diff --git a/.gitattributes b/.gitattributes
index 11e312fd732405653cd8bac54ca5b3924daa3642..2c223cd604b1b594107f0dfb47468c2740e898b3 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1444,3 +1444,12 @@ gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1
 gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-375-sd-4/checkpoint-82/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-375-sd-4/checkpoint-99/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-375-sd-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/README.md b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/adapter_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/adapter_model.safetensors b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..25a6157dd64c1895e96eba28c31bfe1297c5fb71
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81567cf32cadbaf0117b7ad6c654a6b5fedc1775d91f1bdb0c88027d5c8d77d
+size 143153376
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/README.md b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/adapter_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/adapter_model.safetensors b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ccdc7ae9cde2b8b66e78ffee1100907025132c5c
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6473a088390d144a71fb5d6262cfcb03166ec6325101c01439b478ba9bbc7cda
+size 143153376
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/optimizer.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c7cef0c460bf693e72a2462da8a13edc08f577f4
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8be363955abd87a9b2cd189b2be95ffb18b56117f04a81c7d102a2a60fe5bf62
+size 72886650
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/rng_state.pth b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6ffd8abf20b055f04901d4204aae426e69a046e2
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6bd7fae2fa0cba607da0cb07a269842d7aefc88372e6504dbfbc5450fe150fd
+size 14244
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/scheduler.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..94b80282fc90c2e41c89e7cbf693a65d100a3a26
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:331d722674b800e8c81447e4ed79323e1d696462cdb1e33b3951468ac1e10380
+size 1064
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/special_tokens_map.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/tokenizer.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/tokenizer.model b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/tokenizer_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/trainer_state.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..fc9f81339f9adfadbf56e0ec000c8a664d29d5f1
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/trainer_state.json
@@ -0,0 +1,1071 @@
+{
+  "best_metric": 1.8171186447143555,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733",
+  "epoch": 2.0,
+  "eval_steps": 10,
+  "global_step": 1467,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013633265167007498,
+      "grad_norm": 0.7714291214942932,
+      "learning_rate": 0.0002,
+      "loss": 3.0982,
+      "step": 10
+    },
+    {
+      "epoch": 0.027266530334014997,
+      "grad_norm": 0.5473978519439697,
+      "learning_rate": 0.0002,
+      "loss": 2.5206,
+      "step": 20
+    },
+    {
+      "epoch": 0.0408997955010225,
+      "grad_norm": 0.5452795624732971,
+      "learning_rate": 0.0002,
+      "loss": 2.3079,
+      "step": 30
+    },
+    {
+      "epoch": 0.054533060668029994,
+      "grad_norm": 0.5098028779029846,
+      "learning_rate": 0.0002,
+      "loss": 2.0019,
+      "step": 40
+    },
+    {
+      "epoch": 0.0681663258350375,
+      "grad_norm": 0.48062971234321594,
+      "learning_rate": 0.0002,
+      "loss": 1.9333,
+      "step": 50
+    },
+    {
+      "epoch": 0.081799591002045,
+      "grad_norm": 0.4505695104598999,
+      "learning_rate": 0.0002,
+      "loss": 1.9355,
+      "step": 60
+    },
+    {
+      "epoch": 0.09543285616905249,
+      "grad_norm": 0.41609591245651245,
+      "learning_rate": 0.0002,
+      "loss": 1.9312,
+      "step": 70
+    },
+    {
+      "epoch": 0.10906612133605999,
+      "grad_norm": 0.4323892593383789,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 80
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 0.4670293629169464,
+      "learning_rate": 0.0002,
+      "loss": 1.9294,
+      "step": 90
+    },
+    {
+      "epoch": 0.136332651670075,
+      "grad_norm": 0.40623316168785095,
+      "learning_rate": 0.0002,
+      "loss": 1.7946,
+      "step": 100
+    },
+    {
+      "epoch": 0.1499659168370825,
+      "grad_norm": 0.3620383143424988,
+      "learning_rate": 0.0002,
+      "loss": 1.8565,
+      "step": 110
+    },
+    {
+      "epoch": 0.16359918200409,
+      "grad_norm": 0.332218736410141,
+      "learning_rate": 0.0002,
+      "loss": 1.9238,
+      "step": 120
+    },
+    {
+      "epoch": 0.17723244717109748,
+      "grad_norm": 0.4004521667957306,
+      "learning_rate": 0.0002,
+      "loss": 1.93,
+      "step": 130
+    },
+    {
+      "epoch": 0.19086571233810498,
+      "grad_norm": 0.3698360323905945,
+      "learning_rate": 0.0002,
+      "loss": 1.7549,
+      "step": 140
+    },
+    {
+      "epoch": 0.20449897750511248,
+      "grad_norm": 0.3847949504852295,
+      "learning_rate": 0.0002,
+      "loss": 1.8771,
+      "step": 150
+    },
+    {
+      "epoch": 0.21813224267211997,
+      "grad_norm": 0.36843451857566833,
+      "learning_rate": 0.0002,
+      "loss": 1.8316,
+      "step": 160
+    },
+    {
+      "epoch": 0.23176550783912747,
+      "grad_norm": 0.37301021814346313,
+      "learning_rate": 0.0002,
+      "loss": 1.838,
+      "step": 170
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.3718886971473694,
+      "learning_rate": 0.0002,
+      "loss": 1.8909,
+      "step": 180
+    },
+    {
+      "epoch": 0.25903203817314246,
+      "grad_norm": 0.3088490962982178,
+      "learning_rate": 0.0002,
+      "loss": 1.8454,
+      "step": 190
+    },
+    {
+      "epoch": 0.27266530334015,
+      "grad_norm": 0.3611852526664734,
+      "learning_rate": 0.0002,
+      "loss": 1.9254,
+      "step": 200
+    },
+    {
+      "epoch": 0.28629856850715746,
+      "grad_norm": 0.36093324422836304,
+      "learning_rate": 0.0002,
+      "loss": 1.7844,
+      "step": 210
+    },
+    {
+      "epoch": 0.299931833674165,
+      "grad_norm": 0.3250400722026825,
+      "learning_rate": 0.0002,
+      "loss": 1.719,
+      "step": 220
+    },
+    {
+      "epoch": 0.31356509884117245,
+      "grad_norm": 0.3566756248474121,
+      "learning_rate": 0.0002,
+      "loss": 1.8729,
+      "step": 230
+    },
+    {
+      "epoch": 0.32719836400818,
+      "grad_norm": 0.32872408628463745,
+      "learning_rate": 0.0002,
+      "loss": 1.9259,
+      "step": 240
+    },
+    {
+      "epoch": 0.34083162917518744,
+      "grad_norm": 0.3983881175518036,
+      "learning_rate": 0.0002,
+      "loss": 1.9033,
+      "step": 250
+    },
+    {
+      "epoch": 0.35446489434219497,
+      "grad_norm": 0.3571510910987854,
+      "learning_rate": 0.0002,
+      "loss": 1.8588,
+      "step": 260
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 0.3036131262779236,
+      "learning_rate": 0.0002,
+      "loss": 1.8539,
+      "step": 270
+    },
+    {
+      "epoch": 0.38173142467620996,
+      "grad_norm": 0.36512863636016846,
+      "learning_rate": 0.0002,
+      "loss": 1.8572,
+      "step": 280
+    },
+    {
+      "epoch": 0.39536468984321743,
+      "grad_norm": 0.3429736793041229,
+      "learning_rate": 0.0002,
+      "loss": 1.8022,
+      "step": 290
+    },
+    {
+      "epoch": 0.40899795501022496,
+      "grad_norm": 0.3055964708328247,
+      "learning_rate": 0.0002,
+      "loss": 1.8754,
+      "step": 300
+    },
+    {
+      "epoch": 0.4226312201772324,
+      "grad_norm": 0.33801034092903137,
+      "learning_rate": 0.0002,
+      "loss": 1.8384,
+      "step": 310
+    },
+    {
+      "epoch": 0.43626448534423995,
+      "grad_norm": 0.348783016204834,
+      "learning_rate": 0.0002,
+      "loss": 1.7933,
+      "step": 320
+    },
+    {
+      "epoch": 0.4498977505112474,
+      "grad_norm": 0.3057514727115631,
+      "learning_rate": 0.0002,
+      "loss": 1.8451,
+      "step": 330
+    },
+    {
+      "epoch": 0.46353101567825494,
+      "grad_norm": 0.3849763572216034,
+      "learning_rate": 0.0002,
+      "loss": 1.8766,
+      "step": 340
+    },
+    {
+      "epoch": 0.47716428084526247,
+      "grad_norm": 0.30080053210258484,
+      "learning_rate": 0.0002,
+      "loss": 1.8073,
+      "step": 350
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.3595106303691864,
+      "learning_rate": 0.0002,
+      "loss": 1.8548,
+      "step": 360
+    },
+    {
+      "epoch": 0.5044308111792775,
+      "grad_norm": 0.31099820137023926,
+      "learning_rate": 0.0002,
+      "loss": 1.8232,
+      "step": 370
+    },
+    {
+      "epoch": 0.5180640763462849,
+      "grad_norm": 0.3157978355884552,
+      "learning_rate": 0.0002,
+      "loss": 1.7029,
+      "step": 380
+    },
+    {
+      "epoch": 0.5316973415132924,
+      "grad_norm": 0.27960965037345886,
+      "learning_rate": 0.0002,
+      "loss": 1.8265,
+      "step": 390
+    },
+    {
+      "epoch": 0.5453306066803,
+      "grad_norm": 0.3102385103702545,
+      "learning_rate": 0.0002,
+      "loss": 1.7414,
+      "step": 400
+    },
+    {
+      "epoch": 0.5589638718473074,
+      "grad_norm": 0.32828861474990845,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 410
+    },
+    {
+      "epoch": 0.5725971370143149,
+      "grad_norm": 0.29560017585754395,
+      "learning_rate": 0.0002,
+      "loss": 1.8165,
+      "step": 420
+    },
+    {
+      "epoch": 0.5862304021813224,
+      "grad_norm": 0.33316895365715027,
+      "learning_rate": 0.0002,
+      "loss": 1.9455,
+      "step": 430
+    },
+    {
+      "epoch": 0.59986366734833,
+      "grad_norm": 0.30420982837677,
+      "learning_rate": 0.0002,
+      "loss": 1.8241,
+      "step": 440
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 0.32619214057922363,
+      "learning_rate": 0.0002,
+      "loss": 1.7565,
+      "step": 450
+    },
+    {
+      "epoch": 0.6271301976823449,
+      "grad_norm": 0.3603750765323639,
+      "learning_rate": 0.0002,
+      "loss": 1.7945,
+      "step": 460
+    },
+    {
+      "epoch": 0.6407634628493524,
+      "grad_norm": 0.30834096670150757,
+      "learning_rate": 0.0002,
+      "loss": 1.7773,
+      "step": 470
+    },
+    {
+      "epoch": 0.65439672801636,
+      "grad_norm": 0.28756365180015564,
+      "learning_rate": 0.0002,
+      "loss": 1.8058,
+      "step": 480
+    },
+    {
+      "epoch": 0.6680299931833674,
+      "grad_norm": 0.2878406345844269,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 490
+    },
+    {
+      "epoch": 0.6816632583503749,
+      "grad_norm": 0.31329697370529175,
+      "learning_rate": 0.0002,
+      "loss": 1.8581,
+      "step": 500
+    },
+    {
+      "epoch": 0.6952965235173824,
+      "grad_norm": 0.3405822515487671,
+      "learning_rate": 0.0002,
+      "loss": 1.7886,
+      "step": 510
+    },
+    {
+      "epoch": 0.7089297886843899,
+      "grad_norm": 0.305560827255249,
+      "learning_rate": 0.0002,
+      "loss": 1.778,
+      "step": 520
+    },
+    {
+      "epoch": 0.7225630538513974,
+      "grad_norm": 0.2973416745662689,
+      "learning_rate": 0.0002,
+      "loss": 1.7592,
+      "step": 530
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 0.327303946018219,
+      "learning_rate": 0.0002,
+      "loss": 1.8223,
+      "step": 540
+    },
+    {
+      "epoch": 0.7498295841854125,
+      "grad_norm": 0.62595534324646,
+      "learning_rate": 0.0002,
+      "loss": 1.8591,
+      "step": 550
+    },
+    {
+      "epoch": 0.7634628493524199,
+      "grad_norm": 0.3129784166812897,
+      "learning_rate": 0.0002,
+      "loss": 1.7466,
+      "step": 560
+    },
+    {
+      "epoch": 0.7770961145194274,
+      "grad_norm": 0.32496583461761475,
+      "learning_rate": 0.0002,
+      "loss": 1.8035,
+      "step": 570
+    },
+    {
+      "epoch": 0.7907293796864349,
+      "grad_norm": 0.3098868131637573,
+      "learning_rate": 0.0002,
+      "loss": 1.7787,
+      "step": 580
+    },
+    {
+      "epoch": 0.8043626448534424,
+      "grad_norm": 0.30726853013038635,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 590
+    },
+    {
+      "epoch": 0.8179959100204499,
+      "grad_norm": 0.2964220643043518,
+      "learning_rate": 0.0002,
+      "loss": 1.7898,
+      "step": 600
+    },
+    {
+      "epoch": 0.8316291751874574,
+      "grad_norm": 0.32352274656295776,
+      "learning_rate": 0.0002,
+      "loss": 1.8114,
+      "step": 610
+    },
+    {
+      "epoch": 0.8452624403544649,
+      "grad_norm": 0.2938912510871887,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 620
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 0.295559823513031,
+      "learning_rate": 0.0002,
+      "loss": 1.7727,
+      "step": 630
+    },
+    {
+      "epoch": 0.8725289706884799,
+      "grad_norm": 0.34102028608322144,
+      "learning_rate": 0.0002,
+      "loss": 1.9,
+      "step": 640
+    },
+    {
+      "epoch": 0.8861622358554874,
+      "grad_norm": 0.29676181077957153,
+      "learning_rate": 0.0002,
+      "loss": 1.8006,
+      "step": 650
+    },
+    {
+      "epoch": 0.8997955010224948,
+      "grad_norm": 0.3108902871608734,
+      "learning_rate": 0.0002,
+      "loss": 1.8099,
+      "step": 660
+    },
+    {
+      "epoch": 0.9134287661895024,
+      "grad_norm": 0.2690821588039398,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 670
+    },
+    {
+      "epoch": 0.9270620313565099,
+      "grad_norm": 0.32752540707588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7881,
+      "step": 680
+    },
+    {
+      "epoch": 0.9406952965235174,
+      "grad_norm": 0.8029476404190063,
+      "learning_rate": 0.0002,
+      "loss": 1.7661,
+      "step": 690
+    },
+    {
+      "epoch": 0.9543285616905249,
+      "grad_norm": 0.30534422397613525,
+      "learning_rate": 0.0002,
+      "loss": 1.7733,
+      "step": 700
+    },
+    {
+      "epoch": 0.9679618268575324,
+      "grad_norm": 0.2899954319000244,
+      "learning_rate": 0.0002,
+      "loss": 1.7614,
+      "step": 710
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 0.28814372420310974,
+      "learning_rate": 0.0002,
+      "loss": 1.7845,
+      "step": 720
+    },
+    {
+      "epoch": 0.9952283571915473,
+      "grad_norm": 0.3061596751213074,
+      "learning_rate": 0.0002,
+      "loss": 1.8865,
+      "step": 730
+    },
+    {
+      "epoch": 0.9993183367416496,
+      "eval_loss": 1.8171186447143555,
+      "eval_runtime": 53.6047,
+      "eval_samples_per_second": 9.458,
+      "eval_steps_per_second": 1.194,
+      "step": 733
+    },
+    {
+      "epoch": 1.008861622358555,
+      "grad_norm": 0.3140897750854492,
+      "learning_rate": 0.0002,
+      "loss": 1.6202,
+      "step": 740
+    },
+    {
+      "epoch": 1.0224948875255624,
+      "grad_norm": 0.3346109390258789,
+      "learning_rate": 0.0002,
+      "loss": 1.8409,
+      "step": 750
+    },
+    {
+      "epoch": 1.0361281526925699,
+      "grad_norm": 0.3582976758480072,
+      "learning_rate": 0.0002,
+      "loss": 1.6777,
+      "step": 760
+    },
+    {
+      "epoch": 1.0497614178595773,
+      "grad_norm": 0.30408260226249695,
+      "learning_rate": 0.0002,
+      "loss": 1.7306,
+      "step": 770
+    },
+    {
+      "epoch": 1.0633946830265848,
+      "grad_norm": 0.323585569858551,
+      "learning_rate": 0.0002,
+      "loss": 1.6967,
+      "step": 780
+    },
+    {
+      "epoch": 1.0770279481935923,
+      "grad_norm": 0.3474137783050537,
+      "learning_rate": 0.0002,
+      "loss": 1.768,
+      "step": 790
+    },
+    {
+      "epoch": 1.0906612133606,
+      "grad_norm": 0.35721147060394287,
+      "learning_rate": 0.0002,
+      "loss": 1.6895,
+      "step": 800
+    },
+    {
+      "epoch": 1.1042944785276074,
+      "grad_norm": 0.35366931557655334,
+      "learning_rate": 0.0002,
+      "loss": 1.718,
+      "step": 810
+    },
+    {
+      "epoch": 1.117927743694615,
+      "grad_norm": 0.3250770568847656,
+      "learning_rate": 0.0002,
+      "loss": 1.6797,
+      "step": 820
+    },
+    {
+      "epoch": 1.1315610088616224,
+      "grad_norm": 0.3293766379356384,
+      "learning_rate": 0.0002,
+      "loss": 1.6383,
+      "step": 830
+    },
+    {
+      "epoch": 1.1451942740286298,
+      "grad_norm": 0.3380851745605469,
+      "learning_rate": 0.0002,
+      "loss": 1.7353,
+      "step": 840
+    },
+    {
+      "epoch": 1.1588275391956373,
+      "grad_norm": 0.32584455609321594,
+      "learning_rate": 0.0002,
+      "loss": 1.8236,
+      "step": 850
+    },
+    {
+      "epoch": 1.1724608043626448,
+      "grad_norm": 0.45700767636299133,
+      "learning_rate": 0.0002,
+      "loss": 1.6681,
+      "step": 860
+    },
+    {
+      "epoch": 1.1860940695296525,
+      "grad_norm": 0.30944544076919556,
+      "learning_rate": 0.0002,
+      "loss": 1.7494,
+      "step": 870
+    },
+    {
+      "epoch": 1.19972733469666,
+      "grad_norm": 0.3268151581287384,
+      "learning_rate": 0.0002,
+      "loss": 1.7426,
+      "step": 880
+    },
+    {
+      "epoch": 1.2133605998636674,
+      "grad_norm": 0.39972540736198425,
+      "learning_rate": 0.0002,
+      "loss": 1.7413,
+      "step": 890
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 0.7890929579734802,
+      "learning_rate": 0.0002,
+      "loss": 1.7481,
+      "step": 900
+    },
+    {
+      "epoch": 1.2406271301976823,
+      "grad_norm": 0.3439182639122009,
+      "learning_rate": 0.0002,
+      "loss": 1.7608,
+      "step": 910
+    },
+    {
+      "epoch": 1.2542603953646898,
+      "grad_norm": 0.3986225128173828,
+      "learning_rate": 0.0002,
+      "loss": 1.7617,
+      "step": 920
+    },
+    {
+      "epoch": 1.2678936605316973,
+      "grad_norm": 0.3514605164527893,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 930
+    },
+    {
+      "epoch": 1.2815269256987047,
+      "grad_norm": 0.3682589530944824,
+      "learning_rate": 0.0002,
+      "loss": 1.6987,
+      "step": 940
+    },
+    {
+      "epoch": 1.2951601908657122,
+      "grad_norm": 0.3618335723876953,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 950
+    },
+    {
+      "epoch": 1.30879345603272,
+      "grad_norm": 0.345700740814209,
+      "learning_rate": 0.0002,
+      "loss": 1.7436,
+      "step": 960
+    },
+    {
+      "epoch": 1.3224267211997274,
+      "grad_norm": 0.3514927923679352,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 970
+    },
+    {
+      "epoch": 1.3360599863667348,
+      "grad_norm": 0.365647554397583,
+      "learning_rate": 0.0002,
+      "loss": 1.7704,
+      "step": 980
+    },
+    {
+      "epoch": 1.3496932515337423,
+      "grad_norm": 0.3407285809516907,
+      "learning_rate": 0.0002,
+      "loss": 1.7104,
+      "step": 990
+    },
+    {
+      "epoch": 1.3633265167007498,
+      "grad_norm": 0.3785437345504761,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3769597818677572,
+      "grad_norm": 0.34746724367141724,
+      "learning_rate": 0.0002,
+      "loss": 1.766,
+      "step": 1010
+    },
+    {
+      "epoch": 1.390593047034765,
+      "grad_norm": 0.362444132566452,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4042263122017724,
+      "grad_norm": 0.4424704611301422,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4178595773687799,
+      "grad_norm": 0.38722458481788635,
+      "learning_rate": 0.0002,
+      "loss": 1.726,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4314928425357873,
+      "grad_norm": 0.36089080572128296,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4451261077027948,
+      "grad_norm": 0.33817124366760254,
+      "learning_rate": 0.0002,
+      "loss": 1.6924,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4587593728698023,
+      "grad_norm": 0.34334081411361694,
+      "learning_rate": 0.0002,
+      "loss": 1.7165,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4723926380368098,
+      "grad_norm": 0.3776826858520508,
+      "learning_rate": 0.0002,
+      "loss": 1.6999,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4860259032038172,
+      "grad_norm": 0.4169026017189026,
+      "learning_rate": 0.0002,
+      "loss": 1.7605,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4996591683708247,
+      "grad_norm": 0.34898945689201355,
+      "learning_rate": 0.0002,
+      "loss": 1.7502,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5132924335378322,
+      "grad_norm": 0.34223780035972595,
+      "learning_rate": 0.0002,
+      "loss": 1.635,
+      "step": 1110
+    },
+    {
+      "epoch": 1.5269256987048399,
+      "grad_norm": 0.3686901032924652,
+      "learning_rate": 0.0002,
+      "loss": 1.7248,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5405589638718473,
+      "grad_norm": 0.35054415464401245,
+      "learning_rate": 0.0002,
+      "loss": 1.7525,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5541922290388548,
+      "grad_norm": 0.39496365189552307,
+      "learning_rate": 0.0002,
+      "loss": 1.7776,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5678254942058623,
+      "grad_norm": 0.35451626777648926,
+      "learning_rate": 0.0002,
+      "loss": 1.6574,
+      "step": 1150
+    },
+    {
+      "epoch": 1.58145875937287,
+      "grad_norm": 0.3848083019256592,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5950920245398774,
+      "grad_norm": 0.3760537803173065,
+      "learning_rate": 0.0002,
+      "loss": 1.7272,
+      "step": 1170
+    },
+    {
+      "epoch": 1.6087252897068849,
+      "grad_norm": 0.38981738686561584,
+      "learning_rate": 0.0002,
+      "loss": 1.7441,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6223585548738924,
+      "grad_norm": 0.36830949783325195,
+      "learning_rate": 0.0002,
+      "loss": 1.6951,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6359918200408998,
+      "grad_norm": 0.3405892848968506,
+      "learning_rate": 0.0002,
+      "loss": 1.6925,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6496250852079073,
+      "grad_norm": 0.39027872681617737,
+      "learning_rate": 0.0002,
+      "loss": 1.7473,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6632583503749148,
+      "grad_norm": 0.3342694044113159,
+      "learning_rate": 0.0002,
+      "loss": 1.6792,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6768916155419222,
+      "grad_norm": 0.3600076735019684,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6905248807089297,
+      "grad_norm": 0.3625542223453522,
+      "learning_rate": 0.0002,
+      "loss": 1.7021,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7041581458759372,
+      "grad_norm": 0.32170894742012024,
+      "learning_rate": 0.0002,
+      "loss": 1.6772,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7177914110429446,
+      "grad_norm": 0.3544139862060547,
+      "learning_rate": 0.0002,
+      "loss": 1.7152,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7314246762099523,
+      "grad_norm": 0.35113027691841125,
+      "learning_rate": 0.0002,
+      "loss": 1.7138,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7450579413769598,
+      "grad_norm": 0.3499974310398102,
+      "learning_rate": 0.0002,
+      "loss": 1.7095,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7586912065439673,
+      "grad_norm": 0.3285157382488251,
+      "learning_rate": 0.0002,
+      "loss": 1.7749,
+      "step": 1290
+    },
+    {
+      "epoch": 1.7723244717109747,
+      "grad_norm": 0.3701961636543274,
+      "learning_rate": 0.0002,
+      "loss": 1.6767,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7859577368779824,
+      "grad_norm": 0.3301318287849426,
+      "learning_rate": 0.0002,
+      "loss": 1.6282,
+      "step": 1310
+    },
+    {
+      "epoch": 1.79959100204499,
+      "grad_norm": 0.37801554799079895,
+      "learning_rate": 0.0002,
+      "loss": 1.7097,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8132242672119974,
+      "grad_norm": 0.3726748526096344,
+      "learning_rate": 0.0002,
+      "loss": 1.7437,
+      "step": 1330
+    },
+    {
+      "epoch": 1.8268575323790048,
+      "grad_norm": 0.4059790074825287,
+      "learning_rate": 0.0002,
+      "loss": 1.7959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 0.35712096095085144,
+      "learning_rate": 0.0002,
+      "loss": 1.7739,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8541240627130198,
+      "grad_norm": 0.35995328426361084,
+      "learning_rate": 0.0002,
+      "loss": 1.6375,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8677573278800272,
+      "grad_norm": 0.3679947257041931,
+      "learning_rate": 0.0002,
+      "loss": 1.7332,
+      "step": 1370
+    },
+    {
+      "epoch": 1.8813905930470347,
+      "grad_norm": 0.39645957946777344,
+      "learning_rate": 0.0002,
+      "loss": 1.7587,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950238582140422,
+      "grad_norm": 0.35288700461387634,
+      "learning_rate": 0.0002,
+      "loss": 1.6985,
+      "step": 1390
+    },
+    {
+      "epoch": 1.9086571233810496,
+      "grad_norm": 0.32579198479652405,
+      "learning_rate": 0.0002,
+      "loss": 1.6582,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9222903885480571,
+      "grad_norm": 0.3856561779975891,
+      "learning_rate": 0.0002,
+      "loss": 1.6948,
+      "step": 1410
+    },
+    {
+      "epoch": 1.9359236537150648,
+      "grad_norm": 0.39019331336021423,
+      "learning_rate": 0.0002,
+      "loss": 1.668,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9495569188820723,
+      "grad_norm": 0.38006502389907837,
+      "learning_rate": 0.0002,
+      "loss": 1.7774,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9631901840490797,
+      "grad_norm": 0.38100454211235046,
+      "learning_rate": 0.0002,
+      "loss": 1.8323,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9768234492160872,
+      "grad_norm": 0.3405798673629761,
+      "learning_rate": 0.0002,
+      "loss": 1.7298,
+      "step": 1450
+    },
+    {
+      "epoch": 1.990456714383095,
+      "grad_norm": 0.36582913994789124,
+      "learning_rate": 0.0002,
+      "loss": 1.7045,
+      "step": 1460
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8178424835205078,
+      "eval_runtime": 53.6524,
+      "eval_samples_per_second": 9.45,
+      "eval_steps_per_second": 1.193,
+      "step": 1467
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5864,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.535061483651072e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/training_args.bin b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..da7142eb13ed7f8418e5055c63a0fe0ca5e1972b
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-1467/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8beac9fdfb91726fdf7473c9e77541aa988c61dc8beaba03293eafbe9c0a376
+size 5560
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/README.md b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/adapter_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/adapter_model.safetensors b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..469ee8f5580b54dc41ec605ed1f30225f2fd4009
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5255b8371af121ffd938ad3b296c11bf1b161f300e8b145036ba0aaa36da236e
+size 143153376
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/optimizer.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..849848428ede06e4d606f182ef19ca8b9ad0b7fc
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d06b6771d2ca9a49988d3e599bb788b097cb6f214f737a432c934551a4d6b6
+size 72886650
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/rng_state.pth b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4c0c1ca4878f51ffb00e95998fd416c72a5508d0
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed8108cffd99043e9b0dd148146f3f148b2da7a2ba7574bb45a7036fcb69d26b
+size 14244
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/scheduler.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b82681360d9d3e2a4611f6fac274e2484a59eecd
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140316dec3419a0b494998a177826eeb12bf333a3620cbbec09475ff9aad2c93
+size 1064
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/special_tokens_map.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/tokenizer.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/tokenizer.model b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/tokenizer_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/trainer_state.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..471ad5d16cd7ad12b9adad3c6b8839104bd6ea8d
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/trainer_state.json
@@ -0,0 +1,1597 @@
+{
+  "best_metric": 1.8171186447143555,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733",
+  "epoch": 2.9993183367416494,
+  "eval_steps": 10,
+  "global_step": 2200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013633265167007498,
+      "grad_norm": 0.7714291214942932,
+      "learning_rate": 0.0002,
+      "loss": 3.0982,
+      "step": 10
+    },
+    {
+      "epoch": 0.027266530334014997,
+      "grad_norm": 0.5473978519439697,
+      "learning_rate": 0.0002,
+      "loss": 2.5206,
+      "step": 20
+    },
+    {
+      "epoch": 0.0408997955010225,
+      "grad_norm": 0.5452795624732971,
+      "learning_rate": 0.0002,
+      "loss": 2.3079,
+      "step": 30
+    },
+    {
+      "epoch": 0.054533060668029994,
+      "grad_norm": 0.5098028779029846,
+      "learning_rate": 0.0002,
+      "loss": 2.0019,
+      "step": 40
+    },
+    {
+      "epoch": 0.0681663258350375,
+      "grad_norm": 0.48062971234321594,
+      "learning_rate": 0.0002,
+      "loss": 1.9333,
+      "step": 50
+    },
+    {
+      "epoch": 0.081799591002045,
+      "grad_norm": 0.4505695104598999,
+      "learning_rate": 0.0002,
+      "loss": 1.9355,
+      "step": 60
+    },
+    {
+      "epoch": 0.09543285616905249,
+      "grad_norm": 0.41609591245651245,
+      "learning_rate": 0.0002,
+      "loss": 1.9312,
+      "step": 70
+    },
+    {
+      "epoch": 0.10906612133605999,
+      "grad_norm": 0.4323892593383789,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 80
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 0.4670293629169464,
+      "learning_rate": 0.0002,
+      "loss": 1.9294,
+      "step": 90
+    },
+    {
+      "epoch": 0.136332651670075,
+      "grad_norm": 0.40623316168785095,
+      "learning_rate": 0.0002,
+      "loss": 1.7946,
+      "step": 100
+    },
+    {
+      "epoch": 0.1499659168370825,
+      "grad_norm": 0.3620383143424988,
+      "learning_rate": 0.0002,
+      "loss": 1.8565,
+      "step": 110
+    },
+    {
+      "epoch": 0.16359918200409,
+      "grad_norm": 0.332218736410141,
+      "learning_rate": 0.0002,
+      "loss": 1.9238,
+      "step": 120
+    },
+    {
+      "epoch": 0.17723244717109748,
+      "grad_norm": 0.4004521667957306,
+      "learning_rate": 0.0002,
+      "loss": 1.93,
+      "step": 130
+    },
+    {
+      "epoch": 0.19086571233810498,
+      "grad_norm": 0.3698360323905945,
+      "learning_rate": 0.0002,
+      "loss": 1.7549,
+      "step": 140
+    },
+    {
+      "epoch": 0.20449897750511248,
+      "grad_norm": 0.3847949504852295,
+      "learning_rate": 0.0002,
+      "loss": 1.8771,
+      "step": 150
+    },
+    {
+      "epoch": 0.21813224267211997,
+      "grad_norm": 0.36843451857566833,
+      "learning_rate": 0.0002,
+      "loss": 1.8316,
+      "step": 160
+    },
+    {
+      "epoch": 0.23176550783912747,
+      "grad_norm": 0.37301021814346313,
+      "learning_rate": 0.0002,
+      "loss": 1.838,
+      "step": 170
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.3718886971473694,
+      "learning_rate": 0.0002,
+      "loss": 1.8909,
+      "step": 180
+    },
+    {
+      "epoch": 0.25903203817314246,
+      "grad_norm": 0.3088490962982178,
+      "learning_rate": 0.0002,
+      "loss": 1.8454,
+      "step": 190
+    },
+    {
+      "epoch": 0.27266530334015,
+      "grad_norm": 0.3611852526664734,
+      "learning_rate": 0.0002,
+      "loss": 1.9254,
+      "step": 200
+    },
+    {
+      "epoch": 0.28629856850715746,
+      "grad_norm": 0.36093324422836304,
+      "learning_rate": 0.0002,
+      "loss": 1.7844,
+      "step": 210
+    },
+    {
+      "epoch": 0.299931833674165,
+      "grad_norm": 0.3250400722026825,
+      "learning_rate": 0.0002,
+      "loss": 1.719,
+      "step": 220
+    },
+    {
+      "epoch": 0.31356509884117245,
+      "grad_norm": 0.3566756248474121,
+      "learning_rate": 0.0002,
+      "loss": 1.8729,
+      "step": 230
+    },
+    {
+      "epoch": 0.32719836400818,
+      "grad_norm": 0.32872408628463745,
+      "learning_rate": 0.0002,
+      "loss": 1.9259,
+      "step": 240
+    },
+    {
+      "epoch": 0.34083162917518744,
+      "grad_norm": 0.3983881175518036,
+      "learning_rate": 0.0002,
+      "loss": 1.9033,
+      "step": 250
+    },
+    {
+      "epoch": 0.35446489434219497,
+      "grad_norm": 0.3571510910987854,
+      "learning_rate": 0.0002,
+      "loss": 1.8588,
+      "step": 260
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 0.3036131262779236,
+      "learning_rate": 0.0002,
+      "loss": 1.8539,
+      "step": 270
+    },
+    {
+      "epoch": 0.38173142467620996,
+      "grad_norm": 0.36512863636016846,
+      "learning_rate": 0.0002,
+      "loss": 1.8572,
+      "step": 280
+    },
+    {
+      "epoch": 0.39536468984321743,
+      "grad_norm": 0.3429736793041229,
+      "learning_rate": 0.0002,
+      "loss": 1.8022,
+      "step": 290
+    },
+    {
+      "epoch": 0.40899795501022496,
+      "grad_norm": 0.3055964708328247,
+      "learning_rate": 0.0002,
+      "loss": 1.8754,
+      "step": 300
+    },
+    {
+      "epoch": 0.4226312201772324,
+      "grad_norm": 0.33801034092903137,
+      "learning_rate": 0.0002,
+      "loss": 1.8384,
+      "step": 310
+    },
+    {
+      "epoch": 0.43626448534423995,
+      "grad_norm": 0.348783016204834,
+      "learning_rate": 0.0002,
+      "loss": 1.7933,
+      "step": 320
+    },
+    {
+      "epoch": 0.4498977505112474,
+      "grad_norm": 0.3057514727115631,
+      "learning_rate": 0.0002,
+      "loss": 1.8451,
+      "step": 330
+    },
+    {
+      "epoch": 0.46353101567825494,
+      "grad_norm": 0.3849763572216034,
+      "learning_rate": 0.0002,
+      "loss": 1.8766,
+      "step": 340
+    },
+    {
+      "epoch": 0.47716428084526247,
+      "grad_norm": 0.30080053210258484,
+      "learning_rate": 0.0002,
+      "loss": 1.8073,
+      "step": 350
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.3595106303691864,
+      "learning_rate": 0.0002,
+      "loss": 1.8548,
+      "step": 360
+    },
+    {
+      "epoch": 0.5044308111792775,
+      "grad_norm": 0.31099820137023926,
+      "learning_rate": 0.0002,
+      "loss": 1.8232,
+      "step": 370
+    },
+    {
+      "epoch": 0.5180640763462849,
+      "grad_norm": 0.3157978355884552,
+      "learning_rate": 0.0002,
+      "loss": 1.7029,
+      "step": 380
+    },
+    {
+      "epoch": 0.5316973415132924,
+      "grad_norm": 0.27960965037345886,
+      "learning_rate": 0.0002,
+      "loss": 1.8265,
+      "step": 390
+    },
+    {
+      "epoch": 0.5453306066803,
+      "grad_norm": 0.3102385103702545,
+      "learning_rate": 0.0002,
+      "loss": 1.7414,
+      "step": 400
+    },
+    {
+      "epoch": 0.5589638718473074,
+      "grad_norm": 0.32828861474990845,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 410
+    },
+    {
+      "epoch": 0.5725971370143149,
+      "grad_norm": 0.29560017585754395,
+      "learning_rate": 0.0002,
+      "loss": 1.8165,
+      "step": 420
+    },
+    {
+      "epoch": 0.5862304021813224,
+      "grad_norm": 0.33316895365715027,
+      "learning_rate": 0.0002,
+      "loss": 1.9455,
+      "step": 430
+    },
+    {
+      "epoch": 0.59986366734833,
+      "grad_norm": 0.30420982837677,
+      "learning_rate": 0.0002,
+      "loss": 1.8241,
+      "step": 440
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 0.32619214057922363,
+      "learning_rate": 0.0002,
+      "loss": 1.7565,
+      "step": 450
+    },
+    {
+      "epoch": 0.6271301976823449,
+      "grad_norm": 0.3603750765323639,
+      "learning_rate": 0.0002,
+      "loss": 1.7945,
+      "step": 460
+    },
+    {
+      "epoch": 0.6407634628493524,
+      "grad_norm": 0.30834096670150757,
+      "learning_rate": 0.0002,
+      "loss": 1.7773,
+      "step": 470
+    },
+    {
+      "epoch": 0.65439672801636,
+      "grad_norm": 0.28756365180015564,
+      "learning_rate": 0.0002,
+      "loss": 1.8058,
+      "step": 480
+    },
+    {
+      "epoch": 0.6680299931833674,
+      "grad_norm": 0.2878406345844269,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 490
+    },
+    {
+      "epoch": 0.6816632583503749,
+      "grad_norm": 0.31329697370529175,
+      "learning_rate": 0.0002,
+      "loss": 1.8581,
+      "step": 500
+    },
+    {
+      "epoch": 0.6952965235173824,
+      "grad_norm": 0.3405822515487671,
+      "learning_rate": 0.0002,
+      "loss": 1.7886,
+      "step": 510
+    },
+    {
+      "epoch": 0.7089297886843899,
+      "grad_norm": 0.305560827255249,
+      "learning_rate": 0.0002,
+      "loss": 1.778,
+      "step": 520
+    },
+    {
+      "epoch": 0.7225630538513974,
+      "grad_norm": 0.2973416745662689,
+      "learning_rate": 0.0002,
+      "loss": 1.7592,
+      "step": 530
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 0.327303946018219,
+      "learning_rate": 0.0002,
+      "loss": 1.8223,
+      "step": 540
+    },
+    {
+      "epoch": 0.7498295841854125,
+      "grad_norm": 0.62595534324646,
+      "learning_rate": 0.0002,
+      "loss": 1.8591,
+      "step": 550
+    },
+    {
+      "epoch": 0.7634628493524199,
+      "grad_norm": 0.3129784166812897,
+      "learning_rate": 0.0002,
+      "loss": 1.7466,
+      "step": 560
+    },
+    {
+      "epoch": 0.7770961145194274,
+      "grad_norm": 0.32496583461761475,
+      "learning_rate": 0.0002,
+      "loss": 1.8035,
+      "step": 570
+    },
+    {
+      "epoch": 0.7907293796864349,
+      "grad_norm": 0.3098868131637573,
+      "learning_rate": 0.0002,
+      "loss": 1.7787,
+      "step": 580
+    },
+    {
+      "epoch": 0.8043626448534424,
+      "grad_norm": 0.30726853013038635,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 590
+    },
+    {
+      "epoch": 0.8179959100204499,
+      "grad_norm": 0.2964220643043518,
+      "learning_rate": 0.0002,
+      "loss": 1.7898,
+      "step": 600
+    },
+    {
+      "epoch": 0.8316291751874574,
+      "grad_norm": 0.32352274656295776,
+      "learning_rate": 0.0002,
+      "loss": 1.8114,
+      "step": 610
+    },
+    {
+      "epoch": 0.8452624403544649,
+      "grad_norm": 0.2938912510871887,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 620
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 0.295559823513031,
+      "learning_rate": 0.0002,
+      "loss": 1.7727,
+      "step": 630
+    },
+    {
+      "epoch": 0.8725289706884799,
+      "grad_norm": 0.34102028608322144,
+      "learning_rate": 0.0002,
+      "loss": 1.9,
+      "step": 640
+    },
+    {
+      "epoch": 0.8861622358554874,
+      "grad_norm": 0.29676181077957153,
+      "learning_rate": 0.0002,
+      "loss": 1.8006,
+      "step": 650
+    },
+    {
+      "epoch": 0.8997955010224948,
+      "grad_norm": 0.3108902871608734,
+      "learning_rate": 0.0002,
+      "loss": 1.8099,
+      "step": 660
+    },
+    {
+      "epoch": 0.9134287661895024,
+      "grad_norm": 0.2690821588039398,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 670
+    },
+    {
+      "epoch": 0.9270620313565099,
+      "grad_norm": 0.32752540707588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7881,
+      "step": 680
+    },
+    {
+      "epoch": 0.9406952965235174,
+      "grad_norm": 0.8029476404190063,
+      "learning_rate": 0.0002,
+      "loss": 1.7661,
+      "step": 690
+    },
+    {
+      "epoch": 0.9543285616905249,
+      "grad_norm": 0.30534422397613525,
+      "learning_rate": 0.0002,
+      "loss": 1.7733,
+      "step": 700
+    },
+    {
+      "epoch": 0.9679618268575324,
+      "grad_norm": 0.2899954319000244,
+      "learning_rate": 0.0002,
+      "loss": 1.7614,
+      "step": 710
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 0.28814372420310974,
+      "learning_rate": 0.0002,
+      "loss": 1.7845,
+      "step": 720
+    },
+    {
+      "epoch": 0.9952283571915473,
+      "grad_norm": 0.3061596751213074,
+      "learning_rate": 0.0002,
+      "loss": 1.8865,
+      "step": 730
+    },
+    {
+      "epoch": 0.9993183367416496,
+      "eval_loss": 1.8171186447143555,
+      "eval_runtime": 53.6047,
+      "eval_samples_per_second": 9.458,
+      "eval_steps_per_second": 1.194,
+      "step": 733
+    },
+    {
+      "epoch": 1.008861622358555,
+      "grad_norm": 0.3140897750854492,
+      "learning_rate": 0.0002,
+      "loss": 1.6202,
+      "step": 740
+    },
+    {
+      "epoch": 1.0224948875255624,
+      "grad_norm": 0.3346109390258789,
+      "learning_rate": 0.0002,
+      "loss": 1.8409,
+      "step": 750
+    },
+    {
+      "epoch": 1.0361281526925699,
+      "grad_norm": 0.3582976758480072,
+      "learning_rate": 0.0002,
+      "loss": 1.6777,
+      "step": 760
+    },
+    {
+      "epoch": 1.0497614178595773,
+      "grad_norm": 0.30408260226249695,
+      "learning_rate": 0.0002,
+      "loss": 1.7306,
+      "step": 770
+    },
+    {
+      "epoch": 1.0633946830265848,
+      "grad_norm": 0.323585569858551,
+      "learning_rate": 0.0002,
+      "loss": 1.6967,
+      "step": 780
+    },
+    {
+      "epoch": 1.0770279481935923,
+      "grad_norm": 0.3474137783050537,
+      "learning_rate": 0.0002,
+      "loss": 1.768,
+      "step": 790
+    },
+    {
+      "epoch": 1.0906612133606,
+      "grad_norm": 0.35721147060394287,
+      "learning_rate": 0.0002,
+      "loss": 1.6895,
+      "step": 800
+    },
+    {
+      "epoch": 1.1042944785276074,
+      "grad_norm": 0.35366931557655334,
+      "learning_rate": 0.0002,
+      "loss": 1.718,
+      "step": 810
+    },
+    {
+      "epoch": 1.117927743694615,
+      "grad_norm": 0.3250770568847656,
+      "learning_rate": 0.0002,
+      "loss": 1.6797,
+      "step": 820
+    },
+    {
+      "epoch": 1.1315610088616224,
+      "grad_norm": 0.3293766379356384,
+      "learning_rate": 0.0002,
+      "loss": 1.6383,
+      "step": 830
+    },
+    {
+      "epoch": 1.1451942740286298,
+      "grad_norm": 0.3380851745605469,
+      "learning_rate": 0.0002,
+      "loss": 1.7353,
+      "step": 840
+    },
+    {
+      "epoch": 1.1588275391956373,
+      "grad_norm": 0.32584455609321594,
+      "learning_rate": 0.0002,
+      "loss": 1.8236,
+      "step": 850
+    },
+    {
+      "epoch": 1.1724608043626448,
+      "grad_norm": 0.45700767636299133,
+      "learning_rate": 0.0002,
+      "loss": 1.6681,
+      "step": 860
+    },
+    {
+      "epoch": 1.1860940695296525,
+      "grad_norm": 0.30944544076919556,
+      "learning_rate": 0.0002,
+      "loss": 1.7494,
+      "step": 870
+    },
+    {
+      "epoch": 1.19972733469666,
+      "grad_norm": 0.3268151581287384,
+      "learning_rate": 0.0002,
+      "loss": 1.7426,
+      "step": 880
+    },
+    {
+      "epoch": 1.2133605998636674,
+      "grad_norm": 0.39972540736198425,
+      "learning_rate": 0.0002,
+      "loss": 1.7413,
+      "step": 890
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 0.7890929579734802,
+      "learning_rate": 0.0002,
+      "loss": 1.7481,
+      "step": 900
+    },
+    {
+      "epoch": 1.2406271301976823,
+      "grad_norm": 0.3439182639122009,
+      "learning_rate": 0.0002,
+      "loss": 1.7608,
+      "step": 910
+    },
+    {
+      "epoch": 1.2542603953646898,
+      "grad_norm": 0.3986225128173828,
+      "learning_rate": 0.0002,
+      "loss": 1.7617,
+      "step": 920
+    },
+    {
+      "epoch": 1.2678936605316973,
+      "grad_norm": 0.3514605164527893,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 930
+    },
+    {
+      "epoch": 1.2815269256987047,
+      "grad_norm": 0.3682589530944824,
+      "learning_rate": 0.0002,
+      "loss": 1.6987,
+      "step": 940
+    },
+    {
+      "epoch": 1.2951601908657122,
+      "grad_norm": 0.3618335723876953,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 950
+    },
+    {
+      "epoch": 1.30879345603272,
+      "grad_norm": 0.345700740814209,
+      "learning_rate": 0.0002,
+      "loss": 1.7436,
+      "step": 960
+    },
+    {
+      "epoch": 1.3224267211997274,
+      "grad_norm": 0.3514927923679352,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 970
+    },
+    {
+      "epoch": 1.3360599863667348,
+      "grad_norm": 0.365647554397583,
+      "learning_rate": 0.0002,
+      "loss": 1.7704,
+      "step": 980
+    },
+    {
+      "epoch": 1.3496932515337423,
+      "grad_norm": 0.3407285809516907,
+      "learning_rate": 0.0002,
+      "loss": 1.7104,
+      "step": 990
+    },
+    {
+      "epoch": 1.3633265167007498,
+      "grad_norm": 0.3785437345504761,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3769597818677572,
+      "grad_norm": 0.34746724367141724,
+      "learning_rate": 0.0002,
+      "loss": 1.766,
+      "step": 1010
+    },
+    {
+      "epoch": 1.390593047034765,
+      "grad_norm": 0.362444132566452,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4042263122017724,
+      "grad_norm": 0.4424704611301422,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4178595773687799,
+      "grad_norm": 0.38722458481788635,
+      "learning_rate": 0.0002,
+      "loss": 1.726,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4314928425357873,
+      "grad_norm": 0.36089080572128296,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4451261077027948,
+      "grad_norm": 0.33817124366760254,
+      "learning_rate": 0.0002,
+      "loss": 1.6924,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4587593728698023,
+      "grad_norm": 0.34334081411361694,
+      "learning_rate": 0.0002,
+      "loss": 1.7165,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4723926380368098,
+      "grad_norm": 0.3776826858520508,
+      "learning_rate": 0.0002,
+      "loss": 1.6999,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4860259032038172,
+      "grad_norm": 0.4169026017189026,
+      "learning_rate": 0.0002,
+      "loss": 1.7605,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4996591683708247,
+      "grad_norm": 0.34898945689201355,
+      "learning_rate": 0.0002,
+      "loss": 1.7502,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5132924335378322,
+      "grad_norm": 0.34223780035972595,
+      "learning_rate": 0.0002,
+      "loss": 1.635,
+      "step": 1110
+    },
+    {
+      "epoch": 1.5269256987048399,
+      "grad_norm": 0.3686901032924652,
+      "learning_rate": 0.0002,
+      "loss": 1.7248,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5405589638718473,
+      "grad_norm": 0.35054415464401245,
+      "learning_rate": 0.0002,
+      "loss": 1.7525,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5541922290388548,
+      "grad_norm": 0.39496365189552307,
+      "learning_rate": 0.0002,
+      "loss": 1.7776,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5678254942058623,
+      "grad_norm": 0.35451626777648926,
+      "learning_rate": 0.0002,
+      "loss": 1.6574,
+      "step": 1150
+    },
+    {
+      "epoch": 1.58145875937287,
+      "grad_norm": 0.3848083019256592,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5950920245398774,
+      "grad_norm": 0.3760537803173065,
+      "learning_rate": 0.0002,
+      "loss": 1.7272,
+      "step": 1170
+    },
+    {
+      "epoch": 1.6087252897068849,
+      "grad_norm": 0.38981738686561584,
+      "learning_rate": 0.0002,
+      "loss": 1.7441,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6223585548738924,
+      "grad_norm": 0.36830949783325195,
+      "learning_rate": 0.0002,
+      "loss": 1.6951,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6359918200408998,
+      "grad_norm": 0.3405892848968506,
+      "learning_rate": 0.0002,
+      "loss": 1.6925,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6496250852079073,
+      "grad_norm": 0.39027872681617737,
+      "learning_rate": 0.0002,
+      "loss": 1.7473,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6632583503749148,
+      "grad_norm": 0.3342694044113159,
+      "learning_rate": 0.0002,
+      "loss": 1.6792,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6768916155419222,
+      "grad_norm": 0.3600076735019684,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6905248807089297,
+      "grad_norm": 0.3625542223453522,
+      "learning_rate": 0.0002,
+      "loss": 1.7021,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7041581458759372,
+      "grad_norm": 0.32170894742012024,
+      "learning_rate": 0.0002,
+      "loss": 1.6772,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7177914110429446,
+      "grad_norm": 0.3544139862060547,
+      "learning_rate": 0.0002,
+      "loss": 1.7152,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7314246762099523,
+      "grad_norm": 0.35113027691841125,
+      "learning_rate": 0.0002,
+      "loss": 1.7138,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7450579413769598,
+      "grad_norm": 0.3499974310398102,
+      "learning_rate": 0.0002,
+      "loss": 1.7095,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7586912065439673,
+      "grad_norm": 0.3285157382488251,
+      "learning_rate": 0.0002,
+      "loss": 1.7749,
+      "step": 1290
+    },
+    {
+      "epoch": 1.7723244717109747,
+      "grad_norm": 0.3701961636543274,
+      "learning_rate": 0.0002,
+      "loss": 1.6767,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7859577368779824,
+      "grad_norm": 0.3301318287849426,
+      "learning_rate": 0.0002,
+      "loss": 1.6282,
+      "step": 1310
+    },
+    {
+      "epoch": 1.79959100204499,
+      "grad_norm": 0.37801554799079895,
+      "learning_rate": 0.0002,
+      "loss": 1.7097,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8132242672119974,
+      "grad_norm": 0.3726748526096344,
+      "learning_rate": 0.0002,
+      "loss": 1.7437,
+      "step": 1330
+    },
+    {
+      "epoch": 1.8268575323790048,
+      "grad_norm": 0.4059790074825287,
+      "learning_rate": 0.0002,
+      "loss": 1.7959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 0.35712096095085144,
+      "learning_rate": 0.0002,
+      "loss": 1.7739,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8541240627130198,
+      "grad_norm": 0.35995328426361084,
+      "learning_rate": 0.0002,
+      "loss": 1.6375,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8677573278800272,
+      "grad_norm": 0.3679947257041931,
+      "learning_rate": 0.0002,
+      "loss": 1.7332,
+      "step": 1370
+    },
+    {
+      "epoch": 1.8813905930470347,
+      "grad_norm": 0.39645957946777344,
+      "learning_rate": 0.0002,
+      "loss": 1.7587,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950238582140422,
+      "grad_norm": 0.35288700461387634,
+      "learning_rate": 0.0002,
+      "loss": 1.6985,
+      "step": 1390
+    },
+    {
+      "epoch": 1.9086571233810496,
+      "grad_norm": 0.32579198479652405,
+      "learning_rate": 0.0002,
+      "loss": 1.6582,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9222903885480571,
+      "grad_norm": 0.3856561779975891,
+      "learning_rate": 0.0002,
+      "loss": 1.6948,
+      "step": 1410
+    },
+    {
+      "epoch": 1.9359236537150648,
+      "grad_norm": 0.39019331336021423,
+      "learning_rate": 0.0002,
+      "loss": 1.668,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9495569188820723,
+      "grad_norm": 0.38006502389907837,
+      "learning_rate": 0.0002,
+      "loss": 1.7774,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9631901840490797,
+      "grad_norm": 0.38100454211235046,
+      "learning_rate": 0.0002,
+      "loss": 1.8323,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9768234492160872,
+      "grad_norm": 0.3405798673629761,
+      "learning_rate": 0.0002,
+      "loss": 1.7298,
+      "step": 1450
+    },
+    {
+      "epoch": 1.990456714383095,
+      "grad_norm": 0.36582913994789124,
+      "learning_rate": 0.0002,
+      "loss": 1.7045,
+      "step": 1460
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8178424835205078,
+      "eval_runtime": 53.6524,
+      "eval_samples_per_second": 9.45,
+      "eval_steps_per_second": 1.193,
+      "step": 1467
+    },
+    {
+      "epoch": 2.0040899795501024,
+      "grad_norm": 0.3626647889614105,
+      "learning_rate": 0.0002,
+      "loss": 1.6363,
+      "step": 1470
+    },
+    {
+      "epoch": 2.01772324471711,
+      "grad_norm": 0.40171775221824646,
+      "learning_rate": 0.0002,
+      "loss": 1.5354,
+      "step": 1480
+    },
+    {
+      "epoch": 2.0313565098841173,
+      "grad_norm": 0.5805319547653198,
+      "learning_rate": 0.0002,
+      "loss": 1.5566,
+      "step": 1490
+    },
+    {
+      "epoch": 2.044989775051125,
+      "grad_norm": 0.41954153776168823,
+      "learning_rate": 0.0002,
+      "loss": 1.546,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0586230402181322,
+      "grad_norm": 0.47190725803375244,
+      "learning_rate": 0.0002,
+      "loss": 1.6158,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0722563053851397,
+      "grad_norm": 0.4388456344604492,
+      "learning_rate": 0.0002,
+      "loss": 1.5841,
+      "step": 1520
+    },
+    {
+      "epoch": 2.085889570552147,
+      "grad_norm": 2.2171926498413086,
+      "learning_rate": 0.0002,
+      "loss": 1.5835,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0995228357191547,
+      "grad_norm": 0.4314221143722534,
+      "learning_rate": 0.0002,
+      "loss": 1.6137,
+      "step": 1540
+    },
+    {
+      "epoch": 2.113156100886162,
+      "grad_norm": 0.4154265522956848,
+      "learning_rate": 0.0002,
+      "loss": 1.5511,
+      "step": 1550
+    },
+    {
+      "epoch": 2.1267893660531696,
+      "grad_norm": 0.5025539994239807,
+      "learning_rate": 0.0002,
+      "loss": 1.6323,
+      "step": 1560
+    },
+    {
+      "epoch": 2.140422631220177,
+      "grad_norm": 0.5410493016242981,
+      "learning_rate": 0.0002,
+      "loss": 1.5903,
+      "step": 1570
+    },
+    {
+      "epoch": 2.1540558963871845,
+      "grad_norm": 0.4478487968444824,
+      "learning_rate": 0.0002,
+      "loss": 1.507,
+      "step": 1580
+    },
+    {
+      "epoch": 2.1676891615541924,
+      "grad_norm": 0.4703652560710907,
+      "learning_rate": 0.0002,
+      "loss": 1.5536,
+      "step": 1590
+    },
+    {
+      "epoch": 2.1813224267212,
+      "grad_norm": 0.4555390179157257,
+      "learning_rate": 0.0002,
+      "loss": 1.5991,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1949556918882074,
+      "grad_norm": 0.4877263903617859,
+      "learning_rate": 0.0002,
+      "loss": 1.6117,
+      "step": 1610
+    },
+    {
+      "epoch": 2.208588957055215,
+      "grad_norm": 0.48708245158195496,
+      "learning_rate": 0.0002,
+      "loss": 1.5928,
+      "step": 1620
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.47523951530456543,
+      "learning_rate": 0.0002,
+      "loss": 1.6106,
+      "step": 1630
+    },
+    {
+      "epoch": 2.23585548738923,
+      "grad_norm": 0.4889199733734131,
+      "learning_rate": 0.0002,
+      "loss": 1.6013,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2494887525562373,
+      "grad_norm": 0.4585252106189728,
+      "learning_rate": 0.0002,
+      "loss": 1.6633,
+      "step": 1650
+    },
+    {
+      "epoch": 2.2631220177232447,
+      "grad_norm": 0.4764868915081024,
+      "learning_rate": 0.0002,
+      "loss": 1.6075,
+      "step": 1660
+    },
+    {
+      "epoch": 2.276755282890252,
+      "grad_norm": 0.5028976202011108,
+      "learning_rate": 0.0002,
+      "loss": 1.6427,
+      "step": 1670
+    },
+    {
+      "epoch": 2.2903885480572597,
+      "grad_norm": 0.46131211519241333,
+      "learning_rate": 0.0002,
+      "loss": 1.6258,
+      "step": 1680
+    },
+    {
+      "epoch": 2.304021813224267,
+      "grad_norm": 0.5422874689102173,
+      "learning_rate": 0.0002,
+      "loss": 1.654,
+      "step": 1690
+    },
+    {
+      "epoch": 2.3176550783912746,
+      "grad_norm": 0.47615355253219604,
+      "learning_rate": 0.0002,
+      "loss": 1.6331,
+      "step": 1700
+    },
+    {
+      "epoch": 2.331288343558282,
+      "grad_norm": 0.48005548119544983,
+      "learning_rate": 0.0002,
+      "loss": 1.642,
+      "step": 1710
+    },
+    {
+      "epoch": 2.3449216087252895,
+      "grad_norm": 0.4387182295322418,
+      "learning_rate": 0.0002,
+      "loss": 1.581,
+      "step": 1720
+    },
+    {
+      "epoch": 2.358554873892297,
+      "grad_norm": 0.4487272799015045,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 1730
+    },
+    {
+      "epoch": 2.372188139059305,
+      "grad_norm": 0.5046455264091492,
+      "learning_rate": 0.0002,
+      "loss": 1.5089,
+      "step": 1740
+    },
+    {
+      "epoch": 2.3858214042263124,
+      "grad_norm": 0.4653521180152893,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 1750
+    },
+    {
+      "epoch": 2.39945466939332,
+      "grad_norm": 0.4737723469734192,
+      "learning_rate": 0.0002,
+      "loss": 1.6201,
+      "step": 1760
+    },
+    {
+      "epoch": 2.4130879345603273,
+      "grad_norm": 0.4501931071281433,
+      "learning_rate": 0.0002,
+      "loss": 1.5933,
+      "step": 1770
+    },
+    {
+      "epoch": 2.426721199727335,
+      "grad_norm": 0.4772880971431732,
+      "learning_rate": 0.0002,
+      "loss": 1.6321,
+      "step": 1780
+    },
+    {
+      "epoch": 2.4403544648943423,
+      "grad_norm": 0.4544616937637329,
+      "learning_rate": 0.0002,
+      "loss": 1.5454,
+      "step": 1790
+    },
+    {
+      "epoch": 2.4539877300613497,
+      "grad_norm": 0.488313227891922,
+      "learning_rate": 0.0002,
+      "loss": 1.5501,
+      "step": 1800
+    },
+    {
+      "epoch": 2.467620995228357,
+      "grad_norm": 0.5057830214500427,
+      "learning_rate": 0.0002,
+      "loss": 1.5791,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4812542603953647,
+      "grad_norm": 0.5049484968185425,
+      "learning_rate": 0.0002,
+      "loss": 1.5645,
+      "step": 1820
+    },
+    {
+      "epoch": 2.494887525562372,
+      "grad_norm": 0.44966644048690796,
+      "learning_rate": 0.0002,
+      "loss": 1.6268,
+      "step": 1830
+    },
+    {
+      "epoch": 2.5085207907293796,
+      "grad_norm": 0.5072630643844604,
+      "learning_rate": 0.0002,
+      "loss": 1.5941,
+      "step": 1840
+    },
+    {
+      "epoch": 2.522154055896387,
+      "grad_norm": 0.43989792466163635,
+      "learning_rate": 0.0002,
+      "loss": 1.5251,
+      "step": 1850
+    },
+    {
+      "epoch": 2.5357873210633946,
+      "grad_norm": 1.3504403829574585,
+      "learning_rate": 0.0002,
+      "loss": 1.563,
+      "step": 1860
+    },
+    {
+      "epoch": 2.549420586230402,
+      "grad_norm": 0.46545976400375366,
+      "learning_rate": 0.0002,
+      "loss": 1.5681,
+      "step": 1870
+    },
+    {
+      "epoch": 2.5630538513974095,
+      "grad_norm": 0.4678342044353485,
+      "learning_rate": 0.0002,
+      "loss": 1.6368,
+      "step": 1880
+    },
+    {
+      "epoch": 2.5766871165644174,
+      "grad_norm": 0.529755711555481,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5903203817314244,
+      "grad_norm": 0.5000199675559998,
+      "learning_rate": 0.0002,
+      "loss": 1.5861,
+      "step": 1900
+    },
+    {
+      "epoch": 2.6039536468984323,
+      "grad_norm": 0.5649300217628479,
+      "learning_rate": 0.0002,
+      "loss": 1.6346,
+      "step": 1910
+    },
+    {
+      "epoch": 2.61758691206544,
+      "grad_norm": 0.7920585870742798,
+      "learning_rate": 0.0002,
+      "loss": 1.6317,
+      "step": 1920
+    },
+    {
+      "epoch": 2.6312201772324473,
+      "grad_norm": 0.4960342049598694,
+      "learning_rate": 0.0002,
+      "loss": 1.643,
+      "step": 1930
+    },
+    {
+      "epoch": 2.6448534423994547,
+      "grad_norm": 0.5324710011482239,
+      "learning_rate": 0.0002,
+      "loss": 1.6099,
+      "step": 1940
+    },
+    {
+      "epoch": 2.658486707566462,
+      "grad_norm": 0.606343150138855,
+      "learning_rate": 0.0002,
+      "loss": 1.5874,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6721199727334697,
+      "grad_norm": 0.53038489818573,
+      "learning_rate": 0.0002,
+      "loss": 1.5728,
+      "step": 1960
+    },
+    {
+      "epoch": 2.685753237900477,
+      "grad_norm": 0.4579465091228485,
+      "learning_rate": 0.0002,
+      "loss": 1.5583,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6993865030674846,
+      "grad_norm": 0.4541707932949066,
+      "learning_rate": 0.0002,
+      "loss": 1.6093,
+      "step": 1980
+    },
+    {
+      "epoch": 2.713019768234492,
+      "grad_norm": 0.5009395480155945,
+      "learning_rate": 0.0002,
+      "loss": 1.5316,
+      "step": 1990
+    },
+    {
+      "epoch": 2.7266530334014996,
+      "grad_norm": 0.4723006784915924,
+      "learning_rate": 0.0002,
+      "loss": 1.6724,
+      "step": 2000
+    },
+    {
+      "epoch": 2.740286298568507,
+      "grad_norm": 0.5086126923561096,
+      "learning_rate": 0.0002,
+      "loss": 1.638,
+      "step": 2010
+    },
+    {
+      "epoch": 2.7539195637355145,
+      "grad_norm": 0.47242608666419983,
+      "learning_rate": 0.0002,
+      "loss": 1.6223,
+      "step": 2020
+    },
+    {
+      "epoch": 2.767552828902522,
+      "grad_norm": 0.44922566413879395,
+      "learning_rate": 0.0002,
+      "loss": 1.6242,
+      "step": 2030
+    },
+    {
+      "epoch": 2.78118609406953,
+      "grad_norm": 0.420259565114975,
+      "learning_rate": 0.0002,
+      "loss": 1.6837,
+      "step": 2040
+    },
+    {
+      "epoch": 2.794819359236537,
+      "grad_norm": 0.4762881100177765,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 2050
+    },
+    {
+      "epoch": 2.808452624403545,
+      "grad_norm": 0.5228786468505859,
+      "learning_rate": 0.0002,
+      "loss": 1.5506,
+      "step": 2060
+    },
+    {
+      "epoch": 2.8220858895705523,
+      "grad_norm": 0.4796035587787628,
+      "learning_rate": 0.0002,
+      "loss": 1.6347,
+      "step": 2070
+    },
+    {
+      "epoch": 2.8357191547375598,
+      "grad_norm": 0.5034735202789307,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 2080
+    },
+    {
+      "epoch": 2.8493524199045672,
+      "grad_norm": 0.48005399107933044,
+      "learning_rate": 0.0002,
+      "loss": 1.6455,
+      "step": 2090
+    },
+    {
+      "epoch": 2.8629856850715747,
+      "grad_norm": 0.578820526599884,
+      "learning_rate": 0.0002,
+      "loss": 1.6287,
+      "step": 2100
+    },
+    {
+      "epoch": 2.876618950238582,
+      "grad_norm": 0.48982638120651245,
+      "learning_rate": 0.0002,
+      "loss": 1.6021,
+      "step": 2110
+    },
+    {
+      "epoch": 2.8902522154055896,
+      "grad_norm": 0.5157325863838196,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 2120
+    },
+    {
+      "epoch": 2.903885480572597,
+      "grad_norm": 0.49149683117866516,
+      "learning_rate": 0.0002,
+      "loss": 1.6089,
+      "step": 2130
+    },
+    {
+      "epoch": 2.9175187457396046,
+      "grad_norm": 0.48584499955177307,
+      "learning_rate": 0.0002,
+      "loss": 1.5881,
+      "step": 2140
+    },
+    {
+      "epoch": 2.931152010906612,
+      "grad_norm": 0.5199017524719238,
+      "learning_rate": 0.0002,
+      "loss": 1.5833,
+      "step": 2150
+    },
+    {
+      "epoch": 2.9447852760736195,
+      "grad_norm": 0.5788236856460571,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 2160
+    },
+    {
+      "epoch": 2.958418541240627,
+      "grad_norm": 0.48664185404777527,
+      "learning_rate": 0.0002,
+      "loss": 1.6103,
+      "step": 2170
+    },
+    {
+      "epoch": 2.9720518064076344,
+      "grad_norm": 0.5026682615280151,
+      "learning_rate": 0.0002,
+      "loss": 1.5765,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9856850715746424,
+      "grad_norm": 0.49317044019699097,
+      "learning_rate": 0.0002,
+      "loss": 1.6626,
+      "step": 2190
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "grad_norm": 0.5729128122329712,
+      "learning_rate": 0.0002,
+      "loss": 1.5871,
+      "step": 2200
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "eval_loss": 1.8527295589447021,
+      "eval_runtime": 53.6403,
+      "eval_samples_per_second": 9.452,
+      "eval_steps_per_second": 1.193,
+      "step": 2200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5864,
+  "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": 1.1302592225476608e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/training_args.bin b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..da7142eb13ed7f8418e5055c63a0fe0ca5e1972b
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8beac9fdfb91726fdf7473c9e77541aa988c61dc8beaba03293eafbe9c0a376
+size 5560
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/README.md b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/adapter_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/adapter_model.safetensors b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a053039fd404a8af1cca2911cc0aaeabe3d34ea9
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d322a6c4b731d65414a02fb7b29ee75b00db72c16e6c8653c71479e00fa0e1
+size 143153376
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/optimizer.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7738dc60aa62c1609414c0f2b55306f9b1e09171
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09e218b33248d7341dd93648fcfd8314302bc10aba9cad499e60cdb6caf4e77
+size 72886650
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/rng_state.pth b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..11d2f37303419521e74c16b6b0a3234dab88fd87
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:908b095cc2af9ec1c6d23f35a53f10a3767da3c4e2463cb3255296c45b67b341
+size 14244
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/scheduler.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cdc465ca7f4d94e4cd869785f8e501d0e0595c78
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa0d97a46a5f131b267c442bd1fc27c085f03878ba83833c5fb8f7c8691b001
+size 1064
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/special_tokens_map.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/tokenizer.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/tokenizer.model b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/tokenizer_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/trainer_state.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..91db24949569787a6742f1ab1c72e7155c190e0d
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/trainer_state.json
@@ -0,0 +1,2116 @@
+{
+  "best_metric": 1.8171186447143555,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733",
+  "epoch": 4.0,
+  "eval_steps": 10,
+  "global_step": 2934,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013633265167007498,
+      "grad_norm": 0.7714291214942932,
+      "learning_rate": 0.0002,
+      "loss": 3.0982,
+      "step": 10
+    },
+    {
+      "epoch": 0.027266530334014997,
+      "grad_norm": 0.5473978519439697,
+      "learning_rate": 0.0002,
+      "loss": 2.5206,
+      "step": 20
+    },
+    {
+      "epoch": 0.0408997955010225,
+      "grad_norm": 0.5452795624732971,
+      "learning_rate": 0.0002,
+      "loss": 2.3079,
+      "step": 30
+    },
+    {
+      "epoch": 0.054533060668029994,
+      "grad_norm": 0.5098028779029846,
+      "learning_rate": 0.0002,
+      "loss": 2.0019,
+      "step": 40
+    },
+    {
+      "epoch": 0.0681663258350375,
+      "grad_norm": 0.48062971234321594,
+      "learning_rate": 0.0002,
+      "loss": 1.9333,
+      "step": 50
+    },
+    {
+      "epoch": 0.081799591002045,
+      "grad_norm": 0.4505695104598999,
+      "learning_rate": 0.0002,
+      "loss": 1.9355,
+      "step": 60
+    },
+    {
+      "epoch": 0.09543285616905249,
+      "grad_norm": 0.41609591245651245,
+      "learning_rate": 0.0002,
+      "loss": 1.9312,
+      "step": 70
+    },
+    {
+      "epoch": 0.10906612133605999,
+      "grad_norm": 0.4323892593383789,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 80
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 0.4670293629169464,
+      "learning_rate": 0.0002,
+      "loss": 1.9294,
+      "step": 90
+    },
+    {
+      "epoch": 0.136332651670075,
+      "grad_norm": 0.40623316168785095,
+      "learning_rate": 0.0002,
+      "loss": 1.7946,
+      "step": 100
+    },
+    {
+      "epoch": 0.1499659168370825,
+      "grad_norm": 0.3620383143424988,
+      "learning_rate": 0.0002,
+      "loss": 1.8565,
+      "step": 110
+    },
+    {
+      "epoch": 0.16359918200409,
+      "grad_norm": 0.332218736410141,
+      "learning_rate": 0.0002,
+      "loss": 1.9238,
+      "step": 120
+    },
+    {
+      "epoch": 0.17723244717109748,
+      "grad_norm": 0.4004521667957306,
+      "learning_rate": 0.0002,
+      "loss": 1.93,
+      "step": 130
+    },
+    {
+      "epoch": 0.19086571233810498,
+      "grad_norm": 0.3698360323905945,
+      "learning_rate": 0.0002,
+      "loss": 1.7549,
+      "step": 140
+    },
+    {
+      "epoch": 0.20449897750511248,
+      "grad_norm": 0.3847949504852295,
+      "learning_rate": 0.0002,
+      "loss": 1.8771,
+      "step": 150
+    },
+    {
+      "epoch": 0.21813224267211997,
+      "grad_norm": 0.36843451857566833,
+      "learning_rate": 0.0002,
+      "loss": 1.8316,
+      "step": 160
+    },
+    {
+      "epoch": 0.23176550783912747,
+      "grad_norm": 0.37301021814346313,
+      "learning_rate": 0.0002,
+      "loss": 1.838,
+      "step": 170
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.3718886971473694,
+      "learning_rate": 0.0002,
+      "loss": 1.8909,
+      "step": 180
+    },
+    {
+      "epoch": 0.25903203817314246,
+      "grad_norm": 0.3088490962982178,
+      "learning_rate": 0.0002,
+      "loss": 1.8454,
+      "step": 190
+    },
+    {
+      "epoch": 0.27266530334015,
+      "grad_norm": 0.3611852526664734,
+      "learning_rate": 0.0002,
+      "loss": 1.9254,
+      "step": 200
+    },
+    {
+      "epoch": 0.28629856850715746,
+      "grad_norm": 0.36093324422836304,
+      "learning_rate": 0.0002,
+      "loss": 1.7844,
+      "step": 210
+    },
+    {
+      "epoch": 0.299931833674165,
+      "grad_norm": 0.3250400722026825,
+      "learning_rate": 0.0002,
+      "loss": 1.719,
+      "step": 220
+    },
+    {
+      "epoch": 0.31356509884117245,
+      "grad_norm": 0.3566756248474121,
+      "learning_rate": 0.0002,
+      "loss": 1.8729,
+      "step": 230
+    },
+    {
+      "epoch": 0.32719836400818,
+      "grad_norm": 0.32872408628463745,
+      "learning_rate": 0.0002,
+      "loss": 1.9259,
+      "step": 240
+    },
+    {
+      "epoch": 0.34083162917518744,
+      "grad_norm": 0.3983881175518036,
+      "learning_rate": 0.0002,
+      "loss": 1.9033,
+      "step": 250
+    },
+    {
+      "epoch": 0.35446489434219497,
+      "grad_norm": 0.3571510910987854,
+      "learning_rate": 0.0002,
+      "loss": 1.8588,
+      "step": 260
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 0.3036131262779236,
+      "learning_rate": 0.0002,
+      "loss": 1.8539,
+      "step": 270
+    },
+    {
+      "epoch": 0.38173142467620996,
+      "grad_norm": 0.36512863636016846,
+      "learning_rate": 0.0002,
+      "loss": 1.8572,
+      "step": 280
+    },
+    {
+      "epoch": 0.39536468984321743,
+      "grad_norm": 0.3429736793041229,
+      "learning_rate": 0.0002,
+      "loss": 1.8022,
+      "step": 290
+    },
+    {
+      "epoch": 0.40899795501022496,
+      "grad_norm": 0.3055964708328247,
+      "learning_rate": 0.0002,
+      "loss": 1.8754,
+      "step": 300
+    },
+    {
+      "epoch": 0.4226312201772324,
+      "grad_norm": 0.33801034092903137,
+      "learning_rate": 0.0002,
+      "loss": 1.8384,
+      "step": 310
+    },
+    {
+      "epoch": 0.43626448534423995,
+      "grad_norm": 0.348783016204834,
+      "learning_rate": 0.0002,
+      "loss": 1.7933,
+      "step": 320
+    },
+    {
+      "epoch": 0.4498977505112474,
+      "grad_norm": 0.3057514727115631,
+      "learning_rate": 0.0002,
+      "loss": 1.8451,
+      "step": 330
+    },
+    {
+      "epoch": 0.46353101567825494,
+      "grad_norm": 0.3849763572216034,
+      "learning_rate": 0.0002,
+      "loss": 1.8766,
+      "step": 340
+    },
+    {
+      "epoch": 0.47716428084526247,
+      "grad_norm": 0.30080053210258484,
+      "learning_rate": 0.0002,
+      "loss": 1.8073,
+      "step": 350
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.3595106303691864,
+      "learning_rate": 0.0002,
+      "loss": 1.8548,
+      "step": 360
+    },
+    {
+      "epoch": 0.5044308111792775,
+      "grad_norm": 0.31099820137023926,
+      "learning_rate": 0.0002,
+      "loss": 1.8232,
+      "step": 370
+    },
+    {
+      "epoch": 0.5180640763462849,
+      "grad_norm": 0.3157978355884552,
+      "learning_rate": 0.0002,
+      "loss": 1.7029,
+      "step": 380
+    },
+    {
+      "epoch": 0.5316973415132924,
+      "grad_norm": 0.27960965037345886,
+      "learning_rate": 0.0002,
+      "loss": 1.8265,
+      "step": 390
+    },
+    {
+      "epoch": 0.5453306066803,
+      "grad_norm": 0.3102385103702545,
+      "learning_rate": 0.0002,
+      "loss": 1.7414,
+      "step": 400
+    },
+    {
+      "epoch": 0.5589638718473074,
+      "grad_norm": 0.32828861474990845,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 410
+    },
+    {
+      "epoch": 0.5725971370143149,
+      "grad_norm": 0.29560017585754395,
+      "learning_rate": 0.0002,
+      "loss": 1.8165,
+      "step": 420
+    },
+    {
+      "epoch": 0.5862304021813224,
+      "grad_norm": 0.33316895365715027,
+      "learning_rate": 0.0002,
+      "loss": 1.9455,
+      "step": 430
+    },
+    {
+      "epoch": 0.59986366734833,
+      "grad_norm": 0.30420982837677,
+      "learning_rate": 0.0002,
+      "loss": 1.8241,
+      "step": 440
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 0.32619214057922363,
+      "learning_rate": 0.0002,
+      "loss": 1.7565,
+      "step": 450
+    },
+    {
+      "epoch": 0.6271301976823449,
+      "grad_norm": 0.3603750765323639,
+      "learning_rate": 0.0002,
+      "loss": 1.7945,
+      "step": 460
+    },
+    {
+      "epoch": 0.6407634628493524,
+      "grad_norm": 0.30834096670150757,
+      "learning_rate": 0.0002,
+      "loss": 1.7773,
+      "step": 470
+    },
+    {
+      "epoch": 0.65439672801636,
+      "grad_norm": 0.28756365180015564,
+      "learning_rate": 0.0002,
+      "loss": 1.8058,
+      "step": 480
+    },
+    {
+      "epoch": 0.6680299931833674,
+      "grad_norm": 0.2878406345844269,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 490
+    },
+    {
+      "epoch": 0.6816632583503749,
+      "grad_norm": 0.31329697370529175,
+      "learning_rate": 0.0002,
+      "loss": 1.8581,
+      "step": 500
+    },
+    {
+      "epoch": 0.6952965235173824,
+      "grad_norm": 0.3405822515487671,
+      "learning_rate": 0.0002,
+      "loss": 1.7886,
+      "step": 510
+    },
+    {
+      "epoch": 0.7089297886843899,
+      "grad_norm": 0.305560827255249,
+      "learning_rate": 0.0002,
+      "loss": 1.778,
+      "step": 520
+    },
+    {
+      "epoch": 0.7225630538513974,
+      "grad_norm": 0.2973416745662689,
+      "learning_rate": 0.0002,
+      "loss": 1.7592,
+      "step": 530
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 0.327303946018219,
+      "learning_rate": 0.0002,
+      "loss": 1.8223,
+      "step": 540
+    },
+    {
+      "epoch": 0.7498295841854125,
+      "grad_norm": 0.62595534324646,
+      "learning_rate": 0.0002,
+      "loss": 1.8591,
+      "step": 550
+    },
+    {
+      "epoch": 0.7634628493524199,
+      "grad_norm": 0.3129784166812897,
+      "learning_rate": 0.0002,
+      "loss": 1.7466,
+      "step": 560
+    },
+    {
+      "epoch": 0.7770961145194274,
+      "grad_norm": 0.32496583461761475,
+      "learning_rate": 0.0002,
+      "loss": 1.8035,
+      "step": 570
+    },
+    {
+      "epoch": 0.7907293796864349,
+      "grad_norm": 0.3098868131637573,
+      "learning_rate": 0.0002,
+      "loss": 1.7787,
+      "step": 580
+    },
+    {
+      "epoch": 0.8043626448534424,
+      "grad_norm": 0.30726853013038635,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 590
+    },
+    {
+      "epoch": 0.8179959100204499,
+      "grad_norm": 0.2964220643043518,
+      "learning_rate": 0.0002,
+      "loss": 1.7898,
+      "step": 600
+    },
+    {
+      "epoch": 0.8316291751874574,
+      "grad_norm": 0.32352274656295776,
+      "learning_rate": 0.0002,
+      "loss": 1.8114,
+      "step": 610
+    },
+    {
+      "epoch": 0.8452624403544649,
+      "grad_norm": 0.2938912510871887,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 620
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 0.295559823513031,
+      "learning_rate": 0.0002,
+      "loss": 1.7727,
+      "step": 630
+    },
+    {
+      "epoch": 0.8725289706884799,
+      "grad_norm": 0.34102028608322144,
+      "learning_rate": 0.0002,
+      "loss": 1.9,
+      "step": 640
+    },
+    {
+      "epoch": 0.8861622358554874,
+      "grad_norm": 0.29676181077957153,
+      "learning_rate": 0.0002,
+      "loss": 1.8006,
+      "step": 650
+    },
+    {
+      "epoch": 0.8997955010224948,
+      "grad_norm": 0.3108902871608734,
+      "learning_rate": 0.0002,
+      "loss": 1.8099,
+      "step": 660
+    },
+    {
+      "epoch": 0.9134287661895024,
+      "grad_norm": 0.2690821588039398,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 670
+    },
+    {
+      "epoch": 0.9270620313565099,
+      "grad_norm": 0.32752540707588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7881,
+      "step": 680
+    },
+    {
+      "epoch": 0.9406952965235174,
+      "grad_norm": 0.8029476404190063,
+      "learning_rate": 0.0002,
+      "loss": 1.7661,
+      "step": 690
+    },
+    {
+      "epoch": 0.9543285616905249,
+      "grad_norm": 0.30534422397613525,
+      "learning_rate": 0.0002,
+      "loss": 1.7733,
+      "step": 700
+    },
+    {
+      "epoch": 0.9679618268575324,
+      "grad_norm": 0.2899954319000244,
+      "learning_rate": 0.0002,
+      "loss": 1.7614,
+      "step": 710
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 0.28814372420310974,
+      "learning_rate": 0.0002,
+      "loss": 1.7845,
+      "step": 720
+    },
+    {
+      "epoch": 0.9952283571915473,
+      "grad_norm": 0.3061596751213074,
+      "learning_rate": 0.0002,
+      "loss": 1.8865,
+      "step": 730
+    },
+    {
+      "epoch": 0.9993183367416496,
+      "eval_loss": 1.8171186447143555,
+      "eval_runtime": 53.6047,
+      "eval_samples_per_second": 9.458,
+      "eval_steps_per_second": 1.194,
+      "step": 733
+    },
+    {
+      "epoch": 1.008861622358555,
+      "grad_norm": 0.3140897750854492,
+      "learning_rate": 0.0002,
+      "loss": 1.6202,
+      "step": 740
+    },
+    {
+      "epoch": 1.0224948875255624,
+      "grad_norm": 0.3346109390258789,
+      "learning_rate": 0.0002,
+      "loss": 1.8409,
+      "step": 750
+    },
+    {
+      "epoch": 1.0361281526925699,
+      "grad_norm": 0.3582976758480072,
+      "learning_rate": 0.0002,
+      "loss": 1.6777,
+      "step": 760
+    },
+    {
+      "epoch": 1.0497614178595773,
+      "grad_norm": 0.30408260226249695,
+      "learning_rate": 0.0002,
+      "loss": 1.7306,
+      "step": 770
+    },
+    {
+      "epoch": 1.0633946830265848,
+      "grad_norm": 0.323585569858551,
+      "learning_rate": 0.0002,
+      "loss": 1.6967,
+      "step": 780
+    },
+    {
+      "epoch": 1.0770279481935923,
+      "grad_norm": 0.3474137783050537,
+      "learning_rate": 0.0002,
+      "loss": 1.768,
+      "step": 790
+    },
+    {
+      "epoch": 1.0906612133606,
+      "grad_norm": 0.35721147060394287,
+      "learning_rate": 0.0002,
+      "loss": 1.6895,
+      "step": 800
+    },
+    {
+      "epoch": 1.1042944785276074,
+      "grad_norm": 0.35366931557655334,
+      "learning_rate": 0.0002,
+      "loss": 1.718,
+      "step": 810
+    },
+    {
+      "epoch": 1.117927743694615,
+      "grad_norm": 0.3250770568847656,
+      "learning_rate": 0.0002,
+      "loss": 1.6797,
+      "step": 820
+    },
+    {
+      "epoch": 1.1315610088616224,
+      "grad_norm": 0.3293766379356384,
+      "learning_rate": 0.0002,
+      "loss": 1.6383,
+      "step": 830
+    },
+    {
+      "epoch": 1.1451942740286298,
+      "grad_norm": 0.3380851745605469,
+      "learning_rate": 0.0002,
+      "loss": 1.7353,
+      "step": 840
+    },
+    {
+      "epoch": 1.1588275391956373,
+      "grad_norm": 0.32584455609321594,
+      "learning_rate": 0.0002,
+      "loss": 1.8236,
+      "step": 850
+    },
+    {
+      "epoch": 1.1724608043626448,
+      "grad_norm": 0.45700767636299133,
+      "learning_rate": 0.0002,
+      "loss": 1.6681,
+      "step": 860
+    },
+    {
+      "epoch": 1.1860940695296525,
+      "grad_norm": 0.30944544076919556,
+      "learning_rate": 0.0002,
+      "loss": 1.7494,
+      "step": 870
+    },
+    {
+      "epoch": 1.19972733469666,
+      "grad_norm": 0.3268151581287384,
+      "learning_rate": 0.0002,
+      "loss": 1.7426,
+      "step": 880
+    },
+    {
+      "epoch": 1.2133605998636674,
+      "grad_norm": 0.39972540736198425,
+      "learning_rate": 0.0002,
+      "loss": 1.7413,
+      "step": 890
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 0.7890929579734802,
+      "learning_rate": 0.0002,
+      "loss": 1.7481,
+      "step": 900
+    },
+    {
+      "epoch": 1.2406271301976823,
+      "grad_norm": 0.3439182639122009,
+      "learning_rate": 0.0002,
+      "loss": 1.7608,
+      "step": 910
+    },
+    {
+      "epoch": 1.2542603953646898,
+      "grad_norm": 0.3986225128173828,
+      "learning_rate": 0.0002,
+      "loss": 1.7617,
+      "step": 920
+    },
+    {
+      "epoch": 1.2678936605316973,
+      "grad_norm": 0.3514605164527893,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 930
+    },
+    {
+      "epoch": 1.2815269256987047,
+      "grad_norm": 0.3682589530944824,
+      "learning_rate": 0.0002,
+      "loss": 1.6987,
+      "step": 940
+    },
+    {
+      "epoch": 1.2951601908657122,
+      "grad_norm": 0.3618335723876953,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 950
+    },
+    {
+      "epoch": 1.30879345603272,
+      "grad_norm": 0.345700740814209,
+      "learning_rate": 0.0002,
+      "loss": 1.7436,
+      "step": 960
+    },
+    {
+      "epoch": 1.3224267211997274,
+      "grad_norm": 0.3514927923679352,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 970
+    },
+    {
+      "epoch": 1.3360599863667348,
+      "grad_norm": 0.365647554397583,
+      "learning_rate": 0.0002,
+      "loss": 1.7704,
+      "step": 980
+    },
+    {
+      "epoch": 1.3496932515337423,
+      "grad_norm": 0.3407285809516907,
+      "learning_rate": 0.0002,
+      "loss": 1.7104,
+      "step": 990
+    },
+    {
+      "epoch": 1.3633265167007498,
+      "grad_norm": 0.3785437345504761,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3769597818677572,
+      "grad_norm": 0.34746724367141724,
+      "learning_rate": 0.0002,
+      "loss": 1.766,
+      "step": 1010
+    },
+    {
+      "epoch": 1.390593047034765,
+      "grad_norm": 0.362444132566452,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4042263122017724,
+      "grad_norm": 0.4424704611301422,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4178595773687799,
+      "grad_norm": 0.38722458481788635,
+      "learning_rate": 0.0002,
+      "loss": 1.726,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4314928425357873,
+      "grad_norm": 0.36089080572128296,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4451261077027948,
+      "grad_norm": 0.33817124366760254,
+      "learning_rate": 0.0002,
+      "loss": 1.6924,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4587593728698023,
+      "grad_norm": 0.34334081411361694,
+      "learning_rate": 0.0002,
+      "loss": 1.7165,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4723926380368098,
+      "grad_norm": 0.3776826858520508,
+      "learning_rate": 0.0002,
+      "loss": 1.6999,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4860259032038172,
+      "grad_norm": 0.4169026017189026,
+      "learning_rate": 0.0002,
+      "loss": 1.7605,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4996591683708247,
+      "grad_norm": 0.34898945689201355,
+      "learning_rate": 0.0002,
+      "loss": 1.7502,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5132924335378322,
+      "grad_norm": 0.34223780035972595,
+      "learning_rate": 0.0002,
+      "loss": 1.635,
+      "step": 1110
+    },
+    {
+      "epoch": 1.5269256987048399,
+      "grad_norm": 0.3686901032924652,
+      "learning_rate": 0.0002,
+      "loss": 1.7248,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5405589638718473,
+      "grad_norm": 0.35054415464401245,
+      "learning_rate": 0.0002,
+      "loss": 1.7525,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5541922290388548,
+      "grad_norm": 0.39496365189552307,
+      "learning_rate": 0.0002,
+      "loss": 1.7776,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5678254942058623,
+      "grad_norm": 0.35451626777648926,
+      "learning_rate": 0.0002,
+      "loss": 1.6574,
+      "step": 1150
+    },
+    {
+      "epoch": 1.58145875937287,
+      "grad_norm": 0.3848083019256592,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5950920245398774,
+      "grad_norm": 0.3760537803173065,
+      "learning_rate": 0.0002,
+      "loss": 1.7272,
+      "step": 1170
+    },
+    {
+      "epoch": 1.6087252897068849,
+      "grad_norm": 0.38981738686561584,
+      "learning_rate": 0.0002,
+      "loss": 1.7441,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6223585548738924,
+      "grad_norm": 0.36830949783325195,
+      "learning_rate": 0.0002,
+      "loss": 1.6951,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6359918200408998,
+      "grad_norm": 0.3405892848968506,
+      "learning_rate": 0.0002,
+      "loss": 1.6925,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6496250852079073,
+      "grad_norm": 0.39027872681617737,
+      "learning_rate": 0.0002,
+      "loss": 1.7473,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6632583503749148,
+      "grad_norm": 0.3342694044113159,
+      "learning_rate": 0.0002,
+      "loss": 1.6792,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6768916155419222,
+      "grad_norm": 0.3600076735019684,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6905248807089297,
+      "grad_norm": 0.3625542223453522,
+      "learning_rate": 0.0002,
+      "loss": 1.7021,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7041581458759372,
+      "grad_norm": 0.32170894742012024,
+      "learning_rate": 0.0002,
+      "loss": 1.6772,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7177914110429446,
+      "grad_norm": 0.3544139862060547,
+      "learning_rate": 0.0002,
+      "loss": 1.7152,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7314246762099523,
+      "grad_norm": 0.35113027691841125,
+      "learning_rate": 0.0002,
+      "loss": 1.7138,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7450579413769598,
+      "grad_norm": 0.3499974310398102,
+      "learning_rate": 0.0002,
+      "loss": 1.7095,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7586912065439673,
+      "grad_norm": 0.3285157382488251,
+      "learning_rate": 0.0002,
+      "loss": 1.7749,
+      "step": 1290
+    },
+    {
+      "epoch": 1.7723244717109747,
+      "grad_norm": 0.3701961636543274,
+      "learning_rate": 0.0002,
+      "loss": 1.6767,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7859577368779824,
+      "grad_norm": 0.3301318287849426,
+      "learning_rate": 0.0002,
+      "loss": 1.6282,
+      "step": 1310
+    },
+    {
+      "epoch": 1.79959100204499,
+      "grad_norm": 0.37801554799079895,
+      "learning_rate": 0.0002,
+      "loss": 1.7097,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8132242672119974,
+      "grad_norm": 0.3726748526096344,
+      "learning_rate": 0.0002,
+      "loss": 1.7437,
+      "step": 1330
+    },
+    {
+      "epoch": 1.8268575323790048,
+      "grad_norm": 0.4059790074825287,
+      "learning_rate": 0.0002,
+      "loss": 1.7959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 0.35712096095085144,
+      "learning_rate": 0.0002,
+      "loss": 1.7739,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8541240627130198,
+      "grad_norm": 0.35995328426361084,
+      "learning_rate": 0.0002,
+      "loss": 1.6375,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8677573278800272,
+      "grad_norm": 0.3679947257041931,
+      "learning_rate": 0.0002,
+      "loss": 1.7332,
+      "step": 1370
+    },
+    {
+      "epoch": 1.8813905930470347,
+      "grad_norm": 0.39645957946777344,
+      "learning_rate": 0.0002,
+      "loss": 1.7587,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950238582140422,
+      "grad_norm": 0.35288700461387634,
+      "learning_rate": 0.0002,
+      "loss": 1.6985,
+      "step": 1390
+    },
+    {
+      "epoch": 1.9086571233810496,
+      "grad_norm": 0.32579198479652405,
+      "learning_rate": 0.0002,
+      "loss": 1.6582,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9222903885480571,
+      "grad_norm": 0.3856561779975891,
+      "learning_rate": 0.0002,
+      "loss": 1.6948,
+      "step": 1410
+    },
+    {
+      "epoch": 1.9359236537150648,
+      "grad_norm": 0.39019331336021423,
+      "learning_rate": 0.0002,
+      "loss": 1.668,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9495569188820723,
+      "grad_norm": 0.38006502389907837,
+      "learning_rate": 0.0002,
+      "loss": 1.7774,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9631901840490797,
+      "grad_norm": 0.38100454211235046,
+      "learning_rate": 0.0002,
+      "loss": 1.8323,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9768234492160872,
+      "grad_norm": 0.3405798673629761,
+      "learning_rate": 0.0002,
+      "loss": 1.7298,
+      "step": 1450
+    },
+    {
+      "epoch": 1.990456714383095,
+      "grad_norm": 0.36582913994789124,
+      "learning_rate": 0.0002,
+      "loss": 1.7045,
+      "step": 1460
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8178424835205078,
+      "eval_runtime": 53.6524,
+      "eval_samples_per_second": 9.45,
+      "eval_steps_per_second": 1.193,
+      "step": 1467
+    },
+    {
+      "epoch": 2.0040899795501024,
+      "grad_norm": 0.3626647889614105,
+      "learning_rate": 0.0002,
+      "loss": 1.6363,
+      "step": 1470
+    },
+    {
+      "epoch": 2.01772324471711,
+      "grad_norm": 0.40171775221824646,
+      "learning_rate": 0.0002,
+      "loss": 1.5354,
+      "step": 1480
+    },
+    {
+      "epoch": 2.0313565098841173,
+      "grad_norm": 0.5805319547653198,
+      "learning_rate": 0.0002,
+      "loss": 1.5566,
+      "step": 1490
+    },
+    {
+      "epoch": 2.044989775051125,
+      "grad_norm": 0.41954153776168823,
+      "learning_rate": 0.0002,
+      "loss": 1.546,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0586230402181322,
+      "grad_norm": 0.47190725803375244,
+      "learning_rate": 0.0002,
+      "loss": 1.6158,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0722563053851397,
+      "grad_norm": 0.4388456344604492,
+      "learning_rate": 0.0002,
+      "loss": 1.5841,
+      "step": 1520
+    },
+    {
+      "epoch": 2.085889570552147,
+      "grad_norm": 2.2171926498413086,
+      "learning_rate": 0.0002,
+      "loss": 1.5835,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0995228357191547,
+      "grad_norm": 0.4314221143722534,
+      "learning_rate": 0.0002,
+      "loss": 1.6137,
+      "step": 1540
+    },
+    {
+      "epoch": 2.113156100886162,
+      "grad_norm": 0.4154265522956848,
+      "learning_rate": 0.0002,
+      "loss": 1.5511,
+      "step": 1550
+    },
+    {
+      "epoch": 2.1267893660531696,
+      "grad_norm": 0.5025539994239807,
+      "learning_rate": 0.0002,
+      "loss": 1.6323,
+      "step": 1560
+    },
+    {
+      "epoch": 2.140422631220177,
+      "grad_norm": 0.5410493016242981,
+      "learning_rate": 0.0002,
+      "loss": 1.5903,
+      "step": 1570
+    },
+    {
+      "epoch": 2.1540558963871845,
+      "grad_norm": 0.4478487968444824,
+      "learning_rate": 0.0002,
+      "loss": 1.507,
+      "step": 1580
+    },
+    {
+      "epoch": 2.1676891615541924,
+      "grad_norm": 0.4703652560710907,
+      "learning_rate": 0.0002,
+      "loss": 1.5536,
+      "step": 1590
+    },
+    {
+      "epoch": 2.1813224267212,
+      "grad_norm": 0.4555390179157257,
+      "learning_rate": 0.0002,
+      "loss": 1.5991,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1949556918882074,
+      "grad_norm": 0.4877263903617859,
+      "learning_rate": 0.0002,
+      "loss": 1.6117,
+      "step": 1610
+    },
+    {
+      "epoch": 2.208588957055215,
+      "grad_norm": 0.48708245158195496,
+      "learning_rate": 0.0002,
+      "loss": 1.5928,
+      "step": 1620
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.47523951530456543,
+      "learning_rate": 0.0002,
+      "loss": 1.6106,
+      "step": 1630
+    },
+    {
+      "epoch": 2.23585548738923,
+      "grad_norm": 0.4889199733734131,
+      "learning_rate": 0.0002,
+      "loss": 1.6013,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2494887525562373,
+      "grad_norm": 0.4585252106189728,
+      "learning_rate": 0.0002,
+      "loss": 1.6633,
+      "step": 1650
+    },
+    {
+      "epoch": 2.2631220177232447,
+      "grad_norm": 0.4764868915081024,
+      "learning_rate": 0.0002,
+      "loss": 1.6075,
+      "step": 1660
+    },
+    {
+      "epoch": 2.276755282890252,
+      "grad_norm": 0.5028976202011108,
+      "learning_rate": 0.0002,
+      "loss": 1.6427,
+      "step": 1670
+    },
+    {
+      "epoch": 2.2903885480572597,
+      "grad_norm": 0.46131211519241333,
+      "learning_rate": 0.0002,
+      "loss": 1.6258,
+      "step": 1680
+    },
+    {
+      "epoch": 2.304021813224267,
+      "grad_norm": 0.5422874689102173,
+      "learning_rate": 0.0002,
+      "loss": 1.654,
+      "step": 1690
+    },
+    {
+      "epoch": 2.3176550783912746,
+      "grad_norm": 0.47615355253219604,
+      "learning_rate": 0.0002,
+      "loss": 1.6331,
+      "step": 1700
+    },
+    {
+      "epoch": 2.331288343558282,
+      "grad_norm": 0.48005548119544983,
+      "learning_rate": 0.0002,
+      "loss": 1.642,
+      "step": 1710
+    },
+    {
+      "epoch": 2.3449216087252895,
+      "grad_norm": 0.4387182295322418,
+      "learning_rate": 0.0002,
+      "loss": 1.581,
+      "step": 1720
+    },
+    {
+      "epoch": 2.358554873892297,
+      "grad_norm": 0.4487272799015045,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 1730
+    },
+    {
+      "epoch": 2.372188139059305,
+      "grad_norm": 0.5046455264091492,
+      "learning_rate": 0.0002,
+      "loss": 1.5089,
+      "step": 1740
+    },
+    {
+      "epoch": 2.3858214042263124,
+      "grad_norm": 0.4653521180152893,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 1750
+    },
+    {
+      "epoch": 2.39945466939332,
+      "grad_norm": 0.4737723469734192,
+      "learning_rate": 0.0002,
+      "loss": 1.6201,
+      "step": 1760
+    },
+    {
+      "epoch": 2.4130879345603273,
+      "grad_norm": 0.4501931071281433,
+      "learning_rate": 0.0002,
+      "loss": 1.5933,
+      "step": 1770
+    },
+    {
+      "epoch": 2.426721199727335,
+      "grad_norm": 0.4772880971431732,
+      "learning_rate": 0.0002,
+      "loss": 1.6321,
+      "step": 1780
+    },
+    {
+      "epoch": 2.4403544648943423,
+      "grad_norm": 0.4544616937637329,
+      "learning_rate": 0.0002,
+      "loss": 1.5454,
+      "step": 1790
+    },
+    {
+      "epoch": 2.4539877300613497,
+      "grad_norm": 0.488313227891922,
+      "learning_rate": 0.0002,
+      "loss": 1.5501,
+      "step": 1800
+    },
+    {
+      "epoch": 2.467620995228357,
+      "grad_norm": 0.5057830214500427,
+      "learning_rate": 0.0002,
+      "loss": 1.5791,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4812542603953647,
+      "grad_norm": 0.5049484968185425,
+      "learning_rate": 0.0002,
+      "loss": 1.5645,
+      "step": 1820
+    },
+    {
+      "epoch": 2.494887525562372,
+      "grad_norm": 0.44966644048690796,
+      "learning_rate": 0.0002,
+      "loss": 1.6268,
+      "step": 1830
+    },
+    {
+      "epoch": 2.5085207907293796,
+      "grad_norm": 0.5072630643844604,
+      "learning_rate": 0.0002,
+      "loss": 1.5941,
+      "step": 1840
+    },
+    {
+      "epoch": 2.522154055896387,
+      "grad_norm": 0.43989792466163635,
+      "learning_rate": 0.0002,
+      "loss": 1.5251,
+      "step": 1850
+    },
+    {
+      "epoch": 2.5357873210633946,
+      "grad_norm": 1.3504403829574585,
+      "learning_rate": 0.0002,
+      "loss": 1.563,
+      "step": 1860
+    },
+    {
+      "epoch": 2.549420586230402,
+      "grad_norm": 0.46545976400375366,
+      "learning_rate": 0.0002,
+      "loss": 1.5681,
+      "step": 1870
+    },
+    {
+      "epoch": 2.5630538513974095,
+      "grad_norm": 0.4678342044353485,
+      "learning_rate": 0.0002,
+      "loss": 1.6368,
+      "step": 1880
+    },
+    {
+      "epoch": 2.5766871165644174,
+      "grad_norm": 0.529755711555481,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5903203817314244,
+      "grad_norm": 0.5000199675559998,
+      "learning_rate": 0.0002,
+      "loss": 1.5861,
+      "step": 1900
+    },
+    {
+      "epoch": 2.6039536468984323,
+      "grad_norm": 0.5649300217628479,
+      "learning_rate": 0.0002,
+      "loss": 1.6346,
+      "step": 1910
+    },
+    {
+      "epoch": 2.61758691206544,
+      "grad_norm": 0.7920585870742798,
+      "learning_rate": 0.0002,
+      "loss": 1.6317,
+      "step": 1920
+    },
+    {
+      "epoch": 2.6312201772324473,
+      "grad_norm": 0.4960342049598694,
+      "learning_rate": 0.0002,
+      "loss": 1.643,
+      "step": 1930
+    },
+    {
+      "epoch": 2.6448534423994547,
+      "grad_norm": 0.5324710011482239,
+      "learning_rate": 0.0002,
