diff --git a/.gitattributes b/.gitattributes
index 33736f02c744a5faccc58f9e7e578bc77b8fca4e..306d15af5e77e2dd162b433825f1a0edc089143d 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -4522,3 +4522,12 @@ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_
 Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-0/checkpoint-6088/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-0/checkpoint-761/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/README.md b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d63cb87eaccf2d81de3cdcfa11d2e99c440c0ea0
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..964125ab9fd48536bbe987c48ca9e996e5223801
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deffe23be2cae0be54e805f07b2006c881109d56dcdd7ea094daa5e4104a6166
+size 109069176
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/README.md b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d63cb87eaccf2d81de3cdcfa11d2e99c440c0ea0
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..964125ab9fd48536bbe987c48ca9e996e5223801
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deffe23be2cae0be54e805f07b2006c881109d56dcdd7ea094daa5e4104a6166
+size 109069176
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4cc5164d2824cc1b5adb231cfd133903bd134581
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9128601b1dd4f51e15837ab80efc0df1aa48d229d6814175d61814abb8d2ab3a
+size 55532666
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..034f4a7091ed7da31368f43c194f34e37f4de50f
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:865e3a66c19eeaa7806ebffa8e8ab75dbe90f022d68806907afee9e68de72b83
+size 14244
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bba2ffdbf1afae84b09ca25865a1063b1b54a634
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7849289b953e46b8a593b8a68c5290cd1cb1d956d606e9dd6f3a91f537dd7d22
+size 1064
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/tokenizer_config.json
@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..47d405655e45010dc1287a673cb6cda39e7b053c
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/trainer_state.json
@@ -0,0 +1,1092 @@
+{
+  "best_metric": 1.8132041692733765,
+  "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497",
+  "epoch": 2.0,
+  "eval_steps": 10,
+  "global_step": 1497,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013360053440213761,
+      "grad_norm": 0.5097216367721558,
+      "learning_rate": 0.0002,
+      "loss": 2.6569,
+      "step": 10
+    },
+    {
+      "epoch": 0.026720106880427523,
+      "grad_norm": 0.5924790501594543,
+      "learning_rate": 0.0002,
+      "loss": 2.2557,
+      "step": 20
+    },
+    {
+      "epoch": 0.04008016032064128,
+      "grad_norm": 0.5158102512359619,
+      "learning_rate": 0.0002,
+      "loss": 2.0626,
+      "step": 30
+    },
+    {
+      "epoch": 0.053440213760855046,
+      "grad_norm": 0.5033753514289856,
+      "learning_rate": 0.0002,
+      "loss": 1.9452,
+      "step": 40
+    },
+    {
+      "epoch": 0.06680026720106881,
+      "grad_norm": 0.5390949845314026,
+      "learning_rate": 0.0002,
+      "loss": 1.9128,
+      "step": 50
+    },
+    {
+      "epoch": 0.08016032064128256,
+      "grad_norm": 0.6376217007637024,
+      "learning_rate": 0.0002,
+      "loss": 1.937,
+      "step": 60
+    },
+    {
+      "epoch": 0.09352037408149633,
+      "grad_norm": 0.4202035069465637,
+      "learning_rate": 0.0002,
+      "loss": 1.929,
+      "step": 70
+    },
+    {
+      "epoch": 0.10688042752171009,
+      "grad_norm": 0.4269474744796753,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 80
+    },
+    {
+      "epoch": 0.12024048096192384,
+      "grad_norm": 0.4306574761867523,
+      "learning_rate": 0.0002,
+      "loss": 1.8303,
+      "step": 90
+    },
+    {
+      "epoch": 0.13360053440213762,
+      "grad_norm": 0.5297011137008667,
+      "learning_rate": 0.0002,
+      "loss": 1.8469,
+      "step": 100
+    },
+    {
+      "epoch": 0.14696058784235136,
+      "grad_norm": 1.2313778400421143,
+      "learning_rate": 0.0002,
+      "loss": 1.864,
+      "step": 110
+    },
+    {
+      "epoch": 0.16032064128256512,
+      "grad_norm": 0.5351294279098511,
+      "learning_rate": 0.0002,
+      "loss": 1.8531,
+      "step": 120
+    },
+    {
+      "epoch": 0.1736806947227789,
+      "grad_norm": 0.4848092496395111,
+      "learning_rate": 0.0002,
+      "loss": 1.9232,
+      "step": 130
+    },
+    {
+      "epoch": 0.18704074816299265,
+      "grad_norm": 0.4339500665664673,
+      "learning_rate": 0.0002,
+      "loss": 1.8633,
+      "step": 140
+    },
+    {
+      "epoch": 0.20040080160320642,
+      "grad_norm": 0.46877285838127136,
+      "learning_rate": 0.0002,
+      "loss": 1.816,
+      "step": 150
+    },
+    {
+      "epoch": 0.21376085504342018,
+      "grad_norm": 0.5600412487983704,
+      "learning_rate": 0.0002,
+      "loss": 1.8033,
+      "step": 160
+    },
+    {
+      "epoch": 0.22712090848363392,
+      "grad_norm": 0.3733620345592499,
+      "learning_rate": 0.0002,
+      "loss": 1.8162,
+      "step": 170
+    },
+    {
+      "epoch": 0.24048096192384769,
+      "grad_norm": 0.5116042494773865,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 180
+    },
+    {
+      "epoch": 0.25384101536406145,
+      "grad_norm": 0.4071602523326874,
+      "learning_rate": 0.0002,
+      "loss": 1.915,
+      "step": 190
+    },
+    {
+      "epoch": 0.26720106880427524,
+      "grad_norm": 0.44189608097076416,
+      "learning_rate": 0.0002,
+      "loss": 1.7984,
+      "step": 200
+    },
+    {
+      "epoch": 0.280561122244489,
+      "grad_norm": 0.398699015378952,
+      "learning_rate": 0.0002,
+      "loss": 1.8728,
+      "step": 210
+    },
+    {
+      "epoch": 0.2939211756847027,
+      "grad_norm": 0.3585626482963562,
+      "learning_rate": 0.0002,
+      "loss": 1.8205,
+      "step": 220
+    },
+    {
+      "epoch": 0.3072812291249165,
+      "grad_norm": 0.3811776041984558,
+      "learning_rate": 0.0002,
+      "loss": 1.8861,
+      "step": 230
+    },
+    {
+      "epoch": 0.32064128256513025,
+      "grad_norm": 0.37261509895324707,
+      "learning_rate": 0.0002,
+      "loss": 1.8365,
+      "step": 240
+    },
+    {
+      "epoch": 0.33400133600534404,
+      "grad_norm": 0.39762404561042786,
+      "learning_rate": 0.0002,
+      "loss": 1.9186,
+      "step": 250
+    },
+    {
+      "epoch": 0.3473613894455578,
+      "grad_norm": 0.3509528934955597,
+      "learning_rate": 0.0002,
+      "loss": 1.7965,
+      "step": 260
+    },
+    {
+      "epoch": 0.36072144288577157,
+      "grad_norm": 0.3169104754924774,
+      "learning_rate": 0.0002,
+      "loss": 1.7802,
+      "step": 270
+    },
+    {
+      "epoch": 0.3740814963259853,
+      "grad_norm": 0.33714795112609863,
+      "learning_rate": 0.0002,
+      "loss": 1.8038,
+      "step": 280
+    },
+    {
+      "epoch": 0.38744154976619904,
+      "grad_norm": 1.2936875820159912,
+      "learning_rate": 0.0002,
+      "loss": 1.787,
+      "step": 290
+    },
+    {
+      "epoch": 0.40080160320641284,
+      "grad_norm": 0.3459427058696747,
+      "learning_rate": 0.0002,
+      "loss": 1.7974,
+      "step": 300
+    },
+    {
+      "epoch": 0.4141616566466266,
+      "grad_norm": 0.3380655348300934,
+      "learning_rate": 0.0002,
+      "loss": 1.8879,
+      "step": 310
+    },
+    {
+      "epoch": 0.42752171008684037,
+      "grad_norm": 0.3890381455421448,
+      "learning_rate": 0.0002,
+      "loss": 1.9196,
+      "step": 320
+    },
+    {
+      "epoch": 0.4408817635270541,
+      "grad_norm": 0.432327002286911,
+      "learning_rate": 0.0002,
+      "loss": 1.8034,
+      "step": 330
+    },
+    {
+      "epoch": 0.45424181696726784,
+      "grad_norm": 0.3736560046672821,
+      "learning_rate": 0.0002,
+      "loss": 1.8443,
+      "step": 340
+    },
+    {
+      "epoch": 0.46760187040748163,
+      "grad_norm": 0.3700982630252838,
+      "learning_rate": 0.0002,
+      "loss": 1.8506,
+      "step": 350
+    },
+    {
+      "epoch": 0.48096192384769537,
+      "grad_norm": 0.4533902406692505,
+      "learning_rate": 0.0002,
+      "loss": 1.7978,
+      "step": 360
+    },
+    {
+      "epoch": 0.49432197728790916,
+      "grad_norm": 0.35999053716659546,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 370
+    },
+    {
+      "epoch": 0.5076820307281229,
+      "grad_norm": 0.3490903675556183,
+      "learning_rate": 0.0002,
+      "loss": 1.7995,
+      "step": 380
+    },
+    {
+      "epoch": 0.5210420841683366,
+      "grad_norm": 0.34704291820526123,
+      "learning_rate": 0.0002,
+      "loss": 1.8709,
+      "step": 390
+    },
+    {
+      "epoch": 0.5344021376085505,
+      "grad_norm": 0.343565434217453,
+      "learning_rate": 0.0002,
+      "loss": 1.7948,
+      "step": 400
+    },
+    {
+      "epoch": 0.5477621910487642,
+      "grad_norm": 0.3573552966117859,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 410
+    },
+    {
+      "epoch": 0.561122244488978,
+      "grad_norm": 0.32980719208717346,
+      "learning_rate": 0.0002,
+      "loss": 1.8477,
+      "step": 420
+    },
+    {
+      "epoch": 0.5744822979291917,
+      "grad_norm": 0.356952428817749,
+      "learning_rate": 0.0002,
+      "loss": 1.9233,
+      "step": 430
+    },
+    {
+      "epoch": 0.5878423513694054,
+      "grad_norm": 0.3170869052410126,
+      "learning_rate": 0.0002,
+      "loss": 1.7433,
+      "step": 440
+    },
+    {
+      "epoch": 0.6012024048096193,
+      "grad_norm": 0.35233718156814575,
+      "learning_rate": 0.0002,
+      "loss": 1.7607,
+      "step": 450
+    },
+    {
+      "epoch": 0.614562458249833,
+      "grad_norm": 0.3480125367641449,
+      "learning_rate": 0.0002,
+      "loss": 1.8111,
+      "step": 460
+    },
+    {
+      "epoch": 0.6279225116900468,
+      "grad_norm": 0.4762810468673706,
+      "learning_rate": 0.0002,
+      "loss": 1.8386,
+      "step": 470
+    },
+    {
+      "epoch": 0.6412825651302605,
+      "grad_norm": 0.3907663822174072,
+      "learning_rate": 0.0002,
+      "loss": 1.805,
+      "step": 480
+    },
+    {
+      "epoch": 0.6546426185704742,
+      "grad_norm": 0.36315613985061646,
+      "learning_rate": 0.0002,
+      "loss": 1.8113,
+      "step": 490
+    },
+    {
+      "epoch": 0.6680026720106881,
+      "grad_norm": 0.377796471118927,
+      "learning_rate": 0.0002,
+      "loss": 1.7805,
+      "step": 500
+    },
+    {
+      "epoch": 0.6813627254509018,
+      "grad_norm": 0.34284207224845886,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 510
+    },
+    {
+      "epoch": 0.6947227788911156,
+      "grad_norm": 0.35563018918037415,
+      "learning_rate": 0.0002,
+      "loss": 1.8013,
+      "step": 520
+    },
+    {
+      "epoch": 0.7080828323313293,
+      "grad_norm": 0.37575867772102356,
+      "learning_rate": 0.0002,
+      "loss": 1.8414,
+      "step": 530
+    },
+    {
+      "epoch": 0.7214428857715431,
+      "grad_norm": 0.35719701647758484,
+      "learning_rate": 0.0002,
+      "loss": 1.7993,
+      "step": 540
+    },
+    {
+      "epoch": 0.7348029392117569,
+      "grad_norm": 0.385813444852829,
+      "learning_rate": 0.0002,
+      "loss": 1.7574,
+      "step": 550
+    },
+    {
+      "epoch": 0.7481629926519706,
+      "grad_norm": 0.44509607553482056,
+      "learning_rate": 0.0002,
+      "loss": 1.7985,
+      "step": 560
+    },
+    {
+      "epoch": 0.7615230460921844,
+      "grad_norm": 0.36108464002609253,
+      "learning_rate": 0.0002,
+      "loss": 1.7459,
+      "step": 570
+    },
+    {
+      "epoch": 0.7748830995323981,
+      "grad_norm": 0.3530745804309845,
+      "learning_rate": 0.0002,
+      "loss": 1.8207,
+      "step": 580
+    },
+    {
+      "epoch": 0.7882431529726119,
+      "grad_norm": 0.34888574481010437,
+      "learning_rate": 0.0002,
+      "loss": 1.7479,
+      "step": 590
+    },
+    {
+      "epoch": 0.8016032064128257,
+      "grad_norm": 0.387346476316452,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 600
+    },
+    {
+      "epoch": 0.8149632598530394,
+      "grad_norm": 0.3641138970851898,
+      "learning_rate": 0.0002,
+      "loss": 1.8071,
+      "step": 610
+    },
+    {
+      "epoch": 0.8283233132932531,
+      "grad_norm": 0.33729103207588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7531,
+      "step": 620
+    },
+    {
+      "epoch": 0.8416833667334669,
+      "grad_norm": 0.3652004599571228,
+      "learning_rate": 0.0002,
+      "loss": 1.8613,
+      "step": 630
+    },
+    {
+      "epoch": 0.8550434201736807,
+      "grad_norm": 0.3986643850803375,
+      "learning_rate": 0.0002,
+      "loss": 1.9184,
+      "step": 640
+    },
+    {
+      "epoch": 0.8684034736138945,
+      "grad_norm": 0.3458964228630066,
+      "learning_rate": 0.0002,
+      "loss": 1.8198,
+      "step": 650
+    },
+    {
+      "epoch": 0.8817635270541082,
+      "grad_norm": 0.3559381365776062,
+      "learning_rate": 0.0002,
+      "loss": 1.803,
+      "step": 660
+    },
+    {
+      "epoch": 0.895123580494322,
+      "grad_norm": 0.3612841069698334,
+      "learning_rate": 0.0002,
+      "loss": 1.7641,
+      "step": 670
+    },
+    {
+      "epoch": 0.9084836339345357,
+      "grad_norm": 0.34771719574928284,
+      "learning_rate": 0.0002,
+      "loss": 1.7888,
+      "step": 680
+    },
+    {
+      "epoch": 0.9218436873747495,
+      "grad_norm": 0.3371497094631195,
+      "learning_rate": 0.0002,
+      "loss": 1.8204,
+      "step": 690
+    },
+    {
+      "epoch": 0.9352037408149633,
+      "grad_norm": 0.5596055388450623,
+      "learning_rate": 0.0002,
+      "loss": 1.7848,
+      "step": 700
+    },
+    {
+      "epoch": 0.948563794255177,
+      "grad_norm": 0.311880499124527,
+      "learning_rate": 0.0002,
+      "loss": 1.7794,
+      "step": 710
+    },
+    {
+      "epoch": 0.9619238476953907,
+      "grad_norm": 0.3462068736553192,
+      "learning_rate": 0.0002,
+      "loss": 1.8464,
+      "step": 720
+    },
+    {
+      "epoch": 0.9752839011356046,
+      "grad_norm": 0.29982393980026245,
+      "learning_rate": 0.0002,
+      "loss": 1.8197,
+      "step": 730
+    },
+    {
+      "epoch": 0.9886439545758183,
+      "grad_norm": 0.34606459736824036,
+      "learning_rate": 0.0002,
+      "loss": 1.8503,
+      "step": 740
+    },
+    {
+      "epoch": 0.9993319973279893,
+      "eval_loss": 1.8201380968093872,
+      "eval_runtime": 38.6124,
+      "eval_samples_per_second": 13.338,
+      "eval_steps_per_second": 1.683,
+      "step": 748
+    },
+    {
+      "epoch": 1.002004008016032,
+      "grad_norm": 0.32302048802375793,
+      "learning_rate": 0.0002,
+      "loss": 1.7786,
+      "step": 750
+    },
+    {
+      "epoch": 1.0153640614562458,
+      "grad_norm": 0.37585633993148804,
+      "learning_rate": 0.0002,
+      "loss": 1.7297,
+      "step": 760
+    },
+    {
+      "epoch": 1.0287241148964597,
+      "grad_norm": 0.33826273679733276,
+      "learning_rate": 0.0002,
+      "loss": 1.7008,
+      "step": 770
+    },
+    {
+      "epoch": 1.0420841683366733,
+      "grad_norm": 0.44682955741882324,
+      "learning_rate": 0.0002,
+      "loss": 1.809,
+      "step": 780
+    },
+    {
+      "epoch": 1.0554442217768871,
+      "grad_norm": 0.422188401222229,
+      "learning_rate": 0.0002,
+      "loss": 1.7092,
+      "step": 790
+    },
+    {
+      "epoch": 1.0688042752171008,
+      "grad_norm": 0.3809906244277954,
+      "learning_rate": 0.0002,
+      "loss": 1.7765,
+      "step": 800
+    },
+    {
+      "epoch": 1.0821643286573146,
+      "grad_norm": 0.3454349637031555,
+      "learning_rate": 0.0002,
+      "loss": 1.7431,
+      "step": 810
+    },
+    {
+      "epoch": 1.0955243820975284,
+      "grad_norm": 0.3767355978488922,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 820
+    },
+    {
+      "epoch": 1.108884435537742,
+      "grad_norm": 0.3361407518386841,
+      "learning_rate": 0.0002,
+      "loss": 1.7224,
+      "step": 830
+    },
+    {
+      "epoch": 1.122244488977956,
+      "grad_norm": 0.3654632568359375,
+      "learning_rate": 0.0002,
+      "loss": 1.7509,
+      "step": 840
+    },
+    {
+      "epoch": 1.1356045424181698,
+      "grad_norm": 0.3822861313819885,
+      "learning_rate": 0.0002,
+      "loss": 1.7151,
+      "step": 850
+    },
+    {
+      "epoch": 1.1489645958583834,
+      "grad_norm": 0.3853831887245178,
+      "learning_rate": 0.0002,
+      "loss": 1.7121,
+      "step": 860
+    },
+    {
+      "epoch": 1.1623246492985972,
+      "grad_norm": 0.35521796345710754,
+      "learning_rate": 0.0002,
+      "loss": 1.7685,
+      "step": 870
+    },
+    {
+      "epoch": 1.1756847027388109,
+      "grad_norm": 0.4107200503349304,
+      "learning_rate": 0.0002,
+      "loss": 1.7735,
+      "step": 880
+    },
+    {
+      "epoch": 1.1890447561790247,
+      "grad_norm": 0.33219534158706665,
+      "learning_rate": 0.0002,
+      "loss": 1.7484,
+      "step": 890
+    },
+    {
+      "epoch": 1.2024048096192386,
+      "grad_norm": 0.3559704124927521,
+      "learning_rate": 0.0002,
+      "loss": 1.7071,
+      "step": 900
+    },
+    {
+      "epoch": 1.2157648630594522,
+      "grad_norm": 0.3700537383556366,
+      "learning_rate": 0.0002,
+      "loss": 1.7535,
+      "step": 910
+    },
+    {
+      "epoch": 1.229124916499666,
+      "grad_norm": 0.3771909475326538,
+      "learning_rate": 0.0002,
+      "loss": 1.7513,
+      "step": 920
+    },
+    {
+      "epoch": 1.2424849699398797,
+      "grad_norm": 0.3136613965034485,
+      "learning_rate": 0.0002,
+      "loss": 1.7566,
+      "step": 930
+    },
+    {
+      "epoch": 1.2558450233800935,
+      "grad_norm": 0.3952099084854126,
+      "learning_rate": 0.0002,
+      "loss": 1.6783,
+      "step": 940
+    },
+    {
+      "epoch": 1.2692050768203074,
+      "grad_norm": 0.36534377932548523,
+      "learning_rate": 0.0002,
+      "loss": 1.7691,
+      "step": 950
+    },
+    {
+      "epoch": 1.282565130260521,
+      "grad_norm": 0.3803492486476898,
+      "learning_rate": 0.0002,
+      "loss": 1.7127,
+      "step": 960
+    },
+    {
+      "epoch": 1.2959251837007348,
+      "grad_norm": 0.3992428183555603,
+      "learning_rate": 0.0002,
+      "loss": 1.7896,
+      "step": 970
+    },
+    {
+      "epoch": 1.3092852371409487,
+      "grad_norm": 0.3627142906188965,
+      "learning_rate": 0.0002,
+      "loss": 1.7343,
+      "step": 980
+    },
+    {
+      "epoch": 1.3226452905811623,
+      "grad_norm": 0.4248180091381073,
+      "learning_rate": 0.0002,
+      "loss": 1.7598,
+      "step": 990
+    },
+    {
+      "epoch": 1.3360053440213762,
+      "grad_norm": 0.4060308039188385,
+      "learning_rate": 0.0002,
+      "loss": 1.6896,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3493653974615898,
+      "grad_norm": 0.3788969814777374,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 1010
+    },
+    {
+      "epoch": 1.3627254509018036,
+      "grad_norm": 0.4174270033836365,
+      "learning_rate": 0.0002,
+      "loss": 1.7111,
+      "step": 1020
+    },
+    {
+      "epoch": 1.3760855043420173,
+      "grad_norm": 0.35500675439834595,
+      "learning_rate": 0.0002,
+      "loss": 1.7975,
+      "step": 1030
+    },
+    {
+      "epoch": 1.389445557782231,
+      "grad_norm": 0.3454059362411499,
+      "learning_rate": 0.0002,
+      "loss": 1.724,
+      "step": 1040
+    },
+    {
+      "epoch": 1.402805611222445,
+      "grad_norm": 0.45807570219039917,
+      "learning_rate": 0.0002,
+      "loss": 1.8299,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4161656646626586,
+      "grad_norm": 0.39338022470474243,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4295257181028724,
+      "grad_norm": 0.3870709240436554,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4428857715430863,
+      "grad_norm": 0.40996190905570984,
+      "learning_rate": 0.0002,
+      "loss": 1.6565,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4562458249833,
+      "grad_norm": 0.38762837648391724,
+      "learning_rate": 0.0002,
+      "loss": 1.7324,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4696058784235138,
+      "grad_norm": 0.36756977438926697,
+      "learning_rate": 0.0002,
+      "loss": 1.7362,
+      "step": 1100
+    },
+    {
+      "epoch": 1.4829659318637274,
+      "grad_norm": 0.4087235927581787,
+      "learning_rate": 0.0002,
+      "loss": 1.7451,
+      "step": 1110
+    },
+    {
+      "epoch": 1.4963259853039412,
+      "grad_norm": 0.3357745110988617,
+      "learning_rate": 0.0002,
+      "loss": 1.7114,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5096860387441549,
+      "grad_norm": 0.37486532330513,
+      "learning_rate": 0.0002,
+      "loss": 1.6877,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5230460921843687,
+      "grad_norm": 0.3387809991836548,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5364061456245826,
+      "grad_norm": 0.37462118268013,
+      "learning_rate": 0.0002,
+      "loss": 1.7169,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5497661990647962,
+      "grad_norm": 0.38575324416160583,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 1160
+    },
+    {
+      "epoch": 1.56312625250501,
+      "grad_norm": 0.3515765964984894,
+      "learning_rate": 0.0002,
+      "loss": 1.7438,
+      "step": 1170
+    },
+    {
+      "epoch": 1.5764863059452239,
+      "grad_norm": 0.39308643341064453,
+      "learning_rate": 0.0002,
+      "loss": 1.7524,
+      "step": 1180
+    },
+    {
+      "epoch": 1.5898463593854375,
+      "grad_norm": 0.3308864235877991,
+      "learning_rate": 0.0002,
+      "loss": 1.6422,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6032064128256514,
+      "grad_norm": 0.3397478461265564,
+      "learning_rate": 0.0002,
+      "loss": 1.7566,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6165664662658652,
+      "grad_norm": 0.3911525309085846,
+      "learning_rate": 0.0002,
+      "loss": 1.7871,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6299265197060788,
+      "grad_norm": 0.3771969974040985,
+      "learning_rate": 0.0002,
+      "loss": 1.7443,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6432865731462925,
+      "grad_norm": 0.35346856713294983,
+      "learning_rate": 0.0002,
+      "loss": 1.7631,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6566466265865063,
+      "grad_norm": 0.41736963391304016,
+      "learning_rate": 0.0002,
+      "loss": 1.7225,
+      "step": 1240
+    },
+    {
+      "epoch": 1.6700066800267201,
+      "grad_norm": 0.3375225067138672,
+      "learning_rate": 0.0002,
+      "loss": 1.7582,
+      "step": 1250
+    },
+    {
+      "epoch": 1.6833667334669338,
+      "grad_norm": 0.3779928982257843,
+      "learning_rate": 0.0002,
+      "loss": 1.6916,
+      "step": 1260
+    },
+    {
+      "epoch": 1.6967267869071476,
+      "grad_norm": 0.35388994216918945,
+      "learning_rate": 0.0002,
+      "loss": 1.728,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7100868403473615,
+      "grad_norm": 0.33884134888648987,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 1280
+    },
+    {
+      "epoch": 1.723446893787575,
+      "grad_norm": 0.35439756512641907,
+      "learning_rate": 0.0002,
+      "loss": 1.7083,
+      "step": 1290
+    },
+    {
+      "epoch": 1.736806947227789,
+      "grad_norm": 0.3766156733036041,
+      "learning_rate": 0.0002,
+      "loss": 1.7389,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7501670006680028,
+      "grad_norm": 0.36148911714553833,
+      "learning_rate": 0.0002,
+      "loss": 1.7847,
+      "step": 1310
+    },
+    {
+      "epoch": 1.7635270541082164,
+      "grad_norm": 0.39687496423721313,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 1320
+    },
+    {
+      "epoch": 1.77688710754843,
+      "grad_norm": 0.35639452934265137,
+      "learning_rate": 0.0002,
+      "loss": 1.7541,
+      "step": 1330
+    },
+    {
+      "epoch": 1.7902471609886441,
+      "grad_norm": 0.38781628012657166,
+      "learning_rate": 0.0002,
+      "loss": 1.7254,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8036072144288577,
+      "grad_norm": 0.42784637212753296,
+      "learning_rate": 0.0002,
+      "loss": 1.7867,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8169672678690714,
+      "grad_norm": 0.40258511900901794,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8303273213092852,
+      "grad_norm": 0.36674195528030396,
+      "learning_rate": 0.0002,
+      "loss": 1.7771,
+      "step": 1370
+    },
+    {
+      "epoch": 1.843687374749499,
+      "grad_norm": 0.4064558446407318,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8570474281897127,
+      "grad_norm": 0.3669849932193756,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1390
+    },
+    {
+      "epoch": 1.8704074816299265,
+      "grad_norm": 0.37569567561149597,
+      "learning_rate": 0.0002,
+      "loss": 1.7924,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8837675350701404,
+      "grad_norm": 0.37307995557785034,
+      "learning_rate": 0.0002,
+      "loss": 1.7885,
+      "step": 1410
+    },
+    {
+      "epoch": 1.897127588510354,
+      "grad_norm": 0.3772695064544678,
+      "learning_rate": 0.0002,
+      "loss": 1.7548,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9104876419505676,
+      "grad_norm": 0.36993589997291565,
+      "learning_rate": 0.0002,
+      "loss": 1.7682,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9238476953907817,
+      "grad_norm": 0.3490557372570038,
+      "learning_rate": 0.0002,
+      "loss": 1.7249,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9372077488309953,
+      "grad_norm": 0.3716149628162384,
+      "learning_rate": 0.0002,
+      "loss": 1.7979,
+      "step": 1450
+    },
+    {
+      "epoch": 1.950567802271209,
+      "grad_norm": 0.39236098527908325,
+      "learning_rate": 0.0002,
+      "loss": 1.6664,
+      "step": 1460
+    },
+    {
+      "epoch": 1.9639278557114228,
+      "grad_norm": 0.37258651852607727,
+      "learning_rate": 0.0002,
+      "loss": 1.6852,
+      "step": 1470
+    },
+    {
+      "epoch": 1.9772879091516367,
+      "grad_norm": 0.36183077096939087,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 1480
+    },
+    {
+      "epoch": 1.9906479625918503,
+      "grad_norm": 0.3956947326660156,
+      "learning_rate": 0.0002,
+      "loss": 1.7055,
+      "step": 1490
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8132041692733765,
+      "eval_runtime": 38.6287,
+      "eval_samples_per_second": 13.332,
+      "eval_steps_per_second": 1.683,
+      "step": 1497
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5984,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.927780808124006e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7025f98e983b93b4fec0d5370c1456c7adecaf8e
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e92f0598f349930e52e126f358a3dca045c3c88312ec4b3f814f018a04982a9
+size 5560
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/README.md b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d63cb87eaccf2d81de3cdcfa11d2e99c440c0ea0
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e3a2bc9e3e10b99ab356fffee3ffefe177b4879f
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc369814feac393d3ace2c6780b443da8e22f0aab9d9abebeb252b5c0de4273
+size 109069176
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..031899978def968de0182cd1d377b3faffa9bc58
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5119c7bc18a0e8aa2d70ba4ae20bf571aff516d7dccfa15fb010c8e94ea9f47
+size 55532666
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..21dee325a9613e8ae441cc919ec4b3971ea7784d
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00e5bd0b522557bfdfbff732fff6e8df84a6a18784c9cc40d6cafab496f2033
+size 14244
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3260ae5b15b8abf75f8091264d9585cc281cc957
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cc8f3029874061e84dd272cb445cc335b8a37c374c04aff0d84b61cef30cb0c
+size 1064
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/tokenizer_config.json
@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d2963f60946f7ada17c9a51136b80265031ec56f
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/trainer_state.json
@@ -0,0 +1,1625 @@
+{
+  "best_metric": 1.8132041692733765,
+  "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497",
+  "epoch": 2.9993319973279893,
+  "eval_steps": 10,
+  "global_step": 2245,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013360053440213761,
+      "grad_norm": 0.5097216367721558,
+      "learning_rate": 0.0002,
+      "loss": 2.6569,
+      "step": 10
+    },
+    {
+      "epoch": 0.026720106880427523,
+      "grad_norm": 0.5924790501594543,
+      "learning_rate": 0.0002,
+      "loss": 2.2557,
+      "step": 20
+    },
+    {
+      "epoch": 0.04008016032064128,
+      "grad_norm": 0.5158102512359619,
+      "learning_rate": 0.0002,
+      "loss": 2.0626,
+      "step": 30
+    },
+    {
+      "epoch": 0.053440213760855046,
+      "grad_norm": 0.5033753514289856,
+      "learning_rate": 0.0002,
+      "loss": 1.9452,
+      "step": 40
+    },
+    {
+      "epoch": 0.06680026720106881,
+      "grad_norm": 0.5390949845314026,
+      "learning_rate": 0.0002,
+      "loss": 1.9128,
+      "step": 50
+    },
+    {
+      "epoch": 0.08016032064128256,
+      "grad_norm": 0.6376217007637024,
+      "learning_rate": 0.0002,
+      "loss": 1.937,
+      "step": 60
+    },
+    {
+      "epoch": 0.09352037408149633,
+      "grad_norm": 0.4202035069465637,
+      "learning_rate": 0.0002,
+      "loss": 1.929,
+      "step": 70
+    },
+    {
+      "epoch": 0.10688042752171009,
+      "grad_norm": 0.4269474744796753,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 80
+    },
+    {
+      "epoch": 0.12024048096192384,
+      "grad_norm": 0.4306574761867523,
+      "learning_rate": 0.0002,
+      "loss": 1.8303,
+      "step": 90
+    },
+    {
+      "epoch": 0.13360053440213762,
+      "grad_norm": 0.5297011137008667,
+      "learning_rate": 0.0002,
+      "loss": 1.8469,
+      "step": 100
+    },
+    {
+      "epoch": 0.14696058784235136,
+      "grad_norm": 1.2313778400421143,
+      "learning_rate": 0.0002,
+      "loss": 1.864,
+      "step": 110
+    },
+    {
+      "epoch": 0.16032064128256512,
+      "grad_norm": 0.5351294279098511,
+      "learning_rate": 0.0002,
+      "loss": 1.8531,
+      "step": 120
+    },
+    {
+      "epoch": 0.1736806947227789,
+      "grad_norm": 0.4848092496395111,
+      "learning_rate": 0.0002,
+      "loss": 1.9232,
+      "step": 130
+    },
+    {
+      "epoch": 0.18704074816299265,
+      "grad_norm": 0.4339500665664673,
+      "learning_rate": 0.0002,
+      "loss": 1.8633,
+      "step": 140
+    },
+    {
+      "epoch": 0.20040080160320642,
+      "grad_norm": 0.46877285838127136,
+      "learning_rate": 0.0002,
+      "loss": 1.816,
+      "step": 150
+    },
+    {
+      "epoch": 0.21376085504342018,
+      "grad_norm": 0.5600412487983704,
+      "learning_rate": 0.0002,
+      "loss": 1.8033,
+      "step": 160
+    },
+    {
+      "epoch": 0.22712090848363392,
+      "grad_norm": 0.3733620345592499,
+      "learning_rate": 0.0002,
+      "loss": 1.8162,
+      "step": 170
+    },
+    {
+      "epoch": 0.24048096192384769,
+      "grad_norm": 0.5116042494773865,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 180
+    },
+    {
+      "epoch": 0.25384101536406145,
+      "grad_norm": 0.4071602523326874,
+      "learning_rate": 0.0002,
+      "loss": 1.915,
+      "step": 190
+    },
+    {
+      "epoch": 0.26720106880427524,
+      "grad_norm": 0.44189608097076416,
+      "learning_rate": 0.0002,
+      "loss": 1.7984,
+      "step": 200
+    },
+    {
+      "epoch": 0.280561122244489,
+      "grad_norm": 0.398699015378952,
+      "learning_rate": 0.0002,
+      "loss": 1.8728,
+      "step": 210
+    },
+    {
+      "epoch": 0.2939211756847027,
+      "grad_norm": 0.3585626482963562,
+      "learning_rate": 0.0002,
+      "loss": 1.8205,
+      "step": 220
+    },
+    {
+      "epoch": 0.3072812291249165,
+      "grad_norm": 0.3811776041984558,
+      "learning_rate": 0.0002,
+      "loss": 1.8861,
+      "step": 230
+    },
+    {
+      "epoch": 0.32064128256513025,
+      "grad_norm": 0.37261509895324707,
+      "learning_rate": 0.0002,
+      "loss": 1.8365,
+      "step": 240
+    },
+    {
+      "epoch": 0.33400133600534404,
+      "grad_norm": 0.39762404561042786,
+      "learning_rate": 0.0002,
+      "loss": 1.9186,
+      "step": 250
+    },
+    {
+      "epoch": 0.3473613894455578,
+      "grad_norm": 0.3509528934955597,
+      "learning_rate": 0.0002,
+      "loss": 1.7965,
+      "step": 260
+    },
+    {
+      "epoch": 0.36072144288577157,
+      "grad_norm": 0.3169104754924774,
+      "learning_rate": 0.0002,
+      "loss": 1.7802,
+      "step": 270
+    },
+    {
+      "epoch": 0.3740814963259853,
+      "grad_norm": 0.33714795112609863,
+      "learning_rate": 0.0002,
+      "loss": 1.8038,
+      "step": 280
+    },
+    {
+      "epoch": 0.38744154976619904,
+      "grad_norm": 1.2936875820159912,
+      "learning_rate": 0.0002,
+      "loss": 1.787,
+      "step": 290
+    },
+    {
+      "epoch": 0.40080160320641284,
+      "grad_norm": 0.3459427058696747,
+      "learning_rate": 0.0002,
+      "loss": 1.7974,
+      "step": 300
+    },
+    {
+      "epoch": 0.4141616566466266,
+      "grad_norm": 0.3380655348300934,
+      "learning_rate": 0.0002,
+      "loss": 1.8879,
+      "step": 310
+    },
+    {
+      "epoch": 0.42752171008684037,
+      "grad_norm": 0.3890381455421448,
+      "learning_rate": 0.0002,
+      "loss": 1.9196,
+      "step": 320
+    },
+    {
+      "epoch": 0.4408817635270541,
+      "grad_norm": 0.432327002286911,
+      "learning_rate": 0.0002,
+      "loss": 1.8034,
+      "step": 330
+    },
+    {
+      "epoch": 0.45424181696726784,
+      "grad_norm": 0.3736560046672821,
+      "learning_rate": 0.0002,
+      "loss": 1.8443,
+      "step": 340
+    },
+    {
+      "epoch": 0.46760187040748163,
+      "grad_norm": 0.3700982630252838,
+      "learning_rate": 0.0002,
+      "loss": 1.8506,
+      "step": 350
+    },
+    {
+      "epoch": 0.48096192384769537,
+      "grad_norm": 0.4533902406692505,
+      "learning_rate": 0.0002,
+      "loss": 1.7978,
+      "step": 360
+    },
+    {
+      "epoch": 0.49432197728790916,
+      "grad_norm": 0.35999053716659546,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 370
+    },
