.262638717632552, "step": 5890}, {"loss": 0.1828, "grad_norm": 0.9512502551078796, "learning_rate": 0.0002, "epoch": 7.274969173859433, "step": 5900}, {"loss": 0.1655, "grad_norm": 0.7542949318885803, "learning_rate": 0.0002, "epoch": 7.287299630086313, "step": 5910}, {"loss": 0.1985, "grad_norm": 0.7638646364212036, "learning_rate": 0.0002, "epoch": 7.2996300863131935, "step": 5920}, {"loss": 0.1953, "grad_norm": 1.162330985069275, "learning_rate": 0.0002, "epoch": 7.311960542540074, "step": 5930}, {"loss": 0.204, "grad_norm": 1.5835925340652466, "learning_rate": 0.0002, "epoch": 7.324290998766954, "step": 5940}, {"loss": 0.178, "grad_norm": 1.0043281316757202, "learning_rate": 0.0002, "epoch": 7.336621454993835, "step": 5950}, {"loss": 0.1819, "grad_norm": 1.2750244140625, "learning_rate": 0.0002, "epoch": 7.348951911220715, "step": 5960}, {"loss": 0.1917, "grad_norm": 0.8582083582878113, "learning_rate": 0.0002, "epoch": 7.361282367447595, "step": 5970}, {"loss": 0.2022, "grad_norm": 1.0025495290756226, "learning_rate": 0.0002, "epoch": 7.373612823674476, "step": 5980}, {"loss": 0.1971, "grad_norm": 1.030452847480774, "learning_rate": 0.0002, "epoch": 7.3859432799013565, "step": 5990}, {"loss": 0.2026, "grad_norm": 0.9436936378479004, "learning_rate": 0.0002, "epoch": 7.398273736128237, "step": 6000}, {"loss": 0.1847, "grad_norm": 1.3259925842285156, "learning_rate": 0.0002, "epoch": 7.410604192355117, "step": 6010}, {"loss": 0.1794, "grad_norm": 0.884767472743988, "learning_rate": 0.0002, "epoch": 7.422934648581998, "step": 6020}, {"loss": 0.1712, "grad_norm": 0.8467209339141846, "learning_rate": 0.0002, "epoch": 7.435265104808878, "step": 6030}, {"loss": 0.2025, "grad_norm": 0.9294904470443726, "learning_rate": 0.0002, "epoch": 7.447595561035758, "step": 6040}, {"loss": 0.1808, "grad_norm": 1.2054014205932617, "learning_rate": 0.0002, "epoch": 7.459926017262639, "step": 6050}, {"loss": 0.193, "grad_norm": 0.9458960294723511, "learning_rate": 0.0002, "epoch": 7.472256473489519, "step": 6060}, {"loss": 0.1762, "grad_norm": 1.0876508951187134, "learning_rate": 0.0002, "epoch": 7.484586929716399, "step": 6070}, {"loss": 0.1999, "grad_norm": 1.110326886177063, "learning_rate": 0.0002, "epoch": 7.49691738594328, "step": 6080}, {"loss": 0.1854, "grad_norm": 1.1584968566894531, "learning_rate": 0.0002, "epoch": 7.5092478421701605, "step": 6090}, {"loss": 0.2059, "grad_norm": 1.0806410312652588, "learning_rate": 0.0002, "epoch": 7.52157829839704, "step": 6100}, {"loss": 0.2042, "grad_norm": 0.9162251353263855, "learning_rate": 0.0002, "epoch": 7.533908754623921, "step": 6110}, {"loss": 0.1981, "grad_norm": 1.044049620628357, "learning_rate": 0.0002, "epoch": 7.546239210850802, "step": 6120}, {"loss": 0.1857, "grad_norm": 0.9524619579315186, "learning_rate": 0.0002, "epoch": 7.558569667077682, "step": 6130}, {"loss": 0.2113, "grad_norm": 1.0031976699829102, "learning_rate": 0.0002, "epoch": 7.570900123304562, "step": 6140}, {"loss": 0.2008, "grad_norm": 1.342751383781433, "learning_rate": 0.0002, "epoch": 7.583230579531443, "step": 6150}, {"loss": 0.1895, "grad_norm": 1.4278815984725952, "learning_rate": 0.0002, "epoch": 7.595561035758323, "step": 6160}, {"loss": 0.2473, "grad_norm": 1.6231565475463867, "learning_rate": 0.0002, "epoch": 7.607891491985203, "step": 6170}, {"loss": 0.1861, "grad_norm": 1.0082448720932007, "learning_rate": 0.0002, "epoch": 7.620221948212084, "step": 6180}, {"loss": 0.1945, "grad_norm": 