+      "loss": 1.6099,
+      "step": 1940
+    },
+    {
+      "epoch": 2.658486707566462,
+      "grad_norm": 0.606343150138855,
+      "learning_rate": 0.0002,
+      "loss": 1.5874,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6721199727334697,
+      "grad_norm": 0.53038489818573,
+      "learning_rate": 0.0002,
+      "loss": 1.5728,
+      "step": 1960
+    },
+    {
+      "epoch": 2.685753237900477,
+      "grad_norm": 0.4579465091228485,
+      "learning_rate": 0.0002,
+      "loss": 1.5583,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6993865030674846,
+      "grad_norm": 0.4541707932949066,
+      "learning_rate": 0.0002,
+      "loss": 1.6093,
+      "step": 1980
+    },
+    {
+      "epoch": 2.713019768234492,
+      "grad_norm": 0.5009395480155945,
+      "learning_rate": 0.0002,
+      "loss": 1.5316,
+      "step": 1990
+    },
+    {
+      "epoch": 2.7266530334014996,
+      "grad_norm": 0.4723006784915924,
+      "learning_rate": 0.0002,
+      "loss": 1.6724,
+      "step": 2000
+    },
+    {
+      "epoch": 2.740286298568507,
+      "grad_norm": 0.5086126923561096,
+      "learning_rate": 0.0002,
+      "loss": 1.638,
+      "step": 2010
+    },
+    {
+      "epoch": 2.7539195637355145,
+      "grad_norm": 0.47242608666419983,
+      "learning_rate": 0.0002,
+      "loss": 1.6223,
+      "step": 2020
+    },
+    {
+      "epoch": 2.767552828902522,
+      "grad_norm": 0.44922566413879395,
+      "learning_rate": 0.0002,
+      "loss": 1.6242,
+      "step": 2030
+    },
+    {
+      "epoch": 2.78118609406953,
+      "grad_norm": 0.420259565114975,
+      "learning_rate": 0.0002,
+      "loss": 1.6837,
+      "step": 2040
+    },
+    {
+      "epoch": 2.794819359236537,
+      "grad_norm": 0.4762881100177765,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 2050
+    },
+    {
+      "epoch": 2.808452624403545,
+      "grad_norm": 0.5228786468505859,
+      "learning_rate": 0.0002,
+      "loss": 1.5506,
+      "step": 2060
+    },
+    {
+      "epoch": 2.8220858895705523,
+      "grad_norm": 0.4796035587787628,
+      "learning_rate": 0.0002,
+      "loss": 1.6347,
+      "step": 2070
+    },
+    {
+      "epoch": 2.8357191547375598,
+      "grad_norm": 0.5034735202789307,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 2080
+    },
+    {
+      "epoch": 2.8493524199045672,
+      "grad_norm": 0.48005399107933044,
+      "learning_rate": 0.0002,
+      "loss": 1.6455,
+      "step": 2090
+    },
+    {
+      "epoch": 2.8629856850715747,
+      "grad_norm": 0.578820526599884,
+      "learning_rate": 0.0002,
+      "loss": 1.6287,
+      "step": 2100
+    },
+    {
+      "epoch": 2.876618950238582,
+      "grad_norm": 0.48982638120651245,
+      "learning_rate": 0.0002,
+      "loss": 1.6021,
+      "step": 2110
+    },
+    {
+      "epoch": 2.8902522154055896,
+      "grad_norm": 0.5157325863838196,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 2120
+    },
+    {
+      "epoch": 2.903885480572597,
+      "grad_norm": 0.49149683117866516,
+      "learning_rate": 0.0002,
+      "loss": 1.6089,
+      "step": 2130
+    },
+    {
+      "epoch": 2.9175187457396046,
+      "grad_norm": 0.48584499955177307,
+      "learning_rate": 0.0002,
+      "loss": 1.5881,
+      "step": 2140
+    },
+    {
+      "epoch": 2.931152010906612,
+      "grad_norm": 0.5199017524719238,
+      "learning_rate": 0.0002,
+      "loss": 1.5833,
+      "step": 2150
+    },
+    {
+      "epoch": 2.9447852760736195,
+      "grad_norm": 0.5788236856460571,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 2160
+    },
+    {
+      "epoch": 2.958418541240627,
+      "grad_norm": 0.48664185404777527,
+      "learning_rate": 0.0002,
+      "loss": 1.6103,
+      "step": 2170
+    },
+    {
+      "epoch": 2.9720518064076344,
+      "grad_norm": 0.5026682615280151,
+      "learning_rate": 0.0002,
+      "loss": 1.5765,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9856850715746424,
+      "grad_norm": 0.49317044019699097,
+      "learning_rate": 0.0002,
+      "loss": 1.6626,
+      "step": 2190
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "grad_norm": 0.5729128122329712,
+      "learning_rate": 0.0002,
+      "loss": 1.5871,
+      "step": 2200
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "eval_loss": 1.8527295589447021,
+      "eval_runtime": 53.6403,
+      "eval_samples_per_second": 9.452,
+      "eval_steps_per_second": 1.193,
+      "step": 2200
+    },
+    {
+      "epoch": 3.0129516019086573,
+      "grad_norm": 0.5530241131782532,
+      "learning_rate": 0.0002,
+      "loss": 1.4719,
+      "step": 2210
+    },
+    {
+      "epoch": 3.0265848670756648,
+      "grad_norm": 0.6642216444015503,
+      "learning_rate": 0.0002,
+      "loss": 1.4088,
+      "step": 2220
+    },
+    {
+      "epoch": 3.0402181322426722,
+      "grad_norm": 0.61470627784729,
+      "learning_rate": 0.0002,
+      "loss": 1.4382,
+      "step": 2230
+    },
+    {
+      "epoch": 3.0538513974096797,
+      "grad_norm": 0.8559566140174866,
+      "learning_rate": 0.0002,
+      "loss": 1.4634,
+      "step": 2240
+    },
+    {
+      "epoch": 3.067484662576687,
+      "grad_norm": 0.7015801668167114,
+      "learning_rate": 0.0002,
+      "loss": 1.3854,
+      "step": 2250
+    },
+    {
+      "epoch": 3.0811179277436946,
+      "grad_norm": 0.7226442694664001,
+      "learning_rate": 0.0002,
+      "loss": 1.4981,
+      "step": 2260
+    },
+    {
+      "epoch": 3.094751192910702,
+      "grad_norm": 0.7560588717460632,
+      "learning_rate": 0.0002,
+      "loss": 1.4143,
+      "step": 2270
+    },
+    {
+      "epoch": 3.1083844580777096,
+      "grad_norm": 0.6216568946838379,
+      "learning_rate": 0.0002,
+      "loss": 1.4395,
+      "step": 2280
+    },
+    {
+      "epoch": 3.122017723244717,
+      "grad_norm": 0.6768500804901123,
+      "learning_rate": 0.0002,
+      "loss": 1.3842,
+      "step": 2290
+    },
+    {
+      "epoch": 3.1356509884117245,
+      "grad_norm": 0.7028762102127075,
+      "learning_rate": 0.0002,
+      "loss": 1.4672,
+      "step": 2300
+    },
+    {
+      "epoch": 3.149284253578732,
+      "grad_norm": 0.6329697966575623,
+      "learning_rate": 0.0002,
+      "loss": 1.3826,
+      "step": 2310
+    },
+    {
+      "epoch": 3.1629175187457395,
+      "grad_norm": 0.6328264474868774,
+      "learning_rate": 0.0002,
+      "loss": 1.442,
+      "step": 2320
+    },
+    {
+      "epoch": 3.176550783912747,
+      "grad_norm": 0.7573632001876831,
+      "learning_rate": 0.0002,
+      "loss": 1.3762,
+      "step": 2330
+    },
+    {
+      "epoch": 3.190184049079755,
+      "grad_norm": 0.595740795135498,
+      "learning_rate": 0.0002,
+      "loss": 1.3553,
+      "step": 2340
+    },
+    {
+      "epoch": 3.2038173142467623,
+      "grad_norm": 0.7111806869506836,
+      "learning_rate": 0.0002,
+      "loss": 1.3953,
+      "step": 2350
+    },
+    {
+      "epoch": 3.2174505794137698,
+      "grad_norm": 0.6328730583190918,
+      "learning_rate": 0.0002,
+      "loss": 1.3797,
+      "step": 2360
+    },
+    {
+      "epoch": 3.2310838445807772,
+      "grad_norm": 0.5860254168510437,
+      "learning_rate": 0.0002,
+      "loss": 1.3855,
+      "step": 2370
+    },
+    {
+      "epoch": 3.2447171097477847,
+      "grad_norm": 0.7387157082557678,
+      "learning_rate": 0.0002,
+      "loss": 1.4267,
+      "step": 2380
+    },
+    {
+      "epoch": 3.258350374914792,
+      "grad_norm": 0.6897673606872559,
+      "learning_rate": 0.0002,
+      "loss": 1.4837,
+      "step": 2390
+    },
+    {
+      "epoch": 3.2719836400817996,
+      "grad_norm": 0.7157699465751648,
+      "learning_rate": 0.0002,
+      "loss": 1.4372,
+      "step": 2400
+    },
+    {
+      "epoch": 3.285616905248807,
+      "grad_norm": 0.6422511339187622,
+      "learning_rate": 0.0002,
+      "loss": 1.4432,
+      "step": 2410
+    },
+    {
+      "epoch": 3.2992501704158146,
+      "grad_norm": 1.0481886863708496,
+      "learning_rate": 0.0002,
+      "loss": 1.4828,
+      "step": 2420
+    },
+    {
+      "epoch": 3.312883435582822,
+      "grad_norm": 0.7050786018371582,
+      "learning_rate": 0.0002,
+      "loss": 1.4473,
+      "step": 2430
+    },
+    {
+      "epoch": 3.3265167007498295,
+      "grad_norm": 0.6090759038925171,
+      "learning_rate": 0.0002,
+      "loss": 1.3465,
+      "step": 2440
+    },
+    {
+      "epoch": 3.340149965916837,
+      "grad_norm": 0.6626465320587158,
+      "learning_rate": 0.0002,
+      "loss": 1.4619,
+      "step": 2450
+    },
+    {
+      "epoch": 3.3537832310838445,
+      "grad_norm": 0.6565486788749695,
+      "learning_rate": 0.0002,
+      "loss": 1.4512,
+      "step": 2460
+    },
+    {
+      "epoch": 3.367416496250852,
+      "grad_norm": 0.6449528932571411,
+      "learning_rate": 0.0002,
+      "loss": 1.588,
+      "step": 2470
+    },
+    {
+      "epoch": 3.3810497614178594,
+      "grad_norm": 0.7746227383613586,
+      "learning_rate": 0.0002,
+      "loss": 1.4773,
+      "step": 2480
+    },
+    {
+      "epoch": 3.3946830265848673,
+      "grad_norm": 0.7074846029281616,
+      "learning_rate": 0.0002,
+      "loss": 1.417,
+      "step": 2490
+    },
+    {
+      "epoch": 3.4083162917518743,
+      "grad_norm": 0.6547690033912659,
+      "learning_rate": 0.0002,
+      "loss": 1.4476,
+      "step": 2500
+    },
+    {
+      "epoch": 3.4219495569188823,
+      "grad_norm": 0.784721314907074,
+      "learning_rate": 0.0002,
+      "loss": 1.4074,
+      "step": 2510
+    },
+    {
+      "epoch": 3.4355828220858897,
+      "grad_norm": 0.7270277738571167,
+      "learning_rate": 0.0002,
+      "loss": 1.4326,
+      "step": 2520
+    },
+    {
+      "epoch": 3.449216087252897,
+      "grad_norm": 0.67588871717453,
+      "learning_rate": 0.0002,
+      "loss": 1.4354,
+      "step": 2530
+    },
+    {
+      "epoch": 3.4628493524199047,
+      "grad_norm": 0.6768023371696472,
+      "learning_rate": 0.0002,
+      "loss": 1.4074,
+      "step": 2540
+    },
+    {
+      "epoch": 3.476482617586912,
+      "grad_norm": 0.7026481628417969,
+      "learning_rate": 0.0002,
+      "loss": 1.4863,
+      "step": 2550
+    },
+    {
+      "epoch": 3.4901158827539196,
+      "grad_norm": 0.646075963973999,
+      "learning_rate": 0.0002,
+      "loss": 1.468,
+      "step": 2560
+    },
+    {
+      "epoch": 3.503749147920927,
+      "grad_norm": 0.6288973689079285,
+      "learning_rate": 0.0002,
+      "loss": 1.4058,
+      "step": 2570
+    },
+    {
+      "epoch": 3.5173824130879345,
+      "grad_norm": 0.6440825462341309,
+      "learning_rate": 0.0002,
+      "loss": 1.4613,
+      "step": 2580
+    },
+    {
+      "epoch": 3.531015678254942,
+      "grad_norm": 0.7074111700057983,
+      "learning_rate": 0.0002,
+      "loss": 1.3808,
+      "step": 2590
+    },
+    {
+      "epoch": 3.5446489434219495,
+      "grad_norm": 0.7007562518119812,
+      "learning_rate": 0.0002,
+      "loss": 1.4901,
+      "step": 2600
+    },
+    {
+      "epoch": 3.558282208588957,
+      "grad_norm": 0.6045376658439636,
+      "learning_rate": 0.0002,
+      "loss": 1.4511,
+      "step": 2610
+    },
+    {
+      "epoch": 3.5719154737559644,
+      "grad_norm": 0.9149952530860901,
+      "learning_rate": 0.0002,
+      "loss": 1.4596,
+      "step": 2620
+    },
+    {
+      "epoch": 3.585548738922972,
+      "grad_norm": 0.6490362882614136,
+      "learning_rate": 0.0002,
+      "loss": 1.4355,
+      "step": 2630
+    },
+    {
+      "epoch": 3.59918200408998,
+      "grad_norm": 0.6552226543426514,
+      "learning_rate": 0.0002,
+      "loss": 1.4107,
+      "step": 2640
+    },
+    {
+      "epoch": 3.612815269256987,
+      "grad_norm": 0.6541850566864014,
+      "learning_rate": 0.0002,
+      "loss": 1.433,
+      "step": 2650
+    },
+    {
+      "epoch": 3.6264485344239947,
+      "grad_norm": 0.6500770449638367,
+      "learning_rate": 0.0002,
+      "loss": 1.4279,
+      "step": 2660
+    },
+    {
+      "epoch": 3.640081799591002,
+      "grad_norm": 0.6345893740653992,
+      "learning_rate": 0.0002,
+      "loss": 1.3929,
+      "step": 2670
+    },
+    {
+      "epoch": 3.6537150647580097,
+      "grad_norm": 0.6382275223731995,
+      "learning_rate": 0.0002,
+      "loss": 1.3634,
+      "step": 2680
+    },
+    {
+      "epoch": 3.667348329925017,
+      "grad_norm": 0.6738566160202026,
+      "learning_rate": 0.0002,
+      "loss": 1.4478,
+      "step": 2690
+    },
+    {
+      "epoch": 3.6809815950920246,
+      "grad_norm": 0.7446315288543701,
+      "learning_rate": 0.0002,
+      "loss": 1.4642,
+      "step": 2700
+    },
+    {
+      "epoch": 3.694614860259032,
+      "grad_norm": 0.6717571020126343,
+      "learning_rate": 0.0002,
+      "loss": 1.4342,
+      "step": 2710
+    },
+    {
+      "epoch": 3.7082481254260395,
+      "grad_norm": 0.667259693145752,
+      "learning_rate": 0.0002,
+      "loss": 1.4285,
+      "step": 2720
+    },
+    {
+      "epoch": 3.721881390593047,
+      "grad_norm": 0.6808622479438782,
+      "learning_rate": 0.0002,
+      "loss": 1.5389,
+      "step": 2730
+    },
+    {
+      "epoch": 3.7355146557600545,
+      "grad_norm": 0.7254287004470825,
+      "learning_rate": 0.0002,
+      "loss": 1.4297,
+      "step": 2740
+    },
+    {
+      "epoch": 3.749147920927062,
+      "grad_norm": 0.6864007711410522,
+      "learning_rate": 0.0002,
+      "loss": 1.4176,
+      "step": 2750
+    },
+    {
+      "epoch": 3.7627811860940694,
+      "grad_norm": 0.7041361331939697,
+      "learning_rate": 0.0002,
+      "loss": 1.4811,
+      "step": 2760
+    },
+    {
+      "epoch": 3.776414451261077,
+      "grad_norm": 0.6559903025627136,
+      "learning_rate": 0.0002,
+      "loss": 1.4284,
+      "step": 2770
+    },
+    {
+      "epoch": 3.7900477164280844,
+      "grad_norm": 0.6602269411087036,
+      "learning_rate": 0.0002,
+      "loss": 1.4608,
+      "step": 2780
+    },
+    {
+      "epoch": 3.8036809815950923,
+      "grad_norm": 0.692611813545227,
+      "learning_rate": 0.0002,
+      "loss": 1.4588,
+      "step": 2790
+    },
+    {
+      "epoch": 3.8173142467620993,
+      "grad_norm": 0.7051475644111633,
+      "learning_rate": 0.0002,
+      "loss": 1.4065,
+      "step": 2800
+    },
+    {
+      "epoch": 3.830947511929107,
+      "grad_norm": 0.6685371398925781,
+      "learning_rate": 0.0002,
+      "loss": 1.4083,
+      "step": 2810
+    },
+    {
+      "epoch": 3.8445807770961147,
+      "grad_norm": 0.6706477403640747,
+      "learning_rate": 0.0002,
+      "loss": 1.5227,
+      "step": 2820
+    },
+    {
+      "epoch": 3.858214042263122,
+      "grad_norm": 0.6671637296676636,
+      "learning_rate": 0.0002,
+      "loss": 1.4076,
+      "step": 2830
+    },
+    {
+      "epoch": 3.8718473074301296,
+      "grad_norm": 0.694092333316803,
+      "learning_rate": 0.0002,
+      "loss": 1.4736,
+      "step": 2840
+    },
+    {
+      "epoch": 3.885480572597137,
+      "grad_norm": 0.7349600195884705,
+      "learning_rate": 0.0002,
+      "loss": 1.4161,
+      "step": 2850
+    },
+    {
+      "epoch": 3.8991138377641446,
+      "grad_norm": 0.6647971868515015,
+      "learning_rate": 0.0002,
+      "loss": 1.4617,
+      "step": 2860
+    },
+    {
+      "epoch": 3.912747102931152,
+      "grad_norm": 0.806656539440155,
+      "learning_rate": 0.0002,
+      "loss": 1.5046,
+      "step": 2870
+    },
+    {
+      "epoch": 3.9263803680981595,
+      "grad_norm": 0.6008772850036621,
+      "learning_rate": 0.0002,
+      "loss": 1.428,
+      "step": 2880
+    },
+    {
+      "epoch": 3.940013633265167,
+      "grad_norm": 0.659227728843689,
+      "learning_rate": 0.0002,
+      "loss": 1.4116,
+      "step": 2890
+    },
+    {
+      "epoch": 3.9536468984321744,
+      "grad_norm": 0.6357656717300415,
+      "learning_rate": 0.0002,
+      "loss": 1.4136,
+      "step": 2900
+    },
+    {
+      "epoch": 3.967280163599182,
+      "grad_norm": 0.6541687846183777,
+      "learning_rate": 0.0002,
+      "loss": 1.4655,
+      "step": 2910
+    },
+    {
+      "epoch": 3.9809134287661894,
+      "grad_norm": 0.6090909838676453,
+      "learning_rate": 0.0002,
+      "loss": 1.4854,
+      "step": 2920
+    },
+    {
+      "epoch": 3.994546693933197,
+      "grad_norm": 0.7198411822319031,
+      "learning_rate": 0.0002,
+      "loss": 1.4615,
+      "step": 2930
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.9278366565704346,
+      "eval_runtime": 53.6567,
+      "eval_samples_per_second": 9.449,
+      "eval_steps_per_second": 1.193,
+      "step": 2934
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5864,
+  "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": 1.5070122967302144e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/training_args.bin b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..da7142eb13ed7f8418e5055c63a0fe0ca5e1972b
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-2934/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8beac9fdfb91726fdf7473c9e77541aa988c61dc8beaba03293eafbe9c0a376
+size 5560
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/README.md b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/adapter_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/adapter_model.safetensors b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..40154ff703d01ea7d5182e11e3373f7b82b8cca8
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886255eb323b08886d2d430ad04a712afc30b8023f25ea26a3c02c6f10a9ab72
+size 143153376
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/optimizer.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4b0b9d4293b3f35982502da5170b7e23a15bebc5
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5962bbcfb2896cdb8738e2c25f4ea65b58945ba973b1e5689d489e4b831f4e9
+size 72886650
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/rng_state.pth b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..296581d1745771f65b84c9a7388e617bf35f3b70
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c8dadd8ca3b2ae8518245449e0bbab16bc3271b1ac2e131fec9530a85f362c
+size 14244
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/scheduler.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..447bdf5a368652ae6eaf600dea6e5223f98e5503
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69dd9f4175df7ddd0bf47bdd257e171fe3c9ae00d7e681fb5b6267fdcaf2677c
+size 1064
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/special_tokens_map.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/tokenizer.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/tokenizer.model b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/tokenizer_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/trainer_state.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..a5c357ce245dc9cafb9e6134e1580dc10b584e8a
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/trainer_state.json
@@ -0,0 +1,2635 @@
+{
+  "best_metric": 1.8171186447143555,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733",
+  "epoch": 4.999318336741649,
+  "eval_steps": 10,
+  "global_step": 3667,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013633265167007498,
+      "grad_norm": 0.7714291214942932,
+      "learning_rate": 0.0002,
+      "loss": 3.0982,
+      "step": 10
+    },
+    {
+      "epoch": 0.027266530334014997,
+      "grad_norm": 0.5473978519439697,
+      "learning_rate": 0.0002,
+      "loss": 2.5206,
+      "step": 20
+    },
+    {
+      "epoch": 0.0408997955010225,
+      "grad_norm": 0.5452795624732971,
+      "learning_rate": 0.0002,
+      "loss": 2.3079,
+      "step": 30
+    },
+    {
+      "epoch": 0.054533060668029994,
+      "grad_norm": 0.5098028779029846,
+      "learning_rate": 0.0002,
+      "loss": 2.0019,
+      "step": 40
+    },
+    {
+      "epoch": 0.0681663258350375,
+      "grad_norm": 0.48062971234321594,
+      "learning_rate": 0.0002,
+      "loss": 1.9333,
+      "step": 50
+    },
+    {
+      "epoch": 0.081799591002045,
+      "grad_norm": 0.4505695104598999,
+      "learning_rate": 0.0002,
+      "loss": 1.9355,
+      "step": 60
+    },
+    {
+      "epoch": 0.09543285616905249,
+      "grad_norm": 0.41609591245651245,
+      "learning_rate": 0.0002,
+      "loss": 1.9312,
+      "step": 70
+    },
+    {
+      "epoch": 0.10906612133605999,
+      "grad_norm": 0.4323892593383789,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 80
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 0.4670293629169464,
+      "learning_rate": 0.0002,
+      "loss": 1.9294,
+      "step": 90
+    },
+    {
+      "epoch": 0.136332651670075,
+      "grad_norm": 0.40623316168785095,
+      "learning_rate": 0.0002,
+      "loss": 1.7946,
+      "step": 100
+    },
+    {
+      "epoch": 0.1499659168370825,
+      "grad_norm": 0.3620383143424988,
+      "learning_rate": 0.0002,
+      "loss": 1.8565,
+      "step": 110
+    },
+    {
+      "epoch": 0.16359918200409,
+      "grad_norm": 0.332218736410141,
+      "learning_rate": 0.0002,
+      "loss": 1.9238,
+      "step": 120
+    },
+    {
+      "epoch": 0.17723244717109748,
+      "grad_norm": 0.4004521667957306,
+      "learning_rate": 0.0002,
+      "loss": 1.93,
+      "step": 130
+    },
+    {
+      "epoch": 0.19086571233810498,
+      "grad_norm": 0.3698360323905945,
+      "learning_rate": 0.0002,
+      "loss": 1.7549,
+      "step": 140
+    },
+    {
+      "epoch": 0.20449897750511248,
+      "grad_norm": 0.3847949504852295,
+      "learning_rate": 0.0002,
+      "loss": 1.8771,
+      "step": 150
+    },
+    {
+      "epoch": 0.21813224267211997,
+      "grad_norm": 0.36843451857566833,
+      "learning_rate": 0.0002,
+      "loss": 1.8316,
+      "step": 160
+    },
+    {
+      "epoch": 0.23176550783912747,
+      "grad_norm": 0.37301021814346313,
+      "learning_rate": 0.0002,
+      "loss": 1.838,
+      "step": 170
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.3718886971473694,
+      "learning_rate": 0.0002,
+      "loss": 1.8909,
+      "step": 180
+    },
+    {
+      "epoch": 0.25903203817314246,
+      "grad_norm": 0.3088490962982178,
+      "learning_rate": 0.0002,
+      "loss": 1.8454,
+      "step": 190
+    },
+    {
+      "epoch": 0.27266530334015,
+      "grad_norm": 0.3611852526664734,
+      "learning_rate": 0.0002,
+      "loss": 1.9254,
+      "step": 200
+    },
+    {
+      "epoch": 0.28629856850715746,
+      "grad_norm": 0.36093324422836304,
+      "learning_rate": 0.0002,
+      "loss": 1.7844,
+      "step": 210
+    },
+    {
+      "epoch": 0.299931833674165,
+      "grad_norm": 0.3250400722026825,
+      "learning_rate": 0.0002,
+      "loss": 1.719,
+      "step": 220
+    },
+    {
+      "epoch": 0.31356509884117245,
+      "grad_norm": 0.3566756248474121,
+      "learning_rate": 0.0002,
+      "loss": 1.8729,
+      "step": 230
+    },
+    {
+      "epoch": 0.32719836400818,
+      "grad_norm": 0.32872408628463745,
+      "learning_rate": 0.0002,
+      "loss": 1.9259,
+      "step": 240
+    },
+    {
+      "epoch": 0.34083162917518744,
+      "grad_norm": 0.3983881175518036,
+      "learning_rate": 0.0002,
+      "loss": 1.9033,
+      "step": 250
+    },
+    {
+      "epoch": 0.35446489434219497,
+      "grad_norm": 0.3571510910987854,
+      "learning_rate": 0.0002,
+      "loss": 1.8588,
+      "step": 260
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 0.3036131262779236,
+      "learning_rate": 0.0002,
+      "loss": 1.8539,
+      "step": 270
+    },
+    {
+      "epoch": 0.38173142467620996,
+      "grad_norm": 0.36512863636016846,
+      "learning_rate": 0.0002,
+      "loss": 1.8572,
+      "step": 280
+    },
+    {
+      "epoch": 0.39536468984321743,
+      "grad_norm": 0.3429736793041229,
+      "learning_rate": 0.0002,
+      "loss": 1.8022,
+      "step": 290
+    },
+    {
+      "epoch": 0.40899795501022496,
+      "grad_norm": 0.3055964708328247,
+      "learning_rate": 0.0002,
+      "loss": 1.8754,
+      "step": 300
+    },
+    {
+      "epoch": 0.4226312201772324,
+      "grad_norm": 0.33801034092903137,
+      "learning_rate": 0.0002,
+      "loss": 1.8384,
+      "step": 310
+    },
+    {
+      "epoch": 0.43626448534423995,
+      "grad_norm": 0.348783016204834,
+      "learning_rate": 0.0002,
+      "loss": 1.7933,
+      "step": 320
+    },
+    {
+      "epoch": 0.4498977505112474,
+      "grad_norm": 0.3057514727115631,
+      "learning_rate": 0.0002,
+      "loss": 1.8451,
+      "step": 330
+    },
+    {
+      "epoch": 0.46353101567825494,
+      "grad_norm": 0.3849763572216034,
+      "learning_rate": 0.0002,
+      "loss": 1.8766,
+      "step": 340
+    },
+    {
+      "epoch": 0.47716428084526247,
+      "grad_norm": 0.30080053210258484,
+      "learning_rate": 0.0002,
+      "loss": 1.8073,
+      "step": 350
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.3595106303691864,
+      "learning_rate": 0.0002,
+      "loss": 1.8548,
+      "step": 360
+    },
+    {
+      "epoch": 0.5044308111792775,
+      "grad_norm": 0.31099820137023926,
+      "learning_rate": 0.0002,
+      "loss": 1.8232,
+      "step": 370
+    },
+    {
+      "epoch": 0.5180640763462849,
+      "grad_norm": 0.3157978355884552,
+      "learning_rate": 0.0002,
+      "loss": 1.7029,
+      "step": 380
+    },
+    {
+      "epoch": 0.5316973415132924,
+      "grad_norm": 0.27960965037345886,
+      "learning_rate": 0.0002,
+      "loss": 1.8265,
+      "step": 390
+    },
+    {
+      "epoch": 0.5453306066803,
+      "grad_norm": 0.3102385103702545,
+      "learning_rate": 0.0002,
+      "loss": 1.7414,
+      "step": 400
+    },
+    {
+      "epoch": 0.5589638718473074,
+      "grad_norm": 0.32828861474990845,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 410
+    },
+    {
+      "epoch": 0.5725971370143149,
+      "grad_norm": 0.29560017585754395,
+      "learning_rate": 0.0002,
+      "loss": 1.8165,
+      "step": 420
+    },
+    {
+      "epoch": 0.5862304021813224,
+      "grad_norm": 0.33316895365715027,
+      "learning_rate": 0.0002,
+      "loss": 1.9455,
+      "step": 430
+    },
+    {
+      "epoch": 0.59986366734833,
+      "grad_norm": 0.30420982837677,
+      "learning_rate": 0.0002,
+      "loss": 1.8241,
+      "step": 440
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 0.32619214057922363,
+      "learning_rate": 0.0002,
+      "loss": 1.7565,
+      "step": 450
+    },
+    {
+      "epoch": 0.6271301976823449,
+      "grad_norm": 0.3603750765323639,
+      "learning_rate": 0.0002,
+      "loss": 1.7945,
+      "step": 460
+    },
+    {
+      "epoch": 0.6407634628493524,
+      "grad_norm": 0.30834096670150757,
+      "learning_rate": 0.0002,
+      "loss": 1.7773,
+      "step": 470
+    },
+    {
+      "epoch": 0.65439672801636,
+      "grad_norm": 0.28756365180015564,
+      "learning_rate": 0.0002,
+      "loss": 1.8058,
+      "step": 480
+    },
+    {
+      "epoch": 0.6680299931833674,
+      "grad_norm": 0.2878406345844269,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 490
+    },
+    {
+      "epoch": 0.6816632583503749,
+      "grad_norm": 0.31329697370529175,
+      "learning_rate": 0.0002,
+      "loss": 1.8581,
+      "step": 500
+    },
+    {
+      "epoch": 0.6952965235173824,
+      "grad_norm": 0.3405822515487671,
+      "learning_rate": 0.0002,
+      "loss": 1.7886,
+      "step": 510
+    },
+    {
+      "epoch": 0.7089297886843899,
+      "grad_norm": 0.305560827255249,
+      "learning_rate": 0.0002,
+      "loss": 1.778,
+      "step": 520
+    },
+    {
+      "epoch": 0.7225630538513974,
+      "grad_norm": 0.2973416745662689,
+      "learning_rate": 0.0002,
+      "loss": 1.7592,
+      "step": 530
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 0.327303946018219,
+      "learning_rate": 0.0002,
+      "loss": 1.8223,
+      "step": 540
+    },
+    {
+      "epoch": 0.7498295841854125,
+      "grad_norm": 0.62595534324646,
+      "learning_rate": 0.0002,
+      "loss": 1.8591,
+      "step": 550
+    },
+    {
+      "epoch": 0.7634628493524199,
+      "grad_norm": 0.3129784166812897,
+      "learning_rate": 0.0002,
+      "loss": 1.7466,
+      "step": 560
+    },
+    {
+      "epoch": 0.7770961145194274,
+      "grad_norm": 0.32496583461761475,
+      "learning_rate": 0.0002,
+      "loss": 1.8035,
+      "step": 570
+    },
+    {
+      "epoch": 0.7907293796864349,
+      "grad_norm": 0.3098868131637573,
+      "learning_rate": 0.0002,
+      "loss": 1.7787,
+      "step": 580
+    },
+    {
+      "epoch": 0.8043626448534424,
+      "grad_norm": 0.30726853013038635,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 590
+    },
+    {
+      "epoch": 0.8179959100204499,
+      "grad_norm": 0.2964220643043518,
+      "learning_rate": 0.0002,
+      "loss": 1.7898,
+      "step": 600
+    },
+    {
+      "epoch": 0.8316291751874574,
+      "grad_norm": 0.32352274656295776,
+      "learning_rate": 0.0002,
+      "loss": 1.8114,
+      "step": 610
+    },
+    {
+      "epoch": 0.8452624403544649,
+      "grad_norm": 0.2938912510871887,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 620
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 0.295559823513031,
+      "learning_rate": 0.0002,
+      "loss": 1.7727,
+      "step": 630
+    },
+    {
+      "epoch": 0.8725289706884799,
+      "grad_norm": 0.34102028608322144,
+      "learning_rate": 0.0002,
+      "loss": 1.9,
+      "step": 640
+    },
+    {
+      "epoch": 0.8861622358554874,
+      "grad_norm": 0.29676181077957153,
+      "learning_rate": 0.0002,
+      "loss": 1.8006,
+      "step": 650
+    },
+    {
+      "epoch": 0.8997955010224948,
+      "grad_norm": 0.3108902871608734,
+      "learning_rate": 0.0002,
+      "loss": 1.8099,
+      "step": 660
+    },
+    {
+      "epoch": 0.9134287661895024,
+      "grad_norm": 0.2690821588039398,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 670
+    },
+    {
+      "epoch": 0.9270620313565099,
+      "grad_norm": 0.32752540707588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7881,
+      "step": 680
+    },
+    {
+      "epoch": 0.9406952965235174,
+      "grad_norm": 0.8029476404190063,
+      "learning_rate": 0.0002,
+      "loss": 1.7661,
+      "step": 690
+    },
+    {
+      "epoch": 0.9543285616905249,
+      "grad_norm": 0.30534422397613525,
+      "learning_rate": 0.0002,
+      "loss": 1.7733,
+      "step": 700
+    },
+    {
+      "epoch": 0.9679618268575324,
+      "grad_norm": 0.2899954319000244,
+      "learning_rate": 0.0002,
+      "loss": 1.7614,
+      "step": 710
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 0.28814372420310974,
+      "learning_rate": 0.0002,
+      "loss": 1.7845,
+      "step": 720
+    },
+    {
+      "epoch": 0.9952283571915473,
+      "grad_norm": 0.3061596751213074,
+      "learning_rate": 0.0002,
+      "loss": 1.8865,
+      "step": 730
+    },
+    {
+      "epoch": 0.9993183367416496,
+      "eval_loss": 1.8171186447143555,
+      "eval_runtime": 53.6047,
+      "eval_samples_per_second": 9.458,
+      "eval_steps_per_second": 1.194,
+      "step": 733
+    },
+    {
+      "epoch": 1.008861622358555,
+      "grad_norm": 0.3140897750854492,
+      "learning_rate": 0.0002,
+      "loss": 1.6202,
+      "step": 740
+    },
+    {
+      "epoch": 1.0224948875255624,
+      "grad_norm": 0.3346109390258789,
+      "learning_rate": 0.0002,
+      "loss": 1.8409,
+      "step": 750
+    },
+    {
+      "epoch": 1.0361281526925699,
+      "grad_norm": 0.3582976758480072,
+      "learning_rate": 0.0002,
+      "loss": 1.6777,
+      "step": 760
+    },
+    {
+      "epoch": 1.0497614178595773,
+      "grad_norm": 0.30408260226249695,
+      "learning_rate": 0.0002,
+      "loss": 1.7306,
+      "step": 770
+    },
+    {
+      "epoch": 1.0633946830265848,
+      "grad_norm": 0.323585569858551,
+      "learning_rate": 0.0002,
+      "loss": 1.6967,
+      "step": 780
+    },
+    {
+      "epoch": 1.0770279481935923,
+      "grad_norm": 0.3474137783050537,
+      "learning_rate": 0.0002,
+      "loss": 1.768,
+      "step": 790
+    },
+    {
+      "epoch": 1.0906612133606,
+      "grad_norm": 0.35721147060394287,
+      "learning_rate": 0.0002,
+      "loss": 1.6895,
+      "step": 800
+    },
+    {
+      "epoch": 1.1042944785276074,
+      "grad_norm": 0.35366931557655334,
+      "learning_rate": 0.0002,
+      "loss": 1.718,
+      "step": 810
+    },
+    {
+      "epoch": 1.117927743694615,
+      "grad_norm": 0.3250770568847656,
+      "learning_rate": 0.0002,
+      "loss": 1.6797,
+      "step": 820
+    },
+    {
+      "epoch": 1.1315610088616224,
+      "grad_norm": 0.3293766379356384,
+      "learning_rate": 0.0002,
+      "loss": 1.6383,
+      "step": 830
+    },
+    {
+      "epoch": 1.1451942740286298,
+      "grad_norm": 0.3380851745605469,
+      "learning_rate": 0.0002,
+      "loss": 1.7353,
+      "step": 840
+    },
+    {
+      "epoch": 1.1588275391956373,
+      "grad_norm": 0.32584455609321594,
+      "learning_rate": 0.0002,
+      "loss": 1.8236,
+      "step": 850
+    },
+    {
+      "epoch": 1.1724608043626448,
+      "grad_norm": 0.45700767636299133,
+      "learning_rate": 0.0002,
+      "loss": 1.6681,
+      "step": 860
+    },
+    {
+      "epoch": 1.1860940695296525,
+      "grad_norm": 0.30944544076919556,
+      "learning_rate": 0.0002,
+      "loss": 1.7494,
+      "step": 870
+    },
+    {
+      "epoch": 1.19972733469666,
+      "grad_norm": 0.3268151581287384,
+      "learning_rate": 0.0002,
+      "loss": 1.7426,
+      "step": 880
+    },
+    {
+      "epoch": 1.2133605998636674,
+      "grad_norm": 0.39972540736198425,
+      "learning_rate": 0.0002,
+      "loss": 1.7413,
+      "step": 890
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 0.7890929579734802,
+      "learning_rate": 0.0002,
+      "loss": 1.7481,
+      "step": 900
+    },
+    {
+      "epoch": 1.2406271301976823,
+      "grad_norm": 0.3439182639122009,
+      "learning_rate": 0.0002,
+      "loss": 1.7608,
+      "step": 910
+    },
+    {
+      "epoch": 1.2542603953646898,
+      "grad_norm": 0.3986225128173828,
+      "learning_rate": 0.0002,
+      "loss": 1.7617,
+      "step": 920
+    },
+    {
+      "epoch": 1.2678936605316973,
+      "grad_norm": 0.3514605164527893,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 930
+    },
+    {
+      "epoch": 1.2815269256987047,
+      "grad_norm": 0.3682589530944824,
+      "learning_rate": 0.0002,
+      "loss": 1.6987,
+      "step": 940
+    },
+    {
+      "epoch": 1.2951601908657122,
+      "grad_norm": 0.3618335723876953,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 950
+    },
+    {
+      "epoch": 1.30879345603272,
+      "grad_norm": 0.345700740814209,
+      "learning_rate": 0.0002,
+      "loss": 1.7436,
+      "step": 960
+    },
+    {
+      "epoch": 1.3224267211997274,
+      "grad_norm": 0.3514927923679352,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 970
+    },
+    {
+      "epoch": 1.3360599863667348,
+      "grad_norm": 0.365647554397583,
+      "learning_rate": 0.0002,
+      "loss": 1.7704,
+      "step": 980
+    },
+    {
+      "epoch": 1.3496932515337423,
+      "grad_norm": 0.3407285809516907,
+      "learning_rate": 0.0002,
+      "loss": 1.7104,
+      "step": 990
+    },
+    {
+      "epoch": 1.3633265167007498,
+      "grad_norm": 0.3785437345504761,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3769597818677572,
+      "grad_norm": 0.34746724367141724,
+      "learning_rate": 0.0002,
+      "loss": 1.766,
+      "step": 1010
+    },
+    {
+      "epoch": 1.390593047034765,
+      "grad_norm": 0.362444132566452,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4042263122017724,
+      "grad_norm": 0.4424704611301422,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4178595773687799,
+      "grad_norm": 0.38722458481788635,
+      "learning_rate": 0.0002,
+      "loss": 1.726,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4314928425357873,
+      "grad_norm": 0.36089080572128296,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4451261077027948,
+      "grad_norm": 0.33817124366760254,
+      "learning_rate": 0.0002,
+      "loss": 1.6924,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4587593728698023,
+      "grad_norm": 0.34334081411361694,
+      "learning_rate": 0.0002,
+      "loss": 1.7165,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4723926380368098,
+      "grad_norm": 0.3776826858520508,
+      "learning_rate": 0.0002,
+      "loss": 1.6999,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4860259032038172,
+      "grad_norm": 0.4169026017189026,
+      "learning_rate": 0.0002,
+      "loss": 1.7605,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4996591683708247,
+      "grad_norm": 0.34898945689201355,
+      "learning_rate": 0.0002,
+      "loss": 1.7502,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5132924335378322,
+      "grad_norm": 0.34223780035972595,
+      "learning_rate": 0.0002,
+      "loss": 1.635,
+      "step": 1110
+    },
+    {
+      "epoch": 1.5269256987048399,
+      "grad_norm": 0.3686901032924652,
+      "learning_rate": 0.0002,
+      "loss": 1.7248,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5405589638718473,
+      "grad_norm": 0.35054415464401245,
+      "learning_rate": 0.0002,
+      "loss": 1.7525,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5541922290388548,
+      "grad_norm": 0.39496365189552307,
+      "learning_rate": 0.0002,
+      "loss": 1.7776,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5678254942058623,
+      "grad_norm": 0.35451626777648926,
+      "learning_rate": 0.0002,
+      "loss": 1.6574,
+      "step": 1150
+    },
+    {
+      "epoch": 1.58145875937287,
+      "grad_norm": 0.3848083019256592,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5950920245398774,
+      "grad_norm": 0.3760537803173065,
+      "learning_rate": 0.0002,
+      "loss": 1.7272,
+      "step": 1170
+    },
+    {
+      "epoch": 1.6087252897068849,
+      "grad_norm": 0.38981738686561584,
+      "learning_rate": 0.0002,
+      "loss": 1.7441,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6223585548738924,
+      "grad_norm": 0.36830949783325195,
+      "learning_rate": 0.0002,
+      "loss": 1.6951,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6359918200408998,
+      "grad_norm": 0.3405892848968506,
+      "learning_rate": 0.0002,
+      "loss": 1.6925,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6496250852079073,
+      "grad_norm": 0.39027872681617737,
+      "learning_rate": 0.0002,
+      "loss": 1.7473,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6632583503749148,
+      "grad_norm": 0.3342694044113159,
+      "learning_rate": 0.0002,
+      "loss": 1.6792,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6768916155419222,
+      "grad_norm": 0.3600076735019684,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6905248807089297,
+      "grad_norm": 0.3625542223453522,
+      "learning_rate": 0.0002,
+      "loss": 1.7021,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7041581458759372,
+      "grad_norm": 0.32170894742012024,
+      "learning_rate": 0.0002,
+      "loss": 1.6772,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7177914110429446,
+      "grad_norm": 0.3544139862060547,
+      "learning_rate": 0.0002,
+      "loss": 1.7152,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7314246762099523,
+      "grad_norm": 0.35113027691841125,
+      "learning_rate": 0.0002,
+      "loss": 1.7138,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7450579413769598,
+      "grad_norm": 0.3499974310398102,
+      "learning_rate": 0.0002,
+      "loss": 1.7095,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7586912065439673,
+      "grad_norm": 0.3285157382488251,
+      "learning_rate": 0.0002,
+      "loss": 1.7749,
+      "step": 1290
+    },
+    {
+      "epoch": 1.7723244717109747,
+      "grad_norm": 0.3701961636543274,
+      "learning_rate": 0.0002,
+      "loss": 1.6767,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7859577368779824,
+      "grad_norm": 0.3301318287849426,
+      "learning_rate": 0.0002,
+      "loss": 1.6282,
+      "step": 1310
+    },
+    {
+      "epoch": 1.79959100204499,
+      "grad_norm": 0.37801554799079895,
+      "learning_rate": 0.0002,
+      "loss": 1.7097,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8132242672119974,
+      "grad_norm": 0.3726748526096344,
+      "learning_rate": 0.0002,
+      "loss": 1.7437,
+      "step": 1330
+    },
+    {
+      "epoch": 1.8268575323790048,
+      "grad_norm": 0.4059790074825287,
+      "learning_rate": 0.0002,
+      "loss": 1.7959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 0.35712096095085144,
+      "learning_rate": 0.0002,
+      "loss": 1.7739,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8541240627130198,
+      "grad_norm": 0.35995328426361084,
+      "learning_rate": 0.0002,
+      "loss": 1.6375,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8677573278800272,
+      "grad_norm": 0.3679947257041931,
+      "learning_rate": 0.0002,
+      "loss": 1.7332,
+      "step": 1370
+    },
+    {
+      "epoch": 1.8813905930470347,
+      "grad_norm": 0.39645957946777344,
+      "learning_rate": 0.0002,
+      "loss": 1.7587,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950238582140422,
+      "grad_norm": 0.35288700461387634,
+      "learning_rate": 0.0002,
+      "loss": 1.6985,
+      "step": 1390
+    },
+    {
+      "epoch": 1.9086571233810496,
+      "grad_norm": 0.32579198479652405,
+      "learning_rate": 0.0002,
+      "loss": 1.6582,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9222903885480571,
+      "grad_norm": 0.3856561779975891,
+      "learning_rate": 0.0002,
+      "loss": 1.6948,
+      "step": 1410
+    },
+    {
+      "epoch": 1.9359236537150648,
+      "grad_norm": 0.39019331336021423,
+      "learning_rate": 0.0002,
+      "loss": 1.668,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9495569188820723,
+      "grad_norm": 0.38006502389907837,
+      "learning_rate": 0.0002,
+      "loss": 1.7774,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9631901840490797,
+      "grad_norm": 0.38100454211235046,
+      "learning_rate": 0.0002,
+      "loss": 1.8323,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9768234492160872,
+      "grad_norm": 0.3405798673629761,
+      "learning_rate": 0.0002,
+      "loss": 1.7298,
+      "step": 1450
+    },
+    {
+      "epoch": 1.990456714383095,
+      "grad_norm": 0.36582913994789124,
+      "learning_rate": 0.0002,
+      "loss": 1.7045,
+      "step": 1460
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8178424835205078,
+      "eval_runtime": 53.6524,
+      "eval_samples_per_second": 9.45,
+      "eval_steps_per_second": 1.193,
+      "step": 1467
+    },
+    {
+      "epoch": 2.0040899795501024,
+      "grad_norm": 0.3626647889614105,
+      "learning_rate": 0.0002,
+      "loss": 1.6363,
+      "step": 1470
+    },
+    {
+      "epoch": 2.01772324471711,
+      "grad_norm": 0.40171775221824646,
+      "learning_rate": 0.0002,
+      "loss": 1.5354,
+      "step": 1480
+    },
+    {
+      "epoch": 2.0313565098841173,
+      "grad_norm": 0.5805319547653198,
+      "learning_rate": 0.0002,
+      "loss": 1.5566,
+      "step": 1490
+    },
+    {
+      "epoch": 2.044989775051125,
+      "grad_norm": 0.41954153776168823,
+      "learning_rate": 0.0002,
+      "loss": 1.546,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0586230402181322,
+      "grad_norm": 0.47190725803375244,
+      "learning_rate": 0.0002,
+      "loss": 1.6158,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0722563053851397,
+      "grad_norm": 0.4388456344604492,
+      "learning_rate": 0.0002,
+      "loss": 1.5841,
+      "step": 1520
+    },
+    {
+      "epoch": 2.085889570552147,
+      "grad_norm": 2.2171926498413086,
+      "learning_rate": 0.0002,
+      "loss": 1.5835,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0995228357191547,
+      "grad_norm": 0.4314221143722534,
+      "learning_rate": 0.0002,
+      "loss": 1.6137,
+      "step": 1540
+    },
+    {
+      "epoch": 2.113156100886162,
+      "grad_norm": 0.4154265522956848,
+      "learning_rate": 0.0002,
+      "loss": 1.5511,
+      "step": 1550
+    },
+    {
+      "epoch": 2.1267893660531696,
+      "grad_norm": 0.5025539994239807,
+      "learning_rate": 0.0002,
+      "loss": 1.6323,
+      "step": 1560
+    },
+    {
+      "epoch": 2.140422631220177,
+      "grad_norm": 0.5410493016242981,
+      "learning_rate": 0.0002,
+      "loss": 1.5903,
+      "step": 1570
+    },
+    {
+      "epoch": 2.1540558963871845,
+      "grad_norm": 0.4478487968444824,
+      "learning_rate": 0.0002,
+      "loss": 1.507,
+      "step": 1580
+    },
+    {
+      "epoch": 2.1676891615541924,
+      "grad_norm": 0.4703652560710907,
+      "learning_rate": 0.0002,
+      "loss": 1.5536,
+      "step": 1590
+    },
+    {
+      "epoch": 2.1813224267212,
+      "grad_norm": 0.4555390179157257,
+      "learning_rate": 0.0002,
+      "loss": 1.5991,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1949556918882074,
+      "grad_norm": 0.4877263903617859,
+      "learning_rate": 0.0002,
+      "loss": 1.6117,
+      "step": 1610
+    },
+    {
+      "epoch": 2.208588957055215,
+      "grad_norm": 0.48708245158195496,
+      "learning_rate": 0.0002,
+      "loss": 1.5928,
+      "step": 1620
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.47523951530456543,
+      "learning_rate": 0.0002,
+      "loss": 1.6106,
+      "step": 1630
+    },
+    {
+      "epoch": 2.23585548738923,
+      "grad_norm": 0.4889199733734131,
+      "learning_rate": 0.0002,
+      "loss": 1.6013,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2494887525562373,
+      "grad_norm": 0.4585252106189728,
+      "learning_rate": 0.0002,
+      "loss": 1.6633,
+      "step": 1650
+    },
+    {
+      "epoch": 2.2631220177232447,
+      "grad_norm": 0.4764868915081024,
+      "learning_rate": 0.0002,
+      "loss": 1.6075,
+      "step": 1660
+    },
+    {
+      "epoch": 2.276755282890252,
+      "grad_norm": 0.5028976202011108,
+      "learning_rate": 0.0002,
+      "loss": 1.6427,
+      "step": 1670
+    },
+    {
+      "epoch": 2.2903885480572597,
+      "grad_norm": 0.46131211519241333,
+      "learning_rate": 0.0002,
+      "loss": 1.6258,
+      "step": 1680
+    },
+    {
+      "epoch": 2.304021813224267,
+      "grad_norm": 0.5422874689102173,
+      "learning_rate": 0.0002,
+      "loss": 1.654,
+      "step": 1690
+    },
+    {
+      "epoch": 2.3176550783912746,
+      "grad_norm": 0.47615355253219604,
+      "learning_rate": 0.0002,
+      "loss": 1.6331,
+      "step": 1700
+    },
+    {
+      "epoch": 2.331288343558282,
+      "grad_norm": 0.48005548119544983,
+      "learning_rate": 0.0002,
+      "loss": 1.642,
+      "step": 1710
+    },
+    {
+      "epoch": 2.3449216087252895,
+      "grad_norm": 0.4387182295322418,
+      "learning_rate": 0.0002,
+      "loss": 1.581,
+      "step": 1720
+    },
+    {
+      "epoch": 2.358554873892297,
+      "grad_norm": 0.4487272799015045,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 1730
+    },
+    {
+      "epoch": 2.372188139059305,
+      "grad_norm": 0.5046455264091492,
+      "learning_rate": 0.0002,
+      "loss": 1.5089,
+      "step": 1740
+    },
+    {
+      "epoch": 2.3858214042263124,
+      "grad_norm": 0.4653521180152893,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 1750
+    },
+    {
+      "epoch": 2.39945466939332,
+      "grad_norm": 0.4737723469734192,
+      "learning_rate": 0.0002,
+      "loss": 1.6201,
+      "step": 1760
+    },
+    {
+      "epoch": 2.4130879345603273,
+      "grad_norm": 0.4501931071281433,
+      "learning_rate": 0.0002,
+      "loss": 1.5933,
+      "step": 1770
+    },
+    {
+      "epoch": 2.426721199727335,
+      "grad_norm": 0.4772880971431732,
+      "learning_rate": 0.0002,
+      "loss": 1.6321,
+      "step": 1780
+    },
+    {
+      "epoch": 2.4403544648943423,
+      "grad_norm": 0.4544616937637329,
+      "learning_rate": 0.0002,
+      "loss": 1.5454,
+      "step": 1790
+    },
+    {
+      "epoch": 2.4539877300613497,
+      "grad_norm": 0.488313227891922,
+      "learning_rate": 0.0002,
+      "loss": 1.5501,
+      "step": 1800
+    },
+    {
+      "epoch": 2.467620995228357,
+      "grad_norm": 0.5057830214500427,
+      "learning_rate": 0.0002,
+      "loss": 1.5791,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4812542603953647,
+      "grad_norm": 0.5049484968185425,
+      "learning_rate": 0.0002,
+      "loss": 1.5645,
+      "step": 1820
+    },
+    {
+      "epoch": 2.494887525562372,
+      "grad_norm": 0.44966644048690796,
+      "learning_rate": 0.0002,
+      "loss": 1.6268,
+      "step": 1830
+    },
+    {
+      "epoch": 2.5085207907293796,
+      "grad_norm": 0.5072630643844604,
+      "learning_rate": 0.0002,
+      "loss": 1.5941,
+      "step": 1840
+    },
+    {
+      "epoch": 2.522154055896387,
+      "grad_norm": 0.43989792466163635,
+      "learning_rate": 0.0002,
+      "loss": 1.5251,
+      "step": 1850
+    },
+    {
+      "epoch": 2.5357873210633946,
+      "grad_norm": 1.3504403829574585,
+      "learning_rate": 0.0002,
+      "loss": 1.563,
+      "step": 1860
+    },
+    {
+      "epoch": 2.549420586230402,
+      "grad_norm": 0.46545976400375366,
+      "learning_rate": 0.0002,
+      "loss": 1.5681,
+      "step": 1870
+    },
+    {
+      "epoch": 2.5630538513974095,
+      "grad_norm": 0.4678342044353485,
+      "learning_rate": 0.0002,
+      "loss": 1.6368,
+      "step": 1880
+    },
+    {
+      "epoch": 2.5766871165644174,
+      "grad_norm": 0.529755711555481,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5903203817314244,
+      "grad_norm": 0.5000199675559998,
+      "learning_rate": 0.0002,
+      "loss": 1.5861,
+      "step": 1900
+    },
+    {
+      "epoch": 2.6039536468984323,
+      "grad_norm": 0.5649300217628479,
+      "learning_rate": 0.0002,
+      "loss": 1.6346,
+      "step": 1910
+    },
+    {
+      "epoch": 2.61758691206544,
+      "grad_norm": 0.7920585870742798,
+      "learning_rate": 0.0002,
+      "loss": 1.6317,
+      "step": 1920
+    },
+    {
+      "epoch": 2.6312201772324473,
+      "grad_norm": 0.4960342049598694,
+      "learning_rate": 0.0002,
+      "loss": 1.643,
+      "step": 1930
+    },
+    {
+      "epoch": 2.6448534423994547,
+      "grad_norm": 0.5324710011482239,
+      "learning_rate": 0.0002,
+      "loss": 1.6099,
+      "step": 1940
+    },
+    {
+      "epoch": 2.658486707566462,
+      "grad_norm": 0.606343150138855,
+      "learning_rate": 0.0002,
+      "loss": 1.5874,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6721199727334697,
+      "grad_norm": 0.53038489818573,
+      "learning_rate": 0.0002,
+      "loss": 1.5728,
+      "step": 1960
+    },
+    {
+      "epoch": 2.685753237900477,
+      "grad_norm": 0.4579465091228485,
+      "learning_rate": 0.0002,
+      "loss": 1.5583,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6993865030674846,
+      "grad_norm": 0.4541707932949066,
+      "learning_rate": 0.0002,
+      "loss": 1.6093,
+      "step": 1980
+    },
+    {
+      "epoch": 2.713019768234492,
+      "grad_norm": 0.5009395480155945,
+      "learning_rate": 0.0002,
+      "loss": 1.5316,
+      "step": 1990
+    },
+    {
+      "epoch": 2.7266530334014996,
+      "grad_norm": 0.4723006784915924,
+      "learning_rate": 0.0002,
+      "loss": 1.6724,
+      "step": 2000
+    },
+    {
+      "epoch": 2.740286298568507,
+      "grad_norm": 0.5086126923561096,
+      "learning_rate": 0.0002,
+      "loss": 1.638,
+      "step": 2010
+    },
+    {
+      "epoch": 2.7539195637355145,
+      "grad_norm": 0.47242608666419983,
+      "learning_rate": 0.0002,
+      "loss": 1.6223,
+      "step": 2020
+    },
+    {
+      "epoch": 2.767552828902522,
+      "grad_norm": 0.44922566413879395,
+      "learning_rate": 0.0002,
+      "loss": 1.6242,
+      "step": 2030
+    },
+    {
+      "epoch": 2.78118609406953,
+      "grad_norm": 0.420259565114975,
+      "learning_rate": 0.0002,
+      "loss": 1.6837,
+      "step": 2040
+    },
+    {
+      "epoch": 2.794819359236537,
+      "grad_norm": 0.4762881100177765,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 2050
+    },
+    {
+      "epoch": 2.808452624403545,
+      "grad_norm": 0.5228786468505859,
+      "learning_rate": 0.0002,
+      "loss": 1.5506,
+      "step": 2060
+    },
+    {
+      "epoch": 2.8220858895705523,
+      "grad_norm": 0.4796035587787628,
+      "learning_rate": 0.0002,
+      "loss": 1.6347,
+      "step": 2070
+    },
+    {
+      "epoch": 2.8357191547375598,
+      "grad_norm": 0.5034735202789307,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 2080
+    },
+    {
+      "epoch": 2.8493524199045672,
+      "grad_norm": 0.48005399107933044,
+      "learning_rate": 0.0002,
+      "loss": 1.6455,
+      "step": 2090
+    },
+    {
+      "epoch": 2.8629856850715747,
+      "grad_norm": 0.578820526599884,
+      "learning_rate": 0.0002,
+      "loss": 1.6287,
+      "step": 2100
+    },
+    {
+      "epoch": 2.876618950238582,
+      "grad_norm": 0.48982638120651245,
+      "learning_rate": 0.0002,
+      "loss": 1.6021,
+      "step": 2110
+    },
+    {
+      "epoch": 2.8902522154055896,
+      "grad_norm": 0.5157325863838196,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 2120
+    },
+    {
+      "epoch": 2.903885480572597,
+      "grad_norm": 0.49149683117866516,
+      "learning_rate": 0.0002,
+      "loss": 1.6089,
+      "step": 2130
+    },
+    {
+      "epoch": 2.9175187457396046,
+      "grad_norm": 0.48584499955177307,
+      "learning_rate": 0.0002,
+      "loss": 1.5881,
+      "step": 2140
+    },
+    {
+      "epoch": 2.931152010906612,
+      "grad_norm": 0.5199017524719238,
+      "learning_rate": 0.0002,
+      "loss": 1.5833,
+      "step": 2150
+    },
+    {
+      "epoch": 2.9447852760736195,
+      "grad_norm": 0.5788236856460571,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 2160
+    },
+    {
+      "epoch": 2.958418541240627,
+      "grad_norm": 0.48664185404777527,
+      "learning_rate": 0.0002,
+      "loss": 1.6103,
+      "step": 2170
+    },
+    {
+      "epoch": 2.9720518064076344,
+      "grad_norm": 0.5026682615280151,
+      "learning_rate": 0.0002,
+      "loss": 1.5765,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9856850715746424,
+      "grad_norm": 0.49317044019699097,
+      "learning_rate": 0.0002,
+      "loss": 1.6626,
+      "step": 2190
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "grad_norm": 0.5729128122329712,
+      "learning_rate": 0.0002,
+      "loss": 1.5871,
+      "step": 2200
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "eval_loss": 1.8527295589447021,
+      "eval_runtime": 53.6403,
+      "eval_samples_per_second": 9.452,
+      "eval_steps_per_second": 1.193,
+      "step": 2200
+    },
+    {
+      "epoch": 3.0129516019086573,
+      "grad_norm": 0.5530241131782532,
+      "learning_rate": 0.0002,
+      "loss": 1.4719,
+      "step": 2210
+    },
+    {
+      "epoch": 3.0265848670756648,
+      "grad_norm": 0.6642216444015503,
+      "learning_rate": 0.0002,
+      "loss": 1.4088,
+      "step": 2220
+    },
+    {
+      "epoch": 3.0402181322426722,
+      "grad_norm": 0.61470627784729,
+      "learning_rate": 0.0002,
+      "loss": 1.4382,
+      "step": 2230
+    },
+    {
+      "epoch": 3.0538513974096797,
+      "grad_norm": 0.8559566140174866,
+      "learning_rate": 0.0002,
+      "loss": 1.4634,
+      "step": 2240
+    },
+    {
+      "epoch": 3.067484662576687,
+      "grad_norm": 0.7015801668167114,
+      "learning_rate": 0.0002,
+      "loss": 1.3854,
+      "step": 2250
+    },
+    {
+      "epoch": 3.0811179277436946,
+      "grad_norm": 0.7226442694664001,
+      "learning_rate": 0.0002,
+      "loss": 1.4981,
+      "step": 2260
+    },
+    {
+      "epoch": 3.094751192910702,
+      "grad_norm": 0.7560588717460632,
+      "learning_rate": 0.0002,
+      "loss": 1.4143,
+      "step": 2270
+    },
+    {
+      "epoch": 3.1083844580777096,
+      "grad_norm": 0.6216568946838379,
+      "learning_rate": 0.0002,
+      "loss": 1.4395,
+      "step": 2280
+    },
+    {
+      "epoch": 3.122017723244717,
+      "grad_norm": 0.6768500804901123,
+      "learning_rate": 0.0002,
+      "loss": 1.3842,
+      "step": 2290
+    },
+    {
+      "epoch": 3.1356509884117245,
+      "grad_norm": 0.7028762102127075,
+      "learning_rate": 0.0002,
+      "loss": 1.4672,
+      "step": 2300
+    },
+    {
+      "epoch": 3.149284253578732,
+      "grad_norm": 0.6329697966575623,
+      "learning_rate": 0.0002,
+      "loss": 1.3826,
+      "step": 2310
+    },
+    {
+      "epoch": 3.1629175187457395,
+      "grad_norm": 0.6328264474868774,
+      "learning_rate": 0.0002,
+      "loss": 1.442,
+      "step": 2320
+    },
+    {
+      "epoch": 3.176550783912747,
+      "grad_norm": 0.7573632001876831,
+      "learning_rate": 0.0002,
+      "loss": 1.3762,
+      "step": 2330
+    },
+    {
+      "epoch": 3.190184049079755,
+      "grad_norm": 0.595740795135498,
+      "learning_rate": 0.0002,
+      "loss": 1.3553,
+      "step": 2340
+    },
+    {
+      "epoch": 3.2038173142467623,
+      "grad_norm": 0.7111806869506836,
+      "learning_rate": 0.0002,
+      "loss": 1.3953,
+      "step": 2350
+    },
+    {
+      "epoch": 3.2174505794137698,
+      "grad_norm": 0.6328730583190918,
+      "learning_rate": 0.0002,
+      "loss": 1.3797,
+      "step": 2360
+    },
+    {
+      "epoch": 3.2310838445807772,
+      "grad_norm": 0.5860254168510437,
+      "learning_rate": 0.0002,
+      "loss": 1.3855,
+      "step": 2370
+    },
+    {
+      "epoch": 3.2447171097477847,
+      "grad_norm": 0.7387157082557678,
+      "learning_rate": 0.0002,
+      "loss": 1.4267,
+      "step": 2380
+    },
+    {
+      "epoch": 3.258350374914792,
+      "grad_norm": 0.6897673606872559,
+      "learning_rate": 0.0002,
+      "loss": 1.4837,
+      "step": 2390
+    },
+    {
+      "epoch": 3.2719836400817996,
+      "grad_norm": 0.7157699465751648,
+      "learning_rate": 0.0002,
+      "loss": 1.4372,
+      "step": 2400
+    },
+    {
+      "epoch": 3.285616905248807,
+      "grad_norm": 0.6422511339187622,
+      "learning_rate": 0.0002,
+      "loss": 1.4432,
+      "step": 2410
+    },
+    {
+      "epoch": 3.2992501704158146,
+      "grad_norm": 1.0481886863708496,
+      "learning_rate": 0.0002,
+      "loss": 1.4828,
+      "step": 2420
+    },
+    {
+      "epoch": 3.312883435582822,
+      "grad_norm": 0.7050786018371582,
+      "learning_rate": 0.0002,
+      "loss": 1.4473,
+      "step": 2430
+    },
+    {
+      "epoch": 3.3265167007498295,
+      "grad_norm": 0.6090759038925171,
+      "learning_rate": 0.0002,
+      "loss": 1.3465,
+      "step": 2440
+    },
+    {
+      "epoch": 3.340149965916837,
+      "grad_norm": 0.6626465320587158,
+      "learning_rate": 0.0002,
+      "loss": 1.4619,
+      "step": 2450
+    },
+    {
+      "epoch": 3.3537832310838445,
+      "grad_norm": 0.6565486788749695,
+      "learning_rate": 0.0002,
+      "loss": 1.4512,
+      "step": 2460
+    },
+    {
+      "epoch": 3.367416496250852,
+      "grad_norm": 0.6449528932571411,
+      "learning_rate": 0.0002,
+      "loss": 1.588,
+      "step": 2470
+    },
+    {
+      "epoch": 3.3810497614178594,
+      "grad_norm": 0.7746227383613586,
+      "learning_rate": 0.0002,
+      "loss": 1.4773,
+      "step": 2480
+    },
+    {
+      "epoch": 3.3946830265848673,
+      "grad_norm": 0.7074846029281616,
+      "learning_rate": 0.0002,
+      "loss": 1.417,
+      "step": 2490
+    },
+    {
+      "epoch": 3.4083162917518743,
+      "grad_norm": 0.6547690033912659,
+      "learning_rate": 0.0002,
+      "loss": 1.4476,
+      "step": 2500
+    },
+    {
+      "epoch": 3.4219495569188823,
+      "grad_norm": 0.784721314907074,
+      "learning_rate": 0.0002,
+      "loss": 1.4074,
+      "step": 2510
+    },
+    {
+      "epoch": 3.4355828220858897,
+      "grad_norm": 0.7270277738571167,
+      "learning_rate": 0.0002,
+      "loss": 1.4326,
+      "step": 2520
+    },
+    {
+      "epoch": 3.449216087252897,
+      "grad_norm": 0.67588871717453,
+      "learning_rate": 0.0002,
+      "loss": 1.4354,
+      "step": 2530
+    },
+    {
+      "epoch": 3.4628493524199047,
+      "grad_norm": 0.6768023371696472,
+      "learning_rate": 0.0002,
+      "loss": 1.4074,
+      "step": 2540
+    },
+    {
+      "epoch": 3.476482617586912,
+      "grad_norm": 0.7026481628417969,
+      "learning_rate": 0.0002,
+      "loss": 1.4863,
+      "step": 2550
+    },
+    {
+      "epoch": 3.4901158827539196,
+      "grad_norm": 0.646075963973999,
+      "learning_rate": 0.0002,
+      "loss": 1.468,
+      "step": 2560
+    },
+    {
+      "epoch": 3.503749147920927,
+      "grad_norm": 0.6288973689079285,
+      "learning_rate": 0.0002,
+      "loss": 1.4058,
+      "step": 2570
+    },
+    {
+      "epoch": 3.5173824130879345,
+      "grad_norm": 0.6440825462341309,
+      "learning_rate": 0.0002,
+      "loss": 1.4613,
+      "step": 2580
+    },
+    {
+      "epoch": 3.531015678254942,
+      "grad_norm": 0.7074111700057983,
+      "learning_rate": 0.0002,
+      "loss": 1.3808,
+      "step": 2590
+    },
+    {
+      "epoch": 3.5446489434219495,
+      "grad_norm": 0.7007562518119812,
+      "learning_rate": 0.0002,
+      "loss": 1.4901,
+      "step": 2600
+    },
+    {
+      "epoch": 3.558282208588957,
+      "grad_norm": 0.6045376658439636,
+      "learning_rate": 0.0002,
+      "loss": 1.4511,
+      "step": 2610
+    },
+    {
+      "epoch": 3.5719154737559644,
+      "grad_norm": 0.9149952530860901,
+      "learning_rate": 0.0002,
+      "loss": 1.4596,
+      "step": 2620
+    },
+    {
+      "epoch": 3.585548738922972,
+      "grad_norm": 0.6490362882614136,
+      "learning_rate": 0.0002,
+      "loss": 1.4355,
+      "step": 2630
+    },
+    {
+      "epoch": 3.59918200408998,
+      "grad_norm": 0.6552226543426514,
+      "learning_rate": 0.0002,
+      "loss": 1.4107,
+      "step": 2640
+    },
+    {
+      "epoch": 3.612815269256987,
+      "grad_norm": 0.6541850566864014,
+      "learning_rate": 0.0002,
+      "loss": 1.433,
+      "step": 2650
+    },
+    {
+      "epoch": 3.6264485344239947,
+      "grad_norm": 0.6500770449638367,
+      "learning_rate": 0.0002,
+      "loss": 1.4279,
+      "step": 2660
+    },
+    {
+      "epoch": 3.640081799591002,
+      "grad_norm": 0.6345893740653992,
+      "learning_rate": 0.0002,
+      "loss": 1.3929,
+      "step": 2670
+    },
+    {
+      "epoch": 3.6537150647580097,
+      "grad_norm": 0.6382275223731995,
+      "learning_rate": 0.0002,
+      "loss": 1.3634,
+      "step": 2680
+    },
+    {
+      "epoch": 3.667348329925017,
+      "grad_norm": 0.6738566160202026,
+      "learning_rate": 0.0002,
+      "loss": 1.4478,
+      "step": 2690
+    },
+    {
+      "epoch": 3.6809815950920246,
+      "grad_norm": 0.7446315288543701,
+      "learning_rate": 0.0002,
+      "loss": 1.4642,
+      "step": 2700
+    },
+    {
+      "epoch": 3.694614860259032,
+      "grad_norm": 0.6717571020126343,
+      "learning_rate": 0.0002,
+      "loss": 1.4342,
+      "step": 2710
+    },
+    {
+      "epoch": 3.7082481254260395,
+      "grad_norm": 0.667259693145752,
+      "learning_rate": 0.0002,
+      "loss": 1.4285,
+      "step": 2720
+    },
+    {
+      "epoch": 3.721881390593047,
+      "grad_norm": 0.6808622479438782,
+      "learning_rate": 0.0002,
+      "loss": 1.5389,
+      "step": 2730
+    },
+    {
+      "epoch": 3.7355146557600545,
+      "grad_norm": 0.7254287004470825,
+      "learning_rate": 0.0002,
+      "loss": 1.4297,
+      "step": 2740
+    },
+    {
+      "epoch": 3.749147920927062,
+      "grad_norm": 0.6864007711410522,
+      "learning_rate": 0.0002,
+      "loss": 1.4176,
+      "step": 2750
+    },
+    {
+      "epoch": 3.7627811860940694,
+      "grad_norm": 0.7041361331939697,
+      "learning_rate": 0.0002,
+      "loss": 1.4811,
+      "step": 2760
+    },
+    {
+      "epoch": 3.776414451261077,
+      "grad_norm": 0.6559903025627136,
+      "learning_rate": 0.0002,
+      "loss": 1.4284,
+      "step": 2770
+    },
+    {
+      "epoch": 3.7900477164280844,
+      "grad_norm": 0.6602269411087036,
+      "learning_rate": 0.0002,
+      "loss": 1.4608,
+      "step": 2780
+    },
+    {
+      "epoch": 3.8036809815950923,
+      "grad_norm": 0.692611813545227,
+      "learning_rate": 0.0002,
+      "loss": 1.4588,
+      "step": 2790
+    },
+    {
+      "epoch": 3.8173142467620993,
+      "grad_norm": 0.7051475644111633,
+      "learning_rate": 0.0002,
+      "loss": 1.4065,
+      "step": 2800
+    },
+    {
+      "epoch": 3.830947511929107,
+      "grad_norm": 0.6685371398925781,
+      "learning_rate": 0.0002,
+      "loss": 1.4083,
+      "step": 2810
+    },
+    {
+      "epoch": 3.8445807770961147,
+      "grad_norm": 0.6706477403640747,
+      "learning_rate": 0.0002,
+      "loss": 1.5227,
+      "step": 2820
+    },
+    {
+      "epoch": 3.858214042263122,
+      "grad_norm": 0.6671637296676636,
+      "learning_rate": 0.0002,
+      "loss": 1.4076,
+      "step": 2830
+    },
+    {
+      "epoch": 3.8718473074301296,
+      "grad_norm": 0.694092333316803,
+      "learning_rate": 0.0002,
+      "loss": 1.4736,
+      "step": 2840
+    },
+    {
+      "epoch": 3.885480572597137,
+      "grad_norm": 0.7349600195884705,
+      "learning_rate": 0.0002,
+      "loss": 1.4161,
+      "step": 2850
+    },
+    {
+      "epoch": 3.8991138377641446,
+      "grad_norm": 0.6647971868515015,
+      "learning_rate": 0.0002,
+      "loss": 1.4617,
+      "step": 2860
+    },
+    {
+      "epoch": 3.912747102931152,
+      "grad_norm": 0.806656539440155,
+      "learning_rate": 0.0002,
+      "loss": 1.5046,
+      "step": 2870
+    },
+    {
+      "epoch": 3.9263803680981595,
+      "grad_norm": 0.6008772850036621,
+      "learning_rate": 0.0002,
+      "loss": 1.428,
+      "step": 2880
+    },
+    {
+      "epoch": 3.940013633265167,
+      "grad_norm": 0.659227728843689,
+      "learning_rate": 0.0002,
+      "loss": 1.4116,
+      "step": 2890
+    },
+    {
+      "epoch": 3.9536468984321744,
+      "grad_norm": 0.6357656717300415,
+      "learning_rate": 0.0002,
+      "loss": 1.4136,
+      "step": 2900
+    },
+    {
+      "epoch": 3.967280163599182,
+      "grad_norm": 0.6541687846183777,
+      "learning_rate": 0.0002,
+      "loss": 1.4655,
+      "step": 2910
+    },
+    {
+      "epoch": 3.9809134287661894,
+      "grad_norm": 0.6090909838676453,
+      "learning_rate": 0.0002,
+      "loss": 1.4854,
+      "step": 2920
+    },
+    {
+      "epoch": 3.994546693933197,
+      "grad_norm": 0.7198411822319031,
+      "learning_rate": 0.0002,
+      "loss": 1.4615,
+      "step": 2930
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.9278366565704346,
+      "eval_runtime": 53.6567,
+      "eval_samples_per_second": 9.449,
+      "eval_steps_per_second": 1.193,
+      "step": 2934
+    },
+    {
+      "epoch": 4.008179959100205,
+      "grad_norm": 0.6498575210571289,
+      "learning_rate": 0.0002,
+      "loss": 1.3159,
+      "step": 2940
+    },
+    {
+      "epoch": 4.021813224267212,
+      "grad_norm": 0.865602433681488,
+      "learning_rate": 0.0002,
+      "loss": 1.2075,
+      "step": 2950
+    },
+    {
+      "epoch": 4.03544648943422,
+      "grad_norm": 0.8514999151229858,
+      "learning_rate": 0.0002,
+      "loss": 1.1744,
+      "step": 2960
+    },
+    {
+      "epoch": 4.049079754601227,
+      "grad_norm": 1.0677322149276733,
+      "learning_rate": 0.0002,
+      "loss": 1.1553,
+      "step": 2970
+    },
+    {
+      "epoch": 4.062713019768235,
+      "grad_norm": 1.0126488208770752,
+      "learning_rate": 0.0002,
+      "loss": 1.1962,
+      "step": 2980
+    },
+    {
+      "epoch": 4.076346284935242,
+      "grad_norm": 1.0008870363235474,
+      "learning_rate": 0.0002,
+      "loss": 1.1631,
+      "step": 2990
+    },
+    {
+      "epoch": 4.08997955010225,
+      "grad_norm": 0.7942054271697998,
+      "learning_rate": 0.0002,
+      "loss": 1.2154,
+      "step": 3000
+    },
+    {
+      "epoch": 4.103612815269257,
+      "grad_norm": 1.0482100248336792,
+      "learning_rate": 0.0002,
+      "loss": 1.214,
+      "step": 3010
+    },
+    {
+      "epoch": 4.1172460804362645,
+      "grad_norm": 1.0516992807388306,
+      "learning_rate": 0.0002,
+      "loss": 1.1999,
+      "step": 3020
+    },
+    {
+      "epoch": 4.130879345603272,
+      "grad_norm": 0.8144322037696838,
+      "learning_rate": 0.0002,
+      "loss": 1.2108,
+      "step": 3030
+    },
+    {
+      "epoch": 4.144512610770279,
+      "grad_norm": 0.952297568321228,
+      "learning_rate": 0.0002,
+      "loss": 1.1782,
+      "step": 3040
+    },
+    {
+      "epoch": 4.158145875937287,
+      "grad_norm": 1.007645606994629,
+      "learning_rate": 0.0002,
+      "loss": 1.2814,
+      "step": 3050
+    },
+    {
+      "epoch": 4.171779141104294,
+      "grad_norm": 1.0480353832244873,
+      "learning_rate": 0.0002,
+      "loss": 1.1731,
+      "step": 3060
+    },
+    {
+      "epoch": 4.185412406271302,
+      "grad_norm": 0.9270663857460022,
+      "learning_rate": 0.0002,
+      "loss": 1.196,
+      "step": 3070
+    },
+    {
+      "epoch": 4.199045671438309,
+      "grad_norm": 1.3415262699127197,
+      "learning_rate": 0.0002,
+      "loss": 1.2167,
+      "step": 3080
+    },
+    {
+      "epoch": 4.212678936605317,
+      "grad_norm": 1.167606234550476,
+      "learning_rate": 0.0002,
+      "loss": 1.2601,
+      "step": 3090
+    },
+    {
+      "epoch": 4.226312201772324,
+      "grad_norm": 0.9418690800666809,
+      "learning_rate": 0.0002,
+      "loss": 1.2605,
+      "step": 3100
+    },
+    {
+      "epoch": 4.239945466939332,
+      "grad_norm": 1.0885876417160034,
+      "learning_rate": 0.0002,
+      "loss": 1.2184,
+      "step": 3110
+    },
+    {
+      "epoch": 4.253578732106339,
+      "grad_norm": 0.9165483713150024,
+      "learning_rate": 0.0002,
+      "loss": 1.2594,
+      "step": 3120
+    },
+    {
+      "epoch": 4.267211997273347,
+      "grad_norm": 0.9154694080352783,
+      "learning_rate": 0.0002,
+      "loss": 1.2933,
+      "step": 3130
+    },
+    {
+      "epoch": 4.280845262440354,
+      "grad_norm": 1.100580096244812,
+      "learning_rate": 0.0002,
+      "loss": 1.2584,
+      "step": 3140
+    },
+    {
+      "epoch": 4.294478527607362,
+      "grad_norm": 0.9367576241493225,
+      "learning_rate": 0.0002,
+      "loss": 1.251,
+      "step": 3150
+    },
+    {
+      "epoch": 4.308111792774369,
+      "grad_norm": 0.9744015336036682,
+      "learning_rate": 0.0002,
+      "loss": 1.2032,
+      "step": 3160
+    },
+    {
+      "epoch": 4.321745057941377,
+      "grad_norm": 0.9865175485610962,
+      "learning_rate": 0.0002,
+      "loss": 1.2787,
+      "step": 3170
+    },
+    {
+      "epoch": 4.335378323108385,
+      "grad_norm": 1.0124907493591309,
+      "learning_rate": 0.0002,
+      "loss": 1.2161,
+      "step": 3180
+    },
+    {
+      "epoch": 4.349011588275392,
+      "grad_norm": 1.1044819355010986,
+      "learning_rate": 0.0002,
+      "loss": 1.2452,
+      "step": 3190
+    },
+    {
+      "epoch": 4.3626448534424,
+      "grad_norm": 0.9305577278137207,
+      "learning_rate": 0.0002,
+      "loss": 1.2483,
+      "step": 3200
+    },
+    {
+      "epoch": 4.376278118609407,
+      "grad_norm": 0.969265341758728,
+      "learning_rate": 0.0002,
+      "loss": 1.2101,
+      "step": 3210
+    },
+    {
+      "epoch": 4.389911383776415,
+      "grad_norm": 1.0671923160552979,
+      "learning_rate": 0.0002,
+      "loss": 1.2355,
+      "step": 3220
+    },
+    {
+      "epoch": 4.403544648943422,
+      "grad_norm": 0.9440539479255676,
+      "learning_rate": 0.0002,
+      "loss": 1.2259,
+      "step": 3230
+    },
+    {
+      "epoch": 4.41717791411043,
+      "grad_norm": 0.9824562668800354,
+      "learning_rate": 0.0002,
+      "loss": 1.1706,
+      "step": 3240
+    },
+    {
+      "epoch": 4.430811179277437,
+      "grad_norm": 1.0245535373687744,
+      "learning_rate": 0.0002,
+      "loss": 1.2234,
+      "step": 3250
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.9629312753677368,
+      "learning_rate": 0.0002,
+      "loss": 1.2713,
+      "step": 3260
+    },
+    {
+      "epoch": 4.458077709611452,
+      "grad_norm": 1.1556470394134521,
+      "learning_rate": 0.0002,
+      "loss": 1.2689,
+      "step": 3270
+    },
+    {
+      "epoch": 4.47171097477846,
+      "grad_norm": 0.9796679019927979,
+      "learning_rate": 0.0002,
+      "loss": 1.2214,
+      "step": 3280
+    },
+    {
+      "epoch": 4.485344239945467,
+      "grad_norm": 0.9030535221099854,
+      "learning_rate": 0.0002,
+      "loss": 1.2823,
+      "step": 3290
+    },
+    {
+      "epoch": 4.4989775051124745,
+      "grad_norm": 0.9142820835113525,
+      "learning_rate": 0.0002,
+      "loss": 1.2111,
+      "step": 3300
+    },
+    {
+      "epoch": 4.5126107702794815,
+      "grad_norm": 0.966867208480835,
+      "learning_rate": 0.0002,
+      "loss": 1.2398,
+      "step": 3310
+    },
+    {
+      "epoch": 4.5262440354464895,
+      "grad_norm": 1.0127079486846924,
+      "learning_rate": 0.0002,
+      "loss": 1.2537,
+      "step": 3320
+    },
+    {
+      "epoch": 4.539877300613497,
+      "grad_norm": 1.055506706237793,
+      "learning_rate": 0.0002,
+      "loss": 1.2059,
+      "step": 3330
+    },
+    {
+      "epoch": 4.553510565780504,
+      "grad_norm": 0.9831468462944031,
+      "learning_rate": 0.0002,
+      "loss": 1.2958,
+      "step": 3340
+    },
+    {
+      "epoch": 4.567143830947512,
+      "grad_norm": 0.9304661154747009,
+      "learning_rate": 0.0002,
+      "loss": 1.2643,
+      "step": 3350
+    },
+    {
+      "epoch": 4.580777096114519,
+      "grad_norm": 0.9369107484817505,
+      "learning_rate": 0.0002,
+      "loss": 1.3621,
+      "step": 3360
+    },
+    {
+      "epoch": 4.594410361281527,
+      "grad_norm": 1.009506344795227,
+      "learning_rate": 0.0002,
+      "loss": 1.2301,
+      "step": 3370
+    },
+    {
+      "epoch": 4.608043626448534,
+      "grad_norm": 1.0575741529464722,
+      "learning_rate": 0.0002,
+      "loss": 1.2535,
+      "step": 3380
+    },
+    {
+      "epoch": 4.621676891615542,
+      "grad_norm": 0.9102860689163208,
+      "learning_rate": 0.0002,
+      "loss": 1.1914,
+      "step": 3390
+    },
+    {
+      "epoch": 4.635310156782549,
+      "grad_norm": 0.8111315965652466,
+      "learning_rate": 0.0002,
+      "loss": 1.3156,
+      "step": 3400
+    },
+    {
+      "epoch": 4.648943421949557,
+      "grad_norm": 0.9459649920463562,
+      "learning_rate": 0.0002,
+      "loss": 1.3103,
+      "step": 3410
+    },
+    {
+      "epoch": 4.662576687116564,
+      "grad_norm": 0.9709545969963074,
+      "learning_rate": 0.0002,
+      "loss": 1.3146,
+      "step": 3420
+    },
+    {
+      "epoch": 4.676209952283572,
+      "grad_norm": 0.9909247159957886,
+      "learning_rate": 0.0002,
+      "loss": 1.2958,
+      "step": 3430
+    },
+    {
+      "epoch": 4.689843217450579,
+      "grad_norm": 0.9094610810279846,
+      "learning_rate": 0.0002,
+      "loss": 1.3186,
+      "step": 3440
+    },
+    {
+      "epoch": 4.703476482617587,
+      "grad_norm": 0.9012220501899719,
+      "learning_rate": 0.0002,
+      "loss": 1.3397,
+      "step": 3450
+    },
+    {
+      "epoch": 4.717109747784594,
+      "grad_norm": 0.8669242858886719,
+      "learning_rate": 0.0002,
+      "loss": 1.2595,
+      "step": 3460
+    },
+    {
+      "epoch": 4.730743012951602,
+      "grad_norm": 0.9753699898719788,
+      "learning_rate": 0.0002,
+      "loss": 1.2762,
+      "step": 3470
+    },
+    {
+      "epoch": 4.74437627811861,
+      "grad_norm": 1.0252684354782104,
+      "learning_rate": 0.0002,
+      "loss": 1.2371,
+      "step": 3480
+    },
+    {
+      "epoch": 4.758009543285617,
+      "grad_norm": 1.208098292350769,
+      "learning_rate": 0.0002,
+      "loss": 1.2536,
+      "step": 3490
+    },
+    {
+      "epoch": 4.771642808452625,
+      "grad_norm": 0.8632914423942566,
+      "learning_rate": 0.0002,
+      "loss": 1.2256,
+      "step": 3500
+    },
+    {
+      "epoch": 4.785276073619632,
+      "grad_norm": 1.0084818601608276,
+      "learning_rate": 0.0002,
+      "loss": 1.3062,
+      "step": 3510
+    },
+    {
+      "epoch": 4.79890933878664,
+      "grad_norm": 0.9095172882080078,
+      "learning_rate": 0.0002,
+      "loss": 1.3004,
+      "step": 3520
+    },
+    {
+      "epoch": 4.812542603953647,
+      "grad_norm": 0.9740135669708252,
+      "learning_rate": 0.0002,
+      "loss": 1.263,
+      "step": 3530
+    },
+    {
+      "epoch": 4.826175869120655,
+      "grad_norm": 0.8862348794937134,
+      "learning_rate": 0.0002,
+      "loss": 1.2816,
+      "step": 3540
+    },
+    {
+      "epoch": 4.839809134287662,
+      "grad_norm": 1.0761774778366089,
+      "learning_rate": 0.0002,
+      "loss": 1.2275,
+      "step": 3550
+    },
+    {
+      "epoch": 4.85344239945467,
+      "grad_norm": 1.0134117603302002,
+      "learning_rate": 0.0002,
+      "loss": 1.2257,
+      "step": 3560
+    },
+    {
+      "epoch": 4.867075664621677,
+      "grad_norm": 0.9262851476669312,
+      "learning_rate": 0.0002,
+      "loss": 1.2904,
+      "step": 3570
+    },
+    {
+      "epoch": 4.8807089297886845,
+      "grad_norm": 0.9518504738807678,
+      "learning_rate": 0.0002,
+      "loss": 1.1466,
+      "step": 3580
+    },
+    {
+      "epoch": 4.894342194955692,
+      "grad_norm": 1.10103178024292,
+      "learning_rate": 0.0002,
+      "loss": 1.2741,
+      "step": 3590
+    },
+    {
+      "epoch": 4.9079754601226995,
+      "grad_norm": 1.0133225917816162,
+      "learning_rate": 0.0002,
+      "loss": 1.2592,
+      "step": 3600
+    },
+    {
+      "epoch": 4.9216087252897065,
+      "grad_norm": 0.9637737274169922,
+      "learning_rate": 0.0002,
+      "loss": 1.2856,
+      "step": 3610
+    },
+    {
+      "epoch": 4.935241990456714,
+      "grad_norm": 0.9800633192062378,
+      "learning_rate": 0.0002,
+      "loss": 1.2991,
+      "step": 3620
+    },
+    {
+      "epoch": 4.948875255623722,
+      "grad_norm": 1.0065973997116089,
+      "learning_rate": 0.0002,
+      "loss": 1.2872,
+      "step": 3630
+    },
+    {
+      "epoch": 4.962508520790729,
+      "grad_norm": 0.9354690313339233,
+      "learning_rate": 0.0002,
+      "loss": 1.2408,
+      "step": 3640
+    },
+    {
+      "epoch": 4.976141785957737,
+      "grad_norm": 0.9744119048118591,
+      "learning_rate": 0.0002,
+      "loss": 1.291,
+      "step": 3650
+    },
+    {
+      "epoch": 4.989775051124744,
+      "grad_norm": 0.9357708096504211,
+      "learning_rate": 0.0002,
+      "loss": 1.2513,
+      "step": 3660
+    },
+    {
+      "epoch": 4.999318336741649,
+      "eval_loss": 2.0763096809387207,
+      "eval_runtime": 53.6578,
+      "eval_samples_per_second": 9.449,
+      "eval_steps_per_second": 1.193,
+      "step": 3667
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5864,
+  "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": 1.883765370912768e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/training_args.bin b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..da7142eb13ed7f8418e5055c63a0fe0ca5e1972b
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-3667/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8beac9fdfb91726fdf7473c9e77541aa988c61dc8beaba03293eafbe9c0a376
+size 5560
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/README.md b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/adapter_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/adapter_model.safetensors b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2188e1bdc23b4ed3e71be03659b9c96893cb7646
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a790c1906953e4a115bc5678c3e6141b2eebc3df04b7b63d1093e0cbc9e53150
+size 143153376
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/optimizer.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1a599a749dfa2d7f5a2508070ecde9baeb3db6ff
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36dffa0d48892f3e6cd812f44538d1d4e9159c8ca81e9e662b3f10af1bb8986
+size 72886650
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/rng_state.pth b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2d1c459a2a19a9211d1c0eb29abddb21d17ec9b1
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb4c8acbbdaeb646518182574e28dbbef8acd1ddffaf25ac2b857469af8a5bb2
+size 14244
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/scheduler.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e5590ace99e6075f0ae001c1026ccfa7ccbf440b
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc75e6ddf6a19eaa52d203c945b4a84e1dd59632e32701773cae1cc55b1ec8f
+size 1064
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/special_tokens_map.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/tokenizer.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/tokenizer.model b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/tokenizer_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/trainer_state.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..7c388f3b5327c261ca592f48bd6f8703e83c1c1b
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/trainer_state.json
@@ -0,0 +1,3161 @@
+{
+  "best_metric": 1.8171186447143555,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733",
+  "epoch": 6.0,
+  "eval_steps": 10,
+  "global_step": 4401,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013633265167007498,
+      "grad_norm": 0.7714291214942932,
+      "learning_rate": 0.0002,
+      "loss": 3.0982,
+      "step": 10
+    },
+    {
+      "epoch": 0.027266530334014997,
+      "grad_norm": 0.5473978519439697,
+      "learning_rate": 0.0002,
+      "loss": 2.5206,
+      "step": 20
+    },
+    {
+      "epoch": 0.0408997955010225,
+      "grad_norm": 0.5452795624732971,
+      "learning_rate": 0.0002,
+      "loss": 2.3079,
+      "step": 30
+    },
+    {
+      "epoch": 0.054533060668029994,
+      "grad_norm": 0.5098028779029846,
+      "learning_rate": 0.0002,
+      "loss": 2.0019,
+      "step": 40
+    },
+    {
+      "epoch": 0.0681663258350375,
+      "grad_norm": 0.48062971234321594,
+      "learning_rate": 0.0002,
+      "loss": 1.9333,
+      "step": 50
+    },
+    {
+      "epoch": 0.081799591002045,
+      "grad_norm": 0.4505695104598999,
+      "learning_rate": 0.0002,
+      "loss": 1.9355,
+      "step": 60
+    },
+    {
+      "epoch": 0.09543285616905249,
+      "grad_norm": 0.41609591245651245,
+      "learning_rate": 0.0002,
+      "loss": 1.9312,
+      "step": 70
+    },
+    {
+      "epoch": 0.10906612133605999,
+      "grad_norm": 0.4323892593383789,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 80
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 0.4670293629169464,
+      "learning_rate": 0.0002,
+      "loss": 1.9294,
+      "step": 90
+    },
+    {
+      "epoch": 0.136332651670075,
+      "grad_norm": 0.40623316168785095,
+      "learning_rate": 0.0002,
+      "loss": 1.7946,
+      "step": 100
+    },
+    {
+      "epoch": 0.1499659168370825,
+      "grad_norm": 0.3620383143424988,
+      "learning_rate": 0.0002,
+      "loss": 1.8565,
+      "step": 110
+    },
+    {
+      "epoch": 0.16359918200409,
+      "grad_norm": 0.332218736410141,
+      "learning_rate": 0.0002,
+      "loss": 1.9238,
+      "step": 120
+    },
+    {
+      "epoch": 0.17723244717109748,
+      "grad_norm": 0.4004521667957306,
+      "learning_rate": 0.0002,
+      "loss": 1.93,
+      "step": 130
+    },
+    {
+      "epoch": 0.19086571233810498,
+      "grad_norm": 0.3698360323905945,
+      "learning_rate": 0.0002,
+      "loss": 1.7549,
+      "step": 140
+    },
+    {
+      "epoch": 0.20449897750511248,
+      "grad_norm": 0.3847949504852295,
+      "learning_rate": 0.0002,
+      "loss": 1.8771,
+      "step": 150
+    },
+    {
+      "epoch": 0.21813224267211997,
+      "grad_norm": 0.36843451857566833,
+      "learning_rate": 0.0002,
+      "loss": 1.8316,
+      "step": 160
+    },
+    {
+      "epoch": 0.23176550783912747,
+      "grad_norm": 0.37301021814346313,
+      "learning_rate": 0.0002,
+      "loss": 1.838,
+      "step": 170
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.3718886971473694,
+      "learning_rate": 0.0002,
+      "loss": 1.8909,
+      "step": 180
+    },
+    {
+      "epoch": 0.25903203817314246,
+      "grad_norm": 0.3088490962982178,
+      "learning_rate": 0.0002,
+      "loss": 1.8454,
+      "step": 190
+    },
+    {
+      "epoch": 0.27266530334015,
+      "grad_norm": 0.3611852526664734,
+      "learning_rate": 0.0002,
+      "loss": 1.9254,
+      "step": 200
+    },
+    {
+      "epoch": 0.28629856850715746,
+      "grad_norm": 0.36093324422836304,
+      "learning_rate": 0.0002,
+      "loss": 1.7844,
+      "step": 210
+    },
+    {
+      "epoch": 0.299931833674165,
+      "grad_norm": 0.3250400722026825,
+      "learning_rate": 0.0002,
+      "loss": 1.719,
+      "step": 220
+    },
+    {
+      "epoch": 0.31356509884117245,
+      "grad_norm": 0.3566756248474121,
+      "learning_rate": 0.0002,
+      "loss": 1.8729,
+      "step": 230
+    },
+    {
+      "epoch": 0.32719836400818,
+      "grad_norm": 0.32872408628463745,
+      "learning_rate": 0.0002,
+      "loss": 1.9259,
+      "step": 240
+    },
+    {
+      "epoch": 0.34083162917518744,
+      "grad_norm": 0.3983881175518036,
+      "learning_rate": 0.0002,
+      "loss": 1.9033,
+      "step": 250
+    },
+    {
+      "epoch": 0.35446489434219497,
+      "grad_norm": 0.3571510910987854,
+      "learning_rate": 0.0002,
+      "loss": 1.8588,
+      "step": 260
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 0.3036131262779236,
+      "learning_rate": 0.0002,
+      "loss": 1.8539,
+      "step": 270
+    },
+    {
+      "epoch": 0.38173142467620996,
+      "grad_norm": 0.36512863636016846,
+      "learning_rate": 0.0002,
+      "loss": 1.8572,
+      "step": 280
+    },
+    {
+      "epoch": 0.39536468984321743,
+      "grad_norm": 0.3429736793041229,
+      "learning_rate": 0.0002,
+      "loss": 1.8022,
+      "step": 290
+    },
+    {
+      "epoch": 0.40899795501022496,
+      "grad_norm": 0.3055964708328247,
+      "learning_rate": 0.0002,
+      "loss": 1.8754,
+      "step": 300
+    },
+    {
+      "epoch": 0.4226312201772324,
+      "grad_norm": 0.33801034092903137,
+      "learning_rate": 0.0002,
+      "loss": 1.8384,
+      "step": 310
+    },
+    {
+      "epoch": 0.43626448534423995,
+      "grad_norm": 0.348783016204834,
+      "learning_rate": 0.0002,
+      "loss": 1.7933,
+      "step": 320
+    },
+    {
+      "epoch": 0.4498977505112474,
+      "grad_norm": 0.3057514727115631,
+      "learning_rate": 0.0002,
+      "loss": 1.8451,
+      "step": 330
+    },
+    {
+      "epoch": 0.46353101567825494,
+      "grad_norm": 0.3849763572216034,
+      "learning_rate": 0.0002,
+      "loss": 1.8766,
+      "step": 340
+    },
+    {
+      "epoch": 0.47716428084526247,
+      "grad_norm": 0.30080053210258484,
+      "learning_rate": 0.0002,
+      "loss": 1.8073,
+      "step": 350
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.3595106303691864,
+      "learning_rate": 0.0002,
+      "loss": 1.8548,
+      "step": 360
+    },
+    {
+      "epoch": 0.5044308111792775,
+      "grad_norm": 0.31099820137023926,
+      "learning_rate": 0.0002,
+      "loss": 1.8232,
+      "step": 370
+    },
+    {
+      "epoch": 0.5180640763462849,
+      "grad_norm": 0.3157978355884552,
+      "learning_rate": 0.0002,
+      "loss": 1.7029,
+      "step": 380
+    },
+    {
+      "epoch": 0.5316973415132924,
+      "grad_norm": 0.27960965037345886,
+      "learning_rate": 0.0002,
+      "loss": 1.8265,
+      "step": 390
+    },
+    {
+      "epoch": 0.5453306066803,
+      "grad_norm": 0.3102385103702545,
+      "learning_rate": 0.0002,
+      "loss": 1.7414,
+      "step": 400
+    },
+    {
+      "epoch": 0.5589638718473074,
+      "grad_norm": 0.32828861474990845,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 410
+    },
+    {
+      "epoch": 0.5725971370143149,
+      "grad_norm": 0.29560017585754395,
+      "learning_rate": 0.0002,
+      "loss": 1.8165,
+      "step": 420
+    },
+    {
+      "epoch": 0.5862304021813224,
+      "grad_norm": 0.33316895365715027,
+      "learning_rate": 0.0002,
+      "loss": 1.9455,
+      "step": 430
+    },
+    {
+      "epoch": 0.59986366734833,
+      "grad_norm": 0.30420982837677,
+      "learning_rate": 0.0002,
+      "loss": 1.8241,
+      "step": 440
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 0.32619214057922363,
+      "learning_rate": 0.0002,
+      "loss": 1.7565,
+      "step": 450
+    },
+    {
+      "epoch": 0.6271301976823449,
+      "grad_norm": 0.3603750765323639,
+      "learning_rate": 0.0002,
+      "loss": 1.7945,
+      "step": 460
+    },
+    {
+      "epoch": 0.6407634628493524,
+      "grad_norm": 0.30834096670150757,
+      "learning_rate": 0.0002,
+      "loss": 1.7773,
+      "step": 470
+    },
+    {
+      "epoch": 0.65439672801636,
+      "grad_norm": 0.28756365180015564,
+      "learning_rate": 0.0002,
+      "loss": 1.8058,
+      "step": 480
+    },
+    {
+      "epoch": 0.6680299931833674,
+      "grad_norm": 0.2878406345844269,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 490
+    },
+    {
+      "epoch": 0.6816632583503749,
+      "grad_norm": 0.31329697370529175,
+      "learning_rate": 0.0002,
+      "loss": 1.8581,
+      "step": 500
+    },
+    {
+      "epoch": 0.6952965235173824,
+      "grad_norm": 0.3405822515487671,
+      "learning_rate": 0.0002,
+      "loss": 1.7886,
+      "step": 510
+    },
+    {
+      "epoch": 0.7089297886843899,
+      "grad_norm": 0.305560827255249,
+      "learning_rate": 0.0002,
+      "loss": 1.778,
+      "step": 520
+    },
+    {
+      "epoch": 0.7225630538513974,
+      "grad_norm": 0.2973416745662689,
+      "learning_rate": 0.0002,
+      "loss": 1.7592,
+      "step": 530
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 0.327303946018219,
+      "learning_rate": 0.0002,
+      "loss": 1.8223,
+      "step": 540
+    },
+    {
+      "epoch": 0.7498295841854125,
+      "grad_norm": 0.62595534324646,
+      "learning_rate": 0.0002,
+      "loss": 1.8591,
+      "step": 550
+    },
+    {
+      "epoch": 0.7634628493524199,
+      "grad_norm": 0.3129784166812897,
+      "learning_rate": 0.0002,
+      "loss": 1.7466,
+      "step": 560
+    },
+    {
+      "epoch": 0.7770961145194274,
+      "grad_norm": 0.32496583461761475,
+      "learning_rate": 0.0002,
+      "loss": 1.8035,
+      "step": 570
+    },
+    {
+      "epoch": 0.7907293796864349,
+      "grad_norm": 0.3098868131637573,
+      "learning_rate": 0.0002,
+      "loss": 1.7787,
+      "step": 580
+    },
+    {
+      "epoch": 0.8043626448534424,
+      "grad_norm": 0.30726853013038635,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 590
+    },
+    {
+      "epoch": 0.8179959100204499,
+      "grad_norm": 0.2964220643043518,
+      "learning_rate": 0.0002,
+      "loss": 1.7898,
+      "step": 600
+    },
+    {
+      "epoch": 0.8316291751874574,
+      "grad_norm": 0.32352274656295776,
+      "learning_rate": 0.0002,
+      "loss": 1.8114,
+      "step": 610
+    },
+    {
+      "epoch": 0.8452624403544649,
+      "grad_norm": 0.2938912510871887,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 620
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 0.295559823513031,
+      "learning_rate": 0.0002,
+      "loss": 1.7727,
+      "step": 630
+    },
+    {
+      "epoch": 0.8725289706884799,
+      "grad_norm": 0.34102028608322144,
+      "learning_rate": 0.0002,
+      "loss": 1.9,
+      "step": 640
+    },
+    {
+      "epoch": 0.8861622358554874,
+      "grad_norm": 0.29676181077957153,
+      "learning_rate": 0.0002,
+      "loss": 1.8006,
+      "step": 650
+    },
+    {
+      "epoch": 0.8997955010224948,
+      "grad_norm": 0.3108902871608734,
+      "learning_rate": 0.0002,
+      "loss": 1.8099,
+      "step": 660
+    },
+    {
+      "epoch": 0.9134287661895024,
+      "grad_norm": 0.2690821588039398,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 670
+    },
+    {
+      "epoch": 0.9270620313565099,
+      "grad_norm": 0.32752540707588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7881,
+      "step": 680
+    },
+    {
+      "epoch": 0.9406952965235174,
+      "grad_norm": 0.8029476404190063,
+      "learning_rate": 0.0002,
+      "loss": 1.7661,
+      "step": 690
+    },
+    {
+      "epoch": 0.9543285616905249,
+      "grad_norm": 0.30534422397613525,
+      "learning_rate": 0.0002,
+      "loss": 1.7733,
+      "step": 700
+    },
+    {
+      "epoch": 0.9679618268575324,
+      "grad_norm": 0.2899954319000244,
+      "learning_rate": 0.0002,
+      "loss": 1.7614,
+      "step": 710
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 0.28814372420310974,
+      "learning_rate": 0.0002,
+      "loss": 1.7845,
+      "step": 720
+    },
+    {
+      "epoch": 0.9952283571915473,
+      "grad_norm": 0.3061596751213074,
+      "learning_rate": 0.0002,
+      "loss": 1.8865,
+      "step": 730
+    },
+    {
+      "epoch": 0.9993183367416496,
+      "eval_loss": 1.8171186447143555,
+      "eval_runtime": 53.6047,
+      "eval_samples_per_second": 9.458,
+      "eval_steps_per_second": 1.194,
+      "step": 733
+    },
+    {
+      "epoch": 1.008861622358555,
+      "grad_norm": 0.3140897750854492,
+      "learning_rate": 0.0002,
+      "loss": 1.6202,
+      "step": 740
+    },
+    {
+      "epoch": 1.0224948875255624,
+      "grad_norm": 0.3346109390258789,
+      "learning_rate": 0.0002,
+      "loss": 1.8409,
+      "step": 750
+    },
+    {
+      "epoch": 1.0361281526925699,
+      "grad_norm": 0.3582976758480072,
+      "learning_rate": 0.0002,
+      "loss": 1.6777,
+      "step": 760
+    },
+    {
+      "epoch": 1.0497614178595773,
+      "grad_norm": 0.30408260226249695,
+      "learning_rate": 0.0002,
+      "loss": 1.7306,
+      "step": 770
+    },
+    {
+      "epoch": 1.0633946830265848,
+      "grad_norm": 0.323585569858551,
+      "learning_rate": 0.0002,
+      "loss": 1.6967,
+      "step": 780
+    },
+    {
+      "epoch": 1.0770279481935923,
+      "grad_norm": 0.3474137783050537,
+      "learning_rate": 0.0002,
+      "loss": 1.768,
+      "step": 790
+    },
+    {
+      "epoch": 1.0906612133606,
+      "grad_norm": 0.35721147060394287,
+      "learning_rate": 0.0002,
+      "loss": 1.6895,
+      "step": 800
+    },
+    {
+      "epoch": 1.1042944785276074,
+      "grad_norm": 0.35366931557655334,
+      "learning_rate": 0.0002,
+      "loss": 1.718,
+      "step": 810
+    },
+    {
+      "epoch": 1.117927743694615,
+      "grad_norm": 0.3250770568847656,
+      "learning_rate": 0.0002,
+      "loss": 1.6797,
+      "step": 820
+    },
+    {
+      "epoch": 1.1315610088616224,
+      "grad_norm": 0.3293766379356384,
+      "learning_rate": 0.0002,
+      "loss": 1.6383,
+      "step": 830
+    },
+    {
+      "epoch": 1.1451942740286298,
+      "grad_norm": 0.3380851745605469,
+      "learning_rate": 0.0002,
+      "loss": 1.7353,
+      "step": 840
+    },
+    {
+      "epoch": 1.1588275391956373,
+      "grad_norm": 0.32584455609321594,
+      "learning_rate": 0.0002,
+      "loss": 1.8236,
+      "step": 850
+    },
+    {
+      "epoch": 1.1724608043626448,
+      "grad_norm": 0.45700767636299133,
+      "learning_rate": 0.0002,
+      "loss": 1.6681,
+      "step": 860
+    },
+    {
+      "epoch": 1.1860940695296525,
+      "grad_norm": 0.30944544076919556,
+      "learning_rate": 0.0002,
+      "loss": 1.7494,
+      "step": 870
+    },
+    {
+      "epoch": 1.19972733469666,
+      "grad_norm": 0.3268151581287384,
+      "learning_rate": 0.0002,
+      "loss": 1.7426,
+      "step": 880
+    },
+    {
+      "epoch": 1.2133605998636674,
+      "grad_norm": 0.39972540736198425,
+      "learning_rate": 0.0002,
+      "loss": 1.7413,
+      "step": 890
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 0.7890929579734802,
+      "learning_rate": 0.0002,
+      "loss": 1.7481,
+      "step": 900
+    },
+    {
+      "epoch": 1.2406271301976823,
+      "grad_norm": 0.3439182639122009,
+      "learning_rate": 0.0002,
+      "loss": 1.7608,
+      "step": 910
+    },
+    {
+      "epoch": 1.2542603953646898,
+      "grad_norm": 0.3986225128173828,
+      "learning_rate": 0.0002,
+      "loss": 1.7617,
+      "step": 920
+    },
+    {
+      "epoch": 1.2678936605316973,
+      "grad_norm": 0.3514605164527893,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 930
+    },
+    {
+      "epoch": 1.2815269256987047,
+      "grad_norm": 0.3682589530944824,
+      "learning_rate": 0.0002,
+      "loss": 1.6987,
+      "step": 940
+    },
+    {
+      "epoch": 1.2951601908657122,
+      "grad_norm": 0.3618335723876953,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 950
+    },
+    {
+      "epoch": 1.30879345603272,
+      "grad_norm": 0.345700740814209,
+      "learning_rate": 0.0002,
+      "loss": 1.7436,
+      "step": 960
+    },
+    {
+      "epoch": 1.3224267211997274,
+      "grad_norm": 0.3514927923679352,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 970
+    },
+    {
+      "epoch": 1.3360599863667348,
+      "grad_norm": 0.365647554397583,
+      "learning_rate": 0.0002,
+      "loss": 1.7704,
+      "step": 980
+    },
+    {
+      "epoch": 1.3496932515337423,
+      "grad_norm": 0.3407285809516907,
+      "learning_rate": 0.0002,
+      "loss": 1.7104,
+      "step": 990
+    },
+    {
+      "epoch": 1.3633265167007498,
+      "grad_norm": 0.3785437345504761,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3769597818677572,
+      "grad_norm": 0.34746724367141724,
+      "learning_rate": 0.0002,
+      "loss": 1.766,
+      "step": 1010
+    },
+    {
+      "epoch": 1.390593047034765,
+      "grad_norm": 0.362444132566452,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4042263122017724,
+      "grad_norm": 0.4424704611301422,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4178595773687799,
+      "grad_norm": 0.38722458481788635,
+      "learning_rate": 0.0002,
+      "loss": 1.726,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4314928425357873,
+      "grad_norm": 0.36089080572128296,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4451261077027948,
+      "grad_norm": 0.33817124366760254,