+    {
+      "epoch": 0.5076820307281229,
+      "grad_norm": 0.3490903675556183,
+      "learning_rate": 0.0002,
+      "loss": 1.7995,
+      "step": 380
+    },
+    {
+      "epoch": 0.5210420841683366,
+      "grad_norm": 0.34704291820526123,
+      "learning_rate": 0.0002,
+      "loss": 1.8709,
+      "step": 390
+    },
+    {
+      "epoch": 0.5344021376085505,
+      "grad_norm": 0.343565434217453,
+      "learning_rate": 0.0002,
+      "loss": 1.7948,
+      "step": 400
+    },
+    {
+      "epoch": 0.5477621910487642,
+      "grad_norm": 0.3573552966117859,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 410
+    },
+    {
+      "epoch": 0.561122244488978,
+      "grad_norm": 0.32980719208717346,
+      "learning_rate": 0.0002,
+      "loss": 1.8477,
+      "step": 420
+    },
+    {
+      "epoch": 0.5744822979291917,
+      "grad_norm": 0.356952428817749,
+      "learning_rate": 0.0002,
+      "loss": 1.9233,
+      "step": 430
+    },
+    {
+      "epoch": 0.5878423513694054,
+      "grad_norm": 0.3170869052410126,
+      "learning_rate": 0.0002,
+      "loss": 1.7433,
+      "step": 440
+    },
+    {
+      "epoch": 0.6012024048096193,
+      "grad_norm": 0.35233718156814575,
+      "learning_rate": 0.0002,
+      "loss": 1.7607,
+      "step": 450
+    },
+    {
+      "epoch": 0.614562458249833,
+      "grad_norm": 0.3480125367641449,
+      "learning_rate": 0.0002,
+      "loss": 1.8111,
+      "step": 460
+    },
+    {
+      "epoch": 0.6279225116900468,
+      "grad_norm": 0.4762810468673706,
+      "learning_rate": 0.0002,
+      "loss": 1.8386,
+      "step": 470
+    },
+    {
+      "epoch": 0.6412825651302605,
+      "grad_norm": 0.3907663822174072,
+      "learning_rate": 0.0002,
+      "loss": 1.805,
+      "step": 480
+    },
+    {
+      "epoch": 0.6546426185704742,
+      "grad_norm": 0.36315613985061646,
+      "learning_rate": 0.0002,
+      "loss": 1.8113,
+      "step": 490
+    },
+    {
+      "epoch": 0.6680026720106881,
+      "grad_norm": 0.377796471118927,
+      "learning_rate": 0.0002,
+      "loss": 1.7805,
+      "step": 500
+    },
+    {
+      "epoch": 0.6813627254509018,
+      "grad_norm": 0.34284207224845886,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 510
+    },
+    {
+      "epoch": 0.6947227788911156,
+      "grad_norm": 0.35563018918037415,
+      "learning_rate": 0.0002,
+      "loss": 1.8013,
+      "step": 520
+    },
+    {
+      "epoch": 0.7080828323313293,
+      "grad_norm": 0.37575867772102356,
+      "learning_rate": 0.0002,
+      "loss": 1.8414,
+      "step": 530
+    },
+    {
+      "epoch": 0.7214428857715431,
+      "grad_norm": 0.35719701647758484,
+      "learning_rate": 0.0002,
+      "loss": 1.7993,
+      "step": 540
+    },
+    {
+      "epoch": 0.7348029392117569,
+      "grad_norm": 0.385813444852829,
+      "learning_rate": 0.0002,
+      "loss": 1.7574,
+      "step": 550
+    },
+    {
+      "epoch": 0.7481629926519706,
+      "grad_norm": 0.44509607553482056,
+      "learning_rate": 0.0002,
+      "loss": 1.7985,
+      "step": 560
+    },
+    {
+      "epoch": 0.7615230460921844,
+      "grad_norm": 0.36108464002609253,
+      "learning_rate": 0.0002,
+      "loss": 1.7459,
+      "step": 570
+    },
+    {
+      "epoch": 0.7748830995323981,
+      "grad_norm": 0.3530745804309845,
+      "learning_rate": 0.0002,
+      "loss": 1.8207,
+      "step": 580
+    },
+    {
+      "epoch": 0.7882431529726119,
+      "grad_norm": 0.34888574481010437,
+      "learning_rate": 0.0002,
+      "loss": 1.7479,
+      "step": 590
+    },
+    {
+      "epoch": 0.8016032064128257,
+      "grad_norm": 0.387346476316452,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 600
+    },
+    {
+      "epoch": 0.8149632598530394,
+      "grad_norm": 0.3641138970851898,
+      "learning_rate": 0.0002,
+      "loss": 1.8071,
+      "step": 610
+    },
+    {
+      "epoch": 0.8283233132932531,
+      "grad_norm": 0.33729103207588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7531,
+      "step": 620
+    },
+    {
+      "epoch": 0.8416833667334669,
+      "grad_norm": 0.3652004599571228,
+      "learning_rate": 0.0002,
+      "loss": 1.8613,
+      "step": 630
+    },
+    {
+      "epoch": 0.8550434201736807,
+      "grad_norm": 0.3986643850803375,
+      "learning_rate": 0.0002,
+      "loss": 1.9184,
+      "step": 640
+    },
+    {
+      "epoch": 0.8684034736138945,
+      "grad_norm": 0.3458964228630066,
+      "learning_rate": 0.0002,
+      "loss": 1.8198,
+      "step": 650
+    },
+    {
+      "epoch": 0.8817635270541082,
+      "grad_norm": 0.3559381365776062,
+      "learning_rate": 0.0002,
+      "loss": 1.803,
+      "step": 660
+    },
+    {
+      "epoch": 0.895123580494322,
+      "grad_norm": 0.3612841069698334,
+      "learning_rate": 0.0002,
+      "loss": 1.7641,
+      "step": 670
+    },
+    {
+      "epoch": 0.9084836339345357,
+      "grad_norm": 0.34771719574928284,
+      "learning_rate": 0.0002,
+      "loss": 1.7888,
+      "step": 680
+    },
+    {
+      "epoch": 0.9218436873747495,
+      "grad_norm": 0.3371497094631195,
+      "learning_rate": 0.0002,
+      "loss": 1.8204,
+      "step": 690
+    },
+    {
+      "epoch": 0.9352037408149633,
+      "grad_norm": 0.5596055388450623,
+      "learning_rate": 0.0002,
+      "loss": 1.7848,
+      "step": 700
+    },
+    {
+      "epoch": 0.948563794255177,
+      "grad_norm": 0.311880499124527,
+      "learning_rate": 0.0002,
+      "loss": 1.7794,
+      "step": 710
+    },
+    {
+      "epoch": 0.9619238476953907,
+      "grad_norm": 0.3462068736553192,
+      "learning_rate": 0.0002,
+      "loss": 1.8464,
+      "step": 720
+    },
+    {
+      "epoch": 0.9752839011356046,
+      "grad_norm": 0.29982393980026245,
+      "learning_rate": 0.0002,
+      "loss": 1.8197,
+      "step": 730
+    },
+    {
+      "epoch": 0.9886439545758183,
+      "grad_norm": 0.34606459736824036,
+      "learning_rate": 0.0002,
+      "loss": 1.8503,
+      "step": 740
+    },
+    {
+      "epoch": 0.9993319973279893,
+      "eval_loss": 1.8201380968093872,
+      "eval_runtime": 38.6124,
+      "eval_samples_per_second": 13.338,
+      "eval_steps_per_second": 1.683,
+      "step": 748
+    },
+    {
+      "epoch": 1.002004008016032,
+      "grad_norm": 0.32302048802375793,
+      "learning_rate": 0.0002,
+      "loss": 1.7786,
+      "step": 750
+    },
+    {
+      "epoch": 1.0153640614562458,
+      "grad_norm": 0.37585633993148804,
+      "learning_rate": 0.0002,
+      "loss": 1.7297,
+      "step": 760
+    },
+    {
+      "epoch": 1.0287241148964597,
+      "grad_norm": 0.33826273679733276,
+      "learning_rate": 0.0002,
+      "loss": 1.7008,
+      "step": 770
+    },
+    {
+      "epoch": 1.0420841683366733,
+      "grad_norm": 0.44682955741882324,
+      "learning_rate": 0.0002,
+      "loss": 1.809,
+      "step": 780
+    },
+    {
+      "epoch": 1.0554442217768871,
+      "grad_norm": 0.422188401222229,
+      "learning_rate": 0.0002,
+      "loss": 1.7092,
+      "step": 790
+    },
+    {
+      "epoch": 1.0688042752171008,
+      "grad_norm": 0.3809906244277954,
+      "learning_rate": 0.0002,
+      "loss": 1.7765,
+      "step": 800
+    },
+    {
+      "epoch": 1.0821643286573146,
+      "grad_norm": 0.3454349637031555,
+      "learning_rate": 0.0002,
+      "loss": 1.7431,
+      "step": 810
+    },
+    {
+      "epoch": 1.0955243820975284,
+      "grad_norm": 0.3767355978488922,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 820
+    },
+    {
+      "epoch": 1.108884435537742,
+      "grad_norm": 0.3361407518386841,
+      "learning_rate": 0.0002,
+      "loss": 1.7224,
+      "step": 830
+    },
+    {
+      "epoch": 1.122244488977956,
+      "grad_norm": 0.3654632568359375,
+      "learning_rate": 0.0002,
+      "loss": 1.7509,
+      "step": 840
+    },
+    {
+      "epoch": 1.1356045424181698,
+      "grad_norm": 0.3822861313819885,
+      "learning_rate": 0.0002,
+      "loss": 1.7151,
+      "step": 850
+    },
+    {
+      "epoch": 1.1489645958583834,
+      "grad_norm": 0.3853831887245178,
+      "learning_rate": 0.0002,
+      "loss": 1.7121,
+      "step": 860
+    },
+    {
+      "epoch": 1.1623246492985972,
+      "grad_norm": 0.35521796345710754,
+      "learning_rate": 0.0002,
+      "loss": 1.7685,
+      "step": 870
+    },
+    {
+      "epoch": 1.1756847027388109,
+      "grad_norm": 0.4107200503349304,
+      "learning_rate": 0.0002,
+      "loss": 1.7735,
+      "step": 880
+    },
+    {
+      "epoch": 1.1890447561790247,
+      "grad_norm": 0.33219534158706665,
+      "learning_rate": 0.0002,
+      "loss": 1.7484,
+      "step": 890
+    },
+    {
+      "epoch": 1.2024048096192386,
+      "grad_norm": 0.3559704124927521,
+      "learning_rate": 0.0002,
+      "loss": 1.7071,
+      "step": 900
+    },
+    {
+      "epoch": 1.2157648630594522,
+      "grad_norm": 0.3700537383556366,
+      "learning_rate": 0.0002,
+      "loss": 1.7535,
+      "step": 910
+    },
+    {
+      "epoch": 1.229124916499666,
+      "grad_norm": 0.3771909475326538,
+      "learning_rate": 0.0002,
+      "loss": 1.7513,
+      "step": 920
+    },
+    {
+      "epoch": 1.2424849699398797,
+      "grad_norm": 0.3136613965034485,
+      "learning_rate": 0.0002,
+      "loss": 1.7566,
+      "step": 930
+    },
+    {
+      "epoch": 1.2558450233800935,
+      "grad_norm": 0.3952099084854126,
+      "learning_rate": 0.0002,
+      "loss": 1.6783,
+      "step": 940
+    },
+    {
+      "epoch": 1.2692050768203074,
+      "grad_norm": 0.36534377932548523,
+      "learning_rate": 0.0002,
+      "loss": 1.7691,
+      "step": 950
+    },
+    {
+      "epoch": 1.282565130260521,
+      "grad_norm": 0.3803492486476898,
+      "learning_rate": 0.0002,
+      "loss": 1.7127,
+      "step": 960
+    },
+    {
+      "epoch": 1.2959251837007348,
+      "grad_norm": 0.3992428183555603,
+      "learning_rate": 0.0002,
+      "loss": 1.7896,
+      "step": 970
+    },
+    {
+      "epoch": 1.3092852371409487,
+      "grad_norm": 0.3627142906188965,
+      "learning_rate": 0.0002,
+      "loss": 1.7343,
+      "step": 980
+    },
+    {
+      "epoch": 1.3226452905811623,
+      "grad_norm": 0.4248180091381073,
+      "learning_rate": 0.0002,
+      "loss": 1.7598,
+      "step": 990
+    },
+    {
+      "epoch": 1.3360053440213762,
+      "grad_norm": 0.4060308039188385,
+      "learning_rate": 0.0002,
+      "loss": 1.6896,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3493653974615898,
+      "grad_norm": 0.3788969814777374,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 1010
+    },
+    {
+      "epoch": 1.3627254509018036,
+      "grad_norm": 0.4174270033836365,
+      "learning_rate": 0.0002,
+      "loss": 1.7111,
+      "step": 1020
+    },
+    {
+      "epoch": 1.3760855043420173,
+      "grad_norm": 0.35500675439834595,
+      "learning_rate": 0.0002,
+      "loss": 1.7975,
+      "step": 1030
+    },
+    {
+      "epoch": 1.389445557782231,
+      "grad_norm": 0.3454059362411499,
+      "learning_rate": 0.0002,
+      "loss": 1.724,
+      "step": 1040
+    },
+    {
+      "epoch": 1.402805611222445,
+      "grad_norm": 0.45807570219039917,
+      "learning_rate": 0.0002,
+      "loss": 1.8299,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4161656646626586,
+      "grad_norm": 0.39338022470474243,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4295257181028724,
+      "grad_norm": 0.3870709240436554,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4428857715430863,
+      "grad_norm": 0.40996190905570984,
+      "learning_rate": 0.0002,
+      "loss": 1.6565,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4562458249833,
+      "grad_norm": 0.38762837648391724,
+      "learning_rate": 0.0002,
+      "loss": 1.7324,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4696058784235138,
+      "grad_norm": 0.36756977438926697,
+      "learning_rate": 0.0002,
+      "loss": 1.7362,
+      "step": 1100
+    },
+    {
+      "epoch": 1.4829659318637274,
+      "grad_norm": 0.4087235927581787,
+      "learning_rate": 0.0002,
+      "loss": 1.7451,
+      "step": 1110
+    },
+    {
+      "epoch": 1.4963259853039412,
+      "grad_norm": 0.3357745110988617,
+      "learning_rate": 0.0002,
+      "loss": 1.7114,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5096860387441549,
+      "grad_norm": 0.37486532330513,
+      "learning_rate": 0.0002,
+      "loss": 1.6877,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5230460921843687,
+      "grad_norm": 0.3387809991836548,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5364061456245826,
+      "grad_norm": 0.37462118268013,
+      "learning_rate": 0.0002,
+      "loss": 1.7169,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5497661990647962,
+      "grad_norm": 0.38575324416160583,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 1160
+    },
+    {
+      "epoch": 1.56312625250501,
+      "grad_norm": 0.3515765964984894,
+      "learning_rate": 0.0002,
+      "loss": 1.7438,
+      "step": 1170
+    },
+    {
+      "epoch": 1.5764863059452239,
+      "grad_norm": 0.39308643341064453,
+      "learning_rate": 0.0002,
+      "loss": 1.7524,
+      "step": 1180
+    },
+    {
+      "epoch": 1.5898463593854375,
+      "grad_norm": 0.3308864235877991,
+      "learning_rate": 0.0002,
+      "loss": 1.6422,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6032064128256514,
+      "grad_norm": 0.3397478461265564,
+      "learning_rate": 0.0002,
+      "loss": 1.7566,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6165664662658652,
+      "grad_norm": 0.3911525309085846,
+      "learning_rate": 0.0002,
+      "loss": 1.7871,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6299265197060788,
+      "grad_norm": 0.3771969974040985,
+      "learning_rate": 0.0002,
+      "loss": 1.7443,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6432865731462925,
+      "grad_norm": 0.35346856713294983,
+      "learning_rate": 0.0002,
+      "loss": 1.7631,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6566466265865063,
+      "grad_norm": 0.41736963391304016,
+      "learning_rate": 0.0002,
+      "loss": 1.7225,
+      "step": 1240
+    },
+    {
+      "epoch": 1.6700066800267201,
+      "grad_norm": 0.3375225067138672,
+      "learning_rate": 0.0002,
+      "loss": 1.7582,
+      "step": 1250
+    },
+    {
+      "epoch": 1.6833667334669338,
+      "grad_norm": 0.3779928982257843,
+      "learning_rate": 0.0002,
+      "loss": 1.6916,
+      "step": 1260
+    },
+    {
+      "epoch": 1.6967267869071476,
+      "grad_norm": 0.35388994216918945,
+      "learning_rate": 0.0002,
+      "loss": 1.728,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7100868403473615,
+      "grad_norm": 0.33884134888648987,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 1280
+    },
+    {
+      "epoch": 1.723446893787575,
+      "grad_norm": 0.35439756512641907,
+      "learning_rate": 0.0002,
+      "loss": 1.7083,
+      "step": 1290
+    },
+    {
+      "epoch": 1.736806947227789,
+      "grad_norm": 0.3766156733036041,
+      "learning_rate": 0.0002,
+      "loss": 1.7389,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7501670006680028,
+      "grad_norm": 0.36148911714553833,
+      "learning_rate": 0.0002,
+      "loss": 1.7847,
+      "step": 1310
+    },
+    {
+      "epoch": 1.7635270541082164,
+      "grad_norm": 0.39687496423721313,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 1320
+    },
+    {
+      "epoch": 1.77688710754843,
+      "grad_norm": 0.35639452934265137,
+      "learning_rate": 0.0002,
+      "loss": 1.7541,
+      "step": 1330
+    },
+    {
+      "epoch": 1.7902471609886441,
+      "grad_norm": 0.38781628012657166,
+      "learning_rate": 0.0002,
+      "loss": 1.7254,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8036072144288577,
+      "grad_norm": 0.42784637212753296,
+      "learning_rate": 0.0002,
+      "loss": 1.7867,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8169672678690714,
+      "grad_norm": 0.40258511900901794,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8303273213092852,
+      "grad_norm": 0.36674195528030396,
+      "learning_rate": 0.0002,
+      "loss": 1.7771,
+      "step": 1370
+    },
+    {
+      "epoch": 1.843687374749499,
+      "grad_norm": 0.4064558446407318,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8570474281897127,
+      "grad_norm": 0.3669849932193756,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1390
+    },
+    {
+      "epoch": 1.8704074816299265,
+      "grad_norm": 0.37569567561149597,
+      "learning_rate": 0.0002,
+      "loss": 1.7924,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8837675350701404,
+      "grad_norm": 0.37307995557785034,
+      "learning_rate": 0.0002,
+      "loss": 1.7885,
+      "step": 1410
+    },
+    {
+      "epoch": 1.897127588510354,
+      "grad_norm": 0.3772695064544678,
+      "learning_rate": 0.0002,
+      "loss": 1.7548,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9104876419505676,
+      "grad_norm": 0.36993589997291565,
+      "learning_rate": 0.0002,
+      "loss": 1.7682,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9238476953907817,
+      "grad_norm": 0.3490557372570038,
+      "learning_rate": 0.0002,
+      "loss": 1.7249,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9372077488309953,
+      "grad_norm": 0.3716149628162384,
+      "learning_rate": 0.0002,
+      "loss": 1.7979,
+      "step": 1450
+    },
+    {
+      "epoch": 1.950567802271209,
+      "grad_norm": 0.39236098527908325,
+      "learning_rate": 0.0002,
+      "loss": 1.6664,
+      "step": 1460
+    },
+    {
+      "epoch": 1.9639278557114228,
+      "grad_norm": 0.37258651852607727,
+      "learning_rate": 0.0002,
+      "loss": 1.6852,
+      "step": 1470
+    },
+    {
+      "epoch": 1.9772879091516367,
+      "grad_norm": 0.36183077096939087,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 1480
+    },
+    {
+      "epoch": 1.9906479625918503,
+      "grad_norm": 0.3956947326660156,
+      "learning_rate": 0.0002,
+      "loss": 1.7055,
+      "step": 1490
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8132041692733765,
+      "eval_runtime": 38.6287,
+      "eval_samples_per_second": 13.332,
+      "eval_steps_per_second": 1.683,
+      "step": 1497
+    },
+    {
+      "epoch": 2.004008016032064,
+      "grad_norm": 0.34480565786361694,
+      "learning_rate": 0.0002,
+      "loss": 1.6791,
+      "step": 1500
+    },
+    {
+      "epoch": 2.017368069472278,
+      "grad_norm": 0.3418028652667999,
+      "learning_rate": 0.0002,
+      "loss": 1.6367,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0307281229124916,
+      "grad_norm": 0.4514467716217041,
+      "learning_rate": 0.0002,
+      "loss": 1.5827,
+      "step": 1520
+    },
+    {
+      "epoch": 2.0440881763527052,
+      "grad_norm": 0.4197506606578827,
+      "learning_rate": 0.0002,
+      "loss": 1.6365,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0574482297929193,
+      "grad_norm": 0.4134170711040497,
+      "learning_rate": 0.0002,
+      "loss": 1.6221,
+      "step": 1540
+    },
+    {
+      "epoch": 2.070808283233133,
+      "grad_norm": 0.43709826469421387,
+      "learning_rate": 0.0002,
+      "loss": 1.6876,
+      "step": 1550
+    },
+    {
+      "epoch": 2.0841683366733466,
+      "grad_norm": 0.4703378677368164,
+      "learning_rate": 0.0002,
+      "loss": 1.5779,
+      "step": 1560
+    },
+    {
+      "epoch": 2.0975283901135606,
+      "grad_norm": 0.4538188576698303,
+      "learning_rate": 0.0002,
+      "loss": 1.599,
+      "step": 1570
+    },
+    {
+      "epoch": 2.1108884435537743,
+      "grad_norm": 0.4649668037891388,
+      "learning_rate": 0.0002,
+      "loss": 1.6464,
+      "step": 1580
+    },
+    {
+      "epoch": 2.124248496993988,
+      "grad_norm": 0.42669883370399475,
+      "learning_rate": 0.0002,
+      "loss": 1.6348,
+      "step": 1590
+    },
+    {
+      "epoch": 2.1376085504342015,
+      "grad_norm": 0.43162038922309875,
+      "learning_rate": 0.0002,
+      "loss": 1.5838,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1509686038744156,
+      "grad_norm": 0.4294586479663849,
+      "learning_rate": 0.0002,
+      "loss": 1.6673,
+      "step": 1610
+    },
+    {
+      "epoch": 2.164328657314629,
+      "grad_norm": 0.4669102132320404,
+      "learning_rate": 0.0002,
+      "loss": 1.6024,
+      "step": 1620
+    },
+    {
+      "epoch": 2.177688710754843,
+      "grad_norm": 0.4188412129878998,
+      "learning_rate": 0.0002,
+      "loss": 1.659,
+      "step": 1630
+    },
+    {
+      "epoch": 2.191048764195057,
+      "grad_norm": 0.4662680923938751,
+      "learning_rate": 0.0002,
+      "loss": 1.625,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2044088176352705,
+      "grad_norm": 0.4020286500453949,
+      "learning_rate": 0.0002,
+      "loss": 1.6699,
+      "step": 1650
+    },
+    {
+      "epoch": 2.217768871075484,
+      "grad_norm": 0.41919606924057007,
+      "learning_rate": 0.0002,
+      "loss": 1.6284,
+      "step": 1660
+    },
+    {
+      "epoch": 2.231128924515698,
+      "grad_norm": 0.4644531309604645,
+      "learning_rate": 0.0002,
+      "loss": 1.6776,
+      "step": 1670
+    },
+    {
+      "epoch": 2.244488977955912,
+      "grad_norm": 0.4526427984237671,
+      "learning_rate": 0.0002,
+      "loss": 1.6711,
+      "step": 1680
+    },
+    {
+      "epoch": 2.2578490313961255,
+      "grad_norm": 0.45953166484832764,
+      "learning_rate": 0.0002,
+      "loss": 1.6058,
+      "step": 1690
+    },
+    {
+      "epoch": 2.2712090848363395,
+      "grad_norm": 0.4701860249042511,
+      "learning_rate": 0.0002,
+      "loss": 1.5979,
+      "step": 1700
+    },
+    {
+      "epoch": 2.284569138276553,
+      "grad_norm": 0.4749310612678528,
+      "learning_rate": 0.0002,
+      "loss": 1.6183,
+      "step": 1710
+    },
+    {
+      "epoch": 2.297929191716767,
+      "grad_norm": 0.45026102662086487,
+      "learning_rate": 0.0002,
+      "loss": 1.6703,
+      "step": 1720
+    },
+    {
+      "epoch": 2.3112892451569804,
+      "grad_norm": 0.4755004048347473,
+      "learning_rate": 0.0002,
+      "loss": 1.6386,
+      "step": 1730
+    },
+    {
+      "epoch": 2.3246492985971945,
+      "grad_norm": 0.4505726993083954,
+      "learning_rate": 0.0002,
+      "loss": 1.6365,
+      "step": 1740
+    },
+    {
+      "epoch": 2.338009352037408,
+      "grad_norm": 0.44464054703712463,
+      "learning_rate": 0.0002,
+      "loss": 1.589,
+      "step": 1750
+    },
+    {
+      "epoch": 2.3513694054776217,
+      "grad_norm": 0.4449476897716522,
+      "learning_rate": 0.0002,
+      "loss": 1.6139,
+      "step": 1760
+    },
+    {
+      "epoch": 2.364729458917836,
+      "grad_norm": 0.4216482937335968,
+      "learning_rate": 0.0002,
+      "loss": 1.7195,
+      "step": 1770
+    },
+    {
+      "epoch": 2.3780895123580494,
+      "grad_norm": 0.4379308521747589,
+      "learning_rate": 0.0002,
+      "loss": 1.7075,
+      "step": 1780
+    },
+    {
+      "epoch": 2.391449565798263,
+      "grad_norm": 0.41670042276382446,
+      "learning_rate": 0.0002,
+      "loss": 1.7024,
+      "step": 1790
+    },
+    {
+      "epoch": 2.404809619238477,
+      "grad_norm": 0.48089510202407837,
+      "learning_rate": 0.0002,
+      "loss": 1.5989,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4181696726786908,
+      "grad_norm": 0.4389738142490387,
+      "learning_rate": 0.0002,
+      "loss": 1.6313,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4315297261189044,
+      "grad_norm": 0.45293036103248596,
+      "learning_rate": 0.0002,
+      "loss": 1.5841,
+      "step": 1820
+    },
+    {
+      "epoch": 2.4448897795591185,
+      "grad_norm": 0.5211683511734009,
+      "learning_rate": 0.0002,
+      "loss": 1.6887,
+      "step": 1830
+    },
+    {
+      "epoch": 2.458249832999332,
+      "grad_norm": 0.4631884694099426,
+      "learning_rate": 0.0002,
+      "loss": 1.6599,
+      "step": 1840
+    },
+    {
+      "epoch": 2.4716098864395457,
+      "grad_norm": 0.4276818335056305,
+      "learning_rate": 0.0002,
+      "loss": 1.6537,
+      "step": 1850
+    },
+    {
+      "epoch": 2.4849699398797593,
+      "grad_norm": 0.477524071931839,
+      "learning_rate": 0.0002,
+      "loss": 1.6836,
+      "step": 1860
+    },
+    {
+      "epoch": 2.4983299933199734,
+      "grad_norm": 0.44860973954200745,
+      "learning_rate": 0.0002,
+      "loss": 1.66,
+      "step": 1870
+    },
+    {
+      "epoch": 2.511690046760187,
+      "grad_norm": 0.46413546800613403,
+      "learning_rate": 0.0002,
+      "loss": 1.6308,
+      "step": 1880
+    },
+    {
+      "epoch": 2.5250501002004007,
+      "grad_norm": 0.42487645149230957,
+      "learning_rate": 0.0002,
+      "loss": 1.6225,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5384101536406147,
+      "grad_norm": 0.4778307378292084,
+      "learning_rate": 0.0002,
+      "loss": 1.6268,
+      "step": 1900
+    },
+    {
+      "epoch": 2.5517702070808284,
+      "grad_norm": 0.45307061076164246,
+      "learning_rate": 0.0002,
+      "loss": 1.6143,
+      "step": 1910
+    },
+    {
+      "epoch": 2.565130260521042,
+      "grad_norm": 0.47886642813682556,
+      "learning_rate": 0.0002,
+      "loss": 1.7279,
+      "step": 1920
+    },
+    {
+      "epoch": 2.5784903139612556,
+      "grad_norm": 0.4839435815811157,
+      "learning_rate": 0.0002,
+      "loss": 1.5931,
+      "step": 1930
+    },
+    {
+      "epoch": 2.5918503674014697,
+      "grad_norm": 0.4388359785079956,
+      "learning_rate": 0.0002,
+      "loss": 1.6089,
+      "step": 1940
+    },
+    {
+      "epoch": 2.6052104208416833,
+      "grad_norm": 0.47859734296798706,
+      "learning_rate": 0.0002,
+      "loss": 1.6828,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6185704742818974,
+      "grad_norm": 0.5526517033576965,
+      "learning_rate": 0.0002,
+      "loss": 1.6014,
+      "step": 1960
+    },
+    {
+      "epoch": 2.631930527722111,
+      "grad_norm": 0.5449170470237732,
+      "learning_rate": 0.0002,
+      "loss": 1.6889,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6452905811623246,
+      "grad_norm": 0.48521968722343445,
+      "learning_rate": 0.0002,
+      "loss": 1.6481,
+      "step": 1980
+    },
+    {
+      "epoch": 2.6586506346025383,
+      "grad_norm": 0.4733737111091614,
+      "learning_rate": 0.0002,
+      "loss": 1.6741,
+      "step": 1990
+    },
+    {
+      "epoch": 2.6720106880427523,
+      "grad_norm": 0.507118284702301,
+      "learning_rate": 0.0002,
+      "loss": 1.662,
+      "step": 2000
+    },
+    {
+      "epoch": 2.685370741482966,
+      "grad_norm": 0.4508971571922302,
+      "learning_rate": 0.0002,
+      "loss": 1.6419,
+      "step": 2010
+    },
+    {
+      "epoch": 2.6987307949231796,
+      "grad_norm": 0.4657728672027588,
+      "learning_rate": 0.0002,
+      "loss": 1.7052,
+      "step": 2020
+    },
+    {
+      "epoch": 2.7120908483633936,
+      "grad_norm": 0.48647549748420715,
+      "learning_rate": 0.0002,
+      "loss": 1.6261,
+      "step": 2030
+    },
+    {
+      "epoch": 2.7254509018036073,
+      "grad_norm": 0.49525555968284607,
+      "learning_rate": 0.0002,
+      "loss": 1.5638,
+      "step": 2040
+    },
+    {
+      "epoch": 2.738810955243821,
+      "grad_norm": 0.4712379276752472,
+      "learning_rate": 0.0002,
+      "loss": 1.658,
+      "step": 2050
+    },
+    {
+      "epoch": 2.7521710086840345,
+      "grad_norm": 0.4846591055393219,
+      "learning_rate": 0.0002,
+      "loss": 1.6464,
+      "step": 2060
+    },
+    {
+      "epoch": 2.7655310621242486,
+      "grad_norm": 0.4823240041732788,
+      "learning_rate": 0.0002,
+      "loss": 1.5641,
+      "step": 2070
+    },
+    {
+      "epoch": 2.778891115564462,
+      "grad_norm": 0.4546685516834259,
+      "learning_rate": 0.0002,
+      "loss": 1.6701,
+      "step": 2080
+    },
+    {
+      "epoch": 2.7922511690046763,
+      "grad_norm": 0.45542681217193604,
+      "learning_rate": 0.0002,
+      "loss": 1.7015,
+      "step": 2090
+    },
+    {
+      "epoch": 2.80561122244489,
+      "grad_norm": 0.42137566208839417,
+      "learning_rate": 0.0002,
+      "loss": 1.6398,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8189712758851035,
+      "grad_norm": 0.6143282055854797,
+      "learning_rate": 0.0002,
+      "loss": 1.6526,
+      "step": 2110
+    },
+    {
+      "epoch": 2.832331329325317,
+      "grad_norm": 0.4828081727027893,
+      "learning_rate": 0.0002,
+      "loss": 1.6955,
+      "step": 2120
+    },
+    {
+      "epoch": 2.845691382765531,
+      "grad_norm": 0.4319005608558655,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 2130
+    },
+    {
+      "epoch": 2.859051436205745,
+      "grad_norm": 0.4297086298465729,
+      "learning_rate": 0.0002,
+      "loss": 1.6717,
+      "step": 2140
+    },
+    {
+      "epoch": 2.8724114896459585,
+      "grad_norm": 0.5011981129646301,
+      "learning_rate": 0.0002,
+      "loss": 1.5968,
+      "step": 2150
+    },
+    {
+      "epoch": 2.8857715430861726,
+      "grad_norm": 0.4401548504829407,
+      "learning_rate": 0.0002,
+      "loss": 1.7181,
+      "step": 2160
+    },
+    {
+      "epoch": 2.899131596526386,
+      "grad_norm": 0.48090746998786926,
+      "learning_rate": 0.0002,
+      "loss": 1.5722,
+      "step": 2170
+    },
+    {
+      "epoch": 2.9124916499666,
+      "grad_norm": 0.4740385413169861,
+      "learning_rate": 0.0002,
+      "loss": 1.6596,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9258517034068134,
+      "grad_norm": 0.5337260365486145,
+      "learning_rate": 0.0002,
+      "loss": 1.6501,
+      "step": 2190
+    },
+    {
+      "epoch": 2.9392117568470275,
+      "grad_norm": 0.4420052766799927,
+      "learning_rate": 0.0002,
+      "loss": 1.6802,
+      "step": 2200
+    },
+    {
+      "epoch": 2.952571810287241,
+      "grad_norm": 0.477512389421463,
+      "learning_rate": 0.0002,
+      "loss": 1.5474,
+      "step": 2210
+    },
+    {
+      "epoch": 2.9659318637274548,
+      "grad_norm": 0.5344052910804749,
+      "learning_rate": 0.0002,
+      "loss": 1.6544,
+      "step": 2220
+    },
+    {
+      "epoch": 2.979291917167669,
+      "grad_norm": 0.4483940303325653,
+      "learning_rate": 0.0002,
+      "loss": 1.6866,
+      "step": 2230
+    },
+    {
+      "epoch": 2.9926519706078825,
+      "grad_norm": 0.4366597831249237,
+      "learning_rate": 0.0002,
+      "loss": 1.6477,
+      "step": 2240
+    },
+    {
+      "epoch": 2.9993319973279893,
+      "eval_loss": 1.834012746810913,
+      "eval_runtime": 38.5659,
+      "eval_samples_per_second": 13.354,
+      "eval_steps_per_second": 1.685,
+      "step": 2245
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5984,
+  "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": 1.039167121218601e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7025f98e983b93b4fec0d5370c1456c7adecaf8e
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2245/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e92f0598f349930e52e126f358a3dca045c3c88312ec4b3f814f018a04982a9
+size 5560
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/README.md b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d63cb87eaccf2d81de3cdcfa11d2e99c440c0ea0
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d9c47b281dd363276b5935cdd914f602fb5b097e
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50145fdba72c154193c72a354fd9ed8a9384f2d380d2d052fff0853733b999b9
+size 109069176
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c54f518264268b081d234b966559f7d6206e0061
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d67409eb615b81e95854e8d76155238d3b72eba70e87a1c57213652fb80c51
+size 55532666
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..df8f7a931ab5382a60f213cbc64774cb39fd8340
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf4809ab99e0a3867e853a0003750622809b7d78cab5822d0da5dd6eef01db1
+size 14244
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5b46a4e0b733f29f1695fec8b5c3c466f9cd7944
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8fa4ddd949eedb49a4d50d157f1003d3c620937763ed48cf89d88bbe557bcd6
+size 1064
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/tokenizer_config.json
@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..21498cc9e6bfdb5fd5c874cd8c31cd9880f711e9
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/trainer_state.json
@@ -0,0 +1,2158 @@
+{
+  "best_metric": 1.8132041692733765,
+  "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497",
+  "epoch": 4.0,
+  "eval_steps": 10,
+  "global_step": 2994,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013360053440213761,
+      "grad_norm": 0.5097216367721558,
+      "learning_rate": 0.0002,
+      "loss": 2.6569,
+      "step": 10
+    },
+    {
+      "epoch": 0.026720106880427523,
+      "grad_norm": 0.5924790501594543,
+      "learning_rate": 0.0002,
+      "loss": 2.2557,
+      "step": 20
+    },
+    {
+      "epoch": 0.04008016032064128,
+      "grad_norm": 0.5158102512359619,
+      "learning_rate": 0.0002,
+      "loss": 2.0626,
+      "step": 30
+    },
+    {
+      "epoch": 0.053440213760855046,
+      "grad_norm": 0.5033753514289856,
+      "learning_rate": 0.0002,
+      "loss": 1.9452,
+      "step": 40
+    },
+    {
+      "epoch": 0.06680026720106881,
+      "grad_norm": 0.5390949845314026,
+      "learning_rate": 0.0002,
+      "loss": 1.9128,
+      "step": 50
+    },
+    {
+      "epoch": 0.08016032064128256,
+      "grad_norm": 0.6376217007637024,
+      "learning_rate": 0.0002,
+      "loss": 1.937,
+      "step": 60
+    },
+    {
+      "epoch": 0.09352037408149633,
+      "grad_norm": 0.4202035069465637,
+      "learning_rate": 0.0002,
+      "loss": 1.929,
+      "step": 70
+    },
+    {
+      "epoch": 0.10688042752171009,
+      "grad_norm": 0.4269474744796753,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 80
+    },
+    {
+      "epoch": 0.12024048096192384,
+      "grad_norm": 0.4306574761867523,
+      "learning_rate": 0.0002,
+      "loss": 1.8303,
+      "step": 90
+    },
+    {
+      "epoch": 0.13360053440213762,
+      "grad_norm": 0.5297011137008667,
+      "learning_rate": 0.0002,
+      "loss": 1.8469,
+      "step": 100
+    },
+    {
+      "epoch": 0.14696058784235136,
+      "grad_norm": 1.2313778400421143,
+      "learning_rate": 0.0002,
+      "loss": 1.864,
+      "step": 110