1.1605384349822998, "learning_rate": 0.0002, "epoch": 7.6325524044389645, "step": 6190}, {"loss": 0.196, "grad_norm": 1.3302881717681885, "learning_rate": 0.0002, "epoch": 7.644882860665844, "step": 6200}, {"loss": 0.2169, "grad_norm": 1.3318504095077515, "learning_rate": 0.0002, "epoch": 7.657213316892725, "step": 6210}, {"loss": 0.1872, "grad_norm": 1.265977144241333, "learning_rate": 0.0002, "epoch": 7.669543773119606, "step": 6220}, {"loss": 0.1917, "grad_norm": 1.3964512348175049, "learning_rate": 0.0002, "epoch": 7.6818742293464854, "step": 6230}, {"loss": 0.2244, "grad_norm": 1.148972988128662, "learning_rate": 0.0002, "epoch": 7.694204685573366, "step": 6240}, {"loss": 0.2038, "grad_norm": 0.8778917193412781, "learning_rate": 0.0002, "epoch": 7.706535141800247, "step": 6250}, {"loss": 0.2399, "grad_norm": 1.3537850379943848, "learning_rate": 0.0002, "epoch": 7.7188655980271275, "step": 6260}, {"loss": 0.194, "grad_norm": 0.8741335868835449, "learning_rate": 0.0002, "epoch": 7.731196054254007, "step": 6270}, {"loss": 0.2178, "grad_norm": 0.9642979502677917, "learning_rate": 0.0002, "epoch": 7.743526510480888, "step": 6280}, {"loss": 0.2328, "grad_norm": 1.4556978940963745, "learning_rate": 0.0002, "epoch": 7.755856966707768, "step": 6290}, {"loss": 0.2309, "grad_norm": 1.1485596895217896, "learning_rate": 0.0002, "epoch": 7.768187422934648, "step": 6300}, {"loss": 0.2178, "grad_norm": 1.2361459732055664, "learning_rate": 0.0002, "epoch": 7.780517879161529, "step": 6310}, {"loss": 0.2291, "grad_norm": 1.0271167755126953, "learning_rate": 0.0002, "epoch": 7.79284833538841, "step": 6320}, {"loss": 0.2112, "grad_norm": 1.2584497928619385, "learning_rate": 0.0002, "epoch": 7.8051787916152895, "step": 6330}, {"loss": 0.2098, "grad_norm": 0.9013339877128601, "learning_rate": 0.0002, "epoch": 7.81750924784217, "step": 6340}, {"loss": 0.1927, "grad_norm": 1.1033759117126465, "learning_rate": 0.0002, "epoch": 7.829839704069051, "step": 6350}, {"loss": 0.2294, "grad_norm": 1.4669054746627808, "learning_rate": 0.0002, "epoch": 7.842170160295931, "step": 6360}, {"loss": 0.2176, "grad_norm": 1.3915599584579468, "learning_rate": 0.0002, "epoch": 7.854500616522811, "step": 6370}, {"loss": 0.2294, "grad_norm": 1.6034538745880127, "learning_rate": 0.0002, "epoch": 7.866831072749692, "step": 6380}, {"loss": 0.2244, "grad_norm": 1.3022582530975342, "learning_rate": 0.0002, "epoch": 7.879161528976573, "step": 6390}, {"loss": 0.2316, "grad_norm": 1.0695449113845825, "learning_rate": 0.0002, "epoch": 7.891491985203452, "step": 6400}, {"loss": 0.2203, "grad_norm": 1.1082428693771362, "learning_rate": 0.0002, "epoch": 7.903822441430333, "step": 6410}, {"loss": 0.2102, "grad_norm": 0.9848728775978088, "learning_rate": 0.0002, "epoch": 7.916152897657213, "step": 6420}, {"loss": 0.2049, "grad_norm": 0.8668254017829895, "learning_rate": 0.0002, "epoch": 7.9284833538840935, "step": 6430}, {"loss": 0.2054, "grad_norm": 0.9431440234184265, "learning_rate": 0.0002, "epoch": 7.940813810110974, "step": 6440}, {"loss": 0.2364, "grad_norm": 1.3903534412384033, "learning_rate": 0.0002, "epoch": 7.953144266337855, "step": 6450}, {"loss": 0.2193, "grad_norm": 1.111591100692749, "learning_rate": 0.0002, "epoch": 7.965474722564735, "step": 6460}, {"loss": 0.2178, "grad_norm": 0.9858004450798035, "learning_rate": 0.0002, "epoch": 7.977805178791615, "step": 6470}, {"loss": 0.208, "grad_norm": 0.9721771478652954, "learning_rate": 0.0002, "epoch": 7.990135635018496, "step": 6480}]}