+      "learning_rate": 0.0002,
+      "loss": 1.6924,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4587593728698023,
+      "grad_norm": 0.34334081411361694,
+      "learning_rate": 0.0002,
+      "loss": 1.7165,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4723926380368098,
+      "grad_norm": 0.3776826858520508,
+      "learning_rate": 0.0002,
+      "loss": 1.6999,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4860259032038172,
+      "grad_norm": 0.4169026017189026,
+      "learning_rate": 0.0002,
+      "loss": 1.7605,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4996591683708247,
+      "grad_norm": 0.34898945689201355,
+      "learning_rate": 0.0002,
+      "loss": 1.7502,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5132924335378322,
+      "grad_norm": 0.34223780035972595,
+      "learning_rate": 0.0002,
+      "loss": 1.635,
+      "step": 1110
+    },
+    {
+      "epoch": 1.5269256987048399,
+      "grad_norm": 0.3686901032924652,
+      "learning_rate": 0.0002,
+      "loss": 1.7248,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5405589638718473,
+      "grad_norm": 0.35054415464401245,
+      "learning_rate": 0.0002,
+      "loss": 1.7525,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5541922290388548,
+      "grad_norm": 0.39496365189552307,
+      "learning_rate": 0.0002,
+      "loss": 1.7776,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5678254942058623,
+      "grad_norm": 0.35451626777648926,
+      "learning_rate": 0.0002,
+      "loss": 1.6574,
+      "step": 1150
+    },
+    {
+      "epoch": 1.58145875937287,
+      "grad_norm": 0.3848083019256592,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5950920245398774,
+      "grad_norm": 0.3760537803173065,
+      "learning_rate": 0.0002,
+      "loss": 1.7272,
+      "step": 1170
+    },
+    {
+      "epoch": 1.6087252897068849,
+      "grad_norm": 0.38981738686561584,
+      "learning_rate": 0.0002,
+      "loss": 1.7441,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6223585548738924,
+      "grad_norm": 0.36830949783325195,
+      "learning_rate": 0.0002,
+      "loss": 1.6951,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6359918200408998,
+      "grad_norm": 0.3405892848968506,
+      "learning_rate": 0.0002,
+      "loss": 1.6925,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6496250852079073,
+      "grad_norm": 0.39027872681617737,
+      "learning_rate": 0.0002,
+      "loss": 1.7473,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6632583503749148,
+      "grad_norm": 0.3342694044113159,
+      "learning_rate": 0.0002,
+      "loss": 1.6792,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6768916155419222,
+      "grad_norm": 0.3600076735019684,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6905248807089297,
+      "grad_norm": 0.3625542223453522,
+      "learning_rate": 0.0002,
+      "loss": 1.7021,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7041581458759372,
+      "grad_norm": 0.32170894742012024,
+      "learning_rate": 0.0002,
+      "loss": 1.6772,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7177914110429446,
+      "grad_norm": 0.3544139862060547,
+      "learning_rate": 0.0002,
+      "loss": 1.7152,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7314246762099523,
+      "grad_norm": 0.35113027691841125,
+      "learning_rate": 0.0002,
+      "loss": 1.7138,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7450579413769598,
+      "grad_norm": 0.3499974310398102,
+      "learning_rate": 0.0002,
+      "loss": 1.7095,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7586912065439673,
+      "grad_norm": 0.3285157382488251,
+      "learning_rate": 0.0002,
+      "loss": 1.7749,
+      "step": 1290
+    },
+    {
+      "epoch": 1.7723244717109747,
+      "grad_norm": 0.3701961636543274,
+      "learning_rate": 0.0002,
+      "loss": 1.6767,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7859577368779824,
+      "grad_norm": 0.3301318287849426,
+      "learning_rate": 0.0002,
+      "loss": 1.6282,
+      "step": 1310
+    },
+    {
+      "epoch": 1.79959100204499,
+      "grad_norm": 0.37801554799079895,
+      "learning_rate": 0.0002,
+      "loss": 1.7097,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8132242672119974,
+      "grad_norm": 0.3726748526096344,
+      "learning_rate": 0.0002,
+      "loss": 1.7437,
+      "step": 1330
+    },
+    {
+      "epoch": 1.8268575323790048,
+      "grad_norm": 0.4059790074825287,
+      "learning_rate": 0.0002,
+      "loss": 1.7959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 0.35712096095085144,
+      "learning_rate": 0.0002,
+      "loss": 1.7739,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8541240627130198,
+      "grad_norm": 0.35995328426361084,
+      "learning_rate": 0.0002,
+      "loss": 1.6375,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8677573278800272,
+      "grad_norm": 0.3679947257041931,
+      "learning_rate": 0.0002,
+      "loss": 1.7332,
+      "step": 1370
+    },
+    {
+      "epoch": 1.8813905930470347,
+      "grad_norm": 0.39645957946777344,
+      "learning_rate": 0.0002,
+      "loss": 1.7587,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950238582140422,
+      "grad_norm": 0.35288700461387634,
+      "learning_rate": 0.0002,
+      "loss": 1.6985,
+      "step": 1390
+    },
+    {
+      "epoch": 1.9086571233810496,
+      "grad_norm": 0.32579198479652405,
+      "learning_rate": 0.0002,
+      "loss": 1.6582,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9222903885480571,
+      "grad_norm": 0.3856561779975891,
+      "learning_rate": 0.0002,
+      "loss": 1.6948,
+      "step": 1410
+    },
+    {
+      "epoch": 1.9359236537150648,
+      "grad_norm": 0.39019331336021423,
+      "learning_rate": 0.0002,
+      "loss": 1.668,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9495569188820723,
+      "grad_norm": 0.38006502389907837,
+      "learning_rate": 0.0002,
+      "loss": 1.7774,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9631901840490797,
+      "grad_norm": 0.38100454211235046,
+      "learning_rate": 0.0002,
+      "loss": 1.8323,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9768234492160872,
+      "grad_norm": 0.3405798673629761,
+      "learning_rate": 0.0002,
+      "loss": 1.7298,
+      "step": 1450
+    },
+    {
+      "epoch": 1.990456714383095,
+      "grad_norm": 0.36582913994789124,
+      "learning_rate": 0.0002,
+      "loss": 1.7045,
+      "step": 1460
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8178424835205078,
+      "eval_runtime": 53.6524,
+      "eval_samples_per_second": 9.45,
+      "eval_steps_per_second": 1.193,
+      "step": 1467
+    },
+    {
+      "epoch": 2.0040899795501024,
+      "grad_norm": 0.3626647889614105,
+      "learning_rate": 0.0002,
+      "loss": 1.6363,
+      "step": 1470
+    },
+    {
+      "epoch": 2.01772324471711,
+      "grad_norm": 0.40171775221824646,
+      "learning_rate": 0.0002,
+      "loss": 1.5354,
+      "step": 1480
+    },
+    {
+      "epoch": 2.0313565098841173,
+      "grad_norm": 0.5805319547653198,
+      "learning_rate": 0.0002,
+      "loss": 1.5566,
+      "step": 1490
+    },
+    {
+      "epoch": 2.044989775051125,
+      "grad_norm": 0.41954153776168823,
+      "learning_rate": 0.0002,
+      "loss": 1.546,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0586230402181322,
+      "grad_norm": 0.47190725803375244,
+      "learning_rate": 0.0002,
+      "loss": 1.6158,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0722563053851397,
+      "grad_norm": 0.4388456344604492,
+      "learning_rate": 0.0002,
+      "loss": 1.5841,
+      "step": 1520
+    },
+    {
+      "epoch": 2.085889570552147,
+      "grad_norm": 2.2171926498413086,
+      "learning_rate": 0.0002,
+      "loss": 1.5835,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0995228357191547,
+      "grad_norm": 0.4314221143722534,
+      "learning_rate": 0.0002,
+      "loss": 1.6137,
+      "step": 1540
+    },
+    {
+      "epoch": 2.113156100886162,
+      "grad_norm": 0.4154265522956848,
+      "learning_rate": 0.0002,
+      "loss": 1.5511,
+      "step": 1550
+    },
+    {
+      "epoch": 2.1267893660531696,
+      "grad_norm": 0.5025539994239807,
+      "learning_rate": 0.0002,
+      "loss": 1.6323,
+      "step": 1560
+    },
+    {
+      "epoch": 2.140422631220177,
+      "grad_norm": 0.5410493016242981,
+      "learning_rate": 0.0002,
+      "loss": 1.5903,
+      "step": 1570
+    },
+    {
+      "epoch": 2.1540558963871845,
+      "grad_norm": 0.4478487968444824,
+      "learning_rate": 0.0002,
+      "loss": 1.507,
+      "step": 1580
+    },
+    {
+      "epoch": 2.1676891615541924,
+      "grad_norm": 0.4703652560710907,
+      "learning_rate": 0.0002,
+      "loss": 1.5536,
+      "step": 1590
+    },
+    {
+      "epoch": 2.1813224267212,
+      "grad_norm": 0.4555390179157257,
+      "learning_rate": 0.0002,
+      "loss": 1.5991,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1949556918882074,
+      "grad_norm": 0.4877263903617859,
+      "learning_rate": 0.0002,
+      "loss": 1.6117,
+      "step": 1610
+    },
+    {
+      "epoch": 2.208588957055215,
+      "grad_norm": 0.48708245158195496,
+      "learning_rate": 0.0002,
+      "loss": 1.5928,
+      "step": 1620
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.47523951530456543,
+      "learning_rate": 0.0002,
+      "loss": 1.6106,
+      "step": 1630
+    },
+    {
+      "epoch": 2.23585548738923,
+      "grad_norm": 0.4889199733734131,
+      "learning_rate": 0.0002,
+      "loss": 1.6013,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2494887525562373,
+      "grad_norm": 0.4585252106189728,
+      "learning_rate": 0.0002,
+      "loss": 1.6633,
+      "step": 1650
+    },
+    {
+      "epoch": 2.2631220177232447,
+      "grad_norm": 0.4764868915081024,
+      "learning_rate": 0.0002,
+      "loss": 1.6075,
+      "step": 1660
+    },
+    {
+      "epoch": 2.276755282890252,
+      "grad_norm": 0.5028976202011108,
+      "learning_rate": 0.0002,
+      "loss": 1.6427,
+      "step": 1670
+    },
+    {
+      "epoch": 2.2903885480572597,
+      "grad_norm": 0.46131211519241333,
+      "learning_rate": 0.0002,
+      "loss": 1.6258,
+      "step": 1680
+    },
+    {
+      "epoch": 2.304021813224267,
+      "grad_norm": 0.5422874689102173,
+      "learning_rate": 0.0002,
+      "loss": 1.654,
+      "step": 1690
+    },
+    {
+      "epoch": 2.3176550783912746,
+      "grad_norm": 0.47615355253219604,
+      "learning_rate": 0.0002,
+      "loss": 1.6331,
+      "step": 1700
+    },
+    {
+      "epoch": 2.331288343558282,
+      "grad_norm": 0.48005548119544983,
+      "learning_rate": 0.0002,
+      "loss": 1.642,
+      "step": 1710
+    },
+    {
+      "epoch": 2.3449216087252895,
+      "grad_norm": 0.4387182295322418,
+      "learning_rate": 0.0002,
+      "loss": 1.581,
+      "step": 1720
+    },
+    {
+      "epoch": 2.358554873892297,
+      "grad_norm": 0.4487272799015045,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 1730
+    },
+    {
+      "epoch": 2.372188139059305,
+      "grad_norm": 0.5046455264091492,
+      "learning_rate": 0.0002,
+      "loss": 1.5089,
+      "step": 1740
+    },
+    {
+      "epoch": 2.3858214042263124,
+      "grad_norm": 0.4653521180152893,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 1750
+    },
+    {
+      "epoch": 2.39945466939332,
+      "grad_norm": 0.4737723469734192,
+      "learning_rate": 0.0002,
+      "loss": 1.6201,
+      "step": 1760
+    },
+    {
+      "epoch": 2.4130879345603273,
+      "grad_norm": 0.4501931071281433,
+      "learning_rate": 0.0002,
+      "loss": 1.5933,
+      "step": 1770
+    },
+    {
+      "epoch": 2.426721199727335,
+      "grad_norm": 0.4772880971431732,
+      "learning_rate": 0.0002,
+      "loss": 1.6321,
+      "step": 1780
+    },
+    {
+      "epoch": 2.4403544648943423,
+      "grad_norm": 0.4544616937637329,
+      "learning_rate": 0.0002,
+      "loss": 1.5454,
+      "step": 1790
+    },
+    {
+      "epoch": 2.4539877300613497,
+      "grad_norm": 0.488313227891922,
+      "learning_rate": 0.0002,
+      "loss": 1.5501,
+      "step": 1800
+    },
+    {
+      "epoch": 2.467620995228357,
+      "grad_norm": 0.5057830214500427,
+      "learning_rate": 0.0002,
+      "loss": 1.5791,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4812542603953647,
+      "grad_norm": 0.5049484968185425,
+      "learning_rate": 0.0002,
+      "loss": 1.5645,
+      "step": 1820
+    },
+    {
+      "epoch": 2.494887525562372,
+      "grad_norm": 0.44966644048690796,
+      "learning_rate": 0.0002,
+      "loss": 1.6268,
+      "step": 1830
+    },
+    {
+      "epoch": 2.5085207907293796,
+      "grad_norm": 0.5072630643844604,
+      "learning_rate": 0.0002,
+      "loss": 1.5941,
+      "step": 1840
+    },
+    {
+      "epoch": 2.522154055896387,
+      "grad_norm": 0.43989792466163635,
+      "learning_rate": 0.0002,
+      "loss": 1.5251,
+      "step": 1850
+    },
+    {
+      "epoch": 2.5357873210633946,
+      "grad_norm": 1.3504403829574585,
+      "learning_rate": 0.0002,
+      "loss": 1.563,
+      "step": 1860
+    },
+    {
+      "epoch": 2.549420586230402,
+      "grad_norm": 0.46545976400375366,
+      "learning_rate": 0.0002,
+      "loss": 1.5681,
+      "step": 1870
+    },
+    {
+      "epoch": 2.5630538513974095,
+      "grad_norm": 0.4678342044353485,
+      "learning_rate": 0.0002,
+      "loss": 1.6368,
+      "step": 1880
+    },
+    {
+      "epoch": 2.5766871165644174,
+      "grad_norm": 0.529755711555481,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5903203817314244,
+      "grad_norm": 0.5000199675559998,
+      "learning_rate": 0.0002,
+      "loss": 1.5861,
+      "step": 1900
+    },
+    {
+      "epoch": 2.6039536468984323,
+      "grad_norm": 0.5649300217628479,
+      "learning_rate": 0.0002,
+      "loss": 1.6346,
+      "step": 1910
+    },
+    {
+      "epoch": 2.61758691206544,
+      "grad_norm": 0.7920585870742798,
+      "learning_rate": 0.0002,
+      "loss": 1.6317,
+      "step": 1920
+    },
+    {
+      "epoch": 2.6312201772324473,
+      "grad_norm": 0.4960342049598694,
+      "learning_rate": 0.0002,
+      "loss": 1.643,
+      "step": 1930
+    },
+    {
+      "epoch": 2.6448534423994547,
+      "grad_norm": 0.5324710011482239,
+      "learning_rate": 0.0002,
+      "loss": 1.6099,
+      "step": 1940
+    },
+    {
+      "epoch": 2.658486707566462,
+      "grad_norm": 0.606343150138855,
+      "learning_rate": 0.0002,
+      "loss": 1.5874,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6721199727334697,
+      "grad_norm": 0.53038489818573,
+      "learning_rate": 0.0002,
+      "loss": 1.5728,
+      "step": 1960
+    },
+    {
+      "epoch": 2.685753237900477,
+      "grad_norm": 0.4579465091228485,
+      "learning_rate": 0.0002,
+      "loss": 1.5583,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6993865030674846,
+      "grad_norm": 0.4541707932949066,
+      "learning_rate": 0.0002,
+      "loss": 1.6093,
+      "step": 1980
+    },
+    {
+      "epoch": 2.713019768234492,
+      "grad_norm": 0.5009395480155945,
+      "learning_rate": 0.0002,
+      "loss": 1.5316,
+      "step": 1990
+    },
+    {
+      "epoch": 2.7266530334014996,
+      "grad_norm": 0.4723006784915924,
+      "learning_rate": 0.0002,
+      "loss": 1.6724,
+      "step": 2000
+    },
+    {
+      "epoch": 2.740286298568507,
+      "grad_norm": 0.5086126923561096,
+      "learning_rate": 0.0002,
+      "loss": 1.638,
+      "step": 2010
+    },
+    {
+      "epoch": 2.7539195637355145,
+      "grad_norm": 0.47242608666419983,
+      "learning_rate": 0.0002,
+      "loss": 1.6223,
+      "step": 2020
+    },
+    {
+      "epoch": 2.767552828902522,
+      "grad_norm": 0.44922566413879395,
+      "learning_rate": 0.0002,
+      "loss": 1.6242,
+      "step": 2030
+    },
+    {
+      "epoch": 2.78118609406953,
+      "grad_norm": 0.420259565114975,
+      "learning_rate": 0.0002,
+      "loss": 1.6837,
+      "step": 2040
+    },
+    {
+      "epoch": 2.794819359236537,
+      "grad_norm": 0.4762881100177765,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 2050
+    },
+    {
+      "epoch": 2.808452624403545,
+      "grad_norm": 0.5228786468505859,
+      "learning_rate": 0.0002,
+      "loss": 1.5506,
+      "step": 2060
+    },
+    {
+      "epoch": 2.8220858895705523,
+      "grad_norm": 0.4796035587787628,
+      "learning_rate": 0.0002,
+      "loss": 1.6347,
+      "step": 2070
+    },
+    {
+      "epoch": 2.8357191547375598,
+      "grad_norm": 0.5034735202789307,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 2080
+    },
+    {
+      "epoch": 2.8493524199045672,
+      "grad_norm": 0.48005399107933044,
+      "learning_rate": 0.0002,
+      "loss": 1.6455,
+      "step": 2090
+    },
+    {
+      "epoch": 2.8629856850715747,
+      "grad_norm": 0.578820526599884,
+      "learning_rate": 0.0002,
+      "loss": 1.6287,
+      "step": 2100
+    },
+    {
+      "epoch": 2.876618950238582,
+      "grad_norm": 0.48982638120651245,
+      "learning_rate": 0.0002,
+      "loss": 1.6021,
+      "step": 2110
+    },
+    {
+      "epoch": 2.8902522154055896,
+      "grad_norm": 0.5157325863838196,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 2120
+    },
+    {
+      "epoch": 2.903885480572597,
+      "grad_norm": 0.49149683117866516,
+      "learning_rate": 0.0002,
+      "loss": 1.6089,
+      "step": 2130
+    },
+    {
+      "epoch": 2.9175187457396046,
+      "grad_norm": 0.48584499955177307,
+      "learning_rate": 0.0002,
+      "loss": 1.5881,
+      "step": 2140
+    },
+    {
+      "epoch": 2.931152010906612,
+      "grad_norm": 0.5199017524719238,
+      "learning_rate": 0.0002,
+      "loss": 1.5833,
+      "step": 2150
+    },
+    {
+      "epoch": 2.9447852760736195,
+      "grad_norm": 0.5788236856460571,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 2160
+    },
+    {
+      "epoch": 2.958418541240627,
+      "grad_norm": 0.48664185404777527,
+      "learning_rate": 0.0002,
+      "loss": 1.6103,
+      "step": 2170
+    },
+    {
+      "epoch": 2.9720518064076344,
+      "grad_norm": 0.5026682615280151,
+      "learning_rate": 0.0002,
+      "loss": 1.5765,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9856850715746424,
+      "grad_norm": 0.49317044019699097,
+      "learning_rate": 0.0002,
+      "loss": 1.6626,
+      "step": 2190
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "grad_norm": 0.5729128122329712,
+      "learning_rate": 0.0002,
+      "loss": 1.5871,
+      "step": 2200
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "eval_loss": 1.8527295589447021,
+      "eval_runtime": 53.6403,
+      "eval_samples_per_second": 9.452,
+      "eval_steps_per_second": 1.193,
+      "step": 2200
+    },
+    {
+      "epoch": 3.0129516019086573,
+      "grad_norm": 0.5530241131782532,
+      "learning_rate": 0.0002,
+      "loss": 1.4719,
+      "step": 2210
+    },
+    {
+      "epoch": 3.0265848670756648,
+      "grad_norm": 0.6642216444015503,
+      "learning_rate": 0.0002,
+      "loss": 1.4088,
+      "step": 2220
+    },
+    {
+      "epoch": 3.0402181322426722,
+      "grad_norm": 0.61470627784729,
+      "learning_rate": 0.0002,
+      "loss": 1.4382,
+      "step": 2230
+    },
+    {
+      "epoch": 3.0538513974096797,
+      "grad_norm": 0.8559566140174866,
+      "learning_rate": 0.0002,
+      "loss": 1.4634,
+      "step": 2240
+    },
+    {
+      "epoch": 3.067484662576687,
+      "grad_norm": 0.7015801668167114,
+      "learning_rate": 0.0002,
+      "loss": 1.3854,
+      "step": 2250
+    },
+    {
+      "epoch": 3.0811179277436946,
+      "grad_norm": 0.7226442694664001,
+      "learning_rate": 0.0002,
+      "loss": 1.4981,
+      "step": 2260
+    },
+    {
+      "epoch": 3.094751192910702,
+      "grad_norm": 0.7560588717460632,
+      "learning_rate": 0.0002,
+      "loss": 1.4143,
+      "step": 2270
+    },
+    {
+      "epoch": 3.1083844580777096,
+      "grad_norm": 0.6216568946838379,
+      "learning_rate": 0.0002,
+      "loss": 1.4395,
+      "step": 2280
+    },
+    {
+      "epoch": 3.122017723244717,
+      "grad_norm": 0.6768500804901123,
+      "learning_rate": 0.0002,
+      "loss": 1.3842,
+      "step": 2290
+    },
+    {
+      "epoch": 3.1356509884117245,
+      "grad_norm": 0.7028762102127075,
+      "learning_rate": 0.0002,
+      "loss": 1.4672,
+      "step": 2300
+    },
+    {
+      "epoch": 3.149284253578732,
+      "grad_norm": 0.6329697966575623,
+      "learning_rate": 0.0002,
+      "loss": 1.3826,
+      "step": 2310
+    },
+    {
+      "epoch": 3.1629175187457395,
+      "grad_norm": 0.6328264474868774,
+      "learning_rate": 0.0002,
+      "loss": 1.442,
+      "step": 2320
+    },
+    {
+      "epoch": 3.176550783912747,
+      "grad_norm": 0.7573632001876831,
+      "learning_rate": 0.0002,
+      "loss": 1.3762,
+      "step": 2330
+    },
+    {
+      "epoch": 3.190184049079755,
+      "grad_norm": 0.595740795135498,
+      "learning_rate": 0.0002,
+      "loss": 1.3553,
+      "step": 2340
+    },
+    {
+      "epoch": 3.2038173142467623,
+      "grad_norm": 0.7111806869506836,
+      "learning_rate": 0.0002,
+      "loss": 1.3953,
+      "step": 2350
+    },
+    {
+      "epoch": 3.2174505794137698,
+      "grad_norm": 0.6328730583190918,
+      "learning_rate": 0.0002,
+      "loss": 1.3797,
+      "step": 2360
+    },
+    {
+      "epoch": 3.2310838445807772,
+      "grad_norm": 0.5860254168510437,
+      "learning_rate": 0.0002,
+      "loss": 1.3855,
+      "step": 2370
+    },
+    {
+      "epoch": 3.2447171097477847,
+      "grad_norm": 0.7387157082557678,
+      "learning_rate": 0.0002,
+      "loss": 1.4267,
+      "step": 2380
+    },
+    {
+      "epoch": 3.258350374914792,
+      "grad_norm": 0.6897673606872559,
+      "learning_rate": 0.0002,
+      "loss": 1.4837,
+      "step": 2390
+    },
+    {
+      "epoch": 3.2719836400817996,
+      "grad_norm": 0.7157699465751648,
+      "learning_rate": 0.0002,
+      "loss": 1.4372,
+      "step": 2400
+    },
+    {
+      "epoch": 3.285616905248807,
+      "grad_norm": 0.6422511339187622,
+      "learning_rate": 0.0002,
+      "loss": 1.4432,
+      "step": 2410
+    },
+    {
+      "epoch": 3.2992501704158146,
+      "grad_norm": 1.0481886863708496,
+      "learning_rate": 0.0002,
+      "loss": 1.4828,
+      "step": 2420
+    },
+    {
+      "epoch": 3.312883435582822,
+      "grad_norm": 0.7050786018371582,
+      "learning_rate": 0.0002,
+      "loss": 1.4473,
+      "step": 2430
+    },
+    {
+      "epoch": 3.3265167007498295,
+      "grad_norm": 0.6090759038925171,
+      "learning_rate": 0.0002,
+      "loss": 1.3465,
+      "step": 2440
+    },
+    {
+      "epoch": 3.340149965916837,
+      "grad_norm": 0.6626465320587158,
+      "learning_rate": 0.0002,
+      "loss": 1.4619,
+      "step": 2450
+    },
+    {
+      "epoch": 3.3537832310838445,
+      "grad_norm": 0.6565486788749695,
+      "learning_rate": 0.0002,
+      "loss": 1.4512,
+      "step": 2460
+    },
+    {
+      "epoch": 3.367416496250852,
+      "grad_norm": 0.6449528932571411,
+      "learning_rate": 0.0002,
+      "loss": 1.588,
+      "step": 2470
+    },
+    {
+      "epoch": 3.3810497614178594,
+      "grad_norm": 0.7746227383613586,
+      "learning_rate": 0.0002,
+      "loss": 1.4773,
+      "step": 2480
+    },
+    {
+      "epoch": 3.3946830265848673,
+      "grad_norm": 0.7074846029281616,
+      "learning_rate": 0.0002,
+      "loss": 1.417,
+      "step": 2490
+    },
+    {
+      "epoch": 3.4083162917518743,
+      "grad_norm": 0.6547690033912659,
+      "learning_rate": 0.0002,
+      "loss": 1.4476,
+      "step": 2500
+    },
+    {
+      "epoch": 3.4219495569188823,
+      "grad_norm": 0.784721314907074,
+      "learning_rate": 0.0002,
+      "loss": 1.4074,
+      "step": 2510
+    },
+    {
+      "epoch": 3.4355828220858897,
+      "grad_norm": 0.7270277738571167,
+      "learning_rate": 0.0002,
+      "loss": 1.4326,
+      "step": 2520
+    },
+    {
+      "epoch": 3.449216087252897,
+      "grad_norm": 0.67588871717453,
+      "learning_rate": 0.0002,
+      "loss": 1.4354,
+      "step": 2530
+    },
+    {
+      "epoch": 3.4628493524199047,
+      "grad_norm": 0.6768023371696472,
+      "learning_rate": 0.0002,
+      "loss": 1.4074,
+      "step": 2540
+    },
+    {
+      "epoch": 3.476482617586912,
+      "grad_norm": 0.7026481628417969,
+      "learning_rate": 0.0002,
+      "loss": 1.4863,
+      "step": 2550
+    },
+    {
+      "epoch": 3.4901158827539196,
+      "grad_norm": 0.646075963973999,
+      "learning_rate": 0.0002,
+      "loss": 1.468,
+      "step": 2560
+    },
+    {
+      "epoch": 3.503749147920927,
+      "grad_norm": 0.6288973689079285,
+      "learning_rate": 0.0002,
+      "loss": 1.4058,
+      "step": 2570
+    },
+    {
+      "epoch": 3.5173824130879345,
+      "grad_norm": 0.6440825462341309,
+      "learning_rate": 0.0002,
+      "loss": 1.4613,
+      "step": 2580
+    },
+    {
+      "epoch": 3.531015678254942,
+      "grad_norm": 0.7074111700057983,
+      "learning_rate": 0.0002,
+      "loss": 1.3808,
+      "step": 2590
+    },
+    {
+      "epoch": 3.5446489434219495,
+      "grad_norm": 0.7007562518119812,
+      "learning_rate": 0.0002,
+      "loss": 1.4901,
+      "step": 2600
+    },
+    {
+      "epoch": 3.558282208588957,
+      "grad_norm": 0.6045376658439636,
+      "learning_rate": 0.0002,
+      "loss": 1.4511,
+      "step": 2610
+    },
+    {
+      "epoch": 3.5719154737559644,
+      "grad_norm": 0.9149952530860901,
+      "learning_rate": 0.0002,
+      "loss": 1.4596,
+      "step": 2620
+    },
+    {
+      "epoch": 3.585548738922972,
+      "grad_norm": 0.6490362882614136,
+      "learning_rate": 0.0002,
+      "loss": 1.4355,
+      "step": 2630
+    },
+    {
+      "epoch": 3.59918200408998,
+      "grad_norm": 0.6552226543426514,
+      "learning_rate": 0.0002,
+      "loss": 1.4107,
+      "step": 2640
+    },
+    {
+      "epoch": 3.612815269256987,
+      "grad_norm": 0.6541850566864014,
+      "learning_rate": 0.0002,
+      "loss": 1.433,
+      "step": 2650
+    },
+    {
+      "epoch": 3.6264485344239947,
+      "grad_norm": 0.6500770449638367,
+      "learning_rate": 0.0002,
+      "loss": 1.4279,
+      "step": 2660
+    },
+    {
+      "epoch": 3.640081799591002,
+      "grad_norm": 0.6345893740653992,
+      "learning_rate": 0.0002,
+      "loss": 1.3929,
+      "step": 2670
+    },
+    {
+      "epoch": 3.6537150647580097,
+      "grad_norm": 0.6382275223731995,
+      "learning_rate": 0.0002,
+      "loss": 1.3634,
+      "step": 2680
+    },
+    {
+      "epoch": 3.667348329925017,
+      "grad_norm": 0.6738566160202026,
+      "learning_rate": 0.0002,
+      "loss": 1.4478,
+      "step": 2690
+    },
+    {
+      "epoch": 3.6809815950920246,
+      "grad_norm": 0.7446315288543701,
+      "learning_rate": 0.0002,
+      "loss": 1.4642,
+      "step": 2700
+    },
+    {
+      "epoch": 3.694614860259032,
+      "grad_norm": 0.6717571020126343,
+      "learning_rate": 0.0002,
+      "loss": 1.4342,
+      "step": 2710
+    },
+    {
+      "epoch": 3.7082481254260395,
+      "grad_norm": 0.667259693145752,
+      "learning_rate": 0.0002,
+      "loss": 1.4285,
+      "step": 2720
+    },
+    {
+      "epoch": 3.721881390593047,
+      "grad_norm": 0.6808622479438782,
+      "learning_rate": 0.0002,
+      "loss": 1.5389,
+      "step": 2730
+    },
+    {
+      "epoch": 3.7355146557600545,
+      "grad_norm": 0.7254287004470825,
+      "learning_rate": 0.0002,
+      "loss": 1.4297,
+      "step": 2740
+    },
+    {
+      "epoch": 3.749147920927062,
+      "grad_norm": 0.6864007711410522,
+      "learning_rate": 0.0002,
+      "loss": 1.4176,
+      "step": 2750
+    },
+    {
+      "epoch": 3.7627811860940694,
+      "grad_norm": 0.7041361331939697,
+      "learning_rate": 0.0002,
+      "loss": 1.4811,
+      "step": 2760
+    },
+    {
+      "epoch": 3.776414451261077,
+      "grad_norm": 0.6559903025627136,
+      "learning_rate": 0.0002,
+      "loss": 1.4284,
+      "step": 2770
+    },
+    {
+      "epoch": 3.7900477164280844,
+      "grad_norm": 0.6602269411087036,
+      "learning_rate": 0.0002,
+      "loss": 1.4608,
+      "step": 2780
+    },
+    {
+      "epoch": 3.8036809815950923,
+      "grad_norm": 0.692611813545227,
+      "learning_rate": 0.0002,
+      "loss": 1.4588,
+      "step": 2790
+    },
+    {
+      "epoch": 3.8173142467620993,
+      "grad_norm": 0.7051475644111633,
+      "learning_rate": 0.0002,
+      "loss": 1.4065,
+      "step": 2800
+    },
+    {
+      "epoch": 3.830947511929107,
+      "grad_norm": 0.6685371398925781,
+      "learning_rate": 0.0002,
+      "loss": 1.4083,
+      "step": 2810
+    },
+    {
+      "epoch": 3.8445807770961147,
+      "grad_norm": 0.6706477403640747,
+      "learning_rate": 0.0002,
+      "loss": 1.5227,
+      "step": 2820
+    },
+    {
+      "epoch": 3.858214042263122,
+      "grad_norm": 0.6671637296676636,
+      "learning_rate": 0.0002,
+      "loss": 1.4076,
+      "step": 2830
+    },
+    {
+      "epoch": 3.8718473074301296,
+      "grad_norm": 0.694092333316803,
+      "learning_rate": 0.0002,
+      "loss": 1.4736,
+      "step": 2840
+    },
+    {
+      "epoch": 3.885480572597137,
+      "grad_norm": 0.7349600195884705,
+      "learning_rate": 0.0002,
+      "loss": 1.4161,
+      "step": 2850
+    },
+    {
+      "epoch": 3.8991138377641446,
+      "grad_norm": 0.6647971868515015,
+      "learning_rate": 0.0002,
+      "loss": 1.4617,
+      "step": 2860
+    },
+    {
+      "epoch": 3.912747102931152,
+      "grad_norm": 0.806656539440155,
+      "learning_rate": 0.0002,
+      "loss": 1.5046,
+      "step": 2870
+    },
+    {
+      "epoch": 3.9263803680981595,
+      "grad_norm": 0.6008772850036621,
+      "learning_rate": 0.0002,
+      "loss": 1.428,
+      "step": 2880
+    },
+    {
+      "epoch": 3.940013633265167,
+      "grad_norm": 0.659227728843689,
+      "learning_rate": 0.0002,
+      "loss": 1.4116,
+      "step": 2890
+    },
+    {
+      "epoch": 3.9536468984321744,
+      "grad_norm": 0.6357656717300415,
+      "learning_rate": 0.0002,
+      "loss": 1.4136,
+      "step": 2900
+    },
+    {
+      "epoch": 3.967280163599182,
+      "grad_norm": 0.6541687846183777,
+      "learning_rate": 0.0002,
+      "loss": 1.4655,
+      "step": 2910
+    },
+    {
+      "epoch": 3.9809134287661894,
+      "grad_norm": 0.6090909838676453,
+      "learning_rate": 0.0002,
+      "loss": 1.4854,
+      "step": 2920
+    },
+    {
+      "epoch": 3.994546693933197,
+      "grad_norm": 0.7198411822319031,
+      "learning_rate": 0.0002,
+      "loss": 1.4615,
+      "step": 2930
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.9278366565704346,
+      "eval_runtime": 53.6567,
+      "eval_samples_per_second": 9.449,
+      "eval_steps_per_second": 1.193,
+      "step": 2934
+    },
+    {
+      "epoch": 4.008179959100205,
+      "grad_norm": 0.6498575210571289,
+      "learning_rate": 0.0002,
+      "loss": 1.3159,
+      "step": 2940
+    },
+    {
+      "epoch": 4.021813224267212,
+      "grad_norm": 0.865602433681488,
+      "learning_rate": 0.0002,
+      "loss": 1.2075,
+      "step": 2950
+    },
+    {
+      "epoch": 4.03544648943422,
+      "grad_norm": 0.8514999151229858,
+      "learning_rate": 0.0002,
+      "loss": 1.1744,
+      "step": 2960
+    },
+    {
+      "epoch": 4.049079754601227,
+      "grad_norm": 1.0677322149276733,
+      "learning_rate": 0.0002,
+      "loss": 1.1553,
+      "step": 2970
+    },
+    {
+      "epoch": 4.062713019768235,
+      "grad_norm": 1.0126488208770752,
+      "learning_rate": 0.0002,
+      "loss": 1.1962,
+      "step": 2980
+    },
+    {
+      "epoch": 4.076346284935242,
+      "grad_norm": 1.0008870363235474,
+      "learning_rate": 0.0002,
+      "loss": 1.1631,
+      "step": 2990
+    },
+    {
+      "epoch": 4.08997955010225,
+      "grad_norm": 0.7942054271697998,
+      "learning_rate": 0.0002,
+      "loss": 1.2154,
+      "step": 3000
+    },
+    {
+      "epoch": 4.103612815269257,
+      "grad_norm": 1.0482100248336792,
+      "learning_rate": 0.0002,
+      "loss": 1.214,
+      "step": 3010
+    },
+    {
+      "epoch": 4.1172460804362645,
+      "grad_norm": 1.0516992807388306,
+      "learning_rate": 0.0002,
+      "loss": 1.1999,
+      "step": 3020
+    },
+    {
+      "epoch": 4.130879345603272,
+      "grad_norm": 0.8144322037696838,
+      "learning_rate": 0.0002,
+      "loss": 1.2108,
+      "step": 3030
+    },
+    {
+      "epoch": 4.144512610770279,
+      "grad_norm": 0.952297568321228,
+      "learning_rate": 0.0002,
+      "loss": 1.1782,
+      "step": 3040
+    },
+    {
+      "epoch": 4.158145875937287,
+      "grad_norm": 1.007645606994629,
+      "learning_rate": 0.0002,
+      "loss": 1.2814,
+      "step": 3050
+    },
+    {
+      "epoch": 4.171779141104294,
+      "grad_norm": 1.0480353832244873,
+      "learning_rate": 0.0002,
+      "loss": 1.1731,
+      "step": 3060
+    },
+    {
+      "epoch": 4.185412406271302,
+      "grad_norm": 0.9270663857460022,
+      "learning_rate": 0.0002,
+      "loss": 1.196,
+      "step": 3070
+    },
+    {
+      "epoch": 4.199045671438309,
+      "grad_norm": 1.3415262699127197,
+      "learning_rate": 0.0002,
+      "loss": 1.2167,
+      "step": 3080
+    },
+    {
+      "epoch": 4.212678936605317,
+      "grad_norm": 1.167606234550476,
+      "learning_rate": 0.0002,
+      "loss": 1.2601,
+      "step": 3090
+    },
+    {
+      "epoch": 4.226312201772324,
+      "grad_norm": 0.9418690800666809,
+      "learning_rate": 0.0002,
+      "loss": 1.2605,
+      "step": 3100
+    },
+    {
+      "epoch": 4.239945466939332,
+      "grad_norm": 1.0885876417160034,
+      "learning_rate": 0.0002,
+      "loss": 1.2184,
+      "step": 3110
+    },
+    {
+      "epoch": 4.253578732106339,
+      "grad_norm": 0.9165483713150024,
+      "learning_rate": 0.0002,
+      "loss": 1.2594,
+      "step": 3120
+    },
+    {
+      "epoch": 4.267211997273347,
+      "grad_norm": 0.9154694080352783,
+      "learning_rate": 0.0002,
+      "loss": 1.2933,
+      "step": 3130
+    },
+    {
+      "epoch": 4.280845262440354,
+      "grad_norm": 1.100580096244812,
+      "learning_rate": 0.0002,
+      "loss": 1.2584,
+      "step": 3140
+    },
+    {
+      "epoch": 4.294478527607362,
+      "grad_norm": 0.9367576241493225,
+      "learning_rate": 0.0002,
+      "loss": 1.251,
+      "step": 3150
+    },
+    {
+      "epoch": 4.308111792774369,
+      "grad_norm": 0.9744015336036682,
+      "learning_rate": 0.0002,
+      "loss": 1.2032,
+      "step": 3160
+    },
+    {
+      "epoch": 4.321745057941377,
+      "grad_norm": 0.9865175485610962,
+      "learning_rate": 0.0002,
+      "loss": 1.2787,
+      "step": 3170
+    },
+    {
+      "epoch": 4.335378323108385,
+      "grad_norm": 1.0124907493591309,
+      "learning_rate": 0.0002,
+      "loss": 1.2161,
+      "step": 3180
+    },
+    {
+      "epoch": 4.349011588275392,
+      "grad_norm": 1.1044819355010986,
+      "learning_rate": 0.0002,
+      "loss": 1.2452,
+      "step": 3190
+    },
+    {
+      "epoch": 4.3626448534424,
+      "grad_norm": 0.9305577278137207,
+      "learning_rate": 0.0002,
+      "loss": 1.2483,
+      "step": 3200
+    },
+    {
+      "epoch": 4.376278118609407,
+      "grad_norm": 0.969265341758728,
+      "learning_rate": 0.0002,
+      "loss": 1.2101,
+      "step": 3210
+    },
+    {
+      "epoch": 4.389911383776415,
+      "grad_norm": 1.0671923160552979,
+      "learning_rate": 0.0002,
+      "loss": 1.2355,
+      "step": 3220
+    },
+    {
+      "epoch": 4.403544648943422,
+      "grad_norm": 0.9440539479255676,
+      "learning_rate": 0.0002,
+      "loss": 1.2259,
+      "step": 3230
+    },
+    {
+      "epoch": 4.41717791411043,
+      "grad_norm": 0.9824562668800354,
+      "learning_rate": 0.0002,
+      "loss": 1.1706,
+      "step": 3240
+    },
+    {
+      "epoch": 4.430811179277437,
+      "grad_norm": 1.0245535373687744,
+      "learning_rate": 0.0002,
+      "loss": 1.2234,
+      "step": 3250
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.9629312753677368,
+      "learning_rate": 0.0002,
+      "loss": 1.2713,
+      "step": 3260
+    },
+    {
+      "epoch": 4.458077709611452,
+      "grad_norm": 1.1556470394134521,
+      "learning_rate": 0.0002,
+      "loss": 1.2689,
+      "step": 3270
+    },
+    {
+      "epoch": 4.47171097477846,
+      "grad_norm": 0.9796679019927979,
+      "learning_rate": 0.0002,
+      "loss": 1.2214,
+      "step": 3280
+    },
+    {
+      "epoch": 4.485344239945467,
+      "grad_norm": 0.9030535221099854,
+      "learning_rate": 0.0002,
+      "loss": 1.2823,
+      "step": 3290
+    },
+    {
+      "epoch": 4.4989775051124745,
+      "grad_norm": 0.9142820835113525,
+      "learning_rate": 0.0002,
+      "loss": 1.2111,
+      "step": 3300
+    },
+    {
+      "epoch": 4.5126107702794815,
+      "grad_norm": 0.966867208480835,
+      "learning_rate": 0.0002,
+      "loss": 1.2398,
+      "step": 3310
+    },
+    {
+      "epoch": 4.5262440354464895,
+      "grad_norm": 1.0127079486846924,
+      "learning_rate": 0.0002,
+      "loss": 1.2537,
+      "step": 3320
+    },
+    {
+      "epoch": 4.539877300613497,
+      "grad_norm": 1.055506706237793,
+      "learning_rate": 0.0002,
+      "loss": 1.2059,
+      "step": 3330
+    },
+    {
+      "epoch": 4.553510565780504,
+      "grad_norm": 0.9831468462944031,
+      "learning_rate": 0.0002,
+      "loss": 1.2958,
+      "step": 3340
+    },
+    {
+      "epoch": 4.567143830947512,
+      "grad_norm": 0.9304661154747009,
+      "learning_rate": 0.0002,
+      "loss": 1.2643,
+      "step": 3350
+    },
+    {
+      "epoch": 4.580777096114519,
+      "grad_norm": 0.9369107484817505,
+      "learning_rate": 0.0002,
+      "loss": 1.3621,
+      "step": 3360
+    },
+    {
+      "epoch": 4.594410361281527,
+      "grad_norm": 1.009506344795227,
+      "learning_rate": 0.0002,
+      "loss": 1.2301,
+      "step": 3370
+    },
+    {
+      "epoch": 4.608043626448534,
+      "grad_norm": 1.0575741529464722,
+      "learning_rate": 0.0002,
+      "loss": 1.2535,
+      "step": 3380
+    },
+    {
+      "epoch": 4.621676891615542,
+      "grad_norm": 0.9102860689163208,
+      "learning_rate": 0.0002,
+      "loss": 1.1914,
+      "step": 3390
+    },
+    {
+      "epoch": 4.635310156782549,
+      "grad_norm": 0.8111315965652466,
+      "learning_rate": 0.0002,
+      "loss": 1.3156,
+      "step": 3400
+    },
+    {
+      "epoch": 4.648943421949557,
+      "grad_norm": 0.9459649920463562,
+      "learning_rate": 0.0002,
+      "loss": 1.3103,
+      "step": 3410
+    },
+    {
+      "epoch": 4.662576687116564,
+      "grad_norm": 0.9709545969963074,
+      "learning_rate": 0.0002,
+      "loss": 1.3146,
+      "step": 3420
+    },
+    {
+      "epoch": 4.676209952283572,
+      "grad_norm": 0.9909247159957886,
+      "learning_rate": 0.0002,
+      "loss": 1.2958,
+      "step": 3430
+    },
+    {
+      "epoch": 4.689843217450579,
+      "grad_norm": 0.9094610810279846,
+      "learning_rate": 0.0002,
+      "loss": 1.3186,
+      "step": 3440
+    },
+    {
+      "epoch": 4.703476482617587,
+      "grad_norm": 0.9012220501899719,
+      "learning_rate": 0.0002,
+      "loss": 1.3397,
+      "step": 3450
+    },
+    {
+      "epoch": 4.717109747784594,
+      "grad_norm": 0.8669242858886719,
+      "learning_rate": 0.0002,
+      "loss": 1.2595,
+      "step": 3460
+    },
+    {
+      "epoch": 4.730743012951602,
+      "grad_norm": 0.9753699898719788,
+      "learning_rate": 0.0002,
+      "loss": 1.2762,
+      "step": 3470
+    },
+    {
+      "epoch": 4.74437627811861,
+      "grad_norm": 1.0252684354782104,
+      "learning_rate": 0.0002,
+      "loss": 1.2371,
+      "step": 3480
+    },
+    {
+      "epoch": 4.758009543285617,
+      "grad_norm": 1.208098292350769,
+      "learning_rate": 0.0002,
+      "loss": 1.2536,
+      "step": 3490
+    },
+    {
+      "epoch": 4.771642808452625,
+      "grad_norm": 0.8632914423942566,
+      "learning_rate": 0.0002,
+      "loss": 1.2256,
+      "step": 3500
+    },
+    {
+      "epoch": 4.785276073619632,
+      "grad_norm": 1.0084818601608276,
+      "learning_rate": 0.0002,
+      "loss": 1.3062,
+      "step": 3510
+    },
+    {
+      "epoch": 4.79890933878664,
+      "grad_norm": 0.9095172882080078,
+      "learning_rate": 0.0002,
+      "loss": 1.3004,
+      "step": 3520
+    },
+    {
+      "epoch": 4.812542603953647,
+      "grad_norm": 0.9740135669708252,
+      "learning_rate": 0.0002,
+      "loss": 1.263,
+      "step": 3530
+    },
+    {
+      "epoch": 4.826175869120655,
+      "grad_norm": 0.8862348794937134,
+      "learning_rate": 0.0002,
+      "loss": 1.2816,
+      "step": 3540
+    },
+    {
+      "epoch": 4.839809134287662,
+      "grad_norm": 1.0761774778366089,
+      "learning_rate": 0.0002,
+      "loss": 1.2275,
+      "step": 3550
+    },
+    {
+      "epoch": 4.85344239945467,
+      "grad_norm": 1.0134117603302002,
+      "learning_rate": 0.0002,
+      "loss": 1.2257,
+      "step": 3560
+    },
+    {
+      "epoch": 4.867075664621677,
+      "grad_norm": 0.9262851476669312,
+      "learning_rate": 0.0002,
+      "loss": 1.2904,
+      "step": 3570
+    },
+    {
+      "epoch": 4.8807089297886845,
+      "grad_norm": 0.9518504738807678,
+      "learning_rate": 0.0002,
+      "loss": 1.1466,
+      "step": 3580
+    },
+    {
+      "epoch": 4.894342194955692,
+      "grad_norm": 1.10103178024292,
+      "learning_rate": 0.0002,
+      "loss": 1.2741,
+      "step": 3590
+    },
+    {
+      "epoch": 4.9079754601226995,
+      "grad_norm": 1.0133225917816162,
+      "learning_rate": 0.0002,
+      "loss": 1.2592,
+      "step": 3600
+    },
+    {
+      "epoch": 4.9216087252897065,
+      "grad_norm": 0.9637737274169922,
+      "learning_rate": 0.0002,
+      "loss": 1.2856,
+      "step": 3610
+    },
+    {
+      "epoch": 4.935241990456714,
+      "grad_norm": 0.9800633192062378,
+      "learning_rate": 0.0002,
+      "loss": 1.2991,
+      "step": 3620
+    },
+    {
+      "epoch": 4.948875255623722,
+      "grad_norm": 1.0065973997116089,
+      "learning_rate": 0.0002,
+      "loss": 1.2872,
+      "step": 3630
+    },
+    {
+      "epoch": 4.962508520790729,
+      "grad_norm": 0.9354690313339233,
+      "learning_rate": 0.0002,
+      "loss": 1.2408,
+      "step": 3640
+    },
+    {
+      "epoch": 4.976141785957737,
+      "grad_norm": 0.9744119048118591,
+      "learning_rate": 0.0002,
+      "loss": 1.291,
+      "step": 3650
+    },
+    {
+      "epoch": 4.989775051124744,
+      "grad_norm": 0.9357708096504211,
+      "learning_rate": 0.0002,
+      "loss": 1.2513,
+      "step": 3660
+    },
+    {
+      "epoch": 4.999318336741649,
+      "eval_loss": 2.0763096809387207,
+      "eval_runtime": 53.6578,
+      "eval_samples_per_second": 9.449,
+      "eval_steps_per_second": 1.193,
+      "step": 3667
+    },
+    {
+      "epoch": 5.003408316291752,
+      "grad_norm": 1.3171669244766235,
+      "learning_rate": 0.0002,
+      "loss": 1.2323,
+      "step": 3670
+    },
+    {
+      "epoch": 5.017041581458759,
+      "grad_norm": 1.4427374601364136,
+      "learning_rate": 0.0002,
+      "loss": 0.9509,
+      "step": 3680
+    },
+    {
+      "epoch": 5.030674846625767,
+      "grad_norm": 0.9313797354698181,
+      "learning_rate": 0.0002,
+      "loss": 1.011,
+      "step": 3690
+    },
+    {
+      "epoch": 5.044308111792774,
+      "grad_norm": 1.417641282081604,
+      "learning_rate": 0.0002,
+      "loss": 0.9481,
+      "step": 3700
+    },
+    {
+      "epoch": 5.057941376959782,
+      "grad_norm": 1.097440242767334,
+      "learning_rate": 0.0002,
+      "loss": 0.9477,
+      "step": 3710
+    },
+    {
+      "epoch": 5.071574642126789,
+      "grad_norm": 1.4277986288070679,
+      "learning_rate": 0.0002,
+      "loss": 1.0416,
+      "step": 3720
+    },
+    {
+      "epoch": 5.085207907293797,
+      "grad_norm": 1.2520873546600342,
+      "learning_rate": 0.0002,
+      "loss": 0.9718,
+      "step": 3730
+    },
+    {
+      "epoch": 5.098841172460804,
+      "grad_norm": 1.39503812789917,
+      "learning_rate": 0.0002,
+      "loss": 0.9531,
+      "step": 3740
+    },
+    {
+      "epoch": 5.112474437627812,
+      "grad_norm": 1.2345329523086548,
+      "learning_rate": 0.0002,
+      "loss": 0.9658,
+      "step": 3750
+    },
+    {
+      "epoch": 5.126107702794819,
+      "grad_norm": 1.2700239419937134,
+      "learning_rate": 0.0002,
+      "loss": 1.0615,
+      "step": 3760
+    },
+    {
+      "epoch": 5.139740967961827,
+      "grad_norm": 1.5343066453933716,
+      "learning_rate": 0.0002,
+      "loss": 0.993,
+      "step": 3770
+    },
+    {
+      "epoch": 5.153374233128835,
+      "grad_norm": 1.4191608428955078,
+      "learning_rate": 0.0002,
+      "loss": 0.9378,
+      "step": 3780
+    },
+    {
+      "epoch": 5.167007498295842,
+      "grad_norm": 1.4591023921966553,
+      "learning_rate": 0.0002,
+      "loss": 1.0179,
+      "step": 3790
+    },
+    {
+      "epoch": 5.18064076346285,
+      "grad_norm": 1.6158121824264526,
+      "learning_rate": 0.0002,
+      "loss": 1.0143,
+      "step": 3800
+    },
+    {
+      "epoch": 5.194274028629857,
+      "grad_norm": 1.6077582836151123,
+      "learning_rate": 0.0002,
+      "loss": 1.0056,
+      "step": 3810
+    },
+    {
+      "epoch": 5.207907293796865,
+      "grad_norm": 1.2815653085708618,
+      "learning_rate": 0.0002,
+      "loss": 0.9711,
+      "step": 3820
+    },
+    {
+      "epoch": 5.221540558963872,
+      "grad_norm": 1.2427219152450562,
+      "learning_rate": 0.0002,
+      "loss": 1.0131,
+      "step": 3830
+    },
+    {
+      "epoch": 5.23517382413088,
+      "grad_norm": 1.3013232946395874,
+      "learning_rate": 0.0002,
+      "loss": 0.9901,
+      "step": 3840
+    },
+    {
+      "epoch": 5.248807089297887,
+      "grad_norm": 1.4643588066101074,
+      "learning_rate": 0.0002,
+      "loss": 0.9862,
+      "step": 3850
+    },
+    {
+      "epoch": 5.2624403544648946,
+      "grad_norm": 1.2571916580200195,
+      "learning_rate": 0.0002,
+      "loss": 1.0149,
+      "step": 3860
+    },
+    {
+      "epoch": 5.276073619631902,
+      "grad_norm": 1.226682186126709,
+      "learning_rate": 0.0002,
+      "loss": 0.9686,
+      "step": 3870
+    },
+    {
+      "epoch": 5.2897068847989095,
+      "grad_norm": 1.2541271448135376,
+      "learning_rate": 0.0002,
+      "loss": 0.9417,
+      "step": 3880
+    },
+    {
+      "epoch": 5.3033401499659165,
+      "grad_norm": 1.2340261936187744,
+      "learning_rate": 0.0002,
+      "loss": 0.9767,
+      "step": 3890
+    },
+    {
+      "epoch": 5.316973415132924,
+      "grad_norm": 1.345527172088623,
+      "learning_rate": 0.0002,
+      "loss": 1.0173,
+      "step": 3900
+    },
+    {
+      "epoch": 5.3306066802999315,
+      "grad_norm": 1.2128909826278687,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 3910
+    },
+    {
+      "epoch": 5.344239945466939,
+      "grad_norm": 1.3052637577056885,
+      "learning_rate": 0.0002,
+      "loss": 1.0002,
+      "step": 3920
+    },
+    {
+      "epoch": 5.357873210633947,
+      "grad_norm": 1.1017392873764038,
+      "learning_rate": 0.0002,
+      "loss": 0.9754,
+      "step": 3930
+    },
+    {
+      "epoch": 5.371506475800954,
+      "grad_norm": 1.26950204372406,
+      "learning_rate": 0.0002,
+      "loss": 1.0579,
+      "step": 3940
+    },
+    {
+      "epoch": 5.385139740967962,
+      "grad_norm": 1.3372546434402466,
+      "learning_rate": 0.0002,
+      "loss": 1.0816,
+      "step": 3950
+    },
+    {
+      "epoch": 5.398773006134969,
+      "grad_norm": 1.3115156888961792,
+      "learning_rate": 0.0002,
+      "loss": 1.0529,
+      "step": 3960
+    },
+    {
+      "epoch": 5.412406271301977,
+      "grad_norm": 1.3511474132537842,
+      "learning_rate": 0.0002,
+      "loss": 1.1179,
+      "step": 3970
+    },
+    {
+      "epoch": 5.426039536468984,
+      "grad_norm": 1.1001893281936646,
+      "learning_rate": 0.0002,
+      "loss": 1.0352,
+      "step": 3980
+    },
+    {
+      "epoch": 5.439672801635992,
+      "grad_norm": 1.2810745239257812,
+      "learning_rate": 0.0002,
+      "loss": 1.0855,
+      "step": 3990
+    },
+    {
+      "epoch": 5.453306066802999,
+      "grad_norm": 1.2999306917190552,
+      "learning_rate": 0.0002,
+      "loss": 1.0573,
+      "step": 4000
+    },
+    {
+      "epoch": 5.466939331970007,
+      "grad_norm": 1.172553300857544,
+      "learning_rate": 0.0002,
+      "loss": 1.0073,
+      "step": 4010
+    },
+    {
+      "epoch": 5.480572597137014,
+      "grad_norm": 1.1483557224273682,
+      "learning_rate": 0.0002,
+      "loss": 1.003,
+      "step": 4020
+    },
+    {
+      "epoch": 5.494205862304022,
+      "grad_norm": 1.4148036241531372,
+      "learning_rate": 0.0002,
+      "loss": 1.0704,
+      "step": 4030
+    },
+    {
+      "epoch": 5.507839127471029,
+      "grad_norm": 1.1611121892929077,
+      "learning_rate": 0.0002,
+      "loss": 1.0519,
+      "step": 4040
+    },
+    {
+      "epoch": 5.521472392638037,
+      "grad_norm": 1.3837119340896606,
+      "learning_rate": 0.0002,
+      "loss": 1.0775,
+      "step": 4050
+    },
+    {
+      "epoch": 5.535105657805044,
+      "grad_norm": 1.3025696277618408,
+      "learning_rate": 0.0002,
+      "loss": 1.0257,
+      "step": 4060
+    },
+    {
+      "epoch": 5.548738922972052,
+      "grad_norm": 1.348091959953308,
+      "learning_rate": 0.0002,
+      "loss": 1.0628,
+      "step": 4070
+    },
+    {
+      "epoch": 5.56237218813906,
+      "grad_norm": 1.3463449478149414,
+      "learning_rate": 0.0002,
+      "loss": 1.0447,
+      "step": 4080
+    },
+    {
+      "epoch": 5.576005453306067,
+      "grad_norm": 1.3904176950454712,
+      "learning_rate": 0.0002,
+      "loss": 1.039,
+      "step": 4090
+    },
+    {
+      "epoch": 5.589638718473074,
+      "grad_norm": 1.2737950086593628,
+      "learning_rate": 0.0002,
+      "loss": 1.0963,
+      "step": 4100
+    },
+    {
+      "epoch": 5.603271983640082,
+      "grad_norm": 1.3311827182769775,
+      "learning_rate": 0.0002,
+      "loss": 1.0441,
+      "step": 4110
+    },
+    {
+      "epoch": 5.61690524880709,
+      "grad_norm": 1.24485182762146,
+      "learning_rate": 0.0002,
+      "loss": 1.0521,
+      "step": 4120
+    },
+    {
+      "epoch": 5.630538513974097,
+      "grad_norm": 1.2724957466125488,
+      "learning_rate": 0.0002,
+      "loss": 1.1103,
+      "step": 4130
+    },
+    {
+      "epoch": 5.644171779141105,
+      "grad_norm": 1.3439847230911255,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 4140
+    },
+    {
+      "epoch": 5.657805044308112,
+      "grad_norm": 1.372359037399292,
+      "learning_rate": 0.0002,
+      "loss": 1.0257,
+      "step": 4150
+    },
+    {
+      "epoch": 5.6714383094751195,
+      "grad_norm": 1.2322949171066284,
+      "learning_rate": 0.0002,
+      "loss": 1.0475,
+      "step": 4160
+    },
+    {
+      "epoch": 5.6850715746421265,
+      "grad_norm": 1.4859193563461304,
+      "learning_rate": 0.0002,
+      "loss": 1.0465,
+      "step": 4170
+    },
+    {
+      "epoch": 5.6987048398091344,
+      "grad_norm": 1.4318448305130005,
+      "learning_rate": 0.0002,
+      "loss": 1.1569,
+      "step": 4180
+    },
+    {
+      "epoch": 5.7123381049761415,
+      "grad_norm": 1.1533565521240234,
+      "learning_rate": 0.0002,
+      "loss": 1.017,
+      "step": 4190
+    },
+    {
+      "epoch": 5.725971370143149,
+      "grad_norm": 1.3009696006774902,
+      "learning_rate": 0.0002,
+      "loss": 1.0948,
+      "step": 4200
+    },
+    {
+      "epoch": 5.739604635310156,
+      "grad_norm": 1.3972162008285522,
+      "learning_rate": 0.0002,
+      "loss": 1.1229,
+      "step": 4210
+    },
+    {
+      "epoch": 5.753237900477164,
+      "grad_norm": 1.2142186164855957,
+      "learning_rate": 0.0002,
+      "loss": 1.033,
+      "step": 4220
+    },
+    {
+      "epoch": 5.766871165644172,
+      "grad_norm": 1.401191234588623,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 4230
+    },
+    {
+      "epoch": 5.780504430811179,
+      "grad_norm": 1.4124404191970825,
+      "learning_rate": 0.0002,
+      "loss": 1.0722,
+      "step": 4240
+    },
+    {
+      "epoch": 5.794137695978186,
+      "grad_norm": 1.3488332033157349,
+      "learning_rate": 0.0002,
+      "loss": 1.0826,
+      "step": 4250
+    },
+    {
+      "epoch": 5.807770961145194,
+      "grad_norm": 1.3671752214431763,
+      "learning_rate": 0.0002,
+      "loss": 1.0599,
+      "step": 4260
+    },
+    {
+      "epoch": 5.821404226312202,
+      "grad_norm": 1.2608201503753662,
+      "learning_rate": 0.0002,
+      "loss": 1.1294,
+      "step": 4270
+    },
+    {
+      "epoch": 5.835037491479209,
+      "grad_norm": 1.1814045906066895,
+      "learning_rate": 0.0002,
+      "loss": 1.1216,
+      "step": 4280
+    },
+    {
+      "epoch": 5.848670756646217,
+      "grad_norm": 1.4139586687088013,
+      "learning_rate": 0.0002,
+      "loss": 1.0973,
+      "step": 4290
+    },
+    {
+      "epoch": 5.862304021813224,
+      "grad_norm": 1.34248948097229,
+      "learning_rate": 0.0002,
+      "loss": 1.0656,
+      "step": 4300
+    },
+    {
+      "epoch": 5.875937286980232,
+      "grad_norm": 1.1428139209747314,
+      "learning_rate": 0.0002,
+      "loss": 1.0791,
+      "step": 4310
+    },
+    {
+      "epoch": 5.889570552147239,
+      "grad_norm": 1.1941087245941162,
+      "learning_rate": 0.0002,
+      "loss": 1.0556,
+      "step": 4320
+    },
+    {
+      "epoch": 5.903203817314247,
+      "grad_norm": 1.2374001741409302,
+      "learning_rate": 0.0002,
+      "loss": 1.1089,
+      "step": 4330
+    },
+    {
+      "epoch": 5.916837082481254,
+      "grad_norm": 1.4314988851547241,
+      "learning_rate": 0.0002,
+      "loss": 1.0802,
+      "step": 4340
+    },
+    {
+      "epoch": 5.930470347648262,
+      "grad_norm": 1.1286126375198364,
+      "learning_rate": 0.0002,
+      "loss": 1.133,
+      "step": 4350
+    },
+    {
+      "epoch": 5.944103612815269,
+      "grad_norm": 1.25884211063385,
+      "learning_rate": 0.0002,
+      "loss": 1.0807,
+      "step": 4360
+    },
+    {
+      "epoch": 5.957736877982277,
+      "grad_norm": 1.223357915878296,
+      "learning_rate": 0.0002,
+      "loss": 1.1189,
+      "step": 4370
+    },
+    {
+      "epoch": 5.971370143149285,
+      "grad_norm": 1.2173810005187988,
+      "learning_rate": 0.0002,
+      "loss": 1.1335,
+      "step": 4380
+    },
+    {
+      "epoch": 5.985003408316292,
+      "grad_norm": 1.3152292966842651,
+      "learning_rate": 0.0002,
+      "loss": 1.1201,
+      "step": 4390
+    },
+    {
+      "epoch": 5.998636673483299,
+      "grad_norm": 1.5576739311218262,
+      "learning_rate": 0.0002,
+      "loss": 1.1456,
+      "step": 4400
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.3435311317443848,
+      "eval_runtime": 53.6362,
+      "eval_samples_per_second": 9.453,
+      "eval_steps_per_second": 1.193,
+      "step": 4401
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5864,
+  "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": 2.2605184450953216e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/training_args.bin b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..da7142eb13ed7f8418e5055c63a0fe0ca5e1972b
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-4401/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8beac9fdfb91726fdf7473c9e77541aa988c61dc8beaba03293eafbe9c0a376
+size 5560
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/README.md b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/adapter_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/adapter_model.safetensors b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e6aac1a12f8d73d9bff6a56f35fc4e01fdb8b3ef
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bbfe19b1249c8fd39eec19852e8daef1c5a4b412213ec445004bdf81ddd97bc
+size 143153376
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/optimizer.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..98066215c4dbcc8c3b7827e83a729859e22370fa
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d01c52a8dd45b65ef67b88921f890a78e3db81781efd189bb78ae27306d98d1c
+size 72886650
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/rng_state.pth b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..19b6052a9c95fdca4735766d87987424ca007bb6
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e4a0c08105fcd5051852976ad1b66b5b6ee2938a154961e7953cc474b6cbbfd
+size 14244
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/scheduler.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9a8787355ac5166e0c748423c41345c39963d75b
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dac04a313bf199901f4905a3dcb49ac1edffce136158830db1eeef05a7184287
+size 1064
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/special_tokens_map.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/tokenizer.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/tokenizer.model b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/tokenizer_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/trainer_state.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e623208074811bd4909907a5384b39f3585a815d
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/trainer_state.json
@@ -0,0 +1,3680 @@
+{
+  "best_metric": 1.8171186447143555,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733",
+  "epoch": 6.999318336741649,
+  "eval_steps": 10,
+  "global_step": 5134,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013633265167007498,
+      "grad_norm": 0.7714291214942932,
+      "learning_rate": 0.0002,
+      "loss": 3.0982,
+      "step": 10
+    },
+    {
+      "epoch": 0.027266530334014997,
+      "grad_norm": 0.5473978519439697,
+      "learning_rate": 0.0002,
+      "loss": 2.5206,
+      "step": 20
+    },
+    {
+      "epoch": 0.0408997955010225,
+      "grad_norm": 0.5452795624732971,
+      "learning_rate": 0.0002,
+      "loss": 2.3079,
+      "step": 30
+    },
+    {
+      "epoch": 0.054533060668029994,
+      "grad_norm": 0.5098028779029846,
+      "learning_rate": 0.0002,
+      "loss": 2.0019,
+      "step": 40
+    },
+    {
+      "epoch": 0.0681663258350375,
+      "grad_norm": 0.48062971234321594,
+      "learning_rate": 0.0002,
+      "loss": 1.9333,
+      "step": 50
+    },
+    {
+      "epoch": 0.081799591002045,
+      "grad_norm": 0.4505695104598999,
+      "learning_rate": 0.0002,
+      "loss": 1.9355,
+      "step": 60
+    },
+    {
+      "epoch": 0.09543285616905249,
+      "grad_norm": 0.41609591245651245,
+      "learning_rate": 0.0002,
+      "loss": 1.9312,
+      "step": 70
+    },
+    {
+      "epoch": 0.10906612133605999,
+      "grad_norm": 0.4323892593383789,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 80
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 0.4670293629169464,
+      "learning_rate": 0.0002,
+      "loss": 1.9294,
+      "step": 90
+    },
+    {
+      "epoch": 0.136332651670075,
+      "grad_norm": 0.40623316168785095,
+      "learning_rate": 0.0002,
+      "loss": 1.7946,
+      "step": 100
+    },
+    {
+      "epoch": 0.1499659168370825,
+      "grad_norm": 0.3620383143424988,
+      "learning_rate": 0.0002,
+      "loss": 1.8565,
+      "step": 110
+    },
+    {
+      "epoch": 0.16359918200409,
+      "grad_norm": 0.332218736410141,
+      "learning_rate": 0.0002,
+      "loss": 1.9238,
+      "step": 120
+    },
+    {
+      "epoch": 0.17723244717109748,
+      "grad_norm": 0.4004521667957306,
+      "learning_rate": 0.0002,
+      "loss": 1.93,
+      "step": 130
+    },
+    {
+      "epoch": 0.19086571233810498,
+      "grad_norm": 0.3698360323905945,
+      "learning_rate": 0.0002,
+      "loss": 1.7549,
+      "step": 140
+    },
+    {
+      "epoch": 0.20449897750511248,
+      "grad_norm": 0.3847949504852295,
+      "learning_rate": 0.0002,
+      "loss": 1.8771,
+      "step": 150
+    },
+    {
+      "epoch": 0.21813224267211997,
+      "grad_norm": 0.36843451857566833,
+      "learning_rate": 0.0002,
+      "loss": 1.8316,
+      "step": 160
+    },
+    {
+      "epoch": 0.23176550783912747,
+      "grad_norm": 0.37301021814346313,
+      "learning_rate": 0.0002,
+      "loss": 1.838,
+      "step": 170
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.3718886971473694,
+      "learning_rate": 0.0002,
+      "loss": 1.8909,
+      "step": 180
+    },
+    {
+      "epoch": 0.25903203817314246,
+      "grad_norm": 0.3088490962982178,
+      "learning_rate": 0.0002,
+      "loss": 1.8454,
+      "step": 190
+    },
+    {
+      "epoch": 0.27266530334015,
+      "grad_norm": 0.3611852526664734,
+      "learning_rate": 0.0002,
+      "loss": 1.9254,
+      "step": 200
+    },
+    {
+      "epoch": 0.28629856850715746,
+      "grad_norm": 0.36093324422836304,
+      "learning_rate": 0.0002,
+      "loss": 1.7844,
+      "step": 210
+    },
+    {
+      "epoch": 0.299931833674165,
+      "grad_norm": 0.3250400722026825,
+      "learning_rate": 0.0002,
+      "loss": 1.719,
+      "step": 220
+    },
+    {
+      "epoch": 0.31356509884117245,
+      "grad_norm": 0.3566756248474121,
+      "learning_rate": 0.0002,
+      "loss": 1.8729,
+      "step": 230
+    },
+    {
+      "epoch": 0.32719836400818,
+      "grad_norm": 0.32872408628463745,
+      "learning_rate": 0.0002,
+      "loss": 1.9259,
+      "step": 240
+    },
+    {
+      "epoch": 0.34083162917518744,
+      "grad_norm": 0.3983881175518036,
+      "learning_rate": 0.0002,
+      "loss": 1.9033,
+      "step": 250
+    },
+    {
+      "epoch": 0.35446489434219497,
+      "grad_norm": 0.3571510910987854,
+      "learning_rate": 0.0002,
+      "loss": 1.8588,
+      "step": 260
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 0.3036131262779236,
+      "learning_rate": 0.0002,
+      "loss": 1.8539,
+      "step": 270
+    },
+    {
+      "epoch": 0.38173142467620996,
+      "grad_norm": 0.36512863636016846,
+      "learning_rate": 0.0002,
+      "loss": 1.8572,
+      "step": 280
+    },
+    {
+      "epoch": 0.39536468984321743,
+      "grad_norm": 0.3429736793041229,
+      "learning_rate": 0.0002,
+      "loss": 1.8022,
+      "step": 290
+    },
+    {
+      "epoch": 0.40899795501022496,
+      "grad_norm": 0.3055964708328247,
+      "learning_rate": 0.0002,
+      "loss": 1.8754,
+      "step": 300
+    },
+    {
+      "epoch": 0.4226312201772324,
+      "grad_norm": 0.33801034092903137,
+      "learning_rate": 0.0002,
+      "loss": 1.8384,
+      "step": 310
+    },
+    {
+      "epoch": 0.43626448534423995,
+      "grad_norm": 0.348783016204834,
+      "learning_rate": 0.0002,
+      "loss": 1.7933,
+      "step": 320
+    },
+    {
+      "epoch": 0.4498977505112474,
+      "grad_norm": 0.3057514727115631,
+      "learning_rate": 0.0002,
+      "loss": 1.8451,
+      "step": 330
+    },
+    {
+      "epoch": 0.46353101567825494,
+      "grad_norm": 0.3849763572216034,
+      "learning_rate": 0.0002,
+      "loss": 1.8766,
+      "step": 340
+    },
+    {
+      "epoch": 0.47716428084526247,
+      "grad_norm": 0.30080053210258484,
+      "learning_rate": 0.0002,
+      "loss": 1.8073,
+      "step": 350
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.3595106303691864,
+      "learning_rate": 0.0002,
+      "loss": 1.8548,
+      "step": 360
+    },
+    {
+      "epoch": 0.5044308111792775,
+      "grad_norm": 0.31099820137023926,
+      "learning_rate": 0.0002,
+      "loss": 1.8232,
+      "step": 370
+    },
+    {
+      "epoch": 0.5180640763462849,
+      "grad_norm": 0.3157978355884552,
+      "learning_rate": 0.0002,
+      "loss": 1.7029,
+      "step": 380
+    },
+    {
+      "epoch": 0.5316973415132924,
+      "grad_norm": 0.27960965037345886,
+      "learning_rate": 0.0002,
+      "loss": 1.8265,
+      "step": 390
+    },
+    {
+      "epoch": 0.5453306066803,
+      "grad_norm": 0.3102385103702545,
+      "learning_rate": 0.0002,
+      "loss": 1.7414,
+      "step": 400
+    },
+    {
+      "epoch": 0.5589638718473074,
+      "grad_norm": 0.32828861474990845,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 410
+    },
+    {
+      "epoch": 0.5725971370143149,
+      "grad_norm": 0.29560017585754395,
+      "learning_rate": 0.0002,
+      "loss": 1.8165,
+      "step": 420
+    },
+    {
+      "epoch": 0.5862304021813224,
+      "grad_norm": 0.33316895365715027,
+      "learning_rate": 0.0002,
+      "loss": 1.9455,
+      "step": 430
+    },
+    {
+      "epoch": 0.59986366734833,
+      "grad_norm": 0.30420982837677,
+      "learning_rate": 0.0002,
+      "loss": 1.8241,
+      "step": 440
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 0.32619214057922363,
+      "learning_rate": 0.0002,
+      "loss": 1.7565,
+      "step": 450
+    },
+    {
+      "epoch": 0.6271301976823449,
+      "grad_norm": 0.3603750765323639,
+      "learning_rate": 0.0002,
+      "loss": 1.7945,
+      "step": 460
+    },
+    {
+      "epoch": 0.6407634628493524,
+      "grad_norm": 0.30834096670150757,
+      "learning_rate": 0.0002,
+      "loss": 1.7773,
+      "step": 470
+    },
+    {
+      "epoch": 0.65439672801636,
+      "grad_norm": 0.28756365180015564,
+      "learning_rate": 0.0002,
+      "loss": 1.8058,
+      "step": 480
+    },
+    {
+      "epoch": 0.6680299931833674,
+      "grad_norm": 0.2878406345844269,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 490
+    },
+    {
+      "epoch": 0.6816632583503749,
+      "grad_norm": 0.31329697370529175,
+      "learning_rate": 0.0002,
+      "loss": 1.8581,
+      "step": 500
+    },
+    {
+      "epoch": 0.6952965235173824,
+      "grad_norm": 0.3405822515487671,
+      "learning_rate": 0.0002,
+      "loss": 1.7886,
+      "step": 510
+    },
+    {
+      "epoch": 0.7089297886843899,
+      "grad_norm": 0.305560827255249,
+      "learning_rate": 0.0002,
+      "loss": 1.778,
+      "step": 520
+    },
+    {
+      "epoch": 0.7225630538513974,
+      "grad_norm": 0.2973416745662689,
+      "learning_rate": 0.0002,
+      "loss": 1.7592,
+      "step": 530
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 0.327303946018219,
+      "learning_rate": 0.0002,
+      "loss": 1.8223,
+      "step": 540
+    },
+    {
+      "epoch": 0.7498295841854125,
+      "grad_norm": 0.62595534324646,
+      "learning_rate": 0.0002,
+      "loss": 1.8591,
+      "step": 550
+    },
+    {
+      "epoch": 0.7634628493524199,
+      "grad_norm": 0.3129784166812897,
+      "learning_rate": 0.0002,
+      "loss": 1.7466,
+      "step": 560
+    },
+    {
+      "epoch": 0.7770961145194274,
+      "grad_norm": 0.32496583461761475,
+      "learning_rate": 0.0002,
+      "loss": 1.8035,
+      "step": 570
+    },
+    {
+      "epoch": 0.7907293796864349,
+      "grad_norm": 0.3098868131637573,
+      "learning_rate": 0.0002,
+      "loss": 1.7787,
+      "step": 580
+    },
+    {
+      "epoch": 0.8043626448534424,
+      "grad_norm": 0.30726853013038635,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 590
+    },
+    {
+      "epoch": 0.8179959100204499,
+      "grad_norm": 0.2964220643043518,
+      "learning_rate": 0.0002,
+      "loss": 1.7898,
+      "step": 600
+    },
+    {
+      "epoch": 0.8316291751874574,
+      "grad_norm": 0.32352274656295776,
+      "learning_rate": 0.0002,
+      "loss": 1.8114,
+      "step": 610
+    },
+    {
+      "epoch": 0.8452624403544649,
+      "grad_norm": 0.2938912510871887,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 620
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 0.295559823513031,
+      "learning_rate": 0.0002,
+      "loss": 1.7727,
+      "step": 630
+    },
+    {
+      "epoch": 0.8725289706884799,
+      "grad_norm": 0.34102028608322144,
+      "learning_rate": 0.0002,
+      "loss": 1.9,
+      "step": 640
+    },
+    {
+      "epoch": 0.8861622358554874,
+      "grad_norm": 0.29676181077957153,
+      "learning_rate": 0.0002,
+      "loss": 1.8006,
+      "step": 650
+    },
+    {
+      "epoch": 0.8997955010224948,
+      "grad_norm": 0.3108902871608734,
+      "learning_rate": 0.0002,
+      "loss": 1.8099,
+      "step": 660
+    },
+    {
+      "epoch": 0.9134287661895024,
+      "grad_norm": 0.2690821588039398,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 670
+    },
+    {
+      "epoch": 0.9270620313565099,
+      "grad_norm": 0.32752540707588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7881,
+      "step": 680
+    },
+    {
+      "epoch": 0.9406952965235174,
+      "grad_norm": 0.8029476404190063,
+      "learning_rate": 0.0002,
+      "loss": 1.7661,
+      "step": 690
+    },
+    {
+      "epoch": 0.9543285616905249,
+      "grad_norm": 0.30534422397613525,
+      "learning_rate": 0.0002,
+      "loss": 1.7733,
+      "step": 700
+    },
+    {
+      "epoch": 0.9679618268575324,
+      "grad_norm": 0.2899954319000244,
+      "learning_rate": 0.0002,
+      "loss": 1.7614,
+      "step": 710
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 0.28814372420310974,
+      "learning_rate": 0.0002,
+      "loss": 1.7845,
+      "step": 720
+    },
+    {
+      "epoch": 0.9952283571915473,
+      "grad_norm": 0.3061596751213074,
+      "learning_rate": 0.0002,
+      "loss": 1.8865,
+      "step": 730
+    },
+    {
+      "epoch": 0.9993183367416496,
+      "eval_loss": 1.8171186447143555,
+      "eval_runtime": 53.6047,
+      "eval_samples_per_second": 9.458,
+      "eval_steps_per_second": 1.194,
+      "step": 733
+    },
+    {
+      "epoch": 1.008861622358555,
+      "grad_norm": 0.3140897750854492,
+      "learning_rate": 0.0002,
+      "loss": 1.6202,
+      "step": 740
+    },
+    {
+      "epoch": 1.0224948875255624,
+      "grad_norm": 0.3346109390258789,
+      "learning_rate": 0.0002,
+      "loss": 1.8409,
+      "step": 750
+    },
+    {
+      "epoch": 1.0361281526925699,
+      "grad_norm": 0.3582976758480072,
+      "learning_rate": 0.0002,
+      "loss": 1.6777,
+      "step": 760
+    },
+    {
+      "epoch": 1.0497614178595773,
+      "grad_norm": 0.30408260226249695,
+      "learning_rate": 0.0002,
+      "loss": 1.7306,
+      "step": 770
+    },
+    {
+      "epoch": 1.0633946830265848,
+      "grad_norm": 0.323585569858551,
+      "learning_rate": 0.0002,
+      "loss": 1.6967,
+      "step": 780
+    },
+    {
+      "epoch": 1.0770279481935923,
+      "grad_norm": 0.3474137783050537,
+      "learning_rate": 0.0002,
+      "loss": 1.768,
+      "step": 790
+    },
+    {
+      "epoch": 1.0906612133606,
+      "grad_norm": 0.35721147060394287,
+      "learning_rate": 0.0002,
+      "loss": 1.6895,
+      "step": 800
+    },
+    {
+      "epoch": 1.1042944785276074,
+      "grad_norm": 0.35366931557655334,
+      "learning_rate": 0.0002,
+      "loss": 1.718,
+      "step": 810
+    },
+    {
+      "epoch": 1.117927743694615,
+      "grad_norm": 0.3250770568847656,
+      "learning_rate": 0.0002,
+      "loss": 1.6797,
+      "step": 820
+    },
+    {
+      "epoch": 1.1315610088616224,
+      "grad_norm": 0.3293766379356384,
+      "learning_rate": 0.0002,
+      "loss": 1.6383,
+      "step": 830
+    },
+    {
+      "epoch": 1.1451942740286298,
+      "grad_norm": 0.3380851745605469,
+      "learning_rate": 0.0002,
+      "loss": 1.7353,
+      "step": 840
+    },
+    {
+      "epoch": 1.1588275391956373,
+      "grad_norm": 0.32584455609321594,
+      "learning_rate": 0.0002,
+      "loss": 1.8236,
+      "step": 850
+    },
+    {
+      "epoch": 1.1724608043626448,
+      "grad_norm": 0.45700767636299133,
+      "learning_rate": 0.0002,
+      "loss": 1.6681,
+      "step": 860
+    },
+    {
+      "epoch": 1.1860940695296525,
+      "grad_norm": 0.30944544076919556,
+      "learning_rate": 0.0002,
+      "loss": 1.7494,
+      "step": 870
+    },
+    {
+      "epoch": 1.19972733469666,
+      "grad_norm": 0.3268151581287384,
+      "learning_rate": 0.0002,
+      "loss": 1.7426,
+      "step": 880
+    },
+    {
+      "epoch": 1.2133605998636674,
+      "grad_norm": 0.39972540736198425,
+      "learning_rate": 0.0002,
+      "loss": 1.7413,
+      "step": 890
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 0.7890929579734802,
+      "learning_rate": 0.0002,
+      "loss": 1.7481,
+      "step": 900
+    },
+    {
+      "epoch": 1.2406271301976823,
+      "grad_norm": 0.3439182639122009,
+      "learning_rate": 0.0002,
+      "loss": 1.7608,
+      "step": 910
+    },
+    {
+      "epoch": 1.2542603953646898,
+      "grad_norm": 0.3986225128173828,
+      "learning_rate": 0.0002,
+      "loss": 1.7617,
+      "step": 920
+    },
+    {
+      "epoch": 1.2678936605316973,
+      "grad_norm": 0.3514605164527893,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 930
+    },
+    {
+      "epoch": 1.2815269256987047,
+      "grad_norm": 0.3682589530944824,
+      "learning_rate": 0.0002,
+      "loss": 1.6987,
+      "step": 940
+    },
+    {
+      "epoch": 1.2951601908657122,
+      "grad_norm": 0.3618335723876953,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 950
+    },
+    {
+      "epoch": 1.30879345603272,
+      "grad_norm": 0.345700740814209,
+      "learning_rate": 0.0002,
+      "loss": 1.7436,
+      "step": 960
+    },
+    {
+      "epoch": 1.3224267211997274,
+      "grad_norm": 0.3514927923679352,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 970
+    },
+    {
+      "epoch": 1.3360599863667348,
+      "grad_norm": 0.365647554397583,
+      "learning_rate": 0.0002,
+      "loss": 1.7704,
+      "step": 980
+    },
+    {
+      "epoch": 1.3496932515337423,
+      "grad_norm": 0.3407285809516907,
+      "learning_rate": 0.0002,
+      "loss": 1.7104,
+      "step": 990
+    },
+    {
+      "epoch": 1.3633265167007498,
+      "grad_norm": 0.3785437345504761,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3769597818677572,
+      "grad_norm": 0.34746724367141724,
+      "learning_rate": 0.0002,
+      "loss": 1.766,
+      "step": 1010
+    },
+    {
+      "epoch": 1.390593047034765,
+      "grad_norm": 0.362444132566452,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4042263122017724,
+      "grad_norm": 0.4424704611301422,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4178595773687799,
+      "grad_norm": 0.38722458481788635,
+      "learning_rate": 0.0002,
+      "loss": 1.726,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4314928425357873,
+      "grad_norm": 0.36089080572128296,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4451261077027948,
+      "grad_norm": 0.33817124366760254,
+      "learning_rate": 0.0002,
+      "loss": 1.6924,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4587593728698023,
+      "grad_norm": 0.34334081411361694,
+      "learning_rate": 0.0002,
+      "loss": 1.7165,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4723926380368098,
+      "grad_norm": 0.3776826858520508,
+      "learning_rate": 0.0002,
+      "loss": 1.6999,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4860259032038172,
+      "grad_norm": 0.4169026017189026,
+      "learning_rate": 0.0002,
+      "loss": 1.7605,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4996591683708247,
+      "grad_norm": 0.34898945689201355,
+      "learning_rate": 0.0002,
+      "loss": 1.7502,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5132924335378322,
+      "grad_norm": 0.34223780035972595,
+      "learning_rate": 0.0002,
+      "loss": 1.635,
+      "step": 1110
+    },
+    {
+      "epoch": 1.5269256987048399,
+      "grad_norm": 0.3686901032924652,
+      "learning_rate": 0.0002,
+      "loss": 1.7248,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5405589638718473,
+      "grad_norm": 0.35054415464401245,
+      "learning_rate": 0.0002,
+      "loss": 1.7525,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5541922290388548,
+      "grad_norm": 0.39496365189552307,
+      "learning_rate": 0.0002,
+      "loss": 1.7776,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5678254942058623,
+      "grad_norm": 0.35451626777648926,
+      "learning_rate": 0.0002,
+      "loss": 1.6574,
+      "step": 1150
+    },
+    {
+      "epoch": 1.58145875937287,
+      "grad_norm": 0.3848083019256592,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5950920245398774,
+      "grad_norm": 0.3760537803173065,
+      "learning_rate": 0.0002,
+      "loss": 1.7272,
+      "step": 1170
+    },
+    {
+      "epoch": 1.6087252897068849,
+      "grad_norm": 0.38981738686561584,
+      "learning_rate": 0.0002,
+      "loss": 1.7441,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6223585548738924,
+      "grad_norm": 0.36830949783325195,
+      "learning_rate": 0.0002,
+      "loss": 1.6951,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6359918200408998,
+      "grad_norm": 0.3405892848968506,
+      "learning_rate": 0.0002,
+      "loss": 1.6925,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6496250852079073,
+      "grad_norm": 0.39027872681617737,
+      "learning_rate": 0.0002,
+      "loss": 1.7473,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6632583503749148,
+      "grad_norm": 0.3342694044113159,
+      "learning_rate": 0.0002,
+      "loss": 1.6792,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6768916155419222,
+      "grad_norm": 0.3600076735019684,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6905248807089297,
+      "grad_norm": 0.3625542223453522,
+      "learning_rate": 0.0002,
+      "loss": 1.7021,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7041581458759372,
+      "grad_norm": 0.32170894742012024,
+      "learning_rate": 0.0002,
+      "loss": 1.6772,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7177914110429446,
+      "grad_norm": 0.3544139862060547,
+      "learning_rate": 0.0002,
+      "loss": 1.7152,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7314246762099523,
+      "grad_norm": 0.35113027691841125,
+      "learning_rate": 0.0002,
+      "loss": 1.7138,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7450579413769598,
+      "grad_norm": 0.3499974310398102,
+      "learning_rate": 0.0002,
+      "loss": 1.7095,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7586912065439673,
+      "grad_norm": 0.3285157382488251,
+      "learning_rate": 0.0002,
+      "loss": 1.7749,
+      "step": 1290
+    },
+    {
+      "epoch": 1.7723244717109747,
+      "grad_norm": 0.3701961636543274,
+      "learning_rate": 0.0002,
+      "loss": 1.6767,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7859577368779824,
+      "grad_norm": 0.3301318287849426,
+      "learning_rate": 0.0002,
+      "loss": 1.6282,
+      "step": 1310
+    },
+    {
+      "epoch": 1.79959100204499,
+      "grad_norm": 0.37801554799079895,
+      "learning_rate": 0.0002,
+      "loss": 1.7097,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8132242672119974,
+      "grad_norm": 0.3726748526096344,
+      "learning_rate": 0.0002,
+      "loss": 1.7437,
+      "step": 1330
+    },
+    {
+      "epoch": 1.8268575323790048,
+      "grad_norm": 0.4059790074825287,
+      "learning_rate": 0.0002,
+      "loss": 1.7959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 0.35712096095085144,
+      "learning_rate": 0.0002,
+      "loss": 1.7739,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8541240627130198,
+      "grad_norm": 0.35995328426361084,
+      "learning_rate": 0.0002,
+      "loss": 1.6375,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8677573278800272,
+      "grad_norm": 0.3679947257041931,
+      "learning_rate": 0.0002,
+      "loss": 1.7332,
+      "step": 1370
+    },
+    {
+      "epoch": 1.8813905930470347,
+      "grad_norm": 0.39645957946777344,
+      "learning_rate": 0.0002,
+      "loss": 1.7587,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950238582140422,
+      "grad_norm": 0.35288700461387634,
+      "learning_rate": 0.0002,
+      "loss": 1.6985,
+      "step": 1390
+    },
+    {
+      "epoch": 1.9086571233810496,
+      "grad_norm": 0.32579198479652405,
+      "learning_rate": 0.0002,
+      "loss": 1.6582,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9222903885480571,
+      "grad_norm": 0.3856561779975891,
+      "learning_rate": 0.0002,
+      "loss": 1.6948,
+      "step": 1410
+    },
+    {
+      "epoch": 1.9359236537150648,
+      "grad_norm": 0.39019331336021423,
+      "learning_rate": 0.0002,
+      "loss": 1.668,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9495569188820723,
+      "grad_norm": 0.38006502389907837,
+      "learning_rate": 0.0002,
+      "loss": 1.7774,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9631901840490797,
+      "grad_norm": 0.38100454211235046,
+      "learning_rate": 0.0002,
+      "loss": 1.8323,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9768234492160872,
+      "grad_norm": 0.3405798673629761,
+      "learning_rate": 0.0002,
+      "loss": 1.7298,
+      "step": 1450
+    },
+    {
+      "epoch": 1.990456714383095,
+      "grad_norm": 0.36582913994789124,
+      "learning_rate": 0.0002,
+      "loss": 1.7045,
+      "step": 1460
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8178424835205078,
+      "eval_runtime": 53.6524,
+      "eval_samples_per_second": 9.45,
+      "eval_steps_per_second": 1.193,
+      "step": 1467
+    },
+    {
+      "epoch": 2.0040899795501024,
+      "grad_norm": 0.3626647889614105,
+      "learning_rate": 0.0002,
+      "loss": 1.6363,
+      "step": 1470
+    },
+    {
+      "epoch": 2.01772324471711,
+      "grad_norm": 0.40171775221824646,
+      "learning_rate": 0.0002,
+      "loss": 1.5354,
+      "step": 1480
+    },
+    {
+      "epoch": 2.0313565098841173,
+      "grad_norm": 0.5805319547653198,
+      "learning_rate": 0.0002,
+      "loss": 1.5566,
+      "step": 1490
+    },
+    {
+      "epoch": 2.044989775051125,
+      "grad_norm": 0.41954153776168823,
+      "learning_rate": 0.0002,
+      "loss": 1.546,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0586230402181322,
+      "grad_norm": 0.47190725803375244,
+      "learning_rate": 0.0002,
+      "loss": 1.6158,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0722563053851397,
+      "grad_norm": 0.4388456344604492,
+      "learning_rate": 0.0002,
+      "loss": 1.5841,
+      "step": 1520
+    },
+    {
+      "epoch": 2.085889570552147,
+      "grad_norm": 2.2171926498413086,
+      "learning_rate": 0.0002,
+      "loss": 1.5835,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0995228357191547,
+      "grad_norm": 0.4314221143722534,
+      "learning_rate": 0.0002,
+      "loss": 1.6137,
+      "step": 1540
+    },
+    {
+      "epoch": 2.113156100886162,
+      "grad_norm": 0.4154265522956848,
+      "learning_rate": 0.0002,
+      "loss": 1.5511,
+      "step": 1550
+    },
+    {
+      "epoch": 2.1267893660531696,
+      "grad_norm": 0.5025539994239807,
+      "learning_rate": 0.0002,
+      "loss": 1.6323,
+      "step": 1560
+    },
+    {
+      "epoch": 2.140422631220177,
+      "grad_norm": 0.5410493016242981,
+      "learning_rate": 0.0002,
+      "loss": 1.5903,
+      "step": 1570
+    },
+    {
+      "epoch": 2.1540558963871845,
+      "grad_norm": 0.4478487968444824,
+      "learning_rate": 0.0002,
+      "loss": 1.507,
+      "step": 1580
+    },
+    {
+      "epoch": 2.1676891615541924,
+      "grad_norm": 0.4703652560710907,
+      "learning_rate": 0.0002,
+      "loss": 1.5536,
+      "step": 1590
+    },
+    {
+      "epoch": 2.1813224267212,
+      "grad_norm": 0.4555390179157257,
+      "learning_rate": 0.0002,
+      "loss": 1.5991,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1949556918882074,
+      "grad_norm": 0.4877263903617859,
+      "learning_rate": 0.0002,
+      "loss": 1.6117,
+      "step": 1610
+    },
+    {
+      "epoch": 2.208588957055215,
+      "grad_norm": 0.48708245158195496,
+      "learning_rate": 0.0002,
+      "loss": 1.5928,
+      "step": 1620
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.47523951530456543,
+      "learning_rate": 0.0002,
+      "loss": 1.6106,
+      "step": 1630
+    },
+    {
+      "epoch": 2.23585548738923,
+      "grad_norm": 0.4889199733734131,
+      "learning_rate": 0.0002,
+      "loss": 1.6013,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2494887525562373,
+      "grad_norm": 0.4585252106189728,
+      "learning_rate": 0.0002,
+      "loss": 1.6633,
+      "step": 1650
+    },
+    {
+      "epoch": 2.2631220177232447,
+      "grad_norm": 0.4764868915081024,
+      "learning_rate": 0.0002,
+      "loss": 1.6075,
+      "step": 1660
+    },
+    {
+      "epoch": 2.276755282890252,
+      "grad_norm": 0.5028976202011108,
+      "learning_rate": 0.0002,
+      "loss": 1.6427,
+      "step": 1670
+    },
+    {
+      "epoch": 2.2903885480572597,
+      "grad_norm": 0.46131211519241333,
+      "learning_rate": 0.0002,
+      "loss": 1.6258,
+      "step": 1680
+    },
+    {
+      "epoch": 2.304021813224267,
+      "grad_norm": 0.5422874689102173,
+      "learning_rate": 0.0002,
+      "loss": 1.654,
+      "step": 1690
+    },
+    {
+      "epoch": 2.3176550783912746,
+      "grad_norm": 0.47615355253219604,
+      "learning_rate": 0.0002,
+      "loss": 1.6331,
+      "step": 1700
+    },
+    {
+      "epoch": 2.331288343558282,
+      "grad_norm": 0.48005548119544983,
+      "learning_rate": 0.0002,
+      "loss": 1.642,
+      "step": 1710
+    },
+    {
+      "epoch": 2.3449216087252895,
+      "grad_norm": 0.4387182295322418,
+      "learning_rate": 0.0002,
+      "loss": 1.581,
+      "step": 1720
+    },
+    {
+      "epoch": 2.358554873892297,
+      "grad_norm": 0.4487272799015045,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 1730
+    },
+    {
+      "epoch": 2.372188139059305,
+      "grad_norm": 0.5046455264091492,
+      "learning_rate": 0.0002,
+      "loss": 1.5089,
+      "step": 1740
+    },
+    {
+      "epoch": 2.3858214042263124,
+      "grad_norm": 0.4653521180152893,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 1750
+    },
+    {
+      "epoch": 2.39945466939332,
+      "grad_norm": 0.4737723469734192,
+      "learning_rate": 0.0002,
+      "loss": 1.6201,
+      "step": 1760
+    },
+    {
+      "epoch": 2.4130879345603273,
+      "grad_norm": 0.4501931071281433,
+      "learning_rate": 0.0002,
+      "loss": 1.5933,
+      "step": 1770
+    },
+    {
+      "epoch": 2.426721199727335,
+      "grad_norm": 0.4772880971431732,
+      "learning_rate": 0.0002,
+      "loss": 1.6321,
+      "step": 1780
+    },
+    {
+      "epoch": 2.4403544648943423,
+      "grad_norm": 0.4544616937637329,
+      "learning_rate": 0.0002,
+      "loss": 1.5454,
+      "step": 1790
+    },
+    {
+      "epoch": 2.4539877300613497,
+      "grad_norm": 0.488313227891922,
+      "learning_rate": 0.0002,
+      "loss": 1.5501,
+      "step": 1800
+    },
+    {
+      "epoch": 2.467620995228357,
+      "grad_norm": 0.5057830214500427,
+      "learning_rate": 0.0002,
+      "loss": 1.5791,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4812542603953647,
+      "grad_norm": 0.5049484968185425,
+      "learning_rate": 0.0002,
+      "loss": 1.5645,
+      "step": 1820
+    },
+    {
+      "epoch": 2.494887525562372,
+      "grad_norm": 0.44966644048690796,
+      "learning_rate": 0.0002,
+      "loss": 1.6268,
+      "step": 1830
+    },
+    {
+      "epoch": 2.5085207907293796,
+      "grad_norm": 0.5072630643844604,
+      "learning_rate": 0.0002,
+      "loss": 1.5941,
+      "step": 1840
+    },
+    {
+      "epoch": 2.522154055896387,
+      "grad_norm": 0.43989792466163635,
+      "learning_rate": 0.0002,
+      "loss": 1.5251,
+      "step": 1850
+    },
+    {
+      "epoch": 2.5357873210633946,
+      "grad_norm": 1.3504403829574585,
+      "learning_rate": 0.0002,
+      "loss": 1.563,
+      "step": 1860
+    },
+    {
+      "epoch": 2.549420586230402,
+      "grad_norm": 0.46545976400375366,
+      "learning_rate": 0.0002,
+      "loss": 1.5681,
+      "step": 1870
+    },
+    {
+      "epoch": 2.5630538513974095,
+      "grad_norm": 0.4678342044353485,
+      "learning_rate": 0.0002,
+      "loss": 1.6368,
+      "step": 1880
+    },
+    {
+      "epoch": 2.5766871165644174,
+      "grad_norm": 0.529755711555481,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5903203817314244,
+      "grad_norm": 0.5000199675559998,
+      "learning_rate": 0.0002,
+      "loss": 1.5861,
+      "step": 1900
+    },
+    {
+      "epoch": 2.6039536468984323,
+      "grad_norm": 0.5649300217628479,
+      "learning_rate": 0.0002,
+      "loss": 1.6346,
+      "step": 1910
+    },
+    {
+      "epoch": 2.61758691206544,
+      "grad_norm": 0.7920585870742798,
+      "learning_rate": 0.0002,
+      "loss": 1.6317,
+      "step": 1920
+    },
+    {
+      "epoch": 2.6312201772324473,
+      "grad_norm": 0.4960342049598694,
+      "learning_rate": 0.0002,
+      "loss": 1.643,
+      "step": 1930
+    },
+    {
+      "epoch": 2.6448534423994547,
+      "grad_norm": 0.5324710011482239,
+      "learning_rate": 0.0002,
+      "loss": 1.6099,
+      "step": 1940
+    },
+    {
+      "epoch": 2.658486707566462,
+      "grad_norm": 0.606343150138855,
+      "learning_rate": 0.0002,
+      "loss": 1.5874,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6721199727334697,
+      "grad_norm": 0.53038489818573,
+      "learning_rate": 0.0002,
+      "loss": 1.5728,
+      "step": 1960
+    },
+    {
+      "epoch": 2.685753237900477,
+      "grad_norm": 0.4579465091228485,
+      "learning_rate": 0.0002,
+      "loss": 1.5583,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6993865030674846,
+      "grad_norm": 0.4541707932949066,
+      "learning_rate": 0.0002,
+      "loss": 1.6093,
+      "step": 1980
+    },
+    {
+      "epoch": 2.713019768234492,
+      "grad_norm": 0.5009395480155945,
+      "learning_rate": 0.0002,
+      "loss": 1.5316,
+      "step": 1990
+    },
+    {
+      "epoch": 2.7266530334014996,
+      "grad_norm": 0.4723006784915924,
+      "learning_rate": 0.0002,
+      "loss": 1.6724,
+      "step": 2000
+    },
+    {
+      "epoch": 2.740286298568507,
+      "grad_norm": 0.5086126923561096,
+      "learning_rate": 0.0002,
+      "loss": 1.638,
+      "step": 2010
+    },
+    {
+      "epoch": 2.7539195637355145,
+      "grad_norm": 0.47242608666419983,
+      "learning_rate": 0.0002,
+      "loss": 1.6223,
+      "step": 2020
+    },
+    {
+      "epoch": 2.767552828902522,
+      "grad_norm": 0.44922566413879395,
+      "learning_rate": 0.0002,
+      "loss": 1.6242,
+      "step": 2030
+    },
+    {
+      "epoch": 2.78118609406953,
+      "grad_norm": 0.420259565114975,
+      "learning_rate": 0.0002,
+      "loss": 1.6837,
+      "step": 2040
+    },
+    {
+      "epoch": 2.794819359236537,
+      "grad_norm": 0.4762881100177765,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 2050
+    },
+    {
+      "epoch": 2.808452624403545,
+      "grad_norm": 0.5228786468505859,
+      "learning_rate": 0.0002,
+      "loss": 1.5506,
+      "step": 2060
+    },
+    {
+      "epoch": 2.8220858895705523,
+      "grad_norm": 0.4796035587787628,
+      "learning_rate": 0.0002,
+      "loss": 1.6347,
+      "step": 2070
+    },
+    {
+      "epoch": 2.8357191547375598,
+      "grad_norm": 0.5034735202789307,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 2080
+    },
+    {
+      "epoch": 2.8493524199045672,
+      "grad_norm": 0.48005399107933044,
+      "learning_rate": 0.0002,
+      "loss": 1.6455,
+      "step": 2090
+    },
+    {
+      "epoch": 2.8629856850715747,
+      "grad_norm": 0.578820526599884,
+      "learning_rate": 0.0002,
+      "loss": 1.6287,
+      "step": 2100
+    },
+    {
+      "epoch": 2.876618950238582,
+      "grad_norm": 0.48982638120651245,
+      "learning_rate": 0.0002,
+      "loss": 1.6021,
+      "step": 2110
+    },
+    {
+      "epoch": 2.8902522154055896,
+      "grad_norm": 0.5157325863838196,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 2120
+    },
+    {
+      "epoch": 2.903885480572597,
+      "grad_norm": 0.49149683117866516,
+      "learning_rate": 0.0002,
+      "loss": 1.6089,
+      "step": 2130
+    },
+    {
+      "epoch": 2.9175187457396046,
+      "grad_norm": 0.48584499955177307,
+      "learning_rate": 0.0002,
+      "loss": 1.5881,
+      "step": 2140
+    },
+    {
+      "epoch": 2.931152010906612,
+      "grad_norm": 0.5199017524719238,
+      "learning_rate": 0.0002,
+      "loss": 1.5833,
+      "step": 2150
+    },
+    {
+      "epoch": 2.9447852760736195,
+      "grad_norm": 0.5788236856460571,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 2160
+    },
+    {
+      "epoch": 2.958418541240627,
+      "grad_norm": 0.48664185404777527,
+      "learning_rate": 0.0002,
+      "loss": 1.6103,
+      "step": 2170
+    },
+    {
+      "epoch": 2.9720518064076344,
+      "grad_norm": 0.5026682615280151,
+      "learning_rate": 0.0002,
+      "loss": 1.5765,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9856850715746424,
+      "grad_norm": 0.49317044019699097,
+      "learning_rate": 0.0002,
+      "loss": 1.6626,
+      "step": 2190
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "grad_norm": 0.5729128122329712,
+      "learning_rate": 0.0002,
+      "loss": 1.5871,
+      "step": 2200
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "eval_loss": 1.8527295589447021,
+      "eval_runtime": 53.6403,
+      "eval_samples_per_second": 9.452,
+      "eval_steps_per_second": 1.193,
+      "step": 2200
+    },
+    {
+      "epoch": 3.0129516019086573,
+      "grad_norm": 0.5530241131782532,
+      "learning_rate": 0.0002,
+      "loss": 1.4719,
+      "step": 2210
+    },
+    {
+      "epoch": 3.0265848670756648,
+      "grad_norm": 0.6642216444015503,
+      "learning_rate": 0.0002,
+      "loss": 1.4088,
+      "step": 2220
+    },
+    {
+      "epoch": 3.0402181322426722,
+      "grad_norm": 0.61470627784729,
+      "learning_rate": 0.0002,
+      "loss": 1.4382,
+      "step": 2230
+    },
+    {
+      "epoch": 3.0538513974096797,
+      "grad_norm": 0.8559566140174866,
+      "learning_rate": 0.0002,
+      "loss": 1.4634,
+      "step": 2240
+    },
+    {
+      "epoch": 3.067484662576687,
+      "grad_norm": 0.7015801668167114,
+      "learning_rate": 0.0002,
+      "loss": 1.3854,
+      "step": 2250
+    },
+    {
+      "epoch": 3.0811179277436946,
+      "grad_norm": 0.7226442694664001,
+      "learning_rate": 0.0002,
+      "loss": 1.4981,
+      "step": 2260
+    },
+    {
+      "epoch": 3.094751192910702,
+      "grad_norm": 0.7560588717460632,
+      "learning_rate": 0.0002,
+      "loss": 1.4143,
+      "step": 2270
+    },
+    {
+      "epoch": 3.1083844580777096,
+      "grad_norm": 0.6216568946838379,
+      "learning_rate": 0.0002,
+      "loss": 1.4395,
+      "step": 2280
+    },
+    {
+      "epoch": 3.122017723244717,
+      "grad_norm": 0.6768500804901123,
+      "learning_rate": 0.0002,
+      "loss": 1.3842,
+      "step": 2290
+    },
+    {
+      "epoch": 3.1356509884117245,
+      "grad_norm": 0.7028762102127075,
+      "learning_rate": 0.0002,
+      "loss": 1.4672,
+      "step": 2300
+    },
+    {
+      "epoch": 3.149284253578732,
+      "grad_norm": 0.6329697966575623,
+      "learning_rate": 0.0002,
+      "loss": 1.3826,
+      "step": 2310
+    },
+    {
+      "epoch": 3.1629175187457395,
+      "grad_norm": 0.6328264474868774,
+      "learning_rate": 0.0002,
+      "loss": 1.442,
+      "step": 2320
+    },
+    {
+      "epoch": 3.176550783912747,
+      "grad_norm": 0.7573632001876831,
+      "learning_rate": 0.0002,
+      "loss": 1.3762,
+      "step": 2330
+    },
+    {
+      "epoch": 3.190184049079755,
+      "grad_norm": 0.595740795135498,
+      "learning_rate": 0.0002,
+      "loss": 1.3553,
+      "step": 2340
+    },
+    {
+      "epoch": 3.2038173142467623,
+      "grad_norm": 0.7111806869506836,
+      "learning_rate": 0.0002,
+      "loss": 1.3953,
+      "step": 2350
+    },
+    {
+      "epoch": 3.2174505794137698,
+      "grad_norm": 0.6328730583190918,
+      "learning_rate": 0.0002,
+      "loss": 1.3797,
+      "step": 2360
+    },
+    {
+      "epoch": 3.2310838445807772,
+      "grad_norm": 0.5860254168510437,
+      "learning_rate": 0.0002,
+      "loss": 1.3855,
+      "step": 2370
+    },
+    {
+      "epoch": 3.2447171097477847,
+      "grad_norm": 0.7387157082557678,
+      "learning_rate": 0.0002,
+      "loss": 1.4267,
+      "step": 2380
+    },
+    {
+      "epoch": 3.258350374914792,
+      "grad_norm": 0.6897673606872559,
+      "learning_rate": 0.0002,
+      "loss": 1.4837,
+      "step": 2390
+    },
+    {
+      "epoch": 3.2719836400817996,
+      "grad_norm": 0.7157699465751648,
+      "learning_rate": 0.0002,
+      "loss": 1.4372,
+      "step": 2400
+    },
+    {
+      "epoch": 3.285616905248807,
+      "grad_norm": 0.6422511339187622,
+      "learning_rate": 0.0002,
+      "loss": 1.4432,
+      "step": 2410
+    },
+    {
+      "epoch": 3.2992501704158146,
+      "grad_norm": 1.0481886863708496,
+      "learning_rate": 0.0002,
+      "loss": 1.4828,
+      "step": 2420
+    },
+    {
+      "epoch": 3.312883435582822,
+      "grad_norm": 0.7050786018371582,
+      "learning_rate": 0.0002,
+      "loss": 1.4473,
+      "step": 2430
+    },
+    {
+      "epoch": 3.3265167007498295,
+      "grad_norm": 0.6090759038925171,
+      "learning_rate": 0.0002,
+      "loss": 1.3465,
+      "step": 2440
+    },
+    {
+      "epoch": 3.340149965916837,
+      "grad_norm": 0.6626465320587158,
+      "learning_rate": 0.0002,
+      "loss": 1.4619,
+      "step": 2450
+    },
+    {
+      "epoch": 3.3537832310838445,
+      "grad_norm": 0.6565486788749695,
+      "learning_rate": 0.0002,
+      "loss": 1.4512,
+      "step": 2460
+    },
+    {
+      "epoch": 3.367416496250852,
+      "grad_norm": 0.6449528932571411,
+      "learning_rate": 0.0002,
+      "loss": 1.588,
+      "step": 2470
+    },
+    {
+      "epoch": 3.3810497614178594,
+      "grad_norm": 0.7746227383613586,
+      "learning_rate": 0.0002,
+      "loss": 1.4773,
+      "step": 2480
+    },
+    {
+      "epoch": 3.3946830265848673,
+      "grad_norm": 0.7074846029281616,
+      "learning_rate": 0.0002,
+      "loss": 1.417,
+      "step": 2490
+    },
+    {
+      "epoch": 3.4083162917518743,
+      "grad_norm": 0.6547690033912659,
+      "learning_rate": 0.0002,
+      "loss": 1.4476,
+      "step": 2500
+    },
+    {