+    },
+    {
+      "epoch": 0.16032064128256512,
+      "grad_norm": 0.5351294279098511,
+      "learning_rate": 0.0002,
+      "loss": 1.8531,
+      "step": 120
+    },
+    {
+      "epoch": 0.1736806947227789,
+      "grad_norm": 0.4848092496395111,
+      "learning_rate": 0.0002,
+      "loss": 1.9232,
+      "step": 130
+    },
+    {
+      "epoch": 0.18704074816299265,
+      "grad_norm": 0.4339500665664673,
+      "learning_rate": 0.0002,
+      "loss": 1.8633,
+      "step": 140
+    },
+    {
+      "epoch": 0.20040080160320642,
+      "grad_norm": 0.46877285838127136,
+      "learning_rate": 0.0002,
+      "loss": 1.816,
+      "step": 150
+    },
+    {
+      "epoch": 0.21376085504342018,
+      "grad_norm": 0.5600412487983704,
+      "learning_rate": 0.0002,
+      "loss": 1.8033,
+      "step": 160
+    },
+    {
+      "epoch": 0.22712090848363392,
+      "grad_norm": 0.3733620345592499,
+      "learning_rate": 0.0002,
+      "loss": 1.8162,
+      "step": 170
+    },
+    {
+      "epoch": 0.24048096192384769,
+      "grad_norm": 0.5116042494773865,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 180
+    },
+    {
+      "epoch": 0.25384101536406145,
+      "grad_norm": 0.4071602523326874,
+      "learning_rate": 0.0002,
+      "loss": 1.915,
+      "step": 190
+    },
+    {
+      "epoch": 0.26720106880427524,
+      "grad_norm": 0.44189608097076416,
+      "learning_rate": 0.0002,
+      "loss": 1.7984,
+      "step": 200
+    },
+    {
+      "epoch": 0.280561122244489,
+      "grad_norm": 0.398699015378952,
+      "learning_rate": 0.0002,
+      "loss": 1.8728,
+      "step": 210
+    },
+    {
+      "epoch": 0.2939211756847027,
+      "grad_norm": 0.3585626482963562,
+      "learning_rate": 0.0002,
+      "loss": 1.8205,
+      "step": 220
+    },
+    {
+      "epoch": 0.3072812291249165,
+      "grad_norm": 0.3811776041984558,
+      "learning_rate": 0.0002,
+      "loss": 1.8861,
+      "step": 230
+    },
+    {
+      "epoch": 0.32064128256513025,
+      "grad_norm": 0.37261509895324707,
+      "learning_rate": 0.0002,
+      "loss": 1.8365,
+      "step": 240
+    },
+    {
+      "epoch": 0.33400133600534404,
+      "grad_norm": 0.39762404561042786,
+      "learning_rate": 0.0002,
+      "loss": 1.9186,
+      "step": 250
+    },
+    {
+      "epoch": 0.3473613894455578,
+      "grad_norm": 0.3509528934955597,
+      "learning_rate": 0.0002,
+      "loss": 1.7965,
+      "step": 260
+    },
+    {
+      "epoch": 0.36072144288577157,
+      "grad_norm": 0.3169104754924774,
+      "learning_rate": 0.0002,
+      "loss": 1.7802,
+      "step": 270
+    },
+    {
+      "epoch": 0.3740814963259853,
+      "grad_norm": 0.33714795112609863,
+      "learning_rate": 0.0002,
+      "loss": 1.8038,
+      "step": 280
+    },
+    {
+      "epoch": 0.38744154976619904,
+      "grad_norm": 1.2936875820159912,
+      "learning_rate": 0.0002,
+      "loss": 1.787,
+      "step": 290
+    },
+    {
+      "epoch": 0.40080160320641284,
+      "grad_norm": 0.3459427058696747,
+      "learning_rate": 0.0002,
+      "loss": 1.7974,
+      "step": 300
+    },
+    {
+      "epoch": 0.4141616566466266,
+      "grad_norm": 0.3380655348300934,
+      "learning_rate": 0.0002,
+      "loss": 1.8879,
+      "step": 310
+    },
+    {
+      "epoch": 0.42752171008684037,
+      "grad_norm": 0.3890381455421448,
+      "learning_rate": 0.0002,
+      "loss": 1.9196,
+      "step": 320
+    },
+    {
+      "epoch": 0.4408817635270541,
+      "grad_norm": 0.432327002286911,
+      "learning_rate": 0.0002,
+      "loss": 1.8034,
+      "step": 330
+    },
+    {
+      "epoch": 0.45424181696726784,
+      "grad_norm": 0.3736560046672821,
+      "learning_rate": 0.0002,
+      "loss": 1.8443,
+      "step": 340
+    },
+    {
+      "epoch": 0.46760187040748163,
+      "grad_norm": 0.3700982630252838,
+      "learning_rate": 0.0002,
+      "loss": 1.8506,
+      "step": 350
+    },
+    {
+      "epoch": 0.48096192384769537,
+      "grad_norm": 0.4533902406692505,
+      "learning_rate": 0.0002,
+      "loss": 1.7978,
+      "step": 360
+    },
+    {
+      "epoch": 0.49432197728790916,
+      "grad_norm": 0.35999053716659546,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 370
+    },
+    {
+      "epoch": 0.5076820307281229,
+      "grad_norm": 0.3490903675556183,
+      "learning_rate": 0.0002,
+      "loss": 1.7995,
+      "step": 380
+    },
+    {
+      "epoch": 0.5210420841683366,
+      "grad_norm": 0.34704291820526123,
+      "learning_rate": 0.0002,
+      "loss": 1.8709,
+      "step": 390
+    },
+    {
+      "epoch": 0.5344021376085505,
+      "grad_norm": 0.343565434217453,
+      "learning_rate": 0.0002,
+      "loss": 1.7948,
+      "step": 400
+    },
+    {
+      "epoch": 0.5477621910487642,
+      "grad_norm": 0.3573552966117859,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 410
+    },
+    {
+      "epoch": 0.561122244488978,
+      "grad_norm": 0.32980719208717346,
+      "learning_rate": 0.0002,
+      "loss": 1.8477,
+      "step": 420
+    },
+    {
+      "epoch": 0.5744822979291917,
+      "grad_norm": 0.356952428817749,
+      "learning_rate": 0.0002,
+      "loss": 1.9233,
+      "step": 430
+    },
+    {
+      "epoch": 0.5878423513694054,
+      "grad_norm": 0.3170869052410126,
+      "learning_rate": 0.0002,
+      "loss": 1.7433,
+      "step": 440
+    },
+    {
+      "epoch": 0.6012024048096193,
+      "grad_norm": 0.35233718156814575,
+      "learning_rate": 0.0002,
+      "loss": 1.7607,
+      "step": 450
+    },
+    {
+      "epoch": 0.614562458249833,
+      "grad_norm": 0.3480125367641449,
+      "learning_rate": 0.0002,
+      "loss": 1.8111,
+      "step": 460
+    },
+    {
+      "epoch": 0.6279225116900468,
+      "grad_norm": 0.4762810468673706,
+      "learning_rate": 0.0002,
+      "loss": 1.8386,
+      "step": 470
+    },
+    {
+      "epoch": 0.6412825651302605,
+      "grad_norm": 0.3907663822174072,
+      "learning_rate": 0.0002,
+      "loss": 1.805,
+      "step": 480
+    },
+    {
+      "epoch": 0.6546426185704742,
+      "grad_norm": 0.36315613985061646,
+      "learning_rate": 0.0002,
+      "loss": 1.8113,
+      "step": 490
+    },
+    {
+      "epoch": 0.6680026720106881,
+      "grad_norm": 0.377796471118927,
+      "learning_rate": 0.0002,
+      "loss": 1.7805,
+      "step": 500
+    },
+    {
+      "epoch": 0.6813627254509018,
+      "grad_norm": 0.34284207224845886,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 510
+    },
+    {
+      "epoch": 0.6947227788911156,
+      "grad_norm": 0.35563018918037415,
+      "learning_rate": 0.0002,
+      "loss": 1.8013,
+      "step": 520
+    },
+    {
+      "epoch": 0.7080828323313293,
+      "grad_norm": 0.37575867772102356,
+      "learning_rate": 0.0002,
+      "loss": 1.8414,
+      "step": 530
+    },
+    {
+      "epoch": 0.7214428857715431,
+      "grad_norm": 0.35719701647758484,
+      "learning_rate": 0.0002,
+      "loss": 1.7993,
+      "step": 540
+    },
+    {
+      "epoch": 0.7348029392117569,
+      "grad_norm": 0.385813444852829,
+      "learning_rate": 0.0002,
+      "loss": 1.7574,
+      "step": 550
+    },
+    {
+      "epoch": 0.7481629926519706,
+      "grad_norm": 0.44509607553482056,
+      "learning_rate": 0.0002,
+      "loss": 1.7985,
+      "step": 560
+    },
+    {
+      "epoch": 0.7615230460921844,
+      "grad_norm": 0.36108464002609253,
+      "learning_rate": 0.0002,
+      "loss": 1.7459,
+      "step": 570
+    },
+    {
+      "epoch": 0.7748830995323981,
+      "grad_norm": 0.3530745804309845,
+      "learning_rate": 0.0002,
+      "loss": 1.8207,
+      "step": 580
+    },
+    {
+      "epoch": 0.7882431529726119,
+      "grad_norm": 0.34888574481010437,
+      "learning_rate": 0.0002,
+      "loss": 1.7479,
+      "step": 590
+    },
+    {
+      "epoch": 0.8016032064128257,
+      "grad_norm": 0.387346476316452,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 600
+    },
+    {
+      "epoch": 0.8149632598530394,
+      "grad_norm": 0.3641138970851898,
+      "learning_rate": 0.0002,
+      "loss": 1.8071,
+      "step": 610
+    },
+    {
+      "epoch": 0.8283233132932531,
+      "grad_norm": 0.33729103207588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7531,
+      "step": 620
+    },
+    {
+      "epoch": 0.8416833667334669,
+      "grad_norm": 0.3652004599571228,
+      "learning_rate": 0.0002,
+      "loss": 1.8613,
+      "step": 630
+    },
+    {
+      "epoch": 0.8550434201736807,
+      "grad_norm": 0.3986643850803375,
+      "learning_rate": 0.0002,
+      "loss": 1.9184,
+      "step": 640
+    },
+    {
+      "epoch": 0.8684034736138945,
+      "grad_norm": 0.3458964228630066,
+      "learning_rate": 0.0002,
+      "loss": 1.8198,
+      "step": 650
+    },
+    {
+      "epoch": 0.8817635270541082,
+      "grad_norm": 0.3559381365776062,
+      "learning_rate": 0.0002,
+      "loss": 1.803,
+      "step": 660
+    },
+    {
+      "epoch": 0.895123580494322,
+      "grad_norm": 0.3612841069698334,
+      "learning_rate": 0.0002,
+      "loss": 1.7641,
+      "step": 670
+    },
+    {
+      "epoch": 0.9084836339345357,
+      "grad_norm": 0.34771719574928284,
+      "learning_rate": 0.0002,
+      "loss": 1.7888,
+      "step": 680
+    },
+    {
+      "epoch": 0.9218436873747495,
+      "grad_norm": 0.3371497094631195,
+      "learning_rate": 0.0002,
+      "loss": 1.8204,
+      "step": 690
+    },
+    {
+      "epoch": 0.9352037408149633,
+      "grad_norm": 0.5596055388450623,
+      "learning_rate": 0.0002,
+      "loss": 1.7848,
+      "step": 700
+    },
+    {
+      "epoch": 0.948563794255177,
+      "grad_norm": 0.311880499124527,
+      "learning_rate": 0.0002,
+      "loss": 1.7794,
+      "step": 710
+    },
+    {
+      "epoch": 0.9619238476953907,
+      "grad_norm": 0.3462068736553192,
+      "learning_rate": 0.0002,
+      "loss": 1.8464,
+      "step": 720
+    },
+    {
+      "epoch": 0.9752839011356046,
+      "grad_norm": 0.29982393980026245,
+      "learning_rate": 0.0002,
+      "loss": 1.8197,
+      "step": 730
+    },
+    {
+      "epoch": 0.9886439545758183,
+      "grad_norm": 0.34606459736824036,
+      "learning_rate": 0.0002,
+      "loss": 1.8503,
+      "step": 740
+    },
+    {
+      "epoch": 0.9993319973279893,
+      "eval_loss": 1.8201380968093872,
+      "eval_runtime": 38.6124,
+      "eval_samples_per_second": 13.338,
+      "eval_steps_per_second": 1.683,
+      "step": 748
+    },
+    {
+      "epoch": 1.002004008016032,
+      "grad_norm": 0.32302048802375793,
+      "learning_rate": 0.0002,
+      "loss": 1.7786,
+      "step": 750
+    },
+    {
+      "epoch": 1.0153640614562458,
+      "grad_norm": 0.37585633993148804,
+      "learning_rate": 0.0002,
+      "loss": 1.7297,
+      "step": 760
+    },
+    {
+      "epoch": 1.0287241148964597,
+      "grad_norm": 0.33826273679733276,
+      "learning_rate": 0.0002,
+      "loss": 1.7008,
+      "step": 770
+    },
+    {
+      "epoch": 1.0420841683366733,
+      "grad_norm": 0.44682955741882324,
+      "learning_rate": 0.0002,
+      "loss": 1.809,
+      "step": 780
+    },
+    {
+      "epoch": 1.0554442217768871,
+      "grad_norm": 0.422188401222229,
+      "learning_rate": 0.0002,
+      "loss": 1.7092,
+      "step": 790
+    },
+    {
+      "epoch": 1.0688042752171008,
+      "grad_norm": 0.3809906244277954,
+      "learning_rate": 0.0002,
+      "loss": 1.7765,
+      "step": 800
+    },
+    {
+      "epoch": 1.0821643286573146,
+      "grad_norm": 0.3454349637031555,
+      "learning_rate": 0.0002,
+      "loss": 1.7431,
+      "step": 810
+    },
+    {
+      "epoch": 1.0955243820975284,
+      "grad_norm": 0.3767355978488922,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 820
+    },
+    {
+      "epoch": 1.108884435537742,
+      "grad_norm": 0.3361407518386841,
+      "learning_rate": 0.0002,
+      "loss": 1.7224,
+      "step": 830
+    },
+    {
+      "epoch": 1.122244488977956,
+      "grad_norm": 0.3654632568359375,
+      "learning_rate": 0.0002,
+      "loss": 1.7509,
+      "step": 840
+    },
+    {
+      "epoch": 1.1356045424181698,
+      "grad_norm": 0.3822861313819885,
+      "learning_rate": 0.0002,
+      "loss": 1.7151,
+      "step": 850
+    },
+    {
+      "epoch": 1.1489645958583834,
+      "grad_norm": 0.3853831887245178,
+      "learning_rate": 0.0002,
+      "loss": 1.7121,
+      "step": 860
+    },
+    {
+      "epoch": 1.1623246492985972,
+      "grad_norm": 0.35521796345710754,
+      "learning_rate": 0.0002,
+      "loss": 1.7685,
+      "step": 870
+    },
+    {
+      "epoch": 1.1756847027388109,
+      "grad_norm": 0.4107200503349304,
+      "learning_rate": 0.0002,
+      "loss": 1.7735,
+      "step": 880
+    },
+    {
+      "epoch": 1.1890447561790247,
+      "grad_norm": 0.33219534158706665,
+      "learning_rate": 0.0002,
+      "loss": 1.7484,
+      "step": 890
+    },
+    {
+      "epoch": 1.2024048096192386,
+      "grad_norm": 0.3559704124927521,
+      "learning_rate": 0.0002,
+      "loss": 1.7071,
+      "step": 900
+    },
+    {
+      "epoch": 1.2157648630594522,
+      "grad_norm": 0.3700537383556366,
+      "learning_rate": 0.0002,
+      "loss": 1.7535,
+      "step": 910
+    },
+    {
+      "epoch": 1.229124916499666,
+      "grad_norm": 0.3771909475326538,
+      "learning_rate": 0.0002,
+      "loss": 1.7513,
+      "step": 920
+    },
+    {
+      "epoch": 1.2424849699398797,
+      "grad_norm": 0.3136613965034485,
+      "learning_rate": 0.0002,
+      "loss": 1.7566,
+      "step": 930
+    },
+    {
+      "epoch": 1.2558450233800935,
+      "grad_norm": 0.3952099084854126,
+      "learning_rate": 0.0002,
+      "loss": 1.6783,
+      "step": 940
+    },
+    {
+      "epoch": 1.2692050768203074,
+      "grad_norm": 0.36534377932548523,
+      "learning_rate": 0.0002,
+      "loss": 1.7691,
+      "step": 950
+    },
+    {
+      "epoch": 1.282565130260521,
+      "grad_norm": 0.3803492486476898,
+      "learning_rate": 0.0002,
+      "loss": 1.7127,
+      "step": 960
+    },
+    {
+      "epoch": 1.2959251837007348,
+      "grad_norm": 0.3992428183555603,
+      "learning_rate": 0.0002,
+      "loss": 1.7896,
+      "step": 970
+    },
+    {
+      "epoch": 1.3092852371409487,
+      "grad_norm": 0.3627142906188965,
+      "learning_rate": 0.0002,
+      "loss": 1.7343,
+      "step": 980
+    },
+    {
+      "epoch": 1.3226452905811623,
+      "grad_norm": 0.4248180091381073,
+      "learning_rate": 0.0002,
+      "loss": 1.7598,
+      "step": 990
+    },
+    {
+      "epoch": 1.3360053440213762,
+      "grad_norm": 0.4060308039188385,
+      "learning_rate": 0.0002,
+      "loss": 1.6896,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3493653974615898,
+      "grad_norm": 0.3788969814777374,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 1010
+    },
+    {
+      "epoch": 1.3627254509018036,
+      "grad_norm": 0.4174270033836365,
+      "learning_rate": 0.0002,
+      "loss": 1.7111,
+      "step": 1020
+    },
+    {
+      "epoch": 1.3760855043420173,
+      "grad_norm": 0.35500675439834595,
+      "learning_rate": 0.0002,
+      "loss": 1.7975,
+      "step": 1030
+    },
+    {
+      "epoch": 1.389445557782231,
+      "grad_norm": 0.3454059362411499,
+      "learning_rate": 0.0002,
+      "loss": 1.724,
+      "step": 1040
+    },
+    {
+      "epoch": 1.402805611222445,
+      "grad_norm": 0.45807570219039917,
+      "learning_rate": 0.0002,
+      "loss": 1.8299,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4161656646626586,
+      "grad_norm": 0.39338022470474243,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4295257181028724,
+      "grad_norm": 0.3870709240436554,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4428857715430863,
+      "grad_norm": 0.40996190905570984,
+      "learning_rate": 0.0002,
+      "loss": 1.6565,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4562458249833,
+      "grad_norm": 0.38762837648391724,
+      "learning_rate": 0.0002,
+      "loss": 1.7324,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4696058784235138,
+      "grad_norm": 0.36756977438926697,
+      "learning_rate": 0.0002,
+      "loss": 1.7362,
+      "step": 1100
+    },
+    {
+      "epoch": 1.4829659318637274,
+      "grad_norm": 0.4087235927581787,
+      "learning_rate": 0.0002,
+      "loss": 1.7451,
+      "step": 1110
+    },
+    {
+      "epoch": 1.4963259853039412,
+      "grad_norm": 0.3357745110988617,
+      "learning_rate": 0.0002,
+      "loss": 1.7114,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5096860387441549,
+      "grad_norm": 0.37486532330513,
+      "learning_rate": 0.0002,
+      "loss": 1.6877,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5230460921843687,
+      "grad_norm": 0.3387809991836548,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5364061456245826,
+      "grad_norm": 0.37462118268013,
+      "learning_rate": 0.0002,
+      "loss": 1.7169,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5497661990647962,
+      "grad_norm": 0.38575324416160583,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 1160
+    },
+    {
+      "epoch": 1.56312625250501,
+      "grad_norm": 0.3515765964984894,
+      "learning_rate": 0.0002,
+      "loss": 1.7438,
+      "step": 1170
+    },
+    {
+      "epoch": 1.5764863059452239,
+      "grad_norm": 0.39308643341064453,
+      "learning_rate": 0.0002,
+      "loss": 1.7524,
+      "step": 1180
+    },
+    {
+      "epoch": 1.5898463593854375,
+      "grad_norm": 0.3308864235877991,
+      "learning_rate": 0.0002,
+      "loss": 1.6422,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6032064128256514,
+      "grad_norm": 0.3397478461265564,
+      "learning_rate": 0.0002,
+      "loss": 1.7566,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6165664662658652,
+      "grad_norm": 0.3911525309085846,
+      "learning_rate": 0.0002,
+      "loss": 1.7871,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6299265197060788,
+      "grad_norm": 0.3771969974040985,
+      "learning_rate": 0.0002,
+      "loss": 1.7443,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6432865731462925,
+      "grad_norm": 0.35346856713294983,
+      "learning_rate": 0.0002,
+      "loss": 1.7631,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6566466265865063,
+      "grad_norm": 0.41736963391304016,
+      "learning_rate": 0.0002,
+      "loss": 1.7225,
+      "step": 1240
+    },
+    {
+      "epoch": 1.6700066800267201,
+      "grad_norm": 0.3375225067138672,
+      "learning_rate": 0.0002,
+      "loss": 1.7582,
+      "step": 1250
+    },
+    {
+      "epoch": 1.6833667334669338,
+      "grad_norm": 0.3779928982257843,
+      "learning_rate": 0.0002,
+      "loss": 1.6916,
+      "step": 1260
+    },
+    {
+      "epoch": 1.6967267869071476,
+      "grad_norm": 0.35388994216918945,
+      "learning_rate": 0.0002,
+      "loss": 1.728,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7100868403473615,
+      "grad_norm": 0.33884134888648987,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 1280
+    },
+    {
+      "epoch": 1.723446893787575,
+      "grad_norm": 0.35439756512641907,
+      "learning_rate": 0.0002,
+      "loss": 1.7083,
+      "step": 1290
+    },
+    {
+      "epoch": 1.736806947227789,
+      "grad_norm": 0.3766156733036041,
+      "learning_rate": 0.0002,
+      "loss": 1.7389,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7501670006680028,
+      "grad_norm": 0.36148911714553833,
+      "learning_rate": 0.0002,
+      "loss": 1.7847,
+      "step": 1310
+    },
+    {
+      "epoch": 1.7635270541082164,
+      "grad_norm": 0.39687496423721313,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 1320
+    },
+    {
+      "epoch": 1.77688710754843,
+      "grad_norm": 0.35639452934265137,
+      "learning_rate": 0.0002,
+      "loss": 1.7541,
+      "step": 1330
+    },
+    {
+      "epoch": 1.7902471609886441,
+      "grad_norm": 0.38781628012657166,
+      "learning_rate": 0.0002,
+      "loss": 1.7254,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8036072144288577,
+      "grad_norm": 0.42784637212753296,
+      "learning_rate": 0.0002,
+      "loss": 1.7867,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8169672678690714,
+      "grad_norm": 0.40258511900901794,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8303273213092852,
+      "grad_norm": 0.36674195528030396,
+      "learning_rate": 0.0002,
+      "loss": 1.7771,
+      "step": 1370
+    },
+    {
+      "epoch": 1.843687374749499,
+      "grad_norm": 0.4064558446407318,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8570474281897127,
+      "grad_norm": 0.3669849932193756,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1390
+    },
+    {
+      "epoch": 1.8704074816299265,
+      "grad_norm": 0.37569567561149597,
+      "learning_rate": 0.0002,
+      "loss": 1.7924,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8837675350701404,
+      "grad_norm": 0.37307995557785034,
+      "learning_rate": 0.0002,
+      "loss": 1.7885,
+      "step": 1410
+    },
+    {
+      "epoch": 1.897127588510354,
+      "grad_norm": 0.3772695064544678,
+      "learning_rate": 0.0002,
+      "loss": 1.7548,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9104876419505676,
+      "grad_norm": 0.36993589997291565,
+      "learning_rate": 0.0002,
+      "loss": 1.7682,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9238476953907817,
+      "grad_norm": 0.3490557372570038,
+      "learning_rate": 0.0002,
+      "loss": 1.7249,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9372077488309953,
+      "grad_norm": 0.3716149628162384,
+      "learning_rate": 0.0002,
+      "loss": 1.7979,
+      "step": 1450
+    },
+    {
+      "epoch": 1.950567802271209,
+      "grad_norm": 0.39236098527908325,
+      "learning_rate": 0.0002,
+      "loss": 1.6664,
+      "step": 1460
+    },
+    {
+      "epoch": 1.9639278557114228,
+      "grad_norm": 0.37258651852607727,
+      "learning_rate": 0.0002,
+      "loss": 1.6852,
+      "step": 1470
+    },
+    {
+      "epoch": 1.9772879091516367,
+      "grad_norm": 0.36183077096939087,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 1480
+    },
+    {
+      "epoch": 1.9906479625918503,
+      "grad_norm": 0.3956947326660156,
+      "learning_rate": 0.0002,
+      "loss": 1.7055,
+      "step": 1490
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8132041692733765,
+      "eval_runtime": 38.6287,
+      "eval_samples_per_second": 13.332,
+      "eval_steps_per_second": 1.683,
+      "step": 1497
+    },
+    {
+      "epoch": 2.004008016032064,
+      "grad_norm": 0.34480565786361694,
+      "learning_rate": 0.0002,
+      "loss": 1.6791,
+      "step": 1500
+    },
+    {
+      "epoch": 2.017368069472278,
+      "grad_norm": 0.3418028652667999,
+      "learning_rate": 0.0002,
+      "loss": 1.6367,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0307281229124916,
+      "grad_norm": 0.4514467716217041,
+      "learning_rate": 0.0002,
+      "loss": 1.5827,
+      "step": 1520
+    },
+    {
+      "epoch": 2.0440881763527052,
+      "grad_norm": 0.4197506606578827,
+      "learning_rate": 0.0002,
+      "loss": 1.6365,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0574482297929193,
+      "grad_norm": 0.4134170711040497,
+      "learning_rate": 0.0002,
+      "loss": 1.6221,
+      "step": 1540
+    },
+    {
+      "epoch": 2.070808283233133,
+      "grad_norm": 0.43709826469421387,
+      "learning_rate": 0.0002,
+      "loss": 1.6876,
+      "step": 1550
+    },
+    {
+      "epoch": 2.0841683366733466,
+      "grad_norm": 0.4703378677368164,
+      "learning_rate": 0.0002,
+      "loss": 1.5779,
+      "step": 1560
+    },
+    {
+      "epoch": 2.0975283901135606,
+      "grad_norm": 0.4538188576698303,
+      "learning_rate": 0.0002,
+      "loss": 1.599,
+      "step": 1570
+    },
+    {
+      "epoch": 2.1108884435537743,
+      "grad_norm": 0.4649668037891388,
+      "learning_rate": 0.0002,
+      "loss": 1.6464,
+      "step": 1580
+    },
+    {
+      "epoch": 2.124248496993988,
+      "grad_norm": 0.42669883370399475,
+      "learning_rate": 0.0002,
+      "loss": 1.6348,
+      "step": 1590
+    },
+    {
+      "epoch": 2.1376085504342015,
+      "grad_norm": 0.43162038922309875,
+      "learning_rate": 0.0002,
+      "loss": 1.5838,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1509686038744156,
+      "grad_norm": 0.4294586479663849,
+      "learning_rate": 0.0002,
+      "loss": 1.6673,
+      "step": 1610
+    },
+    {
+      "epoch": 2.164328657314629,
+      "grad_norm": 0.4669102132320404,
+      "learning_rate": 0.0002,
+      "loss": 1.6024,
+      "step": 1620
+    },
+    {
+      "epoch": 2.177688710754843,
+      "grad_norm": 0.4188412129878998,
+      "learning_rate": 0.0002,
+      "loss": 1.659,
+      "step": 1630
+    },
+    {
+      "epoch": 2.191048764195057,
+      "grad_norm": 0.4662680923938751,
+      "learning_rate": 0.0002,
+      "loss": 1.625,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2044088176352705,
+      "grad_norm": 0.4020286500453949,
+      "learning_rate": 0.0002,
+      "loss": 1.6699,
+      "step": 1650
+    },
+    {
+      "epoch": 2.217768871075484,
+      "grad_norm": 0.41919606924057007,
+      "learning_rate": 0.0002,
+      "loss": 1.6284,
+      "step": 1660
+    },
+    {
+      "epoch": 2.231128924515698,
+      "grad_norm": 0.4644531309604645,
+      "learning_rate": 0.0002,
+      "loss": 1.6776,
+      "step": 1670
+    },
+    {
+      "epoch": 2.244488977955912,
+      "grad_norm": 0.4526427984237671,
+      "learning_rate": 0.0002,
+      "loss": 1.6711,
+      "step": 1680
+    },
+    {
+      "epoch": 2.2578490313961255,
+      "grad_norm": 0.45953166484832764,
+      "learning_rate": 0.0002,
+      "loss": 1.6058,
+      "step": 1690
+    },
+    {
+      "epoch": 2.2712090848363395,
+      "grad_norm": 0.4701860249042511,
+      "learning_rate": 0.0002,
+      "loss": 1.5979,
+      "step": 1700
+    },
+    {
+      "epoch": 2.284569138276553,
+      "grad_norm": 0.4749310612678528,
+      "learning_rate": 0.0002,
+      "loss": 1.6183,
+      "step": 1710
+    },
+    {
+      "epoch": 2.297929191716767,
+      "grad_norm": 0.45026102662086487,
+      "learning_rate": 0.0002,
+      "loss": 1.6703,
+      "step": 1720
+    },
+    {
+      "epoch": 2.3112892451569804,
+      "grad_norm": 0.4755004048347473,
+      "learning_rate": 0.0002,
+      "loss": 1.6386,
+      "step": 1730
+    },
+    {
+      "epoch": 2.3246492985971945,
+      "grad_norm": 0.4505726993083954,
+      "learning_rate": 0.0002,
+      "loss": 1.6365,
+      "step": 1740
+    },
+    {
+      "epoch": 2.338009352037408,
+      "grad_norm": 0.44464054703712463,
+      "learning_rate": 0.0002,
+      "loss": 1.589,
+      "step": 1750
+    },
+    {
+      "epoch": 2.3513694054776217,
+      "grad_norm": 0.4449476897716522,
+      "learning_rate": 0.0002,
+      "loss": 1.6139,
+      "step": 1760
+    },
+    {
+      "epoch": 2.364729458917836,
+      "grad_norm": 0.4216482937335968,
+      "learning_rate": 0.0002,
+      "loss": 1.7195,
+      "step": 1770
+    },
+    {
+      "epoch": 2.3780895123580494,
+      "grad_norm": 0.4379308521747589,
+      "learning_rate": 0.0002,
+      "loss": 1.7075,
+      "step": 1780
+    },
+    {
+      "epoch": 2.391449565798263,
+      "grad_norm": 0.41670042276382446,
+      "learning_rate": 0.0002,
+      "loss": 1.7024,
+      "step": 1790
+    },
+    {
+      "epoch": 2.404809619238477,
+      "grad_norm": 0.48089510202407837,
+      "learning_rate": 0.0002,
+      "loss": 1.5989,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4181696726786908,
+      "grad_norm": 0.4389738142490387,
+      "learning_rate": 0.0002,
+      "loss": 1.6313,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4315297261189044,
+      "grad_norm": 0.45293036103248596,
+      "learning_rate": 0.0002,
+      "loss": 1.5841,
+      "step": 1820
+    },
+    {
+      "epoch": 2.4448897795591185,
+      "grad_norm": 0.5211683511734009,
+      "learning_rate": 0.0002,
+      "loss": 1.6887,
+      "step": 1830
+    },
+    {
+      "epoch": 2.458249832999332,
+      "grad_norm": 0.4631884694099426,
+      "learning_rate": 0.0002,
+      "loss": 1.6599,
+      "step": 1840
+    },
+    {
+      "epoch": 2.4716098864395457,
+      "grad_norm": 0.4276818335056305,
+      "learning_rate": 0.0002,
+      "loss": 1.6537,
+      "step": 1850
+    },
+    {
+      "epoch": 2.4849699398797593,
+      "grad_norm": 0.477524071931839,
+      "learning_rate": 0.0002,
+      "loss": 1.6836,
+      "step": 1860
+    },
+    {
+      "epoch": 2.4983299933199734,
+      "grad_norm": 0.44860973954200745,
+      "learning_rate": 0.0002,
+      "loss": 1.66,
+      "step": 1870
+    },
+    {
+      "epoch": 2.511690046760187,
+      "grad_norm": 0.46413546800613403,
+      "learning_rate": 0.0002,
+      "loss": 1.6308,
+      "step": 1880
+    },
+    {
+      "epoch": 2.5250501002004007,
+      "grad_norm": 0.42487645149230957,
+      "learning_rate": 0.0002,
+      "loss": 1.6225,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5384101536406147,
+      "grad_norm": 0.4778307378292084,
+      "learning_rate": 0.0002,
+      "loss": 1.6268,
+      "step": 1900
+    },
+    {
+      "epoch": 2.5517702070808284,
+      "grad_norm": 0.45307061076164246,
+      "learning_rate": 0.0002,
+      "loss": 1.6143,
+      "step": 1910
+    },
+    {
+      "epoch": 2.565130260521042,
+      "grad_norm": 0.47886642813682556,
+      "learning_rate": 0.0002,
+      "loss": 1.7279,
+      "step": 1920
+    },
+    {
+      "epoch": 2.5784903139612556,
+      "grad_norm": 0.4839435815811157,
+      "learning_rate": 0.0002,
+      "loss": 1.5931,
+      "step": 1930
+    },
+    {
+      "epoch": 2.5918503674014697,
+      "grad_norm": 0.4388359785079956,
+      "learning_rate": 0.0002,
+      "loss": 1.6089,
+      "step": 1940
+    },
+    {
+      "epoch": 2.6052104208416833,
+      "grad_norm": 0.47859734296798706,
+      "learning_rate": 0.0002,
+      "loss": 1.6828,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6185704742818974,
+      "grad_norm": 0.5526517033576965,
+      "learning_rate": 0.0002,
+      "loss": 1.6014,
+      "step": 1960
+    },
+    {
+      "epoch": 2.631930527722111,
+      "grad_norm": 0.5449170470237732,
+      "learning_rate": 0.0002,
+      "loss": 1.6889,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6452905811623246,
+      "grad_norm": 0.48521968722343445,
+      "learning_rate": 0.0002,
+      "loss": 1.6481,
+      "step": 1980
+    },
+    {
+      "epoch": 2.6586506346025383,
+      "grad_norm": 0.4733737111091614,
+      "learning_rate": 0.0002,
+      "loss": 1.6741,
+      "step": 1990
+    },
+    {
+      "epoch": 2.6720106880427523,
+      "grad_norm": 0.507118284702301,
+      "learning_rate": 0.0002,
+      "loss": 1.662,
+      "step": 2000
+    },
+    {
+      "epoch": 2.685370741482966,
+      "grad_norm": 0.4508971571922302,
+      "learning_rate": 0.0002,
+      "loss": 1.6419,
+      "step": 2010
+    },
+    {
+      "epoch": 2.6987307949231796,
+      "grad_norm": 0.4657728672027588,
+      "learning_rate": 0.0002,
+      "loss": 1.7052,
+      "step": 2020
+    },
+    {
+      "epoch": 2.7120908483633936,
+      "grad_norm": 0.48647549748420715,
+      "learning_rate": 0.0002,
+      "loss": 1.6261,
+      "step": 2030
+    },
+    {
+      "epoch": 2.7254509018036073,
+      "grad_norm": 0.49525555968284607,
+      "learning_rate": 0.0002,
+      "loss": 1.5638,
+      "step": 2040
+    },
+    {
+      "epoch": 2.738810955243821,
+      "grad_norm": 0.4712379276752472,
+      "learning_rate": 0.0002,
+      "loss": 1.658,
+      "step": 2050
+    },
+    {
+      "epoch": 2.7521710086840345,
+      "grad_norm": 0.4846591055393219,
+      "learning_rate": 0.0002,
+      "loss": 1.6464,
+      "step": 2060
+    },
+    {
+      "epoch": 2.7655310621242486,
+      "grad_norm": 0.4823240041732788,
+      "learning_rate": 0.0002,
+      "loss": 1.5641,
+      "step": 2070
+    },
+    {
+      "epoch": 2.778891115564462,
+      "grad_norm": 0.4546685516834259,
+      "learning_rate": 0.0002,
+      "loss": 1.6701,
+      "step": 2080
+    },
+    {
+      "epoch": 2.7922511690046763,
+      "grad_norm": 0.45542681217193604,
+      "learning_rate": 0.0002,
+      "loss": 1.7015,
+      "step": 2090
+    },
+    {
+      "epoch": 2.80561122244489,
+      "grad_norm": 0.42137566208839417,
+      "learning_rate": 0.0002,
+      "loss": 1.6398,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8189712758851035,
+      "grad_norm": 0.6143282055854797,
+      "learning_rate": 0.0002,
+      "loss": 1.6526,
+      "step": 2110
+    },
+    {
+      "epoch": 2.832331329325317,
+      "grad_norm": 0.4828081727027893,
+      "learning_rate": 0.0002,
+      "loss": 1.6955,
+      "step": 2120
+    },
+    {
+      "epoch": 2.845691382765531,
+      "grad_norm": 0.4319005608558655,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 2130
+    },
+    {
+      "epoch": 2.859051436205745,
+      "grad_norm": 0.4297086298465729,
+      "learning_rate": 0.0002,
+      "loss": 1.6717,
+      "step": 2140
+    },
+    {
+      "epoch": 2.8724114896459585,
+      "grad_norm": 0.5011981129646301,
+      "learning_rate": 0.0002,
+      "loss": 1.5968,
+      "step": 2150
+    },
+    {
+      "epoch": 2.8857715430861726,
+      "grad_norm": 0.4401548504829407,
+      "learning_rate": 0.0002,
+      "loss": 1.7181,
+      "step": 2160
+    },
+    {
+      "epoch": 2.899131596526386,
+      "grad_norm": 0.48090746998786926,
+      "learning_rate": 0.0002,
+      "loss": 1.5722,
+      "step": 2170
+    },
+    {
+      "epoch": 2.9124916499666,
+      "grad_norm": 0.4740385413169861,
+      "learning_rate": 0.0002,
+      "loss": 1.6596,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9258517034068134,
+      "grad_norm": 0.5337260365486145,
+      "learning_rate": 0.0002,
+      "loss": 1.6501,
+      "step": 2190
+    },
+    {
+      "epoch": 2.9392117568470275,
+      "grad_norm": 0.4420052766799927,
+      "learning_rate": 0.0002,
+      "loss": 1.6802,
+      "step": 2200
+    },
+    {
+      "epoch": 2.952571810287241,
+      "grad_norm": 0.477512389421463,
+      "learning_rate": 0.0002,
+      "loss": 1.5474,
+      "step": 2210
+    },
+    {
+      "epoch": 2.9659318637274548,
+      "grad_norm": 0.5344052910804749,
+      "learning_rate": 0.0002,
+      "loss": 1.6544,
+      "step": 2220