+      "epoch": 3.4219495569188823,
+      "grad_norm": 0.784721314907074,
+      "learning_rate": 0.0002,
+      "loss": 1.4074,
+      "step": 2510
+    },
+    {
+      "epoch": 3.4355828220858897,
+      "grad_norm": 0.7270277738571167,
+      "learning_rate": 0.0002,
+      "loss": 1.4326,
+      "step": 2520
+    },
+    {
+      "epoch": 3.449216087252897,
+      "grad_norm": 0.67588871717453,
+      "learning_rate": 0.0002,
+      "loss": 1.4354,
+      "step": 2530
+    },
+    {
+      "epoch": 3.4628493524199047,
+      "grad_norm": 0.6768023371696472,
+      "learning_rate": 0.0002,
+      "loss": 1.4074,
+      "step": 2540
+    },
+    {
+      "epoch": 3.476482617586912,
+      "grad_norm": 0.7026481628417969,
+      "learning_rate": 0.0002,
+      "loss": 1.4863,
+      "step": 2550
+    },
+    {
+      "epoch": 3.4901158827539196,
+      "grad_norm": 0.646075963973999,
+      "learning_rate": 0.0002,
+      "loss": 1.468,
+      "step": 2560
+    },
+    {
+      "epoch": 3.503749147920927,
+      "grad_norm": 0.6288973689079285,
+      "learning_rate": 0.0002,
+      "loss": 1.4058,
+      "step": 2570
+    },
+    {
+      "epoch": 3.5173824130879345,
+      "grad_norm": 0.6440825462341309,
+      "learning_rate": 0.0002,
+      "loss": 1.4613,
+      "step": 2580
+    },
+    {
+      "epoch": 3.531015678254942,
+      "grad_norm": 0.7074111700057983,
+      "learning_rate": 0.0002,
+      "loss": 1.3808,
+      "step": 2590
+    },
+    {
+      "epoch": 3.5446489434219495,
+      "grad_norm": 0.7007562518119812,
+      "learning_rate": 0.0002,
+      "loss": 1.4901,
+      "step": 2600
+    },
+    {
+      "epoch": 3.558282208588957,
+      "grad_norm": 0.6045376658439636,
+      "learning_rate": 0.0002,
+      "loss": 1.4511,
+      "step": 2610
+    },
+    {
+      "epoch": 3.5719154737559644,
+      "grad_norm": 0.9149952530860901,
+      "learning_rate": 0.0002,
+      "loss": 1.4596,
+      "step": 2620
+    },
+    {
+      "epoch": 3.585548738922972,
+      "grad_norm": 0.6490362882614136,
+      "learning_rate": 0.0002,
+      "loss": 1.4355,
+      "step": 2630
+    },
+    {
+      "epoch": 3.59918200408998,
+      "grad_norm": 0.6552226543426514,
+      "learning_rate": 0.0002,
+      "loss": 1.4107,
+      "step": 2640
+    },
+    {
+      "epoch": 3.612815269256987,
+      "grad_norm": 0.6541850566864014,
+      "learning_rate": 0.0002,
+      "loss": 1.433,
+      "step": 2650
+    },
+    {
+      "epoch": 3.6264485344239947,
+      "grad_norm": 0.6500770449638367,
+      "learning_rate": 0.0002,
+      "loss": 1.4279,
+      "step": 2660
+    },
+    {
+      "epoch": 3.640081799591002,
+      "grad_norm": 0.6345893740653992,
+      "learning_rate": 0.0002,
+      "loss": 1.3929,
+      "step": 2670
+    },
+    {
+      "epoch": 3.6537150647580097,
+      "grad_norm": 0.6382275223731995,
+      "learning_rate": 0.0002,
+      "loss": 1.3634,
+      "step": 2680
+    },
+    {
+      "epoch": 3.667348329925017,
+      "grad_norm": 0.6738566160202026,
+      "learning_rate": 0.0002,
+      "loss": 1.4478,
+      "step": 2690
+    },
+    {
+      "epoch": 3.6809815950920246,
+      "grad_norm": 0.7446315288543701,
+      "learning_rate": 0.0002,
+      "loss": 1.4642,
+      "step": 2700
+    },
+    {
+      "epoch": 3.694614860259032,
+      "grad_norm": 0.6717571020126343,
+      "learning_rate": 0.0002,
+      "loss": 1.4342,
+      "step": 2710
+    },
+    {
+      "epoch": 3.7082481254260395,
+      "grad_norm": 0.667259693145752,
+      "learning_rate": 0.0002,
+      "loss": 1.4285,
+      "step": 2720
+    },
+    {
+      "epoch": 3.721881390593047,
+      "grad_norm": 0.6808622479438782,
+      "learning_rate": 0.0002,
+      "loss": 1.5389,
+      "step": 2730
+    },
+    {
+      "epoch": 3.7355146557600545,
+      "grad_norm": 0.7254287004470825,
+      "learning_rate": 0.0002,
+      "loss": 1.4297,
+      "step": 2740
+    },
+    {
+      "epoch": 3.749147920927062,
+      "grad_norm": 0.6864007711410522,
+      "learning_rate": 0.0002,
+      "loss": 1.4176,
+      "step": 2750
+    },
+    {
+      "epoch": 3.7627811860940694,
+      "grad_norm": 0.7041361331939697,
+      "learning_rate": 0.0002,
+      "loss": 1.4811,
+      "step": 2760
+    },
+    {
+      "epoch": 3.776414451261077,
+      "grad_norm": 0.6559903025627136,
+      "learning_rate": 0.0002,
+      "loss": 1.4284,
+      "step": 2770
+    },
+    {
+      "epoch": 3.7900477164280844,
+      "grad_norm": 0.6602269411087036,
+      "learning_rate": 0.0002,
+      "loss": 1.4608,
+      "step": 2780
+    },
+    {
+      "epoch": 3.8036809815950923,
+      "grad_norm": 0.692611813545227,
+      "learning_rate": 0.0002,
+      "loss": 1.4588,
+      "step": 2790
+    },
+    {
+      "epoch": 3.8173142467620993,
+      "grad_norm": 0.7051475644111633,
+      "learning_rate": 0.0002,
+      "loss": 1.4065,
+      "step": 2800
+    },
+    {
+      "epoch": 3.830947511929107,
+      "grad_norm": 0.6685371398925781,
+      "learning_rate": 0.0002,
+      "loss": 1.4083,
+      "step": 2810
+    },
+    {
+      "epoch": 3.8445807770961147,
+      "grad_norm": 0.6706477403640747,
+      "learning_rate": 0.0002,
+      "loss": 1.5227,
+      "step": 2820
+    },
+    {
+      "epoch": 3.858214042263122,
+      "grad_norm": 0.6671637296676636,
+      "learning_rate": 0.0002,
+      "loss": 1.4076,
+      "step": 2830
+    },
+    {
+      "epoch": 3.8718473074301296,
+      "grad_norm": 0.694092333316803,
+      "learning_rate": 0.0002,
+      "loss": 1.4736,
+      "step": 2840
+    },
+    {
+      "epoch": 3.885480572597137,
+      "grad_norm": 0.7349600195884705,
+      "learning_rate": 0.0002,
+      "loss": 1.4161,
+      "step": 2850
+    },
+    {
+      "epoch": 3.8991138377641446,
+      "grad_norm": 0.6647971868515015,
+      "learning_rate": 0.0002,
+      "loss": 1.4617,
+      "step": 2860
+    },
+    {
+      "epoch": 3.912747102931152,
+      "grad_norm": 0.806656539440155,
+      "learning_rate": 0.0002,
+      "loss": 1.5046,
+      "step": 2870
+    },
+    {
+      "epoch": 3.9263803680981595,
+      "grad_norm": 0.6008772850036621,
+      "learning_rate": 0.0002,
+      "loss": 1.428,
+      "step": 2880
+    },
+    {
+      "epoch": 3.940013633265167,
+      "grad_norm": 0.659227728843689,
+      "learning_rate": 0.0002,
+      "loss": 1.4116,
+      "step": 2890
+    },
+    {
+      "epoch": 3.9536468984321744,
+      "grad_norm": 0.6357656717300415,
+      "learning_rate": 0.0002,
+      "loss": 1.4136,
+      "step": 2900
+    },
+    {
+      "epoch": 3.967280163599182,
+      "grad_norm": 0.6541687846183777,
+      "learning_rate": 0.0002,
+      "loss": 1.4655,
+      "step": 2910
+    },
+    {
+      "epoch": 3.9809134287661894,
+      "grad_norm": 0.6090909838676453,
+      "learning_rate": 0.0002,
+      "loss": 1.4854,
+      "step": 2920
+    },
+    {
+      "epoch": 3.994546693933197,
+      "grad_norm": 0.7198411822319031,
+      "learning_rate": 0.0002,
+      "loss": 1.4615,
+      "step": 2930
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.9278366565704346,
+      "eval_runtime": 53.6567,
+      "eval_samples_per_second": 9.449,
+      "eval_steps_per_second": 1.193,
+      "step": 2934
+    },
+    {
+      "epoch": 4.008179959100205,
+      "grad_norm": 0.6498575210571289,
+      "learning_rate": 0.0002,
+      "loss": 1.3159,
+      "step": 2940
+    },
+    {
+      "epoch": 4.021813224267212,
+      "grad_norm": 0.865602433681488,
+      "learning_rate": 0.0002,
+      "loss": 1.2075,
+      "step": 2950
+    },
+    {
+      "epoch": 4.03544648943422,
+      "grad_norm": 0.8514999151229858,
+      "learning_rate": 0.0002,
+      "loss": 1.1744,
+      "step": 2960
+    },
+    {
+      "epoch": 4.049079754601227,
+      "grad_norm": 1.0677322149276733,
+      "learning_rate": 0.0002,
+      "loss": 1.1553,
+      "step": 2970
+    },
+    {
+      "epoch": 4.062713019768235,
+      "grad_norm": 1.0126488208770752,
+      "learning_rate": 0.0002,
+      "loss": 1.1962,
+      "step": 2980
+    },
+    {
+      "epoch": 4.076346284935242,
+      "grad_norm": 1.0008870363235474,
+      "learning_rate": 0.0002,
+      "loss": 1.1631,
+      "step": 2990
+    },
+    {
+      "epoch": 4.08997955010225,
+      "grad_norm": 0.7942054271697998,
+      "learning_rate": 0.0002,
+      "loss": 1.2154,
+      "step": 3000
+    },
+    {
+      "epoch": 4.103612815269257,
+      "grad_norm": 1.0482100248336792,
+      "learning_rate": 0.0002,
+      "loss": 1.214,
+      "step": 3010
+    },
+    {
+      "epoch": 4.1172460804362645,
+      "grad_norm": 1.0516992807388306,
+      "learning_rate": 0.0002,
+      "loss": 1.1999,
+      "step": 3020
+    },
+    {
+      "epoch": 4.130879345603272,
+      "grad_norm": 0.8144322037696838,
+      "learning_rate": 0.0002,
+      "loss": 1.2108,
+      "step": 3030
+    },
+    {
+      "epoch": 4.144512610770279,
+      "grad_norm": 0.952297568321228,
+      "learning_rate": 0.0002,
+      "loss": 1.1782,
+      "step": 3040
+    },
+    {
+      "epoch": 4.158145875937287,
+      "grad_norm": 1.007645606994629,
+      "learning_rate": 0.0002,
+      "loss": 1.2814,
+      "step": 3050
+    },
+    {
+      "epoch": 4.171779141104294,
+      "grad_norm": 1.0480353832244873,
+      "learning_rate": 0.0002,
+      "loss": 1.1731,
+      "step": 3060
+    },
+    {
+      "epoch": 4.185412406271302,
+      "grad_norm": 0.9270663857460022,
+      "learning_rate": 0.0002,
+      "loss": 1.196,
+      "step": 3070
+    },
+    {
+      "epoch": 4.199045671438309,
+      "grad_norm": 1.3415262699127197,
+      "learning_rate": 0.0002,
+      "loss": 1.2167,
+      "step": 3080
+    },
+    {
+      "epoch": 4.212678936605317,
+      "grad_norm": 1.167606234550476,
+      "learning_rate": 0.0002,
+      "loss": 1.2601,
+      "step": 3090
+    },
+    {
+      "epoch": 4.226312201772324,
+      "grad_norm": 0.9418690800666809,
+      "learning_rate": 0.0002,
+      "loss": 1.2605,
+      "step": 3100
+    },
+    {
+      "epoch": 4.239945466939332,
+      "grad_norm": 1.0885876417160034,
+      "learning_rate": 0.0002,
+      "loss": 1.2184,
+      "step": 3110
+    },
+    {
+      "epoch": 4.253578732106339,
+      "grad_norm": 0.9165483713150024,
+      "learning_rate": 0.0002,
+      "loss": 1.2594,
+      "step": 3120
+    },
+    {
+      "epoch": 4.267211997273347,
+      "grad_norm": 0.9154694080352783,
+      "learning_rate": 0.0002,
+      "loss": 1.2933,
+      "step": 3130
+    },
+    {
+      "epoch": 4.280845262440354,
+      "grad_norm": 1.100580096244812,
+      "learning_rate": 0.0002,
+      "loss": 1.2584,
+      "step": 3140
+    },
+    {
+      "epoch": 4.294478527607362,
+      "grad_norm": 0.9367576241493225,
+      "learning_rate": 0.0002,
+      "loss": 1.251,
+      "step": 3150
+    },
+    {
+      "epoch": 4.308111792774369,
+      "grad_norm": 0.9744015336036682,
+      "learning_rate": 0.0002,
+      "loss": 1.2032,
+      "step": 3160
+    },
+    {
+      "epoch": 4.321745057941377,
+      "grad_norm": 0.9865175485610962,
+      "learning_rate": 0.0002,
+      "loss": 1.2787,
+      "step": 3170
+    },
+    {
+      "epoch": 4.335378323108385,
+      "grad_norm": 1.0124907493591309,
+      "learning_rate": 0.0002,
+      "loss": 1.2161,
+      "step": 3180
+    },
+    {
+      "epoch": 4.349011588275392,
+      "grad_norm": 1.1044819355010986,
+      "learning_rate": 0.0002,
+      "loss": 1.2452,
+      "step": 3190
+    },
+    {
+      "epoch": 4.3626448534424,
+      "grad_norm": 0.9305577278137207,
+      "learning_rate": 0.0002,
+      "loss": 1.2483,
+      "step": 3200
+    },
+    {
+      "epoch": 4.376278118609407,
+      "grad_norm": 0.969265341758728,
+      "learning_rate": 0.0002,
+      "loss": 1.2101,
+      "step": 3210
+    },
+    {
+      "epoch": 4.389911383776415,
+      "grad_norm": 1.0671923160552979,
+      "learning_rate": 0.0002,
+      "loss": 1.2355,
+      "step": 3220
+    },
+    {
+      "epoch": 4.403544648943422,
+      "grad_norm": 0.9440539479255676,
+      "learning_rate": 0.0002,
+      "loss": 1.2259,
+      "step": 3230
+    },
+    {
+      "epoch": 4.41717791411043,
+      "grad_norm": 0.9824562668800354,
+      "learning_rate": 0.0002,
+      "loss": 1.1706,
+      "step": 3240
+    },
+    {
+      "epoch": 4.430811179277437,
+      "grad_norm": 1.0245535373687744,
+      "learning_rate": 0.0002,
+      "loss": 1.2234,
+      "step": 3250
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.9629312753677368,
+      "learning_rate": 0.0002,
+      "loss": 1.2713,
+      "step": 3260
+    },
+    {
+      "epoch": 4.458077709611452,
+      "grad_norm": 1.1556470394134521,
+      "learning_rate": 0.0002,
+      "loss": 1.2689,
+      "step": 3270
+    },
+    {
+      "epoch": 4.47171097477846,
+      "grad_norm": 0.9796679019927979,
+      "learning_rate": 0.0002,
+      "loss": 1.2214,
+      "step": 3280
+    },
+    {
+      "epoch": 4.485344239945467,
+      "grad_norm": 0.9030535221099854,
+      "learning_rate": 0.0002,
+      "loss": 1.2823,
+      "step": 3290
+    },
+    {
+      "epoch": 4.4989775051124745,
+      "grad_norm": 0.9142820835113525,
+      "learning_rate": 0.0002,
+      "loss": 1.2111,
+      "step": 3300
+    },
+    {
+      "epoch": 4.5126107702794815,
+      "grad_norm": 0.966867208480835,
+      "learning_rate": 0.0002,
+      "loss": 1.2398,
+      "step": 3310
+    },
+    {
+      "epoch": 4.5262440354464895,
+      "grad_norm": 1.0127079486846924,
+      "learning_rate": 0.0002,
+      "loss": 1.2537,
+      "step": 3320
+    },
+    {
+      "epoch": 4.539877300613497,
+      "grad_norm": 1.055506706237793,
+      "learning_rate": 0.0002,
+      "loss": 1.2059,
+      "step": 3330
+    },
+    {
+      "epoch": 4.553510565780504,
+      "grad_norm": 0.9831468462944031,
+      "learning_rate": 0.0002,
+      "loss": 1.2958,
+      "step": 3340
+    },
+    {
+      "epoch": 4.567143830947512,
+      "grad_norm": 0.9304661154747009,
+      "learning_rate": 0.0002,
+      "loss": 1.2643,
+      "step": 3350
+    },
+    {
+      "epoch": 4.580777096114519,
+      "grad_norm": 0.9369107484817505,
+      "learning_rate": 0.0002,
+      "loss": 1.3621,
+      "step": 3360
+    },
+    {
+      "epoch": 4.594410361281527,
+      "grad_norm": 1.009506344795227,
+      "learning_rate": 0.0002,
+      "loss": 1.2301,
+      "step": 3370
+    },
+    {
+      "epoch": 4.608043626448534,
+      "grad_norm": 1.0575741529464722,
+      "learning_rate": 0.0002,
+      "loss": 1.2535,
+      "step": 3380
+    },
+    {
+      "epoch": 4.621676891615542,
+      "grad_norm": 0.9102860689163208,
+      "learning_rate": 0.0002,
+      "loss": 1.1914,
+      "step": 3390
+    },
+    {
+      "epoch": 4.635310156782549,
+      "grad_norm": 0.8111315965652466,
+      "learning_rate": 0.0002,
+      "loss": 1.3156,
+      "step": 3400
+    },
+    {
+      "epoch": 4.648943421949557,
+      "grad_norm": 0.9459649920463562,
+      "learning_rate": 0.0002,
+      "loss": 1.3103,
+      "step": 3410
+    },
+    {
+      "epoch": 4.662576687116564,
+      "grad_norm": 0.9709545969963074,
+      "learning_rate": 0.0002,
+      "loss": 1.3146,
+      "step": 3420
+    },
+    {
+      "epoch": 4.676209952283572,
+      "grad_norm": 0.9909247159957886,
+      "learning_rate": 0.0002,
+      "loss": 1.2958,
+      "step": 3430
+    },
+    {
+      "epoch": 4.689843217450579,
+      "grad_norm": 0.9094610810279846,
+      "learning_rate": 0.0002,
+      "loss": 1.3186,
+      "step": 3440
+    },
+    {
+      "epoch": 4.703476482617587,
+      "grad_norm": 0.9012220501899719,
+      "learning_rate": 0.0002,
+      "loss": 1.3397,
+      "step": 3450
+    },
+    {
+      "epoch": 4.717109747784594,
+      "grad_norm": 0.8669242858886719,
+      "learning_rate": 0.0002,
+      "loss": 1.2595,
+      "step": 3460
+    },
+    {
+      "epoch": 4.730743012951602,
+      "grad_norm": 0.9753699898719788,
+      "learning_rate": 0.0002,
+      "loss": 1.2762,
+      "step": 3470
+    },
+    {
+      "epoch": 4.74437627811861,
+      "grad_norm": 1.0252684354782104,
+      "learning_rate": 0.0002,
+      "loss": 1.2371,
+      "step": 3480
+    },
+    {
+      "epoch": 4.758009543285617,
+      "grad_norm": 1.208098292350769,
+      "learning_rate": 0.0002,
+      "loss": 1.2536,
+      "step": 3490
+    },
+    {
+      "epoch": 4.771642808452625,
+      "grad_norm": 0.8632914423942566,
+      "learning_rate": 0.0002,
+      "loss": 1.2256,
+      "step": 3500
+    },
+    {
+      "epoch": 4.785276073619632,
+      "grad_norm": 1.0084818601608276,
+      "learning_rate": 0.0002,
+      "loss": 1.3062,
+      "step": 3510
+    },
+    {
+      "epoch": 4.79890933878664,
+      "grad_norm": 0.9095172882080078,
+      "learning_rate": 0.0002,
+      "loss": 1.3004,
+      "step": 3520
+    },
+    {
+      "epoch": 4.812542603953647,
+      "grad_norm": 0.9740135669708252,
+      "learning_rate": 0.0002,
+      "loss": 1.263,
+      "step": 3530
+    },
+    {
+      "epoch": 4.826175869120655,
+      "grad_norm": 0.8862348794937134,
+      "learning_rate": 0.0002,
+      "loss": 1.2816,
+      "step": 3540
+    },
+    {
+      "epoch": 4.839809134287662,
+      "grad_norm": 1.0761774778366089,
+      "learning_rate": 0.0002,
+      "loss": 1.2275,
+      "step": 3550
+    },
+    {
+      "epoch": 4.85344239945467,
+      "grad_norm": 1.0134117603302002,
+      "learning_rate": 0.0002,
+      "loss": 1.2257,
+      "step": 3560
+    },
+    {
+      "epoch": 4.867075664621677,
+      "grad_norm": 0.9262851476669312,
+      "learning_rate": 0.0002,
+      "loss": 1.2904,
+      "step": 3570
+    },
+    {
+      "epoch": 4.8807089297886845,
+      "grad_norm": 0.9518504738807678,
+      "learning_rate": 0.0002,
+      "loss": 1.1466,
+      "step": 3580
+    },
+    {
+      "epoch": 4.894342194955692,
+      "grad_norm": 1.10103178024292,
+      "learning_rate": 0.0002,
+      "loss": 1.2741,
+      "step": 3590
+    },
+    {
+      "epoch": 4.9079754601226995,
+      "grad_norm": 1.0133225917816162,
+      "learning_rate": 0.0002,
+      "loss": 1.2592,
+      "step": 3600
+    },
+    {
+      "epoch": 4.9216087252897065,
+      "grad_norm": 0.9637737274169922,
+      "learning_rate": 0.0002,
+      "loss": 1.2856,
+      "step": 3610
+    },
+    {
+      "epoch": 4.935241990456714,
+      "grad_norm": 0.9800633192062378,
+      "learning_rate": 0.0002,
+      "loss": 1.2991,
+      "step": 3620
+    },
+    {
+      "epoch": 4.948875255623722,
+      "grad_norm": 1.0065973997116089,
+      "learning_rate": 0.0002,
+      "loss": 1.2872,
+      "step": 3630
+    },
+    {
+      "epoch": 4.962508520790729,
+      "grad_norm": 0.9354690313339233,
+      "learning_rate": 0.0002,
+      "loss": 1.2408,
+      "step": 3640
+    },
+    {
+      "epoch": 4.976141785957737,
+      "grad_norm": 0.9744119048118591,
+      "learning_rate": 0.0002,
+      "loss": 1.291,
+      "step": 3650
+    },
+    {
+      "epoch": 4.989775051124744,
+      "grad_norm": 0.9357708096504211,
+      "learning_rate": 0.0002,
+      "loss": 1.2513,
+      "step": 3660
+    },
+    {
+      "epoch": 4.999318336741649,
+      "eval_loss": 2.0763096809387207,
+      "eval_runtime": 53.6578,
+      "eval_samples_per_second": 9.449,
+      "eval_steps_per_second": 1.193,
+      "step": 3667
+    },
+    {
+      "epoch": 5.003408316291752,
+      "grad_norm": 1.3171669244766235,
+      "learning_rate": 0.0002,
+      "loss": 1.2323,
+      "step": 3670
+    },
+    {
+      "epoch": 5.017041581458759,
+      "grad_norm": 1.4427374601364136,
+      "learning_rate": 0.0002,
+      "loss": 0.9509,
+      "step": 3680
+    },
+    {
+      "epoch": 5.030674846625767,
+      "grad_norm": 0.9313797354698181,
+      "learning_rate": 0.0002,
+      "loss": 1.011,
+      "step": 3690
+    },
+    {
+      "epoch": 5.044308111792774,
+      "grad_norm": 1.417641282081604,
+      "learning_rate": 0.0002,
+      "loss": 0.9481,
+      "step": 3700
+    },
+    {
+      "epoch": 5.057941376959782,
+      "grad_norm": 1.097440242767334,
+      "learning_rate": 0.0002,
+      "loss": 0.9477,
+      "step": 3710
+    },
+    {
+      "epoch": 5.071574642126789,
+      "grad_norm": 1.4277986288070679,
+      "learning_rate": 0.0002,
+      "loss": 1.0416,
+      "step": 3720
+    },
+    {
+      "epoch": 5.085207907293797,
+      "grad_norm": 1.2520873546600342,
+      "learning_rate": 0.0002,
+      "loss": 0.9718,
+      "step": 3730
+    },
+    {
+      "epoch": 5.098841172460804,
+      "grad_norm": 1.39503812789917,
+      "learning_rate": 0.0002,
+      "loss": 0.9531,
+      "step": 3740
+    },
+    {
+      "epoch": 5.112474437627812,
+      "grad_norm": 1.2345329523086548,
+      "learning_rate": 0.0002,
+      "loss": 0.9658,
+      "step": 3750
+    },
+    {
+      "epoch": 5.126107702794819,
+      "grad_norm": 1.2700239419937134,
+      "learning_rate": 0.0002,
+      "loss": 1.0615,
+      "step": 3760
+    },
+    {
+      "epoch": 5.139740967961827,
+      "grad_norm": 1.5343066453933716,
+      "learning_rate": 0.0002,
+      "loss": 0.993,
+      "step": 3770
+    },
+    {
+      "epoch": 5.153374233128835,
+      "grad_norm": 1.4191608428955078,
+      "learning_rate": 0.0002,
+      "loss": 0.9378,
+      "step": 3780
+    },
+    {
+      "epoch": 5.167007498295842,
+      "grad_norm": 1.4591023921966553,
+      "learning_rate": 0.0002,
+      "loss": 1.0179,
+      "step": 3790
+    },
+    {
+      "epoch": 5.18064076346285,
+      "grad_norm": 1.6158121824264526,
+      "learning_rate": 0.0002,
+      "loss": 1.0143,
+      "step": 3800
+    },
+    {
+      "epoch": 5.194274028629857,
+      "grad_norm": 1.6077582836151123,
+      "learning_rate": 0.0002,
+      "loss": 1.0056,
+      "step": 3810
+    },
+    {
+      "epoch": 5.207907293796865,
+      "grad_norm": 1.2815653085708618,
+      "learning_rate": 0.0002,
+      "loss": 0.9711,
+      "step": 3820
+    },
+    {
+      "epoch": 5.221540558963872,
+      "grad_norm": 1.2427219152450562,
+      "learning_rate": 0.0002,
+      "loss": 1.0131,
+      "step": 3830
+    },
+    {
+      "epoch": 5.23517382413088,
+      "grad_norm": 1.3013232946395874,
+      "learning_rate": 0.0002,
+      "loss": 0.9901,
+      "step": 3840
+    },
+    {
+      "epoch": 5.248807089297887,
+      "grad_norm": 1.4643588066101074,
+      "learning_rate": 0.0002,
+      "loss": 0.9862,
+      "step": 3850
+    },
+    {
+      "epoch": 5.2624403544648946,
+      "grad_norm": 1.2571916580200195,
+      "learning_rate": 0.0002,
+      "loss": 1.0149,
+      "step": 3860
+    },
+    {
+      "epoch": 5.276073619631902,
+      "grad_norm": 1.226682186126709,
+      "learning_rate": 0.0002,
+      "loss": 0.9686,
+      "step": 3870
+    },
+    {
+      "epoch": 5.2897068847989095,
+      "grad_norm": 1.2541271448135376,
+      "learning_rate": 0.0002,
+      "loss": 0.9417,
+      "step": 3880
+    },
+    {
+      "epoch": 5.3033401499659165,
+      "grad_norm": 1.2340261936187744,
+      "learning_rate": 0.0002,
+      "loss": 0.9767,
+      "step": 3890
+    },
+    {
+      "epoch": 5.316973415132924,
+      "grad_norm": 1.345527172088623,
+      "learning_rate": 0.0002,
+      "loss": 1.0173,
+      "step": 3900
+    },
+    {
+      "epoch": 5.3306066802999315,
+      "grad_norm": 1.2128909826278687,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 3910
+    },
+    {
+      "epoch": 5.344239945466939,
+      "grad_norm": 1.3052637577056885,
+      "learning_rate": 0.0002,
+      "loss": 1.0002,
+      "step": 3920
+    },
+    {
+      "epoch": 5.357873210633947,
+      "grad_norm": 1.1017392873764038,
+      "learning_rate": 0.0002,
+      "loss": 0.9754,
+      "step": 3930
+    },
+    {
+      "epoch": 5.371506475800954,
+      "grad_norm": 1.26950204372406,
+      "learning_rate": 0.0002,
+      "loss": 1.0579,
+      "step": 3940
+    },
+    {
+      "epoch": 5.385139740967962,
+      "grad_norm": 1.3372546434402466,
+      "learning_rate": 0.0002,
+      "loss": 1.0816,
+      "step": 3950
+    },
+    {
+      "epoch": 5.398773006134969,
+      "grad_norm": 1.3115156888961792,
+      "learning_rate": 0.0002,
+      "loss": 1.0529,
+      "step": 3960
+    },
+    {
+      "epoch": 5.412406271301977,
+      "grad_norm": 1.3511474132537842,
+      "learning_rate": 0.0002,
+      "loss": 1.1179,
+      "step": 3970
+    },
+    {
+      "epoch": 5.426039536468984,
+      "grad_norm": 1.1001893281936646,
+      "learning_rate": 0.0002,
+      "loss": 1.0352,
+      "step": 3980
+    },
+    {
+      "epoch": 5.439672801635992,
+      "grad_norm": 1.2810745239257812,
+      "learning_rate": 0.0002,
+      "loss": 1.0855,
+      "step": 3990
+    },
+    {
+      "epoch": 5.453306066802999,
+      "grad_norm": 1.2999306917190552,
+      "learning_rate": 0.0002,
+      "loss": 1.0573,
+      "step": 4000
+    },
+    {
+      "epoch": 5.466939331970007,
+      "grad_norm": 1.172553300857544,
+      "learning_rate": 0.0002,
+      "loss": 1.0073,
+      "step": 4010
+    },
+    {
+      "epoch": 5.480572597137014,
+      "grad_norm": 1.1483557224273682,
+      "learning_rate": 0.0002,
+      "loss": 1.003,
+      "step": 4020
+    },
+    {
+      "epoch": 5.494205862304022,
+      "grad_norm": 1.4148036241531372,
+      "learning_rate": 0.0002,
+      "loss": 1.0704,
+      "step": 4030
+    },
+    {
+      "epoch": 5.507839127471029,
+      "grad_norm": 1.1611121892929077,
+      "learning_rate": 0.0002,
+      "loss": 1.0519,
+      "step": 4040
+    },
+    {
+      "epoch": 5.521472392638037,
+      "grad_norm": 1.3837119340896606,
+      "learning_rate": 0.0002,
+      "loss": 1.0775,
+      "step": 4050
+    },
+    {
+      "epoch": 5.535105657805044,
+      "grad_norm": 1.3025696277618408,
+      "learning_rate": 0.0002,
+      "loss": 1.0257,
+      "step": 4060
+    },
+    {
+      "epoch": 5.548738922972052,
+      "grad_norm": 1.348091959953308,
+      "learning_rate": 0.0002,
+      "loss": 1.0628,
+      "step": 4070
+    },
+    {
+      "epoch": 5.56237218813906,
+      "grad_norm": 1.3463449478149414,
+      "learning_rate": 0.0002,
+      "loss": 1.0447,
+      "step": 4080
+    },
+    {
+      "epoch": 5.576005453306067,
+      "grad_norm": 1.3904176950454712,
+      "learning_rate": 0.0002,
+      "loss": 1.039,
+      "step": 4090
+    },
+    {
+      "epoch": 5.589638718473074,
+      "grad_norm": 1.2737950086593628,
+      "learning_rate": 0.0002,
+      "loss": 1.0963,
+      "step": 4100
+    },
+    {
+      "epoch": 5.603271983640082,
+      "grad_norm": 1.3311827182769775,
+      "learning_rate": 0.0002,
+      "loss": 1.0441,
+      "step": 4110
+    },
+    {
+      "epoch": 5.61690524880709,
+      "grad_norm": 1.24485182762146,
+      "learning_rate": 0.0002,
+      "loss": 1.0521,
+      "step": 4120
+    },
+    {
+      "epoch": 5.630538513974097,
+      "grad_norm": 1.2724957466125488,
+      "learning_rate": 0.0002,
+      "loss": 1.1103,
+      "step": 4130
+    },
+    {
+      "epoch": 5.644171779141105,
+      "grad_norm": 1.3439847230911255,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 4140
+    },
+    {
+      "epoch": 5.657805044308112,
+      "grad_norm": 1.372359037399292,
+      "learning_rate": 0.0002,
+      "loss": 1.0257,
+      "step": 4150
+    },
+    {
+      "epoch": 5.6714383094751195,
+      "grad_norm": 1.2322949171066284,
+      "learning_rate": 0.0002,
+      "loss": 1.0475,
+      "step": 4160
+    },
+    {
+      "epoch": 5.6850715746421265,
+      "grad_norm": 1.4859193563461304,
+      "learning_rate": 0.0002,
+      "loss": 1.0465,
+      "step": 4170
+    },
+    {
+      "epoch": 5.6987048398091344,
+      "grad_norm": 1.4318448305130005,
+      "learning_rate": 0.0002,
+      "loss": 1.1569,
+      "step": 4180
+    },
+    {
+      "epoch": 5.7123381049761415,
+      "grad_norm": 1.1533565521240234,
+      "learning_rate": 0.0002,
+      "loss": 1.017,
+      "step": 4190
+    },
+    {
+      "epoch": 5.725971370143149,
+      "grad_norm": 1.3009696006774902,
+      "learning_rate": 0.0002,
+      "loss": 1.0948,
+      "step": 4200
+    },
+    {
+      "epoch": 5.739604635310156,
+      "grad_norm": 1.3972162008285522,
+      "learning_rate": 0.0002,
+      "loss": 1.1229,
+      "step": 4210
+    },
+    {
+      "epoch": 5.753237900477164,
+      "grad_norm": 1.2142186164855957,
+      "learning_rate": 0.0002,
+      "loss": 1.033,
+      "step": 4220
+    },
+    {
+      "epoch": 5.766871165644172,
+      "grad_norm": 1.401191234588623,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 4230
+    },
+    {
+      "epoch": 5.780504430811179,
+      "grad_norm": 1.4124404191970825,
+      "learning_rate": 0.0002,
+      "loss": 1.0722,
+      "step": 4240
+    },
+    {
+      "epoch": 5.794137695978186,
+      "grad_norm": 1.3488332033157349,
+      "learning_rate": 0.0002,
+      "loss": 1.0826,
+      "step": 4250
+    },
+    {
+      "epoch": 5.807770961145194,
+      "grad_norm": 1.3671752214431763,
+      "learning_rate": 0.0002,
+      "loss": 1.0599,
+      "step": 4260
+    },
+    {
+      "epoch": 5.821404226312202,
+      "grad_norm": 1.2608201503753662,
+      "learning_rate": 0.0002,
+      "loss": 1.1294,
+      "step": 4270
+    },
+    {
+      "epoch": 5.835037491479209,
+      "grad_norm": 1.1814045906066895,
+      "learning_rate": 0.0002,
+      "loss": 1.1216,
+      "step": 4280
+    },
+    {
+      "epoch": 5.848670756646217,
+      "grad_norm": 1.4139586687088013,
+      "learning_rate": 0.0002,
+      "loss": 1.0973,
+      "step": 4290
+    },
+    {
+      "epoch": 5.862304021813224,
+      "grad_norm": 1.34248948097229,
+      "learning_rate": 0.0002,
+      "loss": 1.0656,
+      "step": 4300
+    },
+    {
+      "epoch": 5.875937286980232,
+      "grad_norm": 1.1428139209747314,
+      "learning_rate": 0.0002,
+      "loss": 1.0791,
+      "step": 4310
+    },
+    {
+      "epoch": 5.889570552147239,
+      "grad_norm": 1.1941087245941162,
+      "learning_rate": 0.0002,
+      "loss": 1.0556,
+      "step": 4320
+    },
+    {
+      "epoch": 5.903203817314247,
+      "grad_norm": 1.2374001741409302,
+      "learning_rate": 0.0002,
+      "loss": 1.1089,
+      "step": 4330
+    },
+    {
+      "epoch": 5.916837082481254,
+      "grad_norm": 1.4314988851547241,
+      "learning_rate": 0.0002,
+      "loss": 1.0802,
+      "step": 4340
+    },
+    {
+      "epoch": 5.930470347648262,
+      "grad_norm": 1.1286126375198364,
+      "learning_rate": 0.0002,
+      "loss": 1.133,
+      "step": 4350
+    },
+    {
+      "epoch": 5.944103612815269,
+      "grad_norm": 1.25884211063385,
+      "learning_rate": 0.0002,
+      "loss": 1.0807,
+      "step": 4360
+    },
+    {
+      "epoch": 5.957736877982277,
+      "grad_norm": 1.223357915878296,
+      "learning_rate": 0.0002,
+      "loss": 1.1189,
+      "step": 4370
+    },
+    {
+      "epoch": 5.971370143149285,
+      "grad_norm": 1.2173810005187988,
+      "learning_rate": 0.0002,
+      "loss": 1.1335,
+      "step": 4380
+    },
+    {
+      "epoch": 5.985003408316292,
+      "grad_norm": 1.3152292966842651,
+      "learning_rate": 0.0002,
+      "loss": 1.1201,
+      "step": 4390
+    },
+    {
+      "epoch": 5.998636673483299,
+      "grad_norm": 1.5576739311218262,
+      "learning_rate": 0.0002,
+      "loss": 1.1456,
+      "step": 4400
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.3435311317443848,
+      "eval_runtime": 53.6362,
+      "eval_samples_per_second": 9.453,
+      "eval_steps_per_second": 1.193,
+      "step": 4401
+    },
+    {
+      "epoch": 6.012269938650307,
+      "grad_norm": 2.027981758117676,
+      "learning_rate": 0.0002,
+      "loss": 0.8618,
+      "step": 4410
+    },
+    {
+      "epoch": 6.025903203817315,
+      "grad_norm": 1.4775491952896118,
+      "learning_rate": 0.0002,
+      "loss": 0.7702,
+      "step": 4420
+    },
+    {
+      "epoch": 6.039536468984322,
+      "grad_norm": 1.6902967691421509,
+      "learning_rate": 0.0002,
+      "loss": 0.8042,
+      "step": 4430
+    },
+    {
+      "epoch": 6.0531697341513295,
+      "grad_norm": 1.2506479024887085,
+      "learning_rate": 0.0002,
+      "loss": 0.7363,
+      "step": 4440
+    },
+    {
+      "epoch": 6.0668029993183366,
+      "grad_norm": 1.5935661792755127,
+      "learning_rate": 0.0002,
+      "loss": 0.7653,
+      "step": 4450
+    },
+    {
+      "epoch": 6.0804362644853445,
+      "grad_norm": 1.2966011762619019,
+      "learning_rate": 0.0002,
+      "loss": 0.7869,
+      "step": 4460
+    },
+    {
+      "epoch": 6.0940695296523515,
+      "grad_norm": 1.5247948169708252,
+      "learning_rate": 0.0002,
+      "loss": 0.7186,
+      "step": 4470
+    },
+    {
+      "epoch": 6.107702794819359,
+      "grad_norm": 1.6415225267410278,
+      "learning_rate": 0.0002,
+      "loss": 0.7864,
+      "step": 4480
+    },
+    {
+      "epoch": 6.121336059986366,
+      "grad_norm": 1.5510778427124023,
+      "learning_rate": 0.0002,
+      "loss": 0.7561,
+      "step": 4490
+    },
+    {
+      "epoch": 6.134969325153374,
+      "grad_norm": 1.361097812652588,
+      "learning_rate": 0.0002,
+      "loss": 0.7628,
+      "step": 4500
+    },
+    {
+      "epoch": 6.148602590320381,
+      "grad_norm": 1.8347383737564087,
+      "learning_rate": 0.0002,
+      "loss": 0.8053,
+      "step": 4510
+    },
+    {
+      "epoch": 6.162235855487389,
+      "grad_norm": 1.570560097694397,
+      "learning_rate": 0.0002,
+      "loss": 0.8074,
+      "step": 4520
+    },
+    {
+      "epoch": 6.175869120654396,
+      "grad_norm": 1.517993688583374,
+      "learning_rate": 0.0002,
+      "loss": 0.7536,
+      "step": 4530
+    },
+    {
+      "epoch": 6.189502385821404,
+      "grad_norm": 1.4517489671707153,
+      "learning_rate": 0.0002,
+      "loss": 0.8028,
+      "step": 4540
+    },
+    {
+      "epoch": 6.203135650988412,
+      "grad_norm": 1.557098627090454,
+      "learning_rate": 0.0002,
+      "loss": 0.8633,
+      "step": 4550
+    },
+    {
+      "epoch": 6.216768916155419,
+      "grad_norm": 1.7379891872406006,
+      "learning_rate": 0.0002,
+      "loss": 0.7704,
+      "step": 4560
+    },
+    {
+      "epoch": 6.230402181322427,
+      "grad_norm": 2.2292542457580566,
+      "learning_rate": 0.0002,
+      "loss": 0.7341,
+      "step": 4570
+    },
+    {
+      "epoch": 6.244035446489434,
+      "grad_norm": 1.834366798400879,
+      "learning_rate": 0.0002,
+      "loss": 0.7883,
+      "step": 4580
+    },
+    {
+      "epoch": 6.257668711656442,
+      "grad_norm": 1.6755090951919556,
+      "learning_rate": 0.0002,
+      "loss": 0.8222,
+      "step": 4590
+    },
+    {
+      "epoch": 6.271301976823449,
+      "grad_norm": 1.828898549079895,
+      "learning_rate": 0.0002,
+      "loss": 0.8245,
+      "step": 4600
+    },
+    {
+      "epoch": 6.284935241990457,
+      "grad_norm": 1.9773457050323486,
+      "learning_rate": 0.0002,
+      "loss": 0.8116,
+      "step": 4610
+    },
+    {
+      "epoch": 6.298568507157464,
+      "grad_norm": 1.533369541168213,
+      "learning_rate": 0.0002,
+      "loss": 0.811,
+      "step": 4620
+    },
+    {
+      "epoch": 6.312201772324472,
+      "grad_norm": 1.5432997941970825,
+      "learning_rate": 0.0002,
+      "loss": 0.807,
+      "step": 4630
+    },
+    {
+      "epoch": 6.325835037491479,
+      "grad_norm": 1.6686866283416748,
+      "learning_rate": 0.0002,
+      "loss": 0.818,
+      "step": 4640
+    },
+    {
+      "epoch": 6.339468302658487,
+      "grad_norm": 1.545304298400879,
+      "learning_rate": 0.0002,
+      "loss": 0.8656,
+      "step": 4650
+    },
+    {
+      "epoch": 6.353101567825494,
+      "grad_norm": 1.5981945991516113,
+      "learning_rate": 0.0002,
+      "loss": 0.8239,
+      "step": 4660
+    },
+    {
+      "epoch": 6.366734832992502,
+      "grad_norm": 1.6973154544830322,
+      "learning_rate": 0.0002,
+      "loss": 0.8162,
+      "step": 4670
+    },
+    {
+      "epoch": 6.38036809815951,
+      "grad_norm": 1.6782612800598145,
+      "learning_rate": 0.0002,
+      "loss": 0.8377,
+      "step": 4680
+    },
+    {
+      "epoch": 6.394001363326517,
+      "grad_norm": 1.5710086822509766,
+      "learning_rate": 0.0002,
+      "loss": 0.8185,
+      "step": 4690
+    },
+    {
+      "epoch": 6.407634628493525,
+      "grad_norm": 1.7241147756576538,
+      "learning_rate": 0.0002,
+      "loss": 0.7948,
+      "step": 4700
+    },
+    {
+      "epoch": 6.421267893660532,
+      "grad_norm": 1.7736736536026,
+      "learning_rate": 0.0002,
+      "loss": 0.8768,
+      "step": 4710
+    },
+    {
+      "epoch": 6.4349011588275395,
+      "grad_norm": 1.7924901247024536,
+      "learning_rate": 0.0002,
+      "loss": 0.8607,
+      "step": 4720
+    },
+    {
+      "epoch": 6.448534423994547,
+      "grad_norm": 1.4030500650405884,
+      "learning_rate": 0.0002,
+      "loss": 0.832,
+      "step": 4730
+    },
+    {
+      "epoch": 6.4621676891615545,
+      "grad_norm": 1.6925519704818726,
+      "learning_rate": 0.0002,
+      "loss": 0.8806,
+      "step": 4740
+    },
+    {
+      "epoch": 6.4758009543285615,
+      "grad_norm": 1.362905502319336,
+      "learning_rate": 0.0002,
+      "loss": 0.8556,
+      "step": 4750
+    },
+    {
+      "epoch": 6.489434219495569,
+      "grad_norm": 1.5281150341033936,
+      "learning_rate": 0.0002,
+      "loss": 0.838,
+      "step": 4760
+    },
+    {
+      "epoch": 6.5030674846625764,
+      "grad_norm": 1.524671196937561,
+      "learning_rate": 0.0002,
+      "loss": 0.8396,
+      "step": 4770
+    },
+    {
+      "epoch": 6.516700749829584,
+      "grad_norm": 1.7029320001602173,
+      "learning_rate": 0.0002,
+      "loss": 0.8225,
+      "step": 4780
+    },
+    {
+      "epoch": 6.530334014996591,
+      "grad_norm": 1.4663511514663696,
+      "learning_rate": 0.0002,
+      "loss": 0.8377,
+      "step": 4790
+    },
+    {
+      "epoch": 6.543967280163599,
+      "grad_norm": 1.7682101726531982,
+      "learning_rate": 0.0002,
+      "loss": 0.8018,
+      "step": 4800
+    },
+    {
+      "epoch": 6.557600545330606,
+      "grad_norm": 1.6056565046310425,
+      "learning_rate": 0.0002,
+      "loss": 0.8318,
+      "step": 4810
+    },
+    {
+      "epoch": 6.571233810497614,
+      "grad_norm": 1.6552391052246094,
+      "learning_rate": 0.0002,
+      "loss": 0.8747,
+      "step": 4820
+    },
+    {
+      "epoch": 6.584867075664622,
+      "grad_norm": 1.4265215396881104,
+      "learning_rate": 0.0002,
+      "loss": 0.8559,
+      "step": 4830
+    },
+    {
+      "epoch": 6.598500340831629,
+      "grad_norm": 1.6225470304489136,
+      "learning_rate": 0.0002,
+      "loss": 0.8606,
+      "step": 4840
+    },
+    {
+      "epoch": 6.612133605998636,
+      "grad_norm": 1.6568684577941895,
+      "learning_rate": 0.0002,
+      "loss": 0.8817,
+      "step": 4850
+    },
+    {
+      "epoch": 6.625766871165644,
+      "grad_norm": 1.760115146636963,
+      "learning_rate": 0.0002,
+      "loss": 0.8825,
+      "step": 4860
+    },
+    {
+      "epoch": 6.639400136332652,
+      "grad_norm": 1.627966046333313,
+      "learning_rate": 0.0002,
+      "loss": 0.9227,
+      "step": 4870
+    },
+    {
+      "epoch": 6.653033401499659,
+      "grad_norm": 1.7053254842758179,
+      "learning_rate": 0.0002,
+      "loss": 0.8825,
+      "step": 4880
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 1.5339484214782715,
+      "learning_rate": 0.0002,
+      "loss": 0.857,
+      "step": 4890
+    },
+    {
+      "epoch": 6.680299931833674,
+      "grad_norm": 1.5594874620437622,
+      "learning_rate": 0.0002,
+      "loss": 0.8482,
+      "step": 4900
+    },
+    {
+      "epoch": 6.693933197000682,
+      "grad_norm": 1.5322152376174927,
+      "learning_rate": 0.0002,
+      "loss": 0.842,
+      "step": 4910
+    },
+    {
+      "epoch": 6.707566462167689,
+      "grad_norm": 1.733410358428955,
+      "learning_rate": 0.0002,
+      "loss": 0.8049,
+      "step": 4920
+    },
+    {
+      "epoch": 6.721199727334697,
+      "grad_norm": 1.3626887798309326,
+      "learning_rate": 0.0002,
+      "loss": 0.9099,
+      "step": 4930
+    },
+    {
+      "epoch": 6.734832992501704,
+      "grad_norm": 1.6323494911193848,
+      "learning_rate": 0.0002,
+      "loss": 0.9481,
+      "step": 4940
+    },
+    {
+      "epoch": 6.748466257668712,
+      "grad_norm": 1.6548917293548584,
+      "learning_rate": 0.0002,
+      "loss": 0.8803,
+      "step": 4950
+    },
+    {
+      "epoch": 6.762099522835719,
+      "grad_norm": 1.7894278764724731,
+      "learning_rate": 0.0002,
+      "loss": 0.9149,
+      "step": 4960
+    },
+    {
+      "epoch": 6.775732788002727,
+      "grad_norm": 1.7960841655731201,
+      "learning_rate": 0.0002,
+      "loss": 0.9137,
+      "step": 4970
+    },
+    {
+      "epoch": 6.789366053169735,
+      "grad_norm": 1.4888852834701538,
+      "learning_rate": 0.0002,
+      "loss": 0.9088,
+      "step": 4980
+    },
+    {
+      "epoch": 6.802999318336742,
+      "grad_norm": 1.6368865966796875,
+      "learning_rate": 0.0002,
+      "loss": 0.9495,
+      "step": 4990
+    },
+    {
+      "epoch": 6.816632583503749,
+      "grad_norm": 1.7106667757034302,
+      "learning_rate": 0.0002,
+      "loss": 0.9939,
+      "step": 5000
+    },
+    {
+      "epoch": 6.830265848670757,
+      "grad_norm": 4.131956100463867,
+      "learning_rate": 0.0002,
+      "loss": 0.8551,
+      "step": 5010
+    },
+    {
+      "epoch": 6.8438991138377645,
+      "grad_norm": 1.6357536315917969,
+      "learning_rate": 0.0002,
+      "loss": 0.908,
+      "step": 5020
+    },
+    {
+      "epoch": 6.8575323790047715,
+      "grad_norm": 1.621524453163147,
+      "learning_rate": 0.0002,
+      "loss": 0.8661,
+      "step": 5030
+    },
+    {
+      "epoch": 6.871165644171779,
+      "grad_norm": 1.6400790214538574,
+      "learning_rate": 0.0002,
+      "loss": 0.9177,
+      "step": 5040
+    },
+    {
+      "epoch": 6.8847989093387865,
+      "grad_norm": 1.823006272315979,
+      "learning_rate": 0.0002,
+      "loss": 0.9204,
+      "step": 5050
+    },
+    {
+      "epoch": 6.898432174505794,
+      "grad_norm": 1.6328210830688477,
+      "learning_rate": 0.0002,
+      "loss": 0.9133,
+      "step": 5060
+    },
+    {
+      "epoch": 6.912065439672801,
+      "grad_norm": 1.3616089820861816,
+      "learning_rate": 0.0002,
+      "loss": 0.9138,
+      "step": 5070
+    },
+    {
+      "epoch": 6.925698704839809,
+      "grad_norm": 1.7202986478805542,
+      "learning_rate": 0.0002,
+      "loss": 0.8791,
+      "step": 5080
+    },
+    {
+      "epoch": 6.939331970006816,
+      "grad_norm": 1.8145297765731812,
+      "learning_rate": 0.0002,
+      "loss": 0.8331,
+      "step": 5090
+    },
+    {
+      "epoch": 6.952965235173824,
+      "grad_norm": 1.5432910919189453,
+      "learning_rate": 0.0002,
+      "loss": 0.861,
+      "step": 5100
+    },
+    {
+      "epoch": 6.966598500340831,
+      "grad_norm": 1.2784099578857422,
+      "learning_rate": 0.0002,
+      "loss": 0.9282,
+      "step": 5110
+    },
+    {
+      "epoch": 6.980231765507839,
+      "grad_norm": 1.556593894958496,
+      "learning_rate": 0.0002,
+      "loss": 0.9189,
+      "step": 5120
+    },
+    {
+      "epoch": 6.993865030674847,
+      "grad_norm": 1.5102856159210205,
+      "learning_rate": 0.0002,
+      "loss": 0.8961,
+      "step": 5130
+    },
+    {
+      "epoch": 6.999318336741649,
+      "eval_loss": 2.5376713275909424,
+      "eval_runtime": 53.6377,
+      "eval_samples_per_second": 9.452,
+      "eval_steps_per_second": 1.193,
+      "step": 5134
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5864,
+  "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": 2.6372715192778752e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/training_args.bin b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..da7142eb13ed7f8418e5055c63a0fe0ca5e1972b
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5134/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8beac9fdfb91726fdf7473c9e77541aa988c61dc8beaba03293eafbe9c0a376
+size 5560
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/README.md b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/adapter_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/adapter_model.safetensors b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f768e2b866ad8ca4e17f12ea49ff31c2a1602c35
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6864cf11d11ba889d3d40854fe86ffedbe4acbbedf5666c1ae0083cf7c365b
+size 143153376
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/optimizer.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0ed0f4a4563af7bf789dbd43ca6291f63688b98a
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:482ece62c7a685946e2fa4d395e6aa8c206323faa5afc76c7f1444078a9a18bf
+size 72886650
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/rng_state.pth b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e5755f6bdc50d684f7d2b2b869417b2febf68290
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d5dc405ada830755e50aca827264880526a3fa85ccd0b443aee777433ac61c
+size 14244
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/scheduler.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..aa9331c8327df58ec8fc04719d9a463d6bd6c7aa
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad4f28f2c8f846e2a022737f5565cc616369eb1401ac4bc8f8b6b79786bfbac
+size 1064
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/special_tokens_map.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/tokenizer.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/tokenizer.model b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/tokenizer_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/trainer_state.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..558f2c1c4d941f5fbaaef64c107ae7292753dff1
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/trainer_state.json
@@ -0,0 +1,4199 @@
+{
+  "best_metric": 1.8171186447143555,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733",
+  "epoch": 7.994546693933197,
+  "eval_steps": 10,
+  "global_step": 5864,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013633265167007498,
+      "grad_norm": 0.7714291214942932,
+      "learning_rate": 0.0002,
+      "loss": 3.0982,
+      "step": 10
+    },
+    {
+      "epoch": 0.027266530334014997,
+      "grad_norm": 0.5473978519439697,
+      "learning_rate": 0.0002,
+      "loss": 2.5206,
+      "step": 20
+    },
+    {
+      "epoch": 0.0408997955010225,
+      "grad_norm": 0.5452795624732971,
+      "learning_rate": 0.0002,
+      "loss": 2.3079,
+      "step": 30
+    },
+    {
+      "epoch": 0.054533060668029994,
+      "grad_norm": 0.5098028779029846,
+      "learning_rate": 0.0002,
+      "loss": 2.0019,
+      "step": 40
+    },
+    {
+      "epoch": 0.0681663258350375,
+      "grad_norm": 0.48062971234321594,
+      "learning_rate": 0.0002,
+      "loss": 1.9333,
+      "step": 50
+    },
+    {
+      "epoch": 0.081799591002045,
+      "grad_norm": 0.4505695104598999,
+      "learning_rate": 0.0002,
+      "loss": 1.9355,
+      "step": 60
+    },
+    {
+      "epoch": 0.09543285616905249,
+      "grad_norm": 0.41609591245651245,
+      "learning_rate": 0.0002,
+      "loss": 1.9312,
+      "step": 70
+    },
+    {
+      "epoch": 0.10906612133605999,
+      "grad_norm": 0.4323892593383789,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 80
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 0.4670293629169464,
+      "learning_rate": 0.0002,
+      "loss": 1.9294,
+      "step": 90
+    },
+    {
+      "epoch": 0.136332651670075,
+      "grad_norm": 0.40623316168785095,
+      "learning_rate": 0.0002,
+      "loss": 1.7946,
+      "step": 100
+    },
+    {
+      "epoch": 0.1499659168370825,
+      "grad_norm": 0.3620383143424988,
+      "learning_rate": 0.0002,
+      "loss": 1.8565,
+      "step": 110
+    },
+    {
+      "epoch": 0.16359918200409,
+      "grad_norm": 0.332218736410141,
+      "learning_rate": 0.0002,
+      "loss": 1.9238,
+      "step": 120
+    },
+    {
+      "epoch": 0.17723244717109748,
+      "grad_norm": 0.4004521667957306,
+      "learning_rate": 0.0002,
+      "loss": 1.93,
+      "step": 130
+    },
+    {
+      "epoch": 0.19086571233810498,
+      "grad_norm": 0.3698360323905945,
+      "learning_rate": 0.0002,
+      "loss": 1.7549,
+      "step": 140
+    },
+    {
+      "epoch": 0.20449897750511248,
+      "grad_norm": 0.3847949504852295,
+      "learning_rate": 0.0002,
+      "loss": 1.8771,
+      "step": 150
+    },
+    {
+      "epoch": 0.21813224267211997,
+      "grad_norm": 0.36843451857566833,
+      "learning_rate": 0.0002,
+      "loss": 1.8316,
+      "step": 160
+    },
+    {
+      "epoch": 0.23176550783912747,
+      "grad_norm": 0.37301021814346313,
+      "learning_rate": 0.0002,
+      "loss": 1.838,
+      "step": 170
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.3718886971473694,
+      "learning_rate": 0.0002,
+      "loss": 1.8909,
+      "step": 180
+    },
+    {
+      "epoch": 0.25903203817314246,
+      "grad_norm": 0.3088490962982178,
+      "learning_rate": 0.0002,
+      "loss": 1.8454,
+      "step": 190
+    },
+    {
+      "epoch": 0.27266530334015,
+      "grad_norm": 0.3611852526664734,
+      "learning_rate": 0.0002,
+      "loss": 1.9254,
+      "step": 200
+    },
+    {
+      "epoch": 0.28629856850715746,
+      "grad_norm": 0.36093324422836304,
+      "learning_rate": 0.0002,
+      "loss": 1.7844,
+      "step": 210
+    },
+    {
+      "epoch": 0.299931833674165,
+      "grad_norm": 0.3250400722026825,
+      "learning_rate": 0.0002,
+      "loss": 1.719,
+      "step": 220
+    },
+    {
+      "epoch": 0.31356509884117245,
+      "grad_norm": 0.3566756248474121,
+      "learning_rate": 0.0002,
+      "loss": 1.8729,
+      "step": 230
+    },
+    {
+      "epoch": 0.32719836400818,
+      "grad_norm": 0.32872408628463745,
+      "learning_rate": 0.0002,
+      "loss": 1.9259,
+      "step": 240
+    },
+    {
+      "epoch": 0.34083162917518744,
+      "grad_norm": 0.3983881175518036,
+      "learning_rate": 0.0002,
+      "loss": 1.9033,
+      "step": 250
+    },
+    {
+      "epoch": 0.35446489434219497,
+      "grad_norm": 0.3571510910987854,
+      "learning_rate": 0.0002,
+      "loss": 1.8588,
+      "step": 260
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 0.3036131262779236,
+      "learning_rate": 0.0002,
+      "loss": 1.8539,
+      "step": 270
+    },
+    {
+      "epoch": 0.38173142467620996,
+      "grad_norm": 0.36512863636016846,
+      "learning_rate": 0.0002,
+      "loss": 1.8572,
+      "step": 280
+    },
+    {
+      "epoch": 0.39536468984321743,
+      "grad_norm": 0.3429736793041229,
+      "learning_rate": 0.0002,
+      "loss": 1.8022,
+      "step": 290
+    },
+    {
+      "epoch": 0.40899795501022496,
+      "grad_norm": 0.3055964708328247,
+      "learning_rate": 0.0002,
+      "loss": 1.8754,
+      "step": 300
+    },
+    {
+      "epoch": 0.4226312201772324,
+      "grad_norm": 0.33801034092903137,
+      "learning_rate": 0.0002,
+      "loss": 1.8384,
+      "step": 310
+    },
+    {
+      "epoch": 0.43626448534423995,
+      "grad_norm": 0.348783016204834,
+      "learning_rate": 0.0002,
+      "loss": 1.7933,
+      "step": 320
+    },
+    {
+      "epoch": 0.4498977505112474,
+      "grad_norm": 0.3057514727115631,
+      "learning_rate": 0.0002,
+      "loss": 1.8451,
+      "step": 330
+    },
+    {
+      "epoch": 0.46353101567825494,
+      "grad_norm": 0.3849763572216034,
+      "learning_rate": 0.0002,
+      "loss": 1.8766,
+      "step": 340
+    },
+    {
+      "epoch": 0.47716428084526247,
+      "grad_norm": 0.30080053210258484,
+      "learning_rate": 0.0002,
+      "loss": 1.8073,
+      "step": 350
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.3595106303691864,
+      "learning_rate": 0.0002,
+      "loss": 1.8548,
+      "step": 360
+    },
+    {
+      "epoch": 0.5044308111792775,
+      "grad_norm": 0.31099820137023926,
+      "learning_rate": 0.0002,
+      "loss": 1.8232,
+      "step": 370
+    },
+    {
+      "epoch": 0.5180640763462849,
+      "grad_norm": 0.3157978355884552,
+      "learning_rate": 0.0002,
+      "loss": 1.7029,
+      "step": 380
+    },
+    {
+      "epoch": 0.5316973415132924,
+      "grad_norm": 0.27960965037345886,
+      "learning_rate": 0.0002,
+      "loss": 1.8265,
+      "step": 390
+    },
+    {
+      "epoch": 0.5453306066803,
+      "grad_norm": 0.3102385103702545,
+      "learning_rate": 0.0002,
+      "loss": 1.7414,
+      "step": 400
+    },
+    {
+      "epoch": 0.5589638718473074,
+      "grad_norm": 0.32828861474990845,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 410
+    },
+    {
+      "epoch": 0.5725971370143149,
+      "grad_norm": 0.29560017585754395,
+      "learning_rate": 0.0002,
+      "loss": 1.8165,
+      "step": 420
+    },
+    {
+      "epoch": 0.5862304021813224,
+      "grad_norm": 0.33316895365715027,
+      "learning_rate": 0.0002,
+      "loss": 1.9455,
+      "step": 430
+    },
+    {
+      "epoch": 0.59986366734833,
+      "grad_norm": 0.30420982837677,
+      "learning_rate": 0.0002,
+      "loss": 1.8241,
+      "step": 440
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 0.32619214057922363,
+      "learning_rate": 0.0002,
+      "loss": 1.7565,
+      "step": 450
+    },
+    {
+      "epoch": 0.6271301976823449,
+      "grad_norm": 0.3603750765323639,
+      "learning_rate": 0.0002,
+      "loss": 1.7945,
+      "step": 460
+    },
+    {
+      "epoch": 0.6407634628493524,
+      "grad_norm": 0.30834096670150757,
+      "learning_rate": 0.0002,
+      "loss": 1.7773,
+      "step": 470
+    },
+    {
+      "epoch": 0.65439672801636,
+      "grad_norm": 0.28756365180015564,
+      "learning_rate": 0.0002,
+      "loss": 1.8058,
+      "step": 480
+    },
+    {
+      "epoch": 0.6680299931833674,
+      "grad_norm": 0.2878406345844269,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 490
+    },
+    {
+      "epoch": 0.6816632583503749,
+      "grad_norm": 0.31329697370529175,
+      "learning_rate": 0.0002,
+      "loss": 1.8581,
+      "step": 500
+    },
+    {
+      "epoch": 0.6952965235173824,
+      "grad_norm": 0.3405822515487671,
+      "learning_rate": 0.0002,
+      "loss": 1.7886,
+      "step": 510
+    },
+    {
+      "epoch": 0.7089297886843899,
+      "grad_norm": 0.305560827255249,
+      "learning_rate": 0.0002,
+      "loss": 1.778,
+      "step": 520
+    },
+    {
+      "epoch": 0.7225630538513974,
+      "grad_norm": 0.2973416745662689,
+      "learning_rate": 0.0002,
+      "loss": 1.7592,
+      "step": 530
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 0.327303946018219,
+      "learning_rate": 0.0002,
+      "loss": 1.8223,
+      "step": 540
+    },
+    {
+      "epoch": 0.7498295841854125,
+      "grad_norm": 0.62595534324646,
+      "learning_rate": 0.0002,
+      "loss": 1.8591,
+      "step": 550
+    },
+    {
+      "epoch": 0.7634628493524199,
+      "grad_norm": 0.3129784166812897,
+      "learning_rate": 0.0002,
+      "loss": 1.7466,
+      "step": 560
+    },
+    {
+      "epoch": 0.7770961145194274,
+      "grad_norm": 0.32496583461761475,
+      "learning_rate": 0.0002,
+      "loss": 1.8035,
+      "step": 570
+    },
+    {
+      "epoch": 0.7907293796864349,
+      "grad_norm": 0.3098868131637573,
+      "learning_rate": 0.0002,
+      "loss": 1.7787,
+      "step": 580
+    },
+    {
+      "epoch": 0.8043626448534424,
+      "grad_norm": 0.30726853013038635,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 590
+    },
+    {
+      "epoch": 0.8179959100204499,
+      "grad_norm": 0.2964220643043518,
+      "learning_rate": 0.0002,
+      "loss": 1.7898,
+      "step": 600
+    },
+    {
+      "epoch": 0.8316291751874574,
+      "grad_norm": 0.32352274656295776,
+      "learning_rate": 0.0002,
+      "loss": 1.8114,
+      "step": 610
+    },
+    {
+      "epoch": 0.8452624403544649,
+      "grad_norm": 0.2938912510871887,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 620
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 0.295559823513031,
+      "learning_rate": 0.0002,
+      "loss": 1.7727,
+      "step": 630
+    },
+    {
+      "epoch": 0.8725289706884799,
+      "grad_norm": 0.34102028608322144,
+      "learning_rate": 0.0002,
+      "loss": 1.9,
+      "step": 640
+    },
+    {
+      "epoch": 0.8861622358554874,
+      "grad_norm": 0.29676181077957153,
+      "learning_rate": 0.0002,
+      "loss": 1.8006,
+      "step": 650
+    },
+    {
+      "epoch": 0.8997955010224948,
+      "grad_norm": 0.3108902871608734,
+      "learning_rate": 0.0002,
+      "loss": 1.8099,
+      "step": 660
+    },
+    {
+      "epoch": 0.9134287661895024,
+      "grad_norm": 0.2690821588039398,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 670
+    },
+    {
+      "epoch": 0.9270620313565099,
+      "grad_norm": 0.32752540707588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7881,
+      "step": 680
+    },
+    {
+      "epoch": 0.9406952965235174,
+      "grad_norm": 0.8029476404190063,
+      "learning_rate": 0.0002,
+      "loss": 1.7661,
+      "step": 690
+    },
+    {
+      "epoch": 0.9543285616905249,
+      "grad_norm": 0.30534422397613525,
+      "learning_rate": 0.0002,
+      "loss": 1.7733,
+      "step": 700
+    },
+    {
+      "epoch": 0.9679618268575324,
+      "grad_norm": 0.2899954319000244,
+      "learning_rate": 0.0002,
+      "loss": 1.7614,
+      "step": 710
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 0.28814372420310974,
+      "learning_rate": 0.0002,
+      "loss": 1.7845,
+      "step": 720
+    },
+    {
+      "epoch": 0.9952283571915473,
+      "grad_norm": 0.3061596751213074,
+      "learning_rate": 0.0002,
+      "loss": 1.8865,
+      "step": 730
+    },
+    {
+      "epoch": 0.9993183367416496,
+      "eval_loss": 1.8171186447143555,
+      "eval_runtime": 53.6047,
+      "eval_samples_per_second": 9.458,
+      "eval_steps_per_second": 1.194,
+      "step": 733
+    },
+    {
+      "epoch": 1.008861622358555,
+      "grad_norm": 0.3140897750854492,
+      "learning_rate": 0.0002,
+      "loss": 1.6202,
+      "step": 740
+    },
+    {
+      "epoch": 1.0224948875255624,
+      "grad_norm": 0.3346109390258789,
+      "learning_rate": 0.0002,
+      "loss": 1.8409,
+      "step": 750
+    },
+    {
+      "epoch": 1.0361281526925699,
+      "grad_norm": 0.3582976758480072,
+      "learning_rate": 0.0002,
+      "loss": 1.6777,
+      "step": 760
+    },
+    {
+      "epoch": 1.0497614178595773,
+      "grad_norm": 0.30408260226249695,
+      "learning_rate": 0.0002,
+      "loss": 1.7306,
+      "step": 770
+    },
+    {
+      "epoch": 1.0633946830265848,
+      "grad_norm": 0.323585569858551,
+      "learning_rate": 0.0002,
+      "loss": 1.6967,
+      "step": 780
+    },
+    {
+      "epoch": 1.0770279481935923,
+      "grad_norm": 0.3474137783050537,
+      "learning_rate": 0.0002,
+      "loss": 1.768,
+      "step": 790
+    },
+    {
+      "epoch": 1.0906612133606,
+      "grad_norm": 0.35721147060394287,
+      "learning_rate": 0.0002,
+      "loss": 1.6895,
+      "step": 800
+    },
+    {
+      "epoch": 1.1042944785276074,
+      "grad_norm": 0.35366931557655334,
+      "learning_rate": 0.0002,
+      "loss": 1.718,
+      "step": 810
+    },
+    {
+      "epoch": 1.117927743694615,
+      "grad_norm": 0.3250770568847656,
+      "learning_rate": 0.0002,
+      "loss": 1.6797,
+      "step": 820
+    },
+    {
+      "epoch": 1.1315610088616224,
+      "grad_norm": 0.3293766379356384,
+      "learning_rate": 0.0002,
+      "loss": 1.6383,
+      "step": 830
+    },
+    {
+      "epoch": 1.1451942740286298,
+      "grad_norm": 0.3380851745605469,
+      "learning_rate": 0.0002,
+      "loss": 1.7353,
+      "step": 840
+    },
+    {
+      "epoch": 1.1588275391956373,
+      "grad_norm": 0.32584455609321594,
+      "learning_rate": 0.0002,
+      "loss": 1.8236,
+      "step": 850
+    },
+    {
+      "epoch": 1.1724608043626448,
+      "grad_norm": 0.45700767636299133,
+      "learning_rate": 0.0002,
+      "loss": 1.6681,
+      "step": 860
+    },
+    {
+      "epoch": 1.1860940695296525,
+      "grad_norm": 0.30944544076919556,
+      "learning_rate": 0.0002,
+      "loss": 1.7494,
+      "step": 870
+    },
+    {
+      "epoch": 1.19972733469666,
+      "grad_norm": 0.3268151581287384,
+      "learning_rate": 0.0002,
+      "loss": 1.7426,
+      "step": 880
+    },
+    {
+      "epoch": 1.2133605998636674,
+      "grad_norm": 0.39972540736198425,
+      "learning_rate": 0.0002,
+      "loss": 1.7413,
+      "step": 890
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 0.7890929579734802,
+      "learning_rate": 0.0002,
+      "loss": 1.7481,
+      "step": 900
+    },
+    {
+      "epoch": 1.2406271301976823,
+      "grad_norm": 0.3439182639122009,
+      "learning_rate": 0.0002,
+      "loss": 1.7608,
+      "step": 910
+    },
+    {
+      "epoch": 1.2542603953646898,
+      "grad_norm": 0.3986225128173828,
+      "learning_rate": 0.0002,
+      "loss": 1.7617,
+      "step": 920
+    },
+    {
+      "epoch": 1.2678936605316973,
+      "grad_norm": 0.3514605164527893,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 930
+    },
+    {
+      "epoch": 1.2815269256987047,
+      "grad_norm": 0.3682589530944824,
+      "learning_rate": 0.0002,
+      "loss": 1.6987,
+      "step": 940
+    },
+    {
+      "epoch": 1.2951601908657122,
+      "grad_norm": 0.3618335723876953,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 950
+    },
+    {
+      "epoch": 1.30879345603272,
+      "grad_norm": 0.345700740814209,
+      "learning_rate": 0.0002,
+      "loss": 1.7436,
+      "step": 960
+    },
+    {
+      "epoch": 1.3224267211997274,
+      "grad_norm": 0.3514927923679352,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 970
+    },
+    {
+      "epoch": 1.3360599863667348,
+      "grad_norm": 0.365647554397583,
+      "learning_rate": 0.0002,
+      "loss": 1.7704,
+      "step": 980
+    },
+    {
+      "epoch": 1.3496932515337423,
+      "grad_norm": 0.3407285809516907,
+      "learning_rate": 0.0002,
+      "loss": 1.7104,
+      "step": 990
+    },
+    {
+      "epoch": 1.3633265167007498,
+      "grad_norm": 0.3785437345504761,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3769597818677572,
+      "grad_norm": 0.34746724367141724,
+      "learning_rate": 0.0002,
+      "loss": 1.766,
+      "step": 1010
+    },
+    {
+      "epoch": 1.390593047034765,
+      "grad_norm": 0.362444132566452,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4042263122017724,
+      "grad_norm": 0.4424704611301422,
+      "learning_rate": 0.0002,
+      "loss": 1.7132,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4178595773687799,
+      "grad_norm": 0.38722458481788635,
+      "learning_rate": 0.0002,
+      "loss": 1.726,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4314928425357873,
+      "grad_norm": 0.36089080572128296,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4451261077027948,
+      "grad_norm": 0.33817124366760254,
+      "learning_rate": 0.0002,
+      "loss": 1.6924,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4587593728698023,
+      "grad_norm": 0.34334081411361694,
+      "learning_rate": 0.0002,
+      "loss": 1.7165,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4723926380368098,
+      "grad_norm": 0.3776826858520508,
+      "learning_rate": 0.0002,
+      "loss": 1.6999,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4860259032038172,
+      "grad_norm": 0.4169026017189026,
+      "learning_rate": 0.0002,
+      "loss": 1.7605,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4996591683708247,
+      "grad_norm": 0.34898945689201355,
+      "learning_rate": 0.0002,
+      "loss": 1.7502,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5132924335378322,
+      "grad_norm": 0.34223780035972595,
+      "learning_rate": 0.0002,
+      "loss": 1.635,
+      "step": 1110
+    },
+    {
+      "epoch": 1.5269256987048399,
+      "grad_norm": 0.3686901032924652,
+      "learning_rate": 0.0002,
+      "loss": 1.7248,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5405589638718473,
+      "grad_norm": 0.35054415464401245,
+      "learning_rate": 0.0002,
+      "loss": 1.7525,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5541922290388548,
+      "grad_norm": 0.39496365189552307,
+      "learning_rate": 0.0002,
+      "loss": 1.7776,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5678254942058623,
+      "grad_norm": 0.35451626777648926,
+      "learning_rate": 0.0002,
+      "loss": 1.6574,
+      "step": 1150
+    },
+    {
+      "epoch": 1.58145875937287,
+      "grad_norm": 0.3848083019256592,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5950920245398774,
+      "grad_norm": 0.3760537803173065,
+      "learning_rate": 0.0002,
+      "loss": 1.7272,
+      "step": 1170
+    },
+    {
+      "epoch": 1.6087252897068849,
+      "grad_norm": 0.38981738686561584,
+      "learning_rate": 0.0002,
+      "loss": 1.7441,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6223585548738924,
+      "grad_norm": 0.36830949783325195,
+      "learning_rate": 0.0002,
+      "loss": 1.6951,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6359918200408998,
+      "grad_norm": 0.3405892848968506,
+      "learning_rate": 0.0002,
+      "loss": 1.6925,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6496250852079073,
+      "grad_norm": 0.39027872681617737,
+      "learning_rate": 0.0002,
+      "loss": 1.7473,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6632583503749148,
+      "grad_norm": 0.3342694044113159,
+      "learning_rate": 0.0002,
+      "loss": 1.6792,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6768916155419222,
+      "grad_norm": 0.3600076735019684,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6905248807089297,
+      "grad_norm": 0.3625542223453522,
+      "learning_rate": 0.0002,
+      "loss": 1.7021,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7041581458759372,
+      "grad_norm": 0.32170894742012024,
+      "learning_rate": 0.0002,
+      "loss": 1.6772,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7177914110429446,
+      "grad_norm": 0.3544139862060547,
+      "learning_rate": 0.0002,
+      "loss": 1.7152,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7314246762099523,
+      "grad_norm": 0.35113027691841125,
+      "learning_rate": 0.0002,
+      "loss": 1.7138,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7450579413769598,
+      "grad_norm": 0.3499974310398102,
+      "learning_rate": 0.0002,
+      "loss": 1.7095,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7586912065439673,
+      "grad_norm": 0.3285157382488251,
+      "learning_rate": 0.0002,
+      "loss": 1.7749,
+      "step": 1290
+    },
+    {
+      "epoch": 1.7723244717109747,
+      "grad_norm": 0.3701961636543274,
+      "learning_rate": 0.0002,
+      "loss": 1.6767,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7859577368779824,
+      "grad_norm": 0.3301318287849426,
+      "learning_rate": 0.0002,
+      "loss": 1.6282,
+      "step": 1310
+    },
+    {
+      "epoch": 1.79959100204499,
+      "grad_norm": 0.37801554799079895,
+      "learning_rate": 0.0002,
+      "loss": 1.7097,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8132242672119974,
+      "grad_norm": 0.3726748526096344,
+      "learning_rate": 0.0002,
+      "loss": 1.7437,
+      "step": 1330
+    },
+    {
+      "epoch": 1.8268575323790048,
+      "grad_norm": 0.4059790074825287,
+      "learning_rate": 0.0002,
+      "loss": 1.7959,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 0.35712096095085144,
+      "learning_rate": 0.0002,
+      "loss": 1.7739,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8541240627130198,
+      "grad_norm": 0.35995328426361084,
+      "learning_rate": 0.0002,
+      "loss": 1.6375,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8677573278800272,
+      "grad_norm": 0.3679947257041931,
+      "learning_rate": 0.0002,
+      "loss": 1.7332,
+      "step": 1370
+    },
+    {
+      "epoch": 1.8813905930470347,
+      "grad_norm": 0.39645957946777344,
+      "learning_rate": 0.0002,
+      "loss": 1.7587,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8950238582140422,
+      "grad_norm": 0.35288700461387634,
+      "learning_rate": 0.0002,
+      "loss": 1.6985,
+      "step": 1390
+    },
+    {
+      "epoch": 1.9086571233810496,
+      "grad_norm": 0.32579198479652405,
+      "learning_rate": 0.0002,
+      "loss": 1.6582,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9222903885480571,
+      "grad_norm": 0.3856561779975891,
+      "learning_rate": 0.0002,
+      "loss": 1.6948,
+      "step": 1410
+    },
+    {
+      "epoch": 1.9359236537150648,
+      "grad_norm": 0.39019331336021423,
+      "learning_rate": 0.0002,
+      "loss": 1.668,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9495569188820723,
+      "grad_norm": 0.38006502389907837,
+      "learning_rate": 0.0002,
+      "loss": 1.7774,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9631901840490797,
+      "grad_norm": 0.38100454211235046,
+      "learning_rate": 0.0002,
+      "loss": 1.8323,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9768234492160872,
+      "grad_norm": 0.3405798673629761,
+      "learning_rate": 0.0002,
+      "loss": 1.7298,
+      "step": 1450
+    },
+    {
+      "epoch": 1.990456714383095,
+      "grad_norm": 0.36582913994789124,
+      "learning_rate": 0.0002,
+      "loss": 1.7045,
+      "step": 1460
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8178424835205078,
+      "eval_runtime": 53.6524,
+      "eval_samples_per_second": 9.45,
+      "eval_steps_per_second": 1.193,
+      "step": 1467
+    },
+    {
+      "epoch": 2.0040899795501024,
+      "grad_norm": 0.3626647889614105,
+      "learning_rate": 0.0002,
+      "loss": 1.6363,
+      "step": 1470
+    },
+    {
+      "epoch": 2.01772324471711,
+      "grad_norm": 0.40171775221824646,
+      "learning_rate": 0.0002,
+      "loss": 1.5354,
+      "step": 1480
+    },
+    {
+      "epoch": 2.0313565098841173,
+      "grad_norm": 0.5805319547653198,
+      "learning_rate": 0.0002,
+      "loss": 1.5566,
+      "step": 1490
+    },
+    {
+      "epoch": 2.044989775051125,
+      "grad_norm": 0.41954153776168823,
+      "learning_rate": 0.0002,
+      "loss": 1.546,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0586230402181322,
+      "grad_norm": 0.47190725803375244,
+      "learning_rate": 0.0002,
+      "loss": 1.6158,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0722563053851397,
+      "grad_norm": 0.4388456344604492,
+      "learning_rate": 0.0002,
+      "loss": 1.5841,
+      "step": 1520
+    },
+    {
+      "epoch": 2.085889570552147,
+      "grad_norm": 2.2171926498413086,
+      "learning_rate": 0.0002,
+      "loss": 1.5835,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0995228357191547,
+      "grad_norm": 0.4314221143722534,
+      "learning_rate": 0.0002,
+      "loss": 1.6137,
+      "step": 1540
+    },
+    {
+      "epoch": 2.113156100886162,
+      "grad_norm": 0.4154265522956848,
+      "learning_rate": 0.0002,
+      "loss": 1.5511,
+      "step": 1550
+    },
+    {
+      "epoch": 2.1267893660531696,
+      "grad_norm": 0.5025539994239807,
+      "learning_rate": 0.0002,
+      "loss": 1.6323,
+      "step": 1560
+    },
+    {
+      "epoch": 2.140422631220177,
+      "grad_norm": 0.5410493016242981,
+      "learning_rate": 0.0002,
+      "loss": 1.5903,
+      "step": 1570
+    },
+    {
+      "epoch": 2.1540558963871845,
+      "grad_norm": 0.4478487968444824,
+      "learning_rate": 0.0002,
+      "loss": 1.507,
+      "step": 1580
+    },
+    {
+      "epoch": 2.1676891615541924,
+      "grad_norm": 0.4703652560710907,
+      "learning_rate": 0.0002,
+      "loss": 1.5536,
+      "step": 1590
+    },
+    {
+      "epoch": 2.1813224267212,
+      "grad_norm": 0.4555390179157257,
+      "learning_rate": 0.0002,
+      "loss": 1.5991,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1949556918882074,
+      "grad_norm": 0.4877263903617859,
+      "learning_rate": 0.0002,
+      "loss": 1.6117,
+      "step": 1610
+    },
+    {
+      "epoch": 2.208588957055215,
+      "grad_norm": 0.48708245158195496,
+      "learning_rate": 0.0002,
+      "loss": 1.5928,
+      "step": 1620
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.47523951530456543,
+      "learning_rate": 0.0002,
+      "loss": 1.6106,
+      "step": 1630
+    },
+    {
+      "epoch": 2.23585548738923,
+      "grad_norm": 0.4889199733734131,
+      "learning_rate": 0.0002,
+      "loss": 1.6013,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2494887525562373,
+      "grad_norm": 0.4585252106189728,
+      "learning_rate": 0.0002,
+      "loss": 1.6633,
+      "step": 1650
+    },
+    {
+      "epoch": 2.2631220177232447,
+      "grad_norm": 0.4764868915081024,
+      "learning_rate": 0.0002,
+      "loss": 1.6075,
+      "step": 1660
+    },
+    {
+      "epoch": 2.276755282890252,
+      "grad_norm": 0.5028976202011108,
+      "learning_rate": 0.0002,
+      "loss": 1.6427,
+      "step": 1670
+    },
+    {
+      "epoch": 2.2903885480572597,
+      "grad_norm": 0.46131211519241333,
+      "learning_rate": 0.0002,
+      "loss": 1.6258,
+      "step": 1680
+    },
+    {
+      "epoch": 2.304021813224267,
+      "grad_norm": 0.5422874689102173,
+      "learning_rate": 0.0002,
+      "loss": 1.654,
+      "step": 1690
+    },
+    {
+      "epoch": 2.3176550783912746,
+      "grad_norm": 0.47615355253219604,
+      "learning_rate": 0.0002,
+      "loss": 1.6331,
+      "step": 1700
+    },
+    {
+      "epoch": 2.331288343558282,
+      "grad_norm": 0.48005548119544983,
+      "learning_rate": 0.0002,
+      "loss": 1.642,
+      "step": 1710
+    },
+    {
+      "epoch": 2.3449216087252895,
+      "grad_norm": 0.4387182295322418,
+      "learning_rate": 0.0002,
+      "loss": 1.581,
+      "step": 1720
+    },
+    {
+      "epoch": 2.358554873892297,
+      "grad_norm": 0.4487272799015045,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 1730
+    },
+    {
+      "epoch": 2.372188139059305,
+      "grad_norm": 0.5046455264091492,
+      "learning_rate": 0.0002,
+      "loss": 1.5089,
+      "step": 1740
+    },
+    {
+      "epoch": 2.3858214042263124,
+      "grad_norm": 0.4653521180152893,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 1750
+    },
+    {
+      "epoch": 2.39945466939332,
+      "grad_norm": 0.4737723469734192,
+      "learning_rate": 0.0002,
+      "loss": 1.6201,
+      "step": 1760
+    },
+    {
+      "epoch": 2.4130879345603273,
+      "grad_norm": 0.4501931071281433,
+      "learning_rate": 0.0002,
+      "loss": 1.5933,
+      "step": 1770
+    },
+    {
+      "epoch": 2.426721199727335,
+      "grad_norm": 0.4772880971431732,
+      "learning_rate": 0.0002,
+      "loss": 1.6321,
+      "step": 1780
+    },
+    {
+      "epoch": 2.4403544648943423,
+      "grad_norm": 0.4544616937637329,
+      "learning_rate": 0.0002,
+      "loss": 1.5454,
+      "step": 1790
+    },
+    {
+      "epoch": 2.4539877300613497,
+      "grad_norm": 0.488313227891922,
+      "learning_rate": 0.0002,
+      "loss": 1.5501,
+      "step": 1800
+    },
+    {
+      "epoch": 2.467620995228357,
+      "grad_norm": 0.5057830214500427,
+      "learning_rate": 0.0002,
+      "loss": 1.5791,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4812542603953647,
+      "grad_norm": 0.5049484968185425,
+      "learning_rate": 0.0002,
+      "loss": 1.5645,
+      "step": 1820
+    },
+    {
+      "epoch": 2.494887525562372,
+      "grad_norm": 0.44966644048690796,
+      "learning_rate": 0.0002,
+      "loss": 1.6268,
+      "step": 1830
+    },
+    {
+      "epoch": 2.5085207907293796,
+      "grad_norm": 0.5072630643844604,
+      "learning_rate": 0.0002,
+      "loss": 1.5941,
+      "step": 1840
+    },
+    {
+      "epoch": 2.522154055896387,
+      "grad_norm": 0.43989792466163635,
+      "learning_rate": 0.0002,
+      "loss": 1.5251,
+      "step": 1850
+    },
+    {
+      "epoch": 2.5357873210633946,
+      "grad_norm": 1.3504403829574585,
+      "learning_rate": 0.0002,
+      "loss": 1.563,
+      "step": 1860
+    },
+    {
+      "epoch": 2.549420586230402,
+      "grad_norm": 0.46545976400375366,
+      "learning_rate": 0.0002,
+      "loss": 1.5681,
+      "step": 1870
+    },
+    {
+      "epoch": 2.5630538513974095,
+      "grad_norm": 0.4678342044353485,
+      "learning_rate": 0.0002,
+      "loss": 1.6368,
+      "step": 1880
+    },
+    {
+      "epoch": 2.5766871165644174,
+      "grad_norm": 0.529755711555481,
+      "learning_rate": 0.0002,
+      "loss": 1.5814,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5903203817314244,
+      "grad_norm": 0.5000199675559998,
+      "learning_rate": 0.0002,
+      "loss": 1.5861,
+      "step": 1900
+    },
+    {
+      "epoch": 2.6039536468984323,
+      "grad_norm": 0.5649300217628479,
+      "learning_rate": 0.0002,
+      "loss": 1.6346,
+      "step": 1910
+    },
+    {
+      "epoch": 2.61758691206544,
+      "grad_norm": 0.7920585870742798,
+      "learning_rate": 0.0002,
+      "loss": 1.6317,
+      "step": 1920
+    },
+    {
+      "epoch": 2.6312201772324473,
+      "grad_norm": 0.4960342049598694,
+      "learning_rate": 0.0002,
+      "loss": 1.643,
+      "step": 1930
+    },
+    {
+      "epoch": 2.6448534423994547,
+      "grad_norm": 0.5324710011482239,
+      "learning_rate": 0.0002,
+      "loss": 1.6099,
+      "step": 1940
+    },
+    {
+      "epoch": 2.658486707566462,
+      "grad_norm": 0.606343150138855,
+      "learning_rate": 0.0002,
+      "loss": 1.5874,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6721199727334697,
+      "grad_norm": 0.53038489818573,
+      "learning_rate": 0.0002,
+      "loss": 1.5728,
+      "step": 1960
+    },
+    {
+      "epoch": 2.685753237900477,
+      "grad_norm": 0.4579465091228485,
+      "learning_rate": 0.0002,
+      "loss": 1.5583,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6993865030674846,
+      "grad_norm": 0.4541707932949066,
+      "learning_rate": 0.0002,
+      "loss": 1.6093,
+      "step": 1980
+    },
+    {
+      "epoch": 2.713019768234492,
+      "grad_norm": 0.5009395480155945,
+      "learning_rate": 0.0002,
+      "loss": 1.5316,
+      "step": 1990
+    },
+    {
+      "epoch": 2.7266530334014996,
+      "grad_norm": 0.4723006784915924,
+      "learning_rate": 0.0002,
+      "loss": 1.6724,
+      "step": 2000
+    },
+    {
+      "epoch": 2.740286298568507,
+      "grad_norm": 0.5086126923561096,
+      "learning_rate": 0.0002,
+      "loss": 1.638,
+      "step": 2010
+    },
+    {
+      "epoch": 2.7539195637355145,
+      "grad_norm": 0.47242608666419983,
+      "learning_rate": 0.0002,
+      "loss": 1.6223,
+      "step": 2020
+    },
+    {
+      "epoch": 2.767552828902522,
+      "grad_norm": 0.44922566413879395,
+      "learning_rate": 0.0002,
+      "loss": 1.6242,
+      "step": 2030
+    },
+    {
+      "epoch": 2.78118609406953,
+      "grad_norm": 0.420259565114975,
+      "learning_rate": 0.0002,
+      "loss": 1.6837,
+      "step": 2040
+    },
+    {
+      "epoch": 2.794819359236537,
+      "grad_norm": 0.4762881100177765,
+      "learning_rate": 0.0002,
+      "loss": 1.5612,
+      "step": 2050
+    },
+    {
+      "epoch": 2.808452624403545,
+      "grad_norm": 0.5228786468505859,
+      "learning_rate": 0.0002,
+      "loss": 1.5506,
+      "step": 2060
+    },
+    {
+      "epoch": 2.8220858895705523,
+      "grad_norm": 0.4796035587787628,
+      "learning_rate": 0.0002,
+      "loss": 1.6347,
+      "step": 2070
+    },
+    {
+      "epoch": 2.8357191547375598,
+      "grad_norm": 0.5034735202789307,
+      "learning_rate": 0.0002,
+      "loss": 1.6843,
+      "step": 2080
+    },
+    {
+      "epoch": 2.8493524199045672,
+      "grad_norm": 0.48005399107933044,
+      "learning_rate": 0.0002,
+      "loss": 1.6455,
+      "step": 2090
+    },
+    {
+      "epoch": 2.8629856850715747,
+      "grad_norm": 0.578820526599884,
+      "learning_rate": 0.0002,
+      "loss": 1.6287,
+      "step": 2100
+    },
+    {
+      "epoch": 2.876618950238582,
+      "grad_norm": 0.48982638120651245,
+      "learning_rate": 0.0002,
+      "loss": 1.6021,
+      "step": 2110
+    },
+    {
+      "epoch": 2.8902522154055896,
+      "grad_norm": 0.5157325863838196,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 2120
+    },
+    {
+      "epoch": 2.903885480572597,
+      "grad_norm": 0.49149683117866516,
+      "learning_rate": 0.0002,
+      "loss": 1.6089,
+      "step": 2130
+    },
+    {
+      "epoch": 2.9175187457396046,
+      "grad_norm": 0.48584499955177307,
+      "learning_rate": 0.0002,
+      "loss": 1.5881,
+      "step": 2140
+    },
+    {
+      "epoch": 2.931152010906612,
+      "grad_norm": 0.5199017524719238,
+      "learning_rate": 0.0002,
+      "loss": 1.5833,
+      "step": 2150
+    },
+    {
+      "epoch": 2.9447852760736195,
+      "grad_norm": 0.5788236856460571,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 2160
+    },
+    {
+      "epoch": 2.958418541240627,
+      "grad_norm": 0.48664185404777527,
+      "learning_rate": 0.0002,
+      "loss": 1.6103,
+      "step": 2170
+    },
+    {
+      "epoch": 2.9720518064076344,
+      "grad_norm": 0.5026682615280151,
+      "learning_rate": 0.0002,
+      "loss": 1.5765,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9856850715746424,
+      "grad_norm": 0.49317044019699097,
+      "learning_rate": 0.0002,
+      "loss": 1.6626,
+      "step": 2190
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "grad_norm": 0.5729128122329712,
+      "learning_rate": 0.0002,
+      "loss": 1.5871,
+      "step": 2200
+    },
+    {
+      "epoch": 2.9993183367416494,
+      "eval_loss": 1.8527295589447021,
+      "eval_runtime": 53.6403,
+      "eval_samples_per_second": 9.452,
+      "eval_steps_per_second": 1.193,
+      "step": 2200
+    },
+    {
+      "epoch": 3.0129516019086573,
+      "grad_norm": 0.5530241131782532,
+      "learning_rate": 0.0002,
+      "loss": 1.4719,
+      "step": 2210
+    },
+    {
+      "epoch": 3.0265848670756648,
+      "grad_norm": 0.6642216444015503,
+      "learning_rate": 0.0002,
+      "loss": 1.4088,
+      "step": 2220
+    },
+    {
+      "epoch": 3.0402181322426722,
+      "grad_norm": 0.61470627784729,
+      "learning_rate": 0.0002,
+      "loss": 1.4382,
+      "step": 2230
+    },
+    {
+      "epoch": 3.0538513974096797,
+      "grad_norm": 0.8559566140174866,
+      "learning_rate": 0.0002,
+      "loss": 1.4634,
+      "step": 2240
+    },
+    {
+      "epoch": 3.067484662576687,
+      "grad_norm": 0.7015801668167114,
+      "learning_rate": 0.0002,
+      "loss": 1.3854,
+      "step": 2250
+    },
+    {
+      "epoch": 3.0811179277436946,
+      "grad_norm": 0.7226442694664001,
+      "learning_rate": 0.0002,
+      "loss": 1.4981,
+      "step": 2260
+    },
+    {
+      "epoch": 3.094751192910702,
+      "grad_norm": 0.7560588717460632,
+      "learning_rate": 0.0002,
+      "loss": 1.4143,
+      "step": 2270
+    },
+    {
+      "epoch": 3.1083844580777096,
+      "grad_norm": 0.6216568946838379,
+      "learning_rate": 0.0002,
+      "loss": 1.4395,
+      "step": 2280
+    },
+    {
+      "epoch": 3.122017723244717,
+      "grad_norm": 0.6768500804901123,
+      "learning_rate": 0.0002,
+      "loss": 1.3842,
+      "step": 2290
+    },
+    {
+      "epoch": 3.1356509884117245,
+      "grad_norm": 0.7028762102127075,
+      "learning_rate": 0.0002,
+      "loss": 1.4672,
+      "step": 2300
+    },
+    {
+      "epoch": 3.149284253578732,
+      "grad_norm": 0.6329697966575623,
+      "learning_rate": 0.0002,
+      "loss": 1.3826,
+      "step": 2310
+    },
+    {
+      "epoch": 3.1629175187457395,
+      "grad_norm": 0.6328264474868774,
+      "learning_rate": 0.0002,
+      "loss": 1.442,
+      "step": 2320
+    },
+    {
+      "epoch": 3.176550783912747,
+      "grad_norm": 0.7573632001876831,
+      "learning_rate": 0.0002,
+      "loss": 1.3762,
+      "step": 2330
+    },
+    {
+      "epoch": 3.190184049079755,
+      "grad_norm": 0.595740795135498,
+      "learning_rate": 0.0002,
+      "loss": 1.3553,
+      "step": 2340
+    },
+    {
+      "epoch": 3.2038173142467623,
+      "grad_norm": 0.7111806869506836,
+      "learning_rate": 0.0002,
+      "loss": 1.3953,
+      "step": 2350
+    },
+    {
+      "epoch": 3.2174505794137698,
+      "grad_norm": 0.6328730583190918,
+      "learning_rate": 0.0002,
+      "loss": 1.3797,
+      "step": 2360
+    },
+    {
+      "epoch": 3.2310838445807772,
+      "grad_norm": 0.5860254168510437,
+      "learning_rate": 0.0002,
+      "loss": 1.3855,
+      "step": 2370
+    },
+    {
+      "epoch": 3.2447171097477847,
+      "grad_norm": 0.7387157082557678,
+      "learning_rate": 0.0002,
+      "loss": 1.4267,
+      "step": 2380
+    },
+    {
+      "epoch": 3.258350374914792,
+      "grad_norm": 0.6897673606872559,
+      "learning_rate": 0.0002,
+      "loss": 1.4837,
+      "step": 2390
+    },
+    {
+      "epoch": 3.2719836400817996,
+      "grad_norm": 0.7157699465751648,
+      "learning_rate": 0.0002,
+      "loss": 1.4372,
+      "step": 2400
+    },
+    {
+      "epoch": 3.285616905248807,
+      "grad_norm": 0.6422511339187622,
+      "learning_rate": 0.0002,
+      "loss": 1.4432,
+      "step": 2410
+    },
+    {
+      "epoch": 3.2992501704158146,
+      "grad_norm": 1.0481886863708496,
+      "learning_rate": 0.0002,
+      "loss": 1.4828,
+      "step": 2420
+    },
+    {
+      "epoch": 3.312883435582822,
+      "grad_norm": 0.7050786018371582,
+      "learning_rate": 0.0002,
+      "loss": 1.4473,
+      "step": 2430
+    },
+    {
+      "epoch": 3.3265167007498295,
+      "grad_norm": 0.6090759038925171,
+      "learning_rate": 0.0002,
+      "loss": 1.3465,
+      "step": 2440
+    },
+    {
+      "epoch": 3.340149965916837,
+      "grad_norm": 0.6626465320587158,
+      "learning_rate": 0.0002,
+      "loss": 1.4619,
+      "step": 2450
+    },
+    {
+      "epoch": 3.3537832310838445,
+      "grad_norm": 0.6565486788749695,
+      "learning_rate": 0.0002,
+      "loss": 1.4512,
+      "step": 2460
+    },
+    {
+      "epoch": 3.367416496250852,
+      "grad_norm": 0.6449528932571411,
+      "learning_rate": 0.0002,
+      "loss": 1.588,
+      "step": 2470
+    },
+    {
+      "epoch": 3.3810497614178594,
+      "grad_norm": 0.7746227383613586,
+      "learning_rate": 0.0002,
+      "loss": 1.4773,
+      "step": 2480
+    },
+    {
+      "epoch": 3.3946830265848673,
+      "grad_norm": 0.7074846029281616,
+      "learning_rate": 0.0002,
+      "loss": 1.417,
+      "step": 2490
+    },
+    {
+      "epoch": 3.4083162917518743,
+      "grad_norm": 0.6547690033912659,
+      "learning_rate": 0.0002,
+      "loss": 1.4476,
+      "step": 2500
+    },
+    {
+      "epoch": 3.4219495569188823,
+      "grad_norm": 0.784721314907074,
+      "learning_rate": 0.0002,
+      "loss": 1.4074,
+      "step": 2510
+    },
+    {
+      "epoch": 3.4355828220858897,
+      "grad_norm": 0.7270277738571167,
+      "learning_rate": 0.0002,
+      "loss": 1.4326,
+      "step": 2520
+    },
+    {
+      "epoch": 3.449216087252897,
+      "grad_norm": 0.67588871717453,
+      "learning_rate": 0.0002,
+      "loss": 1.4354,
+      "step": 2530
+    },
+    {
+      "epoch": 3.4628493524199047,
+      "grad_norm": 0.6768023371696472,
+      "learning_rate": 0.0002,
+      "loss": 1.4074,
+      "step": 2540
+    },
+    {
+      "epoch": 3.476482617586912,
+      "grad_norm": 0.7026481628417969,
+      "learning_rate": 0.0002,
+      "loss": 1.4863,
+      "step": 2550
+    },
+    {
+      "epoch": 3.4901158827539196,
+      "grad_norm": 0.646075963973999,
+      "learning_rate": 0.0002,
+      "loss": 1.468,
+      "step": 2560
+    },
+    {
+      "epoch": 3.503749147920927,
+      "grad_norm": 0.6288973689079285,
+      "learning_rate": 0.0002,
+      "loss": 1.4058,
+      "step": 2570
+    },
+    {
+      "epoch": 3.5173824130879345,
+      "grad_norm": 0.6440825462341309,
+      "learning_rate": 0.0002,
+      "loss": 1.4613,
+      "step": 2580
+    },
+    {
+      "epoch": 3.531015678254942,
+      "grad_norm": 0.7074111700057983,
+      "learning_rate": 0.0002,
+      "loss": 1.3808,
+      "step": 2590
+    },
+    {
+      "epoch": 3.5446489434219495,
+      "grad_norm": 0.7007562518119812,
+      "learning_rate": 0.0002,
+      "loss": 1.4901,
+      "step": 2600
+    },
+    {
+      "epoch": 3.558282208588957,
+      "grad_norm": 0.6045376658439636,
+      "learning_rate": 0.0002,
+      "loss": 1.4511,
+      "step": 2610
+    },
+    {
+      "epoch": 3.5719154737559644,
+      "grad_norm": 0.9149952530860901,
+      "learning_rate": 0.0002,
+      "loss": 1.4596,
+      "step": 2620
+    },
+    {
+      "epoch": 3.585548738922972,
+      "grad_norm": 0.6490362882614136,
+      "learning_rate": 0.0002,
+      "loss": 1.4355,
+      "step": 2630
+    },
+    {
+      "epoch": 3.59918200408998,
+      "grad_norm": 0.6552226543426514,
+      "learning_rate": 0.0002,
+      "loss": 1.4107,
+      "step": 2640
+    },
+    {
+      "epoch": 3.612815269256987,
+      "grad_norm": 0.6541850566864014,
+      "learning_rate": 0.0002,
+      "loss": 1.433,
+      "step": 2650
+    },
+    {
+      "epoch": 3.6264485344239947,
+      "grad_norm": 0.6500770449638367,
+      "learning_rate": 0.0002,
+      "loss": 1.4279,
+      "step": 2660
+    },
+    {
+      "epoch": 3.640081799591002,
+      "grad_norm": 0.6345893740653992,
+      "learning_rate": 0.0002,
+      "loss": 1.3929,
+      "step": 2670
+    },
+    {
+      "epoch": 3.6537150647580097,
+      "grad_norm": 0.6382275223731995,
+      "learning_rate": 0.0002,
+      "loss": 1.3634,
+      "step": 2680
+    },
+    {
+      "epoch": 3.667348329925017,
+      "grad_norm": 0.6738566160202026,
+      "learning_rate": 0.0002,
+      "loss": 1.4478,
+      "step": 2690
+    },
+    {
+      "epoch": 3.6809815950920246,
+      "grad_norm": 0.7446315288543701,
+      "learning_rate": 0.0002,
+      "loss": 1.4642,
+      "step": 2700
+    },
+    {
+      "epoch": 3.694614860259032,
+      "grad_norm": 0.6717571020126343,
+      "learning_rate": 0.0002,
+      "loss": 1.4342,
+      "step": 2710
+    },
+    {
+      "epoch": 3.7082481254260395,
+      "grad_norm": 0.667259693145752,
+      "learning_rate": 0.0002,
+      "loss": 1.4285,
+      "step": 2720
+    },
+    {
+      "epoch": 3.721881390593047,
+      "grad_norm": 0.6808622479438782,
+      "learning_rate": 0.0002,
+      "loss": 1.5389,
+      "step": 2730
+    },
+    {
+      "epoch": 3.7355146557600545,
+      "grad_norm": 0.7254287004470825,
+      "learning_rate": 0.0002,
+      "loss": 1.4297,
+      "step": 2740
+    },
+    {
+      "epoch": 3.749147920927062,
+      "grad_norm": 0.6864007711410522,
+      "learning_rate": 0.0002,
+      "loss": 1.4176,
+      "step": 2750
+    },
+    {
+      "epoch": 3.7627811860940694,
+      "grad_norm": 0.7041361331939697,
+      "learning_rate": 0.0002,
+      "loss": 1.4811,
+      "step": 2760
+    },
+    {
+      "epoch": 3.776414451261077,
+      "grad_norm": 0.6559903025627136,
+      "learning_rate": 0.0002,
+      "loss": 1.4284,
+      "step": 2770
+    },
+    {
+      "epoch": 3.7900477164280844,
+      "grad_norm": 0.6602269411087036,
+      "learning_rate": 0.0002,
+      "loss": 1.4608,
+      "step": 2780
+    },
+    {
+      "epoch": 3.8036809815950923,
+      "grad_norm": 0.692611813545227,
+      "learning_rate": 0.0002,
+      "loss": 1.4588,
+      "step": 2790
+    },
+    {
+      "epoch": 3.8173142467620993,
+      "grad_norm": 0.7051475644111633,
+      "learning_rate": 0.0002,
+      "loss": 1.4065,
+      "step": 2800
+    },
+    {
+      "epoch": 3.830947511929107,
+      "grad_norm": 0.6685371398925781,
+      "learning_rate": 0.0002,
+      "loss": 1.4083,
+      "step": 2810
+    },
+    {
+      "epoch": 3.8445807770961147,
+      "grad_norm": 0.6706477403640747,
+      "learning_rate": 0.0002,
+      "loss": 1.5227,
+      "step": 2820
+    },
+    {
+      "epoch": 3.858214042263122,
+      "grad_norm": 0.6671637296676636,
+      "learning_rate": 0.0002,
+      "loss": 1.4076,
+      "step": 2830
+    },
+    {
+      "epoch": 3.8718473074301296,
+      "grad_norm": 0.694092333316803,
+      "learning_rate": 0.0002,
+      "loss": 1.4736,
+      "step": 2840
+    },
+    {
+      "epoch": 3.885480572597137,
+      "grad_norm": 0.7349600195884705,
+      "learning_rate": 0.0002,
+      "loss": 1.4161,
+      "step": 2850
+    },
+    {
+      "epoch": 3.8991138377641446,
+      "grad_norm": 0.6647971868515015,
+      "learning_rate": 0.0002,
+      "loss": 1.4617,
+      "step": 2860
+    },
+    {
+      "epoch": 3.912747102931152,
+      "grad_norm": 0.806656539440155,
+      "learning_rate": 0.0002,
+      "loss": 1.5046,
+      "step": 2870
+    },
+    {
+      "epoch": 3.9263803680981595,
+      "grad_norm": 0.6008772850036621,
+      "learning_rate": 0.0002,
+      "loss": 1.428,
+      "step": 2880
+    },
+    {
+      "epoch": 3.940013633265167,
+      "grad_norm": 0.659227728843689,
+      "learning_rate": 0.0002,
+      "loss": 1.4116,
+      "step": 2890
+    },
+    {
+      "epoch": 3.9536468984321744,
+      "grad_norm": 0.6357656717300415,
+      "learning_rate": 0.0002,
+      "loss": 1.4136,
+      "step": 2900
+    },
+    {
+      "epoch": 3.967280163599182,
+      "grad_norm": 0.6541687846183777,
+      "learning_rate": 0.0002,
+      "loss": 1.4655,
+      "step": 2910
+    },
+    {
+      "epoch": 3.9809134287661894,
+      "grad_norm": 0.6090909838676453,
+      "learning_rate": 0.0002,
+      "loss": 1.4854,
+      "step": 2920
+    },
+    {
+      "epoch": 3.994546693933197,
+      "grad_norm": 0.7198411822319031,
+      "learning_rate": 0.0002,
+      "loss": 1.4615,
+      "step": 2930
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.9278366565704346,
+      "eval_runtime": 53.6567,
+      "eval_samples_per_second": 9.449,
+      "eval_steps_per_second": 1.193,
+      "step": 2934
+    },
+    {
+      "epoch": 4.008179959100205,
+      "grad_norm": 0.6498575210571289,
+      "learning_rate": 0.0002,
+      "loss": 1.3159,
+      "step": 2940
+    },
+    {
+      "epoch": 4.021813224267212,
+      "grad_norm": 0.865602433681488,
+      "learning_rate": 0.0002,
+      "loss": 1.2075,
+      "step": 2950
+    },
+    {
+      "epoch": 4.03544648943422,
+      "grad_norm": 0.8514999151229858,
+      "learning_rate": 0.0002,
+      "loss": 1.1744,
+      "step": 2960
+    },
+    {
+      "epoch": 4.049079754601227,
+      "grad_norm": 1.0677322149276733,
+      "learning_rate": 0.0002,
+      "loss": 1.1553,
+      "step": 2970
+    },
+    {
+      "epoch": 4.062713019768235,
+      "grad_norm": 1.0126488208770752,
+      "learning_rate": 0.0002,
+      "loss": 1.1962,
+      "step": 2980
+    },
+    {
+      "epoch": 4.076346284935242,
+      "grad_norm": 1.0008870363235474,
+      "learning_rate": 0.0002,
+      "loss": 1.1631,
+      "step": 2990
+    },
+    {
+      "epoch": 4.08997955010225,
+      "grad_norm": 0.7942054271697998,
+      "learning_rate": 0.0002,
+      "loss": 1.2154,
+      "step": 3000
+    },
+    {
+      "epoch": 4.103612815269257,
+      "grad_norm": 1.0482100248336792,
+      "learning_rate": 0.0002,
+      "loss": 1.214,
+      "step": 3010
+    },
+    {
+      "epoch": 4.1172460804362645,
+      "grad_norm": 1.0516992807388306,
+      "learning_rate": 0.0002,
+      "loss": 1.1999,
+      "step": 3020
+    },
+    {
+      "epoch": 4.130879345603272,
+      "grad_norm": 0.8144322037696838,
+      "learning_rate": 0.0002,
+      "loss": 1.2108,
+      "step": 3030
+    },
+    {
+      "epoch": 4.144512610770279,
+      "grad_norm": 0.952297568321228,
+      "learning_rate": 0.0002,
+      "loss": 1.1782,
+      "step": 3040
+    },
+    {
+      "epoch": 4.158145875937287,
+      "grad_norm": 1.007645606994629,
+      "learning_rate": 0.0002,
+      "loss": 1.2814,
+      "step": 3050
+    },
+    {
+      "epoch": 4.171779141104294,
+      "grad_norm": 1.0480353832244873,
+      "learning_rate": 0.0002,
+      "loss": 1.1731,
+      "step": 3060
+    },
+    {
+      "epoch": 4.185412406271302,
+      "grad_norm": 0.9270663857460022,
+      "learning_rate": 0.0002,
+      "loss": 1.196,
+      "step": 3070
+    },
+    {
+      "epoch": 4.199045671438309,
+      "grad_norm": 1.3415262699127197,
+      "learning_rate": 0.0002,
+      "loss": 1.2167,
+      "step": 3080
+    },
+    {
+      "epoch": 4.212678936605317,
+      "grad_norm": 1.167606234550476,
+      "learning_rate": 0.0002,
+      "loss": 1.2601,
+      "step": 3090
+    },
+    {
+      "epoch": 4.226312201772324,
+      "grad_norm": 0.9418690800666809,
+      "learning_rate": 0.0002,
+      "loss": 1.2605,
+      "step": 3100
+    },
+    {
+      "epoch": 4.239945466939332,
+      "grad_norm": 1.0885876417160034,
+      "learning_rate": 0.0002,
+      "loss": 1.2184,
+      "step": 3110
+    },
+    {
+      "epoch": 4.253578732106339,
+      "grad_norm": 0.9165483713150024,
+      "learning_rate": 0.0002,
+      "loss": 1.2594,
+      "step": 3120
+    },
+    {
+      "epoch": 4.267211997273347,
+      "grad_norm": 0.9154694080352783,
+      "learning_rate": 0.0002,
+      "loss": 1.2933,
+      "step": 3130
+    },
+    {
+      "epoch": 4.280845262440354,
+      "grad_norm": 1.100580096244812,
+      "learning_rate": 0.0002,
+      "loss": 1.2584,
+      "step": 3140
+    },
+    {
+      "epoch": 4.294478527607362,
+      "grad_norm": 0.9367576241493225,
+      "learning_rate": 0.0002,
+      "loss": 1.251,
+      "step": 3150
+    },
+    {
+      "epoch": 4.308111792774369,
+      "grad_norm": 0.9744015336036682,
+      "learning_rate": 0.0002,
+      "loss": 1.2032,
+      "step": 3160
+    },
+    {
+      "epoch": 4.321745057941377,
+      "grad_norm": 0.9865175485610962,
+      "learning_rate": 0.0002,
+      "loss": 1.2787,
+      "step": 3170
+    },
+    {
+      "epoch": 4.335378323108385,
+      "grad_norm": 1.0124907493591309,
+      "learning_rate": 0.0002,
+      "loss": 1.2161,
+      "step": 3180
+    },
+    {
+      "epoch": 4.349011588275392,
+      "grad_norm": 1.1044819355010986,
+      "learning_rate": 0.0002,
+      "loss": 1.2452,
+      "step": 3190
+    },
+    {
+      "epoch": 4.3626448534424,
+      "grad_norm": 0.9305577278137207,
+      "learning_rate": 0.0002,
+      "loss": 1.2483,
+      "step": 3200
+    },
+    {
+      "epoch": 4.376278118609407,
+      "grad_norm": 0.969265341758728,
+      "learning_rate": 0.0002,
+      "loss": 1.2101,
+      "step": 3210
+    },
+    {
+      "epoch": 4.389911383776415,
+      "grad_norm": 1.0671923160552979,
+      "learning_rate": 0.0002,
+      "loss": 1.2355,
+      "step": 3220
+    },
+    {
+      "epoch": 4.403544648943422,
+      "grad_norm": 0.9440539479255676,
+      "learning_rate": 0.0002,
+      "loss": 1.2259,
+      "step": 3230
+    },
+    {
+      "epoch": 4.41717791411043,
+      "grad_norm": 0.9824562668800354,
+      "learning_rate": 0.0002,
+      "loss": 1.1706,
+      "step": 3240
+    },
+    {
+      "epoch": 4.430811179277437,
+      "grad_norm": 1.0245535373687744,
+      "learning_rate": 0.0002,
+      "loss": 1.2234,
+      "step": 3250
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.9629312753677368,
+      "learning_rate": 0.0002,
+      "loss": 1.2713,
+      "step": 3260
+    },
+    {
+      "epoch": 4.458077709611452,
+      "grad_norm": 1.1556470394134521,
+      "learning_rate": 0.0002,
+      "loss": 1.2689,
+      "step": 3270
+    },
+    {
+      "epoch": 4.47171097477846,
+      "grad_norm": 0.9796679019927979,
+      "learning_rate": 0.0002,
+      "loss": 1.2214,
+      "step": 3280
+    },
+    {
+      "epoch": 4.485344239945467,
+      "grad_norm": 0.9030535221099854,
+      "learning_rate": 0.0002,
+      "loss": 1.2823,
+      "step": 3290
+    },
+    {
+      "epoch": 4.4989775051124745,
+      "grad_norm": 0.9142820835113525,
+      "learning_rate": 0.0002,
+      "loss": 1.2111,
+      "step": 3300
+    },
+    {
+      "epoch": 4.5126107702794815,
+      "grad_norm": 0.966867208480835,
+      "learning_rate": 0.0002,
+      "loss": 1.2398,
+      "step": 3310
+    },
+    {
+      "epoch": 4.5262440354464895,
+      "grad_norm": 1.0127079486846924,
+      "learning_rate": 0.0002,
+      "loss": 1.2537,
+      "step": 3320
+    },
+    {
+      "epoch": 4.539877300613497,
+      "grad_norm": 1.055506706237793,
+      "learning_rate": 0.0002,
+      "loss": 1.2059,
+      "step": 3330
+    },
+    {
+      "epoch": 4.553510565780504,
+      "grad_norm": 0.9831468462944031,
+      "learning_rate": 0.0002,
+      "loss": 1.2958,
+      "step": 3340
+    },
+    {
+      "epoch": 4.567143830947512,
+      "grad_norm": 0.9304661154747009,
+      "learning_rate": 0.0002,
+      "loss": 1.2643,
+      "step": 3350
+    },
+    {
+      "epoch": 4.580777096114519,
+      "grad_norm": 0.9369107484817505,
+      "learning_rate": 0.0002,
+      "loss": 1.3621,
+      "step": 3360
+    },
+    {
+      "epoch": 4.594410361281527,
+      "grad_norm": 1.009506344795227,
+      "learning_rate": 0.0002,
+      "loss": 1.2301,
+      "step": 3370
+    },
+    {
+      "epoch": 4.608043626448534,
+      "grad_norm": 1.0575741529464722,
+      "learning_rate": 0.0002,
+      "loss": 1.2535,
+      "step": 3380
+    },
+    {
+      "epoch": 4.621676891615542,
+      "grad_norm": 0.9102860689163208,
+      "learning_rate": 0.0002,
+      "loss": 1.1914,
+      "step": 3390
+    },
+    {
+      "epoch": 4.635310156782549,
+      "grad_norm": 0.8111315965652466,
+      "learning_rate": 0.0002,
+      "loss": 1.3156,
+      "step": 3400
+    },
+    {
+      "epoch": 4.648943421949557,
+      "grad_norm": 0.9459649920463562,
+      "learning_rate": 0.0002,
+      "loss": 1.3103,
+      "step": 3410
+    },
+    {
+      "epoch": 4.662576687116564,
+      "grad_norm": 0.9709545969963074,
+      "learning_rate": 0.0002,
+      "loss": 1.3146,
+      "step": 3420
+    },
+    {
+      "epoch": 4.676209952283572,
+      "grad_norm": 0.9909247159957886,
+      "learning_rate": 0.0002,
+      "loss": 1.2958,
+      "step": 3430
+    },
+    {
+      "epoch": 4.689843217450579,
+      "grad_norm": 0.9094610810279846,
+      "learning_rate": 0.0002,
+      "loss": 1.3186,
+      "step": 3440
+    },
+    {
+      "epoch": 4.703476482617587,
+      "grad_norm": 0.9012220501899719,
+      "learning_rate": 0.0002,
+      "loss": 1.3397,
+      "step": 3450
+    },
+    {
+      "epoch": 4.717109747784594,
+      "grad_norm": 0.8669242858886719,
+      "learning_rate": 0.0002,
+      "loss": 1.2595,
+      "step": 3460
+    },
+    {
+      "epoch": 4.730743012951602,
+      "grad_norm": 0.9753699898719788,
+      "learning_rate": 0.0002,
+      "loss": 1.2762,
+      "step": 3470
+    },
+    {
+      "epoch": 4.74437627811861,
+      "grad_norm": 1.0252684354782104,
+      "learning_rate": 0.0002,
+      "loss": 1.2371,
+      "step": 3480
+    },
+    {
+      "epoch": 4.758009543285617,
+      "grad_norm": 1.208098292350769,
+      "learning_rate": 0.0002,
+      "loss": 1.2536,
+      "step": 3490
+    },
+    {
+      "epoch": 4.771642808452625,
+      "grad_norm": 0.8632914423942566,
+      "learning_rate": 0.0002,
+      "loss": 1.2256,
+      "step": 3500
+    },
+    {
+      "epoch": 4.785276073619632,
+      "grad_norm": 1.0084818601608276,
+      "learning_rate": 0.0002,
+      "loss": 1.3062,
+      "step": 3510
+    },
+    {
+      "epoch": 4.79890933878664,
+      "grad_norm": 0.9095172882080078,
+      "learning_rate": 0.0002,
+      "loss": 1.3004,
+      "step": 3520
+    },
+    {
+      "epoch": 4.812542603953647,
+      "grad_norm": 0.9740135669708252,
+      "learning_rate": 0.0002,
+      "loss": 1.263,
+      "step": 3530
+    },
+    {
+      "epoch": 4.826175869120655,
+      "grad_norm": 0.8862348794937134,
+      "learning_rate": 0.0002,
+      "loss": 1.2816,
+      "step": 3540
+    },
+    {
+      "epoch": 4.839809134287662,
+      "grad_norm": 1.0761774778366089,
+      "learning_rate": 0.0002,
+      "loss": 1.2275,
+      "step": 3550
+    },
+    {
+      "epoch": 4.85344239945467,
+      "grad_norm": 1.0134117603302002,
+      "learning_rate": 0.0002,
+      "loss": 1.2257,
+      "step": 3560
+    },
+    {
+      "epoch": 4.867075664621677,
+      "grad_norm": 0.9262851476669312,
+      "learning_rate": 0.0002,
+      "loss": 1.2904,
+      "step": 3570
+    },
+    {
+      "epoch": 4.8807089297886845,
+      "grad_norm": 0.9518504738807678,
+      "learning_rate": 0.0002,
+      "loss": 1.1466,
+      "step": 3580
+    },
+    {
+      "epoch": 4.894342194955692,
+      "grad_norm": 1.10103178024292,
+      "learning_rate": 0.0002,
+      "loss": 1.2741,
+      "step": 3590
+    },
+    {
+      "epoch": 4.9079754601226995,
+      "grad_norm": 1.0133225917816162,
+      "learning_rate": 0.0002,
+      "loss": 1.2592,
+      "step": 3600
+    },
+    {
+      "epoch": 4.9216087252897065,
+      "grad_norm": 0.9637737274169922,
+      "learning_rate": 0.0002,
+      "loss": 1.2856,
+      "step": 3610
+    },
+    {
+      "epoch": 4.935241990456714,
+      "grad_norm": 0.9800633192062378,
+      "learning_rate": 0.0002,
+      "loss": 1.2991,
+      "step": 3620
+    },
+    {
+      "epoch": 4.948875255623722,
+      "grad_norm": 1.0065973997116089,
+      "learning_rate": 0.0002,
+      "loss": 1.2872,
+      "step": 3630
+    },
+    {
+      "epoch": 4.962508520790729,
+      "grad_norm": 0.9354690313339233,
+      "learning_rate": 0.0002,
+      "loss": 1.2408,
+      "step": 3640
+    },
+    {
+      "epoch": 4.976141785957737,
+      "grad_norm": 0.9744119048118591,
+      "learning_rate": 0.0002,
+      "loss": 1.291,
+      "step": 3650
+    },
+    {
+      "epoch": 4.989775051124744,
+      "grad_norm": 0.9357708096504211,
+      "learning_rate": 0.0002,
+      "loss": 1.2513,
+      "step": 3660
+    },
+    {
+      "epoch": 4.999318336741649,
+      "eval_loss": 2.0763096809387207,
+      "eval_runtime": 53.6578,
+      "eval_samples_per_second": 9.449,
+      "eval_steps_per_second": 1.193,
+      "step": 3667
+    },
+    {
+      "epoch": 5.003408316291752,
+      "grad_norm": 1.3171669244766235,
+      "learning_rate": 0.0002,
+      "loss": 1.2323,
+      "step": 3670
+    },
+    {
+      "epoch": 5.017041581458759,
+      "grad_norm": 1.4427374601364136,
+      "learning_rate": 0.0002,
+      "loss": 0.9509,
+      "step": 3680
+    },
+    {
+      "epoch": 5.030674846625767,
+      "grad_norm": 0.9313797354698181,
+      "learning_rate": 0.0002,
+      "loss": 1.011,
+      "step": 3690
+    },
+    {
+      "epoch": 5.044308111792774,
+      "grad_norm": 1.417641282081604,
+      "learning_rate": 0.0002,
+      "loss": 0.9481,
+      "step": 3700
+    },
+    {
+      "epoch": 5.057941376959782,
+      "grad_norm": 1.097440242767334,
+      "learning_rate": 0.0002,
+      "loss": 0.9477,
+      "step": 3710
+    },
+    {
+      "epoch": 5.071574642126789,
+      "grad_norm": 1.4277986288070679,
+      "learning_rate": 0.0002,
+      "loss": 1.0416,
+      "step": 3720
+    },
+    {
+      "epoch": 5.085207907293797,
+      "grad_norm": 1.2520873546600342,
+      "learning_rate": 0.0002,
+      "loss": 0.9718,
+      "step": 3730
+    },
+    {
+      "epoch": 5.098841172460804,
+      "grad_norm": 1.39503812789917,
+      "learning_rate": 0.0002,
+      "loss": 0.9531,
+      "step": 3740
+    },
+    {
+      "epoch": 5.112474437627812,
+      "grad_norm": 1.2345329523086548,
+      "learning_rate": 0.0002,
+      "loss": 0.9658,
+      "step": 3750
+    },
+    {
+      "epoch": 5.126107702794819,
+      "grad_norm": 1.2700239419937134,
+      "learning_rate": 0.0002,
+      "loss": 1.0615,
+      "step": 3760
+    },
+    {
+      "epoch": 5.139740967961827,
+      "grad_norm": 1.5343066453933716,
+      "learning_rate": 0.0002,
+      "loss": 0.993,
+      "step": 3770
+    },
+    {
+      "epoch": 5.153374233128835,
+      "grad_norm": 1.4191608428955078,
+      "learning_rate": 0.0002,
+      "loss": 0.9378,
+      "step": 3780
+    },
+    {
+      "epoch": 5.167007498295842,
+      "grad_norm": 1.4591023921966553,
+      "learning_rate": 0.0002,
+      "loss": 1.0179,
+      "step": 3790
+    },
+    {
+      "epoch": 5.18064076346285,
+      "grad_norm": 1.6158121824264526,
+      "learning_rate": 0.0002,
+      "loss": 1.0143,
+      "step": 3800
+    },
+    {
+      "epoch": 5.194274028629857,
+      "grad_norm": 1.6077582836151123,
+      "learning_rate": 0.0002,
+      "loss": 1.0056,
+      "step": 3810
+    },
+    {
+      "epoch": 5.207907293796865,
+      "grad_norm": 1.2815653085708618,
+      "learning_rate": 0.0002,
+      "loss": 0.9711,
+      "step": 3820
+    },
+    {
+      "epoch": 5.221540558963872,
+      "grad_norm": 1.2427219152450562,
+      "learning_rate": 0.0002,
+      "loss": 1.0131,
+      "step": 3830
+    },
+    {
+      "epoch": 5.23517382413088,
+      "grad_norm": 1.3013232946395874,
+      "learning_rate": 0.0002,
+      "loss": 0.9901,
+      "step": 3840
+    },
+    {
+      "epoch": 5.248807089297887,
+      "grad_norm": 1.4643588066101074,
+      "learning_rate": 0.0002,
+      "loss": 0.9862,
+      "step": 3850
+    },
+    {
+      "epoch": 5.2624403544648946,
+      "grad_norm": 1.2571916580200195,
+      "learning_rate": 0.0002,
+      "loss": 1.0149,
+      "step": 3860
+    },
+    {
+      "epoch": 5.276073619631902,
+      "grad_norm": 1.226682186126709,
+      "learning_rate": 0.0002,
+      "loss": 0.9686,
+      "step": 3870
+    },
+    {
+      "epoch": 5.2897068847989095,
+      "grad_norm": 1.2541271448135376,
+      "learning_rate": 0.0002,
+      "loss": 0.9417,
+      "step": 3880
+    },
+    {
+      "epoch": 5.3033401499659165,
+      "grad_norm": 1.2340261936187744,
+      "learning_rate": 0.0002,
+      "loss": 0.9767,
+      "step": 3890
+    },
+    {
+      "epoch": 5.316973415132924,
+      "grad_norm": 1.345527172088623,
+      "learning_rate": 0.0002,
+      "loss": 1.0173,
+      "step": 3900
+    },
+    {
+      "epoch": 5.3306066802999315,
+      "grad_norm": 1.2128909826278687,
+      "learning_rate": 0.0002,
+      "loss": 1.0638,
+      "step": 3910
+    },
+    {
+      "epoch": 5.344239945466939,
+      "grad_norm": 1.3052637577056885,
+      "learning_rate": 0.0002,
+      "loss": 1.0002,
+      "step": 3920
+    },
+    {
+      "epoch": 5.357873210633947,
+      "grad_norm": 1.1017392873764038,
+      "learning_rate": 0.0002,
+      "loss": 0.9754,
+      "step": 3930
+    },
+    {
+      "epoch": 5.371506475800954,
+      "grad_norm": 1.26950204372406,
+      "learning_rate": 0.0002,
+      "loss": 1.0579,
+      "step": 3940
+    },
+    {
+      "epoch": 5.385139740967962,
+      "grad_norm": 1.3372546434402466,
+      "learning_rate": 0.0002,
+      "loss": 1.0816,
+      "step": 3950
+    },
+    {
+      "epoch": 5.398773006134969,
+      "grad_norm": 1.3115156888961792,
+      "learning_rate": 0.0002,
+      "loss": 1.0529,
+      "step": 3960
+    },
+    {
+      "epoch": 5.412406271301977,
+      "grad_norm": 1.3511474132537842,
+      "learning_rate": 0.0002,
+      "loss": 1.1179,
+      "step": 3970
+    },
+    {
+      "epoch": 5.426039536468984,
+      "grad_norm": 1.1001893281936646,
+      "learning_rate": 0.0002,
+      "loss": 1.0352,
+      "step": 3980
+    },
+    {
+      "epoch": 5.439672801635992,
+      "grad_norm": 1.2810745239257812,
+      "learning_rate": 0.0002,
+      "loss": 1.0855,
+      "step": 3990
+    },
+    {
+      "epoch": 5.453306066802999,
+      "grad_norm": 1.2999306917190552,
+      "learning_rate": 0.0002,
+      "loss": 1.0573,
+      "step": 4000
+    },
+    {
+      "epoch": 5.466939331970007,
+      "grad_norm": 1.172553300857544,
+      "learning_rate": 0.0002,
+      "loss": 1.0073,
+      "step": 4010
+    },
+    {
+      "epoch": 5.480572597137014,
+      "grad_norm": 1.1483557224273682,
+      "learning_rate": 0.0002,
+      "loss": 1.003,
+      "step": 4020
+    },
+    {
+      "epoch": 5.494205862304022,
+      "grad_norm": 1.4148036241531372,
+      "learning_rate": 0.0002,
+      "loss": 1.0704,
+      "step": 4030
+    },
+    {
+      "epoch": 5.507839127471029,
+      "grad_norm": 1.1611121892929077,
+      "learning_rate": 0.0002,
+      "loss": 1.0519,
+      "step": 4040
+    },
+    {
+      "epoch": 5.521472392638037,
+      "grad_norm": 1.3837119340896606,
+      "learning_rate": 0.0002,
+      "loss": 1.0775,
+      "step": 4050
+    },
+    {
+      "epoch": 5.535105657805044,
+      "grad_norm": 1.3025696277618408,
+      "learning_rate": 0.0002,
+      "loss": 1.0257,
+      "step": 4060
+    },
+    {
+      "epoch": 5.548738922972052,
+      "grad_norm": 1.348091959953308,
+      "learning_rate": 0.0002,
+      "loss": 1.0628,
+      "step": 4070
+    },
+    {
+      "epoch": 5.56237218813906,
+      "grad_norm": 1.3463449478149414,
+      "learning_rate": 0.0002,
+      "loss": 1.0447,
+      "step": 4080
+    },
+    {
+      "epoch": 5.576005453306067,
+      "grad_norm": 1.3904176950454712,
+      "learning_rate": 0.0002,
+      "loss": 1.039,
+      "step": 4090
+    },
+    {
+      "epoch": 5.589638718473074,
+      "grad_norm": 1.2737950086593628,
+      "learning_rate": 0.0002,
+      "loss": 1.0963,
+      "step": 4100
+    },
+    {
+      "epoch": 5.603271983640082,
+      "grad_norm": 1.3311827182769775,
+      "learning_rate": 0.0002,
+      "loss": 1.0441,
+      "step": 4110
+    },
+    {
+      "epoch": 5.61690524880709,
+      "grad_norm": 1.24485182762146,
+      "learning_rate": 0.0002,
+      "loss": 1.0521,
+      "step": 4120
+    },
+    {
+      "epoch": 5.630538513974097,
+      "grad_norm": 1.2724957466125488,
+      "learning_rate": 0.0002,
+      "loss": 1.1103,
+      "step": 4130
+    },
+    {
+      "epoch": 5.644171779141105,
+      "grad_norm": 1.3439847230911255,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 4140
+    },
+    {
+      "epoch": 5.657805044308112,
+      "grad_norm": 1.372359037399292,
+      "learning_rate": 0.0002,
+      "loss": 1.0257,
+      "step": 4150
+    },
+    {
+      "epoch": 5.6714383094751195,
+      "grad_norm": 1.2322949171066284,
+      "learning_rate": 0.0002,
+      "loss": 1.0475,
+      "step": 4160
+    },
+    {
+      "epoch": 5.6850715746421265,
+      "grad_norm": 1.4859193563461304,
+      "learning_rate": 0.0002,
+      "loss": 1.0465,
+      "step": 4170
+    },
+    {
+      "epoch": 5.6987048398091344,
+      "grad_norm": 1.4318448305130005,
+      "learning_rate": 0.0002,
+      "loss": 1.1569,
+      "step": 4180
+    },
+    {
+      "epoch": 5.7123381049761415,
+      "grad_norm": 1.1533565521240234,
+      "learning_rate": 0.0002,
+      "loss": 1.017,
+      "step": 4190
+    },
+    {
+      "epoch": 5.725971370143149,
+      "grad_norm": 1.3009696006774902,
+      "learning_rate": 0.0002,
+      "loss": 1.0948,
+      "step": 4200
+    },
+    {
+      "epoch": 5.739604635310156,
+      "grad_norm": 1.3972162008285522,
+      "learning_rate": 0.0002,
+      "loss": 1.1229,
+      "step": 4210
+    },
+    {
+      "epoch": 5.753237900477164,
+      "grad_norm": 1.2142186164855957,
+      "learning_rate": 0.0002,
+      "loss": 1.033,
+      "step": 4220
+    },
+    {
+      "epoch": 5.766871165644172,
+      "grad_norm": 1.401191234588623,
+      "learning_rate": 0.0002,
+      "loss": 1.0588,
+      "step": 4230
+    },
+    {
+      "epoch": 5.780504430811179,
+      "grad_norm": 1.4124404191970825,
+      "learning_rate": 0.0002,
+      "loss": 1.0722,
+      "step": 4240
+    },
+    {
+      "epoch": 5.794137695978186,
+      "grad_norm": 1.3488332033157349,
+      "learning_rate": 0.0002,
+      "loss": 1.0826,
+      "step": 4250
+    },
+    {
+      "epoch": 5.807770961145194,
+      "grad_norm": 1.3671752214431763,
+      "learning_rate": 0.0002,
+      "loss": 1.0599,
+      "step": 4260
+    },
+    {
+      "epoch": 5.821404226312202,
+      "grad_norm": 1.2608201503753662,
+      "learning_rate": 0.0002,
+      "loss": 1.1294,
+      "step": 4270
+    },
+    {
+      "epoch": 5.835037491479209,
+      "grad_norm": 1.1814045906066895,
+      "learning_rate": 0.0002,
+      "loss": 1.1216,
+      "step": 4280
+    },
+    {
+      "epoch": 5.848670756646217,
+      "grad_norm": 1.4139586687088013,
+      "learning_rate": 0.0002,
+      "loss": 1.0973,
+      "step": 4290
+    },
+    {
+      "epoch": 5.862304021813224,
+      "grad_norm": 1.34248948097229,
+      "learning_rate": 0.0002,
+      "loss": 1.0656,
+      "step": 4300
+    },
+    {
+      "epoch": 5.875937286980232,
+      "grad_norm": 1.1428139209747314,
+      "learning_rate": 0.0002,
+      "loss": 1.0791,
+      "step": 4310
+    },
+    {
+      "epoch": 5.889570552147239,
+      "grad_norm": 1.1941087245941162,
+      "learning_rate": 0.0002,
+      "loss": 1.0556,
+      "step": 4320
+    },
+    {
+      "epoch": 5.903203817314247,
+      "grad_norm": 1.2374001741409302,
+      "learning_rate": 0.0002,
+      "loss": 1.1089,
+      "step": 4330
+    },
+    {
+      "epoch": 5.916837082481254,
+      "grad_norm": 1.4314988851547241,
+      "learning_rate": 0.0002,
+      "loss": 1.0802,
+      "step": 4340
+    },
+    {
+      "epoch": 5.930470347648262,
+      "grad_norm": 1.1286126375198364,
+      "learning_rate": 0.0002,
+      "loss": 1.133,
+      "step": 4350
+    },
+    {
+      "epoch": 5.944103612815269,
+      "grad_norm": 1.25884211063385,
+      "learning_rate": 0.0002,
+      "loss": 1.0807,
+      "step": 4360
+    },
+    {
+      "epoch": 5.957736877982277,
+      "grad_norm": 1.223357915878296,
+      "learning_rate": 0.0002,
+      "loss": 1.1189,
+      "step": 4370
+    },
+    {
+      "epoch": 5.971370143149285,
+      "grad_norm": 1.2173810005187988,
+      "learning_rate": 0.0002,
+      "loss": 1.1335,
+      "step": 4380
+    },
+    {
+      "epoch": 5.985003408316292,
+      "grad_norm": 1.3152292966842651,
+      "learning_rate": 0.0002,
+      "loss": 1.1201,
+      "step": 4390
+    },
+    {
+      "epoch": 5.998636673483299,
+      "grad_norm": 1.5576739311218262,
+      "learning_rate": 0.0002,
+      "loss": 1.1456,
+      "step": 4400
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.3435311317443848,
+      "eval_runtime": 53.6362,
+      "eval_samples_per_second": 9.453,
+      "eval_steps_per_second": 1.193,
+      "step": 4401
+    },
+    {
+      "epoch": 6.012269938650307,
+      "grad_norm": 2.027981758117676,
+      "learning_rate": 0.0002,
+      "loss": 0.8618,
+      "step": 4410
+    },
+    {
+      "epoch": 6.025903203817315,
+      "grad_norm": 1.4775491952896118,
+      "learning_rate": 0.0002,
+      "loss": 0.7702,
+      "step": 4420
+    },
+    {
+      "epoch": 6.039536468984322,
+      "grad_norm": 1.6902967691421509,
+      "learning_rate": 0.0002,
+      "loss": 0.8042,
+      "step": 4430
+    },
+    {
+      "epoch": 6.0531697341513295,
+      "grad_norm": 1.2506479024887085,
+      "learning_rate": 0.0002,
+      "loss": 0.7363,
+      "step": 4440
+    },
+    {
+      "epoch": 6.0668029993183366,
+      "grad_norm": 1.5935661792755127,
+      "learning_rate": 0.0002,
+      "loss": 0.7653,
+      "step": 4450
+    },
+    {
+      "epoch": 6.0804362644853445,
+      "grad_norm": 1.2966011762619019,
+      "learning_rate": 0.0002,
+      "loss": 0.7869,
+      "step": 4460
+    },
+    {
+      "epoch": 6.0940695296523515,
+      "grad_norm": 1.5247948169708252,
+      "learning_rate": 0.0002,
+      "loss": 0.7186,
+      "step": 4470
+    },
+    {
+      "epoch": 6.107702794819359,
+      "grad_norm": 1.6415225267410278,
+      "learning_rate": 0.0002,
+      "loss": 0.7864,
+      "step": 4480
+    },
+    {
+      "epoch": 6.121336059986366,
+      "grad_norm": 1.5510778427124023,
+      "learning_rate": 0.0002,
+      "loss": 0.7561,
+      "step": 4490
+    },
+    {
+      "epoch": 6.134969325153374,
+      "grad_norm": 1.361097812652588,
+      "learning_rate": 0.0002,
+      "loss": 0.7628,
+      "step": 4500
+    },
+    {
+      "epoch": 6.148602590320381,
+      "grad_norm": 1.8347383737564087,
+      "learning_rate": 0.0002,
+      "loss": 0.8053,
+      "step": 4510
+    },
+    {
+      "epoch": 6.162235855487389,
+      "grad_norm": 1.570560097694397,
+      "learning_rate": 0.0002,
+      "loss": 0.8074,
+      "step": 4520
+    },
+    {
+      "epoch": 6.175869120654396,
+      "grad_norm": 1.517993688583374,
+      "learning_rate": 0.0002,
+      "loss": 0.7536,
+      "step": 4530
+    },
+    {
+      "epoch": 6.189502385821404,
+      "grad_norm": 1.4517489671707153,
+      "learning_rate": 0.0002,
+      "loss": 0.8028,
+      "step": 4540
+    },
+    {
+      "epoch": 6.203135650988412,
+      "grad_norm": 1.557098627090454,
+      "learning_rate": 0.0002,
+      "loss": 0.8633,
+      "step": 4550
+    },
+    {
+      "epoch": 6.216768916155419,
+      "grad_norm": 1.7379891872406006,
+      "learning_rate": 0.0002,
+      "loss": 0.7704,
+      "step": 4560
+    },
+    {
+      "epoch": 6.230402181322427,
+      "grad_norm": 2.2292542457580566,
+      "learning_rate": 0.0002,
+      "loss": 0.7341,
+      "step": 4570
+    },
+    {
+      "epoch": 6.244035446489434,
+      "grad_norm": 1.834366798400879,
+      "learning_rate": 0.0002,
+      "loss": 0.7883,
+      "step": 4580
+    },
+    {
+      "epoch": 6.257668711656442,
+      "grad_norm": 1.6755090951919556,
+      "learning_rate": 0.0002,
+      "loss": 0.8222,
+      "step": 4590
+    },
+    {
+      "epoch": 6.271301976823449,
+      "grad_norm": 1.828898549079895,
+      "learning_rate": 0.0002,
+      "loss": 0.8245,
+      "step": 4600
+    },
+    {
+      "epoch": 6.284935241990457,
+      "grad_norm": 1.9773457050323486,
+      "learning_rate": 0.0002,
+      "loss": 0.8116,
+      "step": 4610
+    },
+    {
+      "epoch": 6.298568507157464,
+      "grad_norm": 1.533369541168213,
+      "learning_rate": 0.0002,
+      "loss": 0.811,
+      "step": 4620
+    },
+    {
+      "epoch": 6.312201772324472,
+      "grad_norm": 1.5432997941970825,
+      "learning_rate": 0.0002,
+      "loss": 0.807,
+      "step": 4630
+    },
+    {
+      "epoch": 6.325835037491479,
+      "grad_norm": 1.6686866283416748,
+      "learning_rate": 0.0002,
+      "loss": 0.818,
+      "step": 4640
+    },
+    {
+      "epoch": 6.339468302658487,
+      "grad_norm": 1.545304298400879,
+      "learning_rate": 0.0002,
+      "loss": 0.8656,
+      "step": 4650
+    },
+    {
+      "epoch": 6.353101567825494,
+      "grad_norm": 1.5981945991516113,
+      "learning_rate": 0.0002,
+      "loss": 0.8239,
+      "step": 4660
+    },
+    {
+      "epoch": 6.366734832992502,
+      "grad_norm": 1.6973154544830322,
+      "learning_rate": 0.0002,
+      "loss": 0.8162,
+      "step": 4670
+    },
+    {
+      "epoch": 6.38036809815951,
+      "grad_norm": 1.6782612800598145,
+      "learning_rate": 0.0002,
+      "loss": 0.8377,
+      "step": 4680
+    },
+    {
+      "epoch": 6.394001363326517,
+      "grad_norm": 1.5710086822509766,
+      "learning_rate": 0.0002,
+      "loss": 0.8185,
+      "step": 4690
+    },
+    {
+      "epoch": 6.407634628493525,
+      "grad_norm": 1.7241147756576538,
+      "learning_rate": 0.0002,
+      "loss": 0.7948,
+      "step": 4700
+    },
+    {
+      "epoch": 6.421267893660532,
+      "grad_norm": 1.7736736536026,
+      "learning_rate": 0.0002,
+      "loss": 0.8768,
+      "step": 4710
+    },
+    {
+      "epoch": 6.4349011588275395,
+      "grad_norm": 1.7924901247024536,
+      "learning_rate": 0.0002,
+      "loss": 0.8607,
+      "step": 4720
+    },
+    {
+      "epoch": 6.448534423994547,
+      "grad_norm": 1.4030500650405884,
+      "learning_rate": 0.0002,
+      "loss": 0.832,
+      "step": 4730
+    },
+    {
+      "epoch": 6.4621676891615545,
+      "grad_norm": 1.6925519704818726,
+      "learning_rate": 0.0002,
+      "loss": 0.8806,
+      "step": 4740
+    },
+    {
+      "epoch": 6.4758009543285615,
+      "grad_norm": 1.362905502319336,
+      "learning_rate": 0.0002,
+      "loss": 0.8556,
+      "step": 4750
+    },
+    {
+      "epoch": 6.489434219495569,
+      "grad_norm": 1.5281150341033936,
+      "learning_rate": 0.0002,
+      "loss": 0.838,
+      "step": 4760
+    },
+    {
+      "epoch": 6.5030674846625764,
+      "grad_norm": 1.524671196937561,
+      "learning_rate": 0.0002,
+      "loss": 0.8396,
+      "step": 4770
+    },
+    {
+      "epoch": 6.516700749829584,
+      "grad_norm": 1.7029320001602173,
+      "learning_rate": 0.0002,
+      "loss": 0.8225,
+      "step": 4780
+    },
+    {
+      "epoch": 6.530334014996591,
+      "grad_norm": 1.4663511514663696,
+      "learning_rate": 0.0002,
+      "loss": 0.8377,
+      "step": 4790
+    },
+    {
+      "epoch": 6.543967280163599,
+      "grad_norm": 1.7682101726531982,
+      "learning_rate": 0.0002,
+      "loss": 0.8018,
+      "step": 4800
+    },
+    {
+      "epoch": 6.557600545330606,
+      "grad_norm": 1.6056565046310425,
+      "learning_rate": 0.0002,
+      "loss": 0.8318,
+      "step": 4810
+    },
+    {
+      "epoch": 6.571233810497614,
+      "grad_norm": 1.6552391052246094,
+      "learning_rate": 0.0002,
+      "loss": 0.8747,
+      "step": 4820
+    },
+    {
+      "epoch": 6.584867075664622,
+      "grad_norm": 1.4265215396881104,
+      "learning_rate": 0.0002,
+      "loss": 0.8559,
+      "step": 4830
+    },
+    {
+      "epoch": 6.598500340831629,
+      "grad_norm": 1.6225470304489136,
+      "learning_rate": 0.0002,
+      "loss": 0.8606,
+      "step": 4840
+    },
+    {
+      "epoch": 6.612133605998636,
+      "grad_norm": 1.6568684577941895,
+      "learning_rate": 0.0002,
+      "loss": 0.8817,
+      "step": 4850
+    },
+    {
+      "epoch": 6.625766871165644,
+      "grad_norm": 1.760115146636963,
+      "learning_rate": 0.0002,
+      "loss": 0.8825,
+      "step": 4860
+    },
+    {
+      "epoch": 6.639400136332652,
+      "grad_norm": 1.627966046333313,
+      "learning_rate": 0.0002,
+      "loss": 0.9227,
+      "step": 4870
+    },
+    {
+      "epoch": 6.653033401499659,
+      "grad_norm": 1.7053254842758179,
+      "learning_rate": 0.0002,
+      "loss": 0.8825,
+      "step": 4880
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 1.5339484214782715,
+      "learning_rate": 0.0002,
+      "loss": 0.857,
+      "step": 4890
+    },
+    {
+      "epoch": 6.680299931833674,
+      "grad_norm": 1.5594874620437622,
+      "learning_rate": 0.0002,
+      "loss": 0.8482,
+      "step": 4900
+    },
+    {
+      "epoch": 6.693933197000682,
+      "grad_norm": 1.5322152376174927,
+      "learning_rate": 0.0002,
+      "loss": 0.842,
+      "step": 4910
+    },
+    {
+      "epoch": 6.707566462167689,
+      "grad_norm": 1.733410358428955,
+      "learning_rate": 0.0002,
+      "loss": 0.8049,
+      "step": 4920
+    },
+    {
+      "epoch": 6.721199727334697,
+      "grad_norm": 1.3626887798309326,
+      "learning_rate": 0.0002,
+      "loss": 0.9099,
+      "step": 4930
+    },
+    {
+      "epoch": 6.734832992501704,
+      "grad_norm": 1.6323494911193848,
+      "learning_rate": 0.0002,
+      "loss": 0.9481,
+      "step": 4940
+    },
+    {
+      "epoch": 6.748466257668712,
+      "grad_norm": 1.6548917293548584,
+      "learning_rate": 0.0002,
+      "loss": 0.8803,
+      "step": 4950
+    },
+    {
+      "epoch": 6.762099522835719,
+      "grad_norm": 1.7894278764724731,
+      "learning_rate": 0.0002,
+      "loss": 0.9149,
+      "step": 4960
+    },
+    {
+      "epoch": 6.775732788002727,
+      "grad_norm": 1.7960841655731201,
+      "learning_rate": 0.0002,
+      "loss": 0.9137,
+      "step": 4970
+    },
+    {
+      "epoch": 6.789366053169735,
+      "grad_norm": 1.4888852834701538,
+      "learning_rate": 0.0002,
+      "loss": 0.9088,
+      "step": 4980
+    },
+    {
+      "epoch": 6.802999318336742,
+      "grad_norm": 1.6368865966796875,
+      "learning_rate": 0.0002,
+      "loss": 0.9495,
+      "step": 4990
+    },
+    {
+      "epoch": 6.816632583503749,
+      "grad_norm": 1.7106667757034302,
+      "learning_rate": 0.0002,
+      "loss": 0.9939,
+      "step": 5000
+    },
+    {
+      "epoch": 6.830265848670757,
+      "grad_norm": 4.131956100463867,
+      "learning_rate": 0.0002,
+      "loss": 0.8551,
+      "step": 5010
+    },
+    {
+      "epoch": 6.8438991138377645,
+      "grad_norm": 1.6357536315917969,
+      "learning_rate": 0.0002,
+      "loss": 0.908,
+      "step": 5020
+    },
+    {
+      "epoch": 6.8575323790047715,
+      "grad_norm": 1.621524453163147,
+      "learning_rate": 0.0002,
+      "loss": 0.8661,
+      "step": 5030
+    },
+    {
+      "epoch": 6.871165644171779,
+      "grad_norm": 1.6400790214538574,
+      "learning_rate": 0.0002,
+      "loss": 0.9177,
+      "step": 5040
+    },
+    {
+      "epoch": 6.8847989093387865,
+      "grad_norm": 1.823006272315979,
+      "learning_rate": 0.0002,
+      "loss": 0.9204,
+      "step": 5050
+    },
+    {
+      "epoch": 6.898432174505794,
+      "grad_norm": 1.6328210830688477,
+      "learning_rate": 0.0002,
+      "loss": 0.9133,
+      "step": 5060
+    },
+    {
+      "epoch": 6.912065439672801,
+      "grad_norm": 1.3616089820861816,
+      "learning_rate": 0.0002,
+      "loss": 0.9138,
+      "step": 5070
+    },
+    {
+      "epoch": 6.925698704839809,
+      "grad_norm": 1.7202986478805542,
+      "learning_rate": 0.0002,
+      "loss": 0.8791,
+      "step": 5080
+    },
+    {
+      "epoch": 6.939331970006816,
+      "grad_norm": 1.8145297765731812,
+      "learning_rate": 0.0002,
+      "loss": 0.8331,
+      "step": 5090
+    },
+    {
+      "epoch": 6.952965235173824,
+      "grad_norm": 1.5432910919189453,
+      "learning_rate": 0.0002,
+      "loss": 0.861,
+      "step": 5100
+    },
+    {
+      "epoch": 6.966598500340831,
+      "grad_norm": 1.2784099578857422,
+      "learning_rate": 0.0002,
+      "loss": 0.9282,
+      "step": 5110
+    },
+    {
+      "epoch": 6.980231765507839,
+      "grad_norm": 1.556593894958496,
+      "learning_rate": 0.0002,
+      "loss": 0.9189,
+      "step": 5120
+    },
+    {
+      "epoch": 6.993865030674847,
+      "grad_norm": 1.5102856159210205,
+      "learning_rate": 0.0002,
+      "loss": 0.8961,
+      "step": 5130
+    },
+    {
+      "epoch": 6.999318336741649,
+      "eval_loss": 2.5376713275909424,
+      "eval_runtime": 53.6377,
+      "eval_samples_per_second": 9.452,
+      "eval_steps_per_second": 1.193,
+      "step": 5134
+    },
+    {
+      "epoch": 7.007498295841854,
+      "grad_norm": 1.7083442211151123,
+      "learning_rate": 0.0002,
+      "loss": 0.7888,
+      "step": 5140
+    },
+    {
+      "epoch": 7.021131561008862,
+      "grad_norm": 1.95943021774292,
+      "learning_rate": 0.0002,
+      "loss": 0.581,
+      "step": 5150
+    },
+    {
+      "epoch": 7.034764826175869,
+      "grad_norm": 1.453168511390686,
+      "learning_rate": 0.0002,
+      "loss": 0.5631,
+      "step": 5160
+    },
+    {
+      "epoch": 7.048398091342877,
+      "grad_norm": 2.110145092010498,
+      "learning_rate": 0.0002,
+      "loss": 0.5871,
+      "step": 5170
+    },
+    {
+      "epoch": 7.062031356509884,
+      "grad_norm": 1.567636489868164,
+      "learning_rate": 0.0002,
+      "loss": 0.5418,
+      "step": 5180
+    },
+    {
+      "epoch": 7.075664621676892,
+      "grad_norm": 1.8596835136413574,
+      "learning_rate": 0.0002,
+      "loss": 0.611,
+      "step": 5190
+    },
+    {
+      "epoch": 7.089297886843899,
+      "grad_norm": 1.7342605590820312,
+      "learning_rate": 0.0002,
+      "loss": 0.6174,
+      "step": 5200
+    },
+    {
+      "epoch": 7.102931152010907,
+      "grad_norm": 1.516591191291809,
+      "learning_rate": 0.0002,
+      "loss": 0.5632,
+      "step": 5210
+    },
+    {
+      "epoch": 7.116564417177914,
+      "grad_norm": 1.7696505784988403,
+      "learning_rate": 0.0002,
+      "loss": 0.5977,
+      "step": 5220
+    },
+    {
+      "epoch": 7.130197682344922,
+      "grad_norm": 2.1680636405944824,
+      "learning_rate": 0.0002,
+      "loss": 0.594,
+      "step": 5230
+    },
+    {
+      "epoch": 7.143830947511929,
+      "grad_norm": 1.6825456619262695,
+      "learning_rate": 0.0002,
+      "loss": 0.5885,
+      "step": 5240
+    },
+    {
+      "epoch": 7.157464212678937,
+      "grad_norm": 2.036949634552002,
+      "learning_rate": 0.0002,
+      "loss": 0.6169,
+      "step": 5250
+    },
+    {
+      "epoch": 7.171097477845944,
+      "grad_norm": 1.8820315599441528,
+      "learning_rate": 0.0002,
+      "loss": 0.6561,
+      "step": 5260
+    },
+    {
+      "epoch": 7.184730743012952,
+      "grad_norm": 2.313140630722046,
+      "learning_rate": 0.0002,
+      "loss": 0.6445,
+      "step": 5270
+    },
+    {
+      "epoch": 7.198364008179959,
+      "grad_norm": 2.0305309295654297,
+      "learning_rate": 0.0002,
+      "loss": 0.6265,
+      "step": 5280
+    },
+    {
+      "epoch": 7.211997273346967,
+      "grad_norm": 1.707711100578308,
+      "learning_rate": 0.0002,
+      "loss": 0.5909,
+      "step": 5290
+    },
+    {
+      "epoch": 7.2256305385139745,
+      "grad_norm": 1.687009334564209,
+      "learning_rate": 0.0002,
+      "loss": 0.6321,
+      "step": 5300
+    },
+    {
+      "epoch": 7.2392638036809815,
+      "grad_norm": 2.0011701583862305,
+      "learning_rate": 0.0002,
+      "loss": 0.6435,
+      "step": 5310
+    },
+    {
+      "epoch": 7.2528970688479895,
+      "grad_norm": 1.9455368518829346,
+      "learning_rate": 0.0002,
+      "loss": 0.5955,
+      "step": 5320
+    },
+    {
+      "epoch": 7.2665303340149965,
+      "grad_norm": 1.5780237913131714,
+      "learning_rate": 0.0002,
+      "loss": 0.6644,
+      "step": 5330
+    },
+    {
+      "epoch": 7.280163599182004,
+      "grad_norm": 2.1882123947143555,
+      "learning_rate": 0.0002,
+      "loss": 0.6007,
+      "step": 5340
+    },
+    {
+      "epoch": 7.293796864349011,
+      "grad_norm": 2.089590549468994,
+      "learning_rate": 0.0002,
+      "loss": 0.6055,
+      "step": 5350
+    },
+    {
+      "epoch": 7.307430129516019,
+      "grad_norm": 1.8626707792282104,
+      "learning_rate": 0.0002,
+      "loss": 0.6138,
+      "step": 5360
+    },
+    {
+      "epoch": 7.321063394683026,
+      "grad_norm": 2.127977132797241,
+      "learning_rate": 0.0002,
+      "loss": 0.6269,
+      "step": 5370
+    },
+    {
+      "epoch": 7.334696659850034,
+      "grad_norm": 1.6568187475204468,
+      "learning_rate": 0.0002,
+      "loss": 0.6629,
+      "step": 5380
+    },
+    {
+      "epoch": 7.348329925017041,
+      "grad_norm": 1.5592522621154785,
+      "learning_rate": 0.0002,
+      "loss": 0.6263,
+      "step": 5390
+    },
+    {
+      "epoch": 7.361963190184049,
+      "grad_norm": 1.7897852659225464,
+      "learning_rate": 0.0002,
+      "loss": 0.6351,
+      "step": 5400
+    },
+    {
+      "epoch": 7.375596455351056,
+      "grad_norm": 2.071516275405884,
+      "learning_rate": 0.0002,
+      "loss": 0.6319,
+      "step": 5410
+    },
+    {
+      "epoch": 7.389229720518064,
+      "grad_norm": 2.048238515853882,
+      "learning_rate": 0.0002,
+      "loss": 0.6486,
+      "step": 5420
+    },
+    {
+      "epoch": 7.402862985685071,
+      "grad_norm": 1.770015001296997,
+      "learning_rate": 0.0002,
+      "loss": 0.7037,
+      "step": 5430
+    },
+    {
+      "epoch": 7.416496250852079,
+      "grad_norm": 1.7530136108398438,
+      "learning_rate": 0.0002,
+      "loss": 0.6719,
+      "step": 5440
+    },
+    {
+      "epoch": 7.430129516019086,
+      "grad_norm": 1.8113389015197754,
+      "learning_rate": 0.0002,
+      "loss": 0.6392,
+      "step": 5450
+    },
+    {
+      "epoch": 7.443762781186094,
+      "grad_norm": 1.8129119873046875,
+      "learning_rate": 0.0002,
+      "loss": 0.6589,
+      "step": 5460
+    },
+    {
+      "epoch": 7.457396046353102,
+      "grad_norm": 1.7961417436599731,
+      "learning_rate": 0.0002,
+      "loss": 0.6786,
+      "step": 5470
+    },
+    {
+      "epoch": 7.471029311520109,
+      "grad_norm": 1.8811243772506714,
+      "learning_rate": 0.0002,
+      "loss": 0.6492,
+      "step": 5480
+    },
+    {
+      "epoch": 7.484662576687117,
+      "grad_norm": 1.9619536399841309,
+      "learning_rate": 0.0002,
+      "loss": 0.6442,
+      "step": 5490
+    },
+    {
+      "epoch": 7.498295841854124,
+      "grad_norm": 1.9449920654296875,
+      "learning_rate": 0.0002,
+      "loss": 0.6372,
+      "step": 5500
+    },
+    {
+      "epoch": 7.511929107021132,
+      "grad_norm": 2.0600240230560303,
+      "learning_rate": 0.0002,
+      "loss": 0.6543,
+      "step": 5510
+    },
+    {
+      "epoch": 7.525562372188139,
+      "grad_norm": 1.9339587688446045,
+      "learning_rate": 0.0002,
+      "loss": 0.6695,
+      "step": 5520
+    },
+    {
+      "epoch": 7.539195637355147,
+      "grad_norm": 2.0672056674957275,
+      "learning_rate": 0.0002,
+      "loss": 0.7385,
+      "step": 5530
+    },
+    {
+      "epoch": 7.552828902522154,
+      "grad_norm": 1.8305774927139282,
+      "learning_rate": 0.0002,
+      "loss": 0.6678,
+      "step": 5540
+    },
+    {
+      "epoch": 7.566462167689162,
+      "grad_norm": 1.9546589851379395,
+      "learning_rate": 0.0002,
+      "loss": 0.7,
+      "step": 5550
+    },
+    {
+      "epoch": 7.580095432856169,
+      "grad_norm": 1.657498836517334,
+      "learning_rate": 0.0002,
+      "loss": 0.6481,
+      "step": 5560
+    },
+    {
+      "epoch": 7.593728698023177,
+      "grad_norm": 2.0222396850585938,
+      "learning_rate": 0.0002,
+      "loss": 0.6604,
+      "step": 5570
+    },
+    {
+      "epoch": 7.6073619631901845,
+      "grad_norm": 1.9352941513061523,
+      "learning_rate": 0.0002,
+      "loss": 0.7154,
+      "step": 5580
+    },
+    {
+      "epoch": 7.620995228357192,
+      "grad_norm": 1.9743294715881348,
+      "learning_rate": 0.0002,
+      "loss": 0.6926,
+      "step": 5590
+    },
+    {
+      "epoch": 7.634628493524199,
+      "grad_norm": 1.949228048324585,
+      "learning_rate": 0.0002,
+      "loss": 0.6948,
+      "step": 5600
+    },
+    {
+      "epoch": 7.6482617586912065,
+      "grad_norm": 2.009384870529175,
+      "learning_rate": 0.0002,
+      "loss": 0.6755,
+      "step": 5610
+    },
+    {
+      "epoch": 7.661895023858214,
+      "grad_norm": 1.9622714519500732,
+      "learning_rate": 0.0002,
+      "loss": 0.7467,
+      "step": 5620
+    },
+    {
+      "epoch": 7.675528289025221,
+      "grad_norm": 2.142486810684204,
+      "learning_rate": 0.0002,
+      "loss": 0.7047,
+      "step": 5630
+    },
+    {
+      "epoch": 7.689161554192229,
+      "grad_norm": 2.4306538105010986,
+      "learning_rate": 0.0002,
+      "loss": 0.6908,
+      "step": 5640
+    },
+    {
+      "epoch": 7.702794819359236,
+      "grad_norm": 1.8343422412872314,
+      "learning_rate": 0.0002,
+      "loss": 0.6592,
+      "step": 5650
+    },
+    {
+      "epoch": 7.716428084526244,
+      "grad_norm": 2.1571617126464844,
+      "learning_rate": 0.0002,
+      "loss": 0.7052,
+      "step": 5660
+    },
+    {
+      "epoch": 7.730061349693251,
+      "grad_norm": 2.028083086013794,
+      "learning_rate": 0.0002,
+      "loss": 0.6958,
+      "step": 5670
+    },
+    {
+      "epoch": 7.743694614860259,
+      "grad_norm": 2.0310823917388916,
+      "learning_rate": 0.0002,
+      "loss": 0.6896,
+      "step": 5680
+    },
+    {
+      "epoch": 7.757327880027266,
+      "grad_norm": 1.9675135612487793,
+      "learning_rate": 0.0002,
+      "loss": 0.6927,
+      "step": 5690
+    },
+    {
+      "epoch": 7.770961145194274,
+      "grad_norm": 2.082470417022705,
+      "learning_rate": 0.0002,
+      "loss": 0.6985,
+      "step": 5700
+    },
+    {
+      "epoch": 7.784594410361281,
+      "grad_norm": 1.8454886674880981,
+      "learning_rate": 0.0002,
+      "loss": 0.7519,
+      "step": 5710
+    },
+    {
+      "epoch": 7.798227675528289,
+      "grad_norm": 2.0777692794799805,
+      "learning_rate": 0.0002,
+      "loss": 0.7407,
+      "step": 5720
+    },
+    {
+      "epoch": 7.811860940695297,
+      "grad_norm": 1.751173496246338,
+      "learning_rate": 0.0002,
+      "loss": 0.7149,
+      "step": 5730
+    },
+    {
+      "epoch": 7.825494205862304,
+      "grad_norm": 1.7728252410888672,
+      "learning_rate": 0.0002,
+      "loss": 0.7126,
+      "step": 5740
+    },
+    {
+      "epoch": 7.839127471029311,
+      "grad_norm": 1.9239917993545532,
+      "learning_rate": 0.0002,
+      "loss": 0.7494,
+      "step": 5750
+    },
+    {
+      "epoch": 7.852760736196319,
+      "grad_norm": 2.0526111125946045,
+      "learning_rate": 0.0002,
+      "loss": 0.7374,
+      "step": 5760
+    },
+    {
+      "epoch": 7.866394001363327,
+      "grad_norm": 2.097938060760498,
+      "learning_rate": 0.0002,
+      "loss": 0.713,
+      "step": 5770
+    },
+    {
+      "epoch": 7.880027266530334,
+      "grad_norm": 1.8992373943328857,
+      "learning_rate": 0.0002,
+      "loss": 0.7391,
+      "step": 5780
+    },
+    {
+      "epoch": 7.893660531697342,
+      "grad_norm": 1.812042474746704,
+      "learning_rate": 0.0002,
+      "loss": 0.6744,
+      "step": 5790
+    },
+    {
+      "epoch": 7.907293796864349,
+      "grad_norm": 1.9535222053527832,
+      "learning_rate": 0.0002,
+      "loss": 0.7803,
+      "step": 5800
+    },
+    {
+      "epoch": 7.920927062031357,
+      "grad_norm": 2.0650830268859863,
+      "learning_rate": 0.0002,
+      "loss": 0.6998,
+      "step": 5810
+    },
+    {
+      "epoch": 7.934560327198364,
+      "grad_norm": 1.818130612373352,
+      "learning_rate": 0.0002,
+      "loss": 0.7134,
+      "step": 5820
+    },
+    {
+      "epoch": 7.948193592365372,
+      "grad_norm": 1.9505265951156616,
+      "learning_rate": 0.0002,
+      "loss": 0.7356,
+      "step": 5830
+    },
+    {
+      "epoch": 7.961826857532379,
+      "grad_norm": 2.072112798690796,
+      "learning_rate": 0.0002,
+      "loss": 0.6872,
+      "step": 5840
+    },
+    {
+      "epoch": 7.975460122699387,
+      "grad_norm": 1.6640431880950928,
+      "learning_rate": 0.0002,
+      "loss": 0.6792,
+      "step": 5850
+    },
+    {
+      "epoch": 7.989093387866394,
+      "grad_norm": 1.7920113801956177,
+      "learning_rate": 0.0002,
+      "loss": 0.7391,
+      "step": 5860
+    },
+    {
+      "epoch": 7.994546693933197,
+      "eval_loss": 2.979367971420288,
+      "eval_runtime": 53.6165,
+      "eval_samples_per_second": 9.456,
+      "eval_steps_per_second": 1.194,
+      "step": 5864
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5864,
+  "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": 3.0119700436353024e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/training_args.bin b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..da7142eb13ed7f8418e5055c63a0fe0ca5e1972b
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-5864/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8beac9fdfb91726fdf7473c9e77541aa988c61dc8beaba03293eafbe9c0a376
+size 5560
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/README.md b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/adapter_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/adapter_model.safetensors b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..25a6157dd64c1895e96eba28c31bfe1297c5fb71
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81567cf32cadbaf0117b7ad6c654a6b5fedc1775d91f1bdb0c88027d5c8d77d
+size 143153376
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/optimizer.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0023ef17d16e73687bc471a0c75ff8c35920f5fa
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b56b40b5e5c72dc13141f66816e8b3ddecc7cac5aa6d0b9d49b94287429d35
+size 72886650
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/rng_state.pth b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d745c8a6d6d00d2d456e7c8d01e7c8ce575151e5
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d13d378f48a3b99f4cf51bd02b734679f943a59db3e7293a9045d716b1a0cc3
+size 14244
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/scheduler.pt b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..480830aefb6dd526d5a03844c2ac28aaf126b1ca
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bd2e07a4b2fdc681e2ebaa6e83774d2b06a4ddc96f491816d22089322567c0c
+size 1064
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/special_tokens_map.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/tokenizer.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/tokenizer.model b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/tokenizer_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/trainer_state.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..57f085b44006633b9981cd4bc049ccf265b3a38f
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/trainer_state.json
@@ -0,0 +1,552 @@
+{
+  "best_metric": 1.8171186447143555,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733",
+  "epoch": 0.9993183367416496,
+  "eval_steps": 10,
+  "global_step": 733,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013633265167007498,
+      "grad_norm": 0.7714291214942932,
+      "learning_rate": 0.0002,
+      "loss": 3.0982,
+      "step": 10
+    },
+    {
+      "epoch": 0.027266530334014997,
+      "grad_norm": 0.5473978519439697,
+      "learning_rate": 0.0002,
+      "loss": 2.5206,
+      "step": 20
+    },
+    {
+      "epoch": 0.0408997955010225,
+      "grad_norm": 0.5452795624732971,
+      "learning_rate": 0.0002,
+      "loss": 2.3079,
+      "step": 30
+    },
+    {
+      "epoch": 0.054533060668029994,
+      "grad_norm": 0.5098028779029846,
+      "learning_rate": 0.0002,
+      "loss": 2.0019,
+      "step": 40
+    },
+    {
+      "epoch": 0.0681663258350375,
+      "grad_norm": 0.48062971234321594,
+      "learning_rate": 0.0002,
+      "loss": 1.9333,
+      "step": 50
+    },
+    {
+      "epoch": 0.081799591002045,
+      "grad_norm": 0.4505695104598999,
+      "learning_rate": 0.0002,
+      "loss": 1.9355,
+      "step": 60
+    },
+    {
+      "epoch": 0.09543285616905249,
+      "grad_norm": 0.41609591245651245,
+      "learning_rate": 0.0002,
+      "loss": 1.9312,
+      "step": 70
+    },
+    {
+      "epoch": 0.10906612133605999,
+      "grad_norm": 0.4323892593383789,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 80
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 0.4670293629169464,
+      "learning_rate": 0.0002,
+      "loss": 1.9294,
+      "step": 90
+    },
+    {
+      "epoch": 0.136332651670075,
+      "grad_norm": 0.40623316168785095,
+      "learning_rate": 0.0002,
+      "loss": 1.7946,
+      "step": 100
+    },
+    {
+      "epoch": 0.1499659168370825,
+      "grad_norm": 0.3620383143424988,
+      "learning_rate": 0.0002,
+      "loss": 1.8565,
+      "step": 110
+    },
+    {
+      "epoch": 0.16359918200409,
+      "grad_norm": 0.332218736410141,
+      "learning_rate": 0.0002,
+      "loss": 1.9238,
+      "step": 120
+    },
+    {
+      "epoch": 0.17723244717109748,
+      "grad_norm": 0.4004521667957306,
+      "learning_rate": 0.0002,
+      "loss": 1.93,
+      "step": 130
+    },
+    {
+      "epoch": 0.19086571233810498,
+      "grad_norm": 0.3698360323905945,
+      "learning_rate": 0.0002,
+      "loss": 1.7549,
+      "step": 140
+    },
+    {
+      "epoch": 0.20449897750511248,
+      "grad_norm": 0.3847949504852295,
+      "learning_rate": 0.0002,
+      "loss": 1.8771,
+      "step": 150
+    },
+    {
+      "epoch": 0.21813224267211997,
+      "grad_norm": 0.36843451857566833,
+      "learning_rate": 0.0002,
+      "loss": 1.8316,
+      "step": 160
+    },
+    {
+      "epoch": 0.23176550783912747,
+      "grad_norm": 0.37301021814346313,
+      "learning_rate": 0.0002,
+      "loss": 1.838,
+      "step": 170
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.3718886971473694,
+      "learning_rate": 0.0002,
+      "loss": 1.8909,
+      "step": 180
+    },
+    {
+      "epoch": 0.25903203817314246,
+      "grad_norm": 0.3088490962982178,
+      "learning_rate": 0.0002,
+      "loss": 1.8454,
+      "step": 190
+    },
+    {
+      "epoch": 0.27266530334015,
+      "grad_norm": 0.3611852526664734,
+      "learning_rate": 0.0002,
+      "loss": 1.9254,
+      "step": 200
+    },
+    {
+      "epoch": 0.28629856850715746,
+      "grad_norm": 0.36093324422836304,
+      "learning_rate": 0.0002,
+      "loss": 1.7844,
+      "step": 210
+    },
+    {
+      "epoch": 0.299931833674165,
+      "grad_norm": 0.3250400722026825,
+      "learning_rate": 0.0002,
+      "loss": 1.719,
+      "step": 220
+    },
+    {
+      "epoch": 0.31356509884117245,
+      "grad_norm": 0.3566756248474121,
+      "learning_rate": 0.0002,
+      "loss": 1.8729,
+      "step": 230
+    },
+    {
+      "epoch": 0.32719836400818,
+      "grad_norm": 0.32872408628463745,
+      "learning_rate": 0.0002,
+      "loss": 1.9259,
+      "step": 240
+    },
+    {
+      "epoch": 0.34083162917518744,
+      "grad_norm": 0.3983881175518036,
+      "learning_rate": 0.0002,
+      "loss": 1.9033,
+      "step": 250
+    },
+    {
+      "epoch": 0.35446489434219497,
+      "grad_norm": 0.3571510910987854,
+      "learning_rate": 0.0002,
+      "loss": 1.8588,
+      "step": 260
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 0.3036131262779236,
+      "learning_rate": 0.0002,
+      "loss": 1.8539,
+      "step": 270
+    },
+    {
+      "epoch": 0.38173142467620996,
+      "grad_norm": 0.36512863636016846,
+      "learning_rate": 0.0002,
+      "loss": 1.8572,
+      "step": 280
+    },
+    {
+      "epoch": 0.39536468984321743,
+      "grad_norm": 0.3429736793041229,
+      "learning_rate": 0.0002,
+      "loss": 1.8022,
+      "step": 290
+    },
+    {
+      "epoch": 0.40899795501022496,
+      "grad_norm": 0.3055964708328247,
+      "learning_rate": 0.0002,
+      "loss": 1.8754,
+      "step": 300
+    },
+    {
+      "epoch": 0.4226312201772324,
+      "grad_norm": 0.33801034092903137,
+      "learning_rate": 0.0002,
+      "loss": 1.8384,
+      "step": 310
+    },
+    {
+      "epoch": 0.43626448534423995,
+      "grad_norm": 0.348783016204834,
+      "learning_rate": 0.0002,
+      "loss": 1.7933,
+      "step": 320
+    },
+    {
+      "epoch": 0.4498977505112474,
+      "grad_norm": 0.3057514727115631,
+      "learning_rate": 0.0002,
+      "loss": 1.8451,
+      "step": 330
+    },
+    {
+      "epoch": 0.46353101567825494,
+      "grad_norm": 0.3849763572216034,
+      "learning_rate": 0.0002,
+      "loss": 1.8766,
+      "step": 340
+    },
+    {
+      "epoch": 0.47716428084526247,
+      "grad_norm": 0.30080053210258484,
+      "learning_rate": 0.0002,
+      "loss": 1.8073,
+      "step": 350
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.3595106303691864,
+      "learning_rate": 0.0002,
+      "loss": 1.8548,
+      "step": 360
+    },
+    {
+      "epoch": 0.5044308111792775,
+      "grad_norm": 0.31099820137023926,
+      "learning_rate": 0.0002,
+      "loss": 1.8232,
+      "step": 370
+    },
+    {
+      "epoch": 0.5180640763462849,
+      "grad_norm": 0.3157978355884552,
+      "learning_rate": 0.0002,
+      "loss": 1.7029,
+      "step": 380
+    },
+    {
+      "epoch": 0.5316973415132924,
+      "grad_norm": 0.27960965037345886,
+      "learning_rate": 0.0002,
+      "loss": 1.8265,
+      "step": 390
+    },
+    {
+      "epoch": 0.5453306066803,
+      "grad_norm": 0.3102385103702545,
+      "learning_rate": 0.0002,
+      "loss": 1.7414,
+      "step": 400
+    },
+    {
+      "epoch": 0.5589638718473074,
+      "grad_norm": 0.32828861474990845,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 410
+    },
+    {
+      "epoch": 0.5725971370143149,
+      "grad_norm": 0.29560017585754395,
+      "learning_rate": 0.0002,
+      "loss": 1.8165,
+      "step": 420
+    },
+    {
+      "epoch": 0.5862304021813224,
+      "grad_norm": 0.33316895365715027,
+      "learning_rate": 0.0002,
+      "loss": 1.9455,
+      "step": 430
+    },
+    {
+      "epoch": 0.59986366734833,
+      "grad_norm": 0.30420982837677,
+      "learning_rate": 0.0002,
+      "loss": 1.8241,
+      "step": 440
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 0.32619214057922363,
+      "learning_rate": 0.0002,
+      "loss": 1.7565,
+      "step": 450
+    },
+    {
+      "epoch": 0.6271301976823449,
+      "grad_norm": 0.3603750765323639,
+      "learning_rate": 0.0002,
+      "loss": 1.7945,
+      "step": 460
+    },
+    {
+      "epoch": 0.6407634628493524,
+      "grad_norm": 0.30834096670150757,
+      "learning_rate": 0.0002,
+      "loss": 1.7773,
+      "step": 470
+    },
+    {
+      "epoch": 0.65439672801636,
+      "grad_norm": 0.28756365180015564,
+      "learning_rate": 0.0002,
+      "loss": 1.8058,
+      "step": 480
+    },
+    {
+      "epoch": 0.6680299931833674,
+      "grad_norm": 0.2878406345844269,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 490
+    },
+    {
+      "epoch": 0.6816632583503749,
+      "grad_norm": 0.31329697370529175,
+      "learning_rate": 0.0002,
+      "loss": 1.8581,
+      "step": 500
+    },
+    {
+      "epoch": 0.6952965235173824,
+      "grad_norm": 0.3405822515487671,
+      "learning_rate": 0.0002,
+      "loss": 1.7886,
+      "step": 510
+    },
+    {
+      "epoch": 0.7089297886843899,
+      "grad_norm": 0.305560827255249,
+      "learning_rate": 0.0002,
+      "loss": 1.778,
+      "step": 520
+    },
+    {
+      "epoch": 0.7225630538513974,
+      "grad_norm": 0.2973416745662689,
+      "learning_rate": 0.0002,
+      "loss": 1.7592,
+      "step": 530
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 0.327303946018219,
+      "learning_rate": 0.0002,
+      "loss": 1.8223,
+      "step": 540
+    },
+    {
+      "epoch": 0.7498295841854125,
+      "grad_norm": 0.62595534324646,
+      "learning_rate": 0.0002,
+      "loss": 1.8591,
+      "step": 550
+    },
+    {
+      "epoch": 0.7634628493524199,
+      "grad_norm": 0.3129784166812897,
+      "learning_rate": 0.0002,
+      "loss": 1.7466,
+      "step": 560
+    },
+    {
+      "epoch": 0.7770961145194274,
+      "grad_norm": 0.32496583461761475,
+      "learning_rate": 0.0002,
+      "loss": 1.8035,
+      "step": 570
+    },
+    {
+      "epoch": 0.7907293796864349,
+      "grad_norm": 0.3098868131637573,
+      "learning_rate": 0.0002,
+      "loss": 1.7787,
+      "step": 580
+    },
+    {
+      "epoch": 0.8043626448534424,
+      "grad_norm": 0.30726853013038635,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 590
+    },
+    {
+      "epoch": 0.8179959100204499,
+      "grad_norm": 0.2964220643043518,
+      "learning_rate": 0.0002,
+      "loss": 1.7898,
+      "step": 600
+    },
+    {
+      "epoch": 0.8316291751874574,
+      "grad_norm": 0.32352274656295776,
+      "learning_rate": 0.0002,
+      "loss": 1.8114,
+      "step": 610
+    },
+    {
+      "epoch": 0.8452624403544649,
+      "grad_norm": 0.2938912510871887,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 620
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 0.295559823513031,
+      "learning_rate": 0.0002,
+      "loss": 1.7727,
+      "step": 630
+    },
+    {
+      "epoch": 0.8725289706884799,
+      "grad_norm": 0.34102028608322144,
+      "learning_rate": 0.0002,
+      "loss": 1.9,
+      "step": 640
+    },
+    {
+      "epoch": 0.8861622358554874,
+      "grad_norm": 0.29676181077957153,
+      "learning_rate": 0.0002,
+      "loss": 1.8006,
+      "step": 650
+    },
+    {
+      "epoch": 0.8997955010224948,
+      "grad_norm": 0.3108902871608734,
+      "learning_rate": 0.0002,
+      "loss": 1.8099,
+      "step": 660
+    },
+    {
+      "epoch": 0.9134287661895024,
+      "grad_norm": 0.2690821588039398,
+      "learning_rate": 0.0002,
+      "loss": 1.7955,
+      "step": 670
+    },
+    {
+      "epoch": 0.9270620313565099,
+      "grad_norm": 0.32752540707588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7881,
+      "step": 680
+    },
+    {
+      "epoch": 0.9406952965235174,
+      "grad_norm": 0.8029476404190063,
+      "learning_rate": 0.0002,
+      "loss": 1.7661,
+      "step": 690
+    },
+    {
+      "epoch": 0.9543285616905249,
+      "grad_norm": 0.30534422397613525,
+      "learning_rate": 0.0002,
+      "loss": 1.7733,
+      "step": 700
+    },
+    {
+      "epoch": 0.9679618268575324,
+      "grad_norm": 0.2899954319000244,
+      "learning_rate": 0.0002,
+      "loss": 1.7614,
+      "step": 710
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 0.28814372420310974,
+      "learning_rate": 0.0002,
+      "loss": 1.7845,
+      "step": 720
+    },
+    {
+      "epoch": 0.9952283571915473,
+      "grad_norm": 0.3061596751213074,
+      "learning_rate": 0.0002,
+      "loss": 1.8865,
+      "step": 730
+    },
+    {
+      "epoch": 0.9993183367416496,
+      "eval_loss": 1.8171186447143555,
+      "eval_runtime": 53.6047,
+      "eval_samples_per_second": 9.458,
+      "eval_steps_per_second": 1.194,
+      "step": 733
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5864,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.767530741825536e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/training_args.bin b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..da7142eb13ed7f8418e5055c63a0fe0ca5e1972b
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8beac9fdfb91726fdf7473c9e77541aa988c61dc8beaba03293eafbe9c0a376
+size 5560
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/special_tokens_map.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/tokenizer.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/tokenizer.model b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/tokenizer_config.json b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/training_args.bin b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..da7142eb13ed7f8418e5055c63a0fe0ca5e1972b
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8beac9fdfb91726fdf7473c9e77541aa988c61dc8beaba03293eafbe9c0a376
+size 5560
diff --git a/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/training_log.jsonl b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/training_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..1c955501d718f7a502d8a7a54a70cdf1bf28999c
--- /dev/null
+++ b/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/training_log.jsonl
@@ -0,0 +1,10 @@
+{"epoch": 0.9993183367416496, "step": 733, "epoch_duration": 5468.251661539078, "total_accumulated_duration": 5468.251661539078, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7887.97119140625}, "peak_memory_usage": {"GPU_0": 11696.9921875}, "avg_memory_reserved": {"GPU_0": 12758.0}, "peak_memory_reserved": {"GPU_0": 12758.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.1008, "grad_norm": 0.7675835490226746, "learning_rate": 0.0002, "epoch": 0.013633265167007498, "step": 10}, {"loss": 2.5292, "grad_norm": 0.5283138751983643, "learning_rate": 0.0002, "epoch": 0.027266530334014997, "step": 20}, {"loss": 2.3126, "grad_norm": 0.5684153437614441, "learning_rate": 0.0002, "epoch": 0.0408997955010225, "step": 30}, {"loss": 1.9885, "grad_norm": 0.4469817578792572, "learning_rate": 0.0002, "epoch": 0.054533060668029994, "step": 40}, {"loss": 1.922, "grad_norm": 0.4745156168937683, "learning_rate": 0.0002, "epoch": 0.0681663258350375, "step": 50}, {"loss": 1.9318, "grad_norm": 0.46541205048561096, "learning_rate": 0.0002, "epoch": 0.081799591002045, "step": 60}, {"loss": 1.9332, "grad_norm": 0.42755699157714844, "learning_rate": 0.0002, "epoch": 0.09543285616905249, "step": 70}, {"loss": 1.8678, "grad_norm": 0.46226418018341064, "learning_rate": 0.0002, "epoch": 0.10906612133605999, "step": 80}, {"loss": 1.9255, "grad_norm": 0.4570668637752533, "learning_rate": 0.0002, "epoch": 0.12269938650306748, "step": 90}, {"loss": 1.7914, "grad_norm": 0.4365231394767761, "learning_rate": 0.0002, "epoch": 0.136332651670075, "step": 100}, {"loss": 1.8549, "grad_norm": 0.38550880551338196, "learning_rate": 0.0002, "epoch": 0.1499659168370825, "step": 110}, {"loss": 1.9213, "grad_norm": 0.3430306017398834, "learning_rate": 0.0002, "epoch": 0.16359918200409, "step": 120}, {"loss": 1.9301, "grad_norm": 0.4018137454986572, "learning_rate": 0.0002, "epoch": 0.17723244717109748, "step": 130}, {"loss": 1.7552, "grad_norm": 0.3614208996295929, "learning_rate": 0.0002, "epoch": 0.19086571233810498, "step": 140}, {"loss": 1.8748, "grad_norm": 0.35473498702049255, "learning_rate": 0.0002, "epoch": 0.20449897750511248, "step": 150}, {"loss": 1.8337, "grad_norm": 0.35780423879623413, "learning_rate": 0.0002, "epoch": 0.21813224267211997, "step": 160}, {"loss": 1.8387, "grad_norm": 0.3678103983402252, "learning_rate": 0.0002, "epoch": 0.23176550783912747, "step": 170}, {"loss": 1.8921, "grad_norm": 0.3819291293621063, "learning_rate": 0.0002, "epoch": 0.24539877300613497, "step": 180}, {"loss": 1.8451, "grad_norm": 0.3084178864955902, "learning_rate": 0.0002, "epoch": 0.25903203817314246, "step": 190}, {"loss": 1.9236, "grad_norm": 0.3720385432243347, "learning_rate": 0.0002, "epoch": 0.27266530334015, "step": 200}, {"loss": 1.783, "grad_norm": 0.3562837541103363, "learning_rate": 0.0002, "epoch": 0.28629856850715746, "step": 210}, {"loss": 1.7199, "grad_norm": 0.32655608654022217, "learning_rate": 0.0002, "epoch": 0.299931833674165, "step": 220}, {"loss": 1.8723, "grad_norm": 0.36233681440353394, "learning_rate": 0.0002, "epoch": 0.31356509884117245, "step": 230}, {"loss": 1.9256, "grad_norm": 0.32759809494018555, "learning_rate": 0.0002, "epoch": 0.32719836400818, "step": 240}, {"loss": 1.9013, "grad_norm": 0.4187735915184021, "learning_rate": 0.0002, "epoch": 0.34083162917518744, "step": 250}, {"loss": 1.8576, "grad_norm": 0.37079235911369324, "learning_rate": 0.0002, "epoch": 0.35446489434219497, "step": 260}, {"loss": 1.8521, "grad_norm": 0.383121520280838, "learning_rate": 0.0002, "epoch": 0.36809815950920244, "step": 270}, {"loss": 1.8569, "grad_norm": 0.3556862771511078, "learning_rate": 0.0002, "epoch": 0.38173142467620996, "step": 280}, {"loss": 1.8037, "grad_norm": 0.3265869915485382, "learning_rate": 0.0002, "epoch": 0.39536468984321743, "step": 290}, {"loss": 1.874, "grad_norm": 0.30522024631500244, "learning_rate": 0.0002, "epoch": 0.40899795501022496, "step": 300}, {"loss": 1.8346, "grad_norm": 0.33467918634414673, "learning_rate": 0.0002, "epoch": 0.4226312201772324, "step": 310}, {"loss": 1.7928, "grad_norm": 0.498266339302063, "learning_rate": 0.0002, "epoch": 0.43626448534423995, "step": 320}, {"loss": 1.8451, "grad_norm": 0.3135899305343628, "learning_rate": 0.0002, "epoch": 0.4498977505112474, "step": 330}, {"loss": 1.8759, "grad_norm": 0.39500781893730164, "learning_rate": 0.0002, "epoch": 0.46353101567825494, "step": 340}, {"loss": 1.8084, "grad_norm": 0.3009391129016876, "learning_rate": 0.0002, "epoch": 0.47716428084526247, "step": 350}, {"loss": 1.8536, "grad_norm": 0.36251890659332275, "learning_rate": 0.0002, "epoch": 0.49079754601226994, "step": 360}, {"loss": 1.8244, "grad_norm": 0.31266191601753235, "learning_rate": 0.0002, "epoch": 0.5044308111792775, "step": 370}, {"loss": 1.7026, "grad_norm": 0.3183344900608063, "learning_rate": 0.0002, "epoch": 0.5180640763462849, "step": 380}, {"loss": 1.8262, "grad_norm": 0.28234341740608215, "learning_rate": 0.0002, "epoch": 0.5316973415132924, "step": 390}, {"loss": 1.7407, "grad_norm": 0.3185858726501465, "learning_rate": 0.0002, "epoch": 0.5453306066803, "step": 400}, {"loss": 1.7446, "grad_norm": 0.4044371247291565, "learning_rate": 0.0002, "epoch": 0.5589638718473074, "step": 410}, {"loss": 1.8182, "grad_norm": 0.29381003975868225, "learning_rate": 0.0002, "epoch": 0.5725971370143149, "step": 420}, {"loss": 1.9416, "grad_norm": 0.3450601398944855, "learning_rate": 0.0002, "epoch": 0.5862304021813224, "step": 430}, {"loss": 1.82, "grad_norm": 0.3334464728832245, "learning_rate": 0.0002, "epoch": 0.59986366734833, "step": 440}, {"loss": 1.7556, "grad_norm": 0.3518504500389099, "learning_rate": 0.0002, "epoch": 0.6134969325153374, "step": 450}, {"loss": 1.7957, "grad_norm": 0.3641590178012848, "learning_rate": 0.0002, "epoch": 0.6271301976823449, "step": 460}, {"loss": 1.7757, "grad_norm": 0.36691612005233765, "learning_rate": 0.0002, "epoch": 0.6407634628493524, "step": 470}, {"loss": 1.805, "grad_norm": 0.28644075989723206, "learning_rate": 0.0002, "epoch": 0.65439672801636, "step": 480}, {"loss": 1.7429, "grad_norm": 0.29623064398765564, "learning_rate": 0.0002, "epoch": 0.6680299931833674, "step": 490}, {"loss": 1.8579, "grad_norm": 0.30514174699783325, "learning_rate": 0.0002, "epoch": 0.6816632583503749, "step": 500}, {"loss": 1.7897, "grad_norm": 0.33950939774513245, "learning_rate": 0.0002, "epoch": 0.6952965235173824, "step": 510}, {"loss": 1.7791, "grad_norm": 0.3081190288066864, "learning_rate": 0.0002, "epoch": 0.7089297886843899, "step": 520}, {"loss": 1.76, "grad_norm": 0.29419979453086853, "learning_rate": 0.0002, "epoch": 0.7225630538513974, "step": 530}, {"loss": 1.8211, "grad_norm": 0.3383752107620239, "learning_rate": 0.0002, "epoch": 0.7361963190184049, "step": 540}, {"loss": 1.8593, "grad_norm": 0.2980792820453644, "learning_rate": 0.0002, "epoch": 0.7498295841854125, "step": 550}, {"loss": 1.7466, "grad_norm": 0.3419261872768402, "learning_rate": 0.0002, "epoch": 0.7634628493524199, "step": 560}, {"loss": 1.8007, "grad_norm": 0.31977590918540955, "learning_rate": 0.0002, "epoch": 0.7770961145194274, "step": 570}, {"loss": 1.7766, "grad_norm": 0.3168697655200958, "learning_rate": 0.0002, "epoch": 0.7907293796864349, "step": 580}, {"loss": 1.7201, "grad_norm": 0.31143882870674133, "learning_rate": 0.0002, "epoch": 0.8043626448534424, "step": 590}, {"loss": 1.7912, "grad_norm": 0.29171547293663025, "learning_rate": 0.0002, "epoch": 0.8179959100204499, "step": 600}, {"loss": 1.8147, "grad_norm": 0.3080858886241913, "learning_rate": 0.0002, "epoch": 0.8316291751874574, "step": 610}, {"loss": 1.81, "grad_norm": 0.2734144926071167, "learning_rate": 0.0002, "epoch": 0.8452624403544649, "step": 620}, {"loss": 1.7716, "grad_norm": 0.2898387014865875, "learning_rate": 0.0002, "epoch": 0.8588957055214724, "step": 630}, {"loss": 1.9015, "grad_norm": 0.34029147028923035, "learning_rate": 0.0002, "epoch": 0.8725289706884799, "step": 640}, {"loss": 1.8012, "grad_norm": 0.28186970949172974, "learning_rate": 0.0002, "epoch": 0.8861622358554874, "step": 650}, {"loss": 1.8097, "grad_norm": 0.3147708773612976, "learning_rate": 0.0002, "epoch": 0.8997955010224948, "step": 660}, {"loss": 1.7954, "grad_norm": 0.26419591903686523, "learning_rate": 0.0002, "epoch": 0.9134287661895024, "step": 670}, {"loss": 1.7877, "grad_norm": 0.3258209824562073, "learning_rate": 0.0002, "epoch": 0.9270620313565099, "step": 680}, {"loss": 1.7631, "grad_norm": 0.272344708442688, "learning_rate": 0.0002, "epoch": 0.9406952965235174, "step": 690}, {"loss": 1.7767, "grad_norm": 0.3036558926105499, "learning_rate": 0.0002, "epoch": 0.9543285616905249, "step": 700}, {"loss": 1.76, "grad_norm": 0.2845146059989929, "learning_rate": 0.0002, "epoch": 0.9679618268575324, "step": 710}, {"loss": 1.7801, "grad_norm": 0.28313693404197693, "learning_rate": 0.0002, "epoch": 0.9815950920245399, "step": 720}, {"loss": 1.8849, "grad_norm": 0.3092978596687317, "learning_rate": 0.0002, "epoch": 0.9952283571915473, "step": 730}]}
+{"epoch": 0.9993183367416496, "step": 733, "epoch_duration": 2911.6444346904755, "total_accumulated_duration": 2911.6444346904755, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7887.97119140625}, "peak_memory_usage": {"GPU_0": 11696.9921875}, "avg_memory_reserved": {"GPU_0": 12758.0}, "peak_memory_reserved": {"GPU_0": 12758.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.0948, "grad_norm": 0.7837588787078857, "learning_rate": 0.0002, "epoch": 0.013633265167007498, "step": 10}, {"loss": 2.5115, "grad_norm": 0.5483142733573914, "learning_rate": 0.0002, "epoch": 0.027266530334014997, "step": 20}, {"loss": 2.3159, "grad_norm": 0.5654940605163574, "learning_rate": 0.0002, "epoch": 0.0408997955010225, "step": 30}, {"loss": 1.9985, "grad_norm": 0.47807976603507996, "learning_rate": 0.0002, "epoch": 0.054533060668029994, "step": 40}, {"loss": 1.9277, "grad_norm": 0.5375542044639587, "learning_rate": 0.0002, "epoch": 0.0681663258350375, "step": 50}, {"loss": 1.9403, "grad_norm": 0.4766482412815094, "learning_rate": 0.0002, "epoch": 0.081799591002045, "step": 60}, {"loss": 1.9332, "grad_norm": 0.39935776591300964, "learning_rate": 0.0002, "epoch": 0.09543285616905249, "step": 70}, {"loss": 1.866, "grad_norm": 0.45399025082588196, "learning_rate": 0.0002, "epoch": 0.10906612133605999, "step": 80}, {"loss": 1.9304, "grad_norm": 0.46186086535453796, "learning_rate": 0.0002, "epoch": 0.12269938650306748, "step": 90}, {"loss": 1.795, "grad_norm": 0.43516600131988525, "learning_rate": 0.0002, "epoch": 0.136332651670075, "step": 100}, {"loss": 1.8606, "grad_norm": 0.3928009569644928, "learning_rate": 0.0002, "epoch": 0.1499659168370825, "step": 110}, {"loss": 1.9286, "grad_norm": 0.3584233522415161, "learning_rate": 0.0002, "epoch": 0.16359918200409, "step": 120}, {"loss": 1.9304, "grad_norm": 0.3833671808242798, "learning_rate": 0.0002, "epoch": 0.17723244717109748, "step": 130}, {"loss": 1.7561, "grad_norm": 0.36329957842826843, "learning_rate": 0.0002, "epoch": 0.19086571233810498, "step": 140}, {"loss": 1.8758, "grad_norm": 0.35854387283325195, "learning_rate": 0.0002, "epoch": 0.20449897750511248, "step": 150}, {"loss": 1.8374, "grad_norm": 0.36146774888038635, "learning_rate": 0.0002, "epoch": 0.21813224267211997, "step": 160}, {"loss": 1.8389, "grad_norm": 0.3533250093460083, "learning_rate": 0.0002, "epoch": 0.23176550783912747, "step": 170}, {"loss": 1.8929, "grad_norm": 0.36693814396858215, "learning_rate": 0.0002, "epoch": 0.24539877300613497, "step": 180}, {"loss": 1.847, "grad_norm": 0.3156248927116394, "learning_rate": 0.0002, "epoch": 0.25903203817314246, "step": 190}, {"loss": 1.925, "grad_norm": 0.34866863489151, "learning_rate": 0.0002, "epoch": 0.27266530334015, "step": 200}, {"loss": 1.7853, "grad_norm": 0.36728984117507935, "learning_rate": 0.0002, "epoch": 0.28629856850715746, "step": 210}, {"loss": 1.719, "grad_norm": 0.3290116786956787, "learning_rate": 0.0002, "epoch": 0.299931833674165, "step": 220}, {"loss": 1.8711, "grad_norm": 0.4102158844470978, "learning_rate": 0.0002, "epoch": 0.31356509884117245, "step": 230}, {"loss": 1.9289, "grad_norm": 0.3361101746559143, "learning_rate": 0.0002, "epoch": 0.32719836400818, "step": 240}, {"loss": 1.9025, "grad_norm": 0.4293116629123688, "learning_rate": 0.0002, "epoch": 0.34083162917518744, "step": 250}, {"loss": 1.86, "grad_norm": 0.36179205775260925, "learning_rate": 0.0002, "epoch": 0.35446489434219497, "step": 260}, {"loss": 1.8537, "grad_norm": 0.3195672929286957, "learning_rate": 0.0002, "epoch": 0.36809815950920244, "step": 270}, {"loss": 1.8587, "grad_norm": 0.373018354177475, "learning_rate": 0.0002, "epoch": 0.38173142467620996, "step": 280}, {"loss": 1.8016, "grad_norm": 0.33340632915496826, "learning_rate": 0.0002, "epoch": 0.39536468984321743, "step": 290}, {"loss": 1.8732, "grad_norm": 0.29840829968452454, "learning_rate": 0.0002, "epoch": 0.40899795501022496, "step": 300}, {"loss": 1.8369, "grad_norm": 0.35418516397476196, "learning_rate": 0.0002, "epoch": 0.4226312201772324, "step": 310}, {"loss": 1.7929, "grad_norm": 0.38273194432258606, "learning_rate": 0.0002, "epoch": 0.43626448534423995, "step": 320}, {"loss": 1.8441, "grad_norm": 0.30469033122062683, "learning_rate": 0.0002, "epoch": 0.4498977505112474, "step": 330}, {"loss": 1.8736, "grad_norm": 0.3807629644870758, "learning_rate": 0.0002, "epoch": 0.46353101567825494, "step": 340}, {"loss": 1.8064, "grad_norm": 0.2952139377593994, "learning_rate": 0.0002, "epoch": 0.47716428084526247, "step": 350}, {"loss": 1.8532, "grad_norm": 0.358732134103775, "learning_rate": 0.0002, "epoch": 0.49079754601226994, "step": 360}, {"loss": 1.8269, "grad_norm": 0.3062337636947632, "learning_rate": 0.0002, "epoch": 0.5044308111792775, "step": 370}, {"loss": 1.704, "grad_norm": 0.3123418986797333, "learning_rate": 0.0002, "epoch": 0.5180640763462849, "step": 380}, {"loss": 1.8267, "grad_norm": 0.2843833267688751, "learning_rate": 0.0002, "epoch": 0.5316973415132924, "step": 390}, {"loss": 1.7403, "grad_norm": 0.36187559366226196, "learning_rate": 0.0002, "epoch": 0.5453306066803, "step": 400}, {"loss": 1.7429, "grad_norm": 0.3211730420589447, "learning_rate": 0.0002, "epoch": 0.5589638718473074, "step": 410}, {"loss": 1.8191, "grad_norm": 0.31190505623817444, "learning_rate": 0.0002, "epoch": 0.5725971370143149, "step": 420}, {"loss": 1.946, "grad_norm": 0.44237005710601807, "learning_rate": 0.0002, "epoch": 0.5862304021813224, "step": 430}, {"loss": 1.8204, "grad_norm": 0.30353036522865295, "learning_rate": 0.0002, "epoch": 0.59986366734833, "step": 440}, {"loss": 1.7575, "grad_norm": 0.3608725666999817, "learning_rate": 0.0002, "epoch": 0.6134969325153374, "step": 450}, {"loss": 1.795, "grad_norm": 0.30137816071510315, "learning_rate": 0.0002, "epoch": 0.6271301976823449, "step": 460}, {"loss": 1.7759, "grad_norm": 0.31448695063591003, "learning_rate": 0.0002, "epoch": 0.6407634628493524, "step": 470}, {"loss": 1.8057, "grad_norm": 0.2958511412143707, "learning_rate": 0.0002, "epoch": 0.65439672801636, "step": 480}, {"loss": 1.7433, "grad_norm": 0.28700390458106995, "learning_rate": 0.0002, "epoch": 0.6680299931833674, "step": 490}, {"loss": 1.8576, "grad_norm": 0.31016767024993896, "learning_rate": 0.0002, "epoch": 0.6816632583503749, "step": 500}, {"loss": 1.7904, "grad_norm": 0.33729124069213867, "learning_rate": 0.0002, "epoch": 0.6952965235173824, "step": 510}, {"loss": 1.7786, "grad_norm": 0.32536232471466064, "learning_rate": 0.0002, "epoch": 0.7089297886843899, "step": 520}, {"loss": 1.7588, "grad_norm": 0.30095645785331726, "learning_rate": 0.0002, "epoch": 0.7225630538513974, "step": 530}, {"loss": 1.8186, "grad_norm": 0.3496246635913849, "learning_rate": 0.0002, "epoch": 0.7361963190184049, "step": 540}, {"loss": 1.8587, "grad_norm": 0.30101504921913147, "learning_rate": 0.0002, "epoch": 0.7498295841854125, "step": 550}, {"loss": 1.7467, "grad_norm": 0.3162820637226105, "learning_rate": 0.0002, "epoch": 0.7634628493524199, "step": 560}, {"loss": 1.7999, "grad_norm": 0.31092569231987, "learning_rate": 0.0002, "epoch": 0.7770961145194274, "step": 570}, {"loss": 1.7794, "grad_norm": 0.31278666853904724, "learning_rate": 0.0002, "epoch": 0.7907293796864349, "step": 580}, {"loss": 1.7213, "grad_norm": 0.30959561467170715, "learning_rate": 0.0002, "epoch": 0.8043626448534424, "step": 590}, {"loss": 1.7884, "grad_norm": 0.3000122606754303, "learning_rate": 0.0002, "epoch": 0.8179959100204499, "step": 600}, {"loss": 1.8163, "grad_norm": 0.31050294637680054, "learning_rate": 0.0002, "epoch": 0.8316291751874574, "step": 610}, {"loss": 1.8064, "grad_norm": 0.27638447284698486, "learning_rate": 0.0002, "epoch": 0.8452624403544649, "step": 620}, {"loss": 1.7691, "grad_norm": 0.2875880300998688, "learning_rate": 0.0002, "epoch": 0.8588957055214724, "step": 630}, {"loss": 1.9008, "grad_norm": 0.42822250723838806, "learning_rate": 0.0002, "epoch": 0.8725289706884799, "step": 640}, {"loss": 1.7996, "grad_norm": 0.28577205538749695, "learning_rate": 0.0002, "epoch": 0.8861622358554874, "step": 650}, {"loss": 1.8084, "grad_norm": 0.30910760164260864, "learning_rate": 0.0002, "epoch": 0.8997955010224948, "step": 660}, {"loss": 1.7981, "grad_norm": 0.2699502408504486, "learning_rate": 0.0002, "epoch": 0.9134287661895024, "step": 670}, {"loss": 1.7894, "grad_norm": 0.4193672835826874, "learning_rate": 0.0002, "epoch": 0.9270620313565099, "step": 680}, {"loss": 1.7638, "grad_norm": 0.29555195569992065, "learning_rate": 0.0002, "epoch": 0.9406952965235174, "step": 690}, {"loss": 1.7787, "grad_norm": 0.29588839411735535, "learning_rate": 0.0002, "epoch": 0.9543285616905249, "step": 700}, {"loss": 1.7607, "grad_norm": 0.28271564841270447, "learning_rate": 0.0002, "epoch": 0.9679618268575324, "step": 710}, {"loss": 1.7813, "grad_norm": 0.2848884165287018, "learning_rate": 0.0002, "epoch": 0.9815950920245399, "step": 720}, {"loss": 1.8849, "grad_norm": 0.3218976557254791, "learning_rate": 0.0002, "epoch": 0.9952283571915473, "step": 730}]}
+{"epoch": 0.9993183367416496, "step": 733, "epoch_duration": 1097.0387206077576, "total_accumulated_duration": 1097.0387206077576, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7887.97119140625}, "peak_memory_usage": {"GPU_0": 11696.9921875}, "avg_memory_reserved": {"GPU_0": 12758.0}, "peak_memory_reserved": {"GPU_0": 12758.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 3.0982, "grad_norm": 0.7714291214942932, "learning_rate": 0.0002, "epoch": 0.013633265167007498, "step": 10}, {"loss": 2.5206, "grad_norm": 0.5473978519439697, "learning_rate": 0.0002, "epoch": 0.027266530334014997, "step": 20}, {"loss": 2.3079, "grad_norm": 0.5452795624732971, "learning_rate": 0.0002, "epoch": 0.0408997955010225, "step": 30}, {"loss": 2.0019, "grad_norm": 0.5098028779029846, "learning_rate": 0.0002, "epoch": 0.054533060668029994, "step": 40}, {"loss": 1.9333, "grad_norm": 0.48062971234321594, "learning_rate": 0.0002, "epoch": 0.0681663258350375, "step": 50}, {"loss": 1.9355, "grad_norm": 0.4505695104598999, "learning_rate": 0.0002, "epoch": 0.081799591002045, "step": 60}, {"loss": 1.9312, "grad_norm": 0.41609591245651245, "learning_rate": 0.0002, "epoch": 0.09543285616905249, "step": 70}, {"loss": 1.8656, "grad_norm": 0.4323892593383789, "learning_rate": 0.0002, "epoch": 0.10906612133605999, "step": 80}, {"loss": 1.9294, "grad_norm": 0.4670293629169464, "learning_rate": 0.0002, "epoch": 0.12269938650306748, "step": 90}, {"loss": 1.7946, "grad_norm": 0.40623316168785095, "learning_rate": 0.0002, "epoch": 0.136332651670075, "step": 100}, {"loss": 1.8565, "grad_norm": 0.3620383143424988, "learning_rate": 0.0002, "epoch": 0.1499659168370825, "step": 110}, {"loss": 1.9238, "grad_norm": 0.332218736410141, "learning_rate": 0.0002, "epoch": 0.16359918200409, "step": 120}, {"loss": 1.93, "grad_norm": 0.4004521667957306, "learning_rate": 0.0002, "epoch": 0.17723244717109748, "step": 130}, {"loss": 1.7549, "grad_norm": 0.3698360323905945, "learning_rate": 0.0002, "epoch": 0.19086571233810498, "step": 140}, {"loss": 1.8771, "grad_norm": 0.3847949504852295, "learning_rate": 0.0002, "epoch": 0.20449897750511248, "step": 150}, {"loss": 1.8316, "grad_norm": 0.36843451857566833, "learning_rate": 0.0002, "epoch": 0.21813224267211997, "step": 160}, {"loss": 1.838, "grad_norm": 0.37301021814346313, "learning_rate": 0.0002, "epoch": 0.23176550783912747, "step": 170}, {"loss": 1.8909, "grad_norm": 0.3718886971473694, "learning_rate": 0.0002, "epoch": 0.24539877300613497, "step": 180}, {"loss": 1.8454, "grad_norm": 0.3088490962982178, "learning_rate": 0.0002, "epoch": 0.25903203817314246, "step": 190}, {"loss": 1.9254, "grad_norm": 0.3611852526664734, "learning_rate": 0.0002, "epoch": 0.27266530334015, "step": 200}, {"loss": 1.7844, "grad_norm": 0.36093324422836304, "learning_rate": 0.0002, "epoch": 0.28629856850715746, "step": 210}, {"loss": 1.719, "grad_norm": 0.3250400722026825, "learning_rate": 0.0002, "epoch": 0.299931833674165, "step": 220}, {"loss": 1.8729, "grad_norm": 0.3566756248474121, "learning_rate": 0.0002, "epoch": 0.31356509884117245, "step": 230}, {"loss": 1.9259, "grad_norm": 0.32872408628463745, "learning_rate": 0.0002, "epoch": 0.32719836400818, "step": 240}, {"loss": 1.9033, "grad_norm": 0.3983881175518036, "learning_rate": 0.0002, "epoch": 0.34083162917518744, "step": 250}, {"loss": 1.8588, "grad_norm": 0.3571510910987854, "learning_rate": 0.0002, "epoch": 0.35446489434219497, "step": 260}, {"loss": 1.8539, "grad_norm": 0.3036131262779236, "learning_rate": 0.0002, "epoch": 0.36809815950920244, "step": 270}, {"loss": 1.8572, "grad_norm": 0.36512863636016846, "learning_rate": 0.0002, "epoch": 0.38173142467620996, "step": 280}, {"loss": 1.8022, "grad_norm": 0.3429736793041229, "learning_rate": 0.0002, "epoch": 0.39536468984321743, "step": 290}, {"loss": 1.8754, "grad_norm": 0.3055964708328247, "learning_rate": 0.0002, "epoch": 0.40899795501022496, "step": 300}, {"loss": 1.8384, "grad_norm": 0.33801034092903137, "learning_rate": 0.0002, "epoch": 0.4226312201772324, "step": 310}, {"loss": 1.7933, "grad_norm": 0.348783016204834, "learning_rate": 0.0002, "epoch": 0.43626448534423995, "step": 320}, {"loss": 1.8451, "grad_norm": 0.3057514727115631, "learning_rate": 0.0002, "epoch": 0.4498977505112474, "step": 330}, {"loss": 1.8766, "grad_norm": 0.3849763572216034, "learning_rate": 0.0002, "epoch": 0.46353101567825494, "step": 340}, {"loss": 1.8073, "grad_norm": 0.30080053210258484, "learning_rate": 0.0002, "epoch": 0.47716428084526247, "step": 350}, {"loss": 1.8548, "grad_norm": 0.3595106303691864, "learning_rate": 0.0002, "epoch": 0.49079754601226994, "step": 360}, {"loss": 1.8232, "grad_norm": 0.31099820137023926, "learning_rate": 0.0002, "epoch": 0.5044308111792775, "step": 370}, {"loss": 1.7029, "grad_norm": 0.3157978355884552, "learning_rate": 0.0002, "epoch": 0.5180640763462849, "step": 380}, {"loss": 1.8265, "grad_norm": 0.27960965037345886, "learning_rate": 0.0002, "epoch": 0.5316973415132924, "step": 390}, {"loss": 1.7414, "grad_norm": 0.3102385103702545, "learning_rate": 0.0002, "epoch": 0.5453306066803, "step": 400}, {"loss": 1.7461, "grad_norm": 0.32828861474990845, "learning_rate": 0.0002, "epoch": 0.5589638718473074, "step": 410}, {"loss": 1.8165, "grad_norm": 0.29560017585754395, "learning_rate": 0.0002, "epoch": 0.5725971370143149, "step": 420}, {"loss": 1.9455, "grad_norm": 0.33316895365715027, "learning_rate": 0.0002, "epoch": 0.5862304021813224, "step": 430}, {"loss": 1.8241, "grad_norm": 0.30420982837677, "learning_rate": 0.0002, "epoch": 0.59986366734833, "step": 440}, {"loss": 1.7565, "grad_norm": 0.32619214057922363, "learning_rate": 0.0002, "epoch": 0.6134969325153374, "step": 450}, {"loss": 1.7945, "grad_norm": 0.3603750765323639, "learning_rate": 0.0002, "epoch": 0.6271301976823449, "step": 460}, {"loss": 1.7773, "grad_norm": 0.30834096670150757, "learning_rate": 0.0002, "epoch": 0.6407634628493524, "step": 470}, {"loss": 1.8058, "grad_norm": 0.28756365180015564, "learning_rate": 0.0002, "epoch": 0.65439672801636, "step": 480}, {"loss": 1.744, "grad_norm": 0.2878406345844269, "learning_rate": 0.0002, "epoch": 0.6680299931833674, "step": 490}, {"loss": 1.8581, "grad_norm": 0.31329697370529175, "learning_rate": 0.0002, "epoch": 0.6816632583503749, "step": 500}, {"loss": 1.7886, "grad_norm": 0.3405822515487671, "learning_rate": 0.0002, "epoch": 0.6952965235173824, "step": 510}, {"loss": 1.778, "grad_norm": 0.305560827255249, "learning_rate": 0.0002, "epoch": 0.7089297886843899, "step": 520}, {"loss": 1.7592, "grad_norm": 0.2973416745662689, "learning_rate": 0.0002, "epoch": 0.7225630538513974, "step": 530}, {"loss": 1.8223, "grad_norm": 0.327303946018219, "learning_rate": 0.0002, "epoch": 0.7361963190184049, "step": 540}, {"loss": 1.8591, "grad_norm": 0.62595534324646, "learning_rate": 0.0002, "epoch": 0.7498295841854125, "step": 550}, {"loss": 1.7466, "grad_norm": 0.3129784166812897, "learning_rate": 0.0002, "epoch": 0.7634628493524199, "step": 560}, {"loss": 1.8035, "grad_norm": 0.32496583461761475, "learning_rate": 0.0002, "epoch": 0.7770961145194274, "step": 570}, {"loss": 1.7787, "grad_norm": 0.3098868131637573, "learning_rate": 0.0002, "epoch": 0.7907293796864349, "step": 580}, {"loss": 1.7196, "grad_norm": 0.30726853013038635, "learning_rate": 0.0002, "epoch": 0.8043626448534424, "step": 590}, {"loss": 1.7898, "grad_norm": 0.2964220643043518, "learning_rate": 0.0002, "epoch": 0.8179959100204499, "step": 600}, {"loss": 1.8114, "grad_norm": 0.32352274656295776, "learning_rate": 0.0002, "epoch": 0.8316291751874574, "step": 610}, {"loss": 1.811, "grad_norm": 0.2938912510871887, "learning_rate": 0.0002, "epoch": 0.8452624403544649, "step": 620}, {"loss": 1.7727, "grad_norm": 0.295559823513031, "learning_rate": 0.0002, "epoch": 0.8588957055214724, "step": 630}, {"loss": 1.9, "grad_norm": 0.34102028608322144, "learning_rate": 0.0002, "epoch": 0.8725289706884799, "step": 640}, {"loss": 1.8006, "grad_norm": 0.29676181077957153, "learning_rate": 0.0002, "epoch": 0.8861622358554874, "step": 650}, {"loss": 1.8099, "grad_norm": 0.3108902871608734, "learning_rate": 0.0002, "epoch": 0.8997955010224948, "step": 660}, {"loss": 1.7955, "grad_norm": 0.2690821588039398, "learning_rate": 0.0002, "epoch": 0.9134287661895024, "step": 670}, {"loss": 1.7881, "grad_norm": 0.32752540707588196, "learning_rate": 0.0002, "epoch": 0.9270620313565099, "step": 680}, {"loss": 1.7661, "grad_norm": 0.8029476404190063, "learning_rate": 0.0002, "epoch": 0.9406952965235174, "step": 690}, {"loss": 1.7733, "grad_norm": 0.30534422397613525, "learning_rate": 0.0002, "epoch": 0.9543285616905249, "step": 700}, {"loss": 1.7614, "grad_norm": 0.2899954319000244, "learning_rate": 0.0002, "epoch": 0.9679618268575324, "step": 710}, {"loss": 1.7845, "grad_norm": 0.28814372420310974, "learning_rate": 0.0002, "epoch": 0.9815950920245399, "step": 720}, {"loss": 1.8865, "grad_norm": 0.3061596751213074, "learning_rate": 0.0002, "epoch": 0.9952283571915473, "step": 730}]}
+{"epoch": 2.0, "step": 1467, "epoch_duration": 1095.1415996551514, "total_accumulated_duration": 2192.180320262909, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19996.724609375}, "avg_memory_reserved": {"GPU_0": 28746.0}, "peak_memory_reserved": {"GPU_0": 28746.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733", "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": 3.0982, "grad_norm": 0.7714291214942932, "learning_rate": 0.0002, "epoch": 0.013633265167007498, "step": 10}, {"loss": 2.5206, "grad_norm": 0.5473978519439697, "learning_rate": 0.0002, "epoch": 0.027266530334014997, "step": 20}, {"loss": 2.3079, "grad_norm": 0.5452795624732971, "learning_rate": 0.0002, "epoch": 0.0408997955010225, "step": 30}, {"loss": 2.0019, "grad_norm": 0.5098028779029846, "learning_rate": 0.0002, "epoch": 0.054533060668029994, "step": 40}, {"loss": 1.9333, "grad_norm": 0.48062971234321594, "learning_rate": 0.0002, "epoch": 0.0681663258350375, "step": 50}, {"loss": 1.9355, "grad_norm": 0.4505695104598999, "learning_rate": 0.0002, "epoch": 0.081799591002045, "step": 60}, {"loss": 1.9312, "grad_norm": 0.41609591245651245, "learning_rate": 0.0002, "epoch": 0.09543285616905249, "step": 70}, {"loss": 1.8656, "grad_norm": 0.4323892593383789, "learning_rate": 0.0002, "epoch": 0.10906612133605999, "step": 80}, {"loss": 1.9294, "grad_norm": 0.4670293629169464, "learning_rate": 0.0002, "epoch": 0.12269938650306748, "step": 90}, {"loss": 1.7946, "grad_norm": 0.40623316168785095, "learning_rate": 0.0002, "epoch": 0.136332651670075, "step": 100}, {"loss": 1.8565, "grad_norm": 0.3620383143424988, "learning_rate": 0.0002, "epoch": 0.1499659168370825, "step": 110}, {"loss": 1.9238, "grad_norm": 0.332218736410141, "learning_rate": 0.0002, "epoch": 0.16359918200409, "step": 120}, {"loss": 1.93, "grad_norm": 0.4004521667957306, "learning_rate": 0.0002, "epoch": 0.17723244717109748, "step": 130}, {"loss": 1.7549, "grad_norm": 0.3698360323905945, "learning_rate": 0.0002, "epoch": 0.19086571233810498, "step": 140}, {"loss": 1.8771, "grad_norm": 0.3847949504852295, "learning_rate": 0.0002, "epoch": 0.20449897750511248, "step": 150}, {"loss": 1.8316, "grad_norm": 0.36843451857566833, "learning_rate": 0.0002, "epoch": 0.21813224267211997, "step": 160}, {"loss": 1.838, "grad_norm": 0.37301021814346313, "learning_rate": 0.0002, "epoch": 0.23176550783912747, "step": 170}, {"loss": 1.8909, "grad_norm": 0.3718886971473694, "learning_rate": 0.0002, "epoch": 0.24539877300613497, "step": 180}, {"loss": 1.8454, "grad_norm": 0.3088490962982178, "learning_rate": 0.0002, "epoch": 0.25903203817314246, "step": 190}, {"loss": 1.9254, "grad_norm": 0.3611852526664734, "learning_rate": 0.0002, "epoch": 0.27266530334015, "step": 200}, {"loss": 1.7844, "grad_norm": 0.36093324422836304, "learning_rate": 0.0002, "epoch": 0.28629856850715746, "step": 210}, {"loss": 1.719, "grad_norm": 0.3250400722026825, "learning_rate": 0.0002, "epoch": 0.299931833674165, "step": 220}, {"loss": 1.8729, "grad_norm": 0.3566756248474121, "learning_rate": 0.0002, "epoch": 0.31356509884117245, "step": 230}, {"loss": 1.9259, "grad_norm": 0.32872408628463745, "learning_rate": 0.0002, "epoch": 0.32719836400818, "step": 240}, {"loss": 1.9033, "grad_norm": 0.3983881175518036, "learning_rate": 0.0002, "epoch": 0.34083162917518744, "step": 250}, {"loss": 1.8588, "grad_norm": 0.3571510910987854, "learning_rate": 0.0002, "epoch": 0.35446489434219497, "step": 260}, {"loss": 1.8539, "grad_norm": 0.3036131262779236, "learning_rate": 0.0002, "epoch": 0.36809815950920244, "step": 270}, {"loss": 1.8572, "grad_norm": 0.36512863636016846, "learning_rate": 0.0002, "epoch": 0.38173142467620996, "step": 280}, {"loss": 1.8022, "grad_norm": 0.3429736793041229, "learning_rate": 0.0002, "epoch": 0.39536468984321743, "step": 290}, {"loss": 1.8754, "grad_norm": 0.3055964708328247, "learning_rate": 0.0002, "epoch": 0.40899795501022496, "step": 300}, {"loss": 1.8384, "grad_norm": 0.33801034092903137, "learning_rate": 0.0002, "epoch": 0.4226312201772324, "step": 310}, {"loss": 1.7933, "grad_norm": 0.348783016204834, "learning_rate": 0.0002, "epoch": 0.43626448534423995, "step": 320}, {"loss": 1.8451, "grad_norm": 0.3057514727115631, "learning_rate": 0.0002, "epoch": 0.4498977505112474, "step": 330}, {"loss": 1.8766, "grad_norm": 0.3849763572216034, "learning_rate": 0.0002, "epoch": 0.46353101567825494, "step": 340}, {"loss": 1.8073, "grad_norm": 0.30080053210258484, "learning_rate": 0.0002, "epoch": 0.47716428084526247, "step": 350}, {"loss": 1.8548, "grad_norm": 0.3595106303691864, "learning_rate": 0.0002, "epoch": 0.49079754601226994, "step": 360}, {"loss": 1.8232, "grad_norm": 0.31099820137023926, "learning_rate": 0.0002, "epoch": 0.5044308111792775, "step": 370}, {"loss": 1.7029, "grad_norm": 0.3157978355884552, "learning_rate": 0.0002, "epoch": 0.5180640763462849, "step": 380}, {"loss": 1.8265, "grad_norm": 0.27960965037345886, "learning_rate": 0.0002, "epoch": 0.5316973415132924, "step": 390}, {"loss": 1.7414, "grad_norm": 0.3102385103702545, "learning_rate": 0.0002, "epoch": 0.5453306066803, "step": 400}, {"loss": 1.7461, "grad_norm": 0.32828861474990845, "learning_rate": 0.0002, "epoch": 0.5589638718473074, "step": 410}, {"loss": 1.8165, "grad_norm": 0.29560017585754395, "learning_rate": 0.0002, "epoch": 0.5725971370143149, "step": 420}, {"loss": 1.9455, "grad_norm": 0.33316895365715027, "learning_rate": 0.0002, "epoch": 0.5862304021813224, "step": 430}, {"loss": 1.8241, "grad_norm": 0.30420982837677, "learning_rate": 0.0002, "epoch": 0.59986366734833, "step": 440}, {"loss": 1.7565, "grad_norm": 0.32619214057922363, "learning_rate": 0.0002, "epoch": 0.6134969325153374, "step": 450}, {"loss": 1.7945, "grad_norm": 0.3603750765323639, "learning_rate": 0.0002, "epoch": 0.6271301976823449, "step": 460}, {"loss": 1.7773, "grad_norm": 0.30834096670150757, "learning_rate": 0.0002, "epoch": 0.6407634628493524, "step": 470}, {"loss": 1.8058, "grad_norm": 0.28756365180015564, "learning_rate": 0.0002, "epoch": 0.65439672801636, "step": 480}, {"loss": 1.744, "grad_norm": 0.2878406345844269, "learning_rate": 0.0002, "epoch": 0.6680299931833674, "step": 490}, {"loss": 1.8581, "grad_norm": 0.31329697370529175, "learning_rate": 0.0002, "epoch": 0.6816632583503749, "step": 500}, {"loss": 1.7886, "grad_norm": 0.3405822515487671, "learning_rate": 0.0002, "epoch": 0.6952965235173824, "step": 510}, {"loss": 1.778, "grad_norm": 0.305560827255249, "learning_rate": 0.0002, "epoch": 0.7089297886843899, "step": 520}, {"loss": 1.7592, "grad_norm": 0.2973416745662689, "learning_rate": 0.0002, "epoch": 0.7225630538513974, "step": 530}, {"loss": 1.8223, "grad_norm": 0.327303946018219, "learning_rate": 0.0002, "epoch": 0.7361963190184049, "step": 540}, {"loss": 1.8591, "grad_norm": 0.62595534324646, "learning_rate": 0.0002, "epoch": 0.7498295841854125, "step": 550}, {"loss": 1.7466, "grad_norm": 0.3129784166812897, "learning_rate": 0.0002, "epoch": 0.7634628493524199, "step": 560}, {"loss": 1.8035, "grad_norm": 0.32496583461761475, "learning_rate": 0.0002, "epoch": 0.7770961145194274, "step": 570}, {"loss": 1.7787, "grad_norm": 0.3098868131637573, "learning_rate": 0.0002, "epoch": 0.7907293796864349, "step": 580}, {"loss": 1.7196, "grad_norm": 0.30726853013038635, "learning_rate": 0.0002, "epoch": 0.8043626448534424, "step": 590}, {"loss": 1.7898, "grad_norm": 0.2964220643043518, "learning_rate": 0.0002, "epoch": 0.8179959100204499, "step": 600}, {"loss": 1.8114, "grad_norm": 0.32352274656295776, "learning_rate": 0.0002, "epoch": 0.8316291751874574, "step": 610}, {"loss": 1.811, "grad_norm": 0.2938912510871887, "learning_rate": 0.0002, "epoch": 0.8452624403544649, "step": 620}, {"loss": 1.7727, "grad_norm": 0.295559823513031, "learning_rate": 0.0002, "epoch": 0.8588957055214724, "step": 630}, {"loss": 1.9, "grad_norm": 0.34102028608322144, "learning_rate": 0.0002, "epoch": 0.8725289706884799, "step": 640}, {"loss": 1.8006, "grad_norm": 0.29676181077957153, "learning_rate": 0.0002, "epoch": 0.8861622358554874, "step": 650}, {"loss": 1.8099, "grad_norm": 0.3108902871608734, "learning_rate": 0.0002, "epoch": 0.8997955010224948, "step": 660}, {"loss": 1.7955, "grad_norm": 0.2690821588039398, "learning_rate": 0.0002, "epoch": 0.9134287661895024, "step": 670}, {"loss": 1.7881, "grad_norm": 0.32752540707588196, "learning_rate": 0.0002, "epoch": 0.9270620313565099, "step": 680}, {"loss": 1.7661, "grad_norm": 0.8029476404190063, "learning_rate": 0.0002, "epoch": 0.9406952965235174, "step": 690}, {"loss": 1.7733, "grad_norm": 0.30534422397613525, "learning_rate": 0.0002, "epoch": 0.9543285616905249, "step": 700}, {"loss": 1.7614, "grad_norm": 0.2899954319000244, "learning_rate": 0.0002, "epoch": 0.9679618268575324, "step": 710}, {"loss": 1.7845, "grad_norm": 0.28814372420310974, "learning_rate": 0.0002, "epoch": 0.9815950920245399, "step": 720}, {"loss": 1.8865, "grad_norm": 0.3061596751213074, "learning_rate": 0.0002, "epoch": 0.9952283571915473, "step": 730}, {"eval_loss": 1.8171186447143555, "eval_runtime": 53.6047, "eval_samples_per_second": 9.458, "eval_steps_per_second": 1.194, "epoch": 0.9993183367416496, "step": 733}, {"loss": 1.6202, "grad_norm": 0.3140897750854492, "learning_rate": 0.0002, "epoch": 1.008861622358555, "step": 740}, {"loss": 1.8409, "grad_norm": 0.3346109390258789, "learning_rate": 0.0002, "epoch": 1.0224948875255624, "step": 750}, {"loss": 1.6777, "grad_norm": 0.3582976758480072, "learning_rate": 0.0002, "epoch": 1.0361281526925699, "step": 760}, {"loss": 1.7306, "grad_norm": 0.30408260226249695, "learning_rate": 0.0002, "epoch": 1.0497614178595773, "step": 770}, {"loss": 1.6967, "grad_norm": 0.323585569858551, "learning_rate": 0.0002, "epoch": 1.0633946830265848, "step": 780}, {"loss": 1.768, "grad_norm": 0.3474137783050537, "learning_rate": 0.0002, "epoch": 1.0770279481935923, "step": 790}, {"loss": 1.6895, "grad_norm": 0.35721147060394287, "learning_rate": 0.0002, "epoch": 1.0906612133606, "step": 800}, {"loss": 1.718, "grad_norm": 0.35366931557655334, "learning_rate": 0.0002, "epoch": 1.1042944785276074, "step": 810}, {"loss": 1.6797, "grad_norm": 0.3250770568847656, "learning_rate": 0.0002, "epoch": 1.117927743694615, "step": 820}, {"loss": 1.6383, "grad_norm": 0.3293766379356384, "learning_rate": 0.0002, "epoch": 1.1315610088616224, "step": 830}, {"loss": 1.7353, "grad_norm": 0.3380851745605469, "learning_rate": 0.0002, "epoch": 1.1451942740286298, "step": 840}, {"loss": 1.8236, "grad_norm": 0.32584455609321594, "learning_rate": 0.0002, "epoch": 1.1588275391956373, "step": 850}, {"loss": 1.6681, "grad_norm": 0.45700767636299133, "learning_rate": 0.0002, "epoch": 1.1724608043626448, "step": 860}, {"loss": 1.7494, "grad_norm": 0.30944544076919556, "learning_rate": 0.0002, "epoch": 1.1860940695296525, "step": 870}, {"loss": 1.7426, "grad_norm": 0.3268151581287384, "learning_rate": 0.0002, "epoch": 1.19972733469666, "step": 880}, {"loss": 1.7413, "grad_norm": 0.39972540736198425, "learning_rate": 0.0002, "epoch": 1.2133605998636674, "step": 890}, {"loss": 1.7481, "grad_norm": 0.7890929579734802, "learning_rate": 0.0002, "epoch": 1.2269938650306749, "step": 900}, {"loss": 1.7608, "grad_norm": 0.3439182639122009, "learning_rate": 0.0002, "epoch": 1.2406271301976823, "step": 910}, {"loss": 1.7617, "grad_norm": 0.3986225128173828, "learning_rate": 0.0002, "epoch": 1.2542603953646898, "step": 920}, {"loss": 1.6843, "grad_norm": 0.3514605164527893, "learning_rate": 0.0002, "epoch": 1.2678936605316973, "step": 930}, {"loss": 1.6987, "grad_norm": 0.3682589530944824, "learning_rate": 0.0002, "epoch": 1.2815269256987047, "step": 940}, {"loss": 1.6988, "grad_norm": 0.3618335723876953, "learning_rate": 0.0002, "epoch": 1.2951601908657122, "step": 950}, {"loss": 1.7436, "grad_norm": 0.345700740814209, "learning_rate": 0.0002, "epoch": 1.30879345603272, "step": 960}, {"loss": 1.7336, "grad_norm": 0.3514927923679352, "learning_rate": 0.0002, "epoch": 1.3224267211997274, "step": 970}, {"loss": 1.7704, "grad_norm": 0.365647554397583, "learning_rate": 0.0002, "epoch": 1.3360599863667348, "step": 980}, {"loss": 1.7104, "grad_norm": 0.3407285809516907, "learning_rate": 0.0002, "epoch": 1.3496932515337423, "step": 990}, {"loss": 1.7132, "grad_norm": 0.3785437345504761, "learning_rate": 0.0002, "epoch": 1.3633265167007498, "step": 1000}, {"loss": 1.766, "grad_norm": 0.34746724367141724, "learning_rate": 0.0002, "epoch": 1.3769597818677572, "step": 1010}, {"loss": 1.7252, "grad_norm": 0.362444132566452, "learning_rate": 0.0002, "epoch": 1.390593047034765, "step": 1020}, {"loss": 1.7132, "grad_norm": 0.4424704611301422, "learning_rate": 0.0002, "epoch": 1.4042263122017724, "step": 1030}, {"loss": 1.726, "grad_norm": 0.38722458481788635, "learning_rate": 0.0002, "epoch": 1.4178595773687799, "step": 1040}, {"loss": 1.7955, "grad_norm": 0.36089080572128296, "learning_rate": 0.0002, "epoch": 1.4314928425357873, "step": 1050}, {"loss": 1.6924, "grad_norm": 0.33817124366760254, "learning_rate": 0.0002, "epoch": 1.4451261077027948, "step": 1060}, {"loss": 1.7165, "grad_norm": 0.34334081411361694, "learning_rate": 0.0002, "epoch": 1.4587593728698023, "step": 1070}, {"loss": 1.6999, "grad_norm": 0.3776826858520508, "learning_rate": 0.0002, "epoch": 1.4723926380368098, "step": 1080}, {"loss": 1.7605, "grad_norm": 0.4169026017189026, "learning_rate": 0.0002, "epoch": 1.4860259032038172, "step": 1090}, {"loss": 1.7502, "grad_norm": 0.34898945689201355, "learning_rate": 0.0002, "epoch": 1.4996591683708247, "step": 1100}, {"loss": 1.635, "grad_norm": 0.34223780035972595, "learning_rate": 0.0002, "epoch": 1.5132924335378322, "step": 1110}, {"loss": 1.7248, "grad_norm": 0.3686901032924652, "learning_rate": 0.0002, "epoch": 1.5269256987048399, "step": 1120}, {"loss": 1.7525, "grad_norm": 0.35054415464401245, "learning_rate": 0.0002, "epoch": 1.5405589638718473, "step": 1130}, {"loss": 1.7776, "grad_norm": 0.39496365189552307, "learning_rate": 0.0002, "epoch": 1.5541922290388548, "step": 1140}, {"loss": 1.6574, "grad_norm": 0.35451626777648926, "learning_rate": 0.0002, "epoch": 1.5678254942058623, "step": 1150}, {"loss": 1.7257, "grad_norm": 0.3848083019256592, "learning_rate": 0.0002, "epoch": 1.58145875937287, "step": 1160}, {"loss": 1.7272, "grad_norm": 0.3760537803173065, "learning_rate": 0.0002, "epoch": 1.5950920245398774, "step": 1170}, {"loss": 1.7441, "grad_norm": 0.38981738686561584, "learning_rate": 0.0002, "epoch": 1.6087252897068849, "step": 1180}, {"loss": 1.6951, "grad_norm": 0.36830949783325195, "learning_rate": 0.0002, "epoch": 1.6223585548738924, "step": 1190}, {"loss": 1.6925, "grad_norm": 0.3405892848968506, "learning_rate": 0.0002, "epoch": 1.6359918200408998, "step": 1200}, {"loss": 1.7473, "grad_norm": 0.39027872681617737, "learning_rate": 0.0002, "epoch": 1.6496250852079073, "step": 1210}, {"loss": 1.6792, "grad_norm": 0.3342694044113159, "learning_rate": 0.0002, "epoch": 1.6632583503749148, "step": 1220}, {"loss": 1.7196, "grad_norm": 0.3600076735019684, "learning_rate": 0.0002, "epoch": 1.6768916155419222, "step": 1230}, {"loss": 1.7021, "grad_norm": 0.3625542223453522, "learning_rate": 0.0002, "epoch": 1.6905248807089297, "step": 1240}, {"loss": 1.6772, "grad_norm": 0.32170894742012024, "learning_rate": 0.0002, "epoch": 1.7041581458759372, "step": 1250}, {"loss": 1.7152, "grad_norm": 0.3544139862060547, "learning_rate": 0.0002, "epoch": 1.7177914110429446, "step": 1260}, {"loss": 1.7138, "grad_norm": 0.35113027691841125, "learning_rate": 0.0002, "epoch": 1.7314246762099523, "step": 1270}, {"loss": 1.7095, "grad_norm": 0.3499974310398102, "learning_rate": 0.0002, "epoch": 1.7450579413769598, "step": 1280}, {"loss": 1.7749, "grad_norm": 0.3285157382488251, "learning_rate": 0.0002, "epoch": 1.7586912065439673, "step": 1290}, {"loss": 1.6767, "grad_norm": 0.3701961636543274, "learning_rate": 0.0002, "epoch": 1.7723244717109747, "step": 1300}, {"loss": 1.6282, "grad_norm": 0.3301318287849426, "learning_rate": 0.0002, "epoch": 1.7859577368779824, "step": 1310}, {"loss": 1.7097, "grad_norm": 0.37801554799079895, "learning_rate": 0.0002, "epoch": 1.79959100204499, "step": 1320}, {"loss": 1.7437, "grad_norm": 0.3726748526096344, "learning_rate": 0.0002, "epoch": 1.8132242672119974, "step": 1330}, {"loss": 1.7959, "grad_norm": 0.4059790074825287, "learning_rate": 0.0002, "epoch": 1.8268575323790048, "step": 1340}, {"loss": 1.7739, "grad_norm": 0.35712096095085144, "learning_rate": 0.0002, "epoch": 1.8404907975460123, "step": 1350}, {"loss": 1.6375, "grad_norm": 0.35995328426361084, "learning_rate": 0.0002, "epoch": 1.8541240627130198, "step": 1360}, {"loss": 1.7332, "grad_norm": 0.3679947257041931, "learning_rate": 0.0002, "epoch": 1.8677573278800272, "step": 1370}, {"loss": 1.7587, "grad_norm": 0.39645957946777344, "learning_rate": 0.0002, "epoch": 1.8813905930470347, "step": 1380}, {"loss": 1.6985, "grad_norm": 0.35288700461387634, "learning_rate": 0.0002, "epoch": 1.8950238582140422, "step": 1390}, {"loss": 1.6582, "grad_norm": 0.32579198479652405, "learning_rate": 0.0002, "epoch": 1.9086571233810496, "step": 1400}, {"loss": 1.6948, "grad_norm": 0.3856561779975891, "learning_rate": 0.0002, "epoch": 1.9222903885480571, "step": 1410}, {"loss": 1.668, "grad_norm": 0.39019331336021423, "learning_rate": 0.0002, "epoch": 1.9359236537150648, "step": 1420}, {"loss": 1.7774, "grad_norm": 0.38006502389907837, "learning_rate": 0.0002, "epoch": 1.9495569188820723, "step": 1430}, {"loss": 1.8323, "grad_norm": 0.38100454211235046, "learning_rate": 0.0002, "epoch": 1.9631901840490797, "step": 1440}, {"loss": 1.7298, "grad_norm": 0.3405798673629761, "learning_rate": 0.0002, "epoch": 1.9768234492160872, "step": 1450}, {"loss": 1.7045, "grad_norm": 0.36582913994789124, "learning_rate": 0.0002, "epoch": 1.990456714383095, "step": 1460}]}