+    },
+    {
+      "epoch": 2.979291917167669,
+      "grad_norm": 0.4483940303325653,
+      "learning_rate": 0.0002,
+      "loss": 1.6866,
+      "step": 2230
+    },
+    {
+      "epoch": 2.9926519706078825,
+      "grad_norm": 0.4366597831249237,
+      "learning_rate": 0.0002,
+      "loss": 1.6477,
+      "step": 2240
+    },
+    {
+      "epoch": 2.9993319973279893,
+      "eval_loss": 1.834012746810913,
+      "eval_runtime": 38.5659,
+      "eval_samples_per_second": 13.354,
+      "eval_steps_per_second": 1.685,
+      "step": 2245
+    },
+    {
+      "epoch": 3.006012024048096,
+      "grad_norm": 0.428824245929718,
+      "learning_rate": 0.0002,
+      "loss": 1.5582,
+      "step": 2250
+    },
+    {
+      "epoch": 3.01937207748831,
+      "grad_norm": 0.4870174825191498,
+      "learning_rate": 0.0002,
+      "loss": 1.499,
+      "step": 2260
+    },
+    {
+      "epoch": 3.032732130928524,
+      "grad_norm": 0.4684266149997711,
+      "learning_rate": 0.0002,
+      "loss": 1.4872,
+      "step": 2270
+    },
+    {
+      "epoch": 3.0460921843687374,
+      "grad_norm": 0.581604540348053,
+      "learning_rate": 0.0002,
+      "loss": 1.5284,
+      "step": 2280
+    },
+    {
+      "epoch": 3.059452237808951,
+      "grad_norm": 0.5561677813529968,
+      "learning_rate": 0.0002,
+      "loss": 1.4549,
+      "step": 2290
+    },
+    {
+      "epoch": 3.072812291249165,
+      "grad_norm": 0.5750220417976379,
+      "learning_rate": 0.0002,
+      "loss": 1.4903,
+      "step": 2300
+    },
+    {
+      "epoch": 3.0861723446893787,
+      "grad_norm": 0.5704626441001892,
+      "learning_rate": 0.0002,
+      "loss": 1.5903,
+      "step": 2310
+    },
+    {
+      "epoch": 3.0995323981295924,
+      "grad_norm": 0.6242083311080933,
+      "learning_rate": 0.0002,
+      "loss": 1.4292,
+      "step": 2320
+    },
+    {
+      "epoch": 3.1128924515698064,
+      "grad_norm": 0.5174121260643005,
+      "learning_rate": 0.0002,
+      "loss": 1.5092,
+      "step": 2330
+    },
+    {
+      "epoch": 3.12625250501002,
+      "grad_norm": 0.5697633028030396,
+      "learning_rate": 0.0002,
+      "loss": 1.5106,
+      "step": 2340
+    },
+    {
+      "epoch": 3.1396125584502337,
+      "grad_norm": 0.5969541072845459,
+      "learning_rate": 0.0002,
+      "loss": 1.5156,
+      "step": 2350
+    },
+    {
+      "epoch": 3.1529726118904478,
+      "grad_norm": 0.6244304180145264,
+      "learning_rate": 0.0002,
+      "loss": 1.52,
+      "step": 2360
+    },
+    {
+      "epoch": 3.1663326653306614,
+      "grad_norm": 0.5561705827713013,
+      "learning_rate": 0.0002,
+      "loss": 1.5244,
+      "step": 2370
+    },
+    {
+      "epoch": 3.179692718770875,
+      "grad_norm": 0.5401188135147095,
+      "learning_rate": 0.0002,
+      "loss": 1.6169,
+      "step": 2380
+    },
+    {
+      "epoch": 3.1930527722110886,
+      "grad_norm": 0.6450421810150146,
+      "learning_rate": 0.0002,
+      "loss": 1.5387,
+      "step": 2390
+    },
+    {
+      "epoch": 3.2064128256513027,
+      "grad_norm": 0.5741903185844421,
+      "learning_rate": 0.0002,
+      "loss": 1.4839,
+      "step": 2400
+    },
+    {
+      "epoch": 3.2197728790915163,
+      "grad_norm": 0.6337407231330872,
+      "learning_rate": 0.0002,
+      "loss": 1.5584,
+      "step": 2410
+    },
+    {
+      "epoch": 3.23313293253173,
+      "grad_norm": 0.6493517160415649,
+      "learning_rate": 0.0002,
+      "loss": 1.5025,
+      "step": 2420
+    },
+    {
+      "epoch": 3.246492985971944,
+      "grad_norm": 0.6230176091194153,
+      "learning_rate": 0.0002,
+      "loss": 1.5168,
+      "step": 2430
+    },
+    {
+      "epoch": 3.2598530394121576,
+      "grad_norm": 0.680704653263092,
+      "learning_rate": 0.0002,
+      "loss": 1.5408,
+      "step": 2440
+    },
+    {
+      "epoch": 3.2732130928523713,
+      "grad_norm": 0.5279417037963867,
+      "learning_rate": 0.0002,
+      "loss": 1.6005,
+      "step": 2450
+    },
+    {
+      "epoch": 3.2865731462925853,
+      "grad_norm": 0.5601515173912048,
+      "learning_rate": 0.0002,
+      "loss": 1.5231,
+      "step": 2460
+    },
+    {
+      "epoch": 3.299933199732799,
+      "grad_norm": 0.5591090321540833,
+      "learning_rate": 0.0002,
+      "loss": 1.4949,
+      "step": 2470
+    },
+    {
+      "epoch": 3.3132932531730126,
+      "grad_norm": 0.6596529483795166,
+      "learning_rate": 0.0002,
+      "loss": 1.5181,
+      "step": 2480
+    },
+    {
+      "epoch": 3.3266533066132267,
+      "grad_norm": 0.6115918755531311,
+      "learning_rate": 0.0002,
+      "loss": 1.5259,
+      "step": 2490
+    },
+    {
+      "epoch": 3.3400133600534403,
+      "grad_norm": 0.6443548202514648,
+      "learning_rate": 0.0002,
+      "loss": 1.5344,
+      "step": 2500
+    },
+    {
+      "epoch": 3.353373413493654,
+      "grad_norm": 0.5504242181777954,
+      "learning_rate": 0.0002,
+      "loss": 1.5037,
+      "step": 2510
+    },
+    {
+      "epoch": 3.3667334669338675,
+      "grad_norm": 0.6104483604431152,
+      "learning_rate": 0.0002,
+      "loss": 1.5049,
+      "step": 2520
+    },
+    {
+      "epoch": 3.3800935203740816,
+      "grad_norm": 0.8387531638145447,
+      "learning_rate": 0.0002,
+      "loss": 1.587,
+      "step": 2530
+    },
+    {
+      "epoch": 3.3934535738142952,
+      "grad_norm": 0.6346094012260437,
+      "learning_rate": 0.0002,
+      "loss": 1.5227,
+      "step": 2540
+    },
+    {
+      "epoch": 3.406813627254509,
+      "grad_norm": 0.6261265873908997,
+      "learning_rate": 0.0002,
+      "loss": 1.4855,
+      "step": 2550
+    },
+    {
+      "epoch": 3.420173680694723,
+      "grad_norm": 0.5960372090339661,
+      "learning_rate": 0.0002,
+      "loss": 1.5233,
+      "step": 2560
+    },
+    {
+      "epoch": 3.4335337341349366,
+      "grad_norm": 0.5291280746459961,
+      "learning_rate": 0.0002,
+      "loss": 1.5153,
+      "step": 2570
+    },
+    {
+      "epoch": 3.44689378757515,
+      "grad_norm": 0.6133161783218384,
+      "learning_rate": 0.0002,
+      "loss": 1.5152,
+      "step": 2580
+    },
+    {
+      "epoch": 3.460253841015364,
+      "grad_norm": 0.623573362827301,
+      "learning_rate": 0.0002,
+      "loss": 1.5533,
+      "step": 2590
+    },
+    {
+      "epoch": 3.473613894455578,
+      "grad_norm": 0.5959834456443787,
+      "learning_rate": 0.0002,
+      "loss": 1.4935,
+      "step": 2600
+    },
+    {
+      "epoch": 3.4869739478957915,
+      "grad_norm": 0.583332359790802,
+      "learning_rate": 0.0002,
+      "loss": 1.5792,
+      "step": 2610
+    },
+    {
+      "epoch": 3.5003340013360056,
+      "grad_norm": 0.6003559231758118,
+      "learning_rate": 0.0002,
+      "loss": 1.5229,
+      "step": 2620
+    },
+    {
+      "epoch": 3.513694054776219,
+      "grad_norm": 0.5832992196083069,
+      "learning_rate": 0.0002,
+      "loss": 1.4901,
+      "step": 2630
+    },
+    {
+      "epoch": 3.527054108216433,
+      "grad_norm": 0.5942609906196594,
+      "learning_rate": 0.0002,
+      "loss": 1.5005,
+      "step": 2640
+    },
+    {
+      "epoch": 3.5404141616566465,
+      "grad_norm": 0.6087163686752319,
+      "learning_rate": 0.0002,
+      "loss": 1.5213,
+      "step": 2650
+    },
+    {
+      "epoch": 3.5537742150968605,
+      "grad_norm": 0.631948709487915,
+      "learning_rate": 0.0002,
+      "loss": 1.5826,
+      "step": 2660
+    },
+    {
+      "epoch": 3.567134268537074,
+      "grad_norm": 0.6450803279876709,
+      "learning_rate": 0.0002,
+      "loss": 1.5844,
+      "step": 2670
+    },
+    {
+      "epoch": 3.580494321977288,
+      "grad_norm": 0.6507797837257385,
+      "learning_rate": 0.0002,
+      "loss": 1.4981,
+      "step": 2680
+    },
+    {
+      "epoch": 3.593854375417502,
+      "grad_norm": 0.5778017044067383,
+      "learning_rate": 0.0002,
+      "loss": 1.5826,
+      "step": 2690
+    },
+    {
+      "epoch": 3.6072144288577155,
+      "grad_norm": 0.6214032173156738,
+      "learning_rate": 0.0002,
+      "loss": 1.4688,
+      "step": 2700
+    },
+    {
+      "epoch": 3.620574482297929,
+      "grad_norm": 0.5681133270263672,
+      "learning_rate": 0.0002,
+      "loss": 1.5084,
+      "step": 2710
+    },
+    {
+      "epoch": 3.6339345357381427,
+      "grad_norm": 0.6074244976043701,
+      "learning_rate": 0.0002,
+      "loss": 1.471,
+      "step": 2720
+    },
+    {
+      "epoch": 3.647294589178357,
+      "grad_norm": 0.5900560617446899,
+      "learning_rate": 0.0002,
+      "loss": 1.5243,
+      "step": 2730
+    },
+    {
+      "epoch": 3.6606546426185704,
+      "grad_norm": 0.5817505717277527,
+      "learning_rate": 0.0002,
+      "loss": 1.5074,
+      "step": 2740
+    },
+    {
+      "epoch": 3.6740146960587845,
+      "grad_norm": 0.6095547676086426,
+      "learning_rate": 0.0002,
+      "loss": 1.5117,
+      "step": 2750
+    },
+    {
+      "epoch": 3.687374749498998,
+      "grad_norm": 0.612790584564209,
+      "learning_rate": 0.0002,
+      "loss": 1.5117,
+      "step": 2760
+    },
+    {
+      "epoch": 3.7007348029392118,
+      "grad_norm": 0.6574140787124634,
+      "learning_rate": 0.0002,
+      "loss": 1.4976,
+      "step": 2770
+    },
+    {
+      "epoch": 3.7140948563794254,
+      "grad_norm": 0.5643761157989502,
+      "learning_rate": 0.0002,
+      "loss": 1.5306,
+      "step": 2780
+    },
+    {
+      "epoch": 3.727454909819639,
+      "grad_norm": 0.5652621388435364,
+      "learning_rate": 0.0002,
+      "loss": 1.5751,
+      "step": 2790
+    },
+    {
+      "epoch": 3.740814963259853,
+      "grad_norm": 0.5604206323623657,
+      "learning_rate": 0.0002,
+      "loss": 1.5262,
+      "step": 2800
+    },
+    {
+      "epoch": 3.7541750167000667,
+      "grad_norm": 3.911022663116455,
+      "learning_rate": 0.0002,
+      "loss": 1.5013,
+      "step": 2810
+    },
+    {
+      "epoch": 3.7675350701402808,
+      "grad_norm": 0.6148333549499512,
+      "learning_rate": 0.0002,
+      "loss": 1.5793,
+      "step": 2820
+    },
+    {
+      "epoch": 3.7808951235804944,
+      "grad_norm": 0.5605677962303162,
+      "learning_rate": 0.0002,
+      "loss": 1.5122,
+      "step": 2830
+    },
+    {
+      "epoch": 3.794255177020708,
+      "grad_norm": 0.6101965308189392,
+      "learning_rate": 0.0002,
+      "loss": 1.5659,
+      "step": 2840
+    },
+    {
+      "epoch": 3.8076152304609217,
+      "grad_norm": 0.5387342572212219,
+      "learning_rate": 0.0002,
+      "loss": 1.5618,
+      "step": 2850
+    },
+    {
+      "epoch": 3.8209752839011357,
+      "grad_norm": 0.5733087062835693,
+      "learning_rate": 0.0002,
+      "loss": 1.5193,
+      "step": 2860
+    },
+    {
+      "epoch": 3.8343353373413493,
+      "grad_norm": 0.6538485884666443,
+      "learning_rate": 0.0002,
+      "loss": 1.5545,
+      "step": 2870
+    },
+    {
+      "epoch": 3.847695390781563,
+      "grad_norm": 0.6247632503509521,
+      "learning_rate": 0.0002,
+      "loss": 1.523,
+      "step": 2880
+    },
+    {
+      "epoch": 3.861055444221777,
+      "grad_norm": 0.5745735764503479,
+      "learning_rate": 0.0002,
+      "loss": 1.5591,
+      "step": 2890
+    },
+    {
+      "epoch": 3.8744154976619907,
+      "grad_norm": 0.5942763686180115,
+      "learning_rate": 0.0002,
+      "loss": 1.5706,
+      "step": 2900
+    },
+    {
+      "epoch": 3.8877755511022043,
+      "grad_norm": 0.7086281776428223,
+      "learning_rate": 0.0002,
+      "loss": 1.564,
+      "step": 2910
+    },
+    {
+      "epoch": 3.901135604542418,
+      "grad_norm": 0.8825129866600037,
+      "learning_rate": 0.0002,
+      "loss": 1.5526,
+      "step": 2920
+    },
+    {
+      "epoch": 3.914495657982632,
+      "grad_norm": 0.6260842680931091,
+      "learning_rate": 0.0002,
+      "loss": 1.4519,
+      "step": 2930
+    },
+    {
+      "epoch": 3.9278557114228456,
+      "grad_norm": 0.6015968322753906,
+      "learning_rate": 0.0002,
+      "loss": 1.5433,
+      "step": 2940
+    },
+    {
+      "epoch": 3.9412157648630597,
+      "grad_norm": 0.7042809128761292,
+      "learning_rate": 0.0002,
+      "loss": 1.4931,
+      "step": 2950
+    },
+    {
+      "epoch": 3.9545758183032733,
+      "grad_norm": 0.5860083699226379,
+      "learning_rate": 0.0002,
+      "loss": 1.5596,
+      "step": 2960
+    },
+    {
+      "epoch": 3.967935871743487,
+      "grad_norm": 0.5939757823944092,
+      "learning_rate": 0.0002,
+      "loss": 1.565,
+      "step": 2970
+    },
+    {
+      "epoch": 3.9812959251837006,
+      "grad_norm": 0.5523964166641235,
+      "learning_rate": 0.0002,
+      "loss": 1.408,
+      "step": 2980
+    },
+    {
+      "epoch": 3.9946559786239146,
+      "grad_norm": 0.6380264759063721,
+      "learning_rate": 0.0002,
+      "loss": 1.5629,
+      "step": 2990
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.8875294923782349,
+      "eval_runtime": 38.5837,
+      "eval_samples_per_second": 13.348,
+      "eval_steps_per_second": 1.685,
+      "step": 2994
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5984,
+  "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": 1.3855561616248013e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7025f98e983b93b4fec0d5370c1456c7adecaf8e
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-2994/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e92f0598f349930e52e126f358a3dca045c3c88312ec4b3f814f018a04982a9
+size 5560
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/README.md b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d63cb87eaccf2d81de3cdcfa11d2e99c440c0ea0
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..23c3d054d1bcb21dc734680243dd8e58f0349c53
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0234f046adbb732e82d46b9c17830ca358b6f13dd3813abc98021c87c81720a
+size 109069176
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..330afd31aeb9ffc16dad948e238b713a67db8121
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63365542cce7e88bcd49021c067c91257e90ae815e16060fa11bb928f9845cf2
+size 55532666
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..bb95309cd0eef0bb2b5b08b07f02149b35250e82
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c405372416e5b315715bd99e32cc1f94f9f3960af6a536965472b554f320c098
+size 14244
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3a7d93751d92907fd672b134139791f8f7198d2c
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:368c92ac0b2b6d0ba315c25de97abc6927c0b1af9ed72d1d47ac3cfdc9ec46be
+size 1064
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/tokenizer_config.json
@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..dac1384a5d0bc26351f3cefc189777b5b3b8c39e
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/trainer_state.json
@@ -0,0 +1,2691 @@
+{
+  "best_metric": 1.8132041692733765,
+  "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497",
+  "epoch": 4.999331997327989,
+  "eval_steps": 10,
+  "global_step": 3742,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013360053440213761,
+      "grad_norm": 0.5097216367721558,
+      "learning_rate": 0.0002,
+      "loss": 2.6569,
+      "step": 10
+    },
+    {
+      "epoch": 0.026720106880427523,
+      "grad_norm": 0.5924790501594543,
+      "learning_rate": 0.0002,
+      "loss": 2.2557,
+      "step": 20
+    },
+    {
+      "epoch": 0.04008016032064128,
+      "grad_norm": 0.5158102512359619,
+      "learning_rate": 0.0002,
+      "loss": 2.0626,
+      "step": 30
+    },
+    {
+      "epoch": 0.053440213760855046,
+      "grad_norm": 0.5033753514289856,
+      "learning_rate": 0.0002,
+      "loss": 1.9452,
+      "step": 40
+    },
+    {
+      "epoch": 0.06680026720106881,
+      "grad_norm": 0.5390949845314026,
+      "learning_rate": 0.0002,
+      "loss": 1.9128,
+      "step": 50
+    },
+    {
+      "epoch": 0.08016032064128256,
+      "grad_norm": 0.6376217007637024,
+      "learning_rate": 0.0002,
+      "loss": 1.937,
+      "step": 60
+    },
+    {
+      "epoch": 0.09352037408149633,
+      "grad_norm": 0.4202035069465637,
+      "learning_rate": 0.0002,
+      "loss": 1.929,
+      "step": 70
+    },
+    {
+      "epoch": 0.10688042752171009,
+      "grad_norm": 0.4269474744796753,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 80
+    },
+    {
+      "epoch": 0.12024048096192384,
+      "grad_norm": 0.4306574761867523,
+      "learning_rate": 0.0002,
+      "loss": 1.8303,
+      "step": 90
+    },
+    {
+      "epoch": 0.13360053440213762,
+      "grad_norm": 0.5297011137008667,
+      "learning_rate": 0.0002,
+      "loss": 1.8469,
+      "step": 100
+    },
+    {
+      "epoch": 0.14696058784235136,
+      "grad_norm": 1.2313778400421143,
+      "learning_rate": 0.0002,
+      "loss": 1.864,
+      "step": 110
+    },
+    {
+      "epoch": 0.16032064128256512,
+      "grad_norm": 0.5351294279098511,
+      "learning_rate": 0.0002,
+      "loss": 1.8531,
+      "step": 120
+    },
+    {
+      "epoch": 0.1736806947227789,
+      "grad_norm": 0.4848092496395111,
+      "learning_rate": 0.0002,
+      "loss": 1.9232,
+      "step": 130
+    },
+    {
+      "epoch": 0.18704074816299265,
+      "grad_norm": 0.4339500665664673,
+      "learning_rate": 0.0002,
+      "loss": 1.8633,
+      "step": 140
+    },
+    {
+      "epoch": 0.20040080160320642,
+      "grad_norm": 0.46877285838127136,
+      "learning_rate": 0.0002,
+      "loss": 1.816,
+      "step": 150
+    },
+    {
+      "epoch": 0.21376085504342018,
+      "grad_norm": 0.5600412487983704,
+      "learning_rate": 0.0002,
+      "loss": 1.8033,
+      "step": 160
+    },
+    {
+      "epoch": 0.22712090848363392,
+      "grad_norm": 0.3733620345592499,
+      "learning_rate": 0.0002,
+      "loss": 1.8162,
+      "step": 170
+    },
+    {
+      "epoch": 0.24048096192384769,
+      "grad_norm": 0.5116042494773865,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 180
+    },
+    {
+      "epoch": 0.25384101536406145,
+      "grad_norm": 0.4071602523326874,
+      "learning_rate": 0.0002,
+      "loss": 1.915,
+      "step": 190
+    },
+    {
+      "epoch": 0.26720106880427524,
+      "grad_norm": 0.44189608097076416,
+      "learning_rate": 0.0002,
+      "loss": 1.7984,
+      "step": 200
+    },
+    {
+      "epoch": 0.280561122244489,
+      "grad_norm": 0.398699015378952,
+      "learning_rate": 0.0002,
+      "loss": 1.8728,
+      "step": 210
+    },
+    {
+      "epoch": 0.2939211756847027,
+      "grad_norm": 0.3585626482963562,
+      "learning_rate": 0.0002,
+      "loss": 1.8205,
+      "step": 220
+    },
+    {
+      "epoch": 0.3072812291249165,
+      "grad_norm": 0.3811776041984558,
+      "learning_rate": 0.0002,
+      "loss": 1.8861,
+      "step": 230
+    },
+    {
+      "epoch": 0.32064128256513025,
+      "grad_norm": 0.37261509895324707,
+      "learning_rate": 0.0002,
+      "loss": 1.8365,
+      "step": 240
+    },
+    {
+      "epoch": 0.33400133600534404,
+      "grad_norm": 0.39762404561042786,
+      "learning_rate": 0.0002,
+      "loss": 1.9186,
+      "step": 250
+    },
+    {
+      "epoch": 0.3473613894455578,
+      "grad_norm": 0.3509528934955597,
+      "learning_rate": 0.0002,
+      "loss": 1.7965,
+      "step": 260
+    },
+    {
+      "epoch": 0.36072144288577157,
+      "grad_norm": 0.3169104754924774,
+      "learning_rate": 0.0002,
+      "loss": 1.7802,
+      "step": 270
+    },
+    {
+      "epoch": 0.3740814963259853,
+      "grad_norm": 0.33714795112609863,
+      "learning_rate": 0.0002,
+      "loss": 1.8038,
+      "step": 280
+    },
+    {
+      "epoch": 0.38744154976619904,
+      "grad_norm": 1.2936875820159912,
+      "learning_rate": 0.0002,
+      "loss": 1.787,
+      "step": 290
+    },
+    {
+      "epoch": 0.40080160320641284,
+      "grad_norm": 0.3459427058696747,
+      "learning_rate": 0.0002,
+      "loss": 1.7974,
+      "step": 300
+    },
+    {
+      "epoch": 0.4141616566466266,
+      "grad_norm": 0.3380655348300934,
+      "learning_rate": 0.0002,
+      "loss": 1.8879,
+      "step": 310
+    },
+    {
+      "epoch": 0.42752171008684037,
+      "grad_norm": 0.3890381455421448,
+      "learning_rate": 0.0002,
+      "loss": 1.9196,
+      "step": 320
+    },
+    {
+      "epoch": 0.4408817635270541,
+      "grad_norm": 0.432327002286911,
+      "learning_rate": 0.0002,
+      "loss": 1.8034,
+      "step": 330
+    },
+    {
+      "epoch": 0.45424181696726784,
+      "grad_norm": 0.3736560046672821,
+      "learning_rate": 0.0002,
+      "loss": 1.8443,
+      "step": 340
+    },
+    {
+      "epoch": 0.46760187040748163,
+      "grad_norm": 0.3700982630252838,
+      "learning_rate": 0.0002,
+      "loss": 1.8506,
+      "step": 350
+    },
+    {
+      "epoch": 0.48096192384769537,
+      "grad_norm": 0.4533902406692505,
+      "learning_rate": 0.0002,
+      "loss": 1.7978,
+      "step": 360
+    },
+    {
+      "epoch": 0.49432197728790916,
+      "grad_norm": 0.35999053716659546,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 370
+    },
+    {
+      "epoch": 0.5076820307281229,
+      "grad_norm": 0.3490903675556183,
+      "learning_rate": 0.0002,
+      "loss": 1.7995,
+      "step": 380
+    },
+    {
+      "epoch": 0.5210420841683366,
+      "grad_norm": 0.34704291820526123,
+      "learning_rate": 0.0002,
+      "loss": 1.8709,
+      "step": 390
+    },
+    {
+      "epoch": 0.5344021376085505,
+      "grad_norm": 0.343565434217453,
+      "learning_rate": 0.0002,
+      "loss": 1.7948,
+      "step": 400
+    },
+    {
+      "epoch": 0.5477621910487642,
+      "grad_norm": 0.3573552966117859,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 410
+    },
+    {
+      "epoch": 0.561122244488978,
+      "grad_norm": 0.32980719208717346,
+      "learning_rate": 0.0002,
+      "loss": 1.8477,
+      "step": 420
+    },
+    {
+      "epoch": 0.5744822979291917,
+      "grad_norm": 0.356952428817749,
+      "learning_rate": 0.0002,
+      "loss": 1.9233,
+      "step": 430
+    },
+    {
+      "epoch": 0.5878423513694054,
+      "grad_norm": 0.3170869052410126,
+      "learning_rate": 0.0002,
+      "loss": 1.7433,
+      "step": 440
+    },
+    {
+      "epoch": 0.6012024048096193,
+      "grad_norm": 0.35233718156814575,
+      "learning_rate": 0.0002,
+      "loss": 1.7607,
+      "step": 450
+    },
+    {
+      "epoch": 0.614562458249833,
+      "grad_norm": 0.3480125367641449,
+      "learning_rate": 0.0002,
+      "loss": 1.8111,
+      "step": 460
+    },
+    {
+      "epoch": 0.6279225116900468,
+      "grad_norm": 0.4762810468673706,
+      "learning_rate": 0.0002,
+      "loss": 1.8386,
+      "step": 470
+    },
+    {
+      "epoch": 0.6412825651302605,
+      "grad_norm": 0.3907663822174072,
+      "learning_rate": 0.0002,
+      "loss": 1.805,
+      "step": 480
+    },
+    {
+      "epoch": 0.6546426185704742,
+      "grad_norm": 0.36315613985061646,
+      "learning_rate": 0.0002,
+      "loss": 1.8113,
+      "step": 490
+    },
+    {
+      "epoch": 0.6680026720106881,
+      "grad_norm": 0.377796471118927,
+      "learning_rate": 0.0002,
+      "loss": 1.7805,
+      "step": 500
+    },
+    {
+      "epoch": 0.6813627254509018,
+      "grad_norm": 0.34284207224845886,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 510
+    },
+    {
+      "epoch": 0.6947227788911156,
+      "grad_norm": 0.35563018918037415,
+      "learning_rate": 0.0002,
+      "loss": 1.8013,
+      "step": 520
+    },
+    {
+      "epoch": 0.7080828323313293,
+      "grad_norm": 0.37575867772102356,
+      "learning_rate": 0.0002,
+      "loss": 1.8414,
+      "step": 530
+    },
+    {
+      "epoch": 0.7214428857715431,
+      "grad_norm": 0.35719701647758484,
+      "learning_rate": 0.0002,
+      "loss": 1.7993,
+      "step": 540
+    },
+    {
+      "epoch": 0.7348029392117569,
+      "grad_norm": 0.385813444852829,
+      "learning_rate": 0.0002,
+      "loss": 1.7574,
+      "step": 550
+    },
+    {
+      "epoch": 0.7481629926519706,
+      "grad_norm": 0.44509607553482056,
+      "learning_rate": 0.0002,
+      "loss": 1.7985,
+      "step": 560
+    },
+    {
+      "epoch": 0.7615230460921844,
+      "grad_norm": 0.36108464002609253,
+      "learning_rate": 0.0002,
+      "loss": 1.7459,
+      "step": 570
+    },
+    {
+      "epoch": 0.7748830995323981,
+      "grad_norm": 0.3530745804309845,
+      "learning_rate": 0.0002,
+      "loss": 1.8207,
+      "step": 580
+    },
+    {
+      "epoch": 0.7882431529726119,
+      "grad_norm": 0.34888574481010437,
+      "learning_rate": 0.0002,
+      "loss": 1.7479,
+      "step": 590
+    },
+    {
+      "epoch": 0.8016032064128257,
+      "grad_norm": 0.387346476316452,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 600
+    },
+    {
+      "epoch": 0.8149632598530394,
+      "grad_norm": 0.3641138970851898,
+      "learning_rate": 0.0002,
+      "loss": 1.8071,
+      "step": 610
+    },
+    {
+      "epoch": 0.8283233132932531,
+      "grad_norm": 0.33729103207588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7531,
+      "step": 620
+    },
+    {
+      "epoch": 0.8416833667334669,
+      "grad_norm": 0.3652004599571228,
+      "learning_rate": 0.0002,
+      "loss": 1.8613,
+      "step": 630
+    },
+    {
+      "epoch": 0.8550434201736807,
+      "grad_norm": 0.3986643850803375,
+      "learning_rate": 0.0002,
+      "loss": 1.9184,
+      "step": 640
+    },
+    {
+      "epoch": 0.8684034736138945,
+      "grad_norm": 0.3458964228630066,
+      "learning_rate": 0.0002,
+      "loss": 1.8198,
+      "step": 650
+    },
+    {
+      "epoch": 0.8817635270541082,
+      "grad_norm": 0.3559381365776062,
+      "learning_rate": 0.0002,
+      "loss": 1.803,
+      "step": 660
+    },
+    {
+      "epoch": 0.895123580494322,
+      "grad_norm": 0.3612841069698334,
+      "learning_rate": 0.0002,
+      "loss": 1.7641,
+      "step": 670
+    },
+    {
+      "epoch": 0.9084836339345357,
+      "grad_norm": 0.34771719574928284,
+      "learning_rate": 0.0002,
+      "loss": 1.7888,
+      "step": 680
+    },
+    {
+      "epoch": 0.9218436873747495,
+      "grad_norm": 0.3371497094631195,
+      "learning_rate": 0.0002,
+      "loss": 1.8204,
+      "step": 690
+    },
+    {
+      "epoch": 0.9352037408149633,
+      "grad_norm": 0.5596055388450623,
+      "learning_rate": 0.0002,
+      "loss": 1.7848,
+      "step": 700
+    },
+    {
+      "epoch": 0.948563794255177,
+      "grad_norm": 0.311880499124527,
+      "learning_rate": 0.0002,
+      "loss": 1.7794,
+      "step": 710
+    },
+    {
+      "epoch": 0.9619238476953907,
+      "grad_norm": 0.3462068736553192,
+      "learning_rate": 0.0002,
+      "loss": 1.8464,
+      "step": 720
+    },
+    {
+      "epoch": 0.9752839011356046,
+      "grad_norm": 0.29982393980026245,
+      "learning_rate": 0.0002,
+      "loss": 1.8197,
+      "step": 730
+    },
+    {
+      "epoch": 0.9886439545758183,
+      "grad_norm": 0.34606459736824036,
+      "learning_rate": 0.0002,
+      "loss": 1.8503,
+      "step": 740
+    },
+    {
+      "epoch": 0.9993319973279893,
+      "eval_loss": 1.8201380968093872,
+      "eval_runtime": 38.6124,
+      "eval_samples_per_second": 13.338,
+      "eval_steps_per_second": 1.683,
+      "step": 748
+    },
+    {
+      "epoch": 1.002004008016032,
+      "grad_norm": 0.32302048802375793,
+      "learning_rate": 0.0002,
+      "loss": 1.7786,
+      "step": 750
+    },
+    {
+      "epoch": 1.0153640614562458,
+      "grad_norm": 0.37585633993148804,
+      "learning_rate": 0.0002,
+      "loss": 1.7297,
+      "step": 760
+    },
+    {
+      "epoch": 1.0287241148964597,
+      "grad_norm": 0.33826273679733276,
+      "learning_rate": 0.0002,
+      "loss": 1.7008,
+      "step": 770
+    },
+    {
+      "epoch": 1.0420841683366733,
+      "grad_norm": 0.44682955741882324,
+      "learning_rate": 0.0002,
+      "loss": 1.809,
+      "step": 780
+    },
+    {
+      "epoch": 1.0554442217768871,
+      "grad_norm": 0.422188401222229,
+      "learning_rate": 0.0002,
+      "loss": 1.7092,
+      "step": 790
+    },
+    {
+      "epoch": 1.0688042752171008,
+      "grad_norm": 0.3809906244277954,
+      "learning_rate": 0.0002,
+      "loss": 1.7765,
+      "step": 800
+    },
+    {
+      "epoch": 1.0821643286573146,
+      "grad_norm": 0.3454349637031555,
+      "learning_rate": 0.0002,
+      "loss": 1.7431,
+      "step": 810
+    },
+    {
+      "epoch": 1.0955243820975284,
+      "grad_norm": 0.3767355978488922,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 820
+    },
+    {
+      "epoch": 1.108884435537742,
+      "grad_norm": 0.3361407518386841,
+      "learning_rate": 0.0002,
+      "loss": 1.7224,
+      "step": 830
+    },
+    {
+      "epoch": 1.122244488977956,
+      "grad_norm": 0.3654632568359375,
+      "learning_rate": 0.0002,
+      "loss": 1.7509,
+      "step": 840
+    },
+    {
+      "epoch": 1.1356045424181698,
+      "grad_norm": 0.3822861313819885,
+      "learning_rate": 0.0002,
+      "loss": 1.7151,
+      "step": 850
+    },
+    {
+      "epoch": 1.1489645958583834,
+      "grad_norm": 0.3853831887245178,
+      "learning_rate": 0.0002,
+      "loss": 1.7121,
+      "step": 860
+    },
+    {
+      "epoch": 1.1623246492985972,
+      "grad_norm": 0.35521796345710754,
+      "learning_rate": 0.0002,
+      "loss": 1.7685,
+      "step": 870
+    },
+    {
+      "epoch": 1.1756847027388109,
+      "grad_norm": 0.4107200503349304,
+      "learning_rate": 0.0002,
+      "loss": 1.7735,
+      "step": 880
+    },
+    {
+      "epoch": 1.1890447561790247,
+      "grad_norm": 0.33219534158706665,
+      "learning_rate": 0.0002,
+      "loss": 1.7484,
+      "step": 890
+    },
+    {
+      "epoch": 1.2024048096192386,
+      "grad_norm": 0.3559704124927521,
+      "learning_rate": 0.0002,
+      "loss": 1.7071,
+      "step": 900
+    },
+    {
+      "epoch": 1.2157648630594522,
+      "grad_norm": 0.3700537383556366,
+      "learning_rate": 0.0002,
+      "loss": 1.7535,
+      "step": 910
+    },
+    {
+      "epoch": 1.229124916499666,
+      "grad_norm": 0.3771909475326538,
+      "learning_rate": 0.0002,
+      "loss": 1.7513,
+      "step": 920
+    },
+    {
+      "epoch": 1.2424849699398797,
+      "grad_norm": 0.3136613965034485,
+      "learning_rate": 0.0002,
+      "loss": 1.7566,
+      "step": 930
+    },
+    {
+      "epoch": 1.2558450233800935,
+      "grad_norm": 0.3952099084854126,
+      "learning_rate": 0.0002,
+      "loss": 1.6783,
+      "step": 940
+    },
+    {
+      "epoch": 1.2692050768203074,
+      "grad_norm": 0.36534377932548523,
+      "learning_rate": 0.0002,
+      "loss": 1.7691,
+      "step": 950
+    },
+    {
+      "epoch": 1.282565130260521,
+      "grad_norm": 0.3803492486476898,
+      "learning_rate": 0.0002,
+      "loss": 1.7127,
+      "step": 960
+    },
+    {
+      "epoch": 1.2959251837007348,
+      "grad_norm": 0.3992428183555603,
+      "learning_rate": 0.0002,
+      "loss": 1.7896,
+      "step": 970
+    },
+    {
+      "epoch": 1.3092852371409487,
+      "grad_norm": 0.3627142906188965,
+      "learning_rate": 0.0002,
+      "loss": 1.7343,
+      "step": 980
+    },
+    {
+      "epoch": 1.3226452905811623,
+      "grad_norm": 0.4248180091381073,
+      "learning_rate": 0.0002,
+      "loss": 1.7598,
+      "step": 990
+    },
+    {
+      "epoch": 1.3360053440213762,
+      "grad_norm": 0.4060308039188385,
+      "learning_rate": 0.0002,
+      "loss": 1.6896,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3493653974615898,
+      "grad_norm": 0.3788969814777374,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 1010
+    },
+    {
+      "epoch": 1.3627254509018036,
+      "grad_norm": 0.4174270033836365,
+      "learning_rate": 0.0002,
+      "loss": 1.7111,
+      "step": 1020
+    },
+    {
+      "epoch": 1.3760855043420173,
+      "grad_norm": 0.35500675439834595,
+      "learning_rate": 0.0002,
+      "loss": 1.7975,
+      "step": 1030
+    },
+    {
+      "epoch": 1.389445557782231,
+      "grad_norm": 0.3454059362411499,
+      "learning_rate": 0.0002,
+      "loss": 1.724,
+      "step": 1040
+    },
+    {
+      "epoch": 1.402805611222445,
+      "grad_norm": 0.45807570219039917,
+      "learning_rate": 0.0002,
+      "loss": 1.8299,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4161656646626586,
+      "grad_norm": 0.39338022470474243,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4295257181028724,
+      "grad_norm": 0.3870709240436554,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4428857715430863,
+      "grad_norm": 0.40996190905570984,
+      "learning_rate": 0.0002,
+      "loss": 1.6565,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4562458249833,
+      "grad_norm": 0.38762837648391724,
+      "learning_rate": 0.0002,
+      "loss": 1.7324,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4696058784235138,
+      "grad_norm": 0.36756977438926697,
+      "learning_rate": 0.0002,
+      "loss": 1.7362,
+      "step": 1100
+    },
+    {
+      "epoch": 1.4829659318637274,
+      "grad_norm": 0.4087235927581787,
+      "learning_rate": 0.0002,
+      "loss": 1.7451,
+      "step": 1110
+    },
+    {
+      "epoch": 1.4963259853039412,
+      "grad_norm": 0.3357745110988617,
+      "learning_rate": 0.0002,
+      "loss": 1.7114,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5096860387441549,
+      "grad_norm": 0.37486532330513,
+      "learning_rate": 0.0002,
+      "loss": 1.6877,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5230460921843687,
+      "grad_norm": 0.3387809991836548,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5364061456245826,
+      "grad_norm": 0.37462118268013,
+      "learning_rate": 0.0002,
+      "loss": 1.7169,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5497661990647962,
+      "grad_norm": 0.38575324416160583,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 1160
+    },
+    {
+      "epoch": 1.56312625250501,
+      "grad_norm": 0.3515765964984894,
+      "learning_rate": 0.0002,
+      "loss": 1.7438,
+      "step": 1170
+    },
+    {
+      "epoch": 1.5764863059452239,
+      "grad_norm": 0.39308643341064453,
+      "learning_rate": 0.0002,
+      "loss": 1.7524,
+      "step": 1180
+    },
+    {
+      "epoch": 1.5898463593854375,
+      "grad_norm": 0.3308864235877991,
+      "learning_rate": 0.0002,
+      "loss": 1.6422,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6032064128256514,
+      "grad_norm": 0.3397478461265564,
+      "learning_rate": 0.0002,