+{"epoch": 2.9993183367416494, "step": 2200, "epoch_duration": 1094.913452386856, "total_accumulated_duration": 3287.093772649765, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7887.97119140625}, "peak_memory_usage": {"GPU_0": 19996.724609375}, "avg_memory_reserved": {"GPU_0": 28746.0}, "peak_memory_reserved": {"GPU_0": 28746.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733", "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": 3.0982, "grad_norm": 0.7714291214942932, "learning_rate": 0.0002, "epoch": 0.013633265167007498, "step": 10}, {"loss": 2.5206, "grad_norm": 0.5473978519439697, "learning_rate": 0.0002, "epoch": 0.027266530334014997, "step": 20}, {"loss": 2.3079, "grad_norm": 0.5452795624732971, "learning_rate": 0.0002, "epoch": 0.0408997955010225, "step": 30}, {"loss": 2.0019, "grad_norm": 0.5098028779029846, "learning_rate": 0.0002, "epoch": 0.054533060668029994, "step": 40}, {"loss": 1.9333, "grad_norm": 0.48062971234321594, "learning_rate": 0.0002, "epoch": 0.0681663258350375, "step": 50}, {"loss": 1.9355, "grad_norm": 0.4505695104598999, "learning_rate": 0.0002, "epoch": 0.081799591002045, "step": 60}, {"loss": 1.9312, "grad_norm": 0.41609591245651245, "learning_rate": 0.0002, "epoch": 0.09543285616905249, "step": 70}, {"loss": 1.8656, "grad_norm": 0.4323892593383789, "learning_rate": 0.0002, "epoch": 0.10906612133605999, "step": 80}, {"loss": 1.9294, "grad_norm": 0.4670293629169464, "learning_rate": 0.0002, "epoch": 0.12269938650306748, "step": 90}, {"loss": 1.7946, "grad_norm": 0.40623316168785095, "learning_rate": 0.0002, "epoch": 0.136332651670075, "step": 100}, {"loss": 1.8565, "grad_norm": 0.3620383143424988, "learning_rate": 0.0002, "epoch": 0.1499659168370825, "step": 110}, {"loss": 1.9238, "grad_norm": 0.332218736410141, "learning_rate": 0.0002, "epoch": 0.16359918200409, "step": 120}, {"loss": 1.93, "grad_norm": 0.4004521667957306, "learning_rate": 0.0002, "epoch": 0.17723244717109748, "step": 130}, {"loss": 1.7549, "grad_norm": 0.3698360323905945, "learning_rate": 0.0002, "epoch": 0.19086571233810498, "step": 140}, {"loss": 1.8771, "grad_norm": 0.3847949504852295, "learning_rate": 0.0002, "epoch": 0.20449897750511248, "step": 150}, {"loss": 1.8316, "grad_norm": 0.36843451857566833, "learning_rate": 0.0002, "epoch": 0.21813224267211997, "step": 160}, {"loss": 1.838, "grad_norm": 0.37301021814346313, "learning_rate": 0.0002, "epoch": 0.23176550783912747, "step": 170}, {"loss": 1.8909, "grad_norm": 0.3718886971473694, "learning_rate": 0.0002, "epoch": 0.24539877300613497, "step": 180}, {"loss": 1.8454, "grad_norm": 0.3088490962982178, "learning_rate": 0.0002, "epoch": 0.25903203817314246, "step": 190}, {"loss": 1.9254, "grad_norm": 0.3611852526664734, "learning_rate": 0.0002, "epoch": 0.27266530334015, "step": 200}, {"loss": 1.7844, "grad_norm": 0.36093324422836304, "learning_rate": 0.0002, "epoch": 0.28629856850715746, "step": 210}, {"loss": 1.719, "grad_norm": 0.3250400722026825, "learning_rate": 0.0002, "epoch": 0.299931833674165, "step": 220}, {"loss": 1.8729, "grad_norm": 0.3566756248474121, "learning_rate": 0.0002, "epoch": 0.31356509884117245, "step": 230}, {"loss": 1.9259, "grad_norm": 0.32872408628463745, "learning_rate": 0.0002, "epoch": 0.32719836400818, "step": 240}, {"loss": 1.9033, "grad_norm": 0.3983881175518036, "learning_rate": 0.0002, "epoch": 0.34083162917518744, "step": 250}, {"loss": 1.8588, "grad_norm": 0.3571510910987854, "learning_rate": 0.0002, "epoch": 0.35446489434219497, "step": 260}, {"loss": 1.8539, "grad_norm": 0.3036131262779236, "learning_rate": 0.0002, "epoch": 0.36809815950920244, "step": 270}, {"loss": 1.8572, "grad_norm": 0.36512863636016846, "learning_rate": 0.0002, "epoch": 0.38173142467620996, "step": 280}, {"loss": 1.8022, "grad_norm": 0.3429736793041229, "learning_rate": 0.0002, "epoch": 0.39536468984321743, "step": 290}, {"loss": 1.8754, "grad_norm": 0.3055964708328247, "learning_rate": 0.0002, "epoch": 0.40899795501022496, "step": 300}, {"loss": 1.8384, "grad_norm": 0.33801034092903137, "learning_rate": 0.0002, "epoch": 0.4226312201772324, "step": 310}, {"loss": 1.7933, "grad_norm": 0.348783016204834, "learning_rate": 0.0002, "epoch": 0.43626448534423995, "step": 320}, {"loss": 1.8451, "grad_norm": 0.3057514727115631, "learning_rate": 0.0002, "epoch": 0.4498977505112474, "step": 330}, {"loss": 1.8766, "grad_norm": 0.3849763572216034, "learning_rate": 0.0002, "epoch": 0.46353101567825494, "step": 340}, {"loss": 1.8073, "grad_norm": 0.30080053210258484, "learning_rate": 0.0002, "epoch": 0.47716428084526247, "step": 350}, {"loss": 1.8548, "grad_norm": 0.3595106303691864, "learning_rate": 0.0002, "epoch": 0.49079754601226994, "step": 360}, {"loss": 1.8232, "grad_norm": 0.31099820137023926, "learning_rate": 0.0002, "epoch": 0.5044308111792775, "step": 370}, {"loss": 1.7029, "grad_norm": 0.3157978355884552, "learning_rate": 0.0002, "epoch": 0.5180640763462849, "step": 380}, {"loss": 1.8265, "grad_norm": 0.27960965037345886, "learning_rate": 0.0002, "epoch": 0.5316973415132924, "step": 390}, {"loss": 1.7414, "grad_norm": 0.3102385103702545, "learning_rate": 0.0002, "epoch": 0.5453306066803, "step": 400}, {"loss": 1.7461, "grad_norm": 0.32828861474990845, "learning_rate": 0.0002, "epoch": 0.5589638718473074, "step": 410}, {"loss": 1.8165, "grad_norm": 0.29560017585754395, "learning_rate": 0.0002, "epoch": 0.5725971370143149, "step": 420}, {"loss": 1.9455, "grad_norm": 0.33316895365715027, "learning_rate": 0.0002, "epoch": 0.5862304021813224, "step": 430}, {"loss": 1.8241, "grad_norm": 0.30420982837677, "learning_rate": 0.0002, "epoch": 0.59986366734833, "step": 440}, {"loss": 1.7565, "grad_norm": 0.32619214057922363, "learning_rate": 0.0002, "epoch": 0.6134969325153374, "step": 450}, {"loss": 1.7945, "grad_norm": 0.3603750765323639, "learning_rate": 0.0002, "epoch": 0.6271301976823449, "step": 460}, {"loss": 1.7773, "grad_norm": 0.30834096670150757, "learning_rate": 0.0002, "epoch": 0.6407634628493524, "step": 470}, {"loss": 1.8058, "grad_norm": 0.28756365180015564, "learning_rate": 0.0002, "epoch": 0.65439672801636, "step": 480}, {"loss": 1.744, "grad_norm": 0.2878406345844269, "learning_rate": 0.0002, "epoch": 0.6680299931833674, "step": 490}, {"loss": 1.8581, "grad_norm": 0.31329697370529175, "learning_rate": 0.0002, "epoch": 0.6816632583503749, "step": 500}, {"loss": 1.7886, "grad_norm": 0.3405822515487671, "learning_rate": 0.0002, "epoch": 0.6952965235173824, "step": 510}, {"loss": 1.778, "grad_norm": 0.305560827255249, "learning_rate": 0.0002, "epoch": 0.7089297886843899, "step": 520}, {"loss": 1.7592, "grad_norm": 0.2973416745662689, "learning_rate": 0.0002, "epoch": 0.7225630538513974, "step": 530}, {"loss": 1.8223, "grad_norm": 0.327303946018219, "learning_rate": 0.0002, "epoch": 0.7361963190184049, "step": 540}, {"loss": 1.8591, "grad_norm": 0.62595534324646, "learning_rate": 0.0002, "epoch": 0.7498295841854125, "step": 550}, {"loss": 1.7466, "grad_norm": 0.3129784166812897, "learning_rate": 0.0002, "epoch": 0.7634628493524199, "step": 560}, {"loss": 1.8035, "grad_norm": 0.32496583461761475, "learning_rate": 0.0002, "epoch": 0.7770961145194274, "step": 570}, {"loss": 1.7787, "grad_norm": 0.3098868131637573, "learning_rate": 0.0002, "epoch": 0.7907293796864349, "step": 580}, {"loss": 1.7196, "grad_norm": 0.30726853013038635, "learning_rate": 0.0002, "epoch": 0.8043626448534424, "step": 590}, {"loss": 1.7898, "grad_norm": 0.2964220643043518, "learning_rate": 0.0002, "epoch": 0.8179959100204499, "step": 600}, {"loss": 1.8114, "grad_norm": 0.32352274656295776, "learning_rate": 0.0002, "epoch": 0.8316291751874574, "step": 610}, {"loss": 1.811, "grad_norm": 0.2938912510871887, "learning_rate": 0.0002, "epoch": 0.8452624403544649, "step": 620}, {"loss": 1.7727, "grad_norm": 0.295559823513031, "learning_rate": 0.0002, "epoch": 0.8588957055214724, "step": 630}, {"loss": 1.9, "grad_norm": 0.34102028608322144, "learning_rate": 0.0002, "epoch": 0.8725289706884799, "step": 640}, {"loss": 1.8006, "grad_norm": 0.29676181077957153, "learning_rate": 0.0002, "epoch": 0.8861622358554874, "step": 650}, {"loss": 1.8099, "grad_norm": 0.3108902871608734, "learning_rate": 0.0002, "epoch": 0.8997955010224948, "step": 660}, {"loss": 1.7955, "grad_norm": 0.2690821588039398, "learning_rate": 0.0002, "epoch": 0.9134287661895024, "step": 670}, {"loss": 1.7881, "grad_norm": 0.32752540707588196, "learning_rate": 0.0002, "epoch": 0.9270620313565099, "step": 680}, {"loss": 1.7661, "grad_norm": 0.8029476404190063, "learning_rate": 0.0002, "epoch": 0.9406952965235174, "step": 690}, {"loss": 1.7733, "grad_norm": 0.30534422397613525, "learning_rate": 0.0002, "epoch": 0.9543285616905249, "step": 700}, {"loss": 1.7614, "grad_norm": 0.2899954319000244, "learning_rate": 0.0002, "epoch": 0.9679618268575324, "step": 710}, {"loss": 1.7845, "grad_norm": 0.28814372420310974, "learning_rate": 0.0002, "epoch": 0.9815950920245399, "step": 720}, {"loss": 1.8865, "grad_norm": 0.3061596751213074, "learning_rate": 0.0002, "epoch": 0.9952283571915473, "step": 730}, {"eval_loss": 1.8171186447143555, "eval_runtime": 53.6047, "eval_samples_per_second": 9.458, "eval_steps_per_second": 1.194, "epoch": 0.9993183367416496, "step": 733}, {"loss": 1.6202, "grad_norm": 0.3140897750854492, "learning_rate": 0.0002, "epoch": 1.008861622358555, "step": 740}, {"loss": 1.8409, "grad_norm": 0.3346109390258789, "learning_rate": 0.0002, "epoch": 1.0224948875255624, "step": 750}, {"loss": 1.6777, "grad_norm": 0.3582976758480072, "learning_rate": 0.0002, "epoch": 1.0361281526925699, "step": 760}, {"loss": 1.7306, "grad_norm": 0.30408260226249695, "learning_rate": 0.0002, "epoch": 1.0497614178595773, "step": 770}, {"loss": 1.6967, "grad_norm": 0.323585569858551, "learning_rate": 0.0002, "epoch": 1.0633946830265848, "step": 780}, {"loss": 1.768, "grad_norm": 0.3474137783050537, "learning_rate": 0.0002, "epoch": 1.0770279481935923, "step": 790}, {"loss": 1.6895, "grad_norm": 0.35721147060394287, "learning_rate": 0.0002, "epoch": 1.0906612133606, "step": 800}, {"loss": 1.718, "grad_norm": 0.35366931557655334, "learning_rate": 0.0002, "epoch": 1.1042944785276074, "step": 810}, {"loss": 1.6797, "grad_norm": 0.3250770568847656, "learning_rate": 0.0002, "epoch": 1.117927743694615, "step": 820}, {"loss": 1.6383, "grad_norm": 0.3293766379356384, "learning_rate": 0.0002, "epoch": 1.1315610088616224, "step": 830}, {"loss": 1.7353, "grad_norm": 0.3380851745605469, "learning_rate": 0.0002, "epoch": 1.1451942740286298, "step": 840}, {"loss": 1.8236, "grad_norm": 0.32584455609321594, "learning_rate": 0.0002, "epoch": 1.1588275391956373, "step": 850}, {"loss": 1.6681, "grad_norm": 0.45700767636299133, "learning_rate": 0.0002, "epoch": 1.1724608043626448, "step": 860}, {"loss": 1.7494, "grad_norm": 0.30944544076919556, "learning_rate": 0.0002, "epoch": 1.1860940695296525, "step": 870}, {"loss": 1.7426, "grad_norm": 0.3268151581287384, "learning_rate": 0.0002, "epoch": 1.19972733469666, "step": 880}, {"loss": 1.7413, "grad_norm": 0.39972540736198425, "learning_rate": 0.0002, "epoch": 1.2133605998636674, "step": 890}, {"loss": 1.7481, "grad_norm": 0.7890929579734802, "learning_rate": 0.0002, "epoch": 1.2269938650306749, "step": 900}, {"loss": 1.7608, "grad_norm": 0.3439182639122009, "learning_rate": 0.0002, "epoch": 1.2406271301976823, "step": 910}, {"loss": 1.7617, "grad_norm": 0.3986225128173828, "learning_rate": 0.0002, "epoch": 1.2542603953646898, "step": 920}, {"loss": 1.6843, "grad_norm": 0.3514605164527893, "learning_rate": 0.0002, "epoch": 1.2678936605316973, "step": 930}, {"loss": 1.6987, "grad_norm": 0.3682589530944824, "learning_rate": 0.0002, "epoch": 1.2815269256987047, "step": 940}, {"loss": 1.6988, "grad_norm": 0.3618335723876953, "learning_rate": 0.0002, "epoch": 1.2951601908657122, "step": 950}, {"loss": 1.7436, "grad_norm": 0.345700740814209, "learning_rate": 0.0002, "epoch": 1.30879345603272, "step": 960}, {"loss": 1.7336, "grad_norm": 0.3514927923679352, "learning_rate": 0.0002, "epoch": 1.3224267211997274, "step": 970}, {"loss": 1.7704, "grad_norm": 0.365647554397583, "learning_rate": 0.0002, "epoch": 1.3360599863667348, "step": 980}, {"loss": 1.7104, "grad_norm": 0.3407285809516907, "learning_rate": 0.0002, "epoch": 1.3496932515337423, "step": 990}, {"loss": 1.7132, "grad_norm": 0.3785437345504761, "learning_rate": 0.0002, "epoch": 1.3633265167007498, "step": 1000}, {"loss": 1.766, "grad_norm": 0.34746724367141724, "learning_rate": 0.0002, "epoch": 1.3769597818677572, "step": 1010}, {"loss": 1.7252, "grad_norm": 0.362444132566452, "learning_rate": 0.0002, "epoch": 1.390593047034765, "step": 1020}, {"loss": 1.7132, "grad_norm": 0.4424704611301422, "learning_rate": 0.0002, "epoch": 1.4042263122017724, "step": 1030}, {"loss": 1.726, "grad_norm": 0.38722458481788635, "learning_rate": 0.0002, "epoch": 1.4178595773687799, "step": 1040}, {"loss": 1.7955, "grad_norm": 0.36089080572128296, "learning_rate": 0.0002, "epoch": 1.4314928425357873, "step": 1050}, {"loss": 1.6924, "grad_norm": 0.33817124366760254, "learning_rate": 0.0002, "epoch": 1.4451261077027948, "step": 1060}, {"loss": 1.7165, "grad_norm": 0.34334081411361694, "learning_rate": 0.0002, "epoch": 1.4587593728698023, "step": 1070}, {"loss": 1.6999, "grad_norm": 0.3776826858520508, "learning_rate": 0.0002, "epoch": 1.4723926380368098, "step": 1080}, {"loss": 1.7605, "grad_norm": 0.4169026017189026, "learning_rate": 0.0002, "epoch": 1.4860259032038172, "step": 1090}, {"loss": 1.7502, "grad_norm": 0.34898945689201355, "learning_rate": 0.0002, "epoch": 1.4996591683708247, "step": 1100}, {"loss": 1.635, "grad_norm": 0.34223780035972595, "learning_rate": 0.0002, "epoch": 1.5132924335378322, "step": 1110}, {"loss": 1.7248, "grad_norm": 0.3686901032924652, "learning_rate": 0.0002, "epoch": 1.5269256987048399, "step": 1120}, {"loss": 1.7525, "grad_norm": 0.35054415464401245, "learning_rate": 0.0002, "epoch": 1.5405589638718473, "step": 1130}, {"loss": 1.7776, "grad_norm": 0.39496365189552307, "learning_rate": 0.0002, "epoch": 1.5541922290388548, "step": 1140}, {"loss": 1.6574, "grad_norm": 0.35451626777648926, "learning_rate": 0.0002, "epoch": 1.5678254942058623, "step": 1150}, {"loss": 1.7257, "grad_norm": 0.3848083019256592, "learning_rate": 0.0002, "epoch": 1.58145875937287, "step": 1160}, {"loss": 1.7272, "grad_norm": 0.3760537803173065, "learning_rate": 0.0002, "epoch": 1.5950920245398774, "step": 1170}, {"loss": 1.7441, "grad_norm": 0.38981738686561584, "learning_rate": 0.0002, "epoch": 1.6087252897068849, "step": 1180}, {"loss": 1.6951, "grad_norm": 0.36830949783325195, "learning_rate": 0.0002, "epoch": 1.6223585548738924, "step": 1190}, {"loss": 1.6925, "grad_norm": 0.3405892848968506, "learning_rate": 0.0002, "epoch": 1.6359918200408998, "step": 1200}, {"loss": 1.7473, "grad_norm": 0.39027872681617737, "learning_rate": 0.0002, "epoch": 1.6496250852079073, "step": 1210}, {"loss": 1.6792, "grad_norm": 0.3342694044113159, "learning_rate": 0.0002, "epoch": 1.6632583503749148, "step": 1220}, {"loss": 1.7196, "grad_norm": 0.3600076735019684, "learning_rate": 0.0002, "epoch": 1.6768916155419222, "step": 1230}, {"loss": 1.7021, "grad_norm": 0.3625542223453522, "learning_rate": 0.0002, "epoch": 1.6905248807089297, "step": 1240}, {"loss": 1.6772, "grad_norm": 0.32170894742012024, "learning_rate": 0.0002, "epoch": 1.7041581458759372, "step": 1250}, {"loss": 1.7152, "grad_norm": 0.3544139862060547, "learning_rate": 0.0002, "epoch": 1.7177914110429446, "step": 1260}, {"loss": 1.7138, "grad_norm": 0.35113027691841125, "learning_rate": 0.0002, "epoch": 1.7314246762099523, "step": 1270}, {"loss": 1.7095, "grad_norm": 0.3499974310398102, "learning_rate": 0.0002, "epoch": 1.7450579413769598, "step": 1280}, {"loss": 1.7749, "grad_norm": 0.3285157382488251, "learning_rate": 0.0002, "epoch": 1.7586912065439673, "step": 1290}, {"loss": 1.6767, "grad_norm": 0.3701961636543274, "learning_rate": 0.0002, "epoch": 1.7723244717109747, "step": 1300}, {"loss": 1.6282, "grad_norm": 0.3301318287849426, "learning_rate": 0.0002, "epoch": 1.7859577368779824, "step": 1310}, {"loss": 1.7097, "grad_norm": 0.37801554799079895, "learning_rate": 0.0002, "epoch": 1.79959100204499, "step": 1320}, {"loss": 1.7437, "grad_norm": 0.3726748526096344, "learning_rate": 0.0002, "epoch": 1.8132242672119974, "step": 1330}, {"loss": 1.7959, "grad_norm": 0.4059790074825287, "learning_rate": 0.0002, "epoch": 1.8268575323790048, "step": 1340}, {"loss": 1.7739, "grad_norm": 0.35712096095085144, "learning_rate": 0.0002, "epoch": 1.8404907975460123, "step": 1350}, {"loss": 1.6375, "grad_norm": 0.35995328426361084, "learning_rate": 0.0002, "epoch": 1.8541240627130198, "step": 1360}, {"loss": 1.7332, "grad_norm": 0.3679947257041931, "learning_rate": 0.0002, "epoch": 1.8677573278800272, "step": 1370}, {"loss": 1.7587, "grad_norm": 0.39645957946777344, "learning_rate": 0.0002, "epoch": 1.8813905930470347, "step": 1380}, {"loss": 1.6985, "grad_norm": 0.35288700461387634, "learning_rate": 0.0002, "epoch": 1.8950238582140422, "step": 1390}, {"loss": 1.6582, "grad_norm": 0.32579198479652405, "learning_rate": 0.0002, "epoch": 1.9086571233810496, "step": 1400}, {"loss": 1.6948, "grad_norm": 0.3856561779975891, "learning_rate": 0.0002, "epoch": 1.9222903885480571, "step": 1410}, {"loss": 1.668, "grad_norm": 0.39019331336021423, "learning_rate": 0.0002, "epoch": 1.9359236537150648, "step": 1420}, {"loss": 1.7774, "grad_norm": 0.38006502389907837, "learning_rate": 0.0002, "epoch": 1.9495569188820723, "step": 1430}, {"loss": 1.8323, "grad_norm": 0.38100454211235046, "learning_rate": 0.0002, "epoch": 1.9631901840490797, "step": 1440}, {"loss": 1.7298, "grad_norm": 0.3405798673629761, "learning_rate": 0.0002, "epoch": 1.9768234492160872, "step": 1450}, {"loss": 1.7045, "grad_norm": 0.36582913994789124, "learning_rate": 0.0002, "epoch": 1.990456714383095, "step": 1460}, {"eval_loss": 1.8178424835205078, "eval_runtime": 53.6524, "eval_samples_per_second": 9.45, "eval_steps_per_second": 1.193, "epoch": 2.0, "step": 1467}, {"loss": 1.6363, "grad_norm": 0.3626647889614105, "learning_rate": 0.0002, "epoch": 2.0040899795501024, "step": 1470}, {"loss": 1.5354, "grad_norm": 0.40171775221824646, "learning_rate": 0.0002, "epoch": 2.01772324471711, "step": 1480}, {"loss": 1.5566, "grad_norm": 0.5805319547653198, "learning_rate": 0.0002, "epoch": 2.0313565098841173, "step": 1490}, {"loss": 1.546, "grad_norm": 0.41954153776168823, "learning_rate": 0.0002, "epoch": 2.044989775051125, "step": 1500}, {"loss": 1.6158, "grad_norm": 0.47190725803375244, "learning_rate": 0.0002, "epoch": 2.0586230402181322, "step": 1510}, {"loss": 1.5841, "grad_norm": 0.4388456344604492, "learning_rate": 0.0002, "epoch": 2.0722563053851397, "step": 1520}, {"loss": 1.5835, "grad_norm": 2.2171926498413086, "learning_rate": 0.0002, "epoch": 2.085889570552147, "step": 1530}, {"loss": 1.6137, "grad_norm": 0.4314221143722534, "learning_rate": 0.0002, "epoch": 2.0995228357191547, "step": 1540}, {"loss": 1.5511, "grad_norm": 0.4154265522956848, "learning_rate": 0.0002, "epoch": 2.113156100886162, "step": 1550}, {"loss": 1.6323, "grad_norm": 0.5025539994239807, "learning_rate": 0.0002, "epoch": 2.1267893660531696, "step": 1560}, {"loss": 1.5903, "grad_norm": 0.5410493016242981, "learning_rate": 0.0002, "epoch": 2.140422631220177, "step": 1570}, {"loss": 1.507, "grad_norm": 0.4478487968444824, "learning_rate": 0.0002, "epoch": 2.1540558963871845, "step": 1580}, {"loss": 1.5536, "grad_norm": 0.4703652560710907, "learning_rate": 0.0002, "epoch": 2.1676891615541924, "step": 1590}, {"loss": 1.5991, "grad_norm": 0.4555390179157257, "learning_rate": 0.0002, "epoch": 2.1813224267212, "step": 1600}, {"loss": 1.6117, "grad_norm": 0.4877263903617859, "learning_rate": 0.0002, "epoch": 2.1949556918882074, "step": 1610}, {"loss": 1.5928, "grad_norm": 0.48708245158195496, "learning_rate": 0.0002, "epoch": 2.208588957055215, "step": 1620}, {"loss": 1.6106, "grad_norm": 0.47523951530456543, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 1630}, {"loss": 1.6013, "grad_norm": 0.4889199733734131, "learning_rate": 0.0002, "epoch": 2.23585548738923, "step": 1640}, {"loss": 1.6633, "grad_norm": 0.4585252106189728, "learning_rate": 0.0002, "epoch": 2.2494887525562373, "step": 1650}, {"loss": 1.6075, "grad_norm": 0.4764868915081024, "learning_rate": 0.0002, "epoch": 2.2631220177232447, "step": 1660}, {"loss": 1.6427, "grad_norm": 0.5028976202011108, "learning_rate": 0.0002, "epoch": 2.276755282890252, "step": 1670}, {"loss": 1.6258, "grad_norm": 0.46131211519241333, "learning_rate": 0.0002, "epoch": 2.2903885480572597, "step": 1680}, {"loss": 1.654, "grad_norm": 0.5422874689102173, "learning_rate": 0.0002, "epoch": 2.304021813224267, "step": 1690}, {"loss": 1.6331, "grad_norm": 0.47615355253219604, "learning_rate": 0.0002, "epoch": 2.3176550783912746, "step": 1700}, {"loss": 1.642, "grad_norm": 0.48005548119544983, "learning_rate": 0.0002, "epoch": 2.331288343558282, "step": 1710}, {"loss": 1.581, "grad_norm": 0.4387182295322418, "learning_rate": 0.0002, "epoch": 2.3449216087252895, "step": 1720}, {"loss": 1.5612, "grad_norm": 0.4487272799015045, "learning_rate": 0.0002, "epoch": 2.358554873892297, "step": 1730}, {"loss": 1.5089, "grad_norm": 0.5046455264091492, "learning_rate": 0.0002, "epoch": 2.372188139059305, "step": 1740}, {"loss": 1.5769, "grad_norm": 0.4653521180152893, "learning_rate": 0.0002, "epoch": 2.3858214042263124, "step": 1750}, {"loss": 1.6201, "grad_norm": 0.4737723469734192, "learning_rate": 0.0002, "epoch": 2.39945466939332, "step": 1760}, {"loss": 1.5933, "grad_norm": 0.4501931071281433, "learning_rate": 0.0002, "epoch": 2.4130879345603273, "step": 1770}, {"loss": 1.6321, "grad_norm": 0.4772880971431732, "learning_rate": 0.0002, "epoch": 2.426721199727335, "step": 1780}, {"loss": 1.5454, "grad_norm": 0.4544616937637329, "learning_rate": 0.0002, "epoch": 2.4403544648943423, "step": 1790}, {"loss": 1.5501, "grad_norm": 0.488313227891922, "learning_rate": 0.0002, "epoch": 2.4539877300613497, "step": 1800}, {"loss": 1.5791, "grad_norm": 0.5057830214500427, "learning_rate": 0.0002, "epoch": 2.467620995228357, "step": 1810}, {"loss": 1.5645, "grad_norm": 0.5049484968185425, "learning_rate": 0.0002, "epoch": 2.4812542603953647, "step": 1820}, {"loss": 1.6268, "grad_norm": 0.44966644048690796, "learning_rate": 0.0002, "epoch": 2.494887525562372, "step": 1830}, {"loss": 1.5941, "grad_norm": 0.5072630643844604, "learning_rate": 0.0002, "epoch": 2.5085207907293796, "step": 1840}, {"loss": 1.5251, "grad_norm": 0.43989792466163635, "learning_rate": 0.0002, "epoch": 2.522154055896387, "step": 1850}, {"loss": 1.563, "grad_norm": 1.3504403829574585, "learning_rate": 0.0002, "epoch": 2.5357873210633946, "step": 1860}, {"loss": 1.5681, "grad_norm": 0.46545976400375366, "learning_rate": 0.0002, "epoch": 2.549420586230402, "step": 1870}, {"loss": 1.6368, "grad_norm": 0.4678342044353485, "learning_rate": 0.0002, "epoch": 2.5630538513974095, "step": 1880}, {"loss": 1.5814, "grad_norm": 0.529755711555481, "learning_rate": 0.0002, "epoch": 2.5766871165644174, "step": 1890}, {"loss": 1.5861, "grad_norm": 0.5000199675559998, "learning_rate": 0.0002, "epoch": 2.5903203817314244, "step": 1900}, {"loss": 1.6346, "grad_norm": 0.5649300217628479, "learning_rate": 0.0002, "epoch": 2.6039536468984323, "step": 1910}, {"loss": 1.6317, "grad_norm": 0.7920585870742798, "learning_rate": 0.0002, "epoch": 2.61758691206544, "step": 1920}, {"loss": 1.643, "grad_norm": 0.4960342049598694, "learning_rate": 0.0002, "epoch": 2.6312201772324473, "step": 1930}, {"loss": 1.6099, "grad_norm": 0.5324710011482239, "learning_rate": 0.0002, "epoch": 2.6448534423994547, "step": 1940}, {"loss": 1.5874, "grad_norm": 0.606343150138855, "learning_rate": 0.0002, "epoch": 2.658486707566462, "step": 1950}, {"loss": 1.5728, "grad_norm": 0.53038489818573, "learning_rate": 0.0002, "epoch": 2.6721199727334697, "step": 1960}, {"loss": 1.5583, "grad_norm": 0.4579465091228485, "learning_rate": 0.0002, "epoch": 2.685753237900477, "step": 1970}, {"loss": 1.6093, "grad_norm": 0.4541707932949066, "learning_rate": 0.0002, "epoch": 2.6993865030674846, "step": 1980}, {"loss": 1.5316, "grad_norm": 0.5009395480155945, "learning_rate": 0.0002, "epoch": 2.713019768234492, "step": 1990}, {"loss": 1.6724, "grad_norm": 0.4723006784915924, "learning_rate": 0.0002, "epoch": 2.7266530334014996, "step": 2000}, {"loss": 1.638, "grad_norm": 0.5086126923561096, "learning_rate": 0.0002, "epoch": 2.740286298568507, "step": 2010}, {"loss": 1.6223, "grad_norm": 0.47242608666419983, "learning_rate": 0.0002, "epoch": 2.7539195637355145, "step": 2020}, {"loss": 1.6242, "grad_norm": 0.44922566413879395, "learning_rate": 0.0002, "epoch": 2.767552828902522, "step": 2030}, {"loss": 1.6837, "grad_norm": 0.420259565114975, "learning_rate": 0.0002, "epoch": 2.78118609406953, "step": 2040}, {"loss": 1.5612, "grad_norm": 0.4762881100177765, "learning_rate": 0.0002, "epoch": 2.794819359236537, "step": 2050}, {"loss": 1.5506, "grad_norm": 0.5228786468505859, "learning_rate": 0.0002, "epoch": 2.808452624403545, "step": 2060}, {"loss": 1.6347, "grad_norm": 0.4796035587787628, "learning_rate": 0.0002, "epoch": 2.8220858895705523, "step": 2070}, {"loss": 1.6843, "grad_norm": 0.5034735202789307, "learning_rate": 0.0002, "epoch": 2.8357191547375598, "step": 2080}, {"loss": 1.6455, "grad_norm": 0.48005399107933044, "learning_rate": 0.0002, "epoch": 2.8493524199045672, "step": 2090}, {"loss": 1.6287, "grad_norm": 0.578820526599884, "learning_rate": 0.0002, "epoch": 2.8629856850715747, "step": 2100}, {"loss": 1.6021, "grad_norm": 0.48982638120651245, "learning_rate": 0.0002, "epoch": 2.876618950238582, "step": 2110}, {"loss": 1.5769, "grad_norm": 0.5157325863838196, "learning_rate": 0.0002, "epoch": 2.8902522154055896, "step": 2120}, {"loss": 1.6089, "grad_norm": 0.49149683117866516, "learning_rate": 0.0002, "epoch": 2.903885480572597, "step": 2130}, {"loss": 1.5881, "grad_norm": 0.48584499955177307, "learning_rate": 0.0002, "epoch": 2.9175187457396046, "step": 2140}, {"loss": 1.5833, "grad_norm": 0.5199017524719238, "learning_rate": 0.0002, "epoch": 2.931152010906612, "step": 2150}, {"loss": 1.7344, "grad_norm": 0.5788236856460571, "learning_rate": 0.0002, "epoch": 2.9447852760736195, "step": 2160}, {"loss": 1.6103, "grad_norm": 0.48664185404777527, "learning_rate": 0.0002, "epoch": 2.958418541240627, "step": 2170}, {"loss": 1.5765, "grad_norm": 0.5026682615280151, "learning_rate": 0.0002, "epoch": 2.9720518064076344, "step": 2180}, {"loss": 1.6626, "grad_norm": 0.49317044019699097, "learning_rate": 0.0002, "epoch": 2.9856850715746424, "step": 2190}, {"loss": 1.5871, "grad_norm": 0.5729128122329712, "learning_rate": 0.0002, "epoch": 2.9993183367416494, "step": 2200}]}
+{"epoch": 4.0, "step": 2934, "epoch_duration": 1094.484756231308, "total_accumulated_duration": 4381.578528881073, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19996.724609375}, "avg_memory_reserved": {"GPU_0": 28746.0}, "peak_memory_reserved": {"GPU_0": 28746.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733", "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": 3.0982, "grad_norm": 0.7714291214942932, "learning_rate": 0.0002, "epoch": 0.013633265167007498, "step": 10}, {"loss": 2.5206, "grad_norm": 0.5473978519439697, "learning_rate": 0.0002, "epoch": 0.027266530334014997, "step": 20}, {"loss": 2.3079, "grad_norm": 0.5452795624732971, "learning_rate": 0.0002, "epoch": 0.0408997955010225, "step": 30}, {"loss": 2.0019, "grad_norm": 0.5098028779029846, "learning_rate": 0.0002, "epoch": 0.054533060668029994, "step": 40}, {"loss": 1.9333, "grad_norm": 0.48062971234321594, "learning_rate": 0.0002, "epoch": 0.0681663258350375, "step": 50}, {"loss": 1.9355, "grad_norm": 0.4505695104598999, "learning_rate": 0.0002, "epoch": 0.081799591002045, "step": 60}, {"loss": 1.9312, "grad_norm": 0.41609591245651245, "learning_rate": 0.0002, "epoch": 0.09543285616905249, "step": 70}, {"loss": 1.8656, "grad_norm": 0.4323892593383789, "learning_rate": 0.0002, "epoch": 0.10906612133605999, "step": 80}, {"loss": 1.9294, "grad_norm": 0.4670293629169464, "learning_rate": 0.0002, "epoch": 0.12269938650306748, "step": 90}, {"loss": 1.7946, "grad_norm": 0.40623316168785095, "learning_rate": 0.0002, "epoch": 0.136332651670075, "step": 100}, {"loss": 1.8565, "grad_norm": 0.3620383143424988, "learning_rate": 0.0002, "epoch": 0.1499659168370825, "step": 110}, {"loss": 1.9238, "grad_norm": 0.332218736410141, "learning_rate": 0.0002, "epoch": 0.16359918200409, "step": 120}, {"loss": 1.93, "grad_norm": 0.4004521667957306, "learning_rate": 0.0002, "epoch": 0.17723244717109748, "step": 130}, {"loss": 1.7549, "grad_norm": 0.3698360323905945, "learning_rate": 0.0002, "epoch": 0.19086571233810498, "step": 140}, {"loss": 1.8771, "grad_norm": 0.3847949504852295, "learning_rate": 0.0002, "epoch": 0.20449897750511248, "step": 150}, {"loss": 1.8316, "grad_norm": 0.36843451857566833, "learning_rate": 0.0002, "epoch": 0.21813224267211997, "step": 160}, {"loss": 1.838, "grad_norm": 0.37301021814346313, "learning_rate": 0.0002, "epoch": 0.23176550783912747, "step": 170}, {"loss": 1.8909, "grad_norm": 0.3718886971473694, "learning_rate": 0.0002, "epoch": 0.24539877300613497, "step": 180}, {"loss": 1.8454, "grad_norm": 0.3088490962982178, "learning_rate": 0.0002, "epoch": 0.25903203817314246, "step": 190}, {"loss": 1.9254, "grad_norm": 0.3611852526664734, "learning_rate": 0.0002, "epoch": 0.27266530334015, "step": 200}, {"loss": 1.7844, "grad_norm": 0.36093324422836304, "learning_rate": 0.0002, "epoch": 0.28629856850715746, "step": 210}, {"loss": 1.719, "grad_norm": 0.3250400722026825, "learning_rate": 0.0002, "epoch": 0.299931833674165, "step": 220}, {"loss": 1.8729, "grad_norm": 0.3566756248474121, "learning_rate": 0.0002, "epoch": 0.31356509884117245, "step": 230}, {"loss": 1.9259, "grad_norm": 0.32872408628463745, "learning_rate": 0.0002, "epoch": 0.32719836400818, "step": 240}, {"loss": 1.9033, "grad_norm": 0.3983881175518036, "learning_rate": 0.0002, "epoch": 0.34083162917518744, "step": 250}, {"loss": 1.8588, "grad_norm": 0.3571510910987854, "learning_rate": 0.0002, "epoch": 0.35446489434219497, "step": 260}, {"loss": 1.8539, "grad_norm": 0.3036131262779236, "learning_rate": 0.0002, "epoch": 0.36809815950920244, "step": 270}, {"loss": 1.8572, "grad_norm": 0.36512863636016846, "learning_rate": 0.0002, "epoch": 0.38173142467620996, "step": 280}, {"loss": 1.8022, "grad_norm": 0.3429736793041229, "learning_rate": 0.0002, "epoch": 0.39536468984321743, "step": 290}, {"loss": 1.8754, "grad_norm": 0.3055964708328247, "learning_rate": 0.0002, "epoch": 0.40899795501022496, "step": 300}, {"loss": 1.8384, "grad_norm": 0.33801034092903137, "learning_rate": 0.0002, "epoch": 0.4226312201772324, "step": 310}, {"loss": 1.7933, "grad_norm": 0.348783016204834, "learning_rate": 0.0002, "epoch": 0.43626448534423995, "step": 320}, {"loss": 1.8451, "grad_norm": 0.3057514727115631, "learning_rate": 0.0002, "epoch": 0.4498977505112474, "step": 330}, {"loss": 1.8766, "grad_norm": 0.3849763572216034, "learning_rate": 0.0002, "epoch": 0.46353101567825494, "step": 340}, {"loss": 1.8073, "grad_norm": 0.30080053210258484, "learning_rate": 0.0002, "epoch": 0.47716428084526247, "step": 350}, {"loss": 1.8548, "grad_norm": 0.3595106303691864, "learning_rate": 0.0002, "epoch": 0.49079754601226994, "step": 360}, {"loss": 1.8232, "grad_norm": 0.31099820137023926, "learning_rate": 0.0002, "epoch": 0.5044308111792775, "step": 370}, {"loss": 1.7029, "grad_norm": 0.3157978355884552, "learning_rate": 0.0002, "epoch": 0.5180640763462849, "step": 380}, {"loss": 1.8265, "grad_norm": 0.27960965037345886, "learning_rate": 0.0002, "epoch": 0.5316973415132924, "step": 390}, {"loss": 1.7414, "grad_norm": 0.3102385103702545, "learning_rate": 0.0002, "epoch": 0.5453306066803, "step": 400}, {"loss": 1.7461, "grad_norm": 0.32828861474990845, "learning_rate": 0.0002, "epoch": 0.5589638718473074, "step": 410}, {"loss": 1.8165, "grad_norm": 0.29560017585754395, "learning_rate": 0.0002, "epoch": 0.5725971370143149, "step": 420}, {"loss": 1.9455, "grad_norm": 0.33316895365715027, "learning_rate": 0.0002, "epoch": 0.5862304021813224, "step": 430}, {"loss": 1.8241, "grad_norm": 0.30420982837677, "learning_rate": 0.0002, "epoch": 0.59986366734833, "step": 440}, {"loss": 1.7565, "grad_norm": 0.32619214057922363, "learning_rate": 0.0002, "epoch": 0.6134969325153374, "step": 450}, {"loss": 1.7945, "grad_norm": 0.3603750765323639, "learning_rate": 0.0002, "epoch": 0.6271301976823449, "step": 460}, {"loss": 1.7773, "grad_norm": 0.30834096670150757, "learning_rate": 0.0002, "epoch": 0.6407634628493524, "step": 470}, {"loss": 1.8058, "grad_norm": 0.28756365180015564, "learning_rate": 0.0002, "epoch": 0.65439672801636, "step": 480}, {"loss": 1.744, "grad_norm": 0.2878406345844269, "learning_rate": 0.0002, "epoch": 0.6680299931833674, "step": 490}, {"loss": 1.8581, "grad_norm": 0.31329697370529175, "learning_rate": 0.0002, "epoch": 0.6816632583503749, "step": 500}, {"loss": 1.7886, "grad_norm": 0.3405822515487671, "learning_rate": 0.0002, "epoch": 0.6952965235173824, "step": 510}, {"loss": 1.778, "grad_norm": 0.305560827255249, "learning_rate": 0.0002, "epoch": 0.7089297886843899, "step": 520}, {"loss": 1.7592, "grad_norm": 0.2973416745662689, "learning_rate": 0.0002, "epoch": 0.7225630538513974, "step": 530}, {"loss": 1.8223, "grad_norm": 0.327303946018219, "learning_rate": 0.0002, "epoch": 0.7361963190184049, "step": 540}, {"loss": 1.8591, "grad_norm": 0.62595534324646, "learning_rate": 0.0002, "epoch": 0.7498295841854125, "step": 550}, {"loss": 1.7466, "grad_norm": 0.3129784166812897, "learning_rate": 0.0002, "epoch": 0.7634628493524199, "step": 560}, {"loss": 1.8035, "grad_norm": 0.32496583461761475, "learning_rate": 0.0002, "epoch": 0.7770961145194274, "step": 570}, {"loss": 1.7787, "grad_norm": 0.3098868131637573, "learning_rate": 0.0002, "epoch": 0.7907293796864349, "step": 580}, {"loss": 1.7196, "grad_norm": 0.30726853013038635, "learning_rate": 0.0002, "epoch": 0.8043626448534424, "step": 590}, {"loss": 1.7898, "grad_norm": 0.2964220643043518, "learning_rate": 0.0002, "epoch": 0.8179959100204499, "step": 600}, {"loss": 1.8114, "grad_norm": 0.32352274656295776, "learning_rate": 0.0002, "epoch": 0.8316291751874574, "step": 610}, {"loss": 1.811, "grad_norm": 0.2938912510871887, "learning_rate": 0.0002, "epoch": 0.8452624403544649, "step": 620}, {"loss": 1.7727, "grad_norm": 0.295559823513031, "learning_rate": 0.0002, "epoch": 0.8588957055214724, "step": 630}, {"loss": 1.9, "grad_norm": 0.34102028608322144, "learning_rate": 0.0002, "epoch": 0.8725289706884799, "step": 640}, {"loss": 1.8006, "grad_norm": 0.29676181077957153, "learning_rate": 0.0002, "epoch": 0.8861622358554874, "step": 650}, {"loss": 1.8099, "grad_norm": 0.3108902871608734, "learning_rate": 0.0002, "epoch": 0.8997955010224948, "step": 660}, {"loss": 1.7955, "grad_norm": 0.2690821588039398, "learning_rate": 0.0002, "epoch": 0.9134287661895024, "step": 670}, {"loss": 1.7881, "grad_norm": 0.32752540707588196, "learning_rate": 0.0002, "epoch": 0.9270620313565099, "step": 680}, {"loss": 1.7661, "grad_norm": 0.8029476404190063, "learning_rate": 0.0002, "epoch": 0.9406952965235174, "step": 690}, {"loss": 1.7733, "grad_norm": 0.30534422397613525, "learning_rate": 0.0002, "epoch": 0.9543285616905249, "step": 700}, {"loss": 1.7614, "grad_norm": 0.2899954319000244, "learning_rate": 0.0002, "epoch": 0.9679618268575324, "step": 710}, {"loss": 1.7845, "grad_norm": 0.28814372420310974, "learning_rate": 0.0002, "epoch": 0.9815950920245399, "step": 720}, {"loss": 1.8865, "grad_norm": 0.3061596751213074, "learning_rate": 0.0002, "epoch": 0.9952283571915473, "step": 730}, {"eval_loss": 1.8171186447143555, "eval_runtime": 53.6047, "eval_samples_per_second": 9.458, "eval_steps_per_second": 1.194, "epoch": 0.9993183367416496, "step": 733}, {"loss": 1.6202, "grad_norm": 0.3140897750854492, "learning_rate": 0.0002, "epoch": 1.008861622358555, "step": 740}, {"loss": 1.8409, "grad_norm": 0.3346109390258789, "learning_rate": 0.0002, "epoch": 1.0224948875255624, "step": 750}, {"loss": 1.6777, "grad_norm": 0.3582976758480072, "learning_rate": 0.0002, "epoch": 1.0361281526925699, "step": 760}, {"loss": 1.7306, "grad_norm": 0.30408260226249695, "learning_rate": 0.0002, "epoch": 1.0497614178595773, "step": 770}, {"loss": 1.6967, "grad_norm": 0.323585569858551, "learning_rate": 0.0002, "epoch": 1.0633946830265848, "step": 780}, {"loss": 1.768, "grad_norm": 0.3474137783050537, "learning_rate": 0.0002, "epoch": 1.0770279481935923, "step": 790}, {"loss": 1.6895, "grad_norm": 0.35721147060394287, "learning_rate": 0.0002, "epoch": 1.0906612133606, "step": 800}, {"loss": 1.718, "grad_norm": 0.35366931557655334, "learning_rate": 0.0002, "epoch": 1.1042944785276074, "step": 810}, {"loss": 1.6797, "grad_norm": 0.3250770568847656, "learning_rate": 0.0002, "epoch": 1.117927743694615, "step": 820}, {"loss": 1.6383, "grad_norm": 0.3293766379356384, "learning_rate": 0.0002, "epoch": 1.1315610088616224, "step": 830}, {"loss": 1.7353, "grad_norm": 0.3380851745605469, "learning_rate": 0.0002, "epoch": 1.1451942740286298, "step": 840}, {"loss": 1.8236, "grad_norm": 0.32584455609321594, "learning_rate": 0.0002, "epoch": 1.1588275391956373, "step": 850}, {"loss": 1.6681, "grad_norm": 0.45700767636299133, "learning_rate": 0.0002, "epoch": 1.1724608043626448, "step": 860}, {"loss": 1.7494, "grad_norm": 0.30944544076919556, "learning_rate": 0.0002, "epoch": 1.1860940695296525, "step": 870}, {"loss": 1.7426, "grad_norm": 0.3268151581287384, "learning_rate": 0.0002, "epoch": 1.19972733469666, "step": 880}, {"loss": 1.7413, "grad_norm": 0.39972540736198425, "learning_rate": 0.0002, "epoch": 1.2133605998636674, "step": 890}, {"loss": 1.7481, "grad_norm": 0.7890929579734802, "learning_rate": 0.0002, "epoch": 1.2269938650306749, "step": 900}, {"loss": 1.7608, "grad_norm": 0.3439182639122009, "learning_rate": 0.0002, "epoch": 1.2406271301976823, "step": 910}, {"loss": 1.7617, "grad_norm": 0.3986225128173828, "learning_rate": 0.0002, "epoch": 1.2542603953646898, "step": 920}, {"loss": 1.6843, "grad_norm": 0.3514605164527893, "learning_rate": 0.0002, "epoch": 1.2678936605316973, "step": 930}, {"loss": 1.6987, "grad_norm": 0.3682589530944824, "learning_rate": 0.0002, "epoch": 1.2815269256987047, "step": 940}, {"loss": 1.6988, "grad_norm": 0.3618335723876953, "learning_rate": 0.0002, "epoch": 1.2951601908657122, "step": 950}, {"loss": 1.7436, "grad_norm": 0.345700740814209, "learning_rate": 0.0002, "epoch": 1.30879345603272, "step": 960}, {"loss": 1.7336, "grad_norm": 0.3514927923679352, "learning_rate": 0.0002, "epoch": 1.3224267211997274, "step": 970}, {"loss": 1.7704, "grad_norm": 0.365647554397583, "learning_rate": 0.0002, "epoch": 1.3360599863667348, "step": 980}, {"loss": 1.7104, "grad_norm": 0.3407285809516907, "learning_rate": 0.0002, "epoch": 1.3496932515337423, "step": 990}, {"loss": 1.7132, "grad_norm": 0.3785437345504761, "learning_rate": 0.0002, "epoch": 1.3633265167007498, "step": 1000}, {"loss": 1.766, "grad_norm": 0.34746724367141724, "learning_rate": 0.0002, "epoch": 1.3769597818677572, "step": 1010}, {"loss": 1.7252, "grad_norm": 0.362444132566452, "learning_rate": 0.0002, "epoch": 1.390593047034765, "step": 1020}, {"loss": 1.7132, "grad_norm": 0.4424704611301422, "learning_rate": 0.0002, "epoch": 1.4042263122017724, "step": 1030}, {"loss": 1.726, "grad_norm": 0.38722458481788635, "learning_rate": 0.0002, "epoch": 1.4178595773687799, "step": 1040}, {"loss": 1.7955, "grad_norm": 0.36089080572128296, "learning_rate": 0.0002, "epoch": 1.4314928425357873, "step": 1050}, {"loss": 1.6924, "grad_norm": 0.33817124366760254, "learning_rate": 0.0002, "epoch": 1.4451261077027948, "step": 1060}, {"loss": 1.7165, "grad_norm": 0.34334081411361694, "learning_rate": 0.0002, "epoch": 1.4587593728698023, "step": 1070}, {"loss": 1.6999, "grad_norm": 0.3776826858520508, "learning_rate": 0.0002, "epoch": 1.4723926380368098, "step": 1080}, {"loss": 1.7605, "grad_norm": 0.4169026017189026, "learning_rate": 0.0002, "epoch": 1.4860259032038172, "step": 1090}, {"loss": 1.7502, "grad_norm": 0.34898945689201355, "learning_rate": 0.0002, "epoch": 1.4996591683708247, "step": 1100}, {"loss": 1.635, "grad_norm": 0.34223780035972595, "learning_rate": 0.0002, "epoch": 1.5132924335378322, "step": 1110}, {"loss": 1.7248, "grad_norm": 0.3686901032924652, "learning_rate": 0.0002, "epoch": 1.5269256987048399, "step": 1120}, {"loss": 1.7525, "grad_norm": 0.35054415464401245, "learning_rate": 0.0002, "epoch": 1.5405589638718473, "step": 1130}, {"loss": 1.7776, "grad_norm": 0.39496365189552307, "learning_rate": 0.0002, "epoch": 1.5541922290388548, "step": 1140}, {"loss": 1.6574, "grad_norm": 0.35451626777648926, "learning_rate": 0.0002, "epoch": 1.5678254942058623, "step": 1150}, {"loss": 1.7257, "grad_norm": 0.3848083019256592, "learning_rate": 0.0002, "epoch": 1.58145875937287, "step": 1160}, {"loss": 1.7272, "grad_norm": 0.3760537803173065, "learning_rate": 0.0002, "epoch": 1.5950920245398774, "step": 1170}, {"loss": 1.7441, "grad_norm": 0.38981738686561584, "learning_rate": 0.0002, "epoch": 1.6087252897068849, "step": 1180}, {"loss": 1.6951, "grad_norm": 0.36830949783325195, "learning_rate": 0.0002, "epoch": 1.6223585548738924, "step": 1190}, {"loss": 1.6925, "grad_norm": 0.3405892848968506, "learning_rate": 0.0002, "epoch": 1.6359918200408998, "step": 1200}, {"loss": 1.7473, "grad_norm": 0.39027872681617737, "learning_rate": 0.0002, "epoch": 1.6496250852079073, "step": 1210}, {"loss": 1.6792, "grad_norm": 0.3342694044113159, "learning_rate": 0.0002, "epoch": 1.6632583503749148, "step": 1220}, {"loss": 1.7196, "grad_norm": 0.3600076735019684, "learning_rate": 0.0002, "epoch": 1.6768916155419222, "step": 1230}, {"loss": 1.7021, "grad_norm": 0.3625542223453522, "learning_rate": 0.0002, "epoch": 1.6905248807089297, "step": 1240}, {"loss": 1.6772, "grad_norm": 0.32170894742012024, "learning_rate": 0.0002, "epoch": 1.7041581458759372, "step": 1250}, {"loss": 1.7152, "grad_norm": 0.3544139862060547, "learning_rate": 0.0002, "epoch": 1.7177914110429446, "step": 1260}, {"loss": 1.7138, "grad_norm": 0.35113027691841125, "learning_rate": 0.0002, "epoch": 1.7314246762099523, "step": 1270}, {"loss": 1.7095, "grad_norm": 0.3499974310398102, "learning_rate": 0.0002, "epoch": 1.7450579413769598, "step": 1280}, {"loss": 1.7749, "grad_norm": 0.3285157382488251, "learning_rate": 0.0002, "epoch": 1.7586912065439673, "step": 1290}, {"loss": 1.6767, "grad_norm": 0.3701961636543274, "learning_rate": 0.0002, "epoch": 1.7723244717109747, "step": 1300}, {"loss": 1.6282, "grad_norm": 0.3301318287849426, "learning_rate": 0.0002, "epoch": 1.7859577368779824, "step": 1310}, {"loss": 1.7097, "grad_norm": 0.37801554799079895, "learning_rate": 0.0002, "epoch": 1.79959100204499, "step": 1320}, {"loss": 1.7437, "grad_norm": 0.3726748526096344, "learning_rate": 0.0002, "epoch": 1.8132242672119974, "step": 1330}, {"loss": 1.7959, "grad_norm": 0.4059790074825287, "learning_rate": 0.0002, "epoch": 1.8268575323790048, "step": 1340}, {"loss": 1.7739, "grad_norm": 0.35712096095085144, "learning_rate": 0.0002, "epoch": 1.8404907975460123, "step": 1350}, {"loss": 1.6375, "grad_norm": 0.35995328426361084, "learning_rate": 0.0002, "epoch": 1.8541240627130198, "step": 1360}, {"loss": 1.7332, "grad_norm": 0.3679947257041931, "learning_rate": 0.0002, "epoch": 1.8677573278800272, "step": 1370}, {"loss": 1.7587, "grad_norm": 0.39645957946777344, "learning_rate": 0.0002, "epoch": 1.8813905930470347, "step": 1380}, {"loss": 1.6985, "grad_norm": 0.35288700461387634, "learning_rate": 0.0002, "epoch": 1.8950238582140422, "step": 1390}, {"loss": 1.6582, "grad_norm": 0.32579198479652405, "learning_rate": 0.0002, "epoch": 1.9086571233810496, "step": 1400}, {"loss": 1.6948, "grad_norm": 0.3856561779975891, "learning_rate": 0.0002, "epoch": 1.9222903885480571, "step": 1410}, {"loss": 1.668, "grad_norm": 0.39019331336021423, "learning_rate": 0.0002, "epoch": 1.9359236537150648, "step": 1420}, {"loss": 1.7774, "grad_norm": 0.38006502389907837, "learning_rate": 0.0002, "epoch": 1.9495569188820723, "step": 1430}, {"loss": 1.8323, "grad_norm": 0.38100454211235046, "learning_rate": 0.0002, "epoch": 1.9631901840490797, "step": 1440}, {"loss": 1.7298, "grad_norm": 0.3405798673629761, "learning_rate": 0.0002, "epoch": 1.9768234492160872, "step": 1450}, {"loss": 1.7045, "grad_norm": 0.36582913994789124, "learning_rate": 0.0002, "epoch": 1.990456714383095, "step": 1460}, {"eval_loss": 1.8178424835205078, "eval_runtime": 53.6524, "eval_samples_per_second": 9.45, "eval_steps_per_second": 1.193, "epoch": 2.0, "step": 1467}, {"loss": 1.6363, "grad_norm": 0.3626647889614105, "learning_rate": 0.0002, "epoch": 2.0040899795501024, "step": 1470}, {"loss": 1.5354, "grad_norm": 0.40171775221824646, "learning_rate": 0.0002, "epoch": 2.01772324471711, "step": 1480}, {"loss": 1.5566, "grad_norm": 0.5805319547653198, "learning_rate": 0.0002, "epoch": 2.0313565098841173, "step": 1490}, {"loss": 1.546, "grad_norm": 0.41954153776168823, "learning_rate": 0.0002, "epoch": 2.044989775051125, "step": 1500}, {"loss": 1.6158, "grad_norm": 0.47190725803375244, "learning_rate": 0.0002, "epoch": 2.0586230402181322, "step": 1510}, {"loss": 1.5841, "grad_norm": 0.4388456344604492, "learning_rate": 0.0002, "epoch": 2.0722563053851397, "step": 1520}, {"loss": 1.5835, "grad_norm": 2.2171926498413086, "learning_rate": 0.0002, "epoch": 2.085889570552147, "step": 1530}, {"loss": 1.6137, "grad_norm": 0.4314221143722534, "learning_rate": 0.0002, "epoch": 2.0995228357191547, "step": 1540}, {"loss": 1.5511, "grad_norm": 0.4154265522956848, "learning_rate": 0.0002, "epoch": 2.113156100886162, "step": 1550}, {"loss": 1.6323, "grad_norm": 0.5025539994239807, "learning_rate": 0.0002, "epoch": 2.1267893660531696, "step": 1560}, {"loss": 1.5903, "grad_norm": 0.5410493016242981, "learning_rate": 0.0002, "epoch": 2.140422631220177, "step": 1570}, {"loss": 1.507, "grad_norm": 0.4478487968444824, "learning_rate": 0.0002, "epoch": 2.1540558963871845, "step": 1580}, {"loss": 1.5536, "grad_norm": 0.4703652560710907, "learning_rate": 0.0002, "epoch": 2.1676891615541924, "step": 1590}, {"loss": 1.5991, "grad_norm": 0.4555390179157257, "learning_rate": 0.0002, "epoch": 2.1813224267212, "step": 1600}, {"loss": 1.6117, "grad_norm": 0.4877263903617859, "learning_rate": 0.0002, "epoch": 2.1949556918882074, "step": 1610}, {"loss": 1.5928, "grad_norm": 0.48708245158195496, "learning_rate": 0.0002, "epoch": 2.208588957055215, "step": 1620}, {"loss": 1.6106, "grad_norm": 0.47523951530456543, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 1630}, {"loss": 1.6013, "grad_norm": 0.4889199733734131, "learning_rate": 0.0002, "epoch": 2.23585548738923, "step": 1640}, {"loss": 1.6633, "grad_norm": 0.4585252106189728, "learning_rate": 0.0002, "epoch": 2.2494887525562373, "step": 1650}, {"loss": 1.6075, "grad_norm": 0.4764868915081024, "learning_rate": 0.0002, "epoch": 2.2631220177232447, "step": 1660}, {"loss": 1.6427, "grad_norm": 0.5028976202011108, "learning_rate": 0.0002, "epoch": 2.276755282890252, "step": 1670}, {"loss": 1.6258, "grad_norm": 0.46131211519241333, "learning_rate": 0.0002, "epoch": 2.2903885480572597, "step": 1680}, {"loss": 1.654, "grad_norm": 0.5422874689102173, "learning_rate": 0.0002, "epoch": 2.304021813224267, "step": 1690}, {"loss": 1.6331, "grad_norm": 0.47615355253219604, "learning_rate": 0.0002, "epoch": 2.3176550783912746, "step": 1700}, {"loss": 1.642, "grad_norm": 0.48005548119544983, "learning_rate": 0.0002, "epoch": 2.331288343558282, "step": 1710}, {"loss": 1.581, "grad_norm": 0.4387182295322418, "learning_rate": 0.0002, "epoch": 2.3449216087252895, "step": 1720}, {"loss": 1.5612, "grad_norm": 0.4487272799015045, "learning_rate": 0.0002, "epoch": 2.358554873892297, "step": 1730}, {"loss": 1.5089, "grad_norm": 0.5046455264091492, "learning_rate": 0.0002, "epoch": 2.372188139059305, "step": 1740}, {"loss": 1.5769, "grad_norm": 0.4653521180152893, "learning_rate": 0.0002, "epoch": 2.3858214042263124, "step": 1750}, {"loss": 1.6201, "grad_norm": 0.4737723469734192, "learning_rate": 0.0002, "epoch": 2.39945466939332, "step": 1760}, {"loss": 1.5933, "grad_norm": 0.4501931071281433, "learning_rate": 0.0002, "epoch": 2.4130879345603273, "step": 1770}, {"loss": 1.6321, "grad_norm": 0.4772880971431732, "learning_rate": 0.0002, "epoch": 2.426721199727335, "step": 1780}, {"loss": 1.5454, "grad_norm": 0.4544616937637329, "learning_rate": 0.0002, "epoch": 2.4403544648943423, "step": 1790}, {"loss": 1.5501, "grad_norm": 0.488313227891922, "learning_rate": 0.0002, "epoch": 2.4539877300613497, "step": 1800}, {"loss": 1.5791, "grad_norm": 0.5057830214500427, "learning_rate": 0.0002, "epoch": 2.467620995228357, "step": 1810}, {"loss": 1.5645, "grad_norm": 0.5049484968185425, "learning_rate": 0.0002, "epoch": 2.4812542603953647, "step": 1820}, {"loss": 1.6268, "grad_norm": 0.44966644048690796, "learning_rate": 0.0002, "epoch": 2.494887525562372, "step": 1830}, {"loss": 1.5941, "grad_norm": 0.5072630643844604, "learning_rate": 0.0002, "epoch": 2.5085207907293796, "step": 1840}, {"loss": 1.5251, "grad_norm": 0.43989792466163635, "learning_rate": 0.0002, "epoch": 2.522154055896387, "step": 1850}, {"loss": 1.563, "grad_norm": 1.3504403829574585, "learning_rate": 0.0002, "epoch": 2.5357873210633946, "step": 1860}, {"loss": 1.5681, "grad_norm": 0.46545976400375366, "learning_rate": 0.0002, "epoch": 2.549420586230402, "step": 1870}, {"loss": 1.6368, "grad_norm": 0.4678342044353485, "learning_rate": 0.0002, "epoch": 2.5630538513974095, "step": 1880}, {"loss": 1.5814, "grad_norm": 0.529755711555481, "learning_rate": 0.0002, "epoch": 2.5766871165644174, "step": 1890}, {"loss": 1.5861, "grad_norm": 0.5000199675559998, "learning_rate": 0.0002, "epoch": 2.5903203817314244, "step": 1900}, {"loss": 1.6346, "grad_norm": 0.5649300217628479, "learning_rate": 0.0002, "epoch": 2.6039536468984323, "step": 1910}, {"loss": 1.6317, "grad_norm": 0.7920585870742798, "learning_rate": 0.0002, "epoch": 2.61758691206544, "step": 1920}, {"loss": 1.643, "grad_norm": 0.4960342049598694, "learning_rate": 0.0002, "epoch": 2.6312201772324473, "step": 1930}, {"loss": 1.6099, "grad_norm": 0.5324710011482239, "learning_rate": 0.0002, "epoch": 2.6448534423994547, "step": 1940}, {"loss": 1.5874, "grad_norm": 0.606343150138855, "learning_rate": 0.0002, "epoch": 2.658486707566462, "step": 1950}, {"loss": 1.5728, "grad_norm": 0.53038489818573, "learning_rate": 0.0002, "epoch": 2.6721199727334697, "step": 1960}, {"loss": 1.5583, "grad_norm": 0.4579465091228485, "learning_rate": 0.0002, "epoch": 2.685753237900477, "step": 1970}, {"loss": 1.6093, "grad_norm": 0.4541707932949066, "learning_rate": 0.0002, "epoch": 2.6993865030674846, "step": 1980}, {"loss": 1.5316, "grad_norm": 0.5009395480155945, "learning_rate": 0.0002, "epoch": 2.713019768234492, "step": 1990}, {"loss": 1.6724, "grad_norm": 0.4723006784915924, "learning_rate": 0.0002, "epoch": 2.7266530334014996, "step": 2000}, {"loss": 1.638, "grad_norm": 0.5086126923561096, "learning_rate": 0.0002, "epoch": 2.740286298568507, "step": 2010}, {"loss": 1.6223, "grad_norm": 0.47242608666419983, "learning_rate": 0.0002, "epoch": 2.7539195637355145, "step": 2020}, {"loss": 1.6242, "grad_norm": 0.44922566413879395, "learning_rate": 0.0002, "epoch": 2.767552828902522, "step": 2030}, {"loss": 1.6837, "grad_norm": 0.420259565114975, "learning_rate": 0.0002, "epoch": 2.78118609406953, "step": 2040}, {"loss": 1.5612, "grad_norm": 0.4762881100177765, "learning_rate": 0.0002, "epoch": 2.794819359236537, "step": 2050}, {"loss": 1.5506, "grad_norm": 0.5228786468505859, "learning_rate": 0.0002, "epoch": 2.808452624403545, "step": 2060}, {"loss": 1.6347, "grad_norm": 0.4796035587787628, "learning_rate": 0.0002, "epoch": 2.8220858895705523, "step": 2070}, {"loss": 1.6843, "grad_norm": 0.5034735202789307, "learning_rate": 0.0002, "epoch": 2.8357191547375598, "step": 2080}, {"loss": 1.6455, "grad_norm": 0.48005399107933044, "learning_rate": 0.0002, "epoch": 2.8493524199045672, "step": 2090}, {"loss": 1.6287, "grad_norm": 0.578820526599884, "learning_rate": 0.0002, "epoch": 2.8629856850715747, "step": 2100}, {"loss": 1.6021, "grad_norm": 0.48982638120651245, "learning_rate": 0.0002, "epoch": 2.876618950238582, "step": 2110}, {"loss": 1.5769, "grad_norm": 0.5157325863838196, "learning_rate": 0.0002, "epoch": 2.8902522154055896, "step": 2120}, {"loss": 1.6089, "grad_norm": 0.49149683117866516, "learning_rate": 0.0002, "epoch": 2.903885480572597, "step": 2130}, {"loss": 1.5881, "grad_norm": 0.48584499955177307, "learning_rate": 0.0002, "epoch": 2.9175187457396046, "step": 2140}, {"loss": 1.5833, "grad_norm": 0.5199017524719238, "learning_rate": 0.0002, "epoch": 2.931152010906612, "step": 2150}, {"loss": 1.7344, "grad_norm": 0.5788236856460571, "learning_rate": 0.0002, "epoch": 2.9447852760736195, "step": 2160}, {"loss": 1.6103, "grad_norm": 0.48664185404777527, "learning_rate": 0.0002, "epoch": 2.958418541240627, "step": 2170}, {"loss": 1.5765, "grad_norm": 0.5026682615280151, "learning_rate": 0.0002, "epoch": 2.9720518064076344, "step": 2180}, {"loss": 1.6626, "grad_norm": 0.49317044019699097, "learning_rate": 0.0002, "epoch": 2.9856850715746424, "step": 2190}, {"loss": 1.5871, "grad_norm": 0.5729128122329712, "learning_rate": 0.0002, "epoch": 2.9993183367416494, "step": 2200}, {"eval_loss": 1.8527295589447021, "eval_runtime": 53.6403, "eval_samples_per_second": 9.452, "eval_steps_per_second": 1.193, "epoch": 2.9993183367416494, "step": 2200}, {"loss": 1.4719, "grad_norm": 0.5530241131782532, "learning_rate": 0.0002, "epoch": 3.0129516019086573, "step": 2210}, {"loss": 1.4088, "grad_norm": 0.6642216444015503, "learning_rate": 0.0002, "epoch": 3.0265848670756648, "step": 2220}, {"loss": 1.4382, "grad_norm": 0.61470627784729, "learning_rate": 0.0002, "epoch": 3.0402181322426722, "step": 2230}, {"loss": 1.4634, "grad_norm": 0.8559566140174866, "learning_rate": 0.0002, "epoch": 3.0538513974096797, "step": 2240}, {"loss": 1.3854, "grad_norm": 0.7015801668167114, "learning_rate": 0.0002, "epoch": 3.067484662576687, "step": 2250}, {"loss": 1.4981, "grad_norm": 0.7226442694664001, "learning_rate": 0.0002, "epoch": 3.0811179277436946, "step": 2260}, {"loss": 1.4143, "grad_norm": 0.7560588717460632, "learning_rate": 0.0002, "epoch": 3.094751192910702, "step": 2270}, {"loss": 1.4395, "grad_norm": 0.6216568946838379, "learning_rate": 0.0002, "epoch": 3.1083844580777096, "step": 2280}, {"loss": 1.3842, "grad_norm": 0.6768500804901123, "learning_rate": 0.0002, "epoch": 3.122017723244717, "step": 2290}, {"loss": 1.4672, "grad_norm": 0.7028762102127075, "learning_rate": 0.0002, "epoch": 3.1356509884117245, "step": 2300}, {"loss": 1.3826, "grad_norm": 0.6329697966575623, "learning_rate": 0.0002, "epoch": 3.149284253578732, "step": 2310}, {"loss": 1.442, "grad_norm": 0.6328264474868774, "learning_rate": 0.0002, "epoch": 3.1629175187457395, "step": 2320}, {"loss": 1.3762, "grad_norm": 0.7573632001876831, "learning_rate": 0.0002, "epoch": 3.176550783912747, "step": 2330}, {"loss": 1.3553, "grad_norm": 0.595740795135498, "learning_rate": 0.0002, "epoch": 3.190184049079755, "step": 2340}, {"loss": 1.3953, "grad_norm": 0.7111806869506836, "learning_rate": 0.0002, "epoch": 3.2038173142467623, "step": 2350}, {"loss": 1.3797, "grad_norm": 0.6328730583190918, "learning_rate": 0.0002, "epoch": 3.2174505794137698, "step": 2360}, {"loss": 1.3855, "grad_norm": 0.5860254168510437, "learning_rate": 0.0002, "epoch": 3.2310838445807772, "step": 2370}, {"loss": 1.4267, "grad_norm": 0.7387157082557678, "learning_rate": 0.0002, "epoch": 3.2447171097477847, "step": 2380}, {"loss": 1.4837, "grad_norm": 0.6897673606872559, "learning_rate": 0.0002, "epoch": 3.258350374914792, "step": 2390}, {"loss": 1.4372, "grad_norm": 0.7157699465751648, "learning_rate": 0.0002, "epoch": 3.2719836400817996, "step": 2400}, {"loss": 1.4432, "grad_norm": 0.6422511339187622, "learning_rate": 0.0002, "epoch": 3.285616905248807, "step": 2410}, {"loss": 1.4828, "grad_norm": 1.0481886863708496, "learning_rate": 0.0002, "epoch": 3.2992501704158146, "step": 2420}, {"loss": 1.4473, "grad_norm": 0.7050786018371582, "learning_rate": 0.0002, "epoch": 3.312883435582822, "step": 2430}, {"loss": 1.3465, "grad_norm": 0.6090759038925171, "learning_rate": 0.0002, "epoch": 3.3265167007498295, "step": 2440}, {"loss": 1.4619, "grad_norm": 0.6626465320587158, "learning_rate": 0.0002, "epoch": 3.340149965916837, "step": 2450}, {"loss": 1.4512, "grad_norm": 0.6565486788749695, "learning_rate": 0.0002, "epoch": 3.3537832310838445, "step": 2460}, {"loss": 1.588, "grad_norm": 0.6449528932571411, "learning_rate": 0.0002, "epoch": 3.367416496250852, "step": 2470}, {"loss": 1.4773, "grad_norm": 0.7746227383613586, "learning_rate": 0.0002, "epoch": 3.3810497614178594, "step": 2480}, {"loss": 1.417, "grad_norm": 0.7074846029281616, "learning_rate": 0.0002, "epoch": 3.3946830265848673, "step": 2490}, {"loss": 1.4476, "grad_norm": 0.6547690033912659, "learning_rate": 0.0002, "epoch": 3.4083162917518743, "step": 2500}, {"loss": 1.4074, "grad_norm": 0.784721314907074, "learning_rate": 0.0002, "epoch": 3.4219495569188823, "step": 2510}, {"loss": 1.4326, "grad_norm": 0.7270277738571167, "learning_rate": 0.0002, "epoch": 3.4355828220858897, "step": 2520}, {"loss": 1.4354, "grad_norm": 0.67588871717453, "learning_rate": 0.0002, "epoch": 3.449216087252897, "step": 2530}, {"loss": 1.4074, "grad_norm": 0.6768023371696472, "learning_rate": 0.0002, "epoch": 3.4628493524199047, "step": 2540}, {"loss": 1.4863, "grad_norm": 0.7026481628417969, "learning_rate": 0.0002, "epoch": 3.476482617586912, "step": 2550}, {"loss": 1.468, "grad_norm": 0.646075963973999, "learning_rate": 0.0002, "epoch": 3.4901158827539196, "step": 2560}, {"loss": 1.4058, "grad_norm": 0.6288973689079285, "learning_rate": 0.0002, "epoch": 3.503749147920927, "step": 2570}, {"loss": 1.4613, "grad_norm": 0.6440825462341309, "learning_rate": 0.0002, "epoch": 3.5173824130879345, "step": 2580}, {"loss": 1.3808, "grad_norm": 0.7074111700057983, "learning_rate": 0.0002, "epoch": 3.531015678254942, "step": 2590}, {"loss": 1.4901, "grad_norm": 0.7007562518119812, "learning_rate": 0.0002, "epoch": 3.5446489434219495, "step": 2600}, {"loss": 1.4511, "grad_norm": 0.6045376658439636, "learning_rate": 0.0002, "epoch": 3.558282208588957, "step": 2610}, {"loss": 1.4596, "grad_norm": 0.9149952530860901, "learning_rate": 0.0002, "epoch": 3.5719154737559644, "step": 2620}, {"loss": 1.4355, "grad_norm": 0.6490362882614136, "learning_rate": 0.0002, "epoch": 3.585548738922972, "step": 2630}, {"loss": 1.4107, "grad_norm": 0.6552226543426514, "learning_rate": 0.0002, "epoch": 3.59918200408998, "step": 2640}, {"loss": 1.433, "grad_norm": 0.6541850566864014, "learning_rate": 0.0002, "epoch": 3.612815269256987, "step": 2650}, {"loss": 1.4279, "grad_norm": 0.6500770449638367, "learning_rate": 0.0002, "epoch": 3.6264485344239947, "step": 2660}, {"loss": 1.3929, "grad_norm": 0.6345893740653992, "learning_rate": 0.0002, "epoch": 3.640081799591002, "step": 2670}, {"loss": 1.3634, "grad_norm": 0.6382275223731995, "learning_rate": 0.0002, "epoch": 3.6537150647580097, "step": 2680}, {"loss": 1.4478, "grad_norm": 0.6738566160202026, "learning_rate": 0.0002, "epoch": 3.667348329925017, "step": 2690}, {"loss": 1.4642, "grad_norm": 0.7446315288543701, "learning_rate": 0.0002, "epoch": 3.6809815950920246, "step": 2700}, {"loss": 1.4342, "grad_norm": 0.6717571020126343, "learning_rate": 0.0002, "epoch": 3.694614860259032, "step": 2710}, {"loss": 1.4285, "grad_norm": 0.667259693145752, "learning_rate": 0.0002, "epoch": 3.7082481254260395, "step": 2720}, {"loss": 1.5389, "grad_norm": 0.6808622479438782, "learning_rate": 0.0002, "epoch": 3.721881390593047, "step": 2730}, {"loss": 1.4297, "grad_norm": 0.7254287004470825, "learning_rate": 0.0002, "epoch": 3.7355146557600545, "step": 2740}, {"loss": 1.4176, "grad_norm": 0.6864007711410522, "learning_rate": 0.0002, "epoch": 3.749147920927062, "step": 2750}, {"loss": 1.4811, "grad_norm": 0.7041361331939697, "learning_rate": 0.0002, "epoch": 3.7627811860940694, "step": 2760}, {"loss": 1.4284, "grad_norm": 0.6559903025627136, "learning_rate": 0.0002, "epoch": 3.776414451261077, "step": 2770}, {"loss": 1.4608, "grad_norm": 0.6602269411087036, "learning_rate": 0.0002, "epoch": 3.7900477164280844, "step": 2780}, {"loss": 1.4588, "grad_norm": 0.692611813545227, "learning_rate": 0.0002, "epoch": 3.8036809815950923, "step": 2790}, {"loss": 1.4065, "grad_norm": 0.7051475644111633, "learning_rate": 0.0002, "epoch": 3.8173142467620993, "step": 2800}, {"loss": 1.4083, "grad_norm": 0.6685371398925781, "learning_rate": 0.0002, "epoch": 3.830947511929107, "step": 2810}, {"loss": 1.5227, "grad_norm": 0.6706477403640747, "learning_rate": 0.0002, "epoch": 3.8445807770961147, "step": 2820}, {"loss": 1.4076, "grad_norm": 0.6671637296676636, "learning_rate": 0.0002, "epoch": 3.858214042263122, "step": 2830}, {"loss": 1.4736, "grad_norm": 0.694092333316803, "learning_rate": 0.0002, "epoch": 3.8718473074301296, "step": 2840}, {"loss": 1.4161, "grad_norm": 0.7349600195884705, "learning_rate": 0.0002, "epoch": 3.885480572597137, "step": 2850}, {"loss": 1.4617, "grad_norm": 0.6647971868515015, "learning_rate": 0.0002, "epoch": 3.8991138377641446, "step": 2860}, {"loss": 1.5046, "grad_norm": 0.806656539440155, "learning_rate": 0.0002, "epoch": 3.912747102931152, "step": 2870}, {"loss": 1.428, "grad_norm": 0.6008772850036621, "learning_rate": 0.0002, "epoch": 3.9263803680981595, "step": 2880}, {"loss": 1.4116, "grad_norm": 0.659227728843689, "learning_rate": 0.0002, "epoch": 3.940013633265167, "step": 2890}, {"loss": 1.4136, "grad_norm": 0.6357656717300415, "learning_rate": 0.0002, "epoch": 3.9536468984321744, "step": 2900}, {"loss": 1.4655, "grad_norm": 0.6541687846183777, "learning_rate": 0.0002, "epoch": 3.967280163599182, "step": 2910}, {"loss": 1.4854, "grad_norm": 0.6090909838676453, "learning_rate": 0.0002, "epoch": 3.9809134287661894, "step": 2920}, {"loss": 1.4615, "grad_norm": 0.7198411822319031, "learning_rate": 0.0002, "epoch": 3.994546693933197, "step": 2930}]}
+{"epoch": 4.999318336741649, "step": 3667, "epoch_duration": 1095.6056084632874, "total_accumulated_duration": 5477.18413734436, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7887.97119140625}, "peak_memory_usage": {"GPU_0": 19996.724609375}, "avg_memory_reserved": {"GPU_0": 28746.0}, "peak_memory_reserved": {"GPU_0": 28746.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733", "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": 3.0982, "grad_norm": 0.7714291214942932, "learning_rate": 0.0002, "epoch": 0.013633265167007498, "step": 10}, {"loss": 2.5206, "grad_norm": 0.5473978519439697, "learning_rate": 0.0002, "epoch": 0.027266530334014997, "step": 20}, {"loss": 2.3079, "grad_norm": 0.5452795624732971, "learning_rate": 0.0002, "epoch": 0.0408997955010225, "step": 30}, {"loss": 2.0019, "grad_norm": 0.5098028779029846, "learning_rate": 0.0002, "epoch": 0.054533060668029994, "step": 40}, {"loss": 1.9333, "grad_norm": 0.48062971234321594, "learning_rate": 0.0002, "epoch": 0.0681663258350375, "step": 50}, {"loss": 1.9355, "grad_norm": 0.4505695104598999, "learning_rate": 0.0002, "epoch": 0.081799591002045, "step": 60}, {"loss": 1.9312, "grad_norm": 0.41609591245651245, "learning_rate": 0.0002, "epoch": 0.09543285616905249, "step": 70}, {"loss": 1.8656, "grad_norm": 0.4323892593383789, "learning_rate": 0.0002, "epoch": 0.10906612133605999, "step": 80}, {"loss": 1.9294, "grad_norm": 0.4670293629169464, "learning_rate": 0.0002, "epoch": 0.12269938650306748, "step": 90}, {"loss": 1.7946, "grad_norm": 0.40623316168785095, "learning_rate": 0.0002, "epoch": 0.136332651670075, "step": 100}, {"loss": 1.8565, "grad_norm": 0.3620383143424988, "learning_rate": 0.0002, "epoch": 0.1499659168370825, "step": 110}, {"loss": 1.9238, "grad_norm": 0.332218736410141, "learning_rate": 0.0002, "epoch": 0.16359918200409, "step": 120}, {"loss": 1.93, "grad_norm": 0.4004521667957306, "learning_rate": 0.0002, "epoch": 0.17723244717109748, "step": 130}, {"loss": 1.7549, "grad_norm": 0.3698360323905945, "learning_rate": 0.0002, "epoch": 0.19086571233810498, "step": 140}, {"loss": 1.8771, "grad_norm": 0.3847949504852295, "learning_rate": 0.0002, "epoch": 0.20449897750511248, "step": 150}, {"loss": 1.8316, "grad_norm": 0.36843451857566833, "learning_rate": 0.0002, "epoch": 0.21813224267211997, "step": 160}, {"loss": 1.838, "grad_norm": 0.37301021814346313, "learning_rate": 0.0002, "epoch": 0.23176550783912747, "step": 170}, {"loss": 1.8909, "grad_norm": 0.3718886971473694, "learning_rate": 0.0002, "epoch": 0.24539877300613497, "step": 180}, {"loss": 1.8454, "grad_norm": 0.3088490962982178, "learning_rate": 0.0002, "epoch": 0.25903203817314246, "step": 190}, {"loss": 1.9254, "grad_norm": 0.3611852526664734, "learning_rate": 0.0002, "epoch": 0.27266530334015, "step": 200}, {"loss": 1.7844, "grad_norm": 0.36093324422836304, "learning_rate": 0.0002, "epoch": 0.28629856850715746, "step": 210}, {"loss": 1.719, "grad_norm": 0.3250400722026825, "learning_rate": 0.0002, "epoch": 0.299931833674165, "step": 220}, {"loss": 1.8729, "grad_norm": 0.3566756248474121, "learning_rate": 0.0002, "epoch": 0.31356509884117245, "step": 230}, {"loss": 1.9259, "grad_norm": 0.32872408628463745, "learning_rate": 0.0002, "epoch": 0.32719836400818, "step": 240}, {"loss": 1.9033, "grad_norm": 0.3983881175518036, "learning_rate": 0.0002, "epoch": 0.34083162917518744, "step": 250}, {"loss": 1.8588, "grad_norm": 0.3571510910987854, "learning_rate": 0.0002, "epoch": 0.35446489434219497, "step": 260}, {"loss": 1.8539, "grad_norm": 0.3036131262779236, "learning_rate": 0.0002, "epoch": 0.36809815950920244, "step": 270}, {"loss": 1.8572, "grad_norm": 0.36512863636016846, "learning_rate": 0.0002, "epoch": 0.38173142467620996, "step": 280}, {"loss": 1.8022, "grad_norm": 0.3429736793041229, "learning_rate": 0.0002, "epoch": 0.39536468984321743, "step": 290}, {"loss": 1.8754, "grad_norm": 0.3055964708328247, "learning_rate": 0.0002, "epoch": 0.40899795501022496, "step": 300}, {"loss": 1.8384, "grad_norm": 0.33801034092903137, "learning_rate": 0.0002, "epoch": 0.4226312201772324, "step": 310}, {"loss": 1.7933, "grad_norm": 0.348783016204834, "learning_rate": 0.0002, "epoch": 0.43626448534423995, "step": 320}, {"loss": 1.8451, "grad_norm": 0.3057514727115631, "learning_rate": 0.0002, "epoch": 0.4498977505112474, "step": 330}, {"loss": 1.8766, "grad_norm": 0.3849763572216034, "learning_rate": 0.0002, "epoch": 0.46353101567825494, "step": 340}, {"loss": 1.8073, "grad_norm": 0.30080053210258484, "learning_rate": 0.0002, "epoch": 0.47716428084526247, "step": 350}, {"loss": 1.8548, "grad_norm": 0.3595106303691864, "learning_rate": 0.0002, "epoch": 0.49079754601226994, "step": 360}, {"loss": 1.8232, "grad_norm": 0.31099820137023926, "learning_rate": 0.0002, "epoch": 0.5044308111792775, "step": 370}, {"loss": 1.7029, "grad_norm": 0.3157978355884552, "learning_rate": 0.0002, "epoch": 0.5180640763462849, "step": 380}, {"loss": 1.8265, "grad_norm": 0.27960965037345886, "learning_rate": 0.0002, "epoch": 0.5316973415132924, "step": 390}, {"loss": 1.7414, "grad_norm": 0.3102385103702545, "learning_rate": 0.0002, "epoch": 0.5453306066803, "step": 400}, {"loss": 1.7461, "grad_norm": 0.32828861474990845, "learning_rate": 0.0002, "epoch": 0.5589638718473074, "step": 410}, {"loss": 1.8165, "grad_norm": 0.29560017585754395, "learning_rate": 0.0002, "epoch": 0.5725971370143149, "step": 420}, {"loss": 1.9455, "grad_norm": 0.33316895365715027, "learning_rate": 0.0002, "epoch": 0.5862304021813224, "step": 430}, {"loss": 1.8241, "grad_norm": 0.30420982837677, "learning_rate": 0.0002, "epoch": 0.59986366734833, "step": 440}, {"loss": 1.7565, "grad_norm": 0.32619214057922363, "learning_rate": 0.0002, "epoch": 0.6134969325153374, "step": 450}, {"loss": 1.7945, "grad_norm": 0.3603750765323639, "learning_rate": 0.0002, "epoch": 0.6271301976823449, "step": 460}, {"loss": 1.7773, "grad_norm": 0.30834096670150757, "learning_rate": 0.0002, "epoch": 0.6407634628493524, "step": 470}, {"loss": 1.8058, "grad_norm": 0.28756365180015564, "learning_rate": 0.0002, "epoch": 0.65439672801636, "step": 480}, {"loss": 1.744, "grad_norm": 0.2878406345844269, "learning_rate": 0.0002, "epoch": 0.6680299931833674, "step": 490}, {"loss": 1.8581, "grad_norm": 0.31329697370529175, "learning_rate": 0.0002, "epoch": 0.6816632583503749, "step": 500}, {"loss": 1.7886, "grad_norm": 0.3405822515487671, "learning_rate": 0.0002, "epoch": 0.6952965235173824, "step": 510}, {"loss": 1.778, "grad_norm": 0.305560827255249, "learning_rate": 0.0002, "epoch": 0.7089297886843899, "step": 520}, {"loss": 1.7592, "grad_norm": 0.2973416745662689, "learning_rate": 0.0002, "epoch": 0.7225630538513974, "step": 530}, {"loss": 1.8223, "grad_norm": 0.327303946018219, "learning_rate": 0.0002, "epoch": 0.7361963190184049, "step": 540}, {"loss": 1.8591, "grad_norm": 0.62595534324646, "learning_rate": 0.0002, "epoch": 0.7498295841854125, "step": 550}, {"loss": 1.7466, "grad_norm": 0.3129784166812897, "learning_rate": 0.0002, "epoch": 0.7634628493524199, "step": 560}, {"loss": 1.8035, "grad_norm": 0.32496583461761475, "learning_rate": 0.0002, "epoch": 0.7770961145194274, "step": 570}, {"loss": 1.7787, "grad_norm": 0.3098868131637573, "learning_rate": 0.0002, "epoch": 0.7907293796864349, "step": 580}, {"loss": 1.7196, "grad_norm": 0.30726853013038635, "learning_rate": 0.0002, "epoch": 0.8043626448534424, "step": 590}, {"loss": 1.7898, "grad_norm": 0.2964220643043518, "learning_rate": 0.0002, "epoch": 0.8179959100204499, "step": 600}, {"loss": 1.8114, "grad_norm": 0.32352274656295776, "learning_rate": 0.0002, "epoch": 0.8316291751874574, "step": 610}, {"loss": 1.811, "grad_norm": 0.2938912510871887, "learning_rate": 0.0002, "epoch": 0.8452624403544649, "step": 620}, {"loss": 1.7727, "grad_norm": 0.295559823513031, "learning_rate": 0.0002, "epoch": 0.8588957055214724, "step": 630}, {"loss": 1.9, "grad_norm": 0.34102028608322144, "learning_rate": 0.0002, "epoch": 0.8725289706884799, "step": 640}, {"loss": 1.8006, "grad_norm": 0.29676181077957153, "learning_rate": 0.0002, "epoch": 0.8861622358554874, "step": 650}, {"loss": 1.8099, "grad_norm": 0.3108902871608734, "learning_rate": 0.0002, "epoch": 0.8997955010224948, "step": 660}, {"loss": 1.7955, "grad_norm": 0.2690821588039398, "learning_rate": 0.0002, "epoch": 0.9134287661895024, "step": 670}, {"loss": 1.7881, "grad_norm": 0.32752540707588196, "learning_rate": 0.0002, "epoch": 0.9270620313565099, "step": 680}, {"loss": 1.7661, "grad_norm": 0.8029476404190063, "learning_rate": 0.0002, "epoch": 0.9406952965235174, "step": 690}, {"loss": 1.7733, "grad_norm": 0.30534422397613525, "learning_rate": 0.0002, "epoch": 0.9543285616905249, "step": 700}, {"loss": 1.7614, "grad_norm": 0.2899954319000244, "learning_rate": 0.0002, "epoch": 0.9679618268575324, "step": 710}, {"loss": 1.7845, "grad_norm": 0.28814372420310974, "learning_rate": 0.0002, "epoch": 0.9815950920245399, "step": 720}, {"loss": 1.8865, "grad_norm": 0.3061596751213074, "learning_rate": 0.0002, "epoch": 0.9952283571915473, "step": 730}, {"eval_loss": 1.8171186447143555, "eval_runtime": 53.6047, "eval_samples_per_second": 9.458, "eval_steps_per_second": 1.194, "epoch": 0.9993183367416496, "step": 733}, {"loss": 1.6202, "grad_norm": 0.3140897750854492, "learning_rate": 0.0002, "epoch": 1.008861622358555, "step": 740}, {"loss": 1.8409, "grad_norm": 0.3346109390258789, "learning_rate": 0.0002, "epoch": 1.0224948875255624, "step": 750}, {"loss": 1.6777, "grad_norm": 0.3582976758480072, "learning_rate": 0.0002, "epoch": 1.0361281526925699, "step": 760}, {"loss": 1.7306, "grad_norm": 0.30408260226249695, "learning_rate": 0.0002, "epoch": 1.0497614178595773, "step": 770}, {"loss": 1.6967, "grad_norm": 0.323585569858551, "learning_rate": 0.0002, "epoch": 1.0633946830265848, "step": 780}, {"loss": 1.768, "grad_norm": 0.3474137783050537, "learning_rate": 0.0002, "epoch": 1.0770279481935923, "step": 790}, {"loss": 1.6895, "grad_norm": 0.35721147060394287, "learning_rate": 0.0002, "epoch": 1.0906612133606, "step": 800}, {"loss": 1.718, "grad_norm": 0.35366931557655334, "learning_rate": 0.0002, "epoch": 1.1042944785276074, "step": 810}, {"loss": 1.6797, "grad_norm": 0.3250770568847656, "learning_rate": 0.0002, "epoch": 1.117927743694615, "step": 820}, {"loss": 1.6383, "grad_norm": 0.3293766379356384, "learning_rate": 0.0002, "epoch": 1.1315610088616224, "step": 830}, {"loss": 1.7353, "grad_norm": 0.3380851745605469, "learning_rate": 0.0002, "epoch": 1.1451942740286298, "step": 840}, {"loss": 1.8236, "grad_norm": 0.32584455609321594, "learning_rate": 0.0002, "epoch": 1.1588275391956373, "step": 850}, {"loss": 1.6681, "grad_norm": 0.45700767636299133, "learning_rate": 0.0002, "epoch": 1.1724608043626448, "step": 860}, {"loss": 1.7494, "grad_norm": 0.30944544076919556, "learning_rate": 0.0002, "epoch": 1.1860940695296525, "step": 870}, {"loss": 1.7426, "grad_norm": 0.3268151581287384, "learning_rate": 0.0002, "epoch": 1.19972733469666, "step": 880}, {"loss": 1.7413, "grad_norm": 0.39972540736198425, "learning_rate": 0.0002, "epoch": 1.2133605998636674, "step": 890}, {"loss": 1.7481, "grad_norm": 0.7890929579734802, "learning_rate": 0.0002, "epoch": 1.2269938650306749, "step": 900}, {"loss": 1.7608, "grad_norm": 0.3439182639122009, "learning_rate": 0.0002, "epoch": 1.2406271301976823, "step": 910}, {"loss": 1.7617, "grad_norm": 0.3986225128173828, "learning_rate": 0.0002, "epoch": 1.2542603953646898, "step": 920}, {"loss": 1.6843, "grad_norm": 0.3514605164527893, "learning_rate": 0.0002, "epoch": 1.2678936605316973, "step": 930}, {"loss": 1.6987, "grad_norm": 0.3682589530944824, "learning_rate": 0.0002, "epoch": 1.2815269256987047, "step": 940}, {"loss": 1.6988, "grad_norm": 0.3618335723876953, "learning_rate": 0.0002, "epoch": 1.2951601908657122, "step": 950}, {"loss": 1.7436, "grad_norm": 0.345700740814209, "learning_rate": 0.0002, "epoch": 1.30879345603272, "step": 960}, {"loss": 1.7336, "grad_norm": 0.3514927923679352, "learning_rate": 0.0002, "epoch": 1.3224267211997274, "step": 970}, {"loss": 1.7704, "grad_norm": 0.365647554397583, "learning_rate": 0.0002, "epoch": 1.3360599863667348, "step": 980}, {"loss": 1.7104, "grad_norm": 0.3407285809516907, "learning_rate": 0.0002, "epoch": 1.3496932515337423, "step": 990}, {"loss": 1.7132, "grad_norm": 0.3785437345504761, "learning_rate": 0.0002, "epoch": 1.3633265167007498, "step": 1000}, {"loss": 1.766, "grad_norm": 0.34746724367141724, "learning_rate": 0.0002, "epoch": 1.3769597818677572, "step": 1010}, {"loss": 1.7252, "grad_norm": 0.362444132566452, "learning_rate": 0.0002, "epoch": 1.390593047034765, "step": 1020}, {"loss": 1.7132, "grad_norm": 0.4424704611301422, "learning_rate": 0.0002, "epoch": 1.4042263122017724, "step": 1030}, {"loss": 1.726, "grad_norm": 0.38722458481788635, "learning_rate": 0.0002, "epoch": 1.4178595773687799, "step": 1040}, {"loss": 1.7955, "grad_norm": 0.36089080572128296, "learning_rate": 0.0002, "epoch": 1.4314928425357873, "step": 1050}, {"loss": 1.6924, "grad_norm": 0.33817124366760254, "learning_rate": 0.0002, "epoch": 1.4451261077027948, "step": 1060}, {"loss": 1.7165, "grad_norm": 0.34334081411361694, "learning_rate": 0.0002, "epoch": 1.4587593728698023, "step": 1070}, {"loss": 1.6999, "grad_norm": 0.3776826858520508, "learning_rate": 0.0002, "epoch": 1.4723926380368098, "step": 1080}, {"loss": 1.7605, "grad_norm": 0.4169026017189026, "learning_rate": 0.0002, "epoch": 1.4860259032038172, "step": 1090}, {"loss": 1.7502, "grad_norm": 0.34898945689201355, "learning_rate": 0.0002, "epoch": 1.4996591683708247, "step": 1100}, {"loss": 1.635, "grad_norm": 0.34223780035972595, "learning_rate": 0.0002, "epoch": 1.5132924335378322, "step": 1110}, {"loss": 1.7248, "grad_norm": 0.3686901032924652, "learning_rate": 0.0002, "epoch": 1.5269256987048399, "step": 1120}, {"loss": 1.7525, "grad_norm": 0.35054415464401245, "learning_rate": 0.0002, "epoch": 1.5405589638718473, "step": 1130}, {"loss": 1.7776, "grad_norm": 0.39496365189552307, "learning_rate": 0.0002, "epoch": 1.5541922290388548, "step": 1140}, {"loss": 1.6574, "grad_norm": 0.35451626777648926, "learning_rate": 0.0002, "epoch": 1.5678254942058623, "step": 1150}, {"loss": 1.7257, "grad_norm": 0.3848083019256592, "learning_rate": 0.0002, "epoch": 1.58145875937287, "step": 1160}, {"loss": 1.7272, "grad_norm": 0.3760537803173065, "learning_rate": 0.0002, "epoch": 1.5950920245398774, "step": 1170}, {"loss": 1.7441, "grad_norm": 0.38981738686561584, "learning_rate": 0.0002, "epoch": 1.6087252897068849, "step": 1180}, {"loss": 1.6951, "grad_norm": 0.36830949783325195, "learning_rate": 0.0002, "epoch": 1.6223585548738924, "step": 1190}, {"loss": 1.6925, "grad_norm": 0.3405892848968506, "learning_rate": 0.0002, "epoch": 1.6359918200408998, "step": 1200}, {"loss": 1.7473, "grad_norm": 0.39027872681617737, "learning_rate": 0.0002, "epoch": 1.6496250852079073, "step": 1210}, {"loss": 1.6792, "grad_norm": 0.3342694044113159, "learning_rate": 0.0002, "epoch": 1.6632583503749148, "step": 1220}, {"loss": 1.7196, "grad_norm": 0.3600076735019684, "learning_rate": 0.0002, "epoch": 1.6768916155419222, "step": 1230}, {"loss": 1.7021, "grad_norm": 0.3625542223453522, "learning_rate": 0.0002, "epoch": 1.6905248807089297, "step": 1240}, {"loss": 1.6772, "grad_norm": 0.32170894742012024, "learning_rate": 0.0002, "epoch": 1.7041581458759372, "step": 1250}, {"loss": 1.7152, "grad_norm": 0.3544139862060547, "learning_rate": 0.0002, "epoch": 1.7177914110429446, "step": 1260}, {"loss": 1.7138, "grad_norm": 0.35113027691841125, "learning_rate": 0.0002, "epoch": 1.7314246762099523, "step": 1270}, {"loss": 1.7095, "grad_norm": 0.3499974310398102, "learning_rate": 0.0002, "epoch": 1.7450579413769598, "step": 1280}, {"loss": 1.7749, "grad_norm": 0.3285157382488251, "learning_rate": 0.0002, "epoch": 1.7586912065439673, "step": 1290}, {"loss": 1.6767, "grad_norm": 0.3701961636543274, "learning_rate": 0.0002, "epoch": 1.7723244717109747, "step": 1300}, {"loss": 1.6282, "grad_norm": 0.3301318287849426, "learning_rate": 0.0002, "epoch": 1.7859577368779824, "step": 1310}, {"loss": 1.7097, "grad_norm": 0.37801554799079895, "learning_rate": 0.0002, "epoch": 1.79959100204499, "step": 1320}, {"loss": 1.7437, "grad_norm": 0.3726748526096344, "learning_rate": 0.0002, "epoch": 1.8132242672119974, "step": 1330}, {"loss": 1.7959, "grad_norm": 0.4059790074825287, "learning_rate": 0.0002, "epoch": 1.8268575323790048, "step": 1340}, {"loss": 1.7739, "grad_norm": 0.35712096095085144, "learning_rate": 0.0002, "epoch": 1.8404907975460123, "step": 1350}, {"loss": 1.6375, "grad_norm": 0.35995328426361084, "learning_rate": 0.0002, "epoch": 1.8541240627130198, "step": 1360}, {"loss": 1.7332, "grad_norm": 0.3679947257041931, "learning_rate": 0.0002, "epoch": 1.8677573278800272, "step": 1370}, {"loss": 1.7587, "grad_norm": 0.39645957946777344, "learning_rate": 0.0002, "epoch": 1.8813905930470347, "step": 1380}, {"loss": 1.6985, "grad_norm": 0.35288700461387634, "learning_rate": 0.0002, "epoch": 1.8950238582140422, "step": 1390}, {"loss": 1.6582, "grad_norm": 0.32579198479652405, "learning_rate": 0.0002, "epoch": 1.9086571233810496, "step": 1400}, {"loss": 1.6948, "grad_norm": 0.3856561779975891, "learning_rate": 0.0002, "epoch": 1.9222903885480571, "step": 1410}, {"loss": 1.668, "grad_norm": 0.39019331336021423, "learning_rate": 0.0002, "epoch": 1.9359236537150648, "step": 1420}, {"loss": 1.7774, "grad_norm": 0.38006502389907837, "learning_rate": 0.0002, "epoch": 1.9495569188820723, "step": 1430}, {"loss": 1.8323, "grad_norm": 0.38100454211235046, "learning_rate": 0.0002, "epoch": 1.9631901840490797, "step": 1440}, {"loss": 1.7298, "grad_norm": 0.3405798673629761, "learning_rate": 0.0002, "epoch": 1.9768234492160872, "step": 1450}, {"loss": 1.7045, "grad_norm": 0.36582913994789124, "learning_rate": 0.0002, "epoch": 1.990456714383095, "step": 1460}, {"eval_loss": 1.8178424835205078, "eval_runtime": 53.6524, "eval_samples_per_second": 9.45, "eval_steps_per_second": 1.193, "epoch": 2.0, "step": 1467}, {"loss": 1.6363, "grad_norm": 0.3626647889614105, "learning_rate": 0.0002, "epoch": 2.0040899795501024, "step": 1470}, {"loss": 1.5354, "grad_norm": 0.40171775221824646, "learning_rate": 0.0002, "epoch": 2.01772324471711, "step": 1480}, {"loss": 1.5566, "grad_norm": 0.5805319547653198, "learning_rate": 0.0002, "epoch": 2.0313565098841173, "step": 1490}, {"loss": 1.546, "grad_norm": 0.41954153776168823, "learning_rate": 0.0002, "epoch": 2.044989775051125, "step": 1500}, {"loss": 1.6158, "grad_norm": 0.47190725803375244, "learning_rate": 0.0002, "epoch": 2.0586230402181322, "step": 1510}, {"loss": 1.5841, "grad_norm": 0.4388456344604492, "learning_rate": 0.0002, "epoch": 2.0722563053851397, "step": 1520}, {"loss": 1.5835, "grad_norm": 2.2171926498413086, "learning_rate": 0.0002, "epoch": 2.085889570552147, "step": 1530}, {"loss": 1.6137, "grad_norm": 0.4314221143722534, "learning_rate": 0.0002, "epoch": 2.0995228357191547, "step": 1540}, {"loss": 1.5511, "grad_norm": 0.4154265522956848, "learning_rate": 0.0002, "epoch": 2.113156100886162, "step": 1550}, {"loss": 1.6323, "grad_norm": 0.5025539994239807, "learning_rate": 0.0002, "epoch": 2.1267893660531696, "step": 1560}, {"loss": 1.5903, "grad_norm": 0.5410493016242981, "learning_rate": 0.0002, "epoch": 2.140422631220177, "step": 1570}, {"loss": 1.507, "grad_norm": 0.4478487968444824, "learning_rate": 0.0002, "epoch": 2.1540558963871845, "step": 1580}, {"loss": 1.5536, "grad_norm": 0.4703652560710907, "learning_rate": 0.0002, "epoch": 2.1676891615541924, "step": 1590}, {"loss": 1.5991, "grad_norm": 0.4555390179157257, "learning_rate": 0.0002, "epoch": 2.1813224267212, "step": 1600}, {"loss": 1.6117, "grad_norm": 0.4877263903617859, "learning_rate": 0.0002, "epoch": 2.1949556918882074, "step": 1610}, {"loss": 1.5928, "grad_norm": 0.48708245158195496, "learning_rate": 0.0002, "epoch": 2.208588957055215, "step": 1620}, {"loss": 1.6106, "grad_norm": 0.47523951530456543, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 1630}, {"loss": 1.6013, "grad_norm": 0.4889199733734131, "learning_rate": 0.0002, "epoch": 2.23585548738923, "step": 1640}, {"loss": 1.6633, "grad_norm": 0.4585252106189728, "learning_rate": 0.0002, "epoch": 2.2494887525562373, "step": 1650}, {"loss": 1.6075, "grad_norm": 0.4764868915081024, "learning_rate": 0.0002, "epoch": 2.2631220177232447, "step": 1660}, {"loss": 1.6427, "grad_norm": 0.5028976202011108, "learning_rate": 0.0002, "epoch": 2.276755282890252, "step": 1670}, {"loss": 1.6258, "grad_norm": 0.46131211519241333, "learning_rate": 0.0002, "epoch": 2.2903885480572597, "step": 1680}, {"loss": 1.654, "grad_norm": 0.5422874689102173, "learning_rate": 0.0002, "epoch": 2.304021813224267, "step": 1690}, {"loss": 1.6331, "grad_norm": 0.47615355253219604, "learning_rate": 0.0002, "epoch": 2.3176550783912746, "step": 1700}, {"loss": 1.642, "grad_norm": 0.48005548119544983, "learning_rate": 0.0002, "epoch": 2.331288343558282, "step": 1710}, {"loss": 1.581, "grad_norm": 0.4387182295322418, "learning_rate": 0.0002, "epoch": 2.3449216087252895, "step": 1720}, {"loss": 1.5612, "grad_norm": 0.4487272799015045, "learning_rate": 0.0002, "epoch": 2.358554873892297, "step": 1730}, {"loss": 1.5089, "grad_norm": 0.5046455264091492, "learning_rate": 0.0002, "epoch": 2.372188139059305, "step": 1740}, {"loss": 1.5769, "grad_norm": 0.4653521180152893, "learning_rate": 0.0002, "epoch": 2.3858214042263124, "step": 1750}, {"loss": 1.6201, "grad_norm": 0.4737723469734192, "learning_rate": 0.0002, "epoch": 2.39945466939332, "step": 1760}, {"loss": 1.5933, "grad_norm": 0.4501931071281433, "learning_rate": 0.0002, "epoch": 2.4130879345603273, "step": 1770}, {"loss": 1.6321, "grad_norm": 0.4772880971431732, "learning_rate": 0.0002, "epoch": 2.426721199727335, "step": 1780}, {"loss": 1.5454, "grad_norm": 0.4544616937637329, "learning_rate": 0.0002, "epoch": 2.4403544648943423, "step": 1790}, {"loss": 1.5501, "grad_norm": 0.488313227891922, "learning_rate": 0.0002, "epoch": 2.4539877300613497, "step": 1800}, {"loss": 1.5791, "grad_norm": 0.5057830214500427, "learning_rate": 0.0002, "epoch": 2.467620995228357, "step": 1810}, {"loss": 1.5645, "grad_norm": 0.5049484968185425, "learning_rate": 0.0002, "epoch": 2.4812542603953647, "step": 1820}, {"loss": 1.6268, "grad_norm": 0.44966644048690796, "learning_rate": 0.0002, "epoch": 2.494887525562372, "step": 1830}, {"loss": 1.5941, "grad_norm": 0.5072630643844604, "learning_rate": 0.0002, "epoch": 2.5085207907293796, "step": 1840}, {"loss": 1.5251, "grad_norm": 0.43989792466163635, "learning_rate": 0.0002, "epoch": 2.522154055896387, "step": 1850}, {"loss": 1.563, "grad_norm": 1.3504403829574585, "learning_rate": 0.0002, "epoch": 2.5357873210633946, "step": 1860}, {"loss": 1.5681, "grad_norm": 0.46545976400375366, "learning_rate": 0.0002, "epoch": 2.549420586230402, "step": 1870}, {"loss": 1.6368, "grad_norm": 0.4678342044353485, "learning_rate": 0.0002, "epoch": 2.5630538513974095, "step": 1880}, {"loss": 1.5814, "grad_norm": 0.529755711555481, "learning_rate": 0.0002, "epoch": 2.5766871165644174, "step": 1890}, {"loss": 1.5861, "grad_norm": 0.5000199675559998, "learning_rate": 0.0002, "epoch": 2.5903203817314244, "step": 1900}, {"loss": 1.6346, "grad_norm": 0.5649300217628479, "learning_rate": 0.0002, "epoch": 2.6039536468984323, "step": 1910}, {"loss": 1.6317, "grad_norm": 0.7920585870742798, "learning_rate": 0.0002, "epoch": 2.61758691206544, "step": 1920}, {"loss": 1.643, "grad_norm": 0.4960342049598694, "learning_rate": 0.0002, "epoch": 2.6312201772324473, "step": 1930}, {"loss": 1.6099, "grad_norm": 0.5324710011482239, "learning_rate": 0.0002, "epoch": 2.6448534423994547, "step": 1940}, {"loss": 1.5874, "grad_norm": 0.606343150138855, "learning_rate": 0.0002, "epoch": 2.658486707566462, "step": 1950}, {"loss": 1.5728, "grad_norm": 0.53038489818573, "learning_rate": 0.0002, "epoch": 2.6721199727334697, "step": 1960}, {"loss": 1.5583, "grad_norm": 0.4579465091228485, "learning_rate": 0.0002, "epoch": 2.685753237900477, "step": 1970}, {"loss": 1.6093, "grad_norm": 0.4541707932949066, "learning_rate": 0.0002, "epoch": 2.6993865030674846, "step": 1980}, {"loss": 1.5316, "grad_norm": 0.5009395480155945, "learning_rate": 0.0002, "epoch": 2.713019768234492, "step": 1990}, {"loss": 1.6724, "grad_norm": 0.4723006784915924, "learning_rate": 0.0002, "epoch": 2.7266530334014996, "step": 2000}, {"loss": 1.638, "grad_norm": 0.5086126923561096, "learning_rate": 0.0002, "epoch": 2.740286298568507, "step": 2010}, {"loss": 1.6223, "grad_norm": 0.47242608666419983, "learning_rate": 0.0002, "epoch": 2.7539195637355145, "step": 2020}, {"loss": 1.6242, "grad_norm": 0.44922566413879395, "learning_rate": 0.0002, "epoch": 2.767552828902522, "step": 2030}, {"loss": 1.6837, "grad_norm": 0.420259565114975, "learning_rate": 0.0002, "epoch": 2.78118609406953, "step": 2040}, {"loss": 1.5612, "grad_norm": 0.4762881100177765, "learning_rate": 0.0002, "epoch": 2.794819359236537, "step": 2050}, {"loss": 1.5506, "grad_norm": 0.5228786468505859, "learning_rate": 0.0002, "epoch": 2.808452624403545, "step": 2060}, {"loss": 1.6347, "grad_norm": 0.4796035587787628, "learning_rate": 0.0002, "epoch": 2.8220858895705523, "step": 2070}, {"loss": 1.6843, "grad_norm": 0.5034735202789307, "learning_rate": 0.0002, "epoch": 2.8357191547375598, "step": 2080}, {"loss": 1.6455, "grad_norm": 0.48005399107933044, "learning_rate": 0.0002, "epoch": 2.8493524199045672, "step": 2090}, {"loss": 1.6287, "grad_norm": 0.578820526599884, "learning_rate": 0.0002, "epoch": 2.8629856850715747, "step": 2100}, {"loss": 1.6021, "grad_norm": 0.48982638120651245, "learning_rate": 0.0002, "epoch": 2.876618950238582, "step": 2110}, {"loss": 1.5769, "grad_norm": 0.5157325863838196, "learning_rate": 0.0002, "epoch": 2.8902522154055896, "step": 2120}, {"loss": 1.6089, "grad_norm": 0.49149683117866516, "learning_rate": 0.0002, "epoch": 2.903885480572597, "step": 2130}, {"loss": 1.5881, "grad_norm": 0.48584499955177307, "learning_rate": 0.0002, "epoch": 2.9175187457396046, "step": 2140}, {"loss": 1.5833, "grad_norm": 0.5199017524719238, "learning_rate": 0.0002, "epoch": 2.931152010906612, "step": 2150}, {"loss": 1.7344, "grad_norm": 0.5788236856460571, "learning_rate": 0.0002, "epoch": 2.9447852760736195, "step": 2160}, {"loss": 1.6103, "grad_norm": 0.48664185404777527, "learning_rate": 0.0002, "epoch": 2.958418541240627, "step": 2170}, {"loss": 1.5765, "grad_norm": 0.5026682615280151, "learning_rate": 0.0002, "epoch": 2.9720518064076344, "step": 2180}, {"loss": 1.6626, "grad_norm": 0.49317044019699097, "learning_rate": 0.0002, "epoch": 2.9856850715746424, "step": 2190}, {"loss": 1.5871, "grad_norm": 0.5729128122329712, "learning_rate": 0.0002, "epoch": 2.9993183367416494, "step": 2200}, {"eval_loss": 1.8527295589447021, "eval_runtime": 53.6403, "eval_samples_per_second": 9.452, "eval_steps_per_second": 1.193, "epoch": 2.9993183367416494, "step": 2200}, {"loss": 1.4719, "grad_norm": 0.5530241131782532, "learning_rate": 0.0002, "epoch": 3.0129516019086573, "step": 2210}, {"loss": 1.4088, "grad_norm": 0.6642216444015503, "learning_rate": 0.0002, "epoch": 3.0265848670756648, "step": 2220}, {"loss": 1.4382, "grad_norm": 0.61470627784729, "learning_rate": 0.0002, "epoch": 3.0402181322426722, "step": 2230}, {"loss": 1.4634, "grad_norm": 0.8559566140174866, "learning_rate": 0.0002, "epoch": 3.0538513974096797, "step": 2240}, {"loss": 1.3854, "grad_norm": 0.7015801668167114, "learning_rate": 0.0002, "epoch": 3.067484662576687, "step": 2250}, {"loss": 1.4981, "grad_norm": 0.7226442694664001, "learning_rate": 0.0002, "epoch": 3.0811179277436946, "step": 2260}, {"loss": 1.4143, "grad_norm": 0.7560588717460632, "learning_rate": 0.0002, "epoch": 3.094751192910702, "step": 2270}, {"loss": 1.4395, "grad_norm": 0.6216568946838379, "learning_rate": 0.0002, "epoch": 3.1083844580777096, "step": 2280}, {"loss": 1.3842, "grad_norm": 0.6768500804901123, "learning_rate": 0.0002, "epoch": 3.122017723244717, "step": 2290}, {"loss": 1.4672, "grad_norm": 0.7028762102127075, "learning_rate": 0.0002, "epoch": 3.1356509884117245, "step": 2300}, {"loss": 1.3826, "grad_norm": 0.6329697966575623, "learning_rate": 0.0002, "epoch": 3.149284253578732, "step": 2310}, {"loss": 1.442, "grad_norm": 0.6328264474868774, "learning_rate": 0.0002, "epoch": 3.1629175187457395, "step": 2320}, {"loss": 1.3762, "grad_norm": 0.7573632001876831, "learning_rate": 0.0002, "epoch": 3.176550783912747, "step": 2330}, {"loss": 1.3553, "grad_norm": 0.595740795135498, "learning_rate": 0.0002, "epoch": 3.190184049079755, "step": 2340}, {"loss": 1.3953, "grad_norm": 0.7111806869506836, "learning_rate": 0.0002, "epoch": 3.2038173142467623, "step": 2350}, {"loss": 1.3797, "grad_norm": 0.6328730583190918, "learning_rate": 0.0002, "epoch": 3.2174505794137698, "step": 2360}, {"loss": 1.3855, "grad_norm": 0.5860254168510437, "learning_rate": 0.0002, "epoch": 3.2310838445807772, "step": 2370}, {"loss": 1.4267, "grad_norm": 0.7387157082557678, "learning_rate": 0.0002, "epoch": 3.2447171097477847, "step": 2380}, {"loss": 1.4837, "grad_norm": 0.6897673606872559, "learning_rate": 0.0002, "epoch": 3.258350374914792, "step": 2390}, {"loss": 1.4372, "grad_norm": 0.7157699465751648, "learning_rate": 0.0002, "epoch": 3.2719836400817996, "step": 2400}, {"loss": 1.4432, "grad_norm": 0.6422511339187622, "learning_rate": 0.0002, "epoch": 3.285616905248807, "step": 2410}, {"loss": 1.4828, "grad_norm": 1.0481886863708496, "learning_rate": 0.0002, "epoch": 3.2992501704158146, "step": 2420}, {"loss": 1.4473, "grad_norm": 0.7050786018371582, "learning_rate": 0.0002, "epoch": 3.312883435582822, "step": 2430}, {"loss": 1.3465, "grad_norm": 0.6090759038925171, "learning_rate": 0.0002, "epoch": 3.3265167007498295, "step": 2440}, {"loss": 1.4619, "grad_norm": 0.6626465320587158, "learning_rate": 0.0002, "epoch": 3.340149965916837, "step": 2450}, {"loss": 1.4512, "grad_norm": 0.6565486788749695, "learning_rate": 0.0002, "epoch": 3.3537832310838445, "step": 2460}, {"loss": 1.588, "grad_norm": 0.6449528932571411, "learning_rate": 0.0002, "epoch": 3.367416496250852, "step": 2470}, {"loss": 1.4773, "grad_norm": 0.7746227383613586, "learning_rate": 0.0002, "epoch": 3.3810497614178594, "step": 2480}, {"loss": 1.417, "grad_norm": 0.7074846029281616, "learning_rate": 0.0002, "epoch": 3.3946830265848673, "step": 2490}, {"loss": 1.4476, "grad_norm": 0.6547690033912659, "learning_rate": 0.0002, "epoch": 3.4083162917518743, "step": 2500}, {"loss": 1.4074, "grad_norm": 0.784721314907074, "learning_rate": 0.0002, "epoch": 3.4219495569188823, "step": 2510}, {"loss": 1.4326, "grad_norm": 0.7270277738571167, "learning_rate": 0.0002, "epoch": 3.4355828220858897, "step": 2520}, {"loss": 1.4354, "grad_norm": 0.67588871717453, "learning_rate": 0.0002, "epoch": 3.449216087252897, "step": 2530}, {"loss": 1.4074, "grad_norm": 0.6768023371696472, "learning_rate": 0.0002, "epoch": 3.4628493524199047, "step": 2540}, {"loss": 1.4863, "grad_norm": 0.7026481628417969, "learning_rate": 0.0002, "epoch": 3.476482617586912, "step": 2550}, {"loss": 1.468, "grad_norm": 0.646075963973999, "learning_rate": 0.0002, "epoch": 3.4901158827539196, "step": 2560}, {"loss": 1.4058, "grad_norm": 0.6288973689079285, "learning_rate": 0.0002, "epoch": 3.503749147920927, "step": 2570}, {"loss": 1.4613, "grad_norm": 0.6440825462341309, "learning_rate": 0.0002, "epoch": 3.5173824130879345, "step": 2580}, {"loss": 1.3808, "grad_norm": 0.7074111700057983, "learning_rate": 0.0002, "epoch": 3.531015678254942, "step": 2590}, {"loss": 1.4901, "grad_norm": 0.7007562518119812, "learning_rate": 0.0002, "epoch": 3.5446489434219495, "step": 2600}, {"loss": 1.4511, "grad_norm": 0.6045376658439636, "learning_rate": 0.0002, "epoch": 3.558282208588957, "step": 2610}, {"loss": 1.4596, "grad_norm": 0.9149952530860901, "learning_rate": 0.0002, "epoch": 3.5719154737559644, "step": 2620}, {"loss": 1.4355, "grad_norm": 0.6490362882614136, "learning_rate": 0.0002, "epoch": 3.585548738922972, "step": 2630}, {"loss": 1.4107, "grad_norm": 0.6552226543426514, "learning_rate": 0.0002, "epoch": 3.59918200408998, "step": 2640}, {"loss": 1.433, "grad_norm": 0.6541850566864014, "learning_rate": 0.0002, "epoch": 3.612815269256987, "step": 2650}, {"loss": 1.4279, "grad_norm": 0.6500770449638367, "learning_rate": 0.0002, "epoch": 3.6264485344239947, "step": 2660}, {"loss": 1.3929, "grad_norm": 0.6345893740653992, "learning_rate": 0.0002, "epoch": 3.640081799591002, "step": 2670}, {"loss": 1.3634, "grad_norm": 0.6382275223731995, "learning_rate": 0.0002, "epoch": 3.6537150647580097, "step": 2680}, {"loss": 1.4478, "grad_norm": 0.6738566160202026, "learning_rate": 0.0002, "epoch": 3.667348329925017, "step": 2690}, {"loss": 1.4642, "grad_norm": 0.7446315288543701, "learning_rate": 0.0002, "epoch": 3.6809815950920246, "step": 2700}, {"loss": 1.4342, "grad_norm": 0.6717571020126343, "learning_rate": 0.0002, "epoch": 3.694614860259032, "step": 2710}, {"loss": 1.4285, "grad_norm": 0.667259693145752, "learning_rate": 0.0002, "epoch": 3.7082481254260395, "step": 2720}, {"loss": 1.5389, "grad_norm": 0.6808622479438782, "learning_rate": 0.0002, "epoch": 3.721881390593047, "step": 2730}, {"loss": 1.4297, "grad_norm": 0.7254287004470825, "learning_rate": 0.0002, "epoch": 3.7355146557600545, "step": 2740}, {"loss": 1.4176, "grad_norm": 0.6864007711410522, "learning_rate": 0.0002, "epoch": 3.749147920927062, "step": 2750}, {"loss": 1.4811, "grad_norm": 0.7041361331939697, "learning_rate": 0.0002, "epoch": 3.7627811860940694, "step": 2760}, {"loss": 1.4284, "grad_norm": 0.6559903025627136, "learning_rate": 0.0002, "epoch": 3.776414451261077, "step": 2770}, {"loss": 1.4608, "grad_norm": 0.6602269411087036, "learning_rate": 0.0002, "epoch": 3.7900477164280844, "step": 2780}, {"loss": 1.4588, "grad_norm": 0.692611813545227, "learning_rate": 0.0002, "epoch": 3.8036809815950923, "step": 2790}, {"loss": 1.4065, "grad_norm": 0.7051475644111633, "learning_rate": 0.0002, "epoch": 3.8173142467620993, "step": 2800}, {"loss": 1.4083, "grad_norm": 0.6685371398925781, "learning_rate": 0.0002, "epoch": 3.830947511929107, "step": 2810}, {"loss": 1.5227, "grad_norm": 0.6706477403640747, "learning_rate": 0.0002, "epoch": 3.8445807770961147, "step": 2820}, {"loss": 1.4076, "grad_norm": 0.6671637296676636, "learning_rate": 0.0002, "epoch": 3.858214042263122, "step": 2830}, {"loss": 1.4736, "grad_norm": 0.694092333316803, "learning_rate": 0.0002, "epoch": 3.8718473074301296, "step": 2840}, {"loss": 1.4161, "grad_norm": 0.7349600195884705, "learning_rate": 0.0002, "epoch": 3.885480572597137, "step": 2850}, {"loss": 1.4617, "grad_norm": 0.6647971868515015, "learning_rate": 0.0002, "epoch": 3.8991138377641446, "step": 2860}, {"loss": 1.5046, "grad_norm": 0.806656539440155, "learning_rate": 0.0002, "epoch": 3.912747102931152, "step": 2870}, {"loss": 1.428, "grad_norm": 0.6008772850036621, "learning_rate": 0.0002, "epoch": 3.9263803680981595, "step": 2880}, {"loss": 1.4116, "grad_norm": 0.659227728843689, "learning_rate": 0.0002, "epoch": 3.940013633265167, "step": 2890}, {"loss": 1.4136, "grad_norm": 0.6357656717300415, "learning_rate": 0.0002, "epoch": 3.9536468984321744, "step": 2900}, {"loss": 1.4655, "grad_norm": 0.6541687846183777, "learning_rate": 0.0002, "epoch": 3.967280163599182, "step": 2910}, {"loss": 1.4854, "grad_norm": 0.6090909838676453, "learning_rate": 0.0002, "epoch": 3.9809134287661894, "step": 2920}, {"loss": 1.4615, "grad_norm": 0.7198411822319031, "learning_rate": 0.0002, "epoch": 3.994546693933197, "step": 2930}, {"eval_loss": 1.9278366565704346, "eval_runtime": 53.6567, "eval_samples_per_second": 9.449, "eval_steps_per_second": 1.193, "epoch": 4.0, "step": 2934}, {"loss": 1.3159, "grad_norm": 0.6498575210571289, "learning_rate": 0.0002, "epoch": 4.008179959100205, "step": 2940}, {"loss": 1.2075, "grad_norm": 0.865602433681488, "learning_rate": 0.0002, "epoch": 4.021813224267212, "step": 2950}, {"loss": 1.1744, "grad_norm": 0.8514999151229858, "learning_rate": 0.0002, "epoch": 4.03544648943422, "step": 2960}, {"loss": 1.1553, "grad_norm": 1.0677322149276733, "learning_rate": 0.0002, "epoch": 4.049079754601227, "step": 2970}, {"loss": 1.1962, "grad_norm": 1.0126488208770752, "learning_rate": 0.0002, "epoch": 4.062713019768235, "step": 2980}, {"loss": 1.1631, "grad_norm": 1.0008870363235474, "learning_rate": 0.0002, "epoch": 4.076346284935242, "step": 2990}, {"loss": 1.2154, "grad_norm": 0.7942054271697998, "learning_rate": 0.0002, "epoch": 4.08997955010225, "step": 3000}, {"loss": 1.214, "grad_norm": 1.0482100248336792, "learning_rate": 0.0002, "epoch": 4.103612815269257, "step": 3010}, {"loss": 1.1999, "grad_norm": 1.0516992807388306, "learning_rate": 0.0002, "epoch": 4.1172460804362645, "step": 3020}, {"loss": 1.2108, "grad_norm": 0.8144322037696838, "learning_rate": 0.0002, "epoch": 4.130879345603272, "step": 3030}, {"loss": 1.1782, "grad_norm": 0.952297568321228, "learning_rate": 0.0002, "epoch": 4.144512610770279, "step": 3040}, {"loss": 1.2814, "grad_norm": 1.007645606994629, "learning_rate": 0.0002, "epoch": 4.158145875937287, "step": 3050}, {"loss": 1.1731, "grad_norm": 1.0480353832244873, "learning_rate": 0.0002, "epoch": 4.171779141104294, "step": 3060}, {"loss": 1.196, "grad_norm": 0.9270663857460022, "learning_rate": 0.0002, "epoch": 4.185412406271302, "step": 3070}, {"loss": 1.2167, "grad_norm": 1.3415262699127197, "learning_rate": 0.0002, "epoch": 4.199045671438309, "step": 3080}, {"loss": 1.2601, "grad_norm": 1.167606234550476, "learning_rate": 0.0002, "epoch": 4.212678936605317, "step": 3090}, {"loss": 1.2605, "grad_norm": 0.9418690800666809, "learning_rate": 0.0002, "epoch": 4.226312201772324, "step": 3100}, {"loss": 1.2184, "grad_norm": 1.0885876417160034, "learning_rate": 0.0002, "epoch": 4.239945466939332, "step": 3110}, {"loss": 1.2594, "grad_norm": 0.9165483713150024, "learning_rate": 0.0002, "epoch": 4.253578732106339, "step": 3120}, {"loss": 1.2933, "grad_norm": 0.9154694080352783, "learning_rate": 0.0002, "epoch": 4.267211997273347, "step": 3130}, {"loss": 1.2584, "grad_norm": 1.100580096244812, "learning_rate": 0.0002, "epoch": 4.280845262440354, "step": 3140}, {"loss": 1.251, "grad_norm": 0.9367576241493225, "learning_rate": 0.0002, "epoch": 4.294478527607362, "step": 3150}, {"loss": 1.2032, "grad_norm": 0.9744015336036682, "learning_rate": 0.0002, "epoch": 4.308111792774369, "step": 3160}, {"loss": 1.2787, "grad_norm": 0.9865175485610962, "learning_rate": 0.0002, "epoch": 4.321745057941377, "step": 3170}, {"loss": 1.2161, "grad_norm": 1.0124907493591309, "learning_rate": 0.0002, "epoch": 4.335378323108385, "step": 3180}, {"loss": 1.2452, "grad_norm": 1.1044819355010986, "learning_rate": 0.0002, "epoch": 4.349011588275392, "step": 3190}, {"loss": 1.2483, "grad_norm": 0.9305577278137207, "learning_rate": 0.0002, "epoch": 4.3626448534424, "step": 3200}, {"loss": 1.2101, "grad_norm": 0.969265341758728, "learning_rate": 0.0002, "epoch": 4.376278118609407, "step": 3210}, {"loss": 1.2355, "grad_norm": 1.0671923160552979, "learning_rate": 0.0002, "epoch": 4.389911383776415, "step": 3220}, {"loss": 1.2259, "grad_norm": 0.9440539479255676, "learning_rate": 0.0002, "epoch": 4.403544648943422, "step": 3230}, {"loss": 1.1706, "grad_norm": 0.9824562668800354, "learning_rate": 0.0002, "epoch": 4.41717791411043, "step": 3240}, {"loss": 1.2234, "grad_norm": 1.0245535373687744, "learning_rate": 0.0002, "epoch": 4.430811179277437, "step": 3250}, {"loss": 1.2713, "grad_norm": 0.9629312753677368, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 3260}, {"loss": 1.2689, "grad_norm": 1.1556470394134521, "learning_rate": 0.0002, "epoch": 4.458077709611452, "step": 3270}, {"loss": 1.2214, "grad_norm": 0.9796679019927979, "learning_rate": 0.0002, "epoch": 4.47171097477846, "step": 3280}, {"loss": 1.2823, "grad_norm": 0.9030535221099854, "learning_rate": 0.0002, "epoch": 4.485344239945467, "step": 3290}, {"loss": 1.2111, "grad_norm": 0.9142820835113525, "learning_rate": 0.0002, "epoch": 4.4989775051124745, "step": 3300}, {"loss": 1.2398, "grad_norm": 0.966867208480835, "learning_rate": 0.0002, "epoch": 4.5126107702794815, "step": 3310}, {"loss": 1.2537, "grad_norm": 1.0127079486846924, "learning_rate": 0.0002, "epoch": 4.5262440354464895, "step": 3320}, {"loss": 1.2059, "grad_norm": 1.055506706237793, "learning_rate": 0.0002, "epoch": 4.539877300613497, "step": 3330}, {"loss": 1.2958, "grad_norm": 0.9831468462944031, "learning_rate": 0.0002, "epoch": 4.553510565780504, "step": 3340}, {"loss": 1.2643, "grad_norm": 0.9304661154747009, "learning_rate": 0.0002, "epoch": 4.567143830947512, "step": 3350}, {"loss": 1.3621, "grad_norm": 0.9369107484817505, "learning_rate": 0.0002, "epoch": 4.580777096114519, "step": 3360}, {"loss": 1.2301, "grad_norm": 1.009506344795227, "learning_rate": 0.0002, "epoch": 4.594410361281527, "step": 3370}, {"loss": 1.2535, "grad_norm": 1.0575741529464722, "learning_rate": 0.0002, "epoch": 4.608043626448534, "step": 3380}, {"loss": 1.1914, "grad_norm": 0.9102860689163208, "learning_rate": 0.0002, "epoch": 4.621676891615542, "step": 3390}, {"loss": 1.3156, "grad_norm": 0.8111315965652466, "learning_rate": 0.0002, "epoch": 4.635310156782549, "step": 3400}, {"loss": 1.3103, "grad_norm": 0.9459649920463562, "learning_rate": 0.0002, "epoch": 4.648943421949557, "step": 3410}, {"loss": 1.3146, "grad_norm": 0.9709545969963074, "learning_rate": 0.0002, "epoch": 4.662576687116564, "step": 3420}, {"loss": 1.2958, "grad_norm": 0.9909247159957886, "learning_rate": 0.0002, "epoch": 4.676209952283572, "step": 3430}, {"loss": 1.3186, "grad_norm": 0.9094610810279846, "learning_rate": 0.0002, "epoch": 4.689843217450579, "step": 3440}, {"loss": 1.3397, "grad_norm": 0.9012220501899719, "learning_rate": 0.0002, "epoch": 4.703476482617587, "step": 3450}, {"loss": 1.2595, "grad_norm": 0.8669242858886719, "learning_rate": 0.0002, "epoch": 4.717109747784594, "step": 3460}, {"loss": 1.2762, "grad_norm": 0.9753699898719788, "learning_rate": 0.0002, "epoch": 4.730743012951602, "step": 3470}, {"loss": 1.2371, "grad_norm": 1.0252684354782104, "learning_rate": 0.0002, "epoch": 4.74437627811861, "step": 3480}, {"loss": 1.2536, "grad_norm": 1.208098292350769, "learning_rate": 0.0002, "epoch": 4.758009543285617, "step": 3490}, {"loss": 1.2256, "grad_norm": 0.8632914423942566, "learning_rate": 0.0002, "epoch": 4.771642808452625, "step": 3500}, {"loss": 1.3062, "grad_norm": 1.0084818601608276, "learning_rate": 0.0002, "epoch": 4.785276073619632, "step": 3510}, {"loss": 1.3004, "grad_norm": 0.9095172882080078, "learning_rate": 0.0002, "epoch": 4.79890933878664, "step": 3520}, {"loss": 1.263, "grad_norm": 0.9740135669708252, "learning_rate": 0.0002, "epoch": 4.812542603953647, "step": 3530}, {"loss": 1.2816, "grad_norm": 0.8862348794937134, "learning_rate": 0.0002, "epoch": 4.826175869120655, "step": 3540}, {"loss": 1.2275, "grad_norm": 1.0761774778366089, "learning_rate": 0.0002, "epoch": 4.839809134287662, "step": 3550}, {"loss": 1.2257, "grad_norm": 1.0134117603302002, "learning_rate": 0.0002, "epoch": 4.85344239945467, "step": 3560}, {"loss": 1.2904, "grad_norm": 0.9262851476669312, "learning_rate": 0.0002, "epoch": 4.867075664621677, "step": 3570}, {"loss": 1.1466, "grad_norm": 0.9518504738807678, "learning_rate": 0.0002, "epoch": 4.8807089297886845, "step": 3580}, {"loss": 1.2741, "grad_norm": 1.10103178024292, "learning_rate": 0.0002, "epoch": 4.894342194955692, "step": 3590}, {"loss": 1.2592, "grad_norm": 1.0133225917816162, "learning_rate": 0.0002, "epoch": 4.9079754601226995, "step": 3600}, {"loss": 1.2856, "grad_norm": 0.9637737274169922, "learning_rate": 0.0002, "epoch": 4.9216087252897065, "step": 3610}, {"loss": 1.2991, "grad_norm": 0.9800633192062378, "learning_rate": 0.0002, "epoch": 4.935241990456714, "step": 3620}, {"loss": 1.2872, "grad_norm": 1.0065973997116089, "learning_rate": 0.0002, "epoch": 4.948875255623722, "step": 3630}, {"loss": 1.2408, "grad_norm": 0.9354690313339233, "learning_rate": 0.0002, "epoch": 4.962508520790729, "step": 3640}, {"loss": 1.291, "grad_norm": 0.9744119048118591, "learning_rate": 0.0002, "epoch": 4.976141785957737, "step": 3650}, {"loss": 1.2513, "grad_norm": 0.9357708096504211, "learning_rate": 0.0002, "epoch": 4.989775051124744, "step": 3660}]}
+{"epoch": 6.0, "step": 4401, "epoch_duration": 1095.5983347892761, "total_accumulated_duration": 6572.7824721336365, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19996.724609375}, "avg_memory_reserved": {"GPU_0": 28746.0}, "peak_memory_reserved": {"GPU_0": 28746.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733", "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": 3.0982, "grad_norm": 0.7714291214942932, "learning_rate": 0.0002, "epoch": 0.013633265167007498, "step": 10}, {"loss": 2.5206, "grad_norm": 0.5473978519439697, "learning_rate": 0.0002, "epoch": 0.027266530334014997, "step": 20}, {"loss": 2.3079, "grad_norm": 0.5452795624732971, "learning_rate": 0.0002, "epoch": 0.0408997955010225, "step": 30}, {"loss": 2.0019, "grad_norm": 0.5098028779029846, "learning_rate": 0.0002, "epoch": 0.054533060668029994, "step": 40}, {"loss": 1.9333, "grad_norm": 0.48062971234321594, "learning_rate": 0.0002, "epoch": 0.0681663258350375, "step": 50}, {"loss": 1.9355, "grad_norm": 0.4505695104598999, "learning_rate": 0.0002, "epoch": 0.081799591002045, "step": 60}, {"loss": 1.9312, "grad_norm": 0.41609591245651245, "learning_rate": 0.0002, "epoch": 0.09543285616905249, "step": 70}, {"loss": 1.8656, "grad_norm": 0.4323892593383789, "learning_rate": 0.0002, "epoch": 0.10906612133605999, "step": 80}, {"loss": 1.9294, "grad_norm": 0.4670293629169464, "learning_rate": 0.0002, "epoch": 0.12269938650306748, "step": 90}, {"loss": 1.7946, "grad_norm": 0.40623316168785095, "learning_rate": 0.0002, "epoch": 0.136332651670075, "step": 100}, {"loss": 1.8565, "grad_norm": 0.3620383143424988, "learning_rate": 0.0002, "epoch": 0.1499659168370825, "step": 110}, {"loss": 1.9238, "grad_norm": 0.332218736410141, "learning_rate": 0.0002, "epoch": 0.16359918200409, "step": 120}, {"loss": 1.93, "grad_norm": 0.4004521667957306, "learning_rate": 0.0002, "epoch": 0.17723244717109748, "step": 130}, {"loss": 1.7549, "grad_norm": 0.3698360323905945, "learning_rate": 0.0002, "epoch": 0.19086571233810498, "step": 140}, {"loss": 1.8771, "grad_norm": 0.3847949504852295, "learning_rate": 0.0002, "epoch": 0.20449897750511248, "step": 150}, {"loss": 1.8316, "grad_norm": 0.36843451857566833, "learning_rate": 0.0002, "epoch": 0.21813224267211997, "step": 160}, {"loss": 1.838, "grad_norm": 0.37301021814346313, "learning_rate": 0.0002, "epoch": 0.23176550783912747, "step": 170}, {"loss": 1.8909, "grad_norm": 0.3718886971473694, "learning_rate": 0.0002, "epoch": 0.24539877300613497, "step": 180}, {"loss": 1.8454, "grad_norm": 0.3088490962982178, "learning_rate": 0.0002, "epoch": 0.25903203817314246, "step": 190}, {"loss": 1.9254, "grad_norm": 0.3611852526664734, "learning_rate": 0.0002, "epoch": 0.27266530334015, "step": 200}, {"loss": 1.7844, "grad_norm": 0.36093324422836304, "learning_rate": 0.0002, "epoch": 0.28629856850715746, "step": 210}, {"loss": 1.719, "grad_norm": 0.3250400722026825, "learning_rate": 0.0002, "epoch": 0.299931833674165, "step": 220}, {"loss": 1.8729, "grad_norm": 0.3566756248474121, "learning_rate": 0.0002, "epoch": 0.31356509884117245, "step": 230}, {"loss": 1.9259, "grad_norm": 0.32872408628463745, "learning_rate": 0.0002, "epoch": 0.32719836400818, "step": 240}, {"loss": 1.9033, "grad_norm": 0.3983881175518036, "learning_rate": 0.0002, "epoch": 0.34083162917518744, "step": 250}, {"loss": 1.8588, "grad_norm": 0.3571510910987854, "learning_rate": 0.0002, "epoch": 0.35446489434219497, "step": 260}, {"loss": 1.8539, "grad_norm": 0.3036131262779236, "learning_rate": 0.0002, "epoch": 0.36809815950920244, "step": 270}, {"loss": 1.8572, "grad_norm": 0.36512863636016846, "learning_rate": 0.0002, "epoch": 0.38173142467620996, "step": 280}, {"loss": 1.8022, "grad_norm": 0.3429736793041229, "learning_rate": 0.0002, "epoch": 0.39536468984321743, "step": 290}, {"loss": 1.8754, "grad_norm": 0.3055964708328247, "learning_rate": 0.0002, "epoch": 0.40899795501022496, "step": 300}, {"loss": 1.8384, "grad_norm": 0.33801034092903137, "learning_rate": 0.0002, "epoch": 0.4226312201772324, "step": 310}, {"loss": 1.7933, "grad_norm": 0.348783016204834, "learning_rate": 0.0002, "epoch": 0.43626448534423995, "step": 320}, {"loss": 1.8451, "grad_norm": 0.3057514727115631, "learning_rate": 0.0002, "epoch": 0.4498977505112474, "step": 330}, {"loss": 1.8766, "grad_norm": 0.3849763572216034, "learning_rate": 0.0002, "epoch": 0.46353101567825494, "step": 340}, {"loss": 1.8073, "grad_norm": 0.30080053210258484, "learning_rate": 0.0002, "epoch": 0.47716428084526247, "step": 350}, {"loss": 1.8548, "grad_norm": 0.3595106303691864, "learning_rate": 0.0002, "epoch": 0.49079754601226994, "step": 360}, {"loss": 1.8232, "grad_norm": 0.31099820137023926, "learning_rate": 0.0002, "epoch": 0.5044308111792775, "step": 370}, {"loss": 1.7029, "grad_norm": 0.3157978355884552, "learning_rate": 0.0002, "epoch": 0.5180640763462849, "step": 380}, {"loss": 1.8265, "grad_norm": 0.27960965037345886, "learning_rate": 0.0002, "epoch": 0.5316973415132924, "step": 390}, {"loss": 1.7414, "grad_norm": 0.3102385103702545, "learning_rate": 0.0002, "epoch": 0.5453306066803, "step": 400}, {"loss": 1.7461, "grad_norm": 0.32828861474990845, "learning_rate": 0.0002, "epoch": 0.5589638718473074, "step": 410}, {"loss": 1.8165, "grad_norm": 0.29560017585754395, "learning_rate": 0.0002, "epoch": 0.5725971370143149, "step": 420}, {"loss": 1.9455, "grad_norm": 0.33316895365715027, "learning_rate": 0.0002, "epoch": 0.5862304021813224, "step": 430}, {"loss": 1.8241, "grad_norm": 0.30420982837677, "learning_rate": 0.0002, "epoch": 0.59986366734833, "step": 440}, {"loss": 1.7565, "grad_norm": 0.32619214057922363, "learning_rate": 0.0002, "epoch": 0.6134969325153374, "step": 450}, {"loss": 1.7945, "grad_norm": 0.3603750765323639, "learning_rate": 0.0002, "epoch": 0.6271301976823449, "step": 460}, {"loss": 1.7773, "grad_norm": 0.30834096670150757, "learning_rate": 0.0002, "epoch": 0.6407634628493524, "step": 470}, {"loss": 1.8058, "grad_norm": 0.28756365180015564, "learning_rate": 0.0002, "epoch": 0.65439672801636, "step": 480}, {"loss": 1.744, "grad_norm": 0.2878406345844269, "learning_rate": 0.0002, "epoch": 0.6680299931833674, "step": 490}, {"loss": 1.8581, "grad_norm": 0.31329697370529175, "learning_rate": 0.0002, "epoch": 0.6816632583503749, "step": 500}, {"loss": 1.7886, "grad_norm": 0.3405822515487671, "learning_rate": 0.0002, "epoch": 0.6952965235173824, "step": 510}, {"loss": 1.778, "grad_norm": 0.305560827255249, "learning_rate": 0.0002, "epoch": 0.7089297886843899, "step": 520}, {"loss": 1.7592, "grad_norm": 0.2973416745662689, "learning_rate": 0.0002, "epoch": 0.7225630538513974, "step": 530}, {"loss": 1.8223, "grad_norm": 0.327303946018219, "learning_rate": 0.0002, "epoch": 0.7361963190184049, "step": 540}, {"loss": 1.8591, "grad_norm": 0.62595534324646, "learning_rate": 0.0002, "epoch": 0.7498295841854125, "step": 550}, {"loss": 1.7466, "grad_norm": 0.3129784166812897, "learning_rate": 0.0002, "epoch": 0.7634628493524199, "step": 560}, {"loss": 1.8035, "grad_norm": 0.32496583461761475, "learning_rate": 0.0002, "epoch": 0.7770961145194274, "step": 570}, {"loss": 1.7787, "grad_norm": 0.3098868131637573, "learning_rate": 0.0002, "epoch": 0.7907293796864349, "step": 580}, {"loss": 1.7196, "grad_norm": 0.30726853013038635, "learning_rate": 0.0002, "epoch": 0.8043626448534424, "step": 590}, {"loss": 1.7898, "grad_norm": 0.2964220643043518, "learning_rate": 0.0002, "epoch": 0.8179959100204499, "step": 600}, {"loss": 1.8114, "grad_norm": 0.32352274656295776, "learning_rate": 0.0002, "epoch": 0.8316291751874574, "step": 610}, {"loss": 1.811, "grad_norm": 0.2938912510871887, "learning_rate": 0.0002, "epoch": 0.8452624403544649, "step": 620}, {"loss": 1.7727, "grad_norm": 0.295559823513031, "learning_rate": 0.0002, "epoch": 0.8588957055214724, "step": 630}, {"loss": 1.9, "grad_norm": 0.34102028608322144, "learning_rate": 0.0002, "epoch": 0.8725289706884799, "step": 640}, {"loss": 1.8006, "grad_norm": 0.29676181077957153, "learning_rate": 0.0002, "epoch": 0.8861622358554874, "step": 650}, {"loss": 1.8099, "grad_norm": 0.3108902871608734, "learning_rate": 0.0002, "epoch": 0.8997955010224948, "step": 660}, {"loss": 1.7955, "grad_norm": 0.2690821588039398, "learning_rate": 0.0002, "epoch": 0.9134287661895024, "step": 670}, {"loss": 1.7881, "grad_norm": 0.32752540707588196, "learning_rate": 0.0002, "epoch": 0.9270620313565099, "step": 680}, {"loss": 1.7661, "grad_norm": 0.8029476404190063, "learning_rate": 0.0002, "epoch": 0.9406952965235174, "step": 690}, {"loss": 1.7733, "grad_norm": 0.30534422397613525, "learning_rate": 0.0002, "epoch": 0.9543285616905249, "step": 700}, {"loss": 1.7614, "grad_norm": 0.2899954319000244, "learning_rate": 0.0002, "epoch": 0.9679618268575324, "step": 710}, {"loss": 1.7845, "grad_norm": 0.28814372420310974, "learning_rate": 0.0002, "epoch": 0.9815950920245399, "step": 720}, {"loss": 1.8865, "grad_norm": 0.3061596751213074, "learning_rate": 0.0002, "epoch": 0.9952283571915473, "step": 730}, {"eval_loss": 1.8171186447143555, "eval_runtime": 53.6047, "eval_samples_per_second": 9.458, "eval_steps_per_second": 1.194, "epoch": 0.9993183367416496, "step": 733}, {"loss": 1.6202, "grad_norm": 0.3140897750854492, "learning_rate": 0.0002, "epoch": 1.008861622358555, "step": 740}, {"loss": 1.8409, "grad_norm": 0.3346109390258789, "learning_rate": 0.0002, "epoch": 1.0224948875255624, "step": 750}, {"loss": 1.6777, "grad_norm": 0.3582976758480072, "learning_rate": 0.0002, "epoch": 1.0361281526925699, "step": 760}, {"loss": 1.7306, "grad_norm": 0.30408260226249695, "learning_rate": 0.0002, "epoch": 1.0497614178595773, "step": 770}, {"loss": 1.6967, "grad_norm": 0.323585569858551, "learning_rate": 0.0002, "epoch": 1.0633946830265848, "step": 780}, {"loss": 1.768, "grad_norm": 0.3474137783050537, "learning_rate": 0.0002, "epoch": 1.0770279481935923, "step": 790}, {"loss": 1.6895, "grad_norm": 0.35721147060394287, "learning_rate": 0.0002, "epoch": 1.0906612133606, "step": 800}, {"loss": 1.718, "grad_norm": 0.35366931557655334, "learning_rate": 0.0002, "epoch": 1.1042944785276074, "step": 810}, {"loss": 1.6797, "grad_norm": 0.3250770568847656, "learning_rate": 0.0002, "epoch": 1.117927743694615, "step": 820}, {"loss": 1.6383, "grad_norm": 0.3293766379356384, "learning_rate": 0.0002, "epoch": 1.1315610088616224, "step": 830}, {"loss": 1.7353, "grad_norm": 0.3380851745605469, "learning_rate": 0.0002, "epoch": 1.1451942740286298, "step": 840}, {"loss": 1.8236, "grad_norm": 0.32584455609321594, "learning_rate": 0.0002, "epoch": 1.1588275391956373, "step": 850}, {"loss": 1.6681, "grad_norm": 0.45700767636299133, "learning_rate": 0.0002, "epoch": 1.1724608043626448, "step": 860}, {"loss": 1.7494, "grad_norm": 0.30944544076919556, "learning_rate": 0.0002, "epoch": 1.1860940695296525, "step": 870}, {"loss": 1.7426, "grad_norm": 0.3268151581287384, "learning_rate": 0.0002, "epoch": 1.19972733469666, "step": 880}, {"loss": 1.7413, "grad_norm": 0.39972540736198425, "learning_rate": 0.0002, "epoch": 1.2133605998636674, "step": 890}, {"loss": 1.7481, "grad_norm": 0.7890929579734802, "learning_rate": 0.0002, "epoch": 1.2269938650306749, "step": 900}, {"loss": 1.7608, "grad_norm": 0.3439182639122009, "learning_rate": 0.0002, "epoch": 1.2406271301976823, "step": 910}, {"loss": 1.7617, "grad_norm": 0.3986225128173828, "learning_rate": 0.0002, "epoch": 1.2542603953646898, "step": 920}, {"loss": 1.6843, "grad_norm": 0.3514605164527893, "learning_rate": 0.0002, "epoch": 1.2678936605316973, "step": 930}, {"loss": 1.6987, "grad_norm": 0.3682589530944824, "learning_rate": 0.0002, "epoch": 1.2815269256987047, "step": 940}, {"loss": 1.6988, "grad_norm": 0.3618335723876953, "learning_rate": 0.0002, "epoch": 1.2951601908657122, "step": 950}, {"loss": 1.7436, "grad_norm": 0.345700740814209, "learning_rate": 0.0002, "epoch": 1.30879345603272, "step": 960}, {"loss": 1.7336, "grad_norm": 0.3514927923679352, "learning_rate": 0.0002, "epoch": 1.3224267211997274, "step": 970}, {"loss": 1.7704, "grad_norm": 0.365647554397583, "learning_rate": 0.0002, "epoch": 1.3360599863667348, "step": 980}, {"loss": 1.7104, "grad_norm": 0.3407285809516907, "learning_rate": 0.0002, "epoch": 1.3496932515337423, "step": 990}, {"loss": 1.7132, "grad_norm": 0.3785437345504761, "learning_rate": 0.0002, "epoch": 1.3633265167007498, "step": 1000}, {"loss": 1.766, "grad_norm": 0.34746724367141724, "learning_rate": 0.0002, "epoch": 1.3769597818677572, "step": 1010}, {"loss": 1.7252, "grad_norm": 0.362444132566452, "learning_rate": 0.0002, "epoch": 1.390593047034765, "step": 1020}, {"loss": 1.7132, "grad_norm": 0.4424704611301422, "learning_rate": 0.0002, "epoch": 1.4042263122017724, "step": 1030}, {"loss": 1.726, "grad_norm": 0.38722458481788635, "learning_rate": 0.0002, "epoch": 1.4178595773687799, "step": 1040}, {"loss": 1.7955, "grad_norm": 0.36089080572128296, "learning_rate": 0.0002, "epoch": 1.4314928425357873, "step": 1050}, {"loss": 1.6924, "grad_norm": 0.33817124366760254, "learning_rate": 0.0002, "epoch": 1.4451261077027948, "step": 1060}, {"loss": 1.7165, "grad_norm": 0.34334081411361694, "learning_rate": 0.0002, "epoch": 1.4587593728698023, "step": 1070}, {"loss": 1.6999, "grad_norm": 0.3776826858520508, "learning_rate": 0.0002, "epoch": 1.4723926380368098, "step": 1080}, {"loss": 1.7605, "grad_norm": 0.4169026017189026, "learning_rate": 0.0002, "epoch": 1.4860259032038172, "step": 1090}, {"loss": 1.7502, "grad_norm": 0.34898945689201355, "learning_rate": 0.0002, "epoch": 1.4996591683708247, "step": 1100}, {"loss": 1.635, "grad_norm": 0.34223780035972595, "learning_rate": 0.0002, "epoch": 1.5132924335378322, "step": 1110}, {"loss": 1.7248, "grad_norm": 0.3686901032924652, "learning_rate": 0.0002, "epoch": 1.5269256987048399, "step": 1120}, {"loss": 1.7525, "grad_norm": 0.35054415464401245, "learning_rate": 0.0002, "epoch": 1.5405589638718473, "step": 1130}, {"loss": 1.7776, "grad_norm": 0.39496365189552307, "learning_rate": 0.0002, "epoch": 1.5541922290388548, "step": 1140}, {"loss": 1.6574, "grad_norm": 0.35451626777648926, "learning_rate": 0.0002, "epoch": 1.5678254942058623, "step": 1150}, {"loss": 1.7257, "grad_norm": 0.3848083019256592, "learning_rate": 0.0002, "epoch": 1.58145875937287, "step": 1160}, {"loss": 1.7272, "grad_norm": 0.3760537803173065, "learning_rate": 0.0002, "epoch": 1.5950920245398774, "step": 1170}, {"loss": 1.7441, "grad_norm": 0.38981738686561584, "learning_rate": 0.0002, "epoch": 1.6087252897068849, "step": 1180}, {"loss": 1.6951, "grad_norm": 0.36830949783325195, "learning_rate": 0.0002, "epoch": 1.6223585548738924, "step": 1190}, {"loss": 1.6925, "grad_norm": 0.3405892848968506, "learning_rate": 0.0002, "epoch": 1.6359918200408998, "step": 1200}, {"loss": 1.7473, "grad_norm": 0.39027872681617737, "learning_rate": 0.0002, "epoch": 1.6496250852079073, "step": 1210}, {"loss": 1.6792, "grad_norm": 0.3342694044113159, "learning_rate": 0.0002, "epoch": 1.6632583503749148, "step": 1220}, {"loss": 1.7196, "grad_norm": 0.3600076735019684, "learning_rate": 0.0002, "epoch": 1.6768916155419222, "step": 1230}, {"loss": 1.7021, "grad_norm": 0.3625542223453522, "learning_rate": 0.0002, "epoch": 1.6905248807089297, "step": 1240}, {"loss": 1.6772, "grad_norm": 0.32170894742012024, "learning_rate": 0.0002, "epoch": 1.7041581458759372, "step": 1250}, {"loss": 1.7152, "grad_norm": 0.3544139862060547, "learning_rate": 0.0002, "epoch": 1.7177914110429446, "step": 1260}, {"loss": 1.7138, "grad_norm": 0.35113027691841125, "learning_rate": 0.0002, "epoch": 1.7314246762099523, "step": 1270}, {"loss": 1.7095, "grad_norm": 0.3499974310398102, "learning_rate": 0.0002, "epoch": 1.7450579413769598, "step": 1280}, {"loss": 1.7749, "grad_norm": 0.3285157382488251, "learning_rate": 0.0002, "epoch": 1.7586912065439673, "step": 1290}, {"loss": 1.6767, "grad_norm": 0.3701961636543274, "learning_rate": 0.0002, "epoch": 1.7723244717109747, "step": 1300}, {"loss": 1.6282, "grad_norm": 0.3301318287849426, "learning_rate": 0.0002, "epoch": 1.7859577368779824, "step": 1310}, {"loss": 1.7097, "grad_norm": 0.37801554799079895, "learning_rate": 0.0002, "epoch": 1.79959100204499, "step": 1320}, {"loss": 1.7437, "grad_norm": 0.3726748526096344, "learning_rate": 0.0002, "epoch": 1.8132242672119974, "step": 1330}, {"loss": 1.7959, "grad_norm": 0.4059790074825287, "learning_rate": 0.0002, "epoch": 1.8268575323790048, "step": 1340}, {"loss": 1.7739, "grad_norm": 0.35712096095085144, "learning_rate": 0.0002, "epoch": 1.8404907975460123, "step": 1350}, {"loss": 1.6375, "grad_norm": 0.35995328426361084, "learning_rate": 0.0002, "epoch": 1.8541240627130198, "step": 1360}, {"loss": 1.7332, "grad_norm": 0.3679947257041931, "learning_rate": 0.0002, "epoch": 1.8677573278800272, "step": 1370}, {"loss": 1.7587, "grad_norm": 0.39645957946777344, "learning_rate": 0.0002, "epoch": 1.8813905930470347, "step": 1380}, {"loss": 1.6985, "grad_norm": 0.35288700461387634, "learning_rate": 0.0002, "epoch": 1.8950238582140422, "step": 1390}, {"loss": 1.6582, "grad_norm": 0.32579198479652405, "learning_rate": 0.0002, "epoch": 1.9086571233810496, "step": 1400}, {"loss": 1.6948, "grad_norm": 0.3856561779975891, "learning_rate": 0.0002, "epoch": 1.9222903885480571, "step": 1410}, {"loss": 1.668, "grad_norm": 0.39019331336021423, "learning_rate": 0.0002, "epoch": 1.9359236537150648, "step": 1420}, {"loss": 1.7774, "grad_norm": 0.38006502389907837, "learning_rate": 0.0002, "epoch": 1.9495569188820723, "step": 1430}, {"loss": 1.8323, "grad_norm": 0.38100454211235046, "learning_rate": 0.0002, "epoch": 1.9631901840490797, "step": 1440}, {"loss": 1.7298, "grad_norm": 0.3405798673629761, "learning_rate": 0.0002, "epoch": 1.9768234492160872, "step": 1450}, {"loss": 1.7045, "grad_norm": 0.36582913994789124, "learning_rate": 0.0002, "epoch": 1.990456714383095, "step": 1460}, {"eval_loss": 1.8178424835205078, "eval_runtime": 53.6524, "eval_samples_per_second": 9.45, "eval_steps_per_second": 1.193, "epoch": 2.0, "step": 1467}, {"loss": 1.6363, "grad_norm": 0.3626647889614105, "learning_rate": 0.0002, "epoch": 2.0040899795501024, "step": 1470}, {"loss": 1.5354, "grad_norm": 0.40171775221824646, "learning_rate": 0.0002, "epoch": 2.01772324471711, "step": 1480}, {"loss": 1.5566, "grad_norm": 0.5805319547653198, "learning_rate": 0.0002, "epoch": 2.0313565098841173, "step": 1490}, {"loss": 1.546, "grad_norm": 0.41954153776168823, "learning_rate": 0.0002, "epoch": 2.044989775051125, "step": 1500}, {"loss": 1.6158, "grad_norm": 0.47190725803375244, "learning_rate": 0.0002, "epoch": 2.0586230402181322, "step": 1510}, {"loss": 1.5841, "grad_norm": 0.4388456344604492, "learning_rate": 0.0002, "epoch": 2.0722563053851397, "step": 1520}, {"loss": 1.5835, "grad_norm": 2.2171926498413086, "learning_rate": 0.0002, "epoch": 2.085889570552147, "step": 1530}, {"loss": 1.6137, "grad_norm": 0.4314221143722534, "learning_rate": 0.0002, "epoch": 2.0995228357191547, "step": 1540}, {"loss": 1.5511, "grad_norm": 0.4154265522956848, "learning_rate": 0.0002, "epoch": 2.113156100886162, "step": 1550}, {"loss": 1.6323, "grad_norm": 0.5025539994239807, "learning_rate": 0.0002, "epoch": 2.1267893660531696, "step": 1560}, {"loss": 1.5903, "grad_norm": 0.5410493016242981, "learning_rate": 0.0002, "epoch": 2.140422631220177, "step": 1570}, {"loss": 1.507, "grad_norm": 0.4478487968444824, "learning_rate": 0.0002, "epoch": 2.1540558963871845, "step": 1580}, {"loss": 1.5536, "grad_norm": 0.4703652560710907, "learning_rate": 0.0002, "epoch": 2.1676891615541924, "step": 1590}, {"loss": 1.5991, "grad_norm": 0.4555390179157257, "learning_rate": 0.0002, "epoch": 2.1813224267212, "step": 1600}, {"loss": 1.6117, "grad_norm": 0.4877263903617859, "learning_rate": 0.0002, "epoch": 2.1949556918882074, "step": 1610}, {"loss": 1.5928, "grad_norm": 0.48708245158195496, "learning_rate": 0.0002, "epoch": 2.208588957055215, "step": 1620}, {"loss": 1.6106, "grad_norm": 0.47523951530456543, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 1630}, {"loss": 1.6013, "grad_norm": 0.4889199733734131, "learning_rate": 0.0002, "epoch": 2.23585548738923, "step": 1640}, {"loss": 1.6633, "grad_norm": 0.4585252106189728, "learning_rate": 0.0002, "epoch": 2.2494887525562373, "step": 1650}, {"loss": 1.6075, "grad_norm": 0.4764868915081024, "learning_rate": 0.0002, "epoch": 2.2631220177232447, "step": 1660}, {"loss": 1.6427, "grad_norm": 0.5028976202011108, "learning_rate": 0.0002, "epoch": 2.276755282890252, "step": 1670}, {"loss": 1.6258, "grad_norm": 0.46131211519241333, "learning_rate": 0.0002, "epoch": 2.2903885480572597, "step": 1680}, {"loss": 1.654, "grad_norm": 0.5422874689102173, "learning_rate": 0.0002, "epoch": 2.304021813224267, "step": 1690}, {"loss": 1.6331, "grad_norm": 0.47615355253219604, "learning_rate": 0.0002, "epoch": 2.3176550783912746, "step": 1700}, {"loss": 1.642, "grad_norm": 0.48005548119544983, "learning_rate": 0.0002, "epoch": 2.331288343558282, "step": 1710}, {"loss": 1.581, "grad_norm": 0.4387182295322418, "learning_rate": 0.0002, "epoch": 2.3449216087252895, "step": 1720}, {"loss": 1.5612, "grad_norm": 0.4487272799015045, "learning_rate": 0.0002, "epoch": 2.358554873892297, "step": 1730}, {"loss": 1.5089, "grad_norm": 0.5046455264091492, "learning_rate": 0.0002, "epoch": 2.372188139059305, "step": 1740}, {"loss": 1.5769, "grad_norm": 0.4653521180152893, "learning_rate": 0.0002, "epoch": 2.3858214042263124, "step": 1750}, {"loss": 1.6201, "grad_norm": 0.4737723469734192, "learning_rate": 0.0002, "epoch": 2.39945466939332, "step": 1760}, {"loss": 1.5933, "grad_norm": 0.4501931071281433, "learning_rate": 0.0002, "epoch": 2.4130879345603273, "step": 1770}, {"loss": 1.6321, "grad_norm": 0.4772880971431732, "learning_rate": 0.0002, "epoch": 2.426721199727335, "step": 1780}, {"loss": 1.5454, "grad_norm": 0.4544616937637329, "learning_rate": 0.0002, "epoch": 2.4403544648943423, "step": 1790}, {"loss": 1.5501, "grad_norm": 0.488313227891922, "learning_rate": 0.0002, "epoch": 2.4539877300613497, "step": 1800}, {"loss": 1.5791, "grad_norm": 0.5057830214500427, "learning_rate": 0.0002, "epoch": 2.467620995228357, "step": 1810}, {"loss": 1.5645, "grad_norm": 0.5049484968185425, "learning_rate": 0.0002, "epoch": 2.4812542603953647, "step": 1820}, {"loss": 1.6268, "grad_norm": 0.44966644048690796, "learning_rate": 0.0002, "epoch": 2.494887525562372, "step": 1830}, {"loss": 1.5941, "grad_norm": 0.5072630643844604, "learning_rate": 0.0002, "epoch": 2.5085207907293796, "step": 1840}, {"loss": 1.5251, "grad_norm": 0.43989792466163635, "learning_rate": 0.0002, "epoch": 2.522154055896387, "step": 1850}, {"loss": 1.563, "grad_norm": 1.3504403829574585, "learning_rate": 0.0002, "epoch": 2.5357873210633946, "step": 1860}, {"loss": 1.5681, "grad_norm": 0.46545976400375366, "learning_rate": 0.0002, "epoch": 2.549420586230402, "step": 1870}, {"loss": 1.6368, "grad_norm": 0.4678342044353485, "learning_rate": 0.0002, "epoch": 2.5630538513974095, "step": 1880}, {"loss": 1.5814, "grad_norm": 0.529755711555481, "learning_rate": 0.0002, "epoch": 2.5766871165644174, "step": 1890}, {"loss": 1.5861, "grad_norm": 0.5000199675559998, "learning_rate": 0.0002, "epoch": 2.5903203817314244, "step": 1900}, {"loss": 1.6346, "grad_norm": 0.5649300217628479, "learning_rate": 0.0002, "epoch": 2.6039536468984323, "step": 1910}, {"loss": 1.6317, "grad_norm": 0.7920585870742798, "learning_rate": 0.0002, "epoch": 2.61758691206544, "step": 1920}, {"loss": 1.643, "grad_norm": 0.4960342049598694, "learning_rate": 0.0002, "epoch": 2.6312201772324473, "step": 1930}, {"loss": 1.6099, "grad_norm": 0.5324710011482239, "learning_rate": 0.0002, "epoch": 2.6448534423994547, "step": 1940}, {"loss": 1.5874, "grad_norm": 0.606343150138855, "learning_rate": 0.0002, "epoch": 2.658486707566462, "step": 1950}, {"loss": 1.5728, "grad_norm": 0.53038489818573, "learning_rate": 0.0002, "epoch": 2.6721199727334697, "step": 1960}, {"loss": 1.5583, "grad_norm": 0.4579465091228485, "learning_rate": 0.0002, "epoch": 2.685753237900477, "step": 1970}, {"loss": 1.6093, "grad_norm": 0.4541707932949066, "learning_rate": 0.0002, "epoch": 2.6993865030674846, "step": 1980}, {"loss": 1.5316, "grad_norm": 0.5009395480155945, "learning_rate": 0.0002, "epoch": 2.713019768234492, "step": 1990}, {"loss": 1.6724, "grad_norm": 0.4723006784915924, "learning_rate": 0.0002, "epoch": 2.7266530334014996, "step": 2000}, {"loss": 1.638, "grad_norm": 0.5086126923561096, "learning_rate": 0.0002, "epoch": 2.740286298568507, "step": 2010}, {"loss": 1.6223, "grad_norm": 0.47242608666419983, "learning_rate": 0.0002, "epoch": 2.7539195637355145, "step": 2020}, {"loss": 1.6242, "grad_norm": 0.44922566413879395, "learning_rate": 0.0002, "epoch": 2.767552828902522, "step": 2030}, {"loss": 1.6837, "grad_norm": 0.420259565114975, "learning_rate": 0.0002, "epoch": 2.78118609406953, "step": 2040}, {"loss": 1.5612, "grad_norm": 0.4762881100177765, "learning_rate": 0.0002, "epoch": 2.794819359236537, "step": 2050}, {"loss": 1.5506, "grad_norm": 0.5228786468505859, "learning_rate": 0.0002, "epoch": 2.808452624403545, "step": 2060}, {"loss": 1.6347, "grad_norm": 0.4796035587787628, "learning_rate": 0.0002, "epoch": 2.8220858895705523, "step": 2070}, {"loss": 1.6843, "grad_norm": 0.5034735202789307, "learning_rate": 0.0002, "epoch": 2.8357191547375598, "step": 2080}, {"loss": 1.6455, "grad_norm": 0.48005399107933044, "learning_rate": 0.0002, "epoch": 2.8493524199045672, "step": 2090}, {"loss": 1.6287, "grad_norm": 0.578820526599884, "learning_rate": 0.0002, "epoch": 2.8629856850715747, "step": 2100}, {"loss": 1.6021, "grad_norm": 0.48982638120651245, "learning_rate": 0.0002, "epoch": 2.876618950238582, "step": 2110}, {"loss": 1.5769, "grad_norm": 0.5157325863838196, "learning_rate": 0.0002, "epoch": 2.8902522154055896, "step": 2120}, {"loss": 1.6089, "grad_norm": 0.49149683117866516, "learning_rate": 0.0002, "epoch": 2.903885480572597, "step": 2130}, {"loss": 1.5881, "grad_norm": 0.48584499955177307, "learning_rate": 0.0002, "epoch": 2.9175187457396046, "step": 2140}, {"loss": 1.5833, "grad_norm": 0.5199017524719238, "learning_rate": 0.0002, "epoch": 2.931152010906612, "step": 2150}, {"loss": 1.7344, "grad_norm": 0.5788236856460571, "learning_rate": 0.0002, "epoch": 2.9447852760736195, "step": 2160}, {"loss": 1.6103, "grad_norm": 0.48664185404777527, "learning_rate": 0.0002, "epoch": 2.958418541240627, "step": 2170}, {"loss": 1.5765, "grad_norm": 0.5026682615280151, "learning_rate": 0.0002, "epoch": 2.9720518064076344, "step": 2180}, {"loss": 1.6626, "grad_norm": 0.49317044019699097, "learning_rate": 0.0002, "epoch": 2.9856850715746424, "step": 2190}, {"loss": 1.5871, "grad_norm": 0.5729128122329712, "learning_rate": 0.0002, "epoch": 2.9993183367416494, "step": 2200}, {"eval_loss": 1.8527295589447021, "eval_runtime": 53.6403, "eval_samples_per_second": 9.452, "eval_steps_per_second": 1.193, "epoch": 2.9993183367416494, "step": 2200}, {"loss": 1.4719, "grad_norm": 0.5530241131782532, "learning_rate": 0.0002, "epoch": 3.0129516019086573, "step": 2210}, {"loss": 1.4088, "grad_norm": 0.6642216444015503, "learning_rate": 0.0002, "epoch": 3.0265848670756648, "step": 2220}, {"loss": 1.4382, "grad_norm": 0.61470627784729, "learning_rate": 0.0002, "epoch": 3.0402181322426722, "step": 2230}, {"loss": 1.4634, "grad_norm": 0.8559566140174866, "learning_rate": 0.0002, "epoch": 3.0538513974096797, "step": 2240}, {"loss": 1.3854, "grad_norm": 0.7015801668167114, "learning_rate": 0.0002, "epoch": 3.067484662576687, "step": 2250}, {"loss": 1.4981, "grad_norm": 0.7226442694664001, "learning_rate": 0.0002, "epoch": 3.0811179277436946, "step": 2260}, {"loss": 1.4143, "grad_norm": 0.7560588717460632, "learning_rate": 0.0002, "epoch": 3.094751192910702, "step": 2270}, {"loss": 1.4395, "grad_norm": 0.6216568946838379, "learning_rate": 0.0002, "epoch": 3.1083844580777096, "step": 2280}, {"loss": 1.3842, "grad_norm": 0.6768500804901123, "learning_rate": 0.0002, "epoch": 3.122017723244717, "step": 2290}, {"loss": 1.4672, "grad_norm": 0.7028762102127075, "learning_rate": 0.0002, "epoch": 3.1356509884117245, "step": 2300}, {"loss": 1.3826, "grad_norm": 0.6329697966575623, "learning_rate": 0.0002, "epoch": 3.149284253578732, "step": 2310}, {"loss": 1.442, "grad_norm": 0.6328264474868774, "learning_rate": 0.0002, "epoch": 3.1629175187457395, "step": 2320}, {"loss": 1.3762, "grad_norm": 0.7573632001876831, "learning_rate": 0.0002, "epoch": 3.176550783912747, "step": 2330}, {"loss": 1.3553, "grad_norm": 0.595740795135498, "learning_rate": 0.0002, "epoch": 3.190184049079755, "step": 2340}, {"loss": 1.3953, "grad_norm": 0.7111806869506836, "learning_rate": 0.0002, "epoch": 3.2038173142467623, "step": 2350}, {"loss": 1.3797, "grad_norm": 0.6328730583190918, "learning_rate": 0.0002, "epoch": 3.2174505794137698, "step": 2360}, {"loss": 1.3855, "grad_norm": 0.5860254168510437, "learning_rate": 0.0002, "epoch": 3.2310838445807772, "step": 2370}, {"loss": 1.4267, "grad_norm": 0.7387157082557678, "learning_rate": 0.0002, "epoch": 3.2447171097477847, "step": 2380}, {"loss": 1.4837, "grad_norm": 0.6897673606872559, "learning_rate": 0.0002, "epoch": 3.258350374914792, "step": 2390}, {"loss": 1.4372, "grad_norm": 0.7157699465751648, "learning_rate": 0.0002, "epoch": 3.2719836400817996, "step": 2400}, {"loss": 1.4432, "grad_norm": 0.6422511339187622, "learning_rate": 0.0002, "epoch": 3.285616905248807, "step": 2410}, {"loss": 1.4828, "grad_norm": 1.0481886863708496, "learning_rate": 0.0002, "epoch": 3.2992501704158146, "step": 2420}, {"loss": 1.4473, "grad_norm": 0.7050786018371582, "learning_rate": 0.0002, "epoch": 3.312883435582822, "step": 2430}, {"loss": 1.3465, "grad_norm": 0.6090759038925171, "learning_rate": 0.0002, "epoch": 3.3265167007498295, "step": 2440}, {"loss": 1.4619, "grad_norm": 0.6626465320587158, "learning_rate": 0.0002, "epoch": 3.340149965916837, "step": 2450}, {"loss": 1.4512, "grad_norm": 0.6565486788749695, "learning_rate": 0.0002, "epoch": 3.3537832310838445, "step": 2460}, {"loss": 1.588, "grad_norm": 0.6449528932571411, "learning_rate": 0.0002, "epoch": 3.367416496250852, "step": 2470}, {"loss": 1.4773, "grad_norm": 0.7746227383613586, "learning_rate": 0.0002, "epoch": 3.3810497614178594, "step": 2480}, {"loss": 1.417, "grad_norm": 0.7074846029281616, "learning_rate": 0.0002, "epoch": 3.3946830265848673, "step": 2490}, {"loss": 1.4476, "grad_norm": 0.6547690033912659, "learning_rate": 0.0002, "epoch": 3.4083162917518743, "step": 2500}, {"loss": 1.4074, "grad_norm": 0.784721314907074, "learning_rate": 0.0002, "epoch": 3.4219495569188823, "step": 2510}, {"loss": 1.4326, "grad_norm": 0.7270277738571167, "learning_rate": 0.0002, "epoch": 3.4355828220858897, "step": 2520}, {"loss": 1.4354, "grad_norm": 0.67588871717453, "learning_rate": 0.0002, "epoch": 3.449216087252897, "step": 2530}, {"loss": 1.4074, "grad_norm": 0.6768023371696472, "learning_rate": 0.0002, "epoch": 3.4628493524199047, "step": 2540}, {"loss": 1.4863, "grad_norm": 0.7026481628417969, "learning_rate": 0.0002, "epoch": 3.476482617586912, "step": 2550}, {"loss": 1.468, "grad_norm": 0.646075963973999, "learning_rate": 0.0002, "epoch": 3.4901158827539196, "step": 2560}, {"loss": 1.4058, "grad_norm": 0.6288973689079285, "learning_rate": 0.0002, "epoch": 3.503749147920927, "step": 2570}, {"loss": 1.4613, "grad_norm": 0.6440825462341309, "learning_rate": 0.0002, "epoch": 3.5173824130879345, "step": 2580}, {"loss": 1.3808, "grad_norm": 0.7074111700057983, "learning_rate": 0.0002, "epoch": 3.531015678254942, "step": 2590}, {"loss": 1.4901, "grad_norm": 0.7007562518119812, "learning_rate": 0.0002, "epoch": 3.5446489434219495, "step": 2600}, {"loss": 1.4511, "grad_norm": 0.6045376658439636, "learning_rate": 0.0002, "epoch": 3.558282208588957, "step": 2610}, {"loss": 1.4596, "grad_norm": 0.9149952530860901, "learning_rate": 0.0002, "epoch": 3.5719154737559644, "step": 2620}, {"loss": 1.4355, "grad_norm": 0.6490362882614136, "learning_rate": 0.0002, "epoch": 3.585548738922972, "step": 2630}, {"loss": 1.4107, "grad_norm": 0.6552226543426514, "learning_rate": 0.0002, "epoch": 3.59918200408998, "step": 2640}, {"loss": 1.433, "grad_norm": 0.6541850566864014, "learning_rate": 0.0002, "epoch": 3.612815269256987, "step": 2650}, {"loss": 1.4279, "grad_norm": 0.6500770449638367, "learning_rate": 0.0002, "epoch": 3.6264485344239947, "step": 2660}, {"loss": 1.3929, "grad_norm": 0.6345893740653992, "learning_rate": 0.0002, "epoch": 3.640081799591002, "step": 2670}, {"loss": 1.3634, "grad_norm": 0.6382275223731995, "learning_rate": 0.0002, "epoch": 3.6537150647580097, "step": 2680}, {"loss": 1.4478, "grad_norm": 0.6738566160202026, "learning_rate": 0.0002, "epoch": 3.667348329925017, "step": 2690}, {"loss": 1.4642, "grad_norm": 0.7446315288543701, "learning_rate": 0.0002, "epoch": 3.6809815950920246, "step": 2700}, {"loss": 1.4342, "grad_norm": 0.6717571020126343, "learning_rate": 0.0002, "epoch": 3.694614860259032, "step": 2710}, {"loss": 1.4285, "grad_norm": 0.667259693145752, "learning_rate": 0.0002, "epoch": 3.7082481254260395, "step": 2720}, {"loss": 1.5389, "grad_norm": 0.6808622479438782, "learning_rate": 0.0002, "epoch": 3.721881390593047, "step": 2730}, {"loss": 1.4297, "grad_norm": 0.7254287004470825, "learning_rate": 0.0002, "epoch": 3.7355146557600545, "step": 2740}, {"loss": 1.4176, "grad_norm": 0.6864007711410522, "learning_rate": 0.0002, "epoch": 3.749147920927062, "step": 2750}, {"loss": 1.4811, "grad_norm": 0.7041361331939697, "learning_rate": 0.0002, "epoch": 3.7627811860940694, "step": 2760}, {"loss": 1.4284, "grad_norm": 0.6559903025627136, "learning_rate": 0.0002, "epoch": 3.776414451261077, "step": 2770}, {"loss": 1.4608, "grad_norm": 0.6602269411087036, "learning_rate": 0.0002, "epoch": 3.7900477164280844, "step": 2780}, {"loss": 1.4588, "grad_norm": 0.692611813545227, "learning_rate": 0.0002, "epoch": 3.8036809815950923, "step": 2790}, {"loss": 1.4065, "grad_norm": 0.7051475644111633, "learning_rate": 0.0002, "epoch": 3.8173142467620993, "step": 2800}, {"loss": 1.4083, "grad_norm": 0.6685371398925781, "learning_rate": 0.0002, "epoch": 3.830947511929107, "step": 2810}, {"loss": 1.5227, "grad_norm": 0.6706477403640747, "learning_rate": 0.0002, "epoch": 3.8445807770961147, "step": 2820}, {"loss": 1.4076, "grad_norm": 0.6671637296676636, "learning_rate": 0.0002, "epoch": 3.858214042263122, "step": 2830}, {"loss": 1.4736, "grad_norm": 0.694092333316803, "learning_rate": 0.0002, "epoch": 3.8718473074301296, "step": 2840}, {"loss": 1.4161, "grad_norm": 0.7349600195884705, "learning_rate": 0.0002, "epoch": 3.885480572597137, "step": 2850}, {"loss": 1.4617, "grad_norm": 0.6647971868515015, "learning_rate": 0.0002, "epoch": 3.8991138377641446, "step": 2860}, {"loss": 1.5046, "grad_norm": 0.806656539440155, "learning_rate": 0.0002, "epoch": 3.912747102931152, "step": 2870}, {"loss": 1.428, "grad_norm": 0.6008772850036621, "learning_rate": 0.0002, "epoch": 3.9263803680981595, "step": 2880}, {"loss": 1.4116, "grad_norm": 0.659227728843689, "learning_rate": 0.0002, "epoch": 3.940013633265167, "step": 2890}, {"loss": 1.4136, "grad_norm": 0.6357656717300415, "learning_rate": 0.0002, "epoch": 3.9536468984321744, "step": 2900}, {"loss": 1.4655, "grad_norm": 0.6541687846183777, "learning_rate": 0.0002, "epoch": 3.967280163599182, "step": 2910}, {"loss": 1.4854, "grad_norm": 0.6090909838676453, "learning_rate": 0.0002, "epoch": 3.9809134287661894, "step": 2920}, {"loss": 1.4615, "grad_norm": 0.7198411822319031, "learning_rate": 0.0002, "epoch": 3.994546693933197, "step": 2930}, {"eval_loss": 1.9278366565704346, "eval_runtime": 53.6567, "eval_samples_per_second": 9.449, "eval_steps_per_second": 1.193, "epoch": 4.0, "step": 2934}, {"loss": 1.3159, "grad_norm": 0.6498575210571289, "learning_rate": 0.0002, "epoch": 4.008179959100205, "step": 2940}, {"loss": 1.2075, "grad_norm": 0.865602433681488, "learning_rate": 0.0002, "epoch": 4.021813224267212, "step": 2950}, {"loss": 1.1744, "grad_norm": 0.8514999151229858, "learning_rate": 0.0002, "epoch": 4.03544648943422, "step": 2960}, {"loss": 1.1553, "grad_norm": 1.0677322149276733, "learning_rate": 0.0002, "epoch": 4.049079754601227, "step": 2970}, {"loss": 1.1962, "grad_norm": 1.0126488208770752, "learning_rate": 0.0002, "epoch": 4.062713019768235, "step": 2980}, {"loss": 1.1631, "grad_norm": 1.0008870363235474, "learning_rate": 0.0002, "epoch": 4.076346284935242, "step": 2990}, {"loss": 1.2154, "grad_norm": 0.7942054271697998, "learning_rate": 0.0002, "epoch": 4.08997955010225, "step": 3000}, {"loss": 1.214, "grad_norm": 1.0482100248336792, "learning_rate": 0.0002, "epoch": 4.103612815269257, "step": 3010}, {"loss": 1.1999, "grad_norm": 1.0516992807388306, "learning_rate": 0.0002, "epoch": 4.1172460804362645, "step": 3020}, {"loss": 1.2108, "grad_norm": 0.8144322037696838, "learning_rate": 0.0002, "epoch": 4.130879345603272, "step": 3030}, {"loss": 1.1782, "grad_norm": 0.952297568321228, "learning_rate": 0.0002, "epoch": 4.144512610770279, "step": 3040}, {"loss": 1.2814, "grad_norm": 1.007645606994629, "learning_rate": 0.0002, "epoch": 4.158145875937287, "step": 3050}, {"loss": 1.1731, "grad_norm": 1.0480353832244873, "learning_rate": 0.0002, "epoch": 4.171779141104294, "step": 3060}, {"loss": 1.196, "grad_norm": 0.9270663857460022, "learning_rate": 0.0002, "epoch": 4.185412406271302, "step": 3070}, {"loss": 1.2167, "grad_norm": 1.3415262699127197, "learning_rate": 0.0002, "epoch": 4.199045671438309, "step": 3080}, {"loss": 1.2601, "grad_norm": 1.167606234550476, "learning_rate": 0.0002, "epoch": 4.212678936605317, "step": 3090}, {"loss": 1.2605, "grad_norm": 0.9418690800666809, "learning_rate": 0.0002, "epoch": 4.226312201772324, "step": 3100}, {"loss": 1.2184, "grad_norm": 1.0885876417160034, "learning_rate": 0.0002, "epoch": 4.239945466939332, "step": 3110}, {"loss": 1.2594, "grad_norm": 0.9165483713150024, "learning_rate": 0.0002, "epoch": 4.253578732106339, "step": 3120}, {"loss": 1.2933, "grad_norm": 0.9154694080352783, "learning_rate": 0.0002, "epoch": 4.267211997273347, "step": 3130}, {"loss": 1.2584, "grad_norm": 1.100580096244812, "learning_rate": 0.0002, "epoch": 4.280845262440354, "step": 3140}, {"loss": 1.251, "grad_norm": 0.9367576241493225, "learning_rate": 0.0002, "epoch": 4.294478527607362, "step": 3150}, {"loss": 1.2032, "grad_norm": 0.9744015336036682, "learning_rate": 0.0002, "epoch": 4.308111792774369, "step": 3160}, {"loss": 1.2787, "grad_norm": 0.9865175485610962, "learning_rate": 0.0002, "epoch": 4.321745057941377, "step": 3170}, {"loss": 1.2161, "grad_norm": 1.0124907493591309, "learning_rate": 0.0002, "epoch": 4.335378323108385, "step": 3180}, {"loss": 1.2452, "grad_norm": 1.1044819355010986, "learning_rate": 0.0002, "epoch": 4.349011588275392, "step": 3190}, {"loss": 1.2483, "grad_norm": 0.9305577278137207, "learning_rate": 0.0002, "epoch": 4.3626448534424, "step": 3200}, {"loss": 1.2101, "grad_norm": 0.969265341758728, "learning_rate": 0.0002, "epoch": 4.376278118609407, "step": 3210}, {"loss": 1.2355, "grad_norm": 1.0671923160552979, "learning_rate": 0.0002, "epoch": 4.389911383776415, "step": 3220}, {"loss": 1.2259, "grad_norm": 0.9440539479255676, "learning_rate": 0.0002, "epoch": 4.403544648943422, "step": 3230}, {"loss": 1.1706, "grad_norm": 0.9824562668800354, "learning_rate": 0.0002, "epoch": 4.41717791411043, "step": 3240}, {"loss": 1.2234, "grad_norm": 1.0245535373687744, "learning_rate": 0.0002, "epoch": 4.430811179277437, "step": 3250}, {"loss": 1.2713, "grad_norm": 0.9629312753677368, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 3260}, {"loss": 1.2689, "grad_norm": 1.1556470394134521, "learning_rate": 0.0002, "epoch": 4.458077709611452, "step": 3270}, {"loss": 1.2214, "grad_norm": 0.9796679019927979, "learning_rate": 0.0002, "epoch": 4.47171097477846, "step": 3280}, {"loss": 1.2823, "grad_norm": 0.9030535221099854, "learning_rate": 0.0002, "epoch": 4.485344239945467, "step": 3290}, {"loss": 1.2111, "grad_norm": 0.9142820835113525, "learning_rate": 0.0002, "epoch": 4.4989775051124745, "step": 3300}, {"loss": 1.2398, "grad_norm": 0.966867208480835, "learning_rate": 0.0002, "epoch": 4.5126107702794815, "step": 3310}, {"loss": 1.2537, "grad_norm": 1.0127079486846924, "learning_rate": 0.0002, "epoch": 4.5262440354464895, "step": 3320}, {"loss": 1.2059, "grad_norm": 1.055506706237793, "learning_rate": 0.0002, "epoch": 4.539877300613497, "step": 3330}, {"loss": 1.2958, "grad_norm": 0.9831468462944031, "learning_rate": 0.0002, "epoch": 4.553510565780504, "step": 3340}, {"loss": 1.2643, "grad_norm": 0.9304661154747009, "learning_rate": 0.0002, "epoch": 4.567143830947512, "step": 3350}, {"loss": 1.3621, "grad_norm": 0.9369107484817505, "learning_rate": 0.0002, "epoch": 4.580777096114519, "step": 3360}, {"loss": 1.2301, "grad_norm": 1.009506344795227, "learning_rate": 0.0002, "epoch": 4.594410361281527, "step": 3370}, {"loss": 1.2535, "grad_norm": 1.0575741529464722, "learning_rate": 0.0002, "epoch": 4.608043626448534, "step": 3380}, {"loss": 1.1914, "grad_norm": 0.9102860689163208, "learning_rate": 0.0002, "epoch": 4.621676891615542, "step": 3390}, {"loss": 1.3156, "grad_norm": 0.8111315965652466, "learning_rate": 0.0002, "epoch": 4.635310156782549, "step": 3400}, {"loss": 1.3103, "grad_norm": 0.9459649920463562, "learning_rate": 0.0002, "epoch": 4.648943421949557, "step": 3410}, {"loss": 1.3146, "grad_norm": 0.9709545969963074, "learning_rate": 0.0002, "epoch": 4.662576687116564, "step": 3420}, {"loss": 1.2958, "grad_norm": 0.9909247159957886, "learning_rate": 0.0002, "epoch": 4.676209952283572, "step": 3430}, {"loss": 1.3186, "grad_norm": 0.9094610810279846, "learning_rate": 0.0002, "epoch": 4.689843217450579, "step": 3440}, {"loss": 1.3397, "grad_norm": 0.9012220501899719, "learning_rate": 0.0002, "epoch": 4.703476482617587, "step": 3450}, {"loss": 1.2595, "grad_norm": 0.8669242858886719, "learning_rate": 0.0002, "epoch": 4.717109747784594, "step": 3460}, {"loss": 1.2762, "grad_norm": 0.9753699898719788, "learning_rate": 0.0002, "epoch": 4.730743012951602, "step": 3470}, {"loss": 1.2371, "grad_norm": 1.0252684354782104, "learning_rate": 0.0002, "epoch": 4.74437627811861, "step": 3480}, {"loss": 1.2536, "grad_norm": 1.208098292350769, "learning_rate": 0.0002, "epoch": 4.758009543285617, "step": 3490}, {"loss": 1.2256, "grad_norm": 0.8632914423942566, "learning_rate": 0.0002, "epoch": 4.771642808452625, "step": 3500}, {"loss": 1.3062, "grad_norm": 1.0084818601608276, "learning_rate": 0.0002, "epoch": 4.785276073619632, "step": 3510}, {"loss": 1.3004, "grad_norm": 0.9095172882080078, "learning_rate": 0.0002, "epoch": 4.79890933878664, "step": 3520}, {"loss": 1.263, "grad_norm": 0.9740135669708252, "learning_rate": 0.0002, "epoch": 4.812542603953647, "step": 3530}, {"loss": 1.2816, "grad_norm": 0.8862348794937134, "learning_rate": 0.0002, "epoch": 4.826175869120655, "step": 3540}, {"loss": 1.2275, "grad_norm": 1.0761774778366089, "learning_rate": 0.0002, "epoch": 4.839809134287662, "step": 3550}, {"loss": 1.2257, "grad_norm": 1.0134117603302002, "learning_rate": 0.0002, "epoch": 4.85344239945467, "step": 3560}, {"loss": 1.2904, "grad_norm": 0.9262851476669312, "learning_rate": 0.0002, "epoch": 4.867075664621677, "step": 3570}, {"loss": 1.1466, "grad_norm": 0.9518504738807678, "learning_rate": 0.0002, "epoch": 4.8807089297886845, "step": 3580}, {"loss": 1.2741, "grad_norm": 1.10103178024292, "learning_rate": 0.0002, "epoch": 4.894342194955692, "step": 3590}, {"loss": 1.2592, "grad_norm": 1.0133225917816162, "learning_rate": 0.0002, "epoch": 4.9079754601226995, "step": 3600}, {"loss": 1.2856, "grad_norm": 0.9637737274169922, "learning_rate": 0.0002, "epoch": 4.9216087252897065, "step": 3610}, {"loss": 1.2991, "grad_norm": 0.9800633192062378, "learning_rate": 0.0002, "epoch": 4.935241990456714, "step": 3620}, {"loss": 1.2872, "grad_norm": 1.0065973997116089, "learning_rate": 0.0002, "epoch": 4.948875255623722, "step": 3630}, {"loss": 1.2408, "grad_norm": 0.9354690313339233, "learning_rate": 0.0002, "epoch": 4.962508520790729, "step": 3640}, {"loss": 1.291, "grad_norm": 0.9744119048118591, "learning_rate": 0.0002, "epoch": 4.976141785957737, "step": 3650}, {"loss": 1.2513, "grad_norm": 0.9357708096504211, "learning_rate": 0.0002, "epoch": 4.989775051124744, "step": 3660}, {"eval_loss": 2.0763096809387207, "eval_runtime": 53.6578, "eval_samples_per_second": 9.449, "eval_steps_per_second": 1.193, "epoch": 4.999318336741649, "step": 3667}, {"loss": 1.2323, "grad_norm": 1.3171669244766235, "learning_rate": 0.0002, "epoch": 5.003408316291752, "step": 3670}, {"loss": 0.9509, "grad_norm": 1.4427374601364136, "learning_rate": 0.0002, "epoch": 5.017041581458759, "step": 3680}, {"loss": 1.011, "grad_norm": 0.9313797354698181, "learning_rate": 0.0002, "epoch": 5.030674846625767, "step": 3690}, {"loss": 0.9481, "grad_norm": 1.417641282081604, "learning_rate": 0.0002, "epoch": 5.044308111792774, "step": 3700}, {"loss": 0.9477, "grad_norm": 1.097440242767334, "learning_rate": 0.0002, "epoch": 5.057941376959782, "step": 3710}, {"loss": 1.0416, "grad_norm": 1.4277986288070679, "learning_rate": 0.0002, "epoch": 5.071574642126789, "step": 3720}, {"loss": 0.9718, "grad_norm": 1.2520873546600342, "learning_rate": 0.0002, "epoch": 5.085207907293797, "step": 3730}, {"loss": 0.9531, "grad_norm": 1.39503812789917, "learning_rate": 0.0002, "epoch": 5.098841172460804, "step": 3740}, {"loss": 0.9658, "grad_norm": 1.2345329523086548, "learning_rate": 0.0002, "epoch": 5.112474437627812, "step": 3750}, {"loss": 1.0615, "grad_norm": 1.2700239419937134, "learning_rate": 0.0002, "epoch": 5.126107702794819, "step": 3760}, {"loss": 0.993, "grad_norm": 1.5343066453933716, "learning_rate": 0.0002, "epoch": 5.139740967961827, "step": 3770}, {"loss": 0.9378, "grad_norm": 1.4191608428955078, "learning_rate": 0.0002, "epoch": 5.153374233128835, "step": 3780}, {"loss": 1.0179, "grad_norm": 1.4591023921966553, "learning_rate": 0.0002, "epoch": 5.167007498295842, "step": 3790}, {"loss": 1.0143, "grad_norm": 1.6158121824264526, "learning_rate": 0.0002, "epoch": 5.18064076346285, "step": 3800}, {"loss": 1.0056, "grad_norm": 1.6077582836151123, "learning_rate": 0.0002, "epoch": 5.194274028629857, "step": 3810}, {"loss": 0.9711, "grad_norm": 1.2815653085708618, "learning_rate": 0.0002, "epoch": 5.207907293796865, "step": 3820}, {"loss": 1.0131, "grad_norm": 1.2427219152450562, "learning_rate": 0.0002, "epoch": 5.221540558963872, "step": 3830}, {"loss": 0.9901, "grad_norm": 1.3013232946395874, "learning_rate": 0.0002, "epoch": 5.23517382413088, "step": 3840}, {"loss": 0.9862, "grad_norm": 1.4643588066101074, "learning_rate": 0.0002, "epoch": 5.248807089297887, "step": 3850}, {"loss": 1.0149, "grad_norm": 1.2571916580200195, "learning_rate": 0.0002, "epoch": 5.2624403544648946, "step": 3860}, {"loss": 0.9686, "grad_norm": 1.226682186126709, "learning_rate": 0.0002, "epoch": 5.276073619631902, "step": 3870}, {"loss": 0.9417, "grad_norm": 1.2541271448135376, "learning_rate": 0.0002, "epoch": 5.2897068847989095, "step": 3880}, {"loss": 0.9767, "grad_norm": 1.2340261936187744, "learning_rate": 0.0002, "epoch": 5.3033401499659165, "step": 3890}, {"loss": 1.0173, "grad_norm": 1.345527172088623, "learning_rate": 0.0002, "epoch": 5.316973415132924, "step": 3900}, {"loss": 1.0638, "grad_norm": 1.2128909826278687, "learning_rate": 0.0002, "epoch": 5.3306066802999315, "step": 3910}, {"loss": 1.0002, "grad_norm": 1.3052637577056885, "learning_rate": 0.0002, "epoch": 5.344239945466939, "step": 3920}, {"loss": 0.9754, "grad_norm": 1.1017392873764038, "learning_rate": 0.0002, "epoch": 5.357873210633947, "step": 3930}, {"loss": 1.0579, "grad_norm": 1.26950204372406, "learning_rate": 0.0002, "epoch": 5.371506475800954, "step": 3940}, {"loss": 1.0816, "grad_norm": 1.3372546434402466, "learning_rate": 0.0002, "epoch": 5.385139740967962, "step": 3950}, {"loss": 1.0529, "grad_norm": 1.3115156888961792, "learning_rate": 0.0002, "epoch": 5.398773006134969, "step": 3960}, {"loss": 1.1179, "grad_norm": 1.3511474132537842, "learning_rate": 0.0002, "epoch": 5.412406271301977, "step": 3970}, {"loss": 1.0352, "grad_norm": 1.1001893281936646, "learning_rate": 0.0002, "epoch": 5.426039536468984, "step": 3980}, {"loss": 1.0855, "grad_norm": 1.2810745239257812, "learning_rate": 0.0002, "epoch": 5.439672801635992, "step": 3990}, {"loss": 1.0573, "grad_norm": 1.2999306917190552, "learning_rate": 0.0002, "epoch": 5.453306066802999, "step": 4000}, {"loss": 1.0073, "grad_norm": 1.172553300857544, "learning_rate": 0.0002, "epoch": 5.466939331970007, "step": 4010}, {"loss": 1.003, "grad_norm": 1.1483557224273682, "learning_rate": 0.0002, "epoch": 5.480572597137014, "step": 4020}, {"loss": 1.0704, "grad_norm": 1.4148036241531372, "learning_rate": 0.0002, "epoch": 5.494205862304022, "step": 4030}, {"loss": 1.0519, "grad_norm": 1.1611121892929077, "learning_rate": 0.0002, "epoch": 5.507839127471029, "step": 4040}, {"loss": 1.0775, "grad_norm": 1.3837119340896606, "learning_rate": 0.0002, "epoch": 5.521472392638037, "step": 4050}, {"loss": 1.0257, "grad_norm": 1.3025696277618408, "learning_rate": 0.0002, "epoch": 5.535105657805044, "step": 4060}, {"loss": 1.0628, "grad_norm": 1.348091959953308, "learning_rate": 0.0002, "epoch": 5.548738922972052, "step": 4070}, {"loss": 1.0447, "grad_norm": 1.3463449478149414, "learning_rate": 0.0002, "epoch": 5.56237218813906, "step": 4080}, {"loss": 1.039, "grad_norm": 1.3904176950454712, "learning_rate": 0.0002, "epoch": 5.576005453306067, "step": 4090}, {"loss": 1.0963, "grad_norm": 1.2737950086593628, "learning_rate": 0.0002, "epoch": 5.589638718473074, "step": 4100}, {"loss": 1.0441, "grad_norm": 1.3311827182769775, "learning_rate": 0.0002, "epoch": 5.603271983640082, "step": 4110}, {"loss": 1.0521, "grad_norm": 1.24485182762146, "learning_rate": 0.0002, "epoch": 5.61690524880709, "step": 4120}, {"loss": 1.1103, "grad_norm": 1.2724957466125488, "learning_rate": 0.0002, "epoch": 5.630538513974097, "step": 4130}, {"loss": 1.0588, "grad_norm": 1.3439847230911255, "learning_rate": 0.0002, "epoch": 5.644171779141105, "step": 4140}, {"loss": 1.0257, "grad_norm": 1.372359037399292, "learning_rate": 0.0002, "epoch": 5.657805044308112, "step": 4150}, {"loss": 1.0475, "grad_norm": 1.2322949171066284, "learning_rate": 0.0002, "epoch": 5.6714383094751195, "step": 4160}, {"loss": 1.0465, "grad_norm": 1.4859193563461304, "learning_rate": 0.0002, "epoch": 5.6850715746421265, "step": 4170}, {"loss": 1.1569, "grad_norm": 1.4318448305130005, "learning_rate": 0.0002, "epoch": 5.6987048398091344, "step": 4180}, {"loss": 1.017, "grad_norm": 1.1533565521240234, "learning_rate": 0.0002, "epoch": 5.7123381049761415, "step": 4190}, {"loss": 1.0948, "grad_norm": 1.3009696006774902, "learning_rate": 0.0002, "epoch": 5.725971370143149, "step": 4200}, {"loss": 1.1229, "grad_norm": 1.3972162008285522, "learning_rate": 0.0002, "epoch": 5.739604635310156, "step": 4210}, {"loss": 1.033, "grad_norm": 1.2142186164855957, "learning_rate": 0.0002, "epoch": 5.753237900477164, "step": 4220}, {"loss": 1.0588, "grad_norm": 1.401191234588623, "learning_rate": 0.0002, "epoch": 5.766871165644172, "step": 4230}, {"loss": 1.0722, "grad_norm": 1.4124404191970825, "learning_rate": 0.0002, "epoch": 5.780504430811179, "step": 4240}, {"loss": 1.0826, "grad_norm": 1.3488332033157349, "learning_rate": 0.0002, "epoch": 5.794137695978186, "step": 4250}, {"loss": 1.0599, "grad_norm": 1.3671752214431763, "learning_rate": 0.0002, "epoch": 5.807770961145194, "step": 4260}, {"loss": 1.1294, "grad_norm": 1.2608201503753662, "learning_rate": 0.0002, "epoch": 5.821404226312202, "step": 4270}, {"loss": 1.1216, "grad_norm": 1.1814045906066895, "learning_rate": 0.0002, "epoch": 5.835037491479209, "step": 4280}, {"loss": 1.0973, "grad_norm": 1.4139586687088013, "learning_rate": 0.0002, "epoch": 5.848670756646217, "step": 4290}, {"loss": 1.0656, "grad_norm": 1.34248948097229, "learning_rate": 0.0002, "epoch": 5.862304021813224, "step": 4300}, {"loss": 1.0791, "grad_norm": 1.1428139209747314, "learning_rate": 0.0002, "epoch": 5.875937286980232, "step": 4310}, {"loss": 1.0556, "grad_norm": 1.1941087245941162, "learning_rate": 0.0002, "epoch": 5.889570552147239, "step": 4320}, {"loss": 1.1089, "grad_norm": 1.2374001741409302, "learning_rate": 0.0002, "epoch": 5.903203817314247, "step": 4330}, {"loss": 1.0802, "grad_norm": 1.4314988851547241, "learning_rate": 0.0002, "epoch": 5.916837082481254, "step": 4340}, {"loss": 1.133, "grad_norm": 1.1286126375198364, "learning_rate": 0.0002, "epoch": 5.930470347648262, "step": 4350}, {"loss": 1.0807, "grad_norm": 1.25884211063385, "learning_rate": 0.0002, "epoch": 5.944103612815269, "step": 4360}, {"loss": 1.1189, "grad_norm": 1.223357915878296, "learning_rate": 0.0002, "epoch": 5.957736877982277, "step": 4370}, {"loss": 1.1335, "grad_norm": 1.2173810005187988, "learning_rate": 0.0002, "epoch": 5.971370143149285, "step": 4380}, {"loss": 1.1201, "grad_norm": 1.3152292966842651, "learning_rate": 0.0002, "epoch": 5.985003408316292, "step": 4390}, {"loss": 1.1456, "grad_norm": 1.5576739311218262, "learning_rate": 0.0002, "epoch": 5.998636673483299, "step": 4400}]}
+{"epoch": 6.999318336741649, "step": 5134, "epoch_duration": 1094.620125055313, "total_accumulated_duration": 7667.40259718895, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7887.97119140625}, "peak_memory_usage": {"GPU_0": 19996.724609375}, "avg_memory_reserved": {"GPU_0": 28746.0}, "peak_memory_reserved": {"GPU_0": 28746.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733", "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": 3.0982, "grad_norm": 0.7714291214942932, "learning_rate": 0.0002, "epoch": 0.013633265167007498, "step": 10}, {"loss": 2.5206, "grad_norm": 0.5473978519439697, "learning_rate": 0.0002, "epoch": 0.027266530334014997, "step": 20}, {"loss": 2.3079, "grad_norm": 0.5452795624732971, "learning_rate": 0.0002, "epoch": 0.0408997955010225, "step": 30}, {"loss": 2.0019, "grad_norm": 0.5098028779029846, "learning_rate": 0.0002, "epoch": 0.054533060668029994, "step": 40}, {"loss": 1.9333, "grad_norm": 0.48062971234321594, "learning_rate": 0.0002, "epoch": 0.0681663258350375, "step": 50}, {"loss": 1.9355, "grad_norm": 0.4505695104598999, "learning_rate": 0.0002, "epoch": 0.081799591002045, "step": 60}, {"loss": 1.9312, "grad_norm": 0.41609591245651245, "learning_rate": 0.0002, "epoch": 0.09543285616905249, "step": 70}, {"loss": 1.8656, "grad_norm": 0.4323892593383789, "learning_rate": 0.0002, "epoch": 0.10906612133605999, "step": 80}, {"loss": 1.9294, "grad_norm": 0.4670293629169464, "learning_rate": 0.0002, "epoch": 0.12269938650306748, "step": 90}, {"loss": 1.7946, "grad_norm": 0.40623316168785095, "learning_rate": 0.0002, "epoch": 0.136332651670075, "step": 100}, {"loss": 1.8565, "grad_norm": 0.3620383143424988, "learning_rate": 0.0002, "epoch": 0.1499659168370825, "step": 110}, {"loss": 1.9238, "grad_norm": 0.332218736410141, "learning_rate": 0.0002, "epoch": 0.16359918200409, "step": 120}, {"loss": 1.93, "grad_norm": 0.4004521667957306, "learning_rate": 0.0002, "epoch": 0.17723244717109748, "step": 130}, {"loss": 1.7549, "grad_norm": 0.3698360323905945, "learning_rate": 0.0002, "epoch": 0.19086571233810498, "step": 140}, {"loss": 1.8771, "grad_norm": 0.3847949504852295, "learning_rate": 0.0002, "epoch": 0.20449897750511248, "step": 150}, {"loss": 1.8316, "grad_norm": 0.36843451857566833, "learning_rate": 0.0002, "epoch": 0.21813224267211997, "step": 160}, {"loss": 1.838, "grad_norm": 0.37301021814346313, "learning_rate": 0.0002, "epoch": 0.23176550783912747, "step": 170}, {"loss": 1.8909, "grad_norm": 0.3718886971473694, "learning_rate": 0.0002, "epoch": 0.24539877300613497, "step": 180}, {"loss": 1.8454, "grad_norm": 0.3088490962982178, "learning_rate": 0.0002, "epoch": 0.25903203817314246, "step": 190}, {"loss": 1.9254, "grad_norm": 0.3611852526664734, "learning_rate": 0.0002, "epoch": 0.27266530334015, "step": 200}, {"loss": 1.7844, "grad_norm": 0.36093324422836304, "learning_rate": 0.0002, "epoch": 0.28629856850715746, "step": 210}, {"loss": 1.719, "grad_norm": 0.3250400722026825, "learning_rate": 0.0002, "epoch": 0.299931833674165, "step": 220}, {"loss": 1.8729, "grad_norm": 0.3566756248474121, "learning_rate": 0.0002, "epoch": 0.31356509884117245, "step": 230}, {"loss": 1.9259, "grad_norm": 0.32872408628463745, "learning_rate": 0.0002, "epoch": 0.32719836400818, "step": 240}, {"loss": 1.9033, "grad_norm": 0.3983881175518036, "learning_rate": 0.0002, "epoch": 0.34083162917518744, "step": 250}, {"loss": 1.8588, "grad_norm": 0.3571510910987854, "learning_rate": 0.0002, "epoch": 0.35446489434219497, "step": 260}, {"loss": 1.8539, "grad_norm": 0.3036131262779236, "learning_rate": 0.0002, "epoch": 0.36809815950920244, "step": 270}, {"loss": 1.8572, "grad_norm": 0.36512863636016846, "learning_rate": 0.0002, "epoch": 0.38173142467620996, "step": 280}, {"loss": 1.8022, "grad_norm": 0.3429736793041229, "learning_rate": 0.0002, "epoch": 0.39536468984321743, "step": 290}, {"loss": 1.8754, "grad_norm": 0.3055964708328247, "learning_rate": 0.0002, "epoch": 0.40899795501022496, "step": 300}, {"loss": 1.8384, "grad_norm": 0.33801034092903137, "learning_rate": 0.0002, "epoch": 0.4226312201772324, "step": 310}, {"loss": 1.7933, "grad_norm": 0.348783016204834, "learning_rate": 0.0002, "epoch": 0.43626448534423995, "step": 320}, {"loss": 1.8451, "grad_norm": 0.3057514727115631, "learning_rate": 0.0002, "epoch": 0.4498977505112474, "step": 330}, {"loss": 1.8766, "grad_norm": 0.3849763572216034, "learning_rate": 0.0002, "epoch": 0.46353101567825494, "step": 340}, {"loss": 1.8073, "grad_norm": 0.30080053210258484, "learning_rate": 0.0002, "epoch": 0.47716428084526247, "step": 350}, {"loss": 1.8548, "grad_norm": 0.3595106303691864, "learning_rate": 0.0002, "epoch": 0.49079754601226994, "step": 360}, {"loss": 1.8232, "grad_norm": 0.31099820137023926, "learning_rate": 0.0002, "epoch": 0.5044308111792775, "step": 370}, {"loss": 1.7029, "grad_norm": 0.3157978355884552, "learning_rate": 0.0002, "epoch": 0.5180640763462849, "step": 380}, {"loss": 1.8265, "grad_norm": 0.27960965037345886, "learning_rate": 0.0002, "epoch": 0.5316973415132924, "step": 390}, {"loss": 1.7414, "grad_norm": 0.3102385103702545, "learning_rate": 0.0002, "epoch": 0.5453306066803, "step": 400}, {"loss": 1.7461, "grad_norm": 0.32828861474990845, "learning_rate": 0.0002, "epoch": 0.5589638718473074, "step": 410}, {"loss": 1.8165, "grad_norm": 0.29560017585754395, "learning_rate": 0.0002, "epoch": 0.5725971370143149, "step": 420}, {"loss": 1.9455, "grad_norm": 0.33316895365715027, "learning_rate": 0.0002, "epoch": 0.5862304021813224, "step": 430}, {"loss": 1.8241, "grad_norm": 0.30420982837677, "learning_rate": 0.0002, "epoch": 0.59986366734833, "step": 440}, {"loss": 1.7565, "grad_norm": 0.32619214057922363, "learning_rate": 0.0002, "epoch": 0.6134969325153374, "step": 450}, {"loss": 1.7945, "grad_norm": 0.3603750765323639, "learning_rate": 0.0002, "epoch": 0.6271301976823449, "step": 460}, {"loss": 1.7773, "grad_norm": 0.30834096670150757, "learning_rate": 0.0002, "epoch": 0.6407634628493524, "step": 470}, {"loss": 1.8058, "grad_norm": 0.28756365180015564, "learning_rate": 0.0002, "epoch": 0.65439672801636, "step": 480}, {"loss": 1.744, "grad_norm": 0.2878406345844269, "learning_rate": 0.0002, "epoch": 0.6680299931833674, "step": 490}, {"loss": 1.8581, "grad_norm": 0.31329697370529175, "learning_rate": 0.0002, "epoch": 0.6816632583503749, "step": 500}, {"loss": 1.7886, "grad_norm": 0.3405822515487671, "learning_rate": 0.0002, "epoch": 0.6952965235173824, "step": 510}, {"loss": 1.778, "grad_norm": 0.305560827255249, "learning_rate": 0.0002, "epoch": 0.7089297886843899, "step": 520}, {"loss": 1.7592, "grad_norm": 0.2973416745662689, "learning_rate": 0.0002, "epoch": 0.7225630538513974, "step": 530}, {"loss": 1.8223, "grad_norm": 0.327303946018219, "learning_rate": 0.0002, "epoch": 0.7361963190184049, "step": 540}, {"loss": 1.8591, "grad_norm": 0.62595534324646, "learning_rate": 0.0002, "epoch": 0.7498295841854125, "step": 550}, {"loss": 1.7466, "grad_norm": 0.3129784166812897, "learning_rate": 0.0002, "epoch": 0.7634628493524199, "step": 560}, {"loss": 1.8035, "grad_norm": 0.32496583461761475, "learning_rate": 0.0002, "epoch": 0.7770961145194274, "step": 570}, {"loss": 1.7787, "grad_norm": 0.3098868131637573, "learning_rate": 0.0002, "epoch": 0.7907293796864349, "step": 580}, {"loss": 1.7196, "grad_norm": 0.30726853013038635, "learning_rate": 0.0002, "epoch": 0.8043626448534424, "step": 590}, {"loss": 1.7898, "grad_norm": 0.2964220643043518, "learning_rate": 0.0002, "epoch": 0.8179959100204499, "step": 600}, {"loss": 1.8114, "grad_norm": 0.32352274656295776, "learning_rate": 0.0002, "epoch": 0.8316291751874574, "step": 610}, {"loss": 1.811, "grad_norm": 0.2938912510871887, "learning_rate": 0.0002, "epoch": 0.8452624403544649, "step": 620}, {"loss": 1.7727, "grad_norm": 0.295559823513031, "learning_rate": 0.0002, "epoch": 0.8588957055214724, "step": 630}, {"loss": 1.9, "grad_norm": 0.34102028608322144, "learning_rate": 0.0002, "epoch": 0.8725289706884799, "step": 640}, {"loss": 1.8006, "grad_norm": 0.29676181077957153, "learning_rate": 0.0002, "epoch": 0.8861622358554874, "step": 650}, {"loss": 1.8099, "grad_norm": 0.3108902871608734, "learning_rate": 0.0002, "epoch": 0.8997955010224948, "step": 660}, {"loss": 1.7955, "grad_norm": 0.2690821588039398, "learning_rate": 0.0002, "epoch": 0.9134287661895024, "step": 670}, {"loss": 1.7881, "grad_norm": 0.32752540707588196, "learning_rate": 0.0002, "epoch": 0.9270620313565099, "step": 680}, {"loss": 1.7661, "grad_norm": 0.8029476404190063, "learning_rate": 0.0002, "epoch": 0.9406952965235174, "step": 690}, {"loss": 1.7733, "grad_norm": 0.30534422397613525, "learning_rate": 0.0002, "epoch": 0.9543285616905249, "step": 700}, {"loss": 1.7614, "grad_norm": 0.2899954319000244, "learning_rate": 0.0002, "epoch": 0.9679618268575324, "step": 710}, {"loss": 1.7845, "grad_norm": 0.28814372420310974, "learning_rate": 0.0002, "epoch": 0.9815950920245399, "step": 720}, {"loss": 1.8865, "grad_norm": 0.3061596751213074, "learning_rate": 0.0002, "epoch": 0.9952283571915473, "step": 730}, {"eval_loss": 1.8171186447143555, "eval_runtime": 53.6047, "eval_samples_per_second": 9.458, "eval_steps_per_second": 1.194, "epoch": 0.9993183367416496, "step": 733}, {"loss": 1.6202, "grad_norm": 0.3140897750854492, "learning_rate": 0.0002, "epoch": 1.008861622358555, "step": 740}, {"loss": 1.8409, "grad_norm": 0.3346109390258789, "learning_rate": 0.0002, "epoch": 1.0224948875255624, "step": 750}, {"loss": 1.6777, "grad_norm": 0.3582976758480072, "learning_rate": 0.0002, "epoch": 1.0361281526925699, "step": 760}, {"loss": 1.7306, "grad_norm": 0.30408260226249695, "learning_rate": 0.0002, "epoch": 1.0497614178595773, "step": 770}, {"loss": 1.6967, "grad_norm": 0.323585569858551, "learning_rate": 0.0002, "epoch": 1.0633946830265848, "step": 780}, {"loss": 1.768, "grad_norm": 0.3474137783050537, "learning_rate": 0.0002, "epoch": 1.0770279481935923, "step": 790}, {"loss": 1.6895, "grad_norm": 0.35721147060394287, "learning_rate": 0.0002, "epoch": 1.0906612133606, "step": 800}, {"loss": 1.718, "grad_norm": 0.35366931557655334, "learning_rate": 0.0002, "epoch": 1.1042944785276074, "step": 810}, {"loss": 1.6797, "grad_norm": 0.3250770568847656, "learning_rate": 0.0002, "epoch": 1.117927743694615, "step": 820}, {"loss": 1.6383, "grad_norm": 0.3293766379356384, "learning_rate": 0.0002, "epoch": 1.1315610088616224, "step": 830}, {"loss": 1.7353, "grad_norm": 0.3380851745605469, "learning_rate": 0.0002, "epoch": 1.1451942740286298, "step": 840}, {"loss": 1.8236, "grad_norm": 0.32584455609321594, "learning_rate": 0.0002, "epoch": 1.1588275391956373, "step": 850}, {"loss": 1.6681, "grad_norm": 0.45700767636299133, "learning_rate": 0.0002, "epoch": 1.1724608043626448, "step": 860}, {"loss": 1.7494, "grad_norm": 0.30944544076919556, "learning_rate": 0.0002, "epoch": 1.1860940695296525, "step": 870}, {"loss": 1.7426, "grad_norm": 0.3268151581287384, "learning_rate": 0.0002, "epoch": 1.19972733469666, "step": 880}, {"loss": 1.7413, "grad_norm": 0.39972540736198425, "learning_rate": 0.0002, "epoch": 1.2133605998636674, "step": 890}, {"loss": 1.7481, "grad_norm": 0.7890929579734802, "learning_rate": 0.0002, "epoch": 1.2269938650306749, "step": 900}, {"loss": 1.7608, "grad_norm": 0.3439182639122009, "learning_rate": 0.0002, "epoch": 1.2406271301976823, "step": 910}, {"loss": 1.7617, "grad_norm": 0.3986225128173828, "learning_rate": 0.0002, "epoch": 1.2542603953646898, "step": 920}, {"loss": 1.6843, "grad_norm": 0.3514605164527893, "learning_rate": 0.0002, "epoch": 1.2678936605316973, "step": 930}, {"loss": 1.6987, "grad_norm": 0.3682589530944824, "learning_rate": 0.0002, "epoch": 1.2815269256987047, "step": 940}, {"loss": 1.6988, "grad_norm": 0.3618335723876953, "learning_rate": 0.0002, "epoch": 1.2951601908657122, "step": 950}, {"loss": 1.7436, "grad_norm": 0.345700740814209, "learning_rate": 0.0002, "epoch": 1.30879345603272, "step": 960}, {"loss": 1.7336, "grad_norm": 0.3514927923679352, "learning_rate": 0.0002, "epoch": 1.3224267211997274, "step": 970}, {"loss": 1.7704, "grad_norm": 0.365647554397583, "learning_rate": 0.0002, "epoch": 1.3360599863667348, "step": 980}, {"loss": 1.7104, "grad_norm": 0.3407285809516907, "learning_rate": 0.0002, "epoch": 1.3496932515337423, "step": 990}, {"loss": 1.7132, "grad_norm": 0.3785437345504761, "learning_rate": 0.0002, "epoch": 1.3633265167007498, "step": 1000}, {"loss": 1.766, "grad_norm": 0.34746724367141724, "learning_rate": 0.0002, "epoch": 1.3769597818677572, "step": 1010}, {"loss": 1.7252, "grad_norm": 0.362444132566452, "learning_rate": 0.0002, "epoch": 1.390593047034765, "step": 1020}, {"loss": 1.7132, "grad_norm": 0.4424704611301422, "learning_rate": 0.0002, "epoch": 1.4042263122017724, "step": 1030}, {"loss": 1.726, "grad_norm": 0.38722458481788635, "learning_rate": 0.0002, "epoch": 1.4178595773687799, "step": 1040}, {"loss": 1.7955, "grad_norm": 0.36089080572128296, "learning_rate": 0.0002, "epoch": 1.4314928425357873, "step": 1050}, {"loss": 1.6924, "grad_norm": 0.33817124366760254, "learning_rate": 0.0002, "epoch": 1.4451261077027948, "step": 1060}, {"loss": 1.7165, "grad_norm": 0.34334081411361694, "learning_rate": 0.0002, "epoch": 1.4587593728698023, "step": 1070}, {"loss": 1.6999, "grad_norm": 0.3776826858520508, "learning_rate": 0.0002, "epoch": 1.4723926380368098, "step": 1080}, {"loss": 1.7605, "grad_norm": 0.4169026017189026, "learning_rate": 0.0002, "epoch": 1.4860259032038172, "step": 1090}, {"loss": 1.7502, "grad_norm": 0.34898945689201355, "learning_rate": 0.0002, "epoch": 1.4996591683708247, "step": 1100}, {"loss": 1.635, "grad_norm": 0.34223780035972595, "learning_rate": 0.0002, "epoch": 1.5132924335378322, "step": 1110}, {"loss": 1.7248, "grad_norm": 0.3686901032924652, "learning_rate": 0.0002, "epoch": 1.5269256987048399, "step": 1120}, {"loss": 1.7525, "grad_norm": 0.35054415464401245, "learning_rate": 0.0002, "epoch": 1.5405589638718473, "step": 1130}, {"loss": 1.7776, "grad_norm": 0.39496365189552307, "learning_rate": 0.0002, "epoch": 1.5541922290388548, "step": 1140}, {"loss": 1.6574, "grad_norm": 0.35451626777648926, "learning_rate": 0.0002, "epoch": 1.5678254942058623, "step": 1150}, {"loss": 1.7257, "grad_norm": 0.3848083019256592, "learning_rate": 0.0002, "epoch": 1.58145875937287, "step": 1160}, {"loss": 1.7272, "grad_norm": 0.3760537803173065, "learning_rate": 0.0002, "epoch": 1.5950920245398774, "step": 1170}, {"loss": 1.7441, "grad_norm": 0.38981738686561584, "learning_rate": 0.0002, "epoch": 1.6087252897068849, "step": 1180}, {"loss": 1.6951, "grad_norm": 0.36830949783325195, "learning_rate": 0.0002, "epoch": 1.6223585548738924, "step": 1190}, {"loss": 1.6925, "grad_norm": 0.3405892848968506, "learning_rate": 0.0002, "epoch": 1.6359918200408998, "step": 1200}, {"loss": 1.7473, "grad_norm": 0.39027872681617737, "learning_rate": 0.0002, "epoch": 1.6496250852079073, "step": 1210}, {"loss": 1.6792, "grad_norm": 0.3342694044113159, "learning_rate": 0.0002, "epoch": 1.6632583503749148, "step": 1220}, {"loss": 1.7196, "grad_norm": 0.3600076735019684, "learning_rate": 0.0002, "epoch": 1.6768916155419222, "step": 1230}, {"loss": 1.7021, "grad_norm": 0.3625542223453522, "learning_rate": 0.0002, "epoch": 1.6905248807089297, "step": 1240}, {"loss": 1.6772, "grad_norm": 0.32170894742012024, "learning_rate": 0.0002, "epoch": 1.7041581458759372, "step": 1250}, {"loss": 1.7152, "grad_norm": 0.3544139862060547, "learning_rate": 0.0002, "epoch": 1.7177914110429446, "step": 1260}, {"loss": 1.7138, "grad_norm": 0.35113027691841125, "learning_rate": 0.0002, "epoch": 1.7314246762099523, "step": 1270}, {"loss": 1.7095, "grad_norm": 0.3499974310398102, "learning_rate": 0.0002, "epoch": 1.7450579413769598, "step": 1280}, {"loss": 1.7749, "grad_norm": 0.3285157382488251, "learning_rate": 0.0002, "epoch": 1.7586912065439673, "step": 1290}, {"loss": 1.6767, "grad_norm": 0.3701961636543274, "learning_rate": 0.0002, "epoch": 1.7723244717109747, "step": 1300}, {"loss": 1.6282, "grad_norm": 0.3301318287849426, "learning_rate": 0.0002, "epoch": 1.7859577368779824, "step": 1310}, {"loss": 1.7097, "grad_norm": 0.37801554799079895, "learning_rate": 0.0002, "epoch": 1.79959100204499, "step": 1320}, {"loss": 1.7437, "grad_norm": 0.3726748526096344, "learning_rate": 0.0002, "epoch": 1.8132242672119974, "step": 1330}, {"loss": 1.7959, "grad_norm": 0.4059790074825287, "learning_rate": 0.0002, "epoch": 1.8268575323790048, "step": 1340}, {"loss": 1.7739, "grad_norm": 0.35712096095085144, "learning_rate": 0.0002, "epoch": 1.8404907975460123, "step": 1350}, {"loss": 1.6375, "grad_norm": 0.35995328426361084, "learning_rate": 0.0002, "epoch": 1.8541240627130198, "step": 1360}, {"loss": 1.7332, "grad_norm": 0.3679947257041931, "learning_rate": 0.0002, "epoch": 1.8677573278800272, "step": 1370}, {"loss": 1.7587, "grad_norm": 0.39645957946777344, "learning_rate": 0.0002, "epoch": 1.8813905930470347, "step": 1380}, {"loss": 1.6985, "grad_norm": 0.35288700461387634, "learning_rate": 0.0002, "epoch": 1.8950238582140422, "step": 1390}, {"loss": 1.6582, "grad_norm": 0.32579198479652405, "learning_rate": 0.0002, "epoch": 1.9086571233810496, "step": 1400}, {"loss": 1.6948, "grad_norm": 0.3856561779975891, "learning_rate": 0.0002, "epoch": 1.9222903885480571, "step": 1410}, {"loss": 1.668, "grad_norm": 0.39019331336021423, "learning_rate": 0.0002, "epoch": 1.9359236537150648, "step": 1420}, {"loss": 1.7774, "grad_norm": 0.38006502389907837, "learning_rate": 0.0002, "epoch": 1.9495569188820723, "step": 1430}, {"loss": 1.8323, "grad_norm": 0.38100454211235046, "learning_rate": 0.0002, "epoch": 1.9631901840490797, "step": 1440}, {"loss": 1.7298, "grad_norm": 0.3405798673629761, "learning_rate": 0.0002, "epoch": 1.9768234492160872, "step": 1450}, {"loss": 1.7045, "grad_norm": 0.36582913994789124, "learning_rate": 0.0002, "epoch": 1.990456714383095, "step": 1460}, {"eval_loss": 1.8178424835205078, "eval_runtime": 53.6524, "eval_samples_per_second": 9.45, "eval_steps_per_second": 1.193, "epoch": 2.0, "step": 1467}, {"loss": 1.6363, "grad_norm": 0.3626647889614105, "learning_rate": 0.0002, "epoch": 2.0040899795501024, "step": 1470}, {"loss": 1.5354, "grad_norm": 0.40171775221824646, "learning_rate": 0.0002, "epoch": 2.01772324471711, "step": 1480}, {"loss": 1.5566, "grad_norm": 0.5805319547653198, "learning_rate": 0.0002, "epoch": 2.0313565098841173, "step": 1490}, {"loss": 1.546, "grad_norm": 0.41954153776168823, "learning_rate": 0.0002, "epoch": 2.044989775051125, "step": 1500}, {"loss": 1.6158, "grad_norm": 0.47190725803375244, "learning_rate": 0.0002, "epoch": 2.0586230402181322, "step": 1510}, {"loss": 1.5841, "grad_norm": 0.4388456344604492, "learning_rate": 0.0002, "epoch": 2.0722563053851397, "step": 1520}, {"loss": 1.5835, "grad_norm": 2.2171926498413086, "learning_rate": 0.0002, "epoch": 2.085889570552147, "step": 1530}, {"loss": 1.6137, "grad_norm": 0.4314221143722534, "learning_rate": 0.0002, "epoch": 2.0995228357191547, "step": 1540}, {"loss": 1.5511, "grad_norm": 0.4154265522956848, "learning_rate": 0.0002, "epoch": 2.113156100886162, "step": 1550}, {"loss": 1.6323, "grad_norm": 0.5025539994239807, "learning_rate": 0.0002, "epoch": 2.1267893660531696, "step": 1560}, {"loss": 1.5903, "grad_norm": 0.5410493016242981, "learning_rate": 0.0002, "epoch": 2.140422631220177, "step": 1570}, {"loss": 1.507, "grad_norm": 0.4478487968444824, "learning_rate": 0.0002, "epoch": 2.1540558963871845, "step": 1580}, {"loss": 1.5536, "grad_norm": 0.4703652560710907, "learning_rate": 0.0002, "epoch": 2.1676891615541924, "step": 1590}, {"loss": 1.5991, "grad_norm": 0.4555390179157257, "learning_rate": 0.0002, "epoch": 2.1813224267212, "step": 1600}, {"loss": 1.6117, "grad_norm": 0.4877263903617859, "learning_rate": 0.0002, "epoch": 2.1949556918882074, "step": 1610}, {"loss": 1.5928, "grad_norm": 0.48708245158195496, "learning_rate": 0.0002, "epoch": 2.208588957055215, "step": 1620}, {"loss": 1.6106, "grad_norm": 0.47523951530456543, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 1630}, {"loss": 1.6013, "grad_norm": 0.4889199733734131, "learning_rate": 0.0002, "epoch": 2.23585548738923, "step": 1640}, {"loss": 1.6633, "grad_norm": 0.4585252106189728, "learning_rate": 0.0002, "epoch": 2.2494887525562373, "step": 1650}, {"loss": 1.6075, "grad_norm": 0.4764868915081024, "learning_rate": 0.0002, "epoch": 2.2631220177232447, "step": 1660}, {"loss": 1.6427, "grad_norm": 0.5028976202011108, "learning_rate": 0.0002, "epoch": 2.276755282890252, "step": 1670}, {"loss": 1.6258, "grad_norm": 0.46131211519241333, "learning_rate": 0.0002, "epoch": 2.2903885480572597, "step": 1680}, {"loss": 1.654, "grad_norm": 0.5422874689102173, "learning_rate": 0.0002, "epoch": 2.304021813224267, "step": 1690}, {"loss": 1.6331, "grad_norm": 0.47615355253219604, "learning_rate": 0.0002, "epoch": 2.3176550783912746, "step": 1700}, {"loss": 1.642, "grad_norm": 0.48005548119544983, "learning_rate": 0.0002, "epoch": 2.331288343558282, "step": 1710}, {"loss": 1.581, "grad_norm": 0.4387182295322418, "learning_rate": 0.0002, "epoch": 2.3449216087252895, "step": 1720}, {"loss": 1.5612, "grad_norm": 0.4487272799015045, "learning_rate": 0.0002, "epoch": 2.358554873892297, "step": 1730}, {"loss": 1.5089, "grad_norm": 0.5046455264091492, "learning_rate": 0.0002, "epoch": 2.372188139059305, "step": 1740}, {"loss": 1.5769, "grad_norm": 0.4653521180152893, "learning_rate": 0.0002, "epoch": 2.3858214042263124, "step": 1750}, {"loss": 1.6201, "grad_norm": 0.4737723469734192, "learning_rate": 0.0002, "epoch": 2.39945466939332, "step": 1760}, {"loss": 1.5933, "grad_norm": 0.4501931071281433, "learning_rate": 0.0002, "epoch": 2.4130879345603273, "step": 1770}, {"loss": 1.6321, "grad_norm": 0.4772880971431732, "learning_rate": 0.0002, "epoch": 2.426721199727335, "step": 1780}, {"loss": 1.5454, "grad_norm": 0.4544616937637329, "learning_rate": 0.0002, "epoch": 2.4403544648943423, "step": 1790}, {"loss": 1.5501, "grad_norm": 0.488313227891922, "learning_rate": 0.0002, "epoch": 2.4539877300613497, "step": 1800}, {"loss": 1.5791, "grad_norm": 0.5057830214500427, "learning_rate": 0.0002, "epoch": 2.467620995228357, "step": 1810}, {"loss": 1.5645, "grad_norm": 0.5049484968185425, "learning_rate": 0.0002, "epoch": 2.4812542603953647, "step": 1820}, {"loss": 1.6268, "grad_norm": 0.44966644048690796, "learning_rate": 0.0002, "epoch": 2.494887525562372, "step": 1830}, {"loss": 1.5941, "grad_norm": 0.5072630643844604, "learning_rate": 0.0002, "epoch": 2.5085207907293796, "step": 1840}, {"loss": 1.5251, "grad_norm": 0.43989792466163635, "learning_rate": 0.0002, "epoch": 2.522154055896387, "step": 1850}, {"loss": 1.563, "grad_norm": 1.3504403829574585, "learning_rate": 0.0002, "epoch": 2.5357873210633946, "step": 1860}, {"loss": 1.5681, "grad_norm": 0.46545976400375366, "learning_rate": 0.0002, "epoch": 2.549420586230402, "step": 1870}, {"loss": 1.6368, "grad_norm": 0.4678342044353485, "learning_rate": 0.0002, "epoch": 2.5630538513974095, "step": 1880}, {"loss": 1.5814, "grad_norm": 0.529755711555481, "learning_rate": 0.0002, "epoch": 2.5766871165644174, "step": 1890}, {"loss": 1.5861, "grad_norm": 0.5000199675559998, "learning_rate": 0.0002, "epoch": 2.5903203817314244, "step": 1900}, {"loss": 1.6346, "grad_norm": 0.5649300217628479, "learning_rate": 0.0002, "epoch": 2.6039536468984323, "step": 1910}, {"loss": 1.6317, "grad_norm": 0.7920585870742798, "learning_rate": 0.0002, "epoch": 2.61758691206544, "step": 1920}, {"loss": 1.643, "grad_norm": 0.4960342049598694, "learning_rate": 0.0002, "epoch": 2.6312201772324473, "step": 1930}, {"loss": 1.6099, "grad_norm": 0.5324710011482239, "learning_rate": 0.0002, "epoch": 2.6448534423994547, "step": 1940}, {"loss": 1.5874, "grad_norm": 0.606343150138855, "learning_rate": 0.0002, "epoch": 2.658486707566462, "step": 1950}, {"loss": 1.5728, "grad_norm": 0.53038489818573, "learning_rate": 0.0002, "epoch": 2.6721199727334697, "step": 1960}, {"loss": 1.5583, "grad_norm": 0.4579465091228485, "learning_rate": 0.0002, "epoch": 2.685753237900477, "step": 1970}, {"loss": 1.6093, "grad_norm": 0.4541707932949066, "learning_rate": 0.0002, "epoch": 2.6993865030674846, "step": 1980}, {"loss": 1.5316, "grad_norm": 0.5009395480155945, "learning_rate": 0.0002, "epoch": 2.713019768234492, "step": 1990}, {"loss": 1.6724, "grad_norm": 0.4723006784915924, "learning_rate": 0.0002, "epoch": 2.7266530334014996, "step": 2000}, {"loss": 1.638, "grad_norm": 0.5086126923561096, "learning_rate": 0.0002, "epoch": 2.740286298568507, "step": 2010}, {"loss": 1.6223, "grad_norm": 0.47242608666419983, "learning_rate": 0.0002, "epoch": 2.7539195637355145, "step": 2020}, {"loss": 1.6242, "grad_norm": 0.44922566413879395, "learning_rate": 0.0002, "epoch": 2.767552828902522, "step": 2030}, {"loss": 1.6837, "grad_norm": 0.420259565114975, "learning_rate": 0.0002, "epoch": 2.78118609406953, "step": 2040}, {"loss": 1.5612, "grad_norm": 0.4762881100177765, "learning_rate": 0.0002, "epoch": 2.794819359236537, "step": 2050}, {"loss": 1.5506, "grad_norm": 0.5228786468505859, "learning_rate": 0.0002, "epoch": 2.808452624403545, "step": 2060}, {"loss": 1.6347, "grad_norm": 0.4796035587787628, "learning_rate": 0.0002, "epoch": 2.8220858895705523, "step": 2070}, {"loss": 1.6843, "grad_norm": 0.5034735202789307, "learning_rate": 0.0002, "epoch": 2.8357191547375598, "step": 2080}, {"loss": 1.6455, "grad_norm": 0.48005399107933044, "learning_rate": 0.0002, "epoch": 2.8493524199045672, "step": 2090}, {"loss": 1.6287, "grad_norm": 0.578820526599884, "learning_rate": 0.0002, "epoch": 2.8629856850715747, "step": 2100}, {"loss": 1.6021, "grad_norm": 0.48982638120651245, "learning_rate": 0.0002, "epoch": 2.876618950238582, "step": 2110}, {"loss": 1.5769, "grad_norm": 0.5157325863838196, "learning_rate": 0.0002, "epoch": 2.8902522154055896, "step": 2120}, {"loss": 1.6089, "grad_norm": 0.49149683117866516, "learning_rate": 0.0002, "epoch": 2.903885480572597, "step": 2130}, {"loss": 1.5881, "grad_norm": 0.48584499955177307, "learning_rate": 0.0002, "epoch": 2.9175187457396046, "step": 2140}, {"loss": 1.5833, "grad_norm": 0.5199017524719238, "learning_rate": 0.0002, "epoch": 2.931152010906612, "step": 2150}, {"loss": 1.7344, "grad_norm": 0.5788236856460571, "learning_rate": 0.0002, "epoch": 2.9447852760736195, "step": 2160}, {"loss": 1.6103, "grad_norm": 0.48664185404777527, "learning_rate": 0.0002, "epoch": 2.958418541240627, "step": 2170}, {"loss": 1.5765, "grad_norm": 0.5026682615280151, "learning_rate": 0.0002, "epoch": 2.9720518064076344, "step": 2180}, {"loss": 1.6626, "grad_norm": 0.49317044019699097, "learning_rate": 0.0002, "epoch": 2.9856850715746424, "step": 2190}, {"loss": 1.5871, "grad_norm": 0.5729128122329712, "learning_rate": 0.0002, "epoch": 2.9993183367416494, "step": 2200}, {"eval_loss": 1.8527295589447021, "eval_runtime": 53.6403, "eval_samples_per_second": 9.452, "eval_steps_per_second": 1.193, "epoch": 2.9993183367416494, "step": 2200}, {"loss": 1.4719, "grad_norm": 0.5530241131782532, "learning_rate": 0.0002, "epoch": 3.0129516019086573, "step": 2210}, {"loss": 1.4088, "grad_norm": 0.6642216444015503, "learning_rate": 0.0002, "epoch": 3.0265848670756648, "step": 2220}, {"loss": 1.4382, "grad_norm": 0.61470627784729, "learning_rate": 0.0002, "epoch": 3.0402181322426722, "step": 2230}, {"loss": 1.4634, "grad_norm": 0.8559566140174866, "learning_rate": 0.0002, "epoch": 3.0538513974096797, "step": 2240}, {"loss": 1.3854, "grad_norm": 0.7015801668167114, "learning_rate": 0.0002, "epoch": 3.067484662576687, "step": 2250}, {"loss": 1.4981, "grad_norm": 0.7226442694664001, "learning_rate": 0.0002, "epoch": 3.0811179277436946, "step": 2260}, {"loss": 1.4143, "grad_norm": 0.7560588717460632, "learning_rate": 0.0002, "epoch": 3.094751192910702, "step": 2270}, {"loss": 1.4395, "grad_norm": 0.6216568946838379, "learning_rate": 0.0002, "epoch": 3.1083844580777096, "step": 2280}, {"loss": 1.3842, "grad_norm": 0.6768500804901123, "learning_rate": 0.0002, "epoch": 3.122017723244717, "step": 2290}, {"loss": 1.4672, "grad_norm": 0.7028762102127075, "learning_rate": 0.0002, "epoch": 3.1356509884117245, "step": 2300}, {"loss": 1.3826, "grad_norm": 0.6329697966575623, "learning_rate": 0.0002, "epoch": 3.149284253578732, "step": 2310}, {"loss": 1.442, "grad_norm": 0.6328264474868774, "learning_rate": 0.0002, "epoch": 3.1629175187457395, "step": 2320}, {"loss": 1.3762, "grad_norm": 0.7573632001876831, "learning_rate": 0.0002, "epoch": 3.176550783912747, "step": 2330}, {"loss": 1.3553, "grad_norm": 0.595740795135498, "learning_rate": 0.0002, "epoch": 3.190184049079755, "step": 2340}, {"loss": 1.3953, "grad_norm": 0.7111806869506836, "learning_rate": 0.0002, "epoch": 3.2038173142467623, "step": 2350}, {"loss": 1.3797, "grad_norm": 0.6328730583190918, "learning_rate": 0.0002, "epoch": 3.2174505794137698, "step": 2360}, {"loss": 1.3855, "grad_norm": 0.5860254168510437, "learning_rate": 0.0002, "epoch": 3.2310838445807772, "step": 2370}, {"loss": 1.4267, "grad_norm": 0.7387157082557678, "learning_rate": 0.0002, "epoch": 3.2447171097477847, "step": 2380}, {"loss": 1.4837, "grad_norm": 0.6897673606872559, "learning_rate": 0.0002, "epoch": 3.258350374914792, "step": 2390}, {"loss": 1.4372, "grad_norm": 0.7157699465751648, "learning_rate": 0.0002, "epoch": 3.2719836400817996, "step": 2400}, {"loss": 1.4432, "grad_norm": 0.6422511339187622, "learning_rate": 0.0002, "epoch": 3.285616905248807, "step": 2410}, {"loss": 1.4828, "grad_norm": 1.0481886863708496, "learning_rate": 0.0002, "epoch": 3.2992501704158146, "step": 2420}, {"loss": 1.4473, "grad_norm": 0.7050786018371582, "learning_rate": 0.0002, "epoch": 3.312883435582822, "step": 2430}, {"loss": 1.3465, "grad_norm": 0.6090759038925171, "learning_rate": 0.0002, "epoch": 3.3265167007498295, "step": 2440}, {"loss": 1.4619, "grad_norm": 0.6626465320587158, "learning_rate": 0.0002, "epoch": 3.340149965916837, "step": 2450}, {"loss": 1.4512, "grad_norm": 0.6565486788749695, "learning_rate": 0.0002, "epoch": 3.3537832310838445, "step": 2460}, {"loss": 1.588, "grad_norm": 0.6449528932571411, "learning_rate": 0.0002, "epoch": 3.367416496250852, "step": 2470}, {"loss": 1.4773, "grad_norm": 0.7746227383613586, "learning_rate": 0.0002, "epoch": 3.3810497614178594, "step": 2480}, {"loss": 1.417, "grad_norm": 0.7074846029281616, "learning_rate": 0.0002, "epoch": 3.3946830265848673, "step": 2490}, {"loss": 1.4476, "grad_norm": 0.6547690033912659, "learning_rate": 0.0002, "epoch": 3.4083162917518743, "step": 2500}, {"loss": 1.4074, "grad_norm": 0.784721314907074, "learning_rate": 0.0002, "epoch": 3.4219495569188823, "step": 2510}, {"loss": 1.4326, "grad_norm": 0.7270277738571167, "learning_rate": 0.0002, "epoch": 3.4355828220858897, "step": 2520}, {"loss": 1.4354, "grad_norm": 0.67588871717453, "learning_rate": 0.0002, "epoch": 3.449216087252897, "step": 2530}, {"loss": 1.4074, "grad_norm": 0.6768023371696472, "learning_rate": 0.0002, "epoch": 3.4628493524199047, "step": 2540}, {"loss": 1.4863, "grad_norm": 0.7026481628417969, "learning_rate": 0.0002, "epoch": 3.476482617586912, "step": 2550}, {"loss": 1.468, "grad_norm": 0.646075963973999, "learning_rate": 0.0002, "epoch": 3.4901158827539196, "step": 2560}, {"loss": 1.4058, "grad_norm": 0.6288973689079285, "learning_rate": 0.0002, "epoch": 3.503749147920927, "step": 2570}, {"loss": 1.4613, "grad_norm": 0.6440825462341309, "learning_rate": 0.0002, "epoch": 3.5173824130879345, "step": 2580}, {"loss": 1.3808, "grad_norm": 0.7074111700057983, "learning_rate": 0.0002, "epoch": 3.531015678254942, "step": 2590}, {"loss": 1.4901, "grad_norm": 0.7007562518119812, "learning_rate": 0.0002, "epoch": 3.5446489434219495, "step": 2600}, {"loss": 1.4511, "grad_norm": 0.6045376658439636, "learning_rate": 0.0002, "epoch": 3.558282208588957, "step": 2610}, {"loss": 1.4596, "grad_norm": 0.9149952530860901, "learning_rate": 0.0002, "epoch": 3.5719154737559644, "step": 2620}, {"loss": 1.4355, "grad_norm": 0.6490362882614136, "learning_rate": 0.0002, "epoch": 3.585548738922972, "step": 2630}, {"loss": 1.4107, "grad_norm": 0.6552226543426514, "learning_rate": 0.0002, "epoch": 3.59918200408998, "step": 2640}, {"loss": 1.433, "grad_norm": 0.6541850566864014, "learning_rate": 0.0002, "epoch": 3.612815269256987, "step": 2650}, {"loss": 1.4279, "grad_norm": 0.6500770449638367, "learning_rate": 0.0002, "epoch": 3.6264485344239947, "step": 2660}, {"loss": 1.3929, "grad_norm": 0.6345893740653992, "learning_rate": 0.0002, "epoch": 3.640081799591002, "step": 2670}, {"loss": 1.3634, "grad_norm": 0.6382275223731995, "learning_rate": 0.0002, "epoch": 3.6537150647580097, "step": 2680}, {"loss": 1.4478, "grad_norm": 0.6738566160202026, "learning_rate": 0.0002, "epoch": 3.667348329925017, "step": 2690}, {"loss": 1.4642, "grad_norm": 0.7446315288543701, "learning_rate": 0.0002, "epoch": 3.6809815950920246, "step": 2700}, {"loss": 1.4342, "grad_norm": 0.6717571020126343, "learning_rate": 0.0002, "epoch": 3.694614860259032, "step": 2710}, {"loss": 1.4285, "grad_norm": 0.667259693145752, "learning_rate": 0.0002, "epoch": 3.7082481254260395, "step": 2720}, {"loss": 1.5389, "grad_norm": 