+      "loss": 1.7566,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6165664662658652,
+      "grad_norm": 0.3911525309085846,
+      "learning_rate": 0.0002,
+      "loss": 1.7871,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6299265197060788,
+      "grad_norm": 0.3771969974040985,
+      "learning_rate": 0.0002,
+      "loss": 1.7443,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6432865731462925,
+      "grad_norm": 0.35346856713294983,
+      "learning_rate": 0.0002,
+      "loss": 1.7631,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6566466265865063,
+      "grad_norm": 0.41736963391304016,
+      "learning_rate": 0.0002,
+      "loss": 1.7225,
+      "step": 1240
+    },
+    {
+      "epoch": 1.6700066800267201,
+      "grad_norm": 0.3375225067138672,
+      "learning_rate": 0.0002,
+      "loss": 1.7582,
+      "step": 1250
+    },
+    {
+      "epoch": 1.6833667334669338,
+      "grad_norm": 0.3779928982257843,
+      "learning_rate": 0.0002,
+      "loss": 1.6916,
+      "step": 1260
+    },
+    {
+      "epoch": 1.6967267869071476,
+      "grad_norm": 0.35388994216918945,
+      "learning_rate": 0.0002,
+      "loss": 1.728,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7100868403473615,
+      "grad_norm": 0.33884134888648987,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 1280
+    },
+    {
+      "epoch": 1.723446893787575,
+      "grad_norm": 0.35439756512641907,
+      "learning_rate": 0.0002,
+      "loss": 1.7083,
+      "step": 1290
+    },
+    {
+      "epoch": 1.736806947227789,
+      "grad_norm": 0.3766156733036041,
+      "learning_rate": 0.0002,
+      "loss": 1.7389,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7501670006680028,
+      "grad_norm": 0.36148911714553833,
+      "learning_rate": 0.0002,
+      "loss": 1.7847,
+      "step": 1310
+    },
+    {
+      "epoch": 1.7635270541082164,
+      "grad_norm": 0.39687496423721313,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 1320
+    },
+    {
+      "epoch": 1.77688710754843,
+      "grad_norm": 0.35639452934265137,
+      "learning_rate": 0.0002,
+      "loss": 1.7541,
+      "step": 1330
+    },
+    {
+      "epoch": 1.7902471609886441,
+      "grad_norm": 0.38781628012657166,
+      "learning_rate": 0.0002,
+      "loss": 1.7254,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8036072144288577,
+      "grad_norm": 0.42784637212753296,
+      "learning_rate": 0.0002,
+      "loss": 1.7867,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8169672678690714,
+      "grad_norm": 0.40258511900901794,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8303273213092852,
+      "grad_norm": 0.36674195528030396,
+      "learning_rate": 0.0002,
+      "loss": 1.7771,
+      "step": 1370
+    },
+    {
+      "epoch": 1.843687374749499,
+      "grad_norm": 0.4064558446407318,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8570474281897127,
+      "grad_norm": 0.3669849932193756,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1390
+    },
+    {
+      "epoch": 1.8704074816299265,
+      "grad_norm": 0.37569567561149597,
+      "learning_rate": 0.0002,
+      "loss": 1.7924,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8837675350701404,
+      "grad_norm": 0.37307995557785034,
+      "learning_rate": 0.0002,
+      "loss": 1.7885,
+      "step": 1410
+    },
+    {
+      "epoch": 1.897127588510354,
+      "grad_norm": 0.3772695064544678,
+      "learning_rate": 0.0002,
+      "loss": 1.7548,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9104876419505676,
+      "grad_norm": 0.36993589997291565,
+      "learning_rate": 0.0002,
+      "loss": 1.7682,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9238476953907817,
+      "grad_norm": 0.3490557372570038,
+      "learning_rate": 0.0002,
+      "loss": 1.7249,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9372077488309953,
+      "grad_norm": 0.3716149628162384,
+      "learning_rate": 0.0002,
+      "loss": 1.7979,
+      "step": 1450
+    },
+    {
+      "epoch": 1.950567802271209,
+      "grad_norm": 0.39236098527908325,
+      "learning_rate": 0.0002,
+      "loss": 1.6664,
+      "step": 1460
+    },
+    {
+      "epoch": 1.9639278557114228,
+      "grad_norm": 0.37258651852607727,
+      "learning_rate": 0.0002,
+      "loss": 1.6852,
+      "step": 1470
+    },
+    {
+      "epoch": 1.9772879091516367,
+      "grad_norm": 0.36183077096939087,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 1480
+    },
+    {
+      "epoch": 1.9906479625918503,
+      "grad_norm": 0.3956947326660156,
+      "learning_rate": 0.0002,
+      "loss": 1.7055,
+      "step": 1490
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8132041692733765,
+      "eval_runtime": 38.6287,
+      "eval_samples_per_second": 13.332,
+      "eval_steps_per_second": 1.683,
+      "step": 1497
+    },
+    {
+      "epoch": 2.004008016032064,
+      "grad_norm": 0.34480565786361694,
+      "learning_rate": 0.0002,
+      "loss": 1.6791,
+      "step": 1500
+    },
+    {
+      "epoch": 2.017368069472278,
+      "grad_norm": 0.3418028652667999,
+      "learning_rate": 0.0002,
+      "loss": 1.6367,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0307281229124916,
+      "grad_norm": 0.4514467716217041,
+      "learning_rate": 0.0002,
+      "loss": 1.5827,
+      "step": 1520
+    },
+    {
+      "epoch": 2.0440881763527052,
+      "grad_norm": 0.4197506606578827,
+      "learning_rate": 0.0002,
+      "loss": 1.6365,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0574482297929193,
+      "grad_norm": 0.4134170711040497,
+      "learning_rate": 0.0002,
+      "loss": 1.6221,
+      "step": 1540
+    },
+    {
+      "epoch": 2.070808283233133,
+      "grad_norm": 0.43709826469421387,
+      "learning_rate": 0.0002,
+      "loss": 1.6876,
+      "step": 1550
+    },
+    {
+      "epoch": 2.0841683366733466,
+      "grad_norm": 0.4703378677368164,
+      "learning_rate": 0.0002,
+      "loss": 1.5779,
+      "step": 1560
+    },
+    {
+      "epoch": 2.0975283901135606,
+      "grad_norm": 0.4538188576698303,
+      "learning_rate": 0.0002,
+      "loss": 1.599,
+      "step": 1570
+    },
+    {
+      "epoch": 2.1108884435537743,
+      "grad_norm": 0.4649668037891388,
+      "learning_rate": 0.0002,
+      "loss": 1.6464,
+      "step": 1580
+    },
+    {
+      "epoch": 2.124248496993988,
+      "grad_norm": 0.42669883370399475,
+      "learning_rate": 0.0002,
+      "loss": 1.6348,
+      "step": 1590
+    },
+    {
+      "epoch": 2.1376085504342015,
+      "grad_norm": 0.43162038922309875,
+      "learning_rate": 0.0002,
+      "loss": 1.5838,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1509686038744156,
+      "grad_norm": 0.4294586479663849,
+      "learning_rate": 0.0002,
+      "loss": 1.6673,
+      "step": 1610
+    },
+    {
+      "epoch": 2.164328657314629,
+      "grad_norm": 0.4669102132320404,
+      "learning_rate": 0.0002,
+      "loss": 1.6024,
+      "step": 1620
+    },
+    {
+      "epoch": 2.177688710754843,
+      "grad_norm": 0.4188412129878998,
+      "learning_rate": 0.0002,
+      "loss": 1.659,
+      "step": 1630
+    },
+    {
+      "epoch": 2.191048764195057,
+      "grad_norm": 0.4662680923938751,
+      "learning_rate": 0.0002,
+      "loss": 1.625,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2044088176352705,
+      "grad_norm": 0.4020286500453949,
+      "learning_rate": 0.0002,
+      "loss": 1.6699,
+      "step": 1650
+    },
+    {
+      "epoch": 2.217768871075484,
+      "grad_norm": 0.41919606924057007,
+      "learning_rate": 0.0002,
+      "loss": 1.6284,
+      "step": 1660
+    },
+    {
+      "epoch": 2.231128924515698,
+      "grad_norm": 0.4644531309604645,
+      "learning_rate": 0.0002,
+      "loss": 1.6776,
+      "step": 1670
+    },
+    {
+      "epoch": 2.244488977955912,
+      "grad_norm": 0.4526427984237671,
+      "learning_rate": 0.0002,
+      "loss": 1.6711,
+      "step": 1680
+    },
+    {
+      "epoch": 2.2578490313961255,
+      "grad_norm": 0.45953166484832764,
+      "learning_rate": 0.0002,
+      "loss": 1.6058,
+      "step": 1690
+    },
+    {
+      "epoch": 2.2712090848363395,
+      "grad_norm": 0.4701860249042511,
+      "learning_rate": 0.0002,
+      "loss": 1.5979,
+      "step": 1700
+    },
+    {
+      "epoch": 2.284569138276553,
+      "grad_norm": 0.4749310612678528,
+      "learning_rate": 0.0002,
+      "loss": 1.6183,
+      "step": 1710
+    },
+    {
+      "epoch": 2.297929191716767,
+      "grad_norm": 0.45026102662086487,
+      "learning_rate": 0.0002,
+      "loss": 1.6703,
+      "step": 1720
+    },
+    {
+      "epoch": 2.3112892451569804,
+      "grad_norm": 0.4755004048347473,
+      "learning_rate": 0.0002,
+      "loss": 1.6386,
+      "step": 1730
+    },
+    {
+      "epoch": 2.3246492985971945,
+      "grad_norm": 0.4505726993083954,
+      "learning_rate": 0.0002,
+      "loss": 1.6365,
+      "step": 1740
+    },
+    {
+      "epoch": 2.338009352037408,
+      "grad_norm": 0.44464054703712463,
+      "learning_rate": 0.0002,
+      "loss": 1.589,
+      "step": 1750
+    },
+    {
+      "epoch": 2.3513694054776217,
+      "grad_norm": 0.4449476897716522,
+      "learning_rate": 0.0002,
+      "loss": 1.6139,
+      "step": 1760
+    },
+    {
+      "epoch": 2.364729458917836,
+      "grad_norm": 0.4216482937335968,
+      "learning_rate": 0.0002,
+      "loss": 1.7195,
+      "step": 1770
+    },
+    {
+      "epoch": 2.3780895123580494,
+      "grad_norm": 0.4379308521747589,
+      "learning_rate": 0.0002,
+      "loss": 1.7075,
+      "step": 1780
+    },
+    {
+      "epoch": 2.391449565798263,
+      "grad_norm": 0.41670042276382446,
+      "learning_rate": 0.0002,
+      "loss": 1.7024,
+      "step": 1790
+    },
+    {
+      "epoch": 2.404809619238477,
+      "grad_norm": 0.48089510202407837,
+      "learning_rate": 0.0002,
+      "loss": 1.5989,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4181696726786908,
+      "grad_norm": 0.4389738142490387,
+      "learning_rate": 0.0002,
+      "loss": 1.6313,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4315297261189044,
+      "grad_norm": 0.45293036103248596,
+      "learning_rate": 0.0002,
+      "loss": 1.5841,
+      "step": 1820
+    },
+    {
+      "epoch": 2.4448897795591185,
+      "grad_norm": 0.5211683511734009,
+      "learning_rate": 0.0002,
+      "loss": 1.6887,
+      "step": 1830
+    },
+    {
+      "epoch": 2.458249832999332,
+      "grad_norm": 0.4631884694099426,
+      "learning_rate": 0.0002,
+      "loss": 1.6599,
+      "step": 1840
+    },
+    {
+      "epoch": 2.4716098864395457,
+      "grad_norm": 0.4276818335056305,
+      "learning_rate": 0.0002,
+      "loss": 1.6537,
+      "step": 1850
+    },
+    {
+      "epoch": 2.4849699398797593,
+      "grad_norm": 0.477524071931839,
+      "learning_rate": 0.0002,
+      "loss": 1.6836,
+      "step": 1860
+    },
+    {
+      "epoch": 2.4983299933199734,
+      "grad_norm": 0.44860973954200745,
+      "learning_rate": 0.0002,
+      "loss": 1.66,
+      "step": 1870
+    },
+    {
+      "epoch": 2.511690046760187,
+      "grad_norm": 0.46413546800613403,
+      "learning_rate": 0.0002,
+      "loss": 1.6308,
+      "step": 1880
+    },
+    {
+      "epoch": 2.5250501002004007,
+      "grad_norm": 0.42487645149230957,
+      "learning_rate": 0.0002,
+      "loss": 1.6225,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5384101536406147,
+      "grad_norm": 0.4778307378292084,
+      "learning_rate": 0.0002,
+      "loss": 1.6268,
+      "step": 1900
+    },
+    {
+      "epoch": 2.5517702070808284,
+      "grad_norm": 0.45307061076164246,
+      "learning_rate": 0.0002,
+      "loss": 1.6143,
+      "step": 1910
+    },
+    {
+      "epoch": 2.565130260521042,
+      "grad_norm": 0.47886642813682556,
+      "learning_rate": 0.0002,
+      "loss": 1.7279,
+      "step": 1920
+    },
+    {
+      "epoch": 2.5784903139612556,
+      "grad_norm": 0.4839435815811157,
+      "learning_rate": 0.0002,
+      "loss": 1.5931,
+      "step": 1930
+    },
+    {
+      "epoch": 2.5918503674014697,
+      "grad_norm": 0.4388359785079956,
+      "learning_rate": 0.0002,
+      "loss": 1.6089,
+      "step": 1940
+    },
+    {
+      "epoch": 2.6052104208416833,
+      "grad_norm": 0.47859734296798706,
+      "learning_rate": 0.0002,
+      "loss": 1.6828,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6185704742818974,
+      "grad_norm": 0.5526517033576965,
+      "learning_rate": 0.0002,
+      "loss": 1.6014,
+      "step": 1960
+    },
+    {
+      "epoch": 2.631930527722111,
+      "grad_norm": 0.5449170470237732,
+      "learning_rate": 0.0002,
+      "loss": 1.6889,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6452905811623246,
+      "grad_norm": 0.48521968722343445,
+      "learning_rate": 0.0002,
+      "loss": 1.6481,
+      "step": 1980
+    },
+    {
+      "epoch": 2.6586506346025383,
+      "grad_norm": 0.4733737111091614,
+      "learning_rate": 0.0002,
+      "loss": 1.6741,
+      "step": 1990
+    },
+    {
+      "epoch": 2.6720106880427523,
+      "grad_norm": 0.507118284702301,
+      "learning_rate": 0.0002,
+      "loss": 1.662,
+      "step": 2000
+    },
+    {
+      "epoch": 2.685370741482966,
+      "grad_norm": 0.4508971571922302,
+      "learning_rate": 0.0002,
+      "loss": 1.6419,
+      "step": 2010
+    },
+    {
+      "epoch": 2.6987307949231796,
+      "grad_norm": 0.4657728672027588,
+      "learning_rate": 0.0002,
+      "loss": 1.7052,
+      "step": 2020
+    },
+    {
+      "epoch": 2.7120908483633936,
+      "grad_norm": 0.48647549748420715,
+      "learning_rate": 0.0002,
+      "loss": 1.6261,
+      "step": 2030
+    },
+    {
+      "epoch": 2.7254509018036073,
+      "grad_norm": 0.49525555968284607,
+      "learning_rate": 0.0002,
+      "loss": 1.5638,
+      "step": 2040
+    },
+    {
+      "epoch": 2.738810955243821,
+      "grad_norm": 0.4712379276752472,
+      "learning_rate": 0.0002,
+      "loss": 1.658,
+      "step": 2050
+    },
+    {
+      "epoch": 2.7521710086840345,
+      "grad_norm": 0.4846591055393219,
+      "learning_rate": 0.0002,
+      "loss": 1.6464,
+      "step": 2060
+    },
+    {
+      "epoch": 2.7655310621242486,
+      "grad_norm": 0.4823240041732788,
+      "learning_rate": 0.0002,
+      "loss": 1.5641,
+      "step": 2070
+    },
+    {
+      "epoch": 2.778891115564462,
+      "grad_norm": 0.4546685516834259,
+      "learning_rate": 0.0002,
+      "loss": 1.6701,
+      "step": 2080
+    },
+    {
+      "epoch": 2.7922511690046763,
+      "grad_norm": 0.45542681217193604,
+      "learning_rate": 0.0002,
+      "loss": 1.7015,
+      "step": 2090
+    },
+    {
+      "epoch": 2.80561122244489,
+      "grad_norm": 0.42137566208839417,
+      "learning_rate": 0.0002,
+      "loss": 1.6398,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8189712758851035,
+      "grad_norm": 0.6143282055854797,
+      "learning_rate": 0.0002,
+      "loss": 1.6526,
+      "step": 2110
+    },
+    {
+      "epoch": 2.832331329325317,
+      "grad_norm": 0.4828081727027893,
+      "learning_rate": 0.0002,
+      "loss": 1.6955,
+      "step": 2120
+    },
+    {
+      "epoch": 2.845691382765531,
+      "grad_norm": 0.4319005608558655,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 2130
+    },
+    {
+      "epoch": 2.859051436205745,
+      "grad_norm": 0.4297086298465729,
+      "learning_rate": 0.0002,
+      "loss": 1.6717,
+      "step": 2140
+    },
+    {
+      "epoch": 2.8724114896459585,
+      "grad_norm": 0.5011981129646301,
+      "learning_rate": 0.0002,
+      "loss": 1.5968,
+      "step": 2150
+    },
+    {
+      "epoch": 2.8857715430861726,
+      "grad_norm": 0.4401548504829407,
+      "learning_rate": 0.0002,
+      "loss": 1.7181,
+      "step": 2160
+    },
+    {
+      "epoch": 2.899131596526386,
+      "grad_norm": 0.48090746998786926,
+      "learning_rate": 0.0002,
+      "loss": 1.5722,
+      "step": 2170
+    },
+    {
+      "epoch": 2.9124916499666,
+      "grad_norm": 0.4740385413169861,
+      "learning_rate": 0.0002,
+      "loss": 1.6596,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9258517034068134,
+      "grad_norm": 0.5337260365486145,
+      "learning_rate": 0.0002,
+      "loss": 1.6501,
+      "step": 2190
+    },
+    {
+      "epoch": 2.9392117568470275,
+      "grad_norm": 0.4420052766799927,
+      "learning_rate": 0.0002,
+      "loss": 1.6802,
+      "step": 2200
+    },
+    {
+      "epoch": 2.952571810287241,
+      "grad_norm": 0.477512389421463,
+      "learning_rate": 0.0002,
+      "loss": 1.5474,
+      "step": 2210
+    },
+    {
+      "epoch": 2.9659318637274548,
+      "grad_norm": 0.5344052910804749,
+      "learning_rate": 0.0002,
+      "loss": 1.6544,
+      "step": 2220
+    },
+    {
+      "epoch": 2.979291917167669,
+      "grad_norm": 0.4483940303325653,
+      "learning_rate": 0.0002,
+      "loss": 1.6866,
+      "step": 2230
+    },
+    {
+      "epoch": 2.9926519706078825,
+      "grad_norm": 0.4366597831249237,
+      "learning_rate": 0.0002,
+      "loss": 1.6477,
+      "step": 2240
+    },
+    {
+      "epoch": 2.9993319973279893,
+      "eval_loss": 1.834012746810913,
+      "eval_runtime": 38.5659,
+      "eval_samples_per_second": 13.354,
+      "eval_steps_per_second": 1.685,
+      "step": 2245
+    },
+    {
+      "epoch": 3.006012024048096,
+      "grad_norm": 0.428824245929718,
+      "learning_rate": 0.0002,
+      "loss": 1.5582,
+      "step": 2250
+    },
+    {
+      "epoch": 3.01937207748831,
+      "grad_norm": 0.4870174825191498,
+      "learning_rate": 0.0002,
+      "loss": 1.499,
+      "step": 2260
+    },
+    {
+      "epoch": 3.032732130928524,
+      "grad_norm": 0.4684266149997711,
+      "learning_rate": 0.0002,
+      "loss": 1.4872,
+      "step": 2270
+    },
+    {
+      "epoch": 3.0460921843687374,
+      "grad_norm": 0.581604540348053,
+      "learning_rate": 0.0002,
+      "loss": 1.5284,
+      "step": 2280
+    },
+    {
+      "epoch": 3.059452237808951,
+      "grad_norm": 0.5561677813529968,
+      "learning_rate": 0.0002,
+      "loss": 1.4549,
+      "step": 2290
+    },
+    {
+      "epoch": 3.072812291249165,
+      "grad_norm": 0.5750220417976379,
+      "learning_rate": 0.0002,
+      "loss": 1.4903,
+      "step": 2300
+    },
+    {
+      "epoch": 3.0861723446893787,
+      "grad_norm": 0.5704626441001892,
+      "learning_rate": 0.0002,
+      "loss": 1.5903,
+      "step": 2310
+    },
+    {
+      "epoch": 3.0995323981295924,
+      "grad_norm": 0.6242083311080933,
+      "learning_rate": 0.0002,
+      "loss": 1.4292,
+      "step": 2320
+    },
+    {
+      "epoch": 3.1128924515698064,
+      "grad_norm": 0.5174121260643005,
+      "learning_rate": 0.0002,
+      "loss": 1.5092,
+      "step": 2330
+    },
+    {
+      "epoch": 3.12625250501002,
+      "grad_norm": 0.5697633028030396,
+      "learning_rate": 0.0002,
+      "loss": 1.5106,
+      "step": 2340
+    },
+    {
+      "epoch": 3.1396125584502337,
+      "grad_norm": 0.5969541072845459,
+      "learning_rate": 0.0002,
+      "loss": 1.5156,
+      "step": 2350
+    },
+    {
+      "epoch": 3.1529726118904478,
+      "grad_norm": 0.6244304180145264,
+      "learning_rate": 0.0002,
+      "loss": 1.52,
+      "step": 2360
+    },
+    {
+      "epoch": 3.1663326653306614,
+      "grad_norm": 0.5561705827713013,
+      "learning_rate": 0.0002,
+      "loss": 1.5244,
+      "step": 2370
+    },
+    {
+      "epoch": 3.179692718770875,
+      "grad_norm": 0.5401188135147095,
+      "learning_rate": 0.0002,
+      "loss": 1.6169,
+      "step": 2380
+    },
+    {
+      "epoch": 3.1930527722110886,
+      "grad_norm": 0.6450421810150146,
+      "learning_rate": 0.0002,
+      "loss": 1.5387,
+      "step": 2390
+    },
+    {
+      "epoch": 3.2064128256513027,
+      "grad_norm": 0.5741903185844421,
+      "learning_rate": 0.0002,
+      "loss": 1.4839,
+      "step": 2400
+    },
+    {
+      "epoch": 3.2197728790915163,
+      "grad_norm": 0.6337407231330872,
+      "learning_rate": 0.0002,
+      "loss": 1.5584,
+      "step": 2410
+    },
+    {
+      "epoch": 3.23313293253173,
+      "grad_norm": 0.6493517160415649,
+      "learning_rate": 0.0002,
+      "loss": 1.5025,
+      "step": 2420
+    },
+    {
+      "epoch": 3.246492985971944,
+      "grad_norm": 0.6230176091194153,
+      "learning_rate": 0.0002,
+      "loss": 1.5168,
+      "step": 2430
+    },
+    {
+      "epoch": 3.2598530394121576,
+      "grad_norm": 0.680704653263092,
+      "learning_rate": 0.0002,
+      "loss": 1.5408,
+      "step": 2440
+    },
+    {
+      "epoch": 3.2732130928523713,
+      "grad_norm": 0.5279417037963867,
+      "learning_rate": 0.0002,
+      "loss": 1.6005,
+      "step": 2450
+    },
+    {
+      "epoch": 3.2865731462925853,
+      "grad_norm": 0.5601515173912048,
+      "learning_rate": 0.0002,
+      "loss": 1.5231,
+      "step": 2460
+    },
+    {
+      "epoch": 3.299933199732799,
+      "grad_norm": 0.5591090321540833,
+      "learning_rate": 0.0002,
+      "loss": 1.4949,
+      "step": 2470
+    },
+    {
+      "epoch": 3.3132932531730126,
+      "grad_norm": 0.6596529483795166,
+      "learning_rate": 0.0002,
+      "loss": 1.5181,
+      "step": 2480
+    },
+    {
+      "epoch": 3.3266533066132267,
+      "grad_norm": 0.6115918755531311,
+      "learning_rate": 0.0002,
+      "loss": 1.5259,
+      "step": 2490
+    },
+    {
+      "epoch": 3.3400133600534403,
+      "grad_norm": 0.6443548202514648,
+      "learning_rate": 0.0002,
+      "loss": 1.5344,
+      "step": 2500
+    },
+    {
+      "epoch": 3.353373413493654,
+      "grad_norm": 0.5504242181777954,
+      "learning_rate": 0.0002,
+      "loss": 1.5037,
+      "step": 2510
+    },
+    {
+      "epoch": 3.3667334669338675,
+      "grad_norm": 0.6104483604431152,
+      "learning_rate": 0.0002,
+      "loss": 1.5049,
+      "step": 2520
+    },
+    {
+      "epoch": 3.3800935203740816,
+      "grad_norm": 0.8387531638145447,
+      "learning_rate": 0.0002,
+      "loss": 1.587,
+      "step": 2530
+    },
+    {
+      "epoch": 3.3934535738142952,
+      "grad_norm": 0.6346094012260437,
+      "learning_rate": 0.0002,
+      "loss": 1.5227,
+      "step": 2540
+    },
+    {
+      "epoch": 3.406813627254509,
+      "grad_norm": 0.6261265873908997,
+      "learning_rate": 0.0002,
+      "loss": 1.4855,
+      "step": 2550
+    },
+    {
+      "epoch": 3.420173680694723,
+      "grad_norm": 0.5960372090339661,
+      "learning_rate": 0.0002,
+      "loss": 1.5233,
+      "step": 2560
+    },
+    {
+      "epoch": 3.4335337341349366,
+      "grad_norm": 0.5291280746459961,
+      "learning_rate": 0.0002,
+      "loss": 1.5153,
+      "step": 2570
+    },
+    {
+      "epoch": 3.44689378757515,
+      "grad_norm": 0.6133161783218384,
+      "learning_rate": 0.0002,
+      "loss": 1.5152,
+      "step": 2580
+    },
+    {
+      "epoch": 3.460253841015364,
+      "grad_norm": 0.623573362827301,
+      "learning_rate": 0.0002,
+      "loss": 1.5533,
+      "step": 2590
+    },
+    {
+      "epoch": 3.473613894455578,
+      "grad_norm": 0.5959834456443787,
+      "learning_rate": 0.0002,
+      "loss": 1.4935,
+      "step": 2600
+    },
+    {
+      "epoch": 3.4869739478957915,
+      "grad_norm": 0.583332359790802,
+      "learning_rate": 0.0002,
+      "loss": 1.5792,
+      "step": 2610
+    },
+    {
+      "epoch": 3.5003340013360056,
+      "grad_norm": 0.6003559231758118,
+      "learning_rate": 0.0002,
+      "loss": 1.5229,
+      "step": 2620
+    },
+    {
+      "epoch": 3.513694054776219,
+      "grad_norm": 0.5832992196083069,
+      "learning_rate": 0.0002,
+      "loss": 1.4901,
+      "step": 2630
+    },
+    {
+      "epoch": 3.527054108216433,
+      "grad_norm": 0.5942609906196594,
+      "learning_rate": 0.0002,
+      "loss": 1.5005,
+      "step": 2640
+    },
+    {
+      "epoch": 3.5404141616566465,
+      "grad_norm": 0.6087163686752319,
+      "learning_rate": 0.0002,
+      "loss": 1.5213,
+      "step": 2650
+    },
+    {
+      "epoch": 3.5537742150968605,
+      "grad_norm": 0.631948709487915,
+      "learning_rate": 0.0002,
+      "loss": 1.5826,
+      "step": 2660
+    },
+    {
+      "epoch": 3.567134268537074,
+      "grad_norm": 0.6450803279876709,
+      "learning_rate": 0.0002,
+      "loss": 1.5844,
+      "step": 2670
+    },
+    {
+      "epoch": 3.580494321977288,
+      "grad_norm": 0.6507797837257385,
+      "learning_rate": 0.0002,
+      "loss": 1.4981,
+      "step": 2680
+    },
+    {
+      "epoch": 3.593854375417502,
+      "grad_norm": 0.5778017044067383,
+      "learning_rate": 0.0002,
+      "loss": 1.5826,
+      "step": 2690
+    },
+    {
+      "epoch": 3.6072144288577155,
+      "grad_norm": 0.6214032173156738,
+      "learning_rate": 0.0002,
+      "loss": 1.4688,
+      "step": 2700
+    },
+    {
+      "epoch": 3.620574482297929,
+      "grad_norm": 0.5681133270263672,
+      "learning_rate": 0.0002,
+      "loss": 1.5084,
+      "step": 2710
+    },
+    {
+      "epoch": 3.6339345357381427,
+      "grad_norm": 0.6074244976043701,
+      "learning_rate": 0.0002,
+      "loss": 1.471,
+      "step": 2720
+    },
+    {
+      "epoch": 3.647294589178357,
+      "grad_norm": 0.5900560617446899,
+      "learning_rate": 0.0002,
+      "loss": 1.5243,
+      "step": 2730
+    },
+    {
+      "epoch": 3.6606546426185704,
+      "grad_norm": 0.5817505717277527,
+      "learning_rate": 0.0002,
+      "loss": 1.5074,
+      "step": 2740
+    },
+    {
+      "epoch": 3.6740146960587845,
+      "grad_norm": 0.6095547676086426,
+      "learning_rate": 0.0002,
+      "loss": 1.5117,
+      "step": 2750
+    },
+    {
+      "epoch": 3.687374749498998,
+      "grad_norm": 0.612790584564209,
+      "learning_rate": 0.0002,
+      "loss": 1.5117,
+      "step": 2760
+    },
+    {
+      "epoch": 3.7007348029392118,
+      "grad_norm": 0.6574140787124634,
+      "learning_rate": 0.0002,
+      "loss": 1.4976,
+      "step": 2770
+    },
+    {
+      "epoch": 3.7140948563794254,
+      "grad_norm": 0.5643761157989502,
+      "learning_rate": 0.0002,
+      "loss": 1.5306,
+      "step": 2780
+    },
+    {
+      "epoch": 3.727454909819639,
+      "grad_norm": 0.5652621388435364,
+      "learning_rate": 0.0002,
+      "loss": 1.5751,
+      "step": 2790
+    },
+    {
+      "epoch": 3.740814963259853,
+      "grad_norm": 0.5604206323623657,
+      "learning_rate": 0.0002,
+      "loss": 1.5262,
+      "step": 2800
+    },
+    {
+      "epoch": 3.7541750167000667,
+      "grad_norm": 3.911022663116455,
+      "learning_rate": 0.0002,
+      "loss": 1.5013,
+      "step": 2810
+    },
+    {
+      "epoch": 3.7675350701402808,
+      "grad_norm": 0.6148333549499512,
+      "learning_rate": 0.0002,
+      "loss": 1.5793,
+      "step": 2820
+    },
+    {
+      "epoch": 3.7808951235804944,
+      "grad_norm": 0.5605677962303162,
+      "learning_rate": 0.0002,
+      "loss": 1.5122,
+      "step": 2830
+    },
+    {
+      "epoch": 3.794255177020708,
+      "grad_norm": 0.6101965308189392,
+      "learning_rate": 0.0002,
+      "loss": 1.5659,
+      "step": 2840
+    },
+    {
+      "epoch": 3.8076152304609217,
+      "grad_norm": 0.5387342572212219,
+      "learning_rate": 0.0002,
+      "loss": 1.5618,
+      "step": 2850
+    },
+    {
+      "epoch": 3.8209752839011357,
+      "grad_norm": 0.5733087062835693,
+      "learning_rate": 0.0002,
+      "loss": 1.5193,
+      "step": 2860
+    },
+    {
+      "epoch": 3.8343353373413493,
+      "grad_norm": 0.6538485884666443,
+      "learning_rate": 0.0002,
+      "loss": 1.5545,
+      "step": 2870
+    },
+    {
+      "epoch": 3.847695390781563,
+      "grad_norm": 0.6247632503509521,
+      "learning_rate": 0.0002,
+      "loss": 1.523,
+      "step": 2880
+    },
+    {
+      "epoch": 3.861055444221777,
+      "grad_norm": 0.5745735764503479,
+      "learning_rate": 0.0002,
+      "loss": 1.5591,
+      "step": 2890
+    },
+    {
+      "epoch": 3.8744154976619907,
+      "grad_norm": 0.5942763686180115,
+      "learning_rate": 0.0002,
+      "loss": 1.5706,
+      "step": 2900
+    },
+    {
+      "epoch": 3.8877755511022043,
+      "grad_norm": 0.7086281776428223,
+      "learning_rate": 0.0002,
+      "loss": 1.564,
+      "step": 2910
+    },
+    {
+      "epoch": 3.901135604542418,
+      "grad_norm": 0.8825129866600037,
+      "learning_rate": 0.0002,
+      "loss": 1.5526,
+      "step": 2920
+    },
+    {
+      "epoch": 3.914495657982632,
+      "grad_norm": 0.6260842680931091,
+      "learning_rate": 0.0002,
+      "loss": 1.4519,
+      "step": 2930
+    },
+    {
+      "epoch": 3.9278557114228456,
+      "grad_norm": 0.6015968322753906,
+      "learning_rate": 0.0002,
+      "loss": 1.5433,
+      "step": 2940
+    },
+    {
+      "epoch": 3.9412157648630597,
+      "grad_norm": 0.7042809128761292,
+      "learning_rate": 0.0002,
+      "loss": 1.4931,
+      "step": 2950
+    },
+    {
+      "epoch": 3.9545758183032733,
+      "grad_norm": 0.5860083699226379,
+      "learning_rate": 0.0002,
+      "loss": 1.5596,
+      "step": 2960
+    },
+    {
+      "epoch": 3.967935871743487,
+      "grad_norm": 0.5939757823944092,
+      "learning_rate": 0.0002,
+      "loss": 1.565,
+      "step": 2970
+    },
+    {
+      "epoch": 3.9812959251837006,
+      "grad_norm": 0.5523964166641235,
+      "learning_rate": 0.0002,
+      "loss": 1.408,
+      "step": 2980
+    },
+    {
+      "epoch": 3.9946559786239146,
+      "grad_norm": 0.6380264759063721,
+      "learning_rate": 0.0002,
+      "loss": 1.5629,
+      "step": 2990
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.8875294923782349,
+      "eval_runtime": 38.5837,
+      "eval_samples_per_second": 13.348,
+      "eval_steps_per_second": 1.685,
+      "step": 2994
+    },
+    {
+      "epoch": 4.008016032064128,
+      "grad_norm": 0.5478564500808716,
+      "learning_rate": 0.0002,
+      "loss": 1.4002,
+      "step": 3000
+    },
+    {
+      "epoch": 4.021376085504342,
+      "grad_norm": 0.9384379982948303,
+      "learning_rate": 0.0002,
+      "loss": 1.436,
+      "step": 3010
+    },
+    {
+      "epoch": 4.034736138944556,
+      "grad_norm": 0.7819344401359558,
+      "learning_rate": 0.0002,
+      "loss": 1.4127,
+      "step": 3020
+    },
+    {
+      "epoch": 4.04809619238477,
+      "grad_norm": 0.7737417817115784,
+      "learning_rate": 0.0002,
+      "loss": 1.326,
+      "step": 3030
+    },
+    {
+      "epoch": 4.061456245824983,
+      "grad_norm": 0.8893805742263794,
+      "learning_rate": 0.0002,
+      "loss": 1.3203,
+      "step": 3040
+    },
+    {
+      "epoch": 4.074816299265197,
+      "grad_norm": 0.7759843468666077,
+      "learning_rate": 0.0002,
+      "loss": 1.3913,
+      "step": 3050
+    },
+    {
+      "epoch": 4.0881763527054105,
+      "grad_norm": 0.642654538154602,
+      "learning_rate": 0.0002,
+      "loss": 1.2941,
+      "step": 3060
+    },
+    {
+      "epoch": 4.101536406145625,
+      "grad_norm": 0.8515549302101135,
+      "learning_rate": 0.0002,
+      "loss": 1.3204,
+      "step": 3070
+    },
+    {
+      "epoch": 4.114896459585839,
+      "grad_norm": 0.7033658623695374,
+      "learning_rate": 0.0002,
+      "loss": 1.3683,
+      "step": 3080
+    },
+    {
+      "epoch": 4.128256513026052,
+      "grad_norm": 0.7063882946968079,
+      "learning_rate": 0.0002,
+      "loss": 1.4159,
+      "step": 3090
+    },
+    {
+      "epoch": 4.141616566466266,
+      "grad_norm": 0.6946853995323181,
+      "learning_rate": 0.0002,
+      "loss": 1.384,
+      "step": 3100
+    },
+    {
+      "epoch": 4.1549766199064795,
+      "grad_norm": 0.7286741137504578,
+      "learning_rate": 0.0002,
+      "loss": 1.3689,
+      "step": 3110
+    },
+    {
+      "epoch": 4.168336673346693,
+      "grad_norm": 0.7894193530082703,
+      "learning_rate": 0.0002,
+      "loss": 1.3061,
+      "step": 3120
+    },
+    {
+      "epoch": 4.181696726786907,
+      "grad_norm": 0.7005895376205444,
+      "learning_rate": 0.0002,
+      "loss": 1.3346,
+      "step": 3130
+    },
+    {
+      "epoch": 4.195056780227121,
+      "grad_norm": 0.799567461013794,
+      "learning_rate": 0.0002,
+      "loss": 1.3834,
+      "step": 3140
+    },
+    {
+      "epoch": 4.208416833667335,
+      "grad_norm": 0.7010157108306885,
+      "learning_rate": 0.0002,
+      "loss": 1.3813,
+      "step": 3150
+    },
+    {
+      "epoch": 4.2217768871075485,
+      "grad_norm": 0.7489650249481201,
+      "learning_rate": 0.0002,
+      "loss": 1.3637,
+      "step": 3160
+    },
+    {
+      "epoch": 4.235136940547762,
+      "grad_norm": 0.7908048629760742,
+      "learning_rate": 0.0002,
+      "loss": 1.3546,
+      "step": 3170
+    },
+    {
+      "epoch": 4.248496993987976,
+      "grad_norm": 0.7002180814743042,
+      "learning_rate": 0.0002,
+      "loss": 1.3073,
+      "step": 3180
+    },
+    {
+      "epoch": 4.261857047428189,
+      "grad_norm": 0.8339495062828064,
+      "learning_rate": 0.0002,
+      "loss": 1.4525,
+      "step": 3190
+    },
+    {
+      "epoch": 4.275217100868403,
+      "grad_norm": 0.7884618043899536,
+      "learning_rate": 0.0002,
+      "loss": 1.3471,
+      "step": 3200
+    },
+    {
+      "epoch": 4.2885771543086175,
+      "grad_norm": 0.7964122295379639,
+      "learning_rate": 0.0002,
+      "loss": 1.4261,
+      "step": 3210
+    },
+    {
+      "epoch": 4.301937207748831,
+      "grad_norm": 0.838646650314331,
+      "learning_rate": 0.0002,
+      "loss": 1.3506,
+      "step": 3220
+    },
+    {
+      "epoch": 4.315297261189045,
+      "grad_norm": 0.8063107132911682,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 3230
+    },
+    {
+      "epoch": 4.328657314629258,
+      "grad_norm": 0.8147385120391846,
+      "learning_rate": 0.0002,
+      "loss": 1.3769,
+      "step": 3240
+    },
+    {
+      "epoch": 4.342017368069472,
+      "grad_norm": 0.7636798620223999,
+      "learning_rate": 0.0002,
+      "loss": 1.4118,
+      "step": 3250
+    },
+    {
+      "epoch": 4.355377421509686,
+      "grad_norm": 0.7530609965324402,
+      "learning_rate": 0.0002,
+      "loss": 1.3698,
+      "step": 3260
+    },
+    {
+      "epoch": 4.3687374749499,
+      "grad_norm": 0.8853573799133301,
+      "learning_rate": 0.0002,
+      "loss": 1.3507,
+      "step": 3270
+    },
+    {
+      "epoch": 4.382097528390114,
+      "grad_norm": 0.7180975675582886,
+      "learning_rate": 0.0002,
+      "loss": 1.3614,
+      "step": 3280