0.6808622479438782, "learning_rate": 0.0002, "epoch": 3.721881390593047, "step": 2730}, {"loss": 1.4297, "grad_norm": 0.7254287004470825, "learning_rate": 0.0002, "epoch": 3.7355146557600545, "step": 2740}, {"loss": 1.4176, "grad_norm": 0.6864007711410522, "learning_rate": 0.0002, "epoch": 3.749147920927062, "step": 2750}, {"loss": 1.4811, "grad_norm": 0.7041361331939697, "learning_rate": 0.0002, "epoch": 3.7627811860940694, "step": 2760}, {"loss": 1.4284, "grad_norm": 0.6559903025627136, "learning_rate": 0.0002, "epoch": 3.776414451261077, "step": 2770}, {"loss": 1.4608, "grad_norm": 0.6602269411087036, "learning_rate": 0.0002, "epoch": 3.7900477164280844, "step": 2780}, {"loss": 1.4588, "grad_norm": 0.692611813545227, "learning_rate": 0.0002, "epoch": 3.8036809815950923, "step": 2790}, {"loss": 1.4065, "grad_norm": 0.7051475644111633, "learning_rate": 0.0002, "epoch": 3.8173142467620993, "step": 2800}, {"loss": 1.4083, "grad_norm": 0.6685371398925781, "learning_rate": 0.0002, "epoch": 3.830947511929107, "step": 2810}, {"loss": 1.5227, "grad_norm": 0.6706477403640747, "learning_rate": 0.0002, "epoch": 3.8445807770961147, "step": 2820}, {"loss": 1.4076, "grad_norm": 0.6671637296676636, "learning_rate": 0.0002, "epoch": 3.858214042263122, "step": 2830}, {"loss": 1.4736, "grad_norm": 0.694092333316803, "learning_rate": 0.0002, "epoch": 3.8718473074301296, "step": 2840}, {"loss": 1.4161, "grad_norm": 0.7349600195884705, "learning_rate": 0.0002, "epoch": 3.885480572597137, "step": 2850}, {"loss": 1.4617, "grad_norm": 0.6647971868515015, "learning_rate": 0.0002, "epoch": 3.8991138377641446, "step": 2860}, {"loss": 1.5046, "grad_norm": 0.806656539440155, "learning_rate": 0.0002, "epoch": 3.912747102931152, "step": 2870}, {"loss": 1.428, "grad_norm": 0.6008772850036621, "learning_rate": 0.0002, "epoch": 3.9263803680981595, "step": 2880}, {"loss": 1.4116, "grad_norm": 0.659227728843689, "learning_rate": 0.0002, "epoch": 3.940013633265167, "step": 2890}, {"loss": 1.4136, "grad_norm": 0.6357656717300415, "learning_rate": 0.0002, "epoch": 3.9536468984321744, "step": 2900}, {"loss": 1.4655, "grad_norm": 0.6541687846183777, "learning_rate": 0.0002, "epoch": 3.967280163599182, "step": 2910}, {"loss": 1.4854, "grad_norm": 0.6090909838676453, "learning_rate": 0.0002, "epoch": 3.9809134287661894, "step": 2920}, {"loss": 1.4615, "grad_norm": 0.7198411822319031, "learning_rate": 0.0002, "epoch": 3.994546693933197, "step": 2930}, {"eval_loss": 1.9278366565704346, "eval_runtime": 53.6567, "eval_samples_per_second": 9.449, "eval_steps_per_second": 1.193, "epoch": 4.0, "step": 2934}, {"loss": 1.3159, "grad_norm": 0.6498575210571289, "learning_rate": 0.0002, "epoch": 4.008179959100205, "step": 2940}, {"loss": 1.2075, "grad_norm": 0.865602433681488, "learning_rate": 0.0002, "epoch": 4.021813224267212, "step": 2950}, {"loss": 1.1744, "grad_norm": 0.8514999151229858, "learning_rate": 0.0002, "epoch": 4.03544648943422, "step": 2960}, {"loss": 1.1553, "grad_norm": 1.0677322149276733, "learning_rate": 0.0002, "epoch": 4.049079754601227, "step": 2970}, {"loss": 1.1962, "grad_norm": 1.0126488208770752, "learning_rate": 0.0002, "epoch": 4.062713019768235, "step": 2980}, {"loss": 1.1631, "grad_norm": 1.0008870363235474, "learning_rate": 0.0002, "epoch": 4.076346284935242, "step": 2990}, {"loss": 1.2154, "grad_norm": 0.7942054271697998, "learning_rate": 0.0002, "epoch": 4.08997955010225, "step": 3000}, {"loss": 1.214, "grad_norm": 1.0482100248336792, "learning_rate": 0.0002, "epoch": 4.103612815269257, "step": 3010}, {"loss": 1.1999, "grad_norm": 1.0516992807388306, "learning_rate": 0.0002, "epoch": 4.1172460804362645, "step": 3020}, {"loss": 1.2108, "grad_norm": 0.8144322037696838, "learning_rate": 0.0002, "epoch": 4.130879345603272, "step": 3030}, {"loss": 1.1782, "grad_norm": 0.952297568321228, "learning_rate": 0.0002, "epoch": 4.144512610770279, "step": 3040}, {"loss": 1.2814, "grad_norm": 1.007645606994629, "learning_rate": 0.0002, "epoch": 4.158145875937287, "step": 3050}, {"loss": 1.1731, "grad_norm": 1.0480353832244873, "learning_rate": 0.0002, "epoch": 4.171779141104294, "step": 3060}, {"loss": 1.196, "grad_norm": 0.9270663857460022, "learning_rate": 0.0002, "epoch": 4.185412406271302, "step": 3070}, {"loss": 1.2167, "grad_norm": 1.3415262699127197, "learning_rate": 0.0002, "epoch": 4.199045671438309, "step": 3080}, {"loss": 1.2601, "grad_norm": 1.167606234550476, "learning_rate": 0.0002, "epoch": 4.212678936605317, "step": 3090}, {"loss": 1.2605, "grad_norm": 0.9418690800666809, "learning_rate": 0.0002, "epoch": 4.226312201772324, "step": 3100}, {"loss": 1.2184, "grad_norm": 1.0885876417160034, "learning_rate": 0.0002, "epoch": 4.239945466939332, "step": 3110}, {"loss": 1.2594, "grad_norm": 0.9165483713150024, "learning_rate": 0.0002, "epoch": 4.253578732106339, "step": 3120}, {"loss": 1.2933, "grad_norm": 0.9154694080352783, "learning_rate": 0.0002, "epoch": 4.267211997273347, "step": 3130}, {"loss": 1.2584, "grad_norm": 1.100580096244812, "learning_rate": 0.0002, "epoch": 4.280845262440354, "step": 3140}, {"loss": 1.251, "grad_norm": 0.9367576241493225, "learning_rate": 0.0002, "epoch": 4.294478527607362, "step": 3150}, {"loss": 1.2032, "grad_norm": 0.9744015336036682, "learning_rate": 0.0002, "epoch": 4.308111792774369, "step": 3160}, {"loss": 1.2787, "grad_norm": 0.9865175485610962, "learning_rate": 0.0002, "epoch": 4.321745057941377, "step": 3170}, {"loss": 1.2161, "grad_norm": 1.0124907493591309, "learning_rate": 0.0002, "epoch": 4.335378323108385, "step": 3180}, {"loss": 1.2452, "grad_norm": 1.1044819355010986, "learning_rate": 0.0002, "epoch": 4.349011588275392, "step": 3190}, {"loss": 1.2483, "grad_norm": 0.9305577278137207, "learning_rate": 0.0002, "epoch": 4.3626448534424, "step": 3200}, {"loss": 1.2101, "grad_norm": 0.969265341758728, "learning_rate": 0.0002, "epoch": 4.376278118609407, "step": 3210}, {"loss": 1.2355, "grad_norm": 1.0671923160552979, "learning_rate": 0.0002, "epoch": 4.389911383776415, "step": 3220}, {"loss": 1.2259, "grad_norm": 0.9440539479255676, "learning_rate": 0.0002, "epoch": 4.403544648943422, "step": 3230}, {"loss": 1.1706, "grad_norm": 0.9824562668800354, "learning_rate": 0.0002, "epoch": 4.41717791411043, "step": 3240}, {"loss": 1.2234, "grad_norm": 1.0245535373687744, "learning_rate": 0.0002, "epoch": 4.430811179277437, "step": 3250}, {"loss": 1.2713, "grad_norm": 0.9629312753677368, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 3260}, {"loss": 1.2689, "grad_norm": 1.1556470394134521, "learning_rate": 0.0002, "epoch": 4.458077709611452, "step": 3270}, {"loss": 1.2214, "grad_norm": 0.9796679019927979, "learning_rate": 0.0002, "epoch": 4.47171097477846, "step": 3280}, {"loss": 1.2823, "grad_norm": 0.9030535221099854, "learning_rate": 0.0002, "epoch": 4.485344239945467, "step": 3290}, {"loss": 1.2111, "grad_norm": 0.9142820835113525, "learning_rate": 0.0002, "epoch": 4.4989775051124745, "step": 3300}, {"loss": 1.2398, "grad_norm": 0.966867208480835, "learning_rate": 0.0002, "epoch": 4.5126107702794815, "step": 3310}, {"loss": 1.2537, "grad_norm": 1.0127079486846924, "learning_rate": 0.0002, "epoch": 4.5262440354464895, "step": 3320}, {"loss": 1.2059, "grad_norm": 1.055506706237793, "learning_rate": 0.0002, "epoch": 4.539877300613497, "step": 3330}, {"loss": 1.2958, "grad_norm": 0.9831468462944031, "learning_rate": 0.0002, "epoch": 4.553510565780504, "step": 3340}, {"loss": 1.2643, "grad_norm": 0.9304661154747009, "learning_rate": 0.0002, "epoch": 4.567143830947512, "step": 3350}, {"loss": 1.3621, "grad_norm": 0.9369107484817505, "learning_rate": 0.0002, "epoch": 4.580777096114519, "step": 3360}, {"loss": 1.2301, "grad_norm": 1.009506344795227, "learning_rate": 0.0002, "epoch": 4.594410361281527, "step": 3370}, {"loss": 1.2535, "grad_norm": 1.0575741529464722, "learning_rate": 0.0002, "epoch": 4.608043626448534, "step": 3380}, {"loss": 1.1914, "grad_norm": 0.9102860689163208, "learning_rate": 0.0002, "epoch": 4.621676891615542, "step": 3390}, {"loss": 1.3156, "grad_norm": 0.8111315965652466, "learning_rate": 0.0002, "epoch": 4.635310156782549, "step": 3400}, {"loss": 1.3103, "grad_norm": 0.9459649920463562, "learning_rate": 0.0002, "epoch": 4.648943421949557, "step": 3410}, {"loss": 1.3146, "grad_norm": 0.9709545969963074, "learning_rate": 0.0002, "epoch": 4.662576687116564, "step": 3420}, {"loss": 1.2958, "grad_norm": 0.9909247159957886, "learning_rate": 0.0002, "epoch": 4.676209952283572, "step": 3430}, {"loss": 1.3186, "grad_norm": 0.9094610810279846, "learning_rate": 0.0002, "epoch": 4.689843217450579, "step": 3440}, {"loss": 1.3397, "grad_norm": 0.9012220501899719, "learning_rate": 0.0002, "epoch": 4.703476482617587, "step": 3450}, {"loss": 1.2595, "grad_norm": 0.8669242858886719, "learning_rate": 0.0002, "epoch": 4.717109747784594, "step": 3460}, {"loss": 1.2762, "grad_norm": 0.9753699898719788, "learning_rate": 0.0002, "epoch": 4.730743012951602, "step": 3470}, {"loss": 1.2371, "grad_norm": 1.0252684354782104, "learning_rate": 0.0002, "epoch": 4.74437627811861, "step": 3480}, {"loss": 1.2536, "grad_norm": 1.208098292350769, "learning_rate": 0.0002, "epoch": 4.758009543285617, "step": 3490}, {"loss": 1.2256, "grad_norm": 0.8632914423942566, "learning_rate": 0.0002, "epoch": 4.771642808452625, "step": 3500}, {"loss": 1.3062, "grad_norm": 1.0084818601608276, "learning_rate": 0.0002, "epoch": 4.785276073619632, "step": 3510}, {"loss": 1.3004, "grad_norm": 0.9095172882080078, "learning_rate": 0.0002, "epoch": 4.79890933878664, "step": 3520}, {"loss": 1.263, "grad_norm": 0.9740135669708252, "learning_rate": 0.0002, "epoch": 4.812542603953647, "step": 3530}, {"loss": 1.2816, "grad_norm": 0.8862348794937134, "learning_rate": 0.0002, "epoch": 4.826175869120655, "step": 3540}, {"loss": 1.2275, "grad_norm": 1.0761774778366089, "learning_rate": 0.0002, "epoch": 4.839809134287662, "step": 3550}, {"loss": 1.2257, "grad_norm": 1.0134117603302002, "learning_rate": 0.0002, "epoch": 4.85344239945467, "step": 3560}, {"loss": 1.2904, "grad_norm": 0.9262851476669312, "learning_rate": 0.0002, "epoch": 4.867075664621677, "step": 3570}, {"loss": 1.1466, "grad_norm": 0.9518504738807678, "learning_rate": 0.0002, "epoch": 4.8807089297886845, "step": 3580}, {"loss": 1.2741, "grad_norm": 1.10103178024292, "learning_rate": 0.0002, "epoch": 4.894342194955692, "step": 3590}, {"loss": 1.2592, "grad_norm": 1.0133225917816162, "learning_rate": 0.0002, "epoch": 4.9079754601226995, "step": 3600}, {"loss": 1.2856, "grad_norm": 0.9637737274169922, "learning_rate": 0.0002, "epoch": 4.9216087252897065, "step": 3610}, {"loss": 1.2991, "grad_norm": 0.9800633192062378, "learning_rate": 0.0002, "epoch": 4.935241990456714, "step": 3620}, {"loss": 1.2872, "grad_norm": 1.0065973997116089, "learning_rate": 0.0002, "epoch": 4.948875255623722, "step": 3630}, {"loss": 1.2408, "grad_norm": 0.9354690313339233, "learning_rate": 0.0002, "epoch": 4.962508520790729, "step": 3640}, {"loss": 1.291, "grad_norm": 0.9744119048118591, "learning_rate": 0.0002, "epoch": 4.976141785957737, "step": 3650}, {"loss": 1.2513, "grad_norm": 0.9357708096504211, "learning_rate": 0.0002, "epoch": 4.989775051124744, "step": 3660}, {"eval_loss": 2.0763096809387207, "eval_runtime": 53.6578, "eval_samples_per_second": 9.449, "eval_steps_per_second": 1.193, "epoch": 4.999318336741649, "step": 3667}, {"loss": 1.2323, "grad_norm": 1.3171669244766235, "learning_rate": 0.0002, "epoch": 5.003408316291752, "step": 3670}, {"loss": 0.9509, "grad_norm": 1.4427374601364136, "learning_rate": 0.0002, "epoch": 5.017041581458759, "step": 3680}, {"loss": 1.011, "grad_norm": 0.9313797354698181, "learning_rate": 0.0002, "epoch": 5.030674846625767, "step": 3690}, {"loss": 0.9481, "grad_norm": 1.417641282081604, "learning_rate": 0.0002, "epoch": 5.044308111792774, "step": 3700}, {"loss": 0.9477, "grad_norm": 1.097440242767334, "learning_rate": 0.0002, "epoch": 5.057941376959782, "step": 3710}, {"loss": 1.0416, "grad_norm": 1.4277986288070679, "learning_rate": 0.0002, "epoch": 5.071574642126789, "step": 3720}, {"loss": 0.9718, "grad_norm": 1.2520873546600342, "learning_rate": 0.0002, "epoch": 5.085207907293797, "step": 3730}, {"loss": 0.9531, "grad_norm": 1.39503812789917, "learning_rate": 0.0002, "epoch": 5.098841172460804, "step": 3740}, {"loss": 0.9658, "grad_norm": 1.2345329523086548, "learning_rate": 0.0002, "epoch": 5.112474437627812, "step": 3750}, {"loss": 1.0615, "grad_norm": 1.2700239419937134, "learning_rate": 0.0002, "epoch": 5.126107702794819, "step": 3760}, {"loss": 0.993, "grad_norm": 1.5343066453933716, "learning_rate": 0.0002, "epoch": 5.139740967961827, "step": 3770}, {"loss": 0.9378, "grad_norm": 1.4191608428955078, "learning_rate": 0.0002, "epoch": 5.153374233128835, "step": 3780}, {"loss": 1.0179, "grad_norm": 1.4591023921966553, "learning_rate": 0.0002, "epoch": 5.167007498295842, "step": 3790}, {"loss": 1.0143, "grad_norm": 1.6158121824264526, "learning_rate": 0.0002, "epoch": 5.18064076346285, "step": 3800}, {"loss": 1.0056, "grad_norm": 1.6077582836151123, "learning_rate": 0.0002, "epoch": 5.194274028629857, "step": 3810}, {"loss": 0.9711, "grad_norm": 1.2815653085708618, "learning_rate": 0.0002, "epoch": 5.207907293796865, "step": 3820}, {"loss": 1.0131, "grad_norm": 1.2427219152450562, "learning_rate": 0.0002, "epoch": 5.221540558963872, "step": 3830}, {"loss": 0.9901, "grad_norm": 1.3013232946395874, "learning_rate": 0.0002, "epoch": 5.23517382413088, "step": 3840}, {"loss": 0.9862, "grad_norm": 1.4643588066101074, "learning_rate": 0.0002, "epoch": 5.248807089297887, "step": 3850}, {"loss": 1.0149, "grad_norm": 1.2571916580200195, "learning_rate": 0.0002, "epoch": 5.2624403544648946, "step": 3860}, {"loss": 0.9686, "grad_norm": 1.226682186126709, "learning_rate": 0.0002, "epoch": 5.276073619631902, "step": 3870}, {"loss": 0.9417, "grad_norm": 1.2541271448135376, "learning_rate": 0.0002, "epoch": 5.2897068847989095, "step": 3880}, {"loss": 0.9767, "grad_norm": 1.2340261936187744, "learning_rate": 0.0002, "epoch": 5.3033401499659165, "step": 3890}, {"loss": 1.0173, "grad_norm": 1.345527172088623, "learning_rate": 0.0002, "epoch": 5.316973415132924, "step": 3900}, {"loss": 1.0638, "grad_norm": 1.2128909826278687, "learning_rate": 0.0002, "epoch": 5.3306066802999315, "step": 3910}, {"loss": 1.0002, "grad_norm": 1.3052637577056885, "learning_rate": 0.0002, "epoch": 5.344239945466939, "step": 3920}, {"loss": 0.9754, "grad_norm": 1.1017392873764038, "learning_rate": 0.0002, "epoch": 5.357873210633947, "step": 3930}, {"loss": 1.0579, "grad_norm": 1.26950204372406, "learning_rate": 0.0002, "epoch": 5.371506475800954, "step": 3940}, {"loss": 1.0816, "grad_norm": 1.3372546434402466, "learning_rate": 0.0002, "epoch": 5.385139740967962, "step": 3950}, {"loss": 1.0529, "grad_norm": 1.3115156888961792, "learning_rate": 0.0002, "epoch": 5.398773006134969, "step": 3960}, {"loss": 1.1179, "grad_norm": 1.3511474132537842, "learning_rate": 0.0002, "epoch": 5.412406271301977, "step": 3970}, {"loss": 1.0352, "grad_norm": 1.1001893281936646, "learning_rate": 0.0002, "epoch": 5.426039536468984, "step": 3980}, {"loss": 1.0855, "grad_norm": 1.2810745239257812, "learning_rate": 0.0002, "epoch": 5.439672801635992, "step": 3990}, {"loss": 1.0573, "grad_norm": 1.2999306917190552, "learning_rate": 0.0002, "epoch": 5.453306066802999, "step": 4000}, {"loss": 1.0073, "grad_norm": 1.172553300857544, "learning_rate": 0.0002, "epoch": 5.466939331970007, "step": 4010}, {"loss": 1.003, "grad_norm": 1.1483557224273682, "learning_rate": 0.0002, "epoch": 5.480572597137014, "step": 4020}, {"loss": 1.0704, "grad_norm": 1.4148036241531372, "learning_rate": 0.0002, "epoch": 5.494205862304022, "step": 4030}, {"loss": 1.0519, "grad_norm": 1.1611121892929077, "learning_rate": 0.0002, "epoch": 5.507839127471029, "step": 4040}, {"loss": 1.0775, "grad_norm": 1.3837119340896606, "learning_rate": 0.0002, "epoch": 5.521472392638037, "step": 4050}, {"loss": 1.0257, "grad_norm": 1.3025696277618408, "learning_rate": 0.0002, "epoch": 5.535105657805044, "step": 4060}, {"loss": 1.0628, "grad_norm": 1.348091959953308, "learning_rate": 0.0002, "epoch": 5.548738922972052, "step": 4070}, {"loss": 1.0447, "grad_norm": 1.3463449478149414, "learning_rate": 0.0002, "epoch": 5.56237218813906, "step": 4080}, {"loss": 1.039, "grad_norm": 1.3904176950454712, "learning_rate": 0.0002, "epoch": 5.576005453306067, "step": 4090}, {"loss": 1.0963, "grad_norm": 1.2737950086593628, "learning_rate": 0.0002, "epoch": 5.589638718473074, "step": 4100}, {"loss": 1.0441, "grad_norm": 1.3311827182769775, "learning_rate": 0.0002, "epoch": 5.603271983640082, "step": 4110}, {"loss": 1.0521, "grad_norm": 1.24485182762146, "learning_rate": 0.0002, "epoch": 5.61690524880709, "step": 4120}, {"loss": 1.1103, "grad_norm": 1.2724957466125488, "learning_rate": 0.0002, "epoch": 5.630538513974097, "step": 4130}, {"loss": 1.0588, "grad_norm": 1.3439847230911255, "learning_rate": 0.0002, "epoch": 5.644171779141105, "step": 4140}, {"loss": 1.0257, "grad_norm": 1.372359037399292, "learning_rate": 0.0002, "epoch": 5.657805044308112, "step": 4150}, {"loss": 1.0475, "grad_norm": 1.2322949171066284, "learning_rate": 0.0002, "epoch": 5.6714383094751195, "step": 4160}, {"loss": 1.0465, "grad_norm": 1.4859193563461304, "learning_rate": 0.0002, "epoch": 5.6850715746421265, "step": 4170}, {"loss": 1.1569, "grad_norm": 1.4318448305130005, "learning_rate": 0.0002, "epoch": 5.6987048398091344, "step": 4180}, {"loss": 1.017, "grad_norm": 1.1533565521240234, "learning_rate": 0.0002, "epoch": 5.7123381049761415, "step": 4190}, {"loss": 1.0948, "grad_norm": 1.3009696006774902, "learning_rate": 0.0002, "epoch": 5.725971370143149, "step": 4200}, {"loss": 1.1229, "grad_norm": 1.3972162008285522, "learning_rate": 0.0002, "epoch": 5.739604635310156, "step": 4210}, {"loss": 1.033, "grad_norm": 1.2142186164855957, "learning_rate": 0.0002, "epoch": 5.753237900477164, "step": 4220}, {"loss": 1.0588, "grad_norm": 1.401191234588623, "learning_rate": 0.0002, "epoch": 5.766871165644172, "step": 4230}, {"loss": 1.0722, "grad_norm": 1.4124404191970825, "learning_rate": 0.0002, "epoch": 5.780504430811179, "step": 4240}, {"loss": 1.0826, "grad_norm": 1.3488332033157349, "learning_rate": 0.0002, "epoch": 5.794137695978186, "step": 4250}, {"loss": 1.0599, "grad_norm": 1.3671752214431763, "learning_rate": 0.0002, "epoch": 5.807770961145194, "step": 4260}, {"loss": 1.1294, "grad_norm": 1.2608201503753662, "learning_rate": 0.0002, "epoch": 5.821404226312202, "step": 4270}, {"loss": 1.1216, "grad_norm": 1.1814045906066895, "learning_rate": 0.0002, "epoch": 5.835037491479209, "step": 4280}, {"loss": 1.0973, "grad_norm": 1.4139586687088013, "learning_rate": 0.0002, "epoch": 5.848670756646217, "step": 4290}, {"loss": 1.0656, "grad_norm": 1.34248948097229, "learning_rate": 0.0002, "epoch": 5.862304021813224, "step": 4300}, {"loss": 1.0791, "grad_norm": 1.1428139209747314, "learning_rate": 0.0002, "epoch": 5.875937286980232, "step": 4310}, {"loss": 1.0556, "grad_norm": 1.1941087245941162, "learning_rate": 0.0002, "epoch": 5.889570552147239, "step": 4320}, {"loss": 1.1089, "grad_norm": 1.2374001741409302, "learning_rate": 0.0002, "epoch": 5.903203817314247, "step": 4330}, {"loss": 1.0802, "grad_norm": 1.4314988851547241, "learning_rate": 0.0002, "epoch": 5.916837082481254, "step": 4340}, {"loss": 1.133, "grad_norm": 1.1286126375198364, "learning_rate": 0.0002, "epoch": 5.930470347648262, "step": 4350}, {"loss": 1.0807, "grad_norm": 1.25884211063385, "learning_rate": 0.0002, "epoch": 5.944103612815269, "step": 4360}, {"loss": 1.1189, "grad_norm": 1.223357915878296, "learning_rate": 0.0002, "epoch": 5.957736877982277, "step": 4370}, {"loss": 1.1335, "grad_norm": 1.2173810005187988, "learning_rate": 0.0002, "epoch": 5.971370143149285, "step": 4380}, {"loss": 1.1201, "grad_norm": 1.3152292966842651, "learning_rate": 0.0002, "epoch": 5.985003408316292, "step": 4390}, {"loss": 1.1456, "grad_norm": 1.5576739311218262, "learning_rate": 0.0002, "epoch": 5.998636673483299, "step": 4400}, {"eval_loss": 2.3435311317443848, "eval_runtime": 53.6362, "eval_samples_per_second": 9.453, "eval_steps_per_second": 1.193, "epoch": 6.0, "step": 4401}, {"loss": 0.8618, "grad_norm": 2.027981758117676, "learning_rate": 0.0002, "epoch": 6.012269938650307, "step": 4410}, {"loss": 0.7702, "grad_norm": 1.4775491952896118, "learning_rate": 0.0002, "epoch": 6.025903203817315, "step": 4420}, {"loss": 0.8042, "grad_norm": 1.6902967691421509, "learning_rate": 0.0002, "epoch": 6.039536468984322, "step": 4430}, {"loss": 0.7363, "grad_norm": 1.2506479024887085, "learning_rate": 0.0002, "epoch": 6.0531697341513295, "step": 4440}, {"loss": 0.7653, "grad_norm": 1.5935661792755127, "learning_rate": 0.0002, "epoch": 6.0668029993183366, "step": 4450}, {"loss": 0.7869, "grad_norm": 1.2966011762619019, "learning_rate": 0.0002, "epoch": 6.0804362644853445, "step": 4460}, {"loss": 0.7186, "grad_norm": 1.5247948169708252, "learning_rate": 0.0002, "epoch": 6.0940695296523515, "step": 4470}, {"loss": 0.7864, "grad_norm": 1.6415225267410278, "learning_rate": 0.0002, "epoch": 6.107702794819359, "step": 4480}, {"loss": 0.7561, "grad_norm": 1.5510778427124023, "learning_rate": 0.0002, "epoch": 6.121336059986366, "step": 4490}, {"loss": 0.7628, "grad_norm": 1.361097812652588, "learning_rate": 0.0002, "epoch": 6.134969325153374, "step": 4500}, {"loss": 0.8053, "grad_norm": 1.8347383737564087, "learning_rate": 0.0002, "epoch": 6.148602590320381, "step": 4510}, {"loss": 0.8074, "grad_norm": 1.570560097694397, "learning_rate": 0.0002, "epoch": 6.162235855487389, "step": 4520}, {"loss": 0.7536, "grad_norm": 1.517993688583374, "learning_rate": 0.0002, "epoch": 6.175869120654396, "step": 4530}, {"loss": 0.8028, "grad_norm": 1.4517489671707153, "learning_rate": 0.0002, "epoch": 6.189502385821404, "step": 4540}, {"loss": 0.8633, "grad_norm": 1.557098627090454, "learning_rate": 0.0002, "epoch": 6.203135650988412, "step": 4550}, {"loss": 0.7704, "grad_norm": 1.7379891872406006, "learning_rate": 0.0002, "epoch": 6.216768916155419, "step": 4560}, {"loss": 0.7341, "grad_norm": 2.2292542457580566, "learning_rate": 0.0002, "epoch": 6.230402181322427, "step": 4570}, {"loss": 0.7883, "grad_norm": 1.834366798400879, "learning_rate": 0.0002, "epoch": 6.244035446489434, "step": 4580}, {"loss": 0.8222, "grad_norm": 1.6755090951919556, "learning_rate": 0.0002, "epoch": 6.257668711656442, "step": 4590}, {"loss": 0.8245, "grad_norm": 1.828898549079895, "learning_rate": 0.0002, "epoch": 6.271301976823449, "step": 4600}, {"loss": 0.8116, "grad_norm": 1.9773457050323486, "learning_rate": 0.0002, "epoch": 6.284935241990457, "step": 4610}, {"loss": 0.811, "grad_norm": 1.533369541168213, "learning_rate": 0.0002, "epoch": 6.298568507157464, "step": 4620}, {"loss": 0.807, "grad_norm": 1.5432997941970825, "learning_rate": 0.0002, "epoch": 6.312201772324472, "step": 4630}, {"loss": 0.818, "grad_norm": 1.6686866283416748, "learning_rate": 0.0002, "epoch": 6.325835037491479, "step": 4640}, {"loss": 0.8656, "grad_norm": 1.545304298400879, "learning_rate": 0.0002, "epoch": 6.339468302658487, "step": 4650}, {"loss": 0.8239, "grad_norm": 1.5981945991516113, "learning_rate": 0.0002, "epoch": 6.353101567825494, "step": 4660}, {"loss": 0.8162, "grad_norm": 1.6973154544830322, "learning_rate": 0.0002, "epoch": 6.366734832992502, "step": 4670}, {"loss": 0.8377, "grad_norm": 1.6782612800598145, "learning_rate": 0.0002, "epoch": 6.38036809815951, "step": 4680}, {"loss": 0.8185, "grad_norm": 1.5710086822509766, "learning_rate": 0.0002, "epoch": 6.394001363326517, "step": 4690}, {"loss": 0.7948, "grad_norm": 1.7241147756576538, "learning_rate": 0.0002, "epoch": 6.407634628493525, "step": 4700}, {"loss": 0.8768, "grad_norm": 1.7736736536026, "learning_rate": 0.0002, "epoch": 6.421267893660532, "step": 4710}, {"loss": 0.8607, "grad_norm": 1.7924901247024536, "learning_rate": 0.0002, "epoch": 6.4349011588275395, "step": 4720}, {"loss": 0.832, "grad_norm": 1.4030500650405884, "learning_rate": 0.0002, "epoch": 6.448534423994547, "step": 4730}, {"loss": 0.8806, "grad_norm": 1.6925519704818726, "learning_rate": 0.0002, "epoch": 6.4621676891615545, "step": 4740}, {"loss": 0.8556, "grad_norm": 1.362905502319336, "learning_rate": 0.0002, "epoch": 6.4758009543285615, "step": 4750}, {"loss": 0.838, "grad_norm": 1.5281150341033936, "learning_rate": 0.0002, "epoch": 6.489434219495569, "step": 4760}, {"loss": 0.8396, "grad_norm": 1.524671196937561, "learning_rate": 0.0002, "epoch": 6.5030674846625764, "step": 4770}, {"loss": 0.8225, "grad_norm": 1.7029320001602173, "learning_rate": 0.0002, "epoch": 6.516700749829584, "step": 4780}, {"loss": 0.8377, "grad_norm": 1.4663511514663696, "learning_rate": 0.0002, "epoch": 6.530334014996591, "step": 4790}, {"loss": 0.8018, "grad_norm": 1.7682101726531982, "learning_rate": 0.0002, "epoch": 6.543967280163599, "step": 4800}, {"loss": 0.8318, "grad_norm": 1.6056565046310425, "learning_rate": 0.0002, "epoch": 6.557600545330606, "step": 4810}, {"loss": 0.8747, "grad_norm": 1.6552391052246094, "learning_rate": 0.0002, "epoch": 6.571233810497614, "step": 4820}, {"loss": 0.8559, "grad_norm": 1.4265215396881104, "learning_rate": 0.0002, "epoch": 6.584867075664622, "step": 4830}, {"loss": 0.8606, "grad_norm": 1.6225470304489136, "learning_rate": 0.0002, "epoch": 6.598500340831629, "step": 4840}, {"loss": 0.8817, "grad_norm": 1.6568684577941895, "learning_rate": 0.0002, "epoch": 6.612133605998636, "step": 4850}, {"loss": 0.8825, "grad_norm": 1.760115146636963, "learning_rate": 0.0002, "epoch": 6.625766871165644, "step": 4860}, {"loss": 0.9227, "grad_norm": 1.627966046333313, "learning_rate": 0.0002, "epoch": 6.639400136332652, "step": 4870}, {"loss": 0.8825, "grad_norm": 1.7053254842758179, "learning_rate": 0.0002, "epoch": 6.653033401499659, "step": 4880}, {"loss": 0.857, "grad_norm": 1.5339484214782715, "learning_rate": 0.0002, "epoch": 6.666666666666667, "step": 4890}, {"loss": 0.8482, "grad_norm": 1.5594874620437622, "learning_rate": 0.0002, "epoch": 6.680299931833674, "step": 4900}, {"loss": 0.842, "grad_norm": 1.5322152376174927, "learning_rate": 0.0002, "epoch": 6.693933197000682, "step": 4910}, {"loss": 0.8049, "grad_norm": 1.733410358428955, "learning_rate": 0.0002, "epoch": 6.707566462167689, "step": 4920}, {"loss": 0.9099, "grad_norm": 1.3626887798309326, "learning_rate": 0.0002, "epoch": 6.721199727334697, "step": 4930}, {"loss": 0.9481, "grad_norm": 1.6323494911193848, "learning_rate": 0.0002, "epoch": 6.734832992501704, "step": 4940}, {"loss": 0.8803, "grad_norm": 1.6548917293548584, "learning_rate": 0.0002, "epoch": 6.748466257668712, "step": 4950}, {"loss": 0.9149, "grad_norm": 1.7894278764724731, "learning_rate": 0.0002, "epoch": 6.762099522835719, "step": 4960}, {"loss": 0.9137, "grad_norm": 1.7960841655731201, "learning_rate": 0.0002, "epoch": 6.775732788002727, "step": 4970}, {"loss": 0.9088, "grad_norm": 1.4888852834701538, "learning_rate": 0.0002, "epoch": 6.789366053169735, "step": 4980}, {"loss": 0.9495, "grad_norm": 1.6368865966796875, "learning_rate": 0.0002, "epoch": 6.802999318336742, "step": 4990}, {"loss": 0.9939, "grad_norm": 1.7106667757034302, "learning_rate": 0.0002, "epoch": 6.816632583503749, "step": 5000}, {"loss": 0.8551, "grad_norm": 4.131956100463867, "learning_rate": 0.0002, "epoch": 6.830265848670757, "step": 5010}, {"loss": 0.908, "grad_norm": 1.6357536315917969, "learning_rate": 0.0002, "epoch": 6.8438991138377645, "step": 5020}, {"loss": 0.8661, "grad_norm": 1.621524453163147, "learning_rate": 0.0002, "epoch": 6.8575323790047715, "step": 5030}, {"loss": 0.9177, "grad_norm": 1.6400790214538574, "learning_rate": 0.0002, "epoch": 6.871165644171779, "step": 5040}, {"loss": 0.9204, "grad_norm": 1.823006272315979, "learning_rate": 0.0002, "epoch": 6.8847989093387865, "step": 5050}, {"loss": 0.9133, "grad_norm": 1.6328210830688477, "learning_rate": 0.0002, "epoch": 6.898432174505794, "step": 5060}, {"loss": 0.9138, "grad_norm": 1.3616089820861816, "learning_rate": 0.0002, "epoch": 6.912065439672801, "step": 5070}, {"loss": 0.8791, "grad_norm": 1.7202986478805542, "learning_rate": 0.0002, "epoch": 6.925698704839809, "step": 5080}, {"loss": 0.8331, "grad_norm": 1.8145297765731812, "learning_rate": 0.0002, "epoch": 6.939331970006816, "step": 5090}, {"loss": 0.861, "grad_norm": 1.5432910919189453, "learning_rate": 0.0002, "epoch": 6.952965235173824, "step": 5100}, {"loss": 0.9282, "grad_norm": 1.2784099578857422, "learning_rate": 0.0002, "epoch": 6.966598500340831, "step": 5110}, {"loss": 0.9189, "grad_norm": 1.556593894958496, "learning_rate": 0.0002, "epoch": 6.980231765507839, "step": 5120}, {"loss": 0.8961, "grad_norm": 1.5102856159210205, "learning_rate": 0.0002, "epoch": 6.993865030674847, "step": 5130}]}
+{"epoch": 7.994546693933197, "step": 5864, "epoch_duration": 1089.3252186775208, "total_accumulated_duration": 8756.72781586647, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19996.724609375}, "avg_memory_reserved": {"GPU_0": 28746.0}, "peak_memory_reserved": {"GPU_0": 28746.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-4/checkpoint-733", "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": 3.0982, "grad_norm": 0.7714291214942932, "learning_rate": 0.0002, "epoch": 0.013633265167007498, "step": 10}, {"loss": 2.5206, "grad_norm": 0.5473978519439697, "learning_rate": 0.0002, "epoch": 0.027266530334014997, "step": 20}, {"loss": 2.3079, "grad_norm": 0.5452795624732971, "learning_rate": 0.0002, "epoch": 0.0408997955010225, "step": 30}, {"loss": 2.0019, "grad_norm": 0.5098028779029846, "learning_rate": 0.0002, "epoch": 0.054533060668029994, "step": 40}, {"loss": 1.9333, "grad_norm": 0.48062971234321594, "learning_rate": 0.0002, "epoch": 0.0681663258350375, "step": 50}, {"loss": 1.9355, "grad_norm": 0.4505695104598999, "learning_rate": 0.0002, "epoch": 0.081799591002045, "step": 60}, {"loss": 1.9312, "grad_norm": 0.41609591245651245, "learning_rate": 0.0002, "epoch": 0.09543285616905249, "step": 70}, {"loss": 1.8656, "grad_norm": 0.4323892593383789, "learning_rate": 0.0002, "epoch": 0.10906612133605999, "step": 80}, {"loss": 1.9294, "grad_norm": 0.4670293629169464, "learning_rate": 0.0002, "epoch": 0.12269938650306748, "step": 90}, {"loss": 1.7946, "grad_norm": 0.40623316168785095, "learning_rate": 0.0002, "epoch": 0.136332651670075, "step": 100}, {"loss": 1.8565, "grad_norm": 0.3620383143424988, "learning_rate": 0.0002, "epoch": 0.1499659168370825, "step": 110}, {"loss": 1.9238, "grad_norm": 0.332218736410141, "learning_rate": 0.0002, "epoch": 0.16359918200409, "step": 120}, {"loss": 1.93, "grad_norm": 0.4004521667957306, "learning_rate": 0.0002, "epoch": 0.17723244717109748, "step": 130}, {"loss": 1.7549, "grad_norm": 0.3698360323905945, "learning_rate": 0.0002, "epoch": 0.19086571233810498, "step": 140}, {"loss": 1.8771, "grad_norm": 0.3847949504852295, "learning_rate": 0.0002, "epoch": 0.20449897750511248, "step": 150}, {"loss": 1.8316, "grad_norm": 0.36843451857566833, "learning_rate": 0.0002, "epoch": 0.21813224267211997, "step": 160}, {"loss": 1.838, "grad_norm": 0.37301021814346313, "learning_rate": 0.0002, "epoch": 0.23176550783912747, "step": 170}, {"loss": 1.8909, "grad_norm": 0.3718886971473694, "learning_rate": 0.0002, "epoch": 0.24539877300613497, "step": 180}, {"loss": 1.8454, "grad_norm": 0.3088490962982178, "learning_rate": 0.0002, "epoch": 0.25903203817314246, "step": 190}, {"loss": 1.9254, "grad_norm": 0.3611852526664734, "learning_rate": 0.0002, "epoch": 0.27266530334015, "step": 200}, {"loss": 1.7844, "grad_norm": 0.36093324422836304, "learning_rate": 0.0002, "epoch": 0.28629856850715746, "step": 210}, {"loss": 1.719, "grad_norm": 0.3250400722026825, "learning_rate": 0.0002, "epoch": 0.299931833674165, "step": 220}, {"loss": 1.8729, "grad_norm": 0.3566756248474121, "learning_rate": 0.0002, "epoch": 0.31356509884117245, "step": 230}, {"loss": 1.9259, "grad_norm": 0.32872408628463745, "learning_rate": 0.0002, "epoch": 0.32719836400818, "step": 240}, {"loss": 1.9033, "grad_norm": 0.3983881175518036, "learning_rate": 0.0002, "epoch": 0.34083162917518744, "step": 250}, {"loss": 1.8588, "grad_norm": 0.3571510910987854, "learning_rate": 0.0002, "epoch": 0.35446489434219497, "step": 260}, {"loss": 1.8539, "grad_norm": 0.3036131262779236, "learning_rate": 0.0002, "epoch": 0.36809815950920244, "step": 270}, {"loss": 1.8572, "grad_norm": 0.36512863636016846, "learning_rate": 0.0002, "epoch": 0.38173142467620996, "step": 280}, {"loss": 1.8022, "grad_norm": 0.3429736793041229, "learning_rate": 0.0002, "epoch": 0.39536468984321743, "step": 290}, {"loss": 1.8754, "grad_norm": 0.3055964708328247, "learning_rate": 0.0002, "epoch": 0.40899795501022496, "step": 300}, {"loss": 1.8384, "grad_norm": 0.33801034092903137, "learning_rate": 0.0002, "epoch": 0.4226312201772324, "step": 310}, {"loss": 1.7933, "grad_norm": 0.348783016204834, "learning_rate": 0.0002, "epoch": 0.43626448534423995, "step": 320}, {"loss": 1.8451, "grad_norm": 0.3057514727115631, "learning_rate": 0.0002, "epoch": 0.4498977505112474, "step": 330}, {"loss": 1.8766, "grad_norm": 0.3849763572216034, "learning_rate": 0.0002, "epoch": 0.46353101567825494, "step": 340}, {"loss": 1.8073, "grad_norm": 0.30080053210258484, "learning_rate": 0.0002, "epoch": 0.47716428084526247, "step": 350}, {"loss": 1.8548, "grad_norm": 0.3595106303691864, "learning_rate": 0.0002, "epoch": 0.49079754601226994, "step": 360}, {"loss": 1.8232, "grad_norm": 0.31099820137023926, "learning_rate": 0.0002, "epoch": 0.5044308111792775, "step": 370}, {"loss": 1.7029, "grad_norm": 0.3157978355884552, "learning_rate": 0.0002, "epoch": 0.5180640763462849, "step": 380}, {"loss": 1.8265, "grad_norm": 0.27960965037345886, "learning_rate": 0.0002, "epoch": 0.5316973415132924, "step": 390}, {"loss": 1.7414, "grad_norm": 0.3102385103702545, "learning_rate": 0.0002, "epoch": 0.5453306066803, "step": 400}, {"loss": 1.7461, "grad_norm": 0.32828861474990845, "learning_rate": 0.0002, "epoch": 0.5589638718473074, "step": 410}, {"loss": 1.8165, "grad_norm": 0.29560017585754395, "learning_rate": 0.0002, "epoch": 0.5725971370143149, "step": 420}, {"loss": 1.9455, "grad_norm": 0.33316895365715027, "learning_rate": 0.0002, "epoch": 0.5862304021813224, "step": 430}, {"loss": 1.8241, "grad_norm": 0.30420982837677, "learning_rate": 0.0002, "epoch": 0.59986366734833, "step": 440}, {"loss": 1.7565, "grad_norm": 0.32619214057922363, "learning_rate": 0.0002, "epoch": 0.6134969325153374, "step": 450}, {"loss": 1.7945, "grad_norm": 0.3603750765323639, "learning_rate": 0.0002, "epoch": 0.6271301976823449, "step": 460}, {"loss": 1.7773, "grad_norm": 0.30834096670150757, "learning_rate": 0.0002, "epoch": 0.6407634628493524, "step": 470}, {"loss": 1.8058, "grad_norm": 0.28756365180015564, "learning_rate": 0.0002, "epoch": 0.65439672801636, "step": 480}, {"loss": 1.744, "grad_norm": 0.2878406345844269, "learning_rate": 0.0002, "epoch": 0.6680299931833674, "step": 490}, {"loss": 1.8581, "grad_norm": 0.31329697370529175, "learning_rate": 0.0002, "epoch": 0.6816632583503749, "step": 500}, {"loss": 1.7886, "grad_norm": 0.3405822515487671, "learning_rate": 0.0002, "epoch": 0.6952965235173824, "step": 510}, {"loss": 1.778, "grad_norm": 0.305560827255249, "learning_rate": 0.0002, "epoch": 0.7089297886843899, "step": 520}, {"loss": 1.7592, "grad_norm": 0.2973416745662689, "learning_rate": 0.0002, "epoch": 0.7225630538513974, "step": 530}, {"loss": 1.8223, "grad_norm": 0.327303946018219, "learning_rate": 0.0002, "epoch": 0.7361963190184049, "step": 540}, {"loss": 1.8591, "grad_norm": 0.62595534324646, "learning_rate": 0.0002, "epoch": 0.7498295841854125, "step": 550}, {"loss": 1.7466, "grad_norm": 0.3129784166812897, "learning_rate": 0.0002, "epoch": 0.7634628493524199, "step": 560}, {"loss": 1.8035, "grad_norm": 0.32496583461761475, "learning_rate": 0.0002, "epoch": 0.7770961145194274, "step": 570}, {"loss": 1.7787, "grad_norm": 0.3098868131637573, "learning_rate": 0.0002, "epoch": 0.7907293796864349, "step": 580}, {"loss": 1.7196, "grad_norm": 0.30726853013038635, "learning_rate": 0.0002, "epoch": 0.8043626448534424, "step": 590}, {"loss": 1.7898, "grad_norm": 0.2964220643043518, "learning_rate": 0.0002, "epoch": 0.8179959100204499, "step": 600}, {"loss": 1.8114, "grad_norm": 0.32352274656295776, "learning_rate": 0.0002, "epoch": 0.8316291751874574, "step": 610}, {"loss": 1.811, "grad_norm": 0.2938912510871887, "learning_rate": 0.0002, "epoch": 0.8452624403544649, "step": 620}, {"loss": 1.7727, "grad_norm": 0.295559823513031, "learning_rate": 0.0002, "epoch": 0.8588957055214724, "step": 630}, {"loss": 1.9, "grad_norm": 0.34102028608322144, "learning_rate": 0.0002, "epoch": 0.8725289706884799, "step": 640}, {"loss": 1.8006, "grad_norm": 0.29676181077957153, "learning_rate": 0.0002, "epoch": 0.8861622358554874, "step": 650}, {"loss": 1.8099, "grad_norm": 0.3108902871608734, "learning_rate": 0.0002, "epoch": 0.8997955010224948, "step": 660}, {"loss": 1.7955, "grad_norm": 0.2690821588039398, "learning_rate": 0.0002, "epoch": 0.9134287661895024, "step": 670}, {"loss": 1.7881, "grad_norm": 0.32752540707588196, "learning_rate": 0.0002, "epoch": 0.9270620313565099, "step": 680}, {"loss": 1.7661, "grad_norm": 0.8029476404190063, "learning_rate": 0.0002, "epoch": 0.9406952965235174, "step": 690}, {"loss": 1.7733, "grad_norm": 0.30534422397613525, "learning_rate": 0.0002, "epoch": 0.9543285616905249, "step": 700}, {"loss": 1.7614, "grad_norm": 0.2899954319000244, "learning_rate": 0.0002, "epoch": 0.9679618268575324, "step": 710}, {"loss": 1.7845, "grad_norm": 0.28814372420310974, "learning_rate": 0.0002, "epoch": 0.9815950920245399, "step": 720}, {"loss": 1.8865, "grad_norm": 0.3061596751213074, "learning_rate": 0.0002, "epoch": 0.9952283571915473, "step": 730}, {"eval_loss": 1.8171186447143555, "eval_runtime": 53.6047, "eval_samples_per_second": 9.458, "eval_steps_per_second": 1.194, "epoch": 0.9993183367416496, "step": 733}, {"loss": 1.6202, "grad_norm": 0.3140897750854492, "learning_rate": 0.0002, "epoch": 1.008861622358555, "step": 740}, {"loss": 1.8409, "grad_norm": 0.3346109390258789, "learning_rate": 0.0002, "epoch": 1.0224948875255624, "step": 750}, {"loss": 1.6777, "grad_norm": 0.3582976758480072, "learning_rate": 0.0002, "epoch": 1.0361281526925699, "step": 760}, {"loss": 1.7306, "grad_norm": 0.30408260226249695, "learning_rate": 0.0002, "epoch": 1.0497614178595773, "step": 770}, {"loss": 1.6967, "grad_norm": 0.323585569858551, "learning_rate": 0.0002, "epoch": 1.0633946830265848, "step": 780}, {"loss": 1.768, "grad_norm": 0.3474137783050537, "learning_rate": 0.0002, "epoch": 1.0770279481935923, "step": 790}, {"loss": 1.6895, "grad_norm": 0.35721147060394287, "learning_rate": 0.0002, "epoch": 1.0906612133606, "step": 800}, {"loss": 1.718, "grad_norm": 0.35366931557655334, "learning_rate": 0.0002, "epoch": 1.1042944785276074, "step": 810}, {"loss": 1.6797, "grad_norm": 0.3250770568847656, "learning_rate": 0.0002, "epoch": 1.117927743694615, "step": 820}, {"loss": 1.6383, "grad_norm": 0.3293766379356384, "learning_rate": 0.0002, "epoch": 1.1315610088616224, "step": 830}, {"loss": 1.7353, "grad_norm": 0.3380851745605469, "learning_rate": 0.0002, "epoch": 1.1451942740286298, "step": 840}, {"loss": 1.8236, "grad_norm": 0.32584455609321594, "learning_rate": 0.0002, "epoch": 1.1588275391956373, "step": 850}, {"loss": 1.6681, "grad_norm": 0.45700767636299133, "learning_rate": 0.0002, "epoch": 1.1724608043626448, "step": 860}, {"loss": 1.7494, "grad_norm": 0.30944544076919556, "learning_rate": 0.0002, "epoch": 1.1860940695296525, "step": 870}, {"loss": 1.7426, "grad_norm": 0.3268151581287384, "learning_rate": 0.0002, "epoch": 1.19972733469666, "step": 880}, {"loss": 1.7413, "grad_norm": 0.39972540736198425, "learning_rate": 0.0002, "epoch": 1.2133605998636674, "step": 890}, {"loss": 1.7481, "grad_norm": 0.7890929579734802, "learning_rate": 0.0002, "epoch": 1.2269938650306749, "step": 900}, {"loss": 1.7608, "grad_norm": 0.3439182639122009, "learning_rate": 0.0002, "epoch": 1.2406271301976823, "step": 910}, {"loss": 1.7617, "grad_norm": 0.3986225128173828, "learning_rate": 0.0002, "epoch": 1.2542603953646898, "step": 920}, {"loss": 1.6843, "grad_norm": 0.3514605164527893, "learning_rate": 0.0002, "epoch": 1.2678936605316973, "step": 930}, {"loss": 1.6987, "grad_norm": 0.3682589530944824, "learning_rate": 0.0002, "epoch": 1.2815269256987047, "step": 940}, {"loss": 1.6988, "grad_norm": 0.3618335723876953, "learning_rate": 0.0002, "epoch": 1.2951601908657122, "step": 950}, {"loss": 1.7436, "grad_norm": 0.345700740814209, "learning_rate": 0.0002, "epoch": 1.30879345603272, "step": 960}, {"loss": 1.7336, "grad_norm": 0.3514927923679352, "learning_rate": 0.0002, "epoch": 1.3224267211997274, "step": 970}, {"loss": 1.7704, "grad_norm": 0.365647554397583, "learning_rate": 0.0002, "epoch": 1.3360599863667348, "step": 980}, {"loss": 1.7104, "grad_norm": 0.3407285809516907, "learning_rate": 0.0002, "epoch": 1.3496932515337423, "step": 990}, {"loss": 1.7132, "grad_norm": 0.3785437345504761, "learning_rate": 0.0002, "epoch": 1.3633265167007498, "step": 1000}, {"loss": 1.766, "grad_norm": 0.34746724367141724, "learning_rate": 0.0002, "epoch": 1.3769597818677572, "step": 1010}, {"loss": 1.7252, "grad_norm": 0.362444132566452, "learning_rate": 0.0002, "epoch": 1.390593047034765, "step": 1020}, {"loss": 1.7132, "grad_norm": 0.4424704611301422, "learning_rate": 0.0002, "epoch": 1.4042263122017724, "step": 1030}, {"loss": 1.726, "grad_norm": 0.38722458481788635, "learning_rate": 0.0002, "epoch": 1.4178595773687799, "step": 1040}, {"loss": 1.7955, "grad_norm": 0.36089080572128296, "learning_rate": 0.0002, "epoch": 1.4314928425357873, "step": 1050}, {"loss": 1.6924, "grad_norm": 0.33817124366760254, "learning_rate": 0.0002, "epoch": 1.4451261077027948, "step": 1060}, {"loss": 1.7165, "grad_norm": 0.34334081411361694, "learning_rate": 0.0002, "epoch": 1.4587593728698023, "step": 1070}, {"loss": 1.6999, "grad_norm": 0.3776826858520508, "learning_rate": 0.0002, "epoch": 1.4723926380368098, "step": 1080}, {"loss": 1.7605, "grad_norm": 0.4169026017189026, "learning_rate": 0.0002, "epoch": 1.4860259032038172, "step": 1090}, {"loss": 1.7502, "grad_norm": 0.34898945689201355, "learning_rate": 0.0002, "epoch": 1.4996591683708247, "step": 1100}, {"loss": 1.635, "grad_norm": 0.34223780035972595, "learning_rate": 0.0002, "epoch": 1.5132924335378322, "step": 1110}, {"loss": 1.7248, "grad_norm": 0.3686901032924652, "learning_rate": 0.0002, "epoch": 1.5269256987048399, "step": 1120}, {"loss": 1.7525, "grad_norm": 0.35054415464401245, "learning_rate": 0.0002, "epoch": 1.5405589638718473, "step": 1130}, {"loss": 1.7776, "grad_norm": 0.39496365189552307, "learning_rate": 0.0002, "epoch": 1.5541922290388548, "step": 1140}, {"loss": 1.6574, "grad_norm": 0.35451626777648926, "learning_rate": 0.0002, "epoch": 1.5678254942058623, "step": 1150}, {"loss": 1.7257, "grad_norm": 0.3848083019256592, "learning_rate": 0.0002, "epoch": 1.58145875937287, "step": 1160}, {"loss": 1.7272, "grad_norm": 0.3760537803173065, "learning_rate": 0.0002, "epoch": 1.5950920245398774, "step": 1170}, {"loss": 1.7441, "grad_norm": 0.38981738686561584, "learning_rate": 0.0002, "epoch": 1.6087252897068849, "step": 1180}, {"loss": 1.6951, "grad_norm": 0.36830949783325195, "learning_rate": 0.0002, "epoch": 1.6223585548738924, "step": 1190}, {"loss": 1.6925, "grad_norm": 0.3405892848968506, "learning_rate": 0.0002, "epoch": 1.6359918200408998, "step": 1200}, {"loss": 1.7473, "grad_norm": 0.39027872681617737, "learning_rate": 0.0002, "epoch": 1.6496250852079073, "step": 1210}, {"loss": 1.6792, "grad_norm": 0.3342694044113159, "learning_rate": 0.0002, "epoch": 1.6632583503749148, "step": 1220}, {"loss": 1.7196, "grad_norm": 0.3600076735019684, "learning_rate": 0.0002, "epoch": 1.6768916155419222, "step": 1230}, {"loss": 1.7021, "grad_norm": 0.3625542223453522, "learning_rate": 0.0002, "epoch": 1.6905248807089297, "step": 1240}, {"loss": 1.6772, "grad_norm": 0.32170894742012024, "learning_rate": 0.0002, "epoch": 1.7041581458759372, "step": 1250}, {"loss": 1.7152, "grad_norm": 0.3544139862060547, "learning_rate": 0.0002, "epoch": 1.7177914110429446, "step": 1260}, {"loss": 1.7138, "grad_norm": 0.35113027691841125, "learning_rate": 0.0002, "epoch": 1.7314246762099523, "step": 1270}, {"loss": 1.7095, "grad_norm": 0.3499974310398102, "learning_rate": 0.0002, "epoch": 1.7450579413769598, "step": 1280}, {"loss": 1.7749, "grad_norm": 0.3285157382488251, "learning_rate": 0.0002, "epoch": 1.7586912065439673, "step": 1290}, {"loss": 1.6767, "grad_norm": 0.3701961636543274, "learning_rate": 0.0002, "epoch": 1.7723244717109747, "step": 1300}, {"loss": 1.6282, "grad_norm": 0.3301318287849426, "learning_rate": 0.0002, "epoch": 1.7859577368779824, "step": 1310}, {"loss": 1.7097, "grad_norm": 0.37801554799079895, "learning_rate": 0.0002, "epoch": 1.79959100204499, "step": 1320}, {"loss": 1.7437, "grad_norm": 0.3726748526096344, "learning_rate": 0.0002, "epoch": 1.8132242672119974, "step": 1330}, {"loss": 1.7959, "grad_norm": 0.4059790074825287, "learning_rate": 0.0002, "epoch": 1.8268575323790048, "step": 1340}, {"loss": 1.7739, "grad_norm": 0.35712096095085144, "learning_rate": 0.0002, "epoch": 1.8404907975460123, "step": 1350}, {"loss": 1.6375, "grad_norm": 0.35995328426361084, "learning_rate": 0.0002, "epoch": 1.8541240627130198, "step": 1360}, {"loss": 1.7332, "grad_norm": 0.3679947257041931, "learning_rate": 0.0002, "epoch": 1.8677573278800272, "step": 1370}, {"loss": 1.7587, "grad_norm": 0.39645957946777344, "learning_rate": 0.0002, "epoch": 1.8813905930470347, "step": 1380}, {"loss": 1.6985, "grad_norm": 0.35288700461387634, "learning_rate": 0.0002, "epoch": 1.8950238582140422, "step": 1390}, {"loss": 1.6582, "grad_norm": 0.32579198479652405, "learning_rate": 0.0002, "epoch": 1.9086571233810496, "step": 1400}, {"loss": 1.6948, "grad_norm": 0.3856561779975891, "learning_rate": 0.0002, "epoch": 1.9222903885480571, "step": 1410}, {"loss": 1.668, "grad_norm": 0.39019331336021423, "learning_rate": 0.0002, "epoch": 1.9359236537150648, "step": 1420}, {"loss": 1.7774, "grad_norm": 0.38006502389907837, "learning_rate": 0.0002, "epoch": 1.9495569188820723, "step": 1430}, {"loss": 1.8323, "grad_norm": 0.38100454211235046, "learning_rate": 0.0002, "epoch": 1.9631901840490797, "step": 1440}, {"loss": 1.7298, "grad_norm": 0.3405798673629761, "learning_rate": 0.0002, "epoch": 1.9768234492160872, "step": 1450}, {"loss": 1.7045, "grad_norm": 0.36582913994789124, "learning_rate": 0.0002, "epoch": 1.990456714383095, "step": 1460}, {"eval_loss": 1.8178424835205078, "eval_runtime": 53.6524, "eval_samples_per_second": 9.45, "eval_steps_per_second": 1.193, "epoch": 2.0, "step": 1467}, {"loss": 1.6363, "grad_norm": 0.3626647889614105, "learning_rate": 0.0002, "epoch": 2.0040899795501024, "step": 1470}, {"loss": 1.5354, "grad_norm": 0.40171775221824646, "learning_rate": 0.0002, "epoch": 2.01772324471711, "step": 1480}, {"loss": 1.5566, "grad_norm": 0.5805319547653198, "learning_rate": 0.0002, "epoch": 2.0313565098841173, "step": 1490}, {"loss": 1.546, "grad_norm": 0.41954153776168823, "learning_rate": 0.0002, "epoch": 2.044989775051125, "step": 1500}, {"loss": 1.6158, "grad_norm": 0.47190725803375244, "learning_rate": 0.0002, "epoch": 2.0586230402181322, "step": 1510}, {"loss": 1.5841, "grad_norm": 0.4388456344604492, "learning_rate": 0.0002, "epoch": 2.0722563053851397, "step": 1520}, {"loss": 1.5835, "grad_norm": 2.2171926498413086, "learning_rate": 0.0002, "epoch": 2.085889570552147, "step": 1530}, {"loss": 1.6137, "grad_norm": 0.4314221143722534, "learning_rate": 0.0002, "epoch": 2.0995228357191547, "step": 1540}, {"loss": 1.5511, "grad_norm": 0.4154265522956848, "learning_rate": 0.0002, "epoch": 2.113156100886162, "step": 1550}, {"loss": 1.6323, "grad_norm": 0.5025539994239807, "learning_rate": 0.0002, "epoch": 2.1267893660531696, "step": 1560}, {"loss": 1.5903, "grad_norm": 0.5410493016242981, "learning_rate": 0.0002, "epoch": 2.140422631220177, "step": 1570}, {"loss": 1.507, "grad_norm": 0.4478487968444824, "learning_rate": 0.0002, "epoch": 2.1540558963871845, "step": 1580}, {"loss": 1.5536, "grad_norm": 0.4703652560710907, "learning_rate": 0.0002, "epoch": 2.1676891615541924, "step": 1590}, {"loss": 1.5991, "grad_norm": 0.4555390179157257, "learning_rate": 0.0002, "epoch": 2.1813224267212, "step": 1600}, {"loss": 1.6117, "grad_norm": 0.4877263903617859, "learning_rate": 0.0002, "epoch": 2.1949556918882074, "step": 1610}, {"loss": 1.5928, "grad_norm": 0.48708245158195496, "learning_rate": 0.0002, "epoch": 2.208588957055215, "step": 1620}, {"loss": 1.6106, "grad_norm": 0.47523951530456543, "learning_rate": 0.0002, "epoch": 2.2222222222222223, "step": 1630}, {"loss": 1.6013, "grad_norm": 0.4889199733734131, "learning_rate": 0.0002, "epoch": 2.23585548738923, "step": 1640}, {"loss": 1.6633, "grad_norm": 0.4585252106189728, "learning_rate": 0.0002, "epoch": 2.2494887525562373, "step": 1650}, {"loss": 1.6075, "grad_norm": 0.4764868915081024, "learning_rate": 0.0002, "epoch": 2.2631220177232447, "step": 1660}, {"loss": 1.6427, "grad_norm": 0.5028976202011108, "learning_rate": 0.0002, "epoch": 2.276755282890252, "step": 1670}, {"loss": 1.6258, "grad_norm": 0.46131211519241333, "learning_rate": 0.0002, "epoch": 2.2903885480572597, "step": 1680}, {"loss": 1.654, "grad_norm": 0.5422874689102173, "learning_rate": 0.0002, "epoch": 2.304021813224267, "step": 1690}, {"loss": 1.6331, "grad_norm": 0.47615355253219604, "learning_rate": 0.0002, "epoch": 2.3176550783912746, "step": 1700}, {"loss": 1.642, "grad_norm": 0.48005548119544983, "learning_rate": 0.0002, "epoch": 2.331288343558282, "step": 1710}, {"loss": 1.581, "grad_norm": 0.4387182295322418, "learning_rate": 0.0002, "epoch": 2.3449216087252895, "step": 1720}, {"loss": 1.5612, "grad_norm": 0.4487272799015045, "learning_rate": 0.0002, "epoch": 2.358554873892297, "step": 1730}, {"loss": 1.5089, "grad_norm": 0.5046455264091492, "learning_rate": 0.0002, "epoch": 2.372188139059305, "step": 1740}, {"loss": 1.5769, "grad_norm": 0.4653521180152893, "learning_rate": 0.0002, "epoch": 2.3858214042263124, "step": 1750}, {"loss": 1.6201, "grad_norm": 0.4737723469734192, "learning_rate": 0.0002, "epoch": 2.39945466939332, "step": 1760}, {"loss": 1.5933, "grad_norm": 0.4501931071281433, "learning_rate": 0.0002, "epoch": 2.4130879345603273, "step": 1770}, {"loss": 1.6321, "grad_norm": 0.4772880971431732, "learning_rate": 0.0002, "epoch": 2.426721199727335, "step": 1780}, {"loss": 1.5454, "grad_norm": 0.4544616937637329, "learning_rate": 0.0002, "epoch": 2.4403544648943423, "step": 1790}, {"loss": 1.5501, "grad_norm": 0.488313227891922, "learning_rate": 0.0002, "epoch": 2.4539877300613497, "step": 1800}, {"loss": 1.5791, "grad_norm": 0.5057830214500427, "learning_rate": 0.0002, "epoch": 2.467620995228357, "step": 1810}, {"loss": 1.5645, "grad_norm": 0.5049484968185425, "learning_rate": 0.0002, "epoch": 2.4812542603953647, "step": 1820}, {"loss": 1.6268, "grad_norm": 0.44966644048690796, "learning_rate": 0.0002, "epoch": 2.494887525562372, "step": 1830}, {"loss": 1.5941, "grad_norm": 0.5072630643844604, "learning_rate": 0.0002, "epoch": 2.5085207907293796, "step": 1840}, {"loss": 1.5251, "grad_norm": 0.43989792466163635, "learning_rate": 0.0002, "epoch": 2.522154055896387, "step": 1850}, {"loss": 1.563, "grad_norm": 1.3504403829574585, "learning_rate": 0.0002, "epoch": 2.5357873210633946, "step": 1860}, {"loss": 1.5681, "grad_norm": 0.46545976400375366, "learning_rate": 0.0002, "epoch": 2.549420586230402, "step": 1870}, {"loss": 1.6368, "grad_norm": 0.4678342044353485, "learning_rate": 0.0002, "epoch": 2.5630538513974095, "step": 1880}, {"loss": 1.5814, "grad_norm": 0.529755711555481, "learning_rate": 0.0002, "epoch": 2.5766871165644174, "step": 1890}, {"loss": 1.5861, "grad_norm": 0.5000199675559998, "learning_rate": 0.0002, "epoch": 2.5903203817314244, "step": 1900}, {"loss": 1.6346, "grad_norm": 0.5649300217628479, "learning_rate": 0.0002, "epoch": 2.6039536468984323, "step": 1910}, {"loss": 1.6317, "grad_norm": 0.7920585870742798, "learning_rate": 0.0002, "epoch": 2.61758691206544, "step": 1920}, {"loss": 1.643, "grad_norm": 0.4960342049598694, "learning_rate": 0.0002, "epoch": 2.6312201772324473, "step": 1930}, {"loss": 1.6099, "grad_norm": 0.5324710011482239, "learning_rate": 0.0002, "epoch": 2.6448534423994547, "step": 1940}, {"loss": 1.5874, "grad_norm": 0.606343150138855, "learning_rate": 0.0002, "epoch": 2.658486707566462, "step": 1950}, {"loss": 1.5728, "grad_norm": 0.53038489818573, "learning_rate": 0.0002, "epoch": 2.6721199727334697, "step": 1960}, {"loss": 1.5583, "grad_norm": 0.4579465091228485, "learning_rate": 0.0002, "epoch": 2.685753237900477, "step": 1970}, {"loss": 1.6093, "grad_norm": 0.4541707932949066, "learning_rate": 0.0002, "epoch": 2.6993865030674846, "step": 1980}, {"loss": 1.5316, "grad_norm": 0.5009395480155945, "learning_rate": 0.0002, "epoch": 2.713019768234492, "step": 1990}, {"loss": 1.6724, "grad_norm": 0.4723006784915924, "learning_rate": 0.0002, "epoch": 2.7266530334014996, "step": 2000}, {"loss": 1.638, "grad_norm": 0.5086126923561096, "learning_rate": 0.0002, "epoch": 2.740286298568507, "step": 2010}, {"loss": 1.6223, "grad_norm": 0.47242608666419983, "learning_rate": 0.0002, "epoch": 2.7539195637355145, "step": 2020}, {"loss": 1.6242, "grad_norm": 0.44922566413879395, "learning_rate": 0.0002, "epoch": 2.767552828902522, "step": 2030}, {"loss": 1.6837, "grad_norm": 0.420259565114975, "learning_rate": 0.0002, "epoch": 2.78118609406953, "step": 2040}, {"loss": 1.5612, "grad_norm": 0.4762881100177765, "learning_rate": 0.0002, "epoch": 2.794819359236537, "step": 2050}, {"loss": 1.5506, "grad_norm": 0.5228786468505859, "learning_rate": 0.0002, "epoch": 2.808452624403545, "step": 2060}, {"loss": 1.6347, "grad_norm": 0.4796035587787628, "learning_rate": 0.0002, "epoch": 2.8220858895705523, "step": 2070}, {"loss": 1.6843, "grad_norm": 0.5034735202789307, "learning_rate": 0.0002, "epoch": 2.8357191547375598, "step": 2080}, {"loss": 1.6455, "grad_norm": 0.48005399107933044, "learning_rate": 0.0002, "epoch": 2.8493524199045672, "step": 2090}, {"loss": 1.6287, "grad_norm": 0.578820526599884, "learning_rate": 0.0002, "epoch": 2.8629856850715747, "step": 2100}, {"loss": 1.6021, "grad_norm": 0.48982638120651245, "learning_rate": 0.0002, "epoch": 2.876618950238582, "step": 2110}, {"loss": 1.5769, "grad_norm": 0.5157325863838196, "learning_rate": 0.0002, "epoch": 2.8902522154055896, "step": 2120}, {"loss": 1.6089, "grad_norm": 0.49149683117866516, "learning_rate": 0.0002, "epoch": 2.903885480572597, "step": 2130}, {"loss": 1.5881, "grad_norm": 0.48584499955177307, "learning_rate": 0.0002, "epoch": 2.9175187457396046, "step": 2140}, {"loss": 1.5833, "grad_norm": 0.5199017524719238, "learning_rate": 0.0002, "epoch": 2.931152010906612, "step": 2150}, {"loss": 1.7344, "grad_norm": 0.5788236856460571, "learning_rate": 0.0002, "epoch": 2.9447852760736195, "step": 2160}, {"loss": 1.6103, "grad_norm": 0.48664185404777527, "learning_rate": 0.0002, "epoch": 2.958418541240627, "step": 2170}, {"loss": 1.5765, "grad_norm": 0.5026682615280151, "learning_rate": 0.0002, "epoch": 2.9720518064076344, "step": 2180}, {"loss": 1.6626, "grad_norm": 0.49317044019699097, "learning_rate": 0.0002, "epoch": 2.9856850715746424, "step": 2190}, {"loss": 1.5871, "grad_norm": 0.5729128122329712, "learning_rate": 0.0002, "epoch": 2.9993183367416494, "step": 2200}, {"eval_loss": 1.8527295589447021, "eval_runtime": 53.6403, "eval_samples_per_second": 9.452, "eval_steps_per_second": 1.193, "epoch": 2.9993183367416494, "step": 2200}, {"loss": 1.4719, "grad_norm": 0.5530241131782532, "learning_rate": 0.0002, "epoch": 3.0129516019086573, "step": 2210}, {"loss": 1.4088, "grad_norm": 0.6642216444015503, "learning_rate": 0.0002, "epoch": 3.0265848670756648, "step": 2220}, {"loss": 1.4382, "grad_norm": 0.61470627784729, "learning_rate": 0.0002, "epoch": 3.0402181322426722, "step": 2230}, {"loss": 1.4634, "grad_norm": 0.8559566140174866, "learning_rate": 0.0002, "epoch": 3.0538513974096797, "step": 2240}, {"loss": 1.3854, "grad_norm": 0.7015801668167114, "learning_rate": 0.0002, "epoch": 3.067484662576687, "step": 2250}, {"loss": 1.4981, "grad_norm": 0.7226442694664001, "learning_rate": 0.0002, "epoch": 3.0811179277436946, "step": 2260}, {"loss": 1.4143, "grad_norm": 0.7560588717460632, "learning_rate": 0.0002, "epoch": 3.094751192910702, "step": 2270}, {"loss": 1.4395, "grad_norm": 0.6216568946838379, "learning_rate": 0.0002, "epoch": 3.1083844580777096, "step": 2280}, {"loss": 1.3842, "grad_norm": 0.6768500804901123, "learning_rate": 0.0002, "epoch": 3.122017723244717, "step": 2290}, {"loss": 1.4672, "grad_norm": 0.7028762102127075, "learning_rate": 0.0002, "epoch": 3.1356509884117245, "step": 2300}, {"loss": 1.3826, "grad_norm": 0.6329697966575623, "learning_rate": 0.0002, "epoch": 3.149284253578732, "step": 2310}, {"loss": 1.442, "grad_norm": 0.6328264474868774, "learning_rate": 0.0002, "epoch": 3.1629175187457395, "step": 2320}, {"loss": 1.3762, "grad_norm": 0.7573632001876831, "learning_rate": 0.0002, "epoch": 3.176550783912747, "step": 2330}, {"loss": 1.3553, "grad_norm": 0.595740795135498, "learning_rate": 0.0002, "epoch": 3.190184049079755, "step": 2340}, {"loss": 1.3953, "grad_norm": 0.7111806869506836, "learning_rate": 0.0002, "epoch": 3.2038173142467623, "step": 2350}, {"loss": 1.3797, "grad_norm": 0.6328730583190918, "learning_rate": 0.0002, "epoch": 3.2174505794137698, "step": 2360}, {"loss": 1.3855, "grad_norm": 0.5860254168510437, "learning_rate": 0.0002, "epoch": 3.2310838445807772, "step": 2370}, {"loss": 1.4267, "grad_norm": 0.7387157082557678, "learning_rate": 0.0002, "epoch": 3.2447171097477847, "step": 2380}, {"loss": 1.4837, "grad_norm": 0.6897673606872559, "learning_rate": 0.0002, "epoch": 3.258350374914792, "step": 2390}, {"loss": 1.4372, "grad_norm": 0.7157699465751648, "learning_rate": 0.0002, "epoch": 3.2719836400817996, "step": 2400}, {"loss": 1.4432, "grad_norm": 0.6422511339187622, "learning_rate": 0.0002, "epoch": 3.285616905248807, "step": 2410}, {"loss": 1.4828, "grad_norm": 1.0481886863708496, "learning_rate": 0.0002, "epoch": 3.2992501704158146, "step": 2420}, {"loss": 1.4473, "grad_norm": 0.7050786018371582, "learning_rate": 0.0002, "epoch": 3.312883435582822, "step": 2430}, {"loss": 1.3465, "grad_norm": 0.6090759038925171, "learning_rate": 0.0002, "epoch": 3.3265167007498295, "step": 2440}, {"loss": 1.4619, "grad_norm": 0.6626465320587158, "learning_rate": 0.0002, "epoch": 3.340149965916837, "step": 2450}, {"loss": 1.4512, "grad_norm": 0.6565486788749695, "learning_rate": 0.0002, "epoch": 3.3537832310838445, "step": 2460}, {"loss": 1.588, "grad_norm": 0.6449528932571411, "learning_rate": 0.0002, "epoch": 3.367416496250852, "step": 2470}, {"loss": 1.4773, "grad_norm": 0.7746227383613586, "learning_rate": 0.0002, "epoch": 3.3810497614178594, "step": 2480}, {"loss": 1.417, "grad_norm": 0.7074846029281616, "learning_rate": 0.0002, "epoch": 3.3946830265848673, "step": 2490}, {"loss": 1.4476, "grad_norm": 0.6547690033912659, "learning_rate": 0.0002, "epoch": 3.4083162917518743, "step": 2500}, {"loss": 1.4074, "grad_norm": 0.784721314907074, "learning_rate": 0.0002, "epoch": 3.4219495569188823, "step": 2510}, {"loss": 1.4326, "grad_norm": 0.7270277738571167, "learning_rate": 0.0002, "epoch": 3.4355828220858897, "step": 2520}, {"loss": 1.4354, "grad_norm": 0.67588871717453, "learning_rate": 0.0002, "epoch": 3.449216087252897, "step": 2530}, {"loss": 1.4074, "grad_norm": 0.6768023371696472, "learning_rate": 0.0002, "epoch": 3.4628493524199047, "step": 2540}, {"loss": 1.4863, "grad_norm": 0.7026481628417969, "learning_rate": 0.0002, "epoch": 3.476482617586912, "step": 2550}, {"loss": 1.468, "grad_norm": 0.646075963973999, "learning_rate": 0.0002, "epoch": 3.4901158827539196, "step": 2560}, {"loss": 1.4058, "grad_norm": 0.6288973689079285, "learning_rate": 0.0002, "epoch": 3.503749147920927, "step": 2570}, {"loss": 1.4613, "grad_norm": 0.6440825462341309, "learning_rate": 0.0002, "epoch": 3.5173824130879345, "step": 2580}, {"loss": 1.3808, "grad_norm": 0.7074111700057983, "learning_rate": 0.0002, "epoch": 3.531015678254942, "step": 2590}, {"loss": 1.4901, "grad_norm": 0.7007562518119812, "learning_rate": 0.0002, "epoch": 3.5446489434219495, "step": 2600}, {"loss": 1.4511, "grad_norm": 0.6045376658439636, "learning_rate": 0.0002, "epoch": 3.558282208588957, "step": 2610}, {"loss": 1.4596, "grad_norm": 0.9149952530860901, "learning_rate": 0.0002, "epoch": 3.5719154737559644, "step": 2620}, {"loss": 1.4355, "grad_norm": 0.6490362882614136, "learning_rate": 0.0002, "epoch": 3.585548738922972, "step": 2630}, {"loss": 1.4107, "grad_norm": 0.6552226543426514, "learning_rate": 0.0002, "epoch": 3.59918200408998, "step": 2640}, {"loss": 1.433, "grad_norm": 0.6541850566864014, "learning_rate": 0.0002, "epoch": 3.612815269256987, "step": 2650}, {"loss": 1.4279, "grad_norm": 0.6500770449638367, "learning_rate": 0.0002, "epoch": 3.6264485344239947, "step": 2660}, {"loss": 1.3929, "grad_norm": 0.6345893740653992, "learning_rate": 0.0002, "epoch": 3.640081799591002, "step": 2670}, {"loss": 1.3634, "grad_norm": 0.6382275223731995, "learning_rate": 0.0002, "epoch": 3.6537150647580097, "step": 2680}, {"loss": 1.4478, "grad_norm": 0.6738566160202026, "learning_rate": 0.0002, "epoch": 3.667348329925017, "step": 2690}, {"loss": 1.4642, "grad_norm": 0.7446315288543701, "learning_rate": 0.0002, "epoch": 3.6809815950920246, "step": 2700}, {"loss": 1.4342, "grad_norm": 0.6717571020126343, "learning_rate": 0.0002, "epoch": 3.694614860259032, "step": 2710}, {"loss": 1.4285, "grad_norm": 0.667259693145752, "learning_rate": 0.0002, "epoch": 3.7082481254260395, "step": 2720}, {"loss": 1.5389, "grad_norm": 0.6808622479438782, "learning_rate": 0.0002, "epoch": 3.721881390593047, "step": 2730}, {"loss": 1.4297, "grad_norm": 0.7254287004470825, "learning_rate": 0.0002, "epoch": 3.7355146557600545, "step": 2740}, {"loss": 1.4176, "grad_norm": 0.6864007711410522, "learning_rate": 0.0002, "epoch": 3.749147920927062, "step": 2750}, {"loss": 1.4811, "grad_norm": 0.7041361331939697, "learning_rate": 0.0002, "epoch": 3.7627811860940694, "step": 2760}, {"loss": 1.4284, "grad_norm": 0.6559903025627136, "learning_rate": 0.0002, "epoch": 3.776414451261077, "step": 2770}, {"loss": 1.4608, "grad_norm": 0.6602269411087036, "learning_rate": 0.0002, "epoch": 3.7900477164280844, "step": 2780}, {"loss": 1.4588, "grad_norm": 0.692611813545227, "learning_rate": 0.0002, "epoch": 3.8036809815950923, "step": 2790}, {"loss": 1.4065, "grad_norm": 0.7051475644111633, "learning_rate": 0.0002, "epoch": 3.8173142467620993, "step": 2800}, {"loss": 1.4083, "grad_norm": 0.6685371398925781, "learning_rate": 0.0002, "epoch": 3.830947511929107, "step": 2810}, {"loss": 1.5227, "grad_norm": 0.6706477403640747, "learning_rate": 0.0002, "epoch": 3.8445807770961147, "step": 2820}, {"loss": 1.4076, "grad_norm": 0.6671637296676636, "learning_rate": 0.0002, "epoch": 3.858214042263122, "step": 2830}, {"loss": 1.4736, "grad_norm": 0.694092333316803, "learning_rate": 0.0002, "epoch": 3.8718473074301296, "step": 2840}, {"loss": 1.4161, "grad_norm": 0.7349600195884705, "learning_rate": 0.0002, "epoch": 3.885480572597137, "step": 2850}, {"loss": 1.4617, "grad_norm": 0.6647971868515015, "learning_rate": 0.0002, "epoch": 3.8991138377641446, "step": 2860}, {"loss": 1.5046, "grad_norm": 0.806656539440155, "learning_rate": 0.0002, "epoch": 3.912747102931152, "step": 2870}, {"loss": 1.428, "grad_norm": 0.6008772850036621, "learning_rate": 0.0002, "epoch": 3.9263803680981595, "step": 2880}, {"loss": 1.4116, "grad_norm": 0.659227728843689, "learning_rate": 0.0002, "epoch": 3.940013633265167, "step": 2890}, {"loss": 1.4136, "grad_norm": 0.6357656717300415, "learning_rate": 0.0002, "epoch": 3.9536468984321744, "step": 2900}, {"loss": 1.4655, "grad_norm": 0.6541687846183777, "learning_rate": 0.0002, "epoch": 3.967280163599182, "step": 2910}, {"loss": 1.4854, "grad_norm": 0.6090909838676453, "learning_rate": 0.0002, "epoch": 3.9809134287661894, "step": 2920}, {"loss": 1.4615, "grad_norm": 0.7198411822319031, "learning_rate": 0.0002, "epoch": 3.994546693933197, "step": 2930}, {"eval_loss": 1.9278366565704346, "eval_runtime": 53.6567, "eval_samples_per_second": 9.449, "eval_steps_per_second": 1.193, "epoch": 4.0, "step": 2934}, {"loss": 1.3159, "grad_norm": 0.6498575210571289, "learning_rate": 0.0002, "epoch": 4.008179959100205, "step": 2940}, {"loss": 1.2075, "grad_norm": 0.865602433681488, "learning_rate": 0.0002, "epoch": 4.021813224267212, "step": 2950}, {"loss": 1.1744, "grad_norm": 0.8514999151229858, "learning_rate": 0.0002, "epoch": 4.03544648943422, "step": 2960}, {"loss": 1.1553, "grad_norm": 1.0677322149276733, "learning_rate": 0.0002, "epoch": 4.049079754601227, "step": 2970}, {"loss": 1.1962, "grad_norm": 1.0126488208770752, "learning_rate": 0.0002, "epoch": 4.062713019768235, "step": 2980}, {"loss": 1.1631, "grad_norm": 1.0008870363235474, "learning_rate": 0.0002, "epoch": 4.076346284935242, "step": 2990}, {"loss": 1.2154, "grad_norm": 0.7942054271697998, "learning_rate": 0.0002, "epoch": 4.08997955010225, "step": 3000}, {"loss": 1.214, "grad_norm": 1.0482100248336792, "learning_rate": 0.0002, "epoch": 4.103612815269257, "step": 3010}, {"loss": 1.1999, "grad_norm": 1.0516992807388306, "learning_rate": 0.0002, "epoch": 4.1172460804362645, "step": 3020}, {"loss": 1.2108, "grad_norm": 0.8144322037696838, "learning_rate": 0.0002, "epoch": 4.130879345603272, "step": 3030}, {"loss": 1.1782, "grad_norm": 0.952297568321228, "learning_rate": 0.0002, "epoch": 4.144512610770279, "step": 3040}, {"loss": 1.2814, "grad_norm": 1.007645606994629, "learning_rate": 0.0002, "epoch": 4.158145875937287, "step": 3050}, {"loss": 1.1731, "grad_norm": 1.0480353832244873, "learning_rate": 0.0002, "epoch": 4.171779141104294, "step": 3060}, {"loss": 1.196, "grad_norm": 0.9270663857460022, "learning_rate": 0.0002, "epoch": 4.185412406271302, "step": 3070}, {"loss": 1.2167, "grad_norm": 1.3415262699127197, "learning_rate": 0.0002, "epoch": 4.199045671438309, "step": 3080}, {"loss": 1.2601, "grad_norm": 1.167606234550476, "learning_rate": 0.0002, "epoch": 4.212678936605317, "step": 3090}, {"loss": 1.2605, "grad_norm": 0.9418690800666809, "learning_rate": 0.0002, "epoch": 4.226312201772324, "step": 3100}, {"loss": 1.2184, "grad_norm": 1.0885876417160034, "learning_rate": 0.0002, "epoch": 4.239945466939332, "step": 3110}, {"loss": 1.2594, "grad_norm": 0.9165483713150024, "learning_rate": 0.0002, "epoch": 4.253578732106339, "step": 3120}, {"loss": 1.2933, "grad_norm": 0.9154694080352783, "learning_rate": 0.0002, "epoch": 4.267211997273347, "step": 3130}, {"loss": 1.2584, "grad_norm": 1.100580096244812, "learning_rate": 0.0002, "epoch": 4.280845262440354, "step": 3140}, {"loss": 1.251, "grad_norm": 0.9367576241493225, "learning_rate": 0.0002, "epoch": 4.294478527607362, "step": 3150}, {"loss": 1.2032, "grad_norm": 0.9744015336036682, "learning_rate": 0.0002, "epoch": 4.308111792774369, "step": 3160}, {"loss": 1.2787, "grad_norm": 0.9865175485610962, "learning_rate": 0.0002, "epoch": 4.321745057941377, "step": 3170}, {"loss": 1.2161, "grad_norm": 1.0124907493591309, "learning_rate": 0.0002, "epoch": 4.335378323108385, "step": 3180}, {"loss": 1.2452, "grad_norm": 1.1044819355010986, "learning_rate": 0.0002, "epoch": 4.349011588275392, "step": 3190}, {"loss": 1.2483, "grad_norm": 0.9305577278137207, "learning_rate": 0.0002, "epoch": 4.3626448534424, "step": 3200}, {"loss": 1.2101, "grad_norm": 0.969265341758728, "learning_rate": 0.0002, "epoch": 4.376278118609407, "step": 3210}, {"loss": 1.2355, "grad_norm": 1.0671923160552979, "learning_rate": 0.0002, "epoch": 4.389911383776415, "step": 3220}, {"loss": 1.2259, "grad_norm": 0.9440539479255676, "learning_rate": 0.0002, "epoch": 4.403544648943422, "step": 3230}, {"loss": 1.1706, "grad_norm": 0.9824562668800354, "learning_rate": 0.0002, "epoch": 4.41717791411043, "step": 3240}, {"loss": 1.2234, "grad_norm": 1.0245535373687744, "learning_rate": 0.0002, "epoch": 4.430811179277437, "step": 3250}, {"loss": 1.2713, "grad_norm": 0.9629312753677368, "learning_rate": 0.0002, "epoch": 4.444444444444445, "step": 3260}, {"loss": 1.2689, "grad_norm": 1.1556470394134521, "learning_rate": 0.0002, "epoch": 4.458077709611452, "step": 3270}, {"loss": 1.2214, "grad_norm": 0.9796679019927979, "learning_rate": 0.0002, "epoch": 4.47171097477846, "step": 3280}, {"loss": 1.2823, "grad_norm": 0.9030535221099854, "learning_rate": 0.0002, "epoch": 4.485344239945467, "step": 3290}, {"loss": 1.2111, "grad_norm": 0.9142820835113525, "learning_rate": 0.0002, "epoch": 4.4989775051124745, "step": 3300}, {"loss": 1.2398, "grad_norm": 0.966867208480835, "learning_rate": 0.0002, "epoch": 4.5126107702794815, "step": 3310}, {"loss": 1.2537, "grad_norm": 1.0127079486846924, "learning_rate": 0.0002, "epoch": 4.5262440354464895, "step": 3320}, {"loss": 1.2059, "grad_norm": 1.055506706237793, "learning_rate": 0.0002, "epoch": 4.539877300613497, "step": 3330}, {"loss": 1.2958, "grad_norm": 0.9831468462944031, "learning_rate": 0.0002, "epoch": 4.553510565780504, "step": 3340}, {"loss": 1.2643, "grad_norm": 0.9304661154747009, "learning_rate": 0.0002, "epoch": 4.567143830947512, "step": 3350}, {"loss": 1.3621, "grad_norm": 0.9369107484817505, "learning_rate": 0.0002, "epoch": 4.580777096114519, "step": 3360}, {"loss": 1.2301, "grad_norm": 1.009506344795227, "learning_rate": 0.0002, "epoch": 4.594410361281527, "step": 3370}, {"loss": 1.2535, "grad_norm": 1.0575741529464722, "learning_rate": 0.0002, "epoch": 4.608043626448534, "step": 3380}, {"loss": 1.1914, "grad_norm": 0.9102860689163208, "learning_rate": 0.0002, "epoch": 4.621676891615542, "step": 3390}, {"loss": 1.3156, "grad_norm": 0.8111315965652466, "learning_rate": 0.0002, "epoch": 4.635310156782549, "step": 3400}, {"loss": 1.3103, "grad_norm": 0.9459649920463562, "learning_rate": 0.0002, "epoch": 4.648943421949557, "step": 3410}, {"loss": 1.3146, "grad_norm": 0.9709545969963074, "learning_rate": 0.0002, "epoch": 4.662576687116564, "step": 3420}, {"loss": 1.2958, "grad_norm": 0.9909247159957886, "learning_rate": 0.0002, "epoch": 4.676209952283572, "step": 3430}, {"loss": 1.3186, "grad_norm": 0.9094610810279846, "learning_rate": 0.0002, "epoch": 4.689843217450579, "step": 3440}, {"loss": 1.3397, "grad_norm": 0.9012220501899719, "learning_rate": 0.0002, "epoch": 4.703476482617587, "step": 3450}, {"loss": 1.2595, "grad_norm": 0.8669242858886719, "learning_rate": 0.0002, "epoch": 4.717109747784594, "step": 3460}, {"loss": 1.2762, "grad_norm": 0.9753699898719788, "learning_rate": 0.0002, "epoch": 4.730743012951602, "step": 3470}, {"loss": 1.2371, "grad_norm": 1.0252684354782104, "learning_rate": 0.0002, "epoch": 4.74437627811861, "step": 3480}, {"loss": 1.2536, "grad_norm": 1.208098292350769, "learning_rate": 0.0002, "epoch": 4.758009543285617, "step": 3490}, {"loss": 1.2256, "grad_norm": 0.8632914423942566, "learning_rate": 0.0002, "epoch": 4.771642808452625, "step": 3500}, {"loss": 1.3062, "grad_norm": 1.0084818601608276, "learning_rate": 0.0002, "epoch": 4.785276073619632, "step": 3510}, {"loss": 1.3004, "grad_norm": 0.9095172882080078, "learning_rate": 0.0002, "epoch": 4.79890933878664, "step": 3520}, {"loss": 1.263, "grad_norm": 0.9740135669708252, "learning_rate": 0.0002, "epoch": 4.812542603953647, "step": 3530}, {"loss": 1.2816, "grad_norm": 0.8862348794937134, "learning_rate": 0.0002, "epoch": 4.826175869120655, "step": 3540}, {"loss": 1.2275, "grad_norm": 1.0761774778366089, "learning_rate": 0.0002, "epoch": 4.839809134287662, "step": 3550}, {"loss": 1.2257, "grad_norm": 1.0134117603302002, "learning_rate": 0.0002, "epoch": 4.85344239945467, "step": 3560}, {"loss": 1.2904, "grad_norm": 0.9262851476669312, "learning_rate": 0.0002, "epoch": 4.867075664621677, "step": 3570}, {"loss": 1.1466, "grad_norm": 0.9518504738807678, "learning_rate": 0.0002, "epoch": 4.8807089297886845, "step": 3580}, {"loss": 1.2741, "grad_norm": 1.10103178024292, "learning_rate": 0.0002, "epoch": 4.894342194955692, "step": 3590}, {"loss": 1.2592, "grad_norm": 1.0133225917816162, "learning_rate": 0.0002, "epoch": 4.9079754601226995, "step": 3600}, {"loss": 1.2856, "grad_norm": 0.9637737274169922, "learning_rate": 0.0002, "epoch": 4.9216087252897065, "step": 3610}, {"loss": 1.2991, "grad_norm": 0.9800633192062378, "learning_rate": 0.0002, "epoch": 4.935241990456714, "step": 3620}, {"loss": 1.2872, "grad_norm": 1.0065973997116089, "learning_rate": 0.0002, "epoch": 4.948875255623722, "step": 3630}, {"loss": 1.2408, "grad_norm": 0.9354690313339233, "learning_rate": 0.0002, "epoch": 4.962508520790729, "step": 3640}, {"loss": 1.291, "grad_norm": 0.9744119048118591, "learning_rate": 0.0002, "epoch": 4.976141785957737, "step": 3650}, {"loss": 1.2513, "grad_norm": 0.9357708096504211, "learning_rate": 0.0002, "epoch": 4.989775051124744, "step": 3660}, {"eval_loss": 2.0763096809387207, "eval_runtime": 53.6578, "eval_samples_per_second": 9.449, "eval_steps_per_second": 1.193, "epoch": 4.999318336741649, "step": 3667}, {"loss": 1.2323, "grad_norm": 1.3171669244766235, "learning_rate": 0.0002, "epoch": 5.003408316291752, "step": 3670}, {"loss": 0.9509, "grad_norm": 1.4427374601364136, "learning_rate": 0.0002, "epoch": 5.017041581458759, "step": 3680}, {"loss": 1.011, "grad_norm": 0.9313797354698181, "learning_rate": 0.0002, "epoch": 5.030674846625767, "step": 3690}, {"loss": 0.9481, "grad_norm": 1.417641282081604, "learning_rate": 0.0002, "epoch": 5.044308111792774, "step": 3700}, {"loss": 0.9477, "grad_norm": 1.097440242767334, "learning_rate": 0.0002, "epoch": 5.057941376959782, "step": 3710}, {"loss": 1.0416, "grad_norm": 1.4277986288070679, "learning_rate": 0.0002, "epoch": 5.071574642126789, "step": 3720}, {"loss": 0.9718, "grad_norm": 1.2520873546600342, "learning_rate": 0.0002, "epoch": 5.085207907293797, "step": 3730}, {"loss": 0.9531, "grad_norm": 1.39503812789917, "learning_rate": 0.0002, "epoch": 5.098841172460804, "step": 3740}, {"loss": 0.9658, "grad_norm": 1.2345329523086548, "learning_rate": 0.0002, "epoch": 5.112474437627812, "step": 3750}, {"loss": 1.0615, "grad_norm": 1.2700239419937134, "learning_rate": 0.0002, "epoch": 5.126107702794819, "step": 3760}, {"loss": 0.993, "grad_norm": 1.5343066453933716, "learning_rate": 0.0002, "epoch": 5.139740967961827, "step": 3770}, {"loss": 0.9378, "grad_norm": 1.4191608428955078, "learning_rate": 0.0002, "epoch": 5.153374233128835, "step": 3780}, {"loss": 1.0179, "grad_norm": 1.4591023921966553, "learning_rate": 0.0002, "epoch": 5.167007498295842, "step": 3790}, {"loss": 1.0143, "grad_norm": 1.6158121824264526, "learning_rate": 0.0002, "epoch": 5.18064076346285, "step": 3800}, {"loss": 1.0056, "grad_norm": 1.6077582836151123, "learning_rate": 0.0002, "epoch": 5.194274028629857, "step": 3810}, {"loss": 0.9711, "grad_norm": 1.2815653085708618, "learning_rate": 0.0002, "epoch": 5.207907293796865, "step": 3820}, {"loss": 1.0131, "grad_norm": 1.2427219152450562, "learning_rate": 0.0002, "epoch": 5.221540558963872, "step": 3830}, {"loss": 0.9901, "grad_norm": 1.3013232946395874, "learning_rate": 0.0002, "epoch": 5.23517382413088, "step": 3840}, {"loss": 0.9862, "grad_norm": 1.4643588066101074, "learning_rate": 0.0002, "epoch": 5.248807089297887, "step": 3850}, {"loss": 1.0149, "grad_norm": 1.2571916580200195, "learning_rate": 0.0002, "epoch": 5.2624403544648946, "step": 3860}, {"loss": 0.9686, "grad_norm": 1.226682186126709, "learning_rate": 0.0002, "epoch": 5.276073619631902, "step": 3870}, {"loss": 0.9417, "grad_norm": 1.2541271448135376, "learning_rate": 0.0002, "epoch": 5.2897068847989095, "step": 3880}, {"loss": 0.9767, "grad_norm": 1.2340261936187744, "learning_rate": 0.0002, "epoch": 5.3033401499659165, "step": 3890}, {"loss": 1.0173, "grad_norm": 1.345527172088623, "learning_rate": 0.0002, "epoch": 5.316973415132924, "step": 3900}, {"loss": 1.0638, "grad_norm": 1.2128909826278687, "learning_rate": 0.0002, "epoch": 5.3306066802999315, "step": 3910}, {"loss": 1.0002, "grad_norm": 1.3052637577056885, "learning_rate": 0.0002, "epoch": 5.344239945466939, "step": 3920}, {"loss": 0.9754, "grad_norm": 1.1017392873764038, "learning_rate": 0.0002, "epoch": 5.357873210633947, "step": 3930}, {"loss": 1.0579, "grad_norm": 1.26950204372406, "learning_rate": 0.0002, "epoch": 5.371506475800954, "step": 3940}, {"loss": 1.0816, "grad_norm": 1.3372546434402466, "learning_rate": 0.0002, "epoch": 5.385139740967962, "step": 3950}, {"loss": 1.0529, "grad_norm": 1.3115156888961792, "learning_rate": 0.0002, "epoch": 5.398773006134969, "step": 3960}, {"loss": 1.1179, "grad_norm": 1.3511474132537842, "learning_rate": 0.0002, "epoch": 5.412406271301977, "step": 3970}, {"loss": 1.0352, "grad_norm": 1.1001893281936646, "learning_rate": 0.0002, "epoch": 5.426039536468984, "step": 3980}, {"loss": 1.0855, "grad_norm": 1.2810745239257812, "learning_rate": 0.0002, "epoch": 5.439672801635992, "step": 3990}, {"loss": 1.0573, "grad_norm": 1.2999306917190552, "learning_rate": 0.0002, "epoch": 5.453306066802999, "step": 4000}, {"loss": 1.0073, "grad_norm": 1.172553300857544, "learning_rate": 0.0002, "epoch": 5.466939331970007, "step": 4010}, {"loss": 1.003, "grad_norm": 1.1483557224273682, "learning_rate": 0.0002, "epoch": 5.480572597137014, "step": 4020}, {"loss": 1.0704, "grad_norm": 1.4148036241531372, "learning_rate": 0.0002, "epoch": 5.494205862304022, "step": 4030}, {"loss": 1.0519, "grad_norm": 1.1611121892929077, "learning_rate": 0.0002, "epoch": 5.507839127471029, "step": 4040}, {"loss": 1.0775, "grad_norm": 1.3837119340896606, "learning_rate": 0.0002, "epoch": 5.521472392638037, "step": 4050}, {"loss": 1.0257, "grad_norm": 1.3025696277618408, "learning_rate": 0.0002, "epoch": 5.535105657805044, "step": 4060}, {"loss": 1.0628, "grad_norm": 1.348091959953308, "learning_rate": 0.0002, "epoch": 5.548738922972052, "step": 4070}, {"loss": 1.0447, "grad_norm": 1.3463449478149414, "learning_rate": 0.0002, "epoch": 5.56237218813906, "step": 4080}, {"loss": 1.039, "grad_norm": 1.3904176950454712, "learning_rate": 0.0002, "epoch": 5.576005453306067, "step": 4090}, {"loss": 1.0963, "grad_norm": 1.2737950086593628, "learning_rate": 0.0002, "epoch": 5.589638718473074, "step": 4100}, {"loss": 1.0441, "grad_norm": 1.3311827182769775, "learning_rate": 0.0002, "epoch": 5.603271983640082, "step": 4110}, {"loss": 1.0521, "grad_norm": 1.24485182762146, "learning_rate": 0.0002, "epoch": 5.61690524880709, "step": 4120}, {"loss": 1.1103, "grad_norm": 1.2724957466125488, "learning_rate": 0.0002, "epoch": 5.630538513974097, "step": 4130}, {"loss": 1.0588, "grad_norm": 1.3439847230911255, "learning_rate": 0.0002, "epoch": 5.644171779141105, "step": 4140}, {"loss": 1.0257, "grad_norm": 1.372359037399292, "learning_rate": 0.0002, "epoch": 5.657805044308112, "step": 4150}, {"loss": 1.0475, "grad_norm": 1.2322949171066284, "learning_rate": 0.0002, "epoch": 5.6714383094751195, "step": 4160}, {"loss": 1.0465, "grad_norm": 1.4859193563461304, "learning_rate": 0.0002, "epoch": 5.6850715746421265, "step": 4170}, {"loss": 1.1569, "grad_norm": 1.4318448305130005, "learning_rate": 0.0002, "epoch": 5.6987048398091344, "step": 4180}, {"loss": 1.017, "grad_norm": 1.1533565521240234, "learning_rate": 0.0002, "epoch": 5.7123381049761415, "step": 4190}, {"loss": 1.0948, "grad_norm": 1.3009696006774902, "learning_rate": 0.0002, "epoch": 5.725971370143149, "step": 4200}, {"loss": 1.1229, "grad_norm": 1.3972162008285522, "learning_rate": 0.0002, "epoch": 5.739604635310156, "step": 4210}, {"loss": 1.033, "grad_norm": 1.2142186164855957, "learning_rate": 0.0002, "epoch": 5.753237900477164, "step": 4220}, {"loss": 1.0588, "grad_norm": 1.401191234588623, "learning_rate": 0.0002, "epoch": 5.766871165644172, "step": 4230}, {"loss": 1.0722, "grad_norm": 1.4124404191970825, "learning_rate": 0.0002, "epoch": 5.780504430811179, "step": 4240}, {"loss": 1.0826, "grad_norm": 1.3488332033157349, "learning_rate": 0.0002, "epoch": 5.794137695978186, "step": 4250}, {"loss": 1.0599, "grad_norm": 1.3671752214431763, "learning_rate": 0.0002, "epoch": 5.807770961145194, "step": 4260}, {"loss": 1.1294, "grad_norm": 1.2608201503753662, "learning_rate": 0.0002, "epoch": 5.821404226312202, "step": 4270}, {"loss": 1.1216, "grad_norm": 1.1814045906066895, "learning_rate": 0.0002, "epoch": 5.835037491479209, "step": 4280}, {"loss": 1.0973, "grad_norm": 1.4139586687088013, "learning_rate": 0.0002, "epoch": 5.848670756646217, "step": 4290}, {"loss": 1.0656, "grad_norm": 1.34248948097229, "learning_rate": 0.0002, "epoch": 5.862304021813224, "step": 4300}, {"loss": 1.0791, "grad_norm": 1.1428139209747314, "learning_rate": 0.0002, "epoch": 5.875937286980232, "step": 4310}, {"loss": 1.0556, "grad_norm": 1.1941087245941162, "learning_rate": 0.0002, "epoch": 5.889570552147239, "step": 4320}, {"loss": 1.1089, "grad_norm": 1.2374001741409302, "learning_rate": 0.0002, "epoch": 5.903203817314247, "step": 4330}, {"loss": 1.0802, "grad_norm": 1.4314988851547241, "learning_rate": 0.0002, "epoch": 5.916837082481254, "step": 4340}, {"loss": 1.133, "grad_norm": 1.1286126375198364, "learning_rate": 0.0002, "epoch": 5.930470347648262, "step": 4350}, {"loss": 1.0807, "grad_norm": 1.25884211063385, "learning_rate": 0.0002, "epoch": 5.944103612815269, "step": 4360}, {"loss": 1.1189, "grad_norm": 1.223357915878296, "learning_rate": 0.0002, "epoch": 5.957736877982277, "step": 4370}, {"loss": 1.1335, "grad_norm": 1.2173810005187988, "learning_rate": 0.0002, "epoch": 5.971370143149285, "step": 4380}, {"loss": 1.1201, "grad_norm": 1.3152292966842651, "learning_rate": 0.0002, "epoch": 5.985003408316292, "step": 4390}, {"loss": 1.1456, "grad_norm": 1.5576739311218262, "learning_rate": 0.0002, "epoch": 5.998636673483299, "step": 4400}, {"eval_loss": 2.3435311317443848, "eval_runtime": 53.6362, "eval_samples_per_second": 9.453, "eval_steps_per_second": 1.193, "epoch": 6.0, "step": 4401}, {"loss": 0.8618, "grad_norm": 2.027981758117676, "learning_rate": 0.0002, "epoch": 6.012269938650307, "step": 4410}, {"loss": 0.7702, "grad_norm": 1.4775491952896118, "learning_rate": 0.0002, "epoch": 6.025903203817315, "step": 4420}, {"loss": 0.8042, "grad_norm": 1.6902967691421509, "learning_rate": 0.0002, "epoch": 6.039536468984322, "step": 4430}, {"loss": 0.7363, "grad_norm": 1.2506479024887085, "learning_rate": 0.0002, "epoch": 6.0531697341513295, "step": 4440}, {"loss": 0.7653, "grad_norm": 1.5935661792755127, "learning_rate": 0.0002, "epoch": 6.0668029993183366, "step": 4450}, {"loss": 0.7869, "grad_norm": 1.2966011762619019, "learning_rate": 0.0002, "epoch": 6.0804362644853445, "step": 4460}, {"loss": 0.7186, "grad_norm": 1.5247948169708252, "learning_rate": 0.0002, "epoch": 6.0940695296523515, "step": 4470}, {"loss": 0.7864, "grad_norm": 1.6415225267410278, "learning_rate": 0.0002, "epoch": 6.107702794819359, "step": 4480}, {"loss": 0.7561, "grad_norm": 1.5510778427124023, "learning_rate": 0.0002, "epoch": 6.121336059986366, "step": 4490}, {"loss": 0.7628, "grad_norm": 1.361097812652588, "learning_rate": 0.0002, "epoch": 6.134969325153374, "step": 4500}, {"loss": 0.8053, "grad_norm": 1.8347383737564087, "learning_rate": 0.0002, "epoch": 6.148602590320381, "step": 4510}, {"loss": 0.8074, "grad_norm": 1.570560097694397, "learning_rate": 0.0002, "epoch": 6.162235855487389, "step": 4520}, {"loss": 0.7536, "grad_norm": 1.517993688583374, "learning_rate": 0.0002, "epoch": 6.175869120654396, "step": 4530}, {"loss": 0.8028, "grad_norm": 1.4517489671707153, "learning_rate": 0.0002, "epoch": 6.189502385821404, "step": 4540}, {"loss": 0.8633, "grad_norm": 1.557098627090454, "learning_rate": 0.0002, "epoch": 6.203135650988412, "step": 4550}, {"loss": 0.7704, "grad_norm": 1.7379891872406006, "learning_rate": 0.0002, "epoch": 6.216768916155419, "step": 4560}, {"loss": 0.7341, "grad_norm": 2.2292542457580566, "learning_rate": 0.0002, "epoch": 6.230402181322427, "step": 4570}, {"loss": 0.7883, "grad_norm": 1.834366798400879, "learning_rate": 0.0002, "epoch": 6.244035446489434, "step": 4580}, {"loss": 0.8222, "grad_norm": 1.6755090951919556, "learning_rate": 0.0002, "epoch": 6.257668711656442, "step": 4590}, {"loss": 0.8245, "grad_norm": 1.828898549079895, "learning_rate": 0.0002, "epoch": 6.271301976823449, "step": 4600}, {"loss": 0.8116, "grad_norm": 1.9773457050323486, "learning_rate": 0.0002, "epoch": 6.284935241990457, "step": 4610}, {"loss": 0.811, "grad_norm": 1.533369541168213, "learning_rate": 0.0002, "epoch": 6.298568507157464, "step": 4620}, {"loss": 0.807, "grad_norm": 1.5432997941970825, "learning_rate": 0.0002, "epoch": 6.312201772324472, "step": 4630}, {"loss": 0.818, "grad_norm": 1.6686866283416748, "learning_rate": 0.0002, "epoch": 6.325835037491479, "step": 4640}, {"loss": 0.8656, "grad_norm": 1.545304298400879, "learning_rate": 0.0002, "epoch": 6.339468302658487, "step": 4650}, {"loss": 0.8239, "grad_norm": 1.5981945991516113, "learning_rate": 0.0002, "epoch": 6.353101567825494, "step": 4660}, {"loss": 0.8162, "grad_norm": 1.6973154544830322, "learning_rate": 0.0002, "epoch": 6.366734832992502, "step": 4670}, {"loss": 0.8377, "grad_norm": 1.6782612800598145, "learning_rate": 0.0002, "epoch": 6.38036809815951, "step": 4680}, {"loss": 0.8185, "grad_norm": 1.5710086822509766, "learning_rate": 0.0002, "epoch": 6.394001363326517, "step": 4690}, {"loss": 0.7948, "grad_norm": 1.7241147756576538, "learning_rate": 0.0002, "epoch": 6.407634628493525, "step": 4700}, {"loss": 0.8768, "grad_norm": 1.7736736536026, "learning_rate": 0.0002, "epoch": 6.421267893660532, "step": 4710}, {"loss": 0.8607, "grad_norm": 1.7924901247024536, "learning_rate": 0.0002, "epoch": 6.4349011588275395, "step": 4720}, {"loss": 0.832, "grad_norm": 1.4030500650405884, "learning_rate": 0.0002, "epoch": 6.448534423994547, "step": 4730}, {"loss": 0.8806, "grad_norm": 1.6925519704818726, "learning_rate": 0.0002, "epoch": 6.4621676891615545, "step": 4740}, {"loss": 0.8556, "grad_norm": 1.362905502319336, "learning_rate": 0.0002, "epoch": 6.4758009543285615, "step": 4750}, {"loss": 0.838, "grad_norm": 1.5281150341033936, "learning_rate": 0.0002, "epoch": 6.489434219495569, "step": 4760}, {"loss": 0.8396, "grad_norm": 1.524671196937561, "learning_rate": 0.0002, "epoch": 6.5030674846625764, "step": 4770}, {"loss": 0.8225, "grad_norm": 1.7029320001602173, "learning_rate": 0.0002, "epoch": 6.516700749829584, "step": 4780}, {"loss": 0.8377, "grad_norm": 1.4663511514663696, "learning_rate": 0.0002, "epoch": 6.530334014996591, "step": 4790}, {"loss": 0.8018, "grad_norm": 1.7682101726531982, "learning_rate": 0.0002, "epoch": 6.543967280163599, "step": 4800}, {"loss": 0.8318, "grad_norm": 1.6056565046310425, "learning_rate": 0.0002, "epoch": 6.557600545330606, "step": 4810}, {"loss": 0.8747, "grad_norm": 1.6552391052246094, "learning_rate": 0.0002, "epoch": 6.571233810497614, "step": 4820}, {"loss": 0.8559, "grad_norm": 1.4265215396881104, "learning_rate": 0.0002, "epoch": 6.584867075664622, "step": 4830}, {"loss": 0.8606, "grad_norm": 1.6225470304489136, "learning_rate": 0.0002, "epoch": 6.598500340831629, "step": 4840}, {"loss": 0.8817, "grad_norm": 1.6568684577941895, "learning_rate": 0.0002, "epoch": 6.612133605998636, "step": 4850}, {"loss": 0.8825, "grad_norm": 1.760115146636963, "learning_rate": 0.0002, "epoch": 6.625766871165644, "step": 4860}, {"loss": 0.9227, "grad_norm": 1.627966046333313, "learning_rate": 0.0002, "epoch": 6.639400136332652, "step": 4870}, {"loss": 0.8825, "grad_norm": 1.7053254842758179, "learning_rate": 0.0002, "epoch": 6.653033401499659, "step": 4880}, {"loss": 0.857, "grad_norm": 1.5339484214782715, "learning_rate": 0.0002, "epoch": 6.666666666666667, "step": 4890}, {"loss": 0.8482, "grad_norm": 1.5594874620437622, "learning_rate": 0.0002, "epoch": 6.680299931833674, "step": 4900}, {"loss": 0.842, "grad_norm": 1.5322152376174927, "learning_rate": 0.0002, "epoch": 6.693933197000682, "step": 4910}, {"loss": 0.8049, "grad_norm": 1.733410358428955, "learning_rate": 0.0002, "epoch": 6.707566462167689, "step": 4920}, {"loss": 0.9099, "grad_norm": 1.3626887798309326, "learning_rate": 0.0002, "epoch": 6.721199727334697, "step": 4930}, {"loss": 0.9481, "grad_norm": 1.6323494911193848, "learning_rate": 0.0002, "epoch": 6.734832992501704, "step": 4940}, {"loss": 0.8803, "grad_norm": 1.6548917293548584, "learning_rate": 0.0002, "epoch": 6.748466257668712, "step": 4950}, {"loss": 0.9149, "grad_norm": 1.7894278764724731, "learning_rate": 0.0002, "epoch": 6.762099522835719, "step": 4960}, {"loss": 0.9137, "grad_norm": 1.7960841655731201, "learning_rate": 0.0002, "epoch": 6.775732788002727, "step": 4970}, {"loss": 0.9088, "grad_norm": 1.4888852834701538, "learning_rate": 0.0002, "epoch": 6.789366053169735, "step": 4980}, {"loss": 0.9495, "grad_norm": 1.6368865966796875, "learning_rate": 0.0002, "epoch": 6.802999318336742, "step": 4990}, {"loss": 0.9939, "grad_norm": 1.7106667757034302, "learning_rate": 0.0002, "epoch": 6.816632583503749, "step": 5000}, {"loss": 0.8551, "grad_norm": 4.131956100463867, "learning_rate": 0.0002, "epoch": 6.830265848670757, "step": 5010}, {"loss": 0.908, "grad_norm": 1.6357536315917969, "learning_rate": 0.0002, "epoch": 6.8438991138377645, "step": 5020}, {"loss": 0.8661, "grad_norm": 1.621524453163147, "learning_rate": 0.0002, "epoch": 6.8575323790047715, "step": 5030}, {"loss": 0.9177, "grad_norm": 1.6400790214538574, "learning_rate": 0.0002, "epoch": 6.871165644171779, "step": 5040}, {"loss": 0.9204, "grad_norm": 1.823006272315979, "learning_rate": 0.0002, "epoch": 6.8847989093387865, "step": 5050}, {"loss": 0.9133, "grad_norm": 1.6328210830688477, "learning_rate": 0.0002, "epoch": 6.898432174505794, "step": 5060}, {"loss": 0.9138, "grad_norm": 1.3616089820861816, "learning_rate": 0.0002, "epoch": 6.912065439672801, "step": 5070}, {"loss": 0.8791, "grad_norm": 1.7202986478805542, "learning_rate": 0.0002, "epoch": 6.925698704839809, "step": 5080}, {"loss": 0.8331, "grad_norm": 1.8145297765731812, "learning_rate": 0.0002, "epoch": 6.939331970006816, "step": 5090}, {"loss": 0.861, "grad_norm": 1.5432910919189453, "learning_rate": 0.0002, "epoch": 6.952965235173824, "step": 5100}, {"loss": 0.9282, "grad_norm": 1.2784099578857422, "learning_rate": 0.0002, "epoch": 6.966598500340831, "step": 5110}, {"loss": 0.9189, "grad_norm": 1.556593894958496, "learning_rate": 0.0002, "epoch": 6.980231765507839, "step": 5120}, {"loss": 0.8961, "grad_norm": 1.5102856159210205, "learning_rate": 0.0002, "epoch": 6.993865030674847, "step": 5130}, {"eval_loss": 2.5376713275909424, "eval_runtime": 53.6377, "eval_samples_per_second": 9.452, "eval_steps_per_second": 1.193, "epoch": 6.999318336741649, "step": 5134}, {"loss": 0.7888, "grad_norm": 1.7083442211151123, "learning_rate": 0.0002, "epoch": 7.007498295841854, "step": 5140}, {"loss": 0.581, "grad_norm": 1.95943021774292, "learning_rate": 0.0002, "epoch": 7.021131561008862, "step": 5150}, {"loss": 0.5631, "grad_norm": 1.453168511390686, "learning_rate": 0.0002, "epoch": 7.034764826175869, "step": 5160}, {"loss": 0.5871, "grad_norm": 2.110145092010498, "learning_rate": 0.0002, "epoch": 7.048398091342877, "step": 5170}, {"loss": 0.5418, "grad_norm": 1.567636489868164, "learning_rate": 0.0002, "epoch": 7.062031356509884, "step": 5180}, {"loss": 0.611, "grad_norm": 1.8596835136413574, "learning_rate": 0.0002, "epoch": 7.075664621676892, "step": 5190}, {"loss": 0.6174, "grad_norm": 1.7342605590820312, "learning_rate": 0.0002, "epoch": 7.089297886843899, "step": 5200}, {"loss": 0.5632, "grad_norm": 1.516591191291809, "learning_rate": 0.0002, "epoch": 7.102931152010907, "step": 5210}, {"loss": 0.5977, "grad_norm": 1.7696505784988403, "learning_rate": 0.0002, "epoch": 7.116564417177914, "step": 5220}, {"loss": 0.594, "grad_norm": 2.1680636405944824, "learning_rate": 0.0002, "epoch": 7.130197682344922, "step": 5230}, {"loss": 0.5885, "grad_norm": 1.6825456619262695, "learning_rate": 0.0002, "epoch": 7.143830947511929, "step": 5240}, {"loss": 0.6169, "grad_norm": 2.036949634552002, "learning_rate": 0.0002, "epoch": 7.157464212678937, "step": 5250}, {"loss": 0.6561, "grad_norm": 1.8820315599441528, "learning_rate": 0.0002, "epoch": 7.171097477845944, "step": 5260}, {"loss": 0.6445, "grad_norm": 2.313140630722046, "learning_rate": 0.0002, "epoch": 7.184730743012952, "step": 5270}, {"loss": 0.6265, "grad_norm": 2.0305309295654297, "learning_rate": 0.0002, "epoch": 7.198364008179959, "step": 5280}, {"loss": 0.5909, "grad_norm": 1.707711100578308, "learning_rate": 0.0002, "epoch": 7.211997273346967, "step": 5290}, {"loss": 0.6321, "grad_norm": 1.687009334564209, "learning_rate": 0.0002, "epoch": 7.2256305385139745, "step": 5300}, {"loss": 0.6435, "grad_norm": 2.0011701583862305, "learning_rate": 0.0002, "epoch": 7.2392638036809815, "step": 5310}, {"loss": 0.5955, "grad_norm": 1.9455368518829346, "learning_rate": 0.0002, "epoch": 7.2528970688479895, "step": 5320}, {"loss": 0.6644, "grad_norm": 1.5780237913131714, "learning_rate": 0.0002, "epoch": 7.2665303340149965, "step": 5330}, {"loss": 0.6007, "grad_norm": 2.1882123947143555, "learning_rate": 0.0002, "epoch": 7.280163599182004, "step": 5340}, {"loss": 0.6055, "grad_norm": 2.089590549468994, "learning_rate": 0.0002, "epoch": 7.293796864349011, "step": 5350}, {"loss": 0.6138, "grad_norm": 1.8626707792282104, "learning_rate": 0.0002, "epoch": 7.307430129516019, "step": 5360}, {"loss": 0.6269, "grad_norm": 2.127977132797241, "learning_rate": 0.0002, "epoch": 7.321063394683026, "step": 5370}, {"loss": 0.6629, "grad_norm": 1.6568187475204468, "learning_rate": 0.0002, "epoch": 7.334696659850034, "step": 5380}, {"loss": 0.6263, "grad_norm": 1.5592522621154785, "learning_rate": 0.0002, "epoch": 7.348329925017041, "step": 5390}, {"loss": 0.6351, "grad_norm": 1.7897852659225464, "learning_rate": 0.0002, "epoch": 7.361963190184049, "step": 5400}, {"loss": 0.6319, "grad_norm": 2.071516275405884, "learning_rate": 0.0002, "epoch": 7.375596455351056, "step": 5410}, {"loss": 0.6486, "grad_norm": 2.048238515853882, "learning_rate": 0.0002, "epoch": 7.389229720518064, "step": 5420}, {"loss": 0.7037, "grad_norm": 1.770015001296997, "learning_rate": 0.0002, "epoch": 7.402862985685071, "step": 5430}, {"loss": 0.6719, "grad_norm": 1.7530136108398438, "learning_rate": 0.0002, "epoch": 7.416496250852079, "step": 5440}, {"loss": 0.6392, "grad_norm": 1.8113389015197754, "learning_rate": 0.0002, "epoch": 7.430129516019086, "step": 5450}, {"loss": 0.6589, "grad_norm": 1.8129119873046875, "learning_rate": 0.0002, "epoch": 7.443762781186094, "step": 5460}, {"loss": 0.6786, "grad_norm": 1.7961417436599731, "learning_rate": 0.0002, "epoch": 7.457396046353102, "step": 5470}, {"loss": 0.6492, "grad_norm": 1.8811243772506714, "learning_rate": 0.0002, "epoch": 7.471029311520109, "step": 5480}, {"loss": 0.6442, "grad_norm": 1.9619536399841309, "learning_rate": 0.0002, "epoch": 7.484662576687117, "step": 5490}, {"loss": 0.6372, "grad_norm": 1.9449920654296875, "learning_rate": 0.0002, "epoch": 7.498295841854124, "step": 5500}, {"loss": 0.6543, "grad_norm": 2.0600240230560303, "learning_rate": 0.0002, "epoch": 7.511929107021132, "step": 5510}, {"loss": 0.6695, "grad_norm": 1.9339587688446045, "learning_rate": 0.0002, "epoch": 7.525562372188139, "step": 5520}, {"loss": 0.7385, "grad_norm": 2.0672056674957275, "learning_rate": 0.0002, "epoch": 7.539195637355147, "step": 5530}, {"loss": 0.6678, "grad_norm": 1.8305774927139282, "learning_rate": 0.0002, "epoch": 7.552828902522154, "step": 5540}, {"loss": 0.7, "grad_norm": 1.9546589851379395, "learning_rate": 0.0002, "epoch": 7.566462167689162, "step": 5550}, {"loss": 0.6481, "grad_norm": 1.657498836517334, "learning_rate": 0.0002, "epoch": 7.580095432856169, "step": 5560}, {"loss": 0.6604, "grad_norm": 2.0222396850585938, "learning_rate": 0.0002, "epoch": 7.593728698023177, "step": 5570}, {"loss": 0.7154, "grad_norm": 1.9352941513061523, "learning_rate": 0.0002, "epoch": 7.6073619631901845, "step": 5580}, {"loss": 0.6926, "grad_norm": 1.9743294715881348, "learning_rate": 0.0002, "epoch": 7.620995228357192, "step": 5590}, {"loss": 0.6948, "grad_norm": 1.949228048324585, "learning_rate": 0.0002, "epoch": 7.634628493524199, "step": 5600}, {"loss": 0.6755, "grad_norm": 2.009384870529175, "learning_rate": 0.0002, "epoch": 7.6482617586912065, "step": 5610}, {"loss": 0.7467, "grad_norm": 1.9622714519500732, "learning_rate": 0.0002, "epoch": 7.661895023858214, "step": 5620}, {"loss": 0.7047, "grad_norm": 2.142486810684204, "learning_rate": 0.0002, "epoch": 7.675528289025221, "step": 5630}, {"loss": 0.6908, "grad_norm": 2.4306538105010986, "learning_rate": 0.0002, "epoch": 7.689161554192229, "step": 5640}, {"loss": 0.6592, "grad_norm": 1.8343422412872314, "learning_rate": 0.0002, "epoch": 7.702794819359236, "step": 5650}, {"loss": 0.7052, "grad_norm": 2.1571617126464844, "learning_rate": 0.0002, "epoch": 7.716428084526244, "step": 5660}, {"loss": 0.6958, "grad_norm": 2.028083086013794, "learning_rate": 0.0002, "epoch": 7.730061349693251, "step": 5670}, {"loss": 0.6896, "grad_norm": 2.0310823917388916, "learning_rate": 0.0002, "epoch": 7.743694614860259, "step": 5680}, {"loss": 0.6927, "grad_norm": 1.9675135612487793, "learning_rate": 0.0002, "epoch": 7.757327880027266, "step": 5690}, {"loss": 0.6985, "grad_norm": 2.082470417022705, "learning_rate": 0.0002, "epoch": 7.770961145194274, "step": 5700}, {"loss": 0.7519, "grad_norm": 1.8454886674880981, "learning_rate": 0.0002, "epoch": 7.784594410361281, "step": 5710}, {"loss": 0.7407, "grad_norm": 2.0777692794799805, "learning_rate": 0.0002, "epoch": 7.798227675528289, "step": 5720}, {"loss": 0.7149, "grad_norm": 1.751173496246338, "learning_rate": 0.0002, "epoch": 7.811860940695297, "step": 5730}, {"loss": 0.7126, "grad_norm": 1.7728252410888672, "learning_rate": 0.0002, "epoch": 7.825494205862304, "step": 5740}, {"loss": 0.7494, "grad_norm": 1.9239917993545532, "learning_rate": 0.0002, "epoch": 7.839127471029311, "step": 5750}, {"loss": 0.7374, "grad_norm": 2.0526111125946045, "learning_rate": 0.0002, "epoch": 7.852760736196319, "step": 5760}, {"loss": 0.713, "grad_norm": 2.097938060760498, "learning_rate": 0.0002, "epoch": 7.866394001363327, "step": 5770}, {"loss": 0.7391, "grad_norm": 1.8992373943328857, "learning_rate": 0.0002, "epoch": 7.880027266530334, "step": 5780}, {"loss": 0.6744, "grad_norm": 1.812042474746704, "learning_rate": 0.0002, "epoch": 7.893660531697342, "step": 5790}, {"loss": 0.7803, "grad_norm": 1.9535222053527832, "learning_rate": 0.0002, "epoch": 7.907293796864349, "step": 5800}, {"loss": 0.6998, "grad_norm": 2.0650830268859863, "learning_rate": 0.0002, "epoch": 7.920927062031357, "step": 5810}, {"loss": 0.7134, "grad_norm": 1.818130612373352, "learning_rate": 0.0002, "epoch": 7.934560327198364, "step": 5820}, {"loss": 0.7356, "grad_norm": 1.9505265951156616, "learning_rate": 0.0002, "epoch": 7.948193592365372, "step": 5830}, {"loss": 0.6872, "grad_norm": 2.072112798690796, "learning_rate": 0.0002, "epoch": 7.961826857532379, "step": 5840}, {"loss": 0.6792, "grad_norm": 1.6640431880950928, "learning_rate": 0.0002, "epoch": 7.975460122699387, "step": 5850}, {"loss": 0.7391, "grad_norm": 1.7920113801956177, "learning_rate": 0.0002, "epoch": 7.989093387866394, "step": 5860}]}