+    },
+    {
+      "epoch": 4.395457581830327,
+      "grad_norm": 0.837150514125824,
+      "learning_rate": 0.0002,
+      "loss": 1.4119,
+      "step": 3290
+    },
+    {
+      "epoch": 4.408817635270541,
+      "grad_norm": 0.8370638489723206,
+      "learning_rate": 0.0002,
+      "loss": 1.461,
+      "step": 3300
+    },
+    {
+      "epoch": 4.422177688710755,
+      "grad_norm": 0.7738229036331177,
+      "learning_rate": 0.0002,
+      "loss": 1.4478,
+      "step": 3310
+    },
+    {
+      "epoch": 4.435537742150968,
+      "grad_norm": 0.7665290832519531,
+      "learning_rate": 0.0002,
+      "loss": 1.4195,
+      "step": 3320
+    },
+    {
+      "epoch": 4.448897795591183,
+      "grad_norm": 0.7547745704650879,
+      "learning_rate": 0.0002,
+      "loss": 1.3308,
+      "step": 3330
+    },
+    {
+      "epoch": 4.462257849031396,
+      "grad_norm": 0.7421861290931702,
+      "learning_rate": 0.0002,
+      "loss": 1.4165,
+      "step": 3340
+    },
+    {
+      "epoch": 4.47561790247161,
+      "grad_norm": 0.8042104244232178,
+      "learning_rate": 0.0002,
+      "loss": 1.4244,
+      "step": 3350
+    },
+    {
+      "epoch": 4.488977955911824,
+      "grad_norm": 0.8111839890480042,
+      "learning_rate": 0.0002,
+      "loss": 1.365,
+      "step": 3360
+    },
+    {
+      "epoch": 4.502338009352037,
+      "grad_norm": 0.7998340129852295,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 3370
+    },
+    {
+      "epoch": 4.515698062792251,
+      "grad_norm": 0.7668877243995667,
+      "learning_rate": 0.0002,
+      "loss": 1.3812,
+      "step": 3380
+    },
+    {
+      "epoch": 4.529058116232465,
+      "grad_norm": 0.7986718416213989,
+      "learning_rate": 0.0002,
+      "loss": 1.3972,
+      "step": 3390
+    },
+    {
+      "epoch": 4.542418169672679,
+      "grad_norm": 0.6806602478027344,
+      "learning_rate": 0.0002,
+      "loss": 1.3582,
+      "step": 3400
+    },
+    {
+      "epoch": 4.555778223112893,
+      "grad_norm": 0.8788819909095764,
+      "learning_rate": 0.0002,
+      "loss": 1.3942,
+      "step": 3410
+    },
+    {
+      "epoch": 4.569138276553106,
+      "grad_norm": 0.7499664425849915,
+      "learning_rate": 0.0002,
+      "loss": 1.3379,
+      "step": 3420
+    },
+    {
+      "epoch": 4.58249832999332,
+      "grad_norm": 0.7967109084129333,
+      "learning_rate": 0.0002,
+      "loss": 1.3823,
+      "step": 3430
+    },
+    {
+      "epoch": 4.595858383433534,
+      "grad_norm": 0.759639322757721,
+      "learning_rate": 0.0002,
+      "loss": 1.3531,
+      "step": 3440
+    },
+    {
+      "epoch": 4.609218436873747,
+      "grad_norm": 0.8327916264533997,
+      "learning_rate": 0.0002,
+      "loss": 1.3517,
+      "step": 3450
+    },
+    {
+      "epoch": 4.622578490313961,
+      "grad_norm": 0.7400892376899719,
+      "learning_rate": 0.0002,
+      "loss": 1.4619,
+      "step": 3460
+    },
+    {
+      "epoch": 4.635938543754175,
+      "grad_norm": 0.8116602301597595,
+      "learning_rate": 0.0002,
+      "loss": 1.3374,
+      "step": 3470
+    },
+    {
+      "epoch": 4.649298597194389,
+      "grad_norm": 0.7604362368583679,
+      "learning_rate": 0.0002,
+      "loss": 1.4445,
+      "step": 3480
+    },
+    {
+      "epoch": 4.662658650634603,
+      "grad_norm": 0.7397996783256531,
+      "learning_rate": 0.0002,
+      "loss": 1.3724,
+      "step": 3490
+    },
+    {
+      "epoch": 4.676018704074816,
+      "grad_norm": 0.869293749332428,
+      "learning_rate": 0.0002,
+      "loss": 1.4048,
+      "step": 3500
+    },
+    {
+      "epoch": 4.68937875751503,
+      "grad_norm": 0.6854358315467834,
+      "learning_rate": 0.0002,
+      "loss": 1.3873,
+      "step": 3510
+    },
+    {
+      "epoch": 4.7027388109552435,
+      "grad_norm": 0.8326661586761475,
+      "learning_rate": 0.0002,
+      "loss": 1.3413,
+      "step": 3520
+    },
+    {
+      "epoch": 4.716098864395457,
+      "grad_norm": 0.6887506246566772,
+      "learning_rate": 0.0002,
+      "loss": 1.3666,
+      "step": 3530
+    },
+    {
+      "epoch": 4.729458917835672,
+      "grad_norm": 3.837689161300659,
+      "learning_rate": 0.0002,
+      "loss": 1.4508,
+      "step": 3540
+    },
+    {
+      "epoch": 4.742818971275885,
+      "grad_norm": 0.6874563694000244,
+      "learning_rate": 0.0002,
+      "loss": 1.3775,
+      "step": 3550
+    },
+    {
+      "epoch": 4.756179024716099,
+      "grad_norm": 0.8340407609939575,
+      "learning_rate": 0.0002,
+      "loss": 1.3643,
+      "step": 3560
+    },
+    {
+      "epoch": 4.7695390781563125,
+      "grad_norm": 0.7286418676376343,
+      "learning_rate": 0.0002,
+      "loss": 1.3556,
+      "step": 3570
+    },
+    {
+      "epoch": 4.782899131596526,
+      "grad_norm": 0.7239373326301575,
+      "learning_rate": 0.0002,
+      "loss": 1.4338,
+      "step": 3580
+    },
+    {
+      "epoch": 4.796259185036741,
+      "grad_norm": 0.831310510635376,
+      "learning_rate": 0.0002,
+      "loss": 1.4697,
+      "step": 3590
+    },
+    {
+      "epoch": 4.809619238476954,
+      "grad_norm": 0.767715573310852,
+      "learning_rate": 0.0002,
+      "loss": 1.4146,
+      "step": 3600
+    },
+    {
+      "epoch": 4.822979291917168,
+      "grad_norm": 0.9013199210166931,
+      "learning_rate": 0.0002,
+      "loss": 1.4199,
+      "step": 3610
+    },
+    {
+      "epoch": 4.8363393453573815,
+      "grad_norm": 0.7543512582778931,
+      "learning_rate": 0.0002,
+      "loss": 1.4513,
+      "step": 3620
+    },
+    {
+      "epoch": 4.849699398797595,
+      "grad_norm": 0.7626057267189026,
+      "learning_rate": 0.0002,
+      "loss": 1.4218,
+      "step": 3630
+    },
+    {
+      "epoch": 4.863059452237809,
+      "grad_norm": 0.847079336643219,
+      "learning_rate": 0.0002,
+      "loss": 1.4102,
+      "step": 3640
+    },
+    {
+      "epoch": 4.876419505678022,
+      "grad_norm": 0.8273295760154724,
+      "learning_rate": 0.0002,
+      "loss": 1.5014,
+      "step": 3650
+    },
+    {
+      "epoch": 4.889779559118237,
+      "grad_norm": 0.7675244808197021,
+      "learning_rate": 0.0002,
+      "loss": 1.3806,
+      "step": 3660
+    },
+    {
+      "epoch": 4.9031396125584505,
+      "grad_norm": 0.9560356736183167,
+      "learning_rate": 0.0002,
+      "loss": 1.4894,
+      "step": 3670
+    },
+    {
+      "epoch": 4.916499665998664,
+      "grad_norm": 0.7682451605796814,
+      "learning_rate": 0.0002,
+      "loss": 1.4044,
+      "step": 3680
+    },
+    {
+      "epoch": 4.929859719438878,
+      "grad_norm": 0.8113830089569092,
+      "learning_rate": 0.0002,
+      "loss": 1.342,
+      "step": 3690
+    },
+    {
+      "epoch": 4.943219772879091,
+      "grad_norm": 0.7642542719841003,
+      "learning_rate": 0.0002,
+      "loss": 1.3559,
+      "step": 3700
+    },
+    {
+      "epoch": 4.956579826319305,
+      "grad_norm": 0.823863685131073,
+      "learning_rate": 0.0002,
+      "loss": 1.403,
+      "step": 3710
+    },
+    {
+      "epoch": 4.969939879759519,
+      "grad_norm": 0.8287797570228577,
+      "learning_rate": 0.0002,
+      "loss": 1.464,
+      "step": 3720
+    },
+    {
+      "epoch": 4.983299933199733,
+      "grad_norm": 0.778170108795166,
+      "learning_rate": 0.0002,
+      "loss": 1.4139,
+      "step": 3730
+    },
+    {
+      "epoch": 4.996659986639947,
+      "grad_norm": 0.7464073896408081,
+      "learning_rate": 0.0002,
+      "loss": 1.4218,
+      "step": 3740
+    },
+    {
+      "epoch": 4.999331997327989,
+      "eval_loss": 1.9638569355010986,
+      "eval_runtime": 38.5725,
+      "eval_samples_per_second": 13.351,
+      "eval_steps_per_second": 1.685,
+      "step": 3742
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5984,
+  "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": 1.7319452020310016e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7025f98e983b93b4fec0d5370c1456c7adecaf8e
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-3742/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e92f0598f349930e52e126f358a3dca045c3c88312ec4b3f814f018a04982a9
+size 5560
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/README.md b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d63cb87eaccf2d81de3cdcfa11d2e99c440c0ea0
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2ff2b51d5983169399d252f98c92a13f3bbdc79e
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:202ff5a7c06e1be89d42c147ce31dc497efcf6b513dcf3c7a42bee16ae322db5
+size 109069176
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..14d4a83c0d7f5404bd603a5efc2381af337978c7
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dd22daa5b07b64b4f46b5455deaff3f2811e9fdfdb6c7feba673d9eff289ea0
+size 55532666
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..bf8dcb9191ef22ebeaab53bf82e205ac0258fc75
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d71846d766611c4ff35f96afdd2c6f029ba6ba3bb4a869ea9e5a37f2cf03d1c0
+size 14244
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b5e273c84eb88987519772be274a0a747f74d245
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bcae50b846cfe798b14178881a8e1b25456e98e5002e123c0b7e9104d2ee731
+size 1064
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/tokenizer_config.json
@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..6c9b2eaf7064fedf9183215522c1475fdc37d831
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/trainer_state.json
@@ -0,0 +1,3224 @@
+{
+  "best_metric": 1.8132041692733765,
+  "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497",
+  "epoch": 6.0,
+  "eval_steps": 10,
+  "global_step": 4491,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013360053440213761,
+      "grad_norm": 0.5097216367721558,
+      "learning_rate": 0.0002,
+      "loss": 2.6569,
+      "step": 10
+    },
+    {
+      "epoch": 0.026720106880427523,
+      "grad_norm": 0.5924790501594543,
+      "learning_rate": 0.0002,
+      "loss": 2.2557,
+      "step": 20
+    },
+    {
+      "epoch": 0.04008016032064128,
+      "grad_norm": 0.5158102512359619,
+      "learning_rate": 0.0002,
+      "loss": 2.0626,
+      "step": 30
+    },
+    {
+      "epoch": 0.053440213760855046,
+      "grad_norm": 0.5033753514289856,
+      "learning_rate": 0.0002,
+      "loss": 1.9452,
+      "step": 40
+    },
+    {
+      "epoch": 0.06680026720106881,
+      "grad_norm": 0.5390949845314026,
+      "learning_rate": 0.0002,
+      "loss": 1.9128,
+      "step": 50
+    },
+    {
+      "epoch": 0.08016032064128256,
+      "grad_norm": 0.6376217007637024,
+      "learning_rate": 0.0002,
+      "loss": 1.937,
+      "step": 60
+    },
+    {
+      "epoch": 0.09352037408149633,
+      "grad_norm": 0.4202035069465637,
+      "learning_rate": 0.0002,
+      "loss": 1.929,
+      "step": 70
+    },
+    {
+      "epoch": 0.10688042752171009,
+      "grad_norm": 0.4269474744796753,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 80
+    },
+    {
+      "epoch": 0.12024048096192384,
+      "grad_norm": 0.4306574761867523,
+      "learning_rate": 0.0002,
+      "loss": 1.8303,
+      "step": 90
+    },
+    {
+      "epoch": 0.13360053440213762,
+      "grad_norm": 0.5297011137008667,
+      "learning_rate": 0.0002,
+      "loss": 1.8469,
+      "step": 100
+    },
+    {
+      "epoch": 0.14696058784235136,
+      "grad_norm": 1.2313778400421143,
+      "learning_rate": 0.0002,
+      "loss": 1.864,
+      "step": 110
+    },
+    {
+      "epoch": 0.16032064128256512,
+      "grad_norm": 0.5351294279098511,
+      "learning_rate": 0.0002,
+      "loss": 1.8531,
+      "step": 120
+    },
+    {
+      "epoch": 0.1736806947227789,
+      "grad_norm": 0.4848092496395111,
+      "learning_rate": 0.0002,
+      "loss": 1.9232,
+      "step": 130
+    },
+    {
+      "epoch": 0.18704074816299265,
+      "grad_norm": 0.4339500665664673,
+      "learning_rate": 0.0002,
+      "loss": 1.8633,
+      "step": 140
+    },
+    {
+      "epoch": 0.20040080160320642,
+      "grad_norm": 0.46877285838127136,
+      "learning_rate": 0.0002,
+      "loss": 1.816,
+      "step": 150
+    },
+    {
+      "epoch": 0.21376085504342018,
+      "grad_norm": 0.5600412487983704,
+      "learning_rate": 0.0002,
+      "loss": 1.8033,
+      "step": 160
+    },
+    {
+      "epoch": 0.22712090848363392,
+      "grad_norm": 0.3733620345592499,
+      "learning_rate": 0.0002,
+      "loss": 1.8162,
+      "step": 170
+    },
+    {
+      "epoch": 0.24048096192384769,
+      "grad_norm": 0.5116042494773865,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 180
+    },
+    {
+      "epoch": 0.25384101536406145,
+      "grad_norm": 0.4071602523326874,
+      "learning_rate": 0.0002,
+      "loss": 1.915,
+      "step": 190
+    },
+    {
+      "epoch": 0.26720106880427524,
+      "grad_norm": 0.44189608097076416,
+      "learning_rate": 0.0002,
+      "loss": 1.7984,
+      "step": 200
+    },
+    {
+      "epoch": 0.280561122244489,
+      "grad_norm": 0.398699015378952,
+      "learning_rate": 0.0002,
+      "loss": 1.8728,
+      "step": 210
+    },
+    {
+      "epoch": 0.2939211756847027,
+      "grad_norm": 0.3585626482963562,
+      "learning_rate": 0.0002,
+      "loss": 1.8205,
+      "step": 220
+    },
+    {
+      "epoch": 0.3072812291249165,
+      "grad_norm": 0.3811776041984558,
+      "learning_rate": 0.0002,
+      "loss": 1.8861,
+      "step": 230
+    },
+    {
+      "epoch": 0.32064128256513025,
+      "grad_norm": 0.37261509895324707,
+      "learning_rate": 0.0002,
+      "loss": 1.8365,
+      "step": 240
+    },
+    {
+      "epoch": 0.33400133600534404,
+      "grad_norm": 0.39762404561042786,
+      "learning_rate": 0.0002,
+      "loss": 1.9186,
+      "step": 250
+    },
+    {
+      "epoch": 0.3473613894455578,
+      "grad_norm": 0.3509528934955597,
+      "learning_rate": 0.0002,
+      "loss": 1.7965,
+      "step": 260
+    },
+    {
+      "epoch": 0.36072144288577157,
+      "grad_norm": 0.3169104754924774,
+      "learning_rate": 0.0002,
+      "loss": 1.7802,
+      "step": 270
+    },
+    {
+      "epoch": 0.3740814963259853,
+      "grad_norm": 0.33714795112609863,
+      "learning_rate": 0.0002,
+      "loss": 1.8038,
+      "step": 280
+    },
+    {
+      "epoch": 0.38744154976619904,
+      "grad_norm": 1.2936875820159912,
+      "learning_rate": 0.0002,
+      "loss": 1.787,
+      "step": 290
+    },
+    {
+      "epoch": 0.40080160320641284,
+      "grad_norm": 0.3459427058696747,
+      "learning_rate": 0.0002,
+      "loss": 1.7974,
+      "step": 300
+    },
+    {
+      "epoch": 0.4141616566466266,
+      "grad_norm": 0.3380655348300934,
+      "learning_rate": 0.0002,
+      "loss": 1.8879,
+      "step": 310
+    },
+    {
+      "epoch": 0.42752171008684037,
+      "grad_norm": 0.3890381455421448,
+      "learning_rate": 0.0002,
+      "loss": 1.9196,
+      "step": 320
+    },
+    {
+      "epoch": 0.4408817635270541,
+      "grad_norm": 0.432327002286911,
+      "learning_rate": 0.0002,
+      "loss": 1.8034,
+      "step": 330
+    },
+    {
+      "epoch": 0.45424181696726784,
+      "grad_norm": 0.3736560046672821,
+      "learning_rate": 0.0002,
+      "loss": 1.8443,
+      "step": 340
+    },
+    {
+      "epoch": 0.46760187040748163,
+      "grad_norm": 0.3700982630252838,
+      "learning_rate": 0.0002,
+      "loss": 1.8506,
+      "step": 350
+    },
+    {
+      "epoch": 0.48096192384769537,
+      "grad_norm": 0.4533902406692505,
+      "learning_rate": 0.0002,
+      "loss": 1.7978,
+      "step": 360
+    },
+    {
+      "epoch": 0.49432197728790916,
+      "grad_norm": 0.35999053716659546,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 370
+    },
+    {
+      "epoch": 0.5076820307281229,
+      "grad_norm": 0.3490903675556183,
+      "learning_rate": 0.0002,
+      "loss": 1.7995,
+      "step": 380
+    },
+    {
+      "epoch": 0.5210420841683366,
+      "grad_norm": 0.34704291820526123,
+      "learning_rate": 0.0002,
+      "loss": 1.8709,
+      "step": 390
+    },
+    {
+      "epoch": 0.5344021376085505,
+      "grad_norm": 0.343565434217453,
+      "learning_rate": 0.0002,
+      "loss": 1.7948,
+      "step": 400
+    },
+    {
+      "epoch": 0.5477621910487642,
+      "grad_norm": 0.3573552966117859,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 410
+    },
+    {
+      "epoch": 0.561122244488978,
+      "grad_norm": 0.32980719208717346,
+      "learning_rate": 0.0002,
+      "loss": 1.8477,
+      "step": 420
+    },
+    {
+      "epoch": 0.5744822979291917,
+      "grad_norm": 0.356952428817749,
+      "learning_rate": 0.0002,
+      "loss": 1.9233,
+      "step": 430
+    },
+    {
+      "epoch": 0.5878423513694054,
+      "grad_norm": 0.3170869052410126,
+      "learning_rate": 0.0002,
+      "loss": 1.7433,
+      "step": 440
+    },
+    {
+      "epoch": 0.6012024048096193,
+      "grad_norm": 0.35233718156814575,
+      "learning_rate": 0.0002,
+      "loss": 1.7607,
+      "step": 450
+    },
+    {
+      "epoch": 0.614562458249833,
+      "grad_norm": 0.3480125367641449,
+      "learning_rate": 0.0002,
+      "loss": 1.8111,
+      "step": 460
+    },
+    {
+      "epoch": 0.6279225116900468,
+      "grad_norm": 0.4762810468673706,
+      "learning_rate": 0.0002,
+      "loss": 1.8386,
+      "step": 470
+    },
+    {
+      "epoch": 0.6412825651302605,
+      "grad_norm": 0.3907663822174072,
+      "learning_rate": 0.0002,
+      "loss": 1.805,
+      "step": 480
+    },
+    {
+      "epoch": 0.6546426185704742,
+      "grad_norm": 0.36315613985061646,
+      "learning_rate": 0.0002,
+      "loss": 1.8113,
+      "step": 490
+    },
+    {
+      "epoch": 0.6680026720106881,
+      "grad_norm": 0.377796471118927,
+      "learning_rate": 0.0002,
+      "loss": 1.7805,
+      "step": 500
+    },
+    {
+      "epoch": 0.6813627254509018,
+      "grad_norm": 0.34284207224845886,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 510
+    },
+    {
+      "epoch": 0.6947227788911156,
+      "grad_norm": 0.35563018918037415,
+      "learning_rate": 0.0002,
+      "loss": 1.8013,
+      "step": 520
+    },
+    {
+      "epoch": 0.7080828323313293,
+      "grad_norm": 0.37575867772102356,
+      "learning_rate": 0.0002,
+      "loss": 1.8414,
+      "step": 530
+    },
+    {
+      "epoch": 0.7214428857715431,
+      "grad_norm": 0.35719701647758484,
+      "learning_rate": 0.0002,
+      "loss": 1.7993,
+      "step": 540
+    },
+    {
+      "epoch": 0.7348029392117569,
+      "grad_norm": 0.385813444852829,
+      "learning_rate": 0.0002,
+      "loss": 1.7574,
+      "step": 550
+    },
+    {
+      "epoch": 0.7481629926519706,
+      "grad_norm": 0.44509607553482056,
+      "learning_rate": 0.0002,
+      "loss": 1.7985,
+      "step": 560
+    },
+    {
+      "epoch": 0.7615230460921844,
+      "grad_norm": 0.36108464002609253,
+      "learning_rate": 0.0002,
+      "loss": 1.7459,
+      "step": 570
+    },
+    {
+      "epoch": 0.7748830995323981,
+      "grad_norm": 0.3530745804309845,
+      "learning_rate": 0.0002,
+      "loss": 1.8207,
+      "step": 580
+    },
+    {
+      "epoch": 0.7882431529726119,
+      "grad_norm": 0.34888574481010437,
+      "learning_rate": 0.0002,
+      "loss": 1.7479,
+      "step": 590
+    },
+    {
+      "epoch": 0.8016032064128257,
+      "grad_norm": 0.387346476316452,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 600
+    },
+    {
+      "epoch": 0.8149632598530394,
+      "grad_norm": 0.3641138970851898,
+      "learning_rate": 0.0002,
+      "loss": 1.8071,
+      "step": 610
+    },
+    {
+      "epoch": 0.8283233132932531,
+      "grad_norm": 0.33729103207588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7531,
+      "step": 620
+    },
+    {
+      "epoch": 0.8416833667334669,
+      "grad_norm": 0.3652004599571228,
+      "learning_rate": 0.0002,
+      "loss": 1.8613,
+      "step": 630
+    },
+    {
+      "epoch": 0.8550434201736807,
+      "grad_norm": 0.3986643850803375,
+      "learning_rate": 0.0002,
+      "loss": 1.9184,
+      "step": 640
+    },
+    {
+      "epoch": 0.8684034736138945,
+      "grad_norm": 0.3458964228630066,
+      "learning_rate": 0.0002,
+      "loss": 1.8198,
+      "step": 650
+    },
+    {
+      "epoch": 0.8817635270541082,
+      "grad_norm": 0.3559381365776062,
+      "learning_rate": 0.0002,
+      "loss": 1.803,
+      "step": 660
+    },
+    {
+      "epoch": 0.895123580494322,
+      "grad_norm": 0.3612841069698334,
+      "learning_rate": 0.0002,
+      "loss": 1.7641,
+      "step": 670
+    },
+    {
+      "epoch": 0.9084836339345357,
+      "grad_norm": 0.34771719574928284,
+      "learning_rate": 0.0002,
+      "loss": 1.7888,
+      "step": 680
+    },
+    {
+      "epoch": 0.9218436873747495,
+      "grad_norm": 0.3371497094631195,
+      "learning_rate": 0.0002,
+      "loss": 1.8204,
+      "step": 690
+    },
+    {
+      "epoch": 0.9352037408149633,
+      "grad_norm": 0.5596055388450623,
+      "learning_rate": 0.0002,
+      "loss": 1.7848,
+      "step": 700
+    },
+    {
+      "epoch": 0.948563794255177,
+      "grad_norm": 0.311880499124527,
+      "learning_rate": 0.0002,
+      "loss": 1.7794,
+      "step": 710
+    },
+    {
+      "epoch": 0.9619238476953907,
+      "grad_norm": 0.3462068736553192,
+      "learning_rate": 0.0002,
+      "loss": 1.8464,
+      "step": 720
+    },
+    {
+      "epoch": 0.9752839011356046,
+      "grad_norm": 0.29982393980026245,
+      "learning_rate": 0.0002,
+      "loss": 1.8197,
+      "step": 730
+    },
+    {
+      "epoch": 0.9886439545758183,
+      "grad_norm": 0.34606459736824036,
+      "learning_rate": 0.0002,
+      "loss": 1.8503,
+      "step": 740
+    },
+    {
+      "epoch": 0.9993319973279893,
+      "eval_loss": 1.8201380968093872,
+      "eval_runtime": 38.6124,
+      "eval_samples_per_second": 13.338,
+      "eval_steps_per_second": 1.683,
+      "step": 748
+    },
+    {
+      "epoch": 1.002004008016032,
+      "grad_norm": 0.32302048802375793,
+      "learning_rate": 0.0002,
+      "loss": 1.7786,
+      "step": 750
+    },
+    {
+      "epoch": 1.0153640614562458,
+      "grad_norm": 0.37585633993148804,
+      "learning_rate": 0.0002,
+      "loss": 1.7297,
+      "step": 760
+    },
+    {
+      "epoch": 1.0287241148964597,
+      "grad_norm": 0.33826273679733276,
+      "learning_rate": 0.0002,
+      "loss": 1.7008,
+      "step": 770
+    },
+    {
+      "epoch": 1.0420841683366733,
+      "grad_norm": 0.44682955741882324,
+      "learning_rate": 0.0002,
+      "loss": 1.809,
+      "step": 780
+    },
+    {
+      "epoch": 1.0554442217768871,
+      "grad_norm": 0.422188401222229,
+      "learning_rate": 0.0002,
+      "loss": 1.7092,
+      "step": 790
+    },
+    {
+      "epoch": 1.0688042752171008,
+      "grad_norm": 0.3809906244277954,
+      "learning_rate": 0.0002,
+      "loss": 1.7765,
+      "step": 800
+    },
+    {
+      "epoch": 1.0821643286573146,
+      "grad_norm": 0.3454349637031555,
+      "learning_rate": 0.0002,
+      "loss": 1.7431,
+      "step": 810
+    },
+    {
+      "epoch": 1.0955243820975284,
+      "grad_norm": 0.3767355978488922,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 820
+    },
+    {
+      "epoch": 1.108884435537742,
+      "grad_norm": 0.3361407518386841,
+      "learning_rate": 0.0002,
+      "loss": 1.7224,
+      "step": 830
+    },
+    {
+      "epoch": 1.122244488977956,
+      "grad_norm": 0.3654632568359375,
+      "learning_rate": 0.0002,
+      "loss": 1.7509,
+      "step": 840
+    },
+    {
+      "epoch": 1.1356045424181698,
+      "grad_norm": 0.3822861313819885,
+      "learning_rate": 0.0002,
+      "loss": 1.7151,
+      "step": 850
+    },
+    {
+      "epoch": 1.1489645958583834,
+      "grad_norm": 0.3853831887245178,
+      "learning_rate": 0.0002,
+      "loss": 1.7121,
+      "step": 860
+    },
+    {
+      "epoch": 1.1623246492985972,
+      "grad_norm": 0.35521796345710754,
+      "learning_rate": 0.0002,
+      "loss": 1.7685,
+      "step": 870
+    },
+    {
+      "epoch": 1.1756847027388109,
+      "grad_norm": 0.4107200503349304,
+      "learning_rate": 0.0002,
+      "loss": 1.7735,
+      "step": 880
+    },
+    {
+      "epoch": 1.1890447561790247,
+      "grad_norm": 0.33219534158706665,
+      "learning_rate": 0.0002,
+      "loss": 1.7484,
+      "step": 890
+    },
+    {
+      "epoch": 1.2024048096192386,
+      "grad_norm": 0.3559704124927521,
+      "learning_rate": 0.0002,
+      "loss": 1.7071,
+      "step": 900
+    },
+    {
+      "epoch": 1.2157648630594522,
+      "grad_norm": 0.3700537383556366,
+      "learning_rate": 0.0002,
+      "loss": 1.7535,
+      "step": 910
+    },
+    {
+      "epoch": 1.229124916499666,
+      "grad_norm": 0.3771909475326538,
+      "learning_rate": 0.0002,
+      "loss": 1.7513,
+      "step": 920
+    },
+    {
+      "epoch": 1.2424849699398797,
+      "grad_norm": 0.3136613965034485,
+      "learning_rate": 0.0002,
+      "loss": 1.7566,
+      "step": 930
+    },
+    {
+      "epoch": 1.2558450233800935,
+      "grad_norm": 0.3952099084854126,
+      "learning_rate": 0.0002,
+      "loss": 1.6783,
+      "step": 940
+    },
+    {
+      "epoch": 1.2692050768203074,
+      "grad_norm": 0.36534377932548523,
+      "learning_rate": 0.0002,
+      "loss": 1.7691,
+      "step": 950
+    },
+    {
+      "epoch": 1.282565130260521,
+      "grad_norm": 0.3803492486476898,
+      "learning_rate": 0.0002,
+      "loss": 1.7127,
+      "step": 960
+    },
+    {
+      "epoch": 1.2959251837007348,
+      "grad_norm": 0.3992428183555603,
+      "learning_rate": 0.0002,
+      "loss": 1.7896,
+      "step": 970
+    },
+    {
+      "epoch": 1.3092852371409487,
+      "grad_norm": 0.3627142906188965,
+      "learning_rate": 0.0002,
+      "loss": 1.7343,
+      "step": 980
+    },
+    {
+      "epoch": 1.3226452905811623,
+      "grad_norm": 0.4248180091381073,
+      "learning_rate": 0.0002,
+      "loss": 1.7598,
+      "step": 990
+    },
+    {
+      "epoch": 1.3360053440213762,
+      "grad_norm": 0.4060308039188385,
+      "learning_rate": 0.0002,
+      "loss": 1.6896,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3493653974615898,
+      "grad_norm": 0.3788969814777374,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 1010
+    },
+    {
+      "epoch": 1.3627254509018036,
+      "grad_norm": 0.4174270033836365,
+      "learning_rate": 0.0002,
+      "loss": 1.7111,
+      "step": 1020
+    },
+    {
+      "epoch": 1.3760855043420173,
+      "grad_norm": 0.35500675439834595,
+      "learning_rate": 0.0002,
+      "loss": 1.7975,
+      "step": 1030
+    },
+    {
+      "epoch": 1.389445557782231,
+      "grad_norm": 0.3454059362411499,
+      "learning_rate": 0.0002,
+      "loss": 1.724,
+      "step": 1040
+    },
+    {
+      "epoch": 1.402805611222445,
+      "grad_norm": 0.45807570219039917,
+      "learning_rate": 0.0002,
+      "loss": 1.8299,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4161656646626586,
+      "grad_norm": 0.39338022470474243,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4295257181028724,
+      "grad_norm": 0.3870709240436554,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4428857715430863,
+      "grad_norm": 0.40996190905570984,
+      "learning_rate": 0.0002,
+      "loss": 1.6565,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4562458249833,
+      "grad_norm": 0.38762837648391724,
+      "learning_rate": 0.0002,
+      "loss": 1.7324,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4696058784235138,
+      "grad_norm": 0.36756977438926697,
+      "learning_rate": 0.0002,
+      "loss": 1.7362,
+      "step": 1100
+    },
+    {
+      "epoch": 1.4829659318637274,
+      "grad_norm": 0.4087235927581787,
+      "learning_rate": 0.0002,
+      "loss": 1.7451,
+      "step": 1110
+    },
+    {
+      "epoch": 1.4963259853039412,
+      "grad_norm": 0.3357745110988617,
+      "learning_rate": 0.0002,
+      "loss": 1.7114,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5096860387441549,
+      "grad_norm": 0.37486532330513,
+      "learning_rate": 0.0002,
+      "loss": 1.6877,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5230460921843687,
+      "grad_norm": 0.3387809991836548,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5364061456245826,
+      "grad_norm": 0.37462118268013,
+      "learning_rate": 0.0002,
+      "loss": 1.7169,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5497661990647962,
+      "grad_norm": 0.38575324416160583,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 1160
+    },
+    {
+      "epoch": 1.56312625250501,
+      "grad_norm": 0.3515765964984894,
+      "learning_rate": 0.0002,
+      "loss": 1.7438,
+      "step": 1170
+    },
+    {
+      "epoch": 1.5764863059452239,
+      "grad_norm": 0.39308643341064453,
+      "learning_rate": 0.0002,
+      "loss": 1.7524,
+      "step": 1180
+    },
+    {
+      "epoch": 1.5898463593854375,
+      "grad_norm": 0.3308864235877991,
+      "learning_rate": 0.0002,
+      "loss": 1.6422,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6032064128256514,
+      "grad_norm": 0.3397478461265564,
+      "learning_rate": 0.0002,
+      "loss": 1.7566,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6165664662658652,
+      "grad_norm": 0.3911525309085846,
+      "learning_rate": 0.0002,
+      "loss": 1.7871,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6299265197060788,
+      "grad_norm": 0.3771969974040985,
+      "learning_rate": 0.0002,
+      "loss": 1.7443,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6432865731462925,
+      "grad_norm": 0.35346856713294983,
+      "learning_rate": 0.0002,
+      "loss": 1.7631,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6566466265865063,
+      "grad_norm": 0.41736963391304016,
+      "learning_rate": 0.0002,
+      "loss": 1.7225,
+      "step": 1240
+    },
+    {
+      "epoch": 1.6700066800267201,
+      "grad_norm": 0.3375225067138672,
+      "learning_rate": 0.0002,
+      "loss": 1.7582,
+      "step": 1250
+    },
+    {
+      "epoch": 1.6833667334669338,
+      "grad_norm": 0.3779928982257843,
+      "learning_rate": 0.0002,
+      "loss": 1.6916,
+      "step": 1260
+    },
+    {
+      "epoch": 1.6967267869071476,
+      "grad_norm": 0.35388994216918945,
+      "learning_rate": 0.0002,
+      "loss": 1.728,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7100868403473615,
+      "grad_norm": 0.33884134888648987,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 1280
+    },
+    {
+      "epoch": 1.723446893787575,
+      "grad_norm": 0.35439756512641907,
+      "learning_rate": 0.0002,
+      "loss": 1.7083,
+      "step": 1290
+    },
+    {
+      "epoch": 1.736806947227789,
+      "grad_norm": 0.3766156733036041,
+      "learning_rate": 0.0002,
+      "loss": 1.7389,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7501670006680028,
+      "grad_norm": 0.36148911714553833,
+      "learning_rate": 0.0002,
+      "loss": 1.7847,
+      "step": 1310
+    },
+    {
+      "epoch": 1.7635270541082164,
+      "grad_norm": 0.39687496423721313,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 1320
+    },
+    {
+      "epoch": 1.77688710754843,
+      "grad_norm": 0.35639452934265137,
+      "learning_rate": 0.0002,
+      "loss": 1.7541,
+      "step": 1330
+    },
+    {
+      "epoch": 1.7902471609886441,
+      "grad_norm": 0.38781628012657166,
+      "learning_rate": 0.0002,
+      "loss": 1.7254,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8036072144288577,
+      "grad_norm": 0.42784637212753296,
+      "learning_rate": 0.0002,
+      "loss": 1.7867,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8169672678690714,
+      "grad_norm": 0.40258511900901794,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8303273213092852,
+      "grad_norm": 0.36674195528030396,
+      "learning_rate": 0.0002,
+      "loss": 1.7771,
+      "step": 1370
+    },
+    {
+      "epoch": 1.843687374749499,
+      "grad_norm": 0.4064558446407318,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8570474281897127,
+      "grad_norm": 0.3669849932193756,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1390
+    },
+    {
+      "epoch": 1.8704074816299265,
+      "grad_norm": 0.37569567561149597,
+      "learning_rate": 0.0002,
+      "loss": 1.7924,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8837675350701404,
+      "grad_norm": 0.37307995557785034,
+      "learning_rate": 0.0002,
+      "loss": 1.7885,
+      "step": 1410
+    },
+    {
+      "epoch": 1.897127588510354,
+      "grad_norm": 0.3772695064544678,
+      "learning_rate": 0.0002,
+      "loss": 1.7548,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9104876419505676,
+      "grad_norm": 0.36993589997291565,
+      "learning_rate": 0.0002,
+      "loss": 1.7682,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9238476953907817,
+      "grad_norm": 0.3490557372570038,
+      "learning_rate": 0.0002,
+      "loss": 1.7249,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9372077488309953,
+      "grad_norm": 0.3716149628162384,
+      "learning_rate": 0.0002,
+      "loss": 1.7979,
+      "step": 1450
+    },
+    {
+      "epoch": 1.950567802271209,
+      "grad_norm": 0.39236098527908325,
+      "learning_rate": 0.0002,
+      "loss": 1.6664,
+      "step": 1460
+    },
+    {
+      "epoch": 1.9639278557114228,
+      "grad_norm": 0.37258651852607727,
+      "learning_rate": 0.0002,
+      "loss": 1.6852,
+      "step": 1470
+    },
+    {
+      "epoch": 1.9772879091516367,
+      "grad_norm": 0.36183077096939087,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 1480
+    },
+    {
+      "epoch": 1.9906479625918503,
+      "grad_norm": 0.3956947326660156,
+      "learning_rate": 0.0002,
+      "loss": 1.7055,
+      "step": 1490
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8132041692733765,
+      "eval_runtime": 38.6287,
+      "eval_samples_per_second": 13.332,
+      "eval_steps_per_second": 1.683,
+      "step": 1497
+    },
+    {
+      "epoch": 2.004008016032064,
+      "grad_norm": 0.34480565786361694,
+      "learning_rate": 0.0002,
+      "loss": 1.6791,
+      "step": 1500
+    },
+    {
+      "epoch": 2.017368069472278,
+      "grad_norm": 0.3418028652667999,
+      "learning_rate": 0.0002,
+      "loss": 1.6367,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0307281229124916,
+      "grad_norm": 0.4514467716217041,
+      "learning_rate": 0.0002,
+      "loss": 1.5827,
+      "step": 1520
+    },
+    {
+      "epoch": 2.0440881763527052,
+      "grad_norm": 0.4197506606578827,
+      "learning_rate": 0.0002,
+      "loss": 1.6365,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0574482297929193,
+      "grad_norm": 0.4134170711040497,
+      "learning_rate": 0.0002,
+      "loss": 1.6221,
+      "step": 1540
+    },
+    {
+      "epoch": 2.070808283233133,
+      "grad_norm": 0.43709826469421387,
+      "learning_rate": 0.0002,
+      "loss": 1.6876,
+      "step": 1550
+    },
+    {
+      "epoch": 2.0841683366733466,
+      "grad_norm": 0.4703378677368164,
+      "learning_rate": 0.0002,
+      "loss": 1.5779,
+      "step": 1560
+    },
+    {
+      "epoch": 2.0975283901135606,
+      "grad_norm": 0.4538188576698303,
+      "learning_rate": 0.0002,
+      "loss": 1.599,
+      "step": 1570
+    },
+    {
+      "epoch": 2.1108884435537743,
+      "grad_norm": 0.4649668037891388,
+      "learning_rate": 0.0002,
+      "loss": 1.6464,
+      "step": 1580
+    },
+    {
+      "epoch": 2.124248496993988,
+      "grad_norm": 0.42669883370399475,
+      "learning_rate": 0.0002,
+      "loss": 1.6348,
+      "step": 1590
+    },
+    {
+      "epoch": 2.1376085504342015,
+      "grad_norm": 0.43162038922309875,
+      "learning_rate": 0.0002,
+      "loss": 1.5838,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1509686038744156,
+      "grad_norm": 0.4294586479663849,
+      "learning_rate": 0.0002,
+      "loss": 1.6673,
+      "step": 1610
+    },
+    {
+      "epoch": 2.164328657314629,
+      "grad_norm": 0.4669102132320404,
+      "learning_rate": 0.0002,
+      "loss": 1.6024,
+      "step": 1620
+    },
+    {
+      "epoch": 2.177688710754843,
+      "grad_norm": 0.4188412129878998,
+      "learning_rate": 0.0002,
+      "loss": 1.659,
+      "step": 1630
+    },
+    {
+      "epoch": 2.191048764195057,
+      "grad_norm": 0.4662680923938751,
+      "learning_rate": 0.0002,
+      "loss": 1.625,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2044088176352705,
+      "grad_norm": 0.4020286500453949,
+      "learning_rate": 0.0002,
+      "loss": 1.6699,
+      "step": 1650
+    },
+    {
+      "epoch": 2.217768871075484,
+      "grad_norm": 0.41919606924057007,
+      "learning_rate": 0.0002,
+      "loss": 1.6284,
+      "step": 1660
+    },
+    {
+      "epoch": 2.231128924515698,
+      "grad_norm": 0.4644531309604645,
+      "learning_rate": 0.0002,
+      "loss": 1.6776,
+      "step": 1670
+    },
+    {
+      "epoch": 2.244488977955912,
+      "grad_norm": 0.4526427984237671,
+      "learning_rate": 0.0002,
+      "loss": 1.6711,
+      "step": 1680
+    },
+    {
+      "epoch": 2.2578490313961255,
+      "grad_norm": 0.45953166484832764,
+      "learning_rate": 0.0002,
+      "loss": 1.6058,
+      "step": 1690
+    },
+    {
+      "epoch": 2.2712090848363395,
+      "grad_norm": 0.4701860249042511,
+      "learning_rate": 0.0002,
+      "loss": 1.5979,
+      "step": 1700
+    },
+    {
+      "epoch": 2.284569138276553,
+      "grad_norm": 0.4749310612678528,
+      "learning_rate": 0.0002,
+      "loss": 1.6183,
+      "step": 1710
+    },
+    {
+      "epoch": 2.297929191716767,
+      "grad_norm": 0.45026102662086487,
+      "learning_rate": 0.0002,
+      "loss": 1.6703,
+      "step": 1720
+    },
+    {
+      "epoch": 2.3112892451569804,
+      "grad_norm": 0.4755004048347473,
+      "learning_rate": 0.0002,
+      "loss": 1.6386,
+      "step": 1730
+    },
+    {
+      "epoch": 2.3246492985971945,
+      "grad_norm": 0.4505726993083954,
+      "learning_rate": 0.0002,
+      "loss": 1.6365,
+      "step": 1740
+    },
+    {
+      "epoch": 2.338009352037408,
+      "grad_norm": 0.44464054703712463,
+      "learning_rate": 0.0002,
+      "loss": 1.589,
+      "step": 1750
+    },
+    {
+      "epoch": 2.3513694054776217,
+      "grad_norm": 0.4449476897716522,
+      "learning_rate": 0.0002,
+      "loss": 1.6139,
+      "step": 1760
+    },
+    {
+      "epoch": 2.364729458917836,
+      "grad_norm": 0.4216482937335968,
+      "learning_rate": 0.0002,
+      "loss": 1.7195,
+      "step": 1770
+    },
+    {
+      "epoch": 2.3780895123580494,
+      "grad_norm": 0.4379308521747589,
+      "learning_rate": 0.0002,
+      "loss": 1.7075,
+      "step": 1780
+    },
+    {
+      "epoch": 2.391449565798263,
+      "grad_norm": 0.41670042276382446,
+      "learning_rate": 0.0002,
+      "loss": 1.7024,
+      "step": 1790
+    },
+    {
+      "epoch": 2.404809619238477,
+      "grad_norm": 0.48089510202407837,
+      "learning_rate": 0.0002,
+      "loss": 1.5989,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4181696726786908,
+      "grad_norm": 0.4389738142490387,
+      "learning_rate": 0.0002,
+      "loss": 1.6313,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4315297261189044,
+      "grad_norm": 0.45293036103248596,
+      "learning_rate": 0.0002,
+      "loss": 1.5841,
+      "step": 1820
+    },
+    {
+      "epoch": 2.4448897795591185,
+      "grad_norm": 0.5211683511734009,
+      "learning_rate": 0.0002,
+      "loss": 1.6887,
+      "step": 1830
+    },
+    {
+      "epoch": 2.458249832999332,
+      "grad_norm": 0.4631884694099426,
+      "learning_rate": 0.0002,
+      "loss": 1.6599,
+      "step": 1840
+    },
+    {
+      "epoch": 2.4716098864395457,
+      "grad_norm": 0.4276818335056305,
+      "learning_rate": 0.0002,
+      "loss": 1.6537,
+      "step": 1850
+    },
+    {
+      "epoch": 2.4849699398797593,
+      "grad_norm": 0.477524071931839,
+      "learning_rate": 0.0002,
+      "loss": 1.6836,
+      "step": 1860
+    },
+    {
+      "epoch": 2.4983299933199734,
+      "grad_norm": 0.44860973954200745,
+      "learning_rate": 0.0002,
+      "loss": 1.66,
+      "step": 1870
+    },
+    {
+      "epoch": 2.511690046760187,
+      "grad_norm": 0.46413546800613403,
+      "learning_rate": 0.0002,
+      "loss": 1.6308,
+      "step": 1880
+    },
+    {
+      "epoch": 2.5250501002004007,
+      "grad_norm": 0.42487645149230957,
+      "learning_rate": 0.0002,
+      "loss": 1.6225,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5384101536406147,
+      "grad_norm": 0.4778307378292084,
+      "learning_rate": 0.0002,
+      "loss": 1.6268,
+      "step": 1900
+    },
+    {
+      "epoch": 2.5517702070808284,
+      "grad_norm": 0.45307061076164246,
+      "learning_rate": 0.0002,
+      "loss": 1.6143,
+      "step": 1910
+    },
+    {
+      "epoch": 2.565130260521042,
+      "grad_norm": 0.47886642813682556,
+      "learning_rate": 0.0002,
+      "loss": 1.7279,
+      "step": 1920
+    },
+    {
+      "epoch": 2.5784903139612556,
+      "grad_norm": 0.4839435815811157,
+      "learning_rate": 0.0002,
+      "loss": 1.5931,
+      "step": 1930
+    },
+    {
+      "epoch": 2.5918503674014697,
+      "grad_norm": 0.4388359785079956,
+      "learning_rate": 0.0002,
+      "loss": 1.6089,
+      "step": 1940
+    },
+    {
+      "epoch": 2.6052104208416833,
+      "grad_norm": 0.47859734296798706,
+      "learning_rate": 0.0002,
+      "loss": 1.6828,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6185704742818974,
+      "grad_norm": 0.5526517033576965,
+      "learning_rate": 0.0002,
+      "loss": 1.6014,
+      "step": 1960
+    },
+    {
+      "epoch": 2.631930527722111,
+      "grad_norm": 0.5449170470237732,
+      "learning_rate": 0.0002,
+      "loss": 1.6889,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6452905811623246,
+      "grad_norm": 0.48521968722343445,
+      "learning_rate": 0.0002,
+      "loss": 1.6481,
+      "step": 1980
+    },
+    {
+      "epoch": 2.6586506346025383,
+      "grad_norm": 0.4733737111091614,
+      "learning_rate": 0.0002,
+      "loss": 1.6741,
+      "step": 1990
+    },
+    {
+      "epoch": 2.6720106880427523,
+      "grad_norm": 0.507118284702301,
+      "learning_rate": 0.0002,
+      "loss": 1.662,
+      "step": 2000
+    },
+    {
+      "epoch": 2.685370741482966,
+      "grad_norm": 0.4508971571922302,
+      "learning_rate": 0.0002,
+      "loss": 1.6419,
+      "step": 2010
+    },
+    {
+      "epoch": 2.6987307949231796,
+      "grad_norm": 0.4657728672027588,
+      "learning_rate": 0.0002,
+      "loss": 1.7052,
+      "step": 2020
+    },
+    {
+      "epoch": 2.7120908483633936,
+      "grad_norm": 0.48647549748420715,
+      "learning_rate": 0.0002,
+      "loss": 1.6261,
+      "step": 2030
+    },
+    {
+      "epoch": 2.7254509018036073,
+      "grad_norm": 0.49525555968284607,
+      "learning_rate": 0.0002,
+      "loss": 1.5638,
+      "step": 2040
+    },
+    {
+      "epoch": 2.738810955243821,
+      "grad_norm": 0.4712379276752472,
+      "learning_rate": 0.0002,
+      "loss": 1.658,
+      "step": 2050
+    },
+    {
+      "epoch": 2.7521710086840345,
+      "grad_norm": 0.4846591055393219,
+      "learning_rate": 0.0002,
+      "loss": 1.6464,
+      "step": 2060
+    },
+    {
+      "epoch": 2.7655310621242486,
+      "grad_norm": 0.4823240041732788,
+      "learning_rate": 0.0002,
+      "loss": 1.5641,
+      "step": 2070
+    },
+    {
+      "epoch": 2.778891115564462,
+      "grad_norm": 0.4546685516834259,
+      "learning_rate": 0.0002,
+      "loss": 1.6701,
+      "step": 2080
+    },
+    {
+      "epoch": 2.7922511690046763,
+      "grad_norm": 0.45542681217193604,
+      "learning_rate": 0.0002,
+      "loss": 1.7015,
+      "step": 2090
+    },
+    {
+      "epoch": 2.80561122244489,
+      "grad_norm": 0.42137566208839417,
+      "learning_rate": 0.0002,
+      "loss": 1.6398,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8189712758851035,
+      "grad_norm": 0.6143282055854797,
+      "learning_rate": 0.0002,
+      "loss": 1.6526,
+      "step": 2110
+    },
+    {
+      "epoch": 2.832331329325317,
+      "grad_norm": 0.4828081727027893,
+      "learning_rate": 0.0002,
+      "loss": 1.6955,
+      "step": 2120
+    },
+    {
+      "epoch": 2.845691382765531,
+      "grad_norm": 0.4319005608558655,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 2130
+    },
+    {
+      "epoch": 2.859051436205745,
+      "grad_norm": 0.4297086298465729,
+      "learning_rate": 0.0002,
+      "loss": 1.6717,
+      "step": 2140
+    },
+    {
+      "epoch": 2.8724114896459585,
+      "grad_norm": 0.5011981129646301,
+      "learning_rate": 0.0002,
+      "loss": 1.5968,
+      "step": 2150
+    },
+    {
+      "epoch": 2.8857715430861726,
+      "grad_norm": 0.4401548504829407,
+      "learning_rate": 0.0002,
+      "loss": 1.7181,
+      "step": 2160
+    },
+    {
+      "epoch": 2.899131596526386,
+      "grad_norm": 0.48090746998786926,
+      "learning_rate": 0.0002,
+      "loss": 1.5722,
+      "step": 2170
+    },
+    {
+      "epoch": 2.9124916499666,
+      "grad_norm": 0.4740385413169861,
+      "learning_rate": 0.0002,
+      "loss": 1.6596,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9258517034068134,
+      "grad_norm": 0.5337260365486145,
+      "learning_rate": 0.0002,
+      "loss": 1.6501,
+      "step": 2190
+    },
+    {
+      "epoch": 2.9392117568470275,
+      "grad_norm": 0.4420052766799927,
+      "learning_rate": 0.0002,
+      "loss": 1.6802,
+      "step": 2200
+    },
+    {
+      "epoch": 2.952571810287241,
+      "grad_norm": 0.477512389421463,
+      "learning_rate": 0.0002,
+      "loss": 1.5474,
+      "step": 2210
+    },
+    {
+      "epoch": 2.9659318637274548,
+      "grad_norm": 0.5344052910804749,
+      "learning_rate": 0.0002,
+      "loss": 1.6544,
+      "step": 2220
+    },
+    {
+      "epoch": 2.979291917167669,
+      "grad_norm": 0.4483940303325653,
+      "learning_rate": 0.0002,
+      "loss": 1.6866,
+      "step": 2230
+    },
+    {
+      "epoch": 2.9926519706078825,
+      "grad_norm": 0.4366597831249237,
+      "learning_rate": 0.0002,
+      "loss": 1.6477,
+      "step": 2240
+    },
+    {
+      "epoch": 2.9993319973279893,
+      "eval_loss": 1.834012746810913,
+      "eval_runtime": 38.5659,
+      "eval_samples_per_second": 13.354,
+      "eval_steps_per_second": 1.685,
+      "step": 2245
+    },
+    {
+      "epoch": 3.006012024048096,
+      "grad_norm": 0.428824245929718,
+      "learning_rate": 0.0002,
+      "loss": 1.5582,
+      "step": 2250
+    },
+    {
+      "epoch": 3.01937207748831,
+      "grad_norm": 0.4870174825191498,
+      "learning_rate": 0.0002,
+      "loss": 1.499,
+      "step": 2260
+    },
+    {
+      "epoch": 3.032732130928524,
+      "grad_norm": 0.4684266149997711,
+      "learning_rate": 0.0002,
+      "loss": 1.4872,
+      "step": 2270
+    },
+    {
+      "epoch": 3.0460921843687374,
+      "grad_norm": 0.581604540348053,
+      "learning_rate": 0.0002,
+      "loss": 1.5284,
+      "step": 2280
+    },
+    {
+      "epoch": 3.059452237808951,
+      "grad_norm": 0.5561677813529968,
+      "learning_rate": 0.0002,
+      "loss": 1.4549,
+      "step": 2290
+    },
+    {
+      "epoch": 3.072812291249165,
+      "grad_norm": 0.5750220417976379,
+      "learning_rate": 0.0002,
+      "loss": 1.4903,
+      "step": 2300
+    },
+    {
+      "epoch": 3.0861723446893787,
+      "grad_norm": 0.5704626441001892,
+      "learning_rate": 0.0002,
+      "loss": 1.5903,
+      "step": 2310
+    },
+    {
+      "epoch": 3.0995323981295924,
+      "grad_norm": 0.6242083311080933,
+      "learning_rate": 0.0002,
+      "loss": 1.4292,
+      "step": 2320
+    },
+    {
+      "epoch": 3.1128924515698064,
+      "grad_norm": 0.5174121260643005,
+      "learning_rate": 0.0002,
+      "loss": 1.5092,
+      "step": 2330
+    },
+    {
+      "epoch": 3.12625250501002,
+      "grad_norm": 0.5697633028030396,
+      "learning_rate": 0.0002,
+      "loss": 1.5106,
+      "step": 2340
+    },
+    {
+      "epoch": 3.1396125584502337,
+      "grad_norm": 0.5969541072845459,
+      "learning_rate": 0.0002,
+      "loss": 1.5156,
+      "step": 2350
+    },
+    {
+      "epoch": 3.1529726118904478,
+      "grad_norm": 0.6244304180145264,
+      "learning_rate": 0.0002,
+      "loss": 1.52,
+      "step": 2360
+    },
+    {
+      "epoch": 3.1663326653306614,
+      "grad_norm": 0.5561705827713013,
+      "learning_rate": 0.0002,
+      "loss": 1.5244,
+      "step": 2370
+    },
+    {
+      "epoch": 3.179692718770875,
+      "grad_norm": 0.5401188135147095,
+      "learning_rate": 0.0002,
+      "loss": 1.6169,
+      "step": 2380
+    },
+    {
+      "epoch": 3.1930527722110886,
+      "grad_norm": 0.6450421810150146,
+      "learning_rate": 0.0002,
+      "loss": 1.5387,
+      "step": 2390
+    },
+    {
+      "epoch": 3.2064128256513027,
+      "grad_norm": 0.5741903185844421,
+      "learning_rate": 0.0002,
+      "loss": 1.4839,
+      "step": 2400
+    },
+    {
+      "epoch": 3.2197728790915163,
+      "grad_norm": 0.6337407231330872,
+      "learning_rate": 0.0002,
+      "loss": 1.5584,
+      "step": 2410
+    },
+    {
+      "epoch": 3.23313293253173,
+      "grad_norm": 0.6493517160415649,
+      "learning_rate": 0.0002,
+      "loss": 1.5025,
+      "step": 2420
+    },
+    {
+      "epoch": 3.246492985971944,
+      "grad_norm": 0.6230176091194153,
+      "learning_rate": 0.0002,
+      "loss": 1.5168,
+      "step": 2430
+    },
+    {
+      "epoch": 3.2598530394121576,
+      "grad_norm": 0.680704653263092,
+      "learning_rate": 0.0002,
+      "loss": 1.5408,
+      "step": 2440
+    },
+    {
+      "epoch": 3.2732130928523713,
+      "grad_norm": 0.5279417037963867,
+      "learning_rate": 0.0002,
+      "loss": 1.6005,
+      "step": 2450
+    },
+    {
+      "epoch": 3.2865731462925853,
+      "grad_norm": 0.5601515173912048,
+      "learning_rate": 0.0002,
+      "loss": 1.5231,
+      "step": 2460
+    },
+    {
+      "epoch": 3.299933199732799,
+      "grad_norm": 0.5591090321540833,
+      "learning_rate": 0.0002,
+      "loss": 1.4949,
+      "step": 2470
+    },
+    {
+      "epoch": 3.3132932531730126,
+      "grad_norm": 0.6596529483795166,
+      "learning_rate": 0.0002,
+      "loss": 1.5181,
+      "step": 2480
+    },
+    {
+      "epoch": 3.3266533066132267,
+      "grad_norm": 0.6115918755531311,
+      "learning_rate": 0.0002,
+      "loss": 1.5259,
+      "step": 2490
+    },
+    {
+      "epoch": 3.3400133600534403,
+      "grad_norm": 0.6443548202514648,
+      "learning_rate": 0.0002,
+      "loss": 1.5344,
+      "step": 2500
+    },
+    {
+      "epoch": 3.353373413493654,
+      "grad_norm": 0.5504242181777954,
+      "learning_rate": 0.0002,
+      "loss": 1.5037,
+      "step": 2510
+    },
+    {
+      "epoch": 3.3667334669338675,
+      "grad_norm": 0.6104483604431152,
+      "learning_rate": 0.0002,
+      "loss": 1.5049,
+      "step": 2520
+    },
+    {
+      "epoch": 3.3800935203740816,
+      "grad_norm": 0.8387531638145447,
+      "learning_rate": 0.0002,
+      "loss": 1.587,
+      "step": 2530
+    },
+    {
+      "epoch": 3.3934535738142952,
+      "grad_norm": 0.6346094012260437,
+      "learning_rate": 0.0002,
+      "loss": 1.5227,
+      "step": 2540
+    },
+    {
+      "epoch": 3.406813627254509,
+      "grad_norm": 0.6261265873908997,
+      "learning_rate": 0.0002,
+      "loss": 1.4855,
+      "step": 2550
+    },
+    {
+      "epoch": 3.420173680694723,
+      "grad_norm": 0.5960372090339661,
+      "learning_rate": 0.0002,
+      "loss": 1.5233,
+      "step": 2560
+    },
+    {
+      "epoch": 3.4335337341349366,
+      "grad_norm": 0.5291280746459961,
+      "learning_rate": 0.0002,
+      "loss": 1.5153,
+      "step": 2570
+    },
+    {
+      "epoch": 3.44689378757515,
+      "grad_norm": 0.6133161783218384,
+      "learning_rate": 0.0002,
+      "loss": 1.5152,
+      "step": 2580
+    },
+    {
+      "epoch": 3.460253841015364,
+      "grad_norm": 0.623573362827301,
+      "learning_rate": 0.0002,
+      "loss": 1.5533,
+      "step": 2590
+    },
+    {
+      "epoch": 3.473613894455578,
+      "grad_norm": 0.5959834456443787,
+      "learning_rate": 0.0002,
+      "loss": 1.4935,
+      "step": 2600
+    },
+    {
+      "epoch": 3.4869739478957915,
+      "grad_norm": 0.583332359790802,
+      "learning_rate": 0.0002,
+      "loss": 1.5792,
+      "step": 2610
+    },
+    {
+      "epoch": 3.5003340013360056,
+      "grad_norm": 0.6003559231758118,
+      "learning_rate": 0.0002,
+      "loss": 1.5229,
+      "step": 2620
+    },
+    {
+      "epoch": 3.513694054776219,
+      "grad_norm": 0.5832992196083069,
+      "learning_rate": 0.0002,
+      "loss": 1.4901,
+      "step": 2630
+    },
+    {
+      "epoch": 3.527054108216433,
+      "grad_norm": 0.5942609906196594,
+      "learning_rate": 0.0002,
+      "loss": 1.5005,
+      "step": 2640
+    },
+    {
+      "epoch": 3.5404141616566465,
+      "grad_norm": 0.6087163686752319,
+      "learning_rate": 0.0002,
+      "loss": 1.5213,
+      "step": 2650
+    },
+    {
+      "epoch": 3.5537742150968605,
+      "grad_norm": 0.631948709487915,
+      "learning_rate": 0.0002,
+      "loss": 1.5826,
+      "step": 2660
+    },
+    {
+      "epoch": 3.567134268537074,
+      "grad_norm": 0.6450803279876709,
+      "learning_rate": 0.0002,
+      "loss": 1.5844,
+      "step": 2670
+    },
+    {
+      "epoch": 3.580494321977288,
+      "grad_norm": 0.6507797837257385,
+      "learning_rate": 0.0002,
+      "loss": 1.4981,
+      "step": 2680
+    },
+    {
+      "epoch": 3.593854375417502,
+      "grad_norm": 0.5778017044067383,
+      "learning_rate": 0.0002,
+      "loss": 1.5826,
+      "step": 2690
+    },
+    {
+      "epoch": 3.6072144288577155,
+      "grad_norm": 0.6214032173156738,
+      "learning_rate": 0.0002,
+      "loss": 1.4688,
+      "step": 2700
+    },
+    {
+      "epoch": 3.620574482297929,
+      "grad_norm": 0.5681133270263672,
+      "learning_rate": 0.0002,
+      "loss": 1.5084,
+      "step": 2710
+    },
+    {
+      "epoch": 3.6339345357381427,
+      "grad_norm": 0.6074244976043701,
+      "learning_rate": 0.0002,
+      "loss": 1.471,
+      "step": 2720
+    },
+    {
+      "epoch": 3.647294589178357,
+      "grad_norm": 0.5900560617446899,
+      "learning_rate": 0.0002,
+      "loss": 1.5243,
+      "step": 2730
+    },
+    {
+      "epoch": 3.6606546426185704,
+      "grad_norm": 0.5817505717277527,
+      "learning_rate": 0.0002,
+      "loss": 1.5074,
+      "step": 2740
+    },
+    {
+      "epoch": 3.6740146960587845,
+      "grad_norm": 0.6095547676086426,
+      "learning_rate": 0.0002,
+      "loss": 1.5117,
+      "step": 2750
+    },
+    {
+      "epoch": 3.687374749498998,
+      "grad_norm": 0.612790584564209,
+      "learning_rate": 0.0002,
+      "loss": 1.5117,
+      "step": 2760
+    },
+    {
+      "epoch": 3.7007348029392118,
+      "grad_norm": 0.6574140787124634,
+      "learning_rate": 0.0002,
+      "loss": 1.4976,
+      "step": 2770
+    },
+    {
+      "epoch": 3.7140948563794254,
+      "grad_norm": 0.5643761157989502,
+      "learning_rate": 0.0002,
+      "loss": 1.5306,
+      "step": 2780
+    },
+    {
+      "epoch": 3.727454909819639,
+      "grad_norm": 0.5652621388435364,
+      "learning_rate": 0.0002,
+      "loss": 1.5751,
+      "step": 2790
+    },
+    {
+      "epoch": 3.740814963259853,
+      "grad_norm": 0.5604206323623657,
+      "learning_rate": 0.0002,
+      "loss": 1.5262,
+      "step": 2800
+    },
+    {
+      "epoch": 3.7541750167000667,
+      "grad_norm": 3.911022663116455,
+      "learning_rate": 0.0002,
+      "loss": 1.5013,
+      "step": 2810
+    },
+    {
+      "epoch": 3.7675350701402808,
+      "grad_norm": 0.6148333549499512,
+      "learning_rate": 0.0002,
+      "loss": 1.5793,
+      "step": 2820
+    },
+    {
+      "epoch": 3.7808951235804944,
+      "grad_norm": 0.5605677962303162,
+      "learning_rate": 0.0002,
+      "loss": 1.5122,
+      "step": 2830
+    },
+    {
+      "epoch": 3.794255177020708,
+      "grad_norm": 0.6101965308189392,
+      "learning_rate": 0.0002,
+      "loss": 1.5659,
+      "step": 2840
+    },
+    {
+      "epoch": 3.8076152304609217,
+      "grad_norm": 0.5387342572212219,
+      "learning_rate": 0.0002,
+      "loss": 1.5618,
+      "step": 2850
+    },
+    {
+      "epoch": 3.8209752839011357,
+      "grad_norm": 0.5733087062835693,
+      "learning_rate": 0.0002,
+      "loss": 1.5193,
+      "step": 2860
+    },
+    {
+      "epoch": 3.8343353373413493,
+      "grad_norm": 0.6538485884666443,
+      "learning_rate": 0.0002,
+      "loss": 1.5545,
+      "step": 2870
+    },
+    {
+      "epoch": 3.847695390781563,
+      "grad_norm": 0.6247632503509521,
+      "learning_rate": 0.0002,
+      "loss": 1.523,
+      "step": 2880
+    },
+    {
+      "epoch": 3.861055444221777,
+      "grad_norm": 0.5745735764503479,
+      "learning_rate": 0.0002,
+      "loss": 1.5591,
+      "step": 2890
+    },
+    {
+      "epoch": 3.8744154976619907,
+      "grad_norm": 0.5942763686180115,
+      "learning_rate": 0.0002,
+      "loss": 1.5706,
+      "step": 2900
+    },
+    {
+      "epoch": 3.8877755511022043,
+      "grad_norm": 0.7086281776428223,
+      "learning_rate": 0.0002,
+      "loss": 1.564,
+      "step": 2910
+    },
+    {
+      "epoch": 3.901135604542418,
+      "grad_norm": 0.8825129866600037,
+      "learning_rate": 0.0002,
+      "loss": 1.5526,
+      "step": 2920
+    },
+    {
+      "epoch": 3.914495657982632,
+      "grad_norm": 0.6260842680931091,
+      "learning_rate": 0.0002,
+      "loss": 1.4519,
+      "step": 2930
+    },
+    {
+      "epoch": 3.9278557114228456,
+      "grad_norm": 0.6015968322753906,
+      "learning_rate": 0.0002,
+      "loss": 1.5433,
+      "step": 2940
+    },
+    {
+      "epoch": 3.9412157648630597,
+      "grad_norm": 0.7042809128761292,
+      "learning_rate": 0.0002,
+      "loss": 1.4931,
+      "step": 2950
+    },
+    {
+      "epoch": 3.9545758183032733,
+      "grad_norm": 0.5860083699226379,
+      "learning_rate": 0.0002,
+      "loss": 1.5596,
+      "step": 2960
+    },
+    {
+      "epoch": 3.967935871743487,
+      "grad_norm": 0.5939757823944092,
+      "learning_rate": 0.0002,
+      "loss": 1.565,
+      "step": 2970
+    },
+    {
+      "epoch": 3.9812959251837006,
+      "grad_norm": 0.5523964166641235,
+      "learning_rate": 0.0002,
+      "loss": 1.408,
+      "step": 2980
+    },
+    {
+      "epoch": 3.9946559786239146,
+      "grad_norm": 0.6380264759063721,
+      "learning_rate": 0.0002,
+      "loss": 1.5629,
+      "step": 2990
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.8875294923782349,
+      "eval_runtime": 38.5837,
+      "eval_samples_per_second": 13.348,
+      "eval_steps_per_second": 1.685,
+      "step": 2994
+    },
+    {
+      "epoch": 4.008016032064128,
+      "grad_norm": 0.5478564500808716,
+      "learning_rate": 0.0002,
+      "loss": 1.4002,
+      "step": 3000
+    },
+    {
+      "epoch": 4.021376085504342,
+      "grad_norm": 0.9384379982948303,
+      "learning_rate": 0.0002,
+      "loss": 1.436,
+      "step": 3010
+    },
+    {
+      "epoch": 4.034736138944556,
+      "grad_norm": 0.7819344401359558,
+      "learning_rate": 0.0002,
+      "loss": 1.4127,
+      "step": 3020
+    },
+    {
+      "epoch": 4.04809619238477,
+      "grad_norm": 0.7737417817115784,
+      "learning_rate": 0.0002,
+      "loss": 1.326,
+      "step": 3030
+    },
+    {
+      "epoch": 4.061456245824983,
+      "grad_norm": 0.8893805742263794,
+      "learning_rate": 0.0002,
+      "loss": 1.3203,
+      "step": 3040
+    },
+    {
+      "epoch": 4.074816299265197,
+      "grad_norm": 0.7759843468666077,
+      "learning_rate": 0.0002,
+      "loss": 1.3913,
+      "step": 3050
+    },
+    {
+      "epoch": 4.0881763527054105,
+      "grad_norm": 0.642654538154602,
+      "learning_rate": 0.0002,
+      "loss": 1.2941,
+      "step": 3060
+    },
+    {
+      "epoch": 4.101536406145625,
+      "grad_norm": 0.8515549302101135,
+      "learning_rate": 0.0002,
+      "loss": 1.3204,
+      "step": 3070
+    },
+    {
+      "epoch": 4.114896459585839,
+      "grad_norm": 0.7033658623695374,
+      "learning_rate": 0.0002,
+      "loss": 1.3683,
+      "step": 3080
+    },
+    {
+      "epoch": 4.128256513026052,
+      "grad_norm": 0.7063882946968079,
+      "learning_rate": 0.0002,
+      "loss": 1.4159,
+      "step": 3090
+    },
+    {
+      "epoch": 4.141616566466266,
+      "grad_norm": 0.6946853995323181,
+      "learning_rate": 0.0002,
+      "loss": 1.384,
+      "step": 3100
+    },
+    {
+      "epoch": 4.1549766199064795,
+      "grad_norm": 0.7286741137504578,
+      "learning_rate": 0.0002,
+      "loss": 1.3689,
+      "step": 3110
+    },
+    {
+      "epoch": 4.168336673346693,
+      "grad_norm": 0.7894193530082703,
+      "learning_rate": 0.0002,
+      "loss": 1.3061,
+      "step": 3120
+    },
+    {
+      "epoch": 4.181696726786907,
+      "grad_norm": 0.7005895376205444,
+      "learning_rate": 0.0002,
+      "loss": 1.3346,
+      "step": 3130
+    },
+    {
+      "epoch": 4.195056780227121,
+      "grad_norm": 0.799567461013794,
+      "learning_rate": 0.0002,
+      "loss": 1.3834,
+      "step": 3140
+    },
+    {
+      "epoch": 4.208416833667335,
+      "grad_norm": 0.7010157108306885,
+      "learning_rate": 0.0002,
+      "loss": 1.3813,
+      "step": 3150
+    },
+    {
+      "epoch": 4.2217768871075485,
+      "grad_norm": 0.7489650249481201,
+      "learning_rate": 0.0002,
+      "loss": 1.3637,
+      "step": 3160
+    },
+    {
+      "epoch": 4.235136940547762,
+      "grad_norm": 0.7908048629760742,
+      "learning_rate": 0.0002,
+      "loss": 1.3546,
+      "step": 3170
+    },
+    {
+      "epoch": 4.248496993987976,
+      "grad_norm": 0.7002180814743042,
+      "learning_rate": 0.0002,
+      "loss": 1.3073,
+      "step": 3180
+    },
+    {
+      "epoch": 4.261857047428189,
+      "grad_norm": 0.8339495062828064,
+      "learning_rate": 0.0002,
+      "loss": 1.4525,
+      "step": 3190
+    },
+    {
+      "epoch": 4.275217100868403,
+      "grad_norm": 0.7884618043899536,
+      "learning_rate": 0.0002,
+      "loss": 1.3471,
+      "step": 3200
+    },
+    {
+      "epoch": 4.2885771543086175,
+      "grad_norm": 0.7964122295379639,
+      "learning_rate": 0.0002,
+      "loss": 1.4261,
+      "step": 3210
+    },
+    {
+      "epoch": 4.301937207748831,
+      "grad_norm": 0.838646650314331,
+      "learning_rate": 0.0002,
+      "loss": 1.3506,
+      "step": 3220
+    },
+    {
+      "epoch": 4.315297261189045,
+      "grad_norm": 0.8063107132911682,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 3230
+    },
+    {
+      "epoch": 4.328657314629258,
+      "grad_norm": 0.8147385120391846,
+      "learning_rate": 0.0002,
+      "loss": 1.3769,
+      "step": 3240
+    },
+    {
+      "epoch": 4.342017368069472,
+      "grad_norm": 0.7636798620223999,
+      "learning_rate": 0.0002,
+      "loss": 1.4118,
+      "step": 3250
+    },
+    {
+      "epoch": 4.355377421509686,
+      "grad_norm": 0.7530609965324402,
+      "learning_rate": 0.0002,
+      "loss": 1.3698,
+      "step": 3260
+    },
+    {
+      "epoch": 4.3687374749499,
+      "grad_norm": 0.8853573799133301,
+      "learning_rate": 0.0002,
+      "loss": 1.3507,
+      "step": 3270
+    },
+    {
+      "epoch": 4.382097528390114,
+      "grad_norm": 0.7180975675582886,
+      "learning_rate": 0.0002,
+      "loss": 1.3614,
+      "step": 3280
+    },
+    {
+      "epoch": 4.395457581830327,
+      "grad_norm": 0.837150514125824,
+      "learning_rate": 0.0002,
+      "loss": 1.4119,
+      "step": 3290
+    },
+    {
+      "epoch": 4.408817635270541,
+      "grad_norm": 0.8370638489723206,
+      "learning_rate": 0.0002,
+      "loss": 1.461,
+      "step": 3300
+    },
+    {
+      "epoch": 4.422177688710755,
+      "grad_norm": 0.7738229036331177,
+      "learning_rate": 0.0002,
+      "loss": 1.4478,
+      "step": 3310
+    },
+    {
+      "epoch": 4.435537742150968,
+      "grad_norm": 0.7665290832519531,
+      "learning_rate": 0.0002,
+      "loss": 1.4195,
+      "step": 3320
+    },
+    {
+      "epoch": 4.448897795591183,
+      "grad_norm": 0.7547745704650879,
+      "learning_rate": 0.0002,
+      "loss": 1.3308,
+      "step": 3330
+    },
+    {
+      "epoch": 4.462257849031396,
+      "grad_norm": 0.7421861290931702,
+      "learning_rate": 0.0002,
+      "loss": 1.4165,
+      "step": 3340
+    },
+    {
+      "epoch": 4.47561790247161,
+      "grad_norm": 0.8042104244232178,
+      "learning_rate": 0.0002,
+      "loss": 1.4244,
+      "step": 3350
+    },
+    {
+      "epoch": 4.488977955911824,
+      "grad_norm": 0.8111839890480042,
+      "learning_rate": 0.0002,
+      "loss": 1.365,
+      "step": 3360
+    },
+    {
+      "epoch": 4.502338009352037,
+      "grad_norm": 0.7998340129852295,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 3370
+    },
+    {
+      "epoch": 4.515698062792251,
+      "grad_norm": 0.7668877243995667,
+      "learning_rate": 0.0002,
+      "loss": 1.3812,
+      "step": 3380
+    },
+    {
+      "epoch": 4.529058116232465,
+      "grad_norm": 0.7986718416213989,
+      "learning_rate": 0.0002,
+      "loss": 1.3972,
+      "step": 3390
+    },
+    {
+      "epoch": 4.542418169672679,
+      "grad_norm": 0.6806602478027344,
+      "learning_rate": 0.0002,
+      "loss": 1.3582,
+      "step": 3400
+    },
+    {
+      "epoch": 4.555778223112893,
+      "grad_norm": 0.8788819909095764,
+      "learning_rate": 0.0002,
+      "loss": 1.3942,
+      "step": 3410
+    },
+    {
+      "epoch": 4.569138276553106,
+      "grad_norm": 0.7499664425849915,
+      "learning_rate": 0.0002,
+      "loss": 1.3379,
+      "step": 3420
+    },
+    {
+      "epoch": 4.58249832999332,
+      "grad_norm": 0.7967109084129333,
+      "learning_rate": 0.0002,
+      "loss": 1.3823,
+      "step": 3430
+    },
+    {
+      "epoch": 4.595858383433534,
+      "grad_norm": 0.759639322757721,
+      "learning_rate": 0.0002,
+      "loss": 1.3531,
+      "step": 3440
+    },
+    {
+      "epoch": 4.609218436873747,
+      "grad_norm": 0.8327916264533997,
+      "learning_rate": 0.0002,
+      "loss": 1.3517,
+      "step": 3450
+    },
+    {
+      "epoch": 4.622578490313961,
+      "grad_norm": 0.7400892376899719,
+      "learning_rate": 0.0002,
+      "loss": 1.4619,
+      "step": 3460
+    },
+    {
+      "epoch": 4.635938543754175,
+      "grad_norm": 0.8116602301597595,
+      "learning_rate": 0.0002,
+      "loss": 1.3374,
+      "step": 3470
+    },
+    {
+      "epoch": 4.649298597194389,
+      "grad_norm": 0.7604362368583679,
+      "learning_rate": 0.0002,
+      "loss": 1.4445,
+      "step": 3480
+    },
+    {
+      "epoch": 4.662658650634603,
+      "grad_norm": 0.7397996783256531,
+      "learning_rate": 0.0002,
+      "loss": 1.3724,
+      "step": 3490
+    },
+    {
+      "epoch": 4.676018704074816,
+      "grad_norm": 0.869293749332428,
+      "learning_rate": 0.0002,
+      "loss": 1.4048,
+      "step": 3500
+    },
+    {
+      "epoch": 4.68937875751503,
+      "grad_norm": 0.6854358315467834,
+      "learning_rate": 0.0002,
+      "loss": 1.3873,
+      "step": 3510
+    },
+    {
+      "epoch": 4.7027388109552435,
+      "grad_norm": 0.8326661586761475,
+      "learning_rate": 0.0002,
+      "loss": 1.3413,
+      "step": 3520
+    },
+    {
+      "epoch": 4.716098864395457,
+      "grad_norm": 0.6887506246566772,
+      "learning_rate": 0.0002,
+      "loss": 1.3666,
+      "step": 3530
+    },
+    {
+      "epoch": 4.729458917835672,
+      "grad_norm": 3.837689161300659,
+      "learning_rate": 0.0002,
+      "loss": 1.4508,
+      "step": 3540
+    },
+    {
+      "epoch": 4.742818971275885,
+      "grad_norm": 0.6874563694000244,
+      "learning_rate": 0.0002,
+      "loss": 1.3775,
+      "step": 3550
+    },
+    {
+      "epoch": 4.756179024716099,
+      "grad_norm": 0.8340407609939575,
+      "learning_rate": 0.0002,
+      "loss": 1.3643,
+      "step": 3560
+    },
+    {
+      "epoch": 4.7695390781563125,
+      "grad_norm": 0.7286418676376343,
+      "learning_rate": 0.0002,
+      "loss": 1.3556,
+      "step": 3570
+    },
+    {
+      "epoch": 4.782899131596526,
+      "grad_norm": 0.7239373326301575,
+      "learning_rate": 0.0002,
+      "loss": 1.4338,
+      "step": 3580
+    },
+    {
+      "epoch": 4.796259185036741,
+      "grad_norm": 0.831310510635376,
+      "learning_rate": 0.0002,
+      "loss": 1.4697,
+      "step": 3590
+    },
+    {
+      "epoch": 4.809619238476954,
+      "grad_norm": 0.767715573310852,
+      "learning_rate": 0.0002,
+      "loss": 1.4146,
+      "step": 3600
+    },
+    {
+      "epoch": 4.822979291917168,
+      "grad_norm": 0.9013199210166931,
+      "learning_rate": 0.0002,
+      "loss": 1.4199,
+      "step": 3610
+    },
+    {
+      "epoch": 4.8363393453573815,
+      "grad_norm": 0.7543512582778931,
+      "learning_rate": 0.0002,
+      "loss": 1.4513,
+      "step": 3620
+    },
+    {
+      "epoch": 4.849699398797595,
+      "grad_norm": 0.7626057267189026,
+      "learning_rate": 0.0002,
+      "loss": 1.4218,
+      "step": 3630
+    },
+    {
+      "epoch": 4.863059452237809,
+      "grad_norm": 0.847079336643219,
+      "learning_rate": 0.0002,
+      "loss": 1.4102,
+      "step": 3640
+    },
+    {
+      "epoch": 4.876419505678022,
+      "grad_norm": 0.8273295760154724,
+      "learning_rate": 0.0002,
+      "loss": 1.5014,
+      "step": 3650
+    },
+    {
+      "epoch": 4.889779559118237,
+      "grad_norm": 0.7675244808197021,
+      "learning_rate": 0.0002,
+      "loss": 1.3806,
+      "step": 3660
+    },
+    {
+      "epoch": 4.9031396125584505,
+      "grad_norm": 0.9560356736183167,
+      "learning_rate": 0.0002,
+      "loss": 1.4894,
+      "step": 3670
+    },
+    {
+      "epoch": 4.916499665998664,
+      "grad_norm": 0.7682451605796814,
+      "learning_rate": 0.0002,
+      "loss": 1.4044,
+      "step": 3680
+    },
+    {
+      "epoch": 4.929859719438878,
+      "grad_norm": 0.8113830089569092,
+      "learning_rate": 0.0002,
+      "loss": 1.342,
+      "step": 3690
+    },
+    {
+      "epoch": 4.943219772879091,
+      "grad_norm": 0.7642542719841003,
+      "learning_rate": 0.0002,
+      "loss": 1.3559,
+      "step": 3700
+    },
+    {
+      "epoch": 4.956579826319305,
+      "grad_norm": 0.823863685131073,
+      "learning_rate": 0.0002,
+      "loss": 1.403,
+      "step": 3710
+    },
+    {
+      "epoch": 4.969939879759519,
+      "grad_norm": 0.8287797570228577,
+      "learning_rate": 0.0002,
+      "loss": 1.464,
+      "step": 3720
+    },
+    {
+      "epoch": 4.983299933199733,
+      "grad_norm": 0.778170108795166,
+      "learning_rate": 0.0002,
+      "loss": 1.4139,
+      "step": 3730
+    },
+    {
+      "epoch": 4.996659986639947,
+      "grad_norm": 0.7464073896408081,
+      "learning_rate": 0.0002,
+      "loss": 1.4218,
+      "step": 3740
+    },
+    {
+      "epoch": 4.999331997327989,
+      "eval_loss": 1.9638569355010986,
+      "eval_runtime": 38.5725,
+      "eval_samples_per_second": 13.351,
+      "eval_steps_per_second": 1.685,
+      "step": 3742
+    },
+    {
+      "epoch": 5.01002004008016,
+      "grad_norm": 0.8864085078239441,
+      "learning_rate": 0.0002,
+      "loss": 1.225,
+      "step": 3750
+    },
+    {
+      "epoch": 5.023380093520374,
+      "grad_norm": 0.9191637635231018,
+      "learning_rate": 0.0002,
+      "loss": 1.2056,
+      "step": 3760
+    },
+    {
+      "epoch": 5.036740146960588,
+      "grad_norm": 0.749519407749176,
+      "learning_rate": 0.0002,
+      "loss": 1.2453,
+      "step": 3770
+    },
+    {
+      "epoch": 5.050100200400801,
+      "grad_norm": 0.7916892170906067,
+      "learning_rate": 0.0002,
+      "loss": 1.1959,
+      "step": 3780
+    },
+    {
+      "epoch": 5.063460253841015,
+      "grad_norm": 1.0318909883499146,
+      "learning_rate": 0.0002,
+      "loss": 1.2279,
+      "step": 3790
+    },
+    {
+      "epoch": 5.0768203072812295,
+      "grad_norm": 1.028586745262146,
+      "learning_rate": 0.0002,
+      "loss": 1.2585,
+      "step": 3800
+    },
+    {
+      "epoch": 5.090180360721443,
+      "grad_norm": 1.0568538904190063,
+      "learning_rate": 0.0002,
+      "loss": 1.1769,
+      "step": 3810
+    },
+    {
+      "epoch": 5.103540414161657,
+      "grad_norm": 0.9780595302581787,
+      "learning_rate": 0.0002,
+      "loss": 1.263,
+      "step": 3820
+    },
+    {
+      "epoch": 5.11690046760187,
+      "grad_norm": 1.10311758518219,
+      "learning_rate": 0.0002,
+      "loss": 1.2019,
+      "step": 3830
+    },
+    {
+      "epoch": 5.130260521042084,
+      "grad_norm": 0.9497154355049133,
+      "learning_rate": 0.0002,
+      "loss": 1.2133,
+      "step": 3840
+    },
+    {
+      "epoch": 5.143620574482298,
+      "grad_norm": 0.948279857635498,
+      "learning_rate": 0.0002,
+      "loss": 1.1718,
+      "step": 3850
+    },
+    {
+      "epoch": 5.156980627922512,
+      "grad_norm": 0.9497880339622498,
+      "learning_rate": 0.0002,
+      "loss": 1.2108,
+      "step": 3860
+    },
+    {
+      "epoch": 5.170340681362726,
+      "grad_norm": 1.3213258981704712,
+      "learning_rate": 0.0002,
+      "loss": 1.1876,
+      "step": 3870
+    },
+    {
+      "epoch": 5.183700734802939,
+      "grad_norm": 0.9835752248764038,
+      "learning_rate": 0.0002,
+      "loss": 1.2327,
+      "step": 3880
+    },
+    {
+      "epoch": 5.197060788243153,
+      "grad_norm": 0.8426132202148438,
+      "learning_rate": 0.0002,
+      "loss": 1.2256,
+      "step": 3890
+    },
+    {
+      "epoch": 5.210420841683367,
+      "grad_norm": 1.0343470573425293,
+      "learning_rate": 0.0002,
+      "loss": 1.2066,
+      "step": 3900
+    },
+    {
+      "epoch": 5.22378089512358,
+      "grad_norm": 1.0771924257278442,
+      "learning_rate": 0.0002,
+      "loss": 1.2596,
+      "step": 3910
+    },
+    {
+      "epoch": 5.237140948563794,
+      "grad_norm": 0.8542634844779968,
+      "learning_rate": 0.0002,
+      "loss": 1.2371,
+      "step": 3920
+    },
+    {
+      "epoch": 5.250501002004008,
+      "grad_norm": 1.1021966934204102,
+      "learning_rate": 0.0002,
+      "loss": 1.2264,
+      "step": 3930
+    },
+    {
+      "epoch": 5.263861055444222,
+      "grad_norm": 1.170011281967163,
+      "learning_rate": 0.0002,
+      "loss": 1.2097,
+      "step": 3940
+    },
+    {
+      "epoch": 5.277221108884436,
+      "grad_norm": 0.9787653684616089,
+      "learning_rate": 0.0002,
+      "loss": 1.2101,
+      "step": 3950
+    },
+    {
+      "epoch": 5.290581162324649,
+      "grad_norm": 0.914513885974884,
+      "learning_rate": 0.0002,
+      "loss": 1.24,
+      "step": 3960
+    },
+    {
+      "epoch": 5.303941215764863,
+      "grad_norm": 1.0831562280654907,
+      "learning_rate": 0.0002,
+      "loss": 1.1641,
+      "step": 3970
+    },
+    {
+      "epoch": 5.3173012692050765,
+      "grad_norm": 0.9810112714767456,
+      "learning_rate": 0.0002,
+      "loss": 1.2609,
+      "step": 3980
+    },
+    {
+      "epoch": 5.330661322645291,
+      "grad_norm": 0.9624066948890686,
+      "learning_rate": 0.0002,
+      "loss": 1.1825,
+      "step": 3990
+    },
+    {
+      "epoch": 5.344021376085505,
+      "grad_norm": 1.2296923398971558,
+      "learning_rate": 0.0002,
+      "loss": 1.273,
+      "step": 4000
+    },
+    {
+      "epoch": 5.357381429525718,
+      "grad_norm": 1.011299967765808,
+      "learning_rate": 0.0002,
+      "loss": 1.2452,
+      "step": 4010
+    },
+    {
+      "epoch": 5.370741482965932,
+      "grad_norm": 0.9144132733345032,
+      "learning_rate": 0.0002,
+      "loss": 1.2539,
+      "step": 4020
+    },
+    {
+      "epoch": 5.3841015364061455,
+      "grad_norm": 1.0573601722717285,
+      "learning_rate": 0.0002,
+      "loss": 1.2914,
+      "step": 4030
+    },
+    {
+      "epoch": 5.397461589846359,
+      "grad_norm": 1.1667137145996094,
+      "learning_rate": 0.0002,
+      "loss": 1.2295,
+      "step": 4040
+    },
+    {
+      "epoch": 5.410821643286573,
+      "grad_norm": 1.072070598602295,
+      "learning_rate": 0.0002,
+      "loss": 1.2541,
+      "step": 4050
+    },
+    {
+      "epoch": 5.424181696726787,
+      "grad_norm": 1.1005792617797852,
+      "learning_rate": 0.0002,
+      "loss": 1.2448,
+      "step": 4060
+    },
+    {
+      "epoch": 5.437541750167001,
+      "grad_norm": 1.033581018447876,
+      "learning_rate": 0.0002,
+      "loss": 1.2604,
+      "step": 4070
+    },
+    {
+      "epoch": 5.4509018036072145,
+      "grad_norm": 0.9537439942359924,
+      "learning_rate": 0.0002,
+      "loss": 1.2552,
+      "step": 4080
+    },
+    {
+      "epoch": 5.464261857047428,
+      "grad_norm": 1.0502177476882935,
+      "learning_rate": 0.0002,
+      "loss": 1.2985,
+      "step": 4090
+    },
+    {
+      "epoch": 5.477621910487642,
+      "grad_norm": 0.9098296761512756,
+      "learning_rate": 0.0002,
+      "loss": 1.2424,
+      "step": 4100
+    },
+    {
+      "epoch": 5.490981963927855,
+      "grad_norm": 0.9551953077316284,
+      "learning_rate": 0.0002,
+      "loss": 1.2262,
+      "step": 4110
+    },
+    {
+      "epoch": 5.504342017368069,
+      "grad_norm": 0.9169427156448364,
+      "learning_rate": 0.0002,
+      "loss": 1.2848,
+      "step": 4120
+    },
+    {
+      "epoch": 5.517702070808284,
+      "grad_norm": 0.9430235624313354,
+      "learning_rate": 0.0002,
+      "loss": 1.2572,
+      "step": 4130
+    },
+    {
+      "epoch": 5.531062124248497,
+      "grad_norm": 0.817259669303894,
+      "learning_rate": 0.0002,
+      "loss": 1.2618,
+      "step": 4140
+    },
+    {
+      "epoch": 5.544422177688711,
+      "grad_norm": 1.124152660369873,
+      "learning_rate": 0.0002,
+      "loss": 1.3012,
+      "step": 4150
+    },
+    {
+      "epoch": 5.557782231128924,
+      "grad_norm": 0.9250756502151489,
+      "learning_rate": 0.0002,
+      "loss": 1.2508,
+      "step": 4160
+    },
+    {
+      "epoch": 5.571142284569138,
+      "grad_norm": 0.9582970142364502,
+      "learning_rate": 0.0002,
+      "loss": 1.2492,
+      "step": 4170
+    },
+    {
+      "epoch": 5.584502338009352,
+      "grad_norm": 1.0078704357147217,
+      "learning_rate": 0.0002,
+      "loss": 1.2804,
+      "step": 4180
+    },
+    {
+      "epoch": 5.597862391449565,
+      "grad_norm": 0.9585610032081604,
+      "learning_rate": 0.0002,
+      "loss": 1.1961,
+      "step": 4190
+    },
+    {
+      "epoch": 5.61122244488978,
+      "grad_norm": 1.0150971412658691,
+      "learning_rate": 0.0002,
+      "loss": 1.2522,
+      "step": 4200
+    },
+    {
+      "epoch": 5.6245824983299935,
+      "grad_norm": 0.9943351149559021,
+      "learning_rate": 0.0002,
+      "loss": 1.2275,
+      "step": 4210
+    },
+    {
+      "epoch": 5.637942551770207,
+      "grad_norm": 0.8880936503410339,
+      "learning_rate": 0.0002,
+      "loss": 1.2928,
+      "step": 4220
+    },
+    {
+      "epoch": 5.651302605210421,
+      "grad_norm": 0.9873887896537781,
+      "learning_rate": 0.0002,
+      "loss": 1.2323,
+      "step": 4230
+    },
+    {
+      "epoch": 5.664662658650634,
+      "grad_norm": 0.9185152649879456,
+      "learning_rate": 0.0002,
+      "loss": 1.3391,
+      "step": 4240
+    },
+    {
+      "epoch": 5.678022712090849,
+      "grad_norm": 1.0706779956817627,
+      "learning_rate": 0.0002,
+      "loss": 1.2511,
+      "step": 4250
+    },
+    {
+      "epoch": 5.6913827655310625,
+      "grad_norm": 0.9660224914550781,
+      "learning_rate": 0.0002,
+      "loss": 1.2737,
+      "step": 4260
+    },
+    {
+      "epoch": 5.704742818971276,
+      "grad_norm": 0.8685019612312317,
+      "learning_rate": 0.0002,
+      "loss": 1.2815,
+      "step": 4270
+    },
+    {
+      "epoch": 5.71810287241149,
+      "grad_norm": 1.0390565395355225,
+      "learning_rate": 0.0002,
+      "loss": 1.1559,
+      "step": 4280
+    },
+    {
+      "epoch": 5.731462925851703,
+      "grad_norm": 0.9290478825569153,
+      "learning_rate": 0.0002,
+      "loss": 1.3134,
+      "step": 4290
+    },
+    {
+      "epoch": 5.744822979291917,
+      "grad_norm": 1.0361281633377075,
+      "learning_rate": 0.0002,
+      "loss": 1.2426,
+      "step": 4300
+    },
+    {
+      "epoch": 5.758183032732131,
+      "grad_norm": 0.8804615139961243,
+      "learning_rate": 0.0002,
+      "loss": 1.2688,
+      "step": 4310
+    },
+    {
+      "epoch": 5.771543086172345,
+      "grad_norm": 1.0051425695419312,
+      "learning_rate": 0.0002,
+      "loss": 1.2479,
+      "step": 4320
+    },
+    {
+      "epoch": 5.784903139612559,
+      "grad_norm": 1.0051119327545166,
+      "learning_rate": 0.0002,
+      "loss": 1.1946,
+      "step": 4330
+    },
+    {
+      "epoch": 5.798263193052772,
+      "grad_norm": 0.9961661100387573,
+      "learning_rate": 0.0002,
+      "loss": 1.2571,
+      "step": 4340
+    },
+    {
+      "epoch": 5.811623246492986,
+      "grad_norm": 1.0229419469833374,
+      "learning_rate": 0.0002,
+      "loss": 1.2179,
+      "step": 4350
+    },
+    {
+      "epoch": 5.8249832999332,
+      "grad_norm": 1.1129552125930786,
+      "learning_rate": 0.0002,
+      "loss": 1.2984,
+      "step": 4360
+    },
+    {
+      "epoch": 5.838343353373413,
+      "grad_norm": 1.18964421749115,
+      "learning_rate": 0.0002,
+      "loss": 1.2692,
+      "step": 4370
+    },
+    {
+      "epoch": 5.851703406813627,
+      "grad_norm": 0.9490230083465576,
+      "learning_rate": 0.0002,
+      "loss": 1.1996,
+      "step": 4380
+    },
+    {
+      "epoch": 5.865063460253841,
+      "grad_norm": 0.8734540343284607,
+      "learning_rate": 0.0002,
+      "loss": 1.3177,
+      "step": 4390
+    },
+    {
+      "epoch": 5.878423513694055,
+      "grad_norm": 1.0017802715301514,
+      "learning_rate": 0.0002,
+      "loss": 1.3131,
+      "step": 4400
+    },
+    {
+      "epoch": 5.891783567134269,
+      "grad_norm": 0.953556478023529,
+      "learning_rate": 0.0002,
+      "loss": 1.2649,
+      "step": 4410
+    },
+    {
+      "epoch": 5.905143620574482,
+      "grad_norm": 0.8915258646011353,
+      "learning_rate": 0.0002,
+      "loss": 1.2684,
+      "step": 4420
+    },
+    {
+      "epoch": 5.918503674014696,
+      "grad_norm": 0.9715141654014587,
+      "learning_rate": 0.0002,
+      "loss": 1.2843,
+      "step": 4430
+    },
+    {
+      "epoch": 5.9318637274549095,
+      "grad_norm": 0.9432152509689331,
+      "learning_rate": 0.0002,
+      "loss": 1.2769,
+      "step": 4440
+    },
+    {
+      "epoch": 5.945223780895123,
+      "grad_norm": 0.9473979473114014,
+      "learning_rate": 0.0002,
+      "loss": 1.233,
+      "step": 4450
+    },
+    {
+      "epoch": 5.958583834335338,
+      "grad_norm": 1.104871392250061,
+      "learning_rate": 0.0002,
+      "loss": 1.3209,
+      "step": 4460
+    },
+    {
+      "epoch": 5.971943887775551,
+      "grad_norm": 1.0308905839920044,
+      "learning_rate": 0.0002,
+      "loss": 1.3427,
+      "step": 4470
+    },
+    {
+      "epoch": 5.985303941215765,
+      "grad_norm": 0.8895487189292908,
+      "learning_rate": 0.0002,
+      "loss": 1.1808,
+      "step": 4480
+    },
+    {
+      "epoch": 5.9986639946559785,
+      "grad_norm": 1.0148485898971558,
+      "learning_rate": 0.0002,
+      "loss": 1.2634,
+      "step": 4490
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.0830726623535156,
+      "eval_runtime": 38.5442,
+      "eval_samples_per_second": 13.361,
+      "eval_steps_per_second": 1.686,
+      "step": 4491
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5984,
+  "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": 2.078334242437202e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7025f98e983b93b4fec0d5370c1456c7adecaf8e
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-4491/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e92f0598f349930e52e126f358a3dca045c3c88312ec4b3f814f018a04982a9
+size 5560
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/README.md b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d63cb87eaccf2d81de3cdcfa11d2e99c440c0ea0
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0a01b2fc0b54d84f37ddfffdc3279cd1ee50a212
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b119d47c1fb9705c3c5b3c8e56823df542b9f9bc6c68f6f86338f8725b6b1e43
+size 109069176
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..99e069f2d50b91e6b7545c4b385daeb0cbf21098
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d21b5883ac12049ec22ad5b60bacc185273486591700a7cc13e07ab7ac28bc
+size 55532666
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ea52eb077424f886c63d82e99e83a2b8287acf73
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2224c66f4cb4f8ad60fb15486306df8a451cd14b191e6073feaf2b5420feb8
+size 14244
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b6f8ad78e16357cf5218d5719bd480e9f376c074
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b994104d1f62e5245f79451223748faec7b00256fca74faf69dded4a46ebdd6
+size 1064
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/tokenizer_config.json
@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..1cb4185ba24bb16b23dd15f0c1cc5ff6b31d9afd
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/trainer_state.json
@@ -0,0 +1,3750 @@
+{
+  "best_metric": 1.8132041692733765,
+  "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497",
+  "epoch": 6.999331997327989,
+  "eval_steps": 10,
+  "global_step": 5239,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013360053440213761,
+      "grad_norm": 0.5097216367721558,
+      "learning_rate": 0.0002,
+      "loss": 2.6569,
+      "step": 10
+    },
+    {
+      "epoch": 0.026720106880427523,
+      "grad_norm": 0.5924790501594543,
+      "learning_rate": 0.0002,
+      "loss": 2.2557,
+      "step": 20
+    },
+    {
+      "epoch": 0.04008016032064128,
+      "grad_norm": 0.5158102512359619,
+      "learning_rate": 0.0002,
+      "loss": 2.0626,
+      "step": 30
+    },
+    {
+      "epoch": 0.053440213760855046,
+      "grad_norm": 0.5033753514289856,
+      "learning_rate": 0.0002,
+      "loss": 1.9452,
+      "step": 40
+    },
+    {
+      "epoch": 0.06680026720106881,
+      "grad_norm": 0.5390949845314026,
+      "learning_rate": 0.0002,
+      "loss": 1.9128,
+      "step": 50
+    },
+    {
+      "epoch": 0.08016032064128256,
+      "grad_norm": 0.6376217007637024,
+      "learning_rate": 0.0002,
+      "loss": 1.937,
+      "step": 60
+    },
+    {
+      "epoch": 0.09352037408149633,
+      "grad_norm": 0.4202035069465637,
+      "learning_rate": 0.0002,
+      "loss": 1.929,
+      "step": 70
+    },
+    {
+      "epoch": 0.10688042752171009,
+      "grad_norm": 0.4269474744796753,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 80
+    },
+    {
+      "epoch": 0.12024048096192384,
+      "grad_norm": 0.4306574761867523,
+      "learning_rate": 0.0002,
+      "loss": 1.8303,
+      "step": 90
+    },
+    {
+      "epoch": 0.13360053440213762,
+      "grad_norm": 0.5297011137008667,
+      "learning_rate": 0.0002,
+      "loss": 1.8469,
+      "step": 100
+    },
+    {
+      "epoch": 0.14696058784235136,
+      "grad_norm": 1.2313778400421143,
+      "learning_rate": 0.0002,
+      "loss": 1.864,
+      "step": 110
+    },
+    {
+      "epoch": 0.16032064128256512,
+      "grad_norm": 0.5351294279098511,
+      "learning_rate": 0.0002,
+      "loss": 1.8531,
+      "step": 120
+    },
+    {
+      "epoch": 0.1736806947227789,
+      "grad_norm": 0.4848092496395111,
+      "learning_rate": 0.0002,
+      "loss": 1.9232,
+      "step": 130
+    },
+    {
+      "epoch": 0.18704074816299265,
+      "grad_norm": 0.4339500665664673,
+      "learning_rate": 0.0002,
+      "loss": 1.8633,
+      "step": 140
+    },
+    {
+      "epoch": 0.20040080160320642,
+      "grad_norm": 0.46877285838127136,
+      "learning_rate": 0.0002,
+      "loss": 1.816,
+      "step": 150
+    },
+    {
+      "epoch": 0.21376085504342018,
+      "grad_norm": 0.5600412487983704,
+      "learning_rate": 0.0002,
+      "loss": 1.8033,
+      "step": 160
+    },
+    {
+      "epoch": 0.22712090848363392,
+      "grad_norm": 0.3733620345592499,
+      "learning_rate": 0.0002,
+      "loss": 1.8162,
+      "step": 170
+    },
+    {
+      "epoch": 0.24048096192384769,
+      "grad_norm": 0.5116042494773865,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 180
+    },
+    {
+      "epoch": 0.25384101536406145,
+      "grad_norm": 0.4071602523326874,
+      "learning_rate": 0.0002,
+      "loss": 1.915,
+      "step": 190
+    },
+    {
+      "epoch": 0.26720106880427524,
+      "grad_norm": 0.44189608097076416,
+      "learning_rate": 0.0002,
+      "loss": 1.7984,
+      "step": 200
+    },
+    {
+      "epoch": 0.280561122244489,
+      "grad_norm": 0.398699015378952,
+      "learning_rate": 0.0002,
+      "loss": 1.8728,
+      "step": 210
+    },
+    {
+      "epoch": 0.2939211756847027,
+      "grad_norm": 0.3585626482963562,
+      "learning_rate": 0.0002,
+      "loss": 1.8205,
+      "step": 220
+    },
+    {
+      "epoch": 0.3072812291249165,
+      "grad_norm": 0.3811776041984558,
+      "learning_rate": 0.0002,
+      "loss": 1.8861,
+      "step": 230
+    },
+    {
+      "epoch": 0.32064128256513025,
+      "grad_norm": 0.37261509895324707,
+      "learning_rate": 0.0002,
+      "loss": 1.8365,
+      "step": 240
+    },
+    {
+      "epoch": 0.33400133600534404,
+      "grad_norm": 0.39762404561042786,
+      "learning_rate": 0.0002,
+      "loss": 1.9186,
+      "step": 250
+    },
+    {
+      "epoch": 0.3473613894455578,
+      "grad_norm": 0.3509528934955597,
+      "learning_rate": 0.0002,
+      "loss": 1.7965,
+      "step": 260
+    },
+    {
+      "epoch": 0.36072144288577157,
+      "grad_norm": 0.3169104754924774,
+      "learning_rate": 0.0002,
+      "loss": 1.7802,
+      "step": 270
+    },
+    {
+      "epoch": 0.3740814963259853,
+      "grad_norm": 0.33714795112609863,
+      "learning_rate": 0.0002,
+      "loss": 1.8038,
+      "step": 280
+    },
+    {
+      "epoch": 0.38744154976619904,
+      "grad_norm": 1.2936875820159912,
+      "learning_rate": 0.0002,
+      "loss": 1.787,
+      "step": 290
+    },
+    {
+      "epoch": 0.40080160320641284,
+      "grad_norm": 0.3459427058696747,
+      "learning_rate": 0.0002,
+      "loss": 1.7974,
+      "step": 300
+    },
+    {
+      "epoch": 0.4141616566466266,
+      "grad_norm": 0.3380655348300934,
+      "learning_rate": 0.0002,
+      "loss": 1.8879,
+      "step": 310
+    },
+    {
+      "epoch": 0.42752171008684037,
+      "grad_norm": 0.3890381455421448,
+      "learning_rate": 0.0002,
+      "loss": 1.9196,
+      "step": 320
+    },
+    {
+      "epoch": 0.4408817635270541,
+      "grad_norm": 0.432327002286911,
+      "learning_rate": 0.0002,
+      "loss": 1.8034,
+      "step": 330
+    },
+    {
+      "epoch": 0.45424181696726784,
+      "grad_norm": 0.3736560046672821,
+      "learning_rate": 0.0002,
+      "loss": 1.8443,
+      "step": 340
+    },
+    {
+      "epoch": 0.46760187040748163,
+      "grad_norm": 0.3700982630252838,
+      "learning_rate": 0.0002,
+      "loss": 1.8506,
+      "step": 350
+    },
+    {
+      "epoch": 0.48096192384769537,
+      "grad_norm": 0.4533902406692505,
+      "learning_rate": 0.0002,
+      "loss": 1.7978,
+      "step": 360
+    },
+    {
+      "epoch": 0.49432197728790916,
+      "grad_norm": 0.35999053716659546,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 370
+    },
+    {
+      "epoch": 0.5076820307281229,
+      "grad_norm": 0.3490903675556183,
+      "learning_rate": 0.0002,
+      "loss": 1.7995,
+      "step": 380
+    },
+    {
+      "epoch": 0.5210420841683366,
+      "grad_norm": 0.34704291820526123,
+      "learning_rate": 0.0002,
+      "loss": 1.8709,
+      "step": 390
+    },
+    {
+      "epoch": 0.5344021376085505,
+      "grad_norm": 0.343565434217453,
+      "learning_rate": 0.0002,
+      "loss": 1.7948,
+      "step": 400
+    },
+    {
+      "epoch": 0.5477621910487642,
+      "grad_norm": 0.3573552966117859,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 410
+    },
+    {
+      "epoch": 0.561122244488978,
+      "grad_norm": 0.32980719208717346,
+      "learning_rate": 0.0002,
+      "loss": 1.8477,
+      "step": 420
+    },
+    {
+      "epoch": 0.5744822979291917,
+      "grad_norm": 0.356952428817749,
+      "learning_rate": 0.0002,
+      "loss": 1.9233,
+      "step": 430
+    },
+    {
+      "epoch": 0.5878423513694054,
+      "grad_norm": 0.3170869052410126,
+      "learning_rate": 0.0002,
+      "loss": 1.7433,
+      "step": 440
+    },
+    {
+      "epoch": 0.6012024048096193,
+      "grad_norm": 0.35233718156814575,
+      "learning_rate": 0.0002,
+      "loss": 1.7607,
+      "step": 450
+    },
+    {
+      "epoch": 0.614562458249833,
+      "grad_norm": 0.3480125367641449,
+      "learning_rate": 0.0002,
+      "loss": 1.8111,
+      "step": 460
+    },
+    {
+      "epoch": 0.6279225116900468,
+      "grad_norm": 0.4762810468673706,
+      "learning_rate": 0.0002,
+      "loss": 1.8386,
+      "step": 470
+    },
+    {
+      "epoch": 0.6412825651302605,
+      "grad_norm": 0.3907663822174072,
+      "learning_rate": 0.0002,
+      "loss": 1.805,
+      "step": 480
+    },
+    {
+      "epoch": 0.6546426185704742,
+      "grad_norm": 0.36315613985061646,
+      "learning_rate": 0.0002,
+      "loss": 1.8113,
+      "step": 490
+    },
+    {
+      "epoch": 0.6680026720106881,
+      "grad_norm": 0.377796471118927,
+      "learning_rate": 0.0002,
+      "loss": 1.7805,
+      "step": 500
+    },
+    {
+      "epoch": 0.6813627254509018,
+      "grad_norm": 0.34284207224845886,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 510
+    },
+    {
+      "epoch": 0.6947227788911156,
+      "grad_norm": 0.35563018918037415,
+      "learning_rate": 0.0002,
+      "loss": 1.8013,
+      "step": 520
+    },
+    {
+      "epoch": 0.7080828323313293,
+      "grad_norm": 0.37575867772102356,
+      "learning_rate": 0.0002,
+      "loss": 1.8414,
+      "step": 530
+    },
+    {
+      "epoch": 0.7214428857715431,
+      "grad_norm": 0.35719701647758484,
+      "learning_rate": 0.0002,
+      "loss": 1.7993,
+      "step": 540
+    },
+    {
+      "epoch": 0.7348029392117569,
+      "grad_norm": 0.385813444852829,
+      "learning_rate": 0.0002,
+      "loss": 1.7574,
+      "step": 550
+    },
+    {
+      "epoch": 0.7481629926519706,
+      "grad_norm": 0.44509607553482056,
+      "learning_rate": 0.0002,
+      "loss": 1.7985,
+      "step": 560
+    },
+    {
+      "epoch": 0.7615230460921844,
+      "grad_norm": 0.36108464002609253,
+      "learning_rate": 0.0002,
+      "loss": 1.7459,
+      "step": 570
+    },
+    {
+      "epoch": 0.7748830995323981,
+      "grad_norm": 0.3530745804309845,
+      "learning_rate": 0.0002,
+      "loss": 1.8207,
+      "step": 580
+    },
+    {
+      "epoch": 0.7882431529726119,
+      "grad_norm": 0.34888574481010437,
+      "learning_rate": 0.0002,
+      "loss": 1.7479,
+      "step": 590
+    },
+    {
+      "epoch": 0.8016032064128257,
+      "grad_norm": 0.387346476316452,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 600
+    },
+    {
+      "epoch": 0.8149632598530394,
+      "grad_norm": 0.3641138970851898,
+      "learning_rate": 0.0002,
+      "loss": 1.8071,
+      "step": 610
+    },
+    {
+      "epoch": 0.8283233132932531,
+      "grad_norm": 0.33729103207588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7531,
+      "step": 620
+    },
+    {
+      "epoch": 0.8416833667334669,
+      "grad_norm": 0.3652004599571228,
+      "learning_rate": 0.0002,
+      "loss": 1.8613,
+      "step": 630
+    },
+    {
+      "epoch": 0.8550434201736807,
+      "grad_norm": 0.3986643850803375,
+      "learning_rate": 0.0002,
+      "loss": 1.9184,
+      "step": 640
+    },
+    {
+      "epoch": 0.8684034736138945,
+      "grad_norm": 0.3458964228630066,
+      "learning_rate": 0.0002,
+      "loss": 1.8198,
+      "step": 650
+    },
+    {
+      "epoch": 0.8817635270541082,
+      "grad_norm": 0.3559381365776062,
+      "learning_rate": 0.0002,
+      "loss": 1.803,
+      "step": 660
+    },
+    {
+      "epoch": 0.895123580494322,
+      "grad_norm": 0.3612841069698334,
+      "learning_rate": 0.0002,
+      "loss": 1.7641,
+      "step": 670
+    },
+    {
+      "epoch": 0.9084836339345357,
+      "grad_norm": 0.34771719574928284,
+      "learning_rate": 0.0002,
+      "loss": 1.7888,
+      "step": 680
+    },
+    {
+      "epoch": 0.9218436873747495,
+      "grad_norm": 0.3371497094631195,
+      "learning_rate": 0.0002,
+      "loss": 1.8204,
+      "step": 690
+    },
+    {
+      "epoch": 0.9352037408149633,
+      "grad_norm": 0.5596055388450623,
+      "learning_rate": 0.0002,
+      "loss": 1.7848,
+      "step": 700
+    },
+    {
+      "epoch": 0.948563794255177,
+      "grad_norm": 0.311880499124527,
+      "learning_rate": 0.0002,
+      "loss": 1.7794,
+      "step": 710
+    },
+    {
+      "epoch": 0.9619238476953907,
+      "grad_norm": 0.3462068736553192,
+      "learning_rate": 0.0002,
+      "loss": 1.8464,
+      "step": 720
+    },
+    {
+      "epoch": 0.9752839011356046,
+      "grad_norm": 0.29982393980026245,
+      "learning_rate": 0.0002,
+      "loss": 1.8197,
+      "step": 730
+    },
+    {
+      "epoch": 0.9886439545758183,
+      "grad_norm": 0.34606459736824036,
+      "learning_rate": 0.0002,
+      "loss": 1.8503,
+      "step": 740
+    },
+    {
+      "epoch": 0.9993319973279893,
+      "eval_loss": 1.8201380968093872,
+      "eval_runtime": 38.6124,
+      "eval_samples_per_second": 13.338,
+      "eval_steps_per_second": 1.683,
+      "step": 748
+    },
+    {
+      "epoch": 1.002004008016032,
+      "grad_norm": 0.32302048802375793,
+      "learning_rate": 0.0002,
+      "loss": 1.7786,
+      "step": 750
+    },
+    {
+      "epoch": 1.0153640614562458,
+      "grad_norm": 0.37585633993148804,
+      "learning_rate": 0.0002,
+      "loss": 1.7297,
+      "step": 760
+    },
+    {
+      "epoch": 1.0287241148964597,
+      "grad_norm": 0.33826273679733276,
+      "learning_rate": 0.0002,
+      "loss": 1.7008,
+      "step": 770
+    },
+    {
+      "epoch": 1.0420841683366733,
+      "grad_norm": 0.44682955741882324,
+      "learning_rate": 0.0002,
+      "loss": 1.809,
+      "step": 780
+    },
+    {
+      "epoch": 1.0554442217768871,
+      "grad_norm": 0.422188401222229,
+      "learning_rate": 0.0002,
+      "loss": 1.7092,
+      "step": 790
+    },
+    {
+      "epoch": 1.0688042752171008,
+      "grad_norm": 0.3809906244277954,
+      "learning_rate": 0.0002,
+      "loss": 1.7765,
+      "step": 800
+    },
+    {
+      "epoch": 1.0821643286573146,
+      "grad_norm": 0.3454349637031555,
+      "learning_rate": 0.0002,
+      "loss": 1.7431,
+      "step": 810
+    },
+    {
+      "epoch": 1.0955243820975284,
+      "grad_norm": 0.3767355978488922,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 820
+    },
+    {
+      "epoch": 1.108884435537742,
+      "grad_norm": 0.3361407518386841,
+      "learning_rate": 0.0002,
+      "loss": 1.7224,
+      "step": 830
+    },
+    {
+      "epoch": 1.122244488977956,
+      "grad_norm": 0.3654632568359375,
+      "learning_rate": 0.0002,
+      "loss": 1.7509,
+      "step": 840
+    },
+    {
+      "epoch": 1.1356045424181698,
+      "grad_norm": 0.3822861313819885,
+      "learning_rate": 0.0002,
+      "loss": 1.7151,
+      "step": 850
+    },
+    {
+      "epoch": 1.1489645958583834,
+      "grad_norm": 0.3853831887245178,
+      "learning_rate": 0.0002,
+      "loss": 1.7121,
+      "step": 860
+    },
+    {
+      "epoch": 1.1623246492985972,
+      "grad_norm": 0.35521796345710754,
+      "learning_rate": 0.0002,
+      "loss": 1.7685,
+      "step": 870
+    },
+    {
+      "epoch": 1.1756847027388109,
+      "grad_norm": 0.4107200503349304,
+      "learning_rate": 0.0002,
+      "loss": 1.7735,
+      "step": 880
+    },
+    {
+      "epoch": 1.1890447561790247,
+      "grad_norm": 0.33219534158706665,
+      "learning_rate": 0.0002,
+      "loss": 1.7484,
+      "step": 890
+    },
+    {
+      "epoch": 1.2024048096192386,
+      "grad_norm": 0.3559704124927521,
+      "learning_rate": 0.0002,
+      "loss": 1.7071,
+      "step": 900
+    },
+    {
+      "epoch": 1.2157648630594522,
+      "grad_norm": 0.3700537383556366,
+      "learning_rate": 0.0002,
+      "loss": 1.7535,
+      "step": 910
+    },
+    {
+      "epoch": 1.229124916499666,
+      "grad_norm": 0.3771909475326538,
+      "learning_rate": 0.0002,
+      "loss": 1.7513,
+      "step": 920
+    },
+    {
+      "epoch": 1.2424849699398797,
+      "grad_norm": 0.3136613965034485,
+      "learning_rate": 0.0002,
+      "loss": 1.7566,
+      "step": 930
+    },
+    {
+      "epoch": 1.2558450233800935,
+      "grad_norm": 0.3952099084854126,
+      "learning_rate": 0.0002,
+      "loss": 1.6783,
+      "step": 940
+    },
+    {
+      "epoch": 1.2692050768203074,
+      "grad_norm": 0.36534377932548523,
+      "learning_rate": 0.0002,
+      "loss": 1.7691,
+      "step": 950
+    },
+    {
+      "epoch": 1.282565130260521,
+      "grad_norm": 0.3803492486476898,
+      "learning_rate": 0.0002,
+      "loss": 1.7127,
+      "step": 960
+    },
+    {
+      "epoch": 1.2959251837007348,
+      "grad_norm": 0.3992428183555603,
+      "learning_rate": 0.0002,
+      "loss": 1.7896,
+      "step": 970
+    },
+    {
+      "epoch": 1.3092852371409487,
+      "grad_norm": 0.3627142906188965,
+      "learning_rate": 0.0002,
+      "loss": 1.7343,
+      "step": 980
+    },
+    {
+      "epoch": 1.3226452905811623,
+      "grad_norm": 0.4248180091381073,
+      "learning_rate": 0.0002,
+      "loss": 1.7598,
+      "step": 990
+    },
+    {
+      "epoch": 1.3360053440213762,
+      "grad_norm": 0.4060308039188385,
+      "learning_rate": 0.0002,
+      "loss": 1.6896,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3493653974615898,
+      "grad_norm": 0.3788969814777374,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 1010
+    },
+    {
+      "epoch": 1.3627254509018036,
+      "grad_norm": 0.4174270033836365,
+      "learning_rate": 0.0002,
+      "loss": 1.7111,
+      "step": 1020
+    },
+    {
+      "epoch": 1.3760855043420173,
+      "grad_norm": 0.35500675439834595,
+      "learning_rate": 0.0002,
+      "loss": 1.7975,
+      "step": 1030
+    },
+    {
+      "epoch": 1.389445557782231,
+      "grad_norm": 0.3454059362411499,
+      "learning_rate": 0.0002,
+      "loss": 1.724,
+      "step": 1040
+    },
+    {
+      "epoch": 1.402805611222445,
+      "grad_norm": 0.45807570219039917,
+      "learning_rate": 0.0002,
+      "loss": 1.8299,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4161656646626586,
+      "grad_norm": 0.39338022470474243,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4295257181028724,
+      "grad_norm": 0.3870709240436554,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4428857715430863,
+      "grad_norm": 0.40996190905570984,
+      "learning_rate": 0.0002,
+      "loss": 1.6565,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4562458249833,
+      "grad_norm": 0.38762837648391724,
+      "learning_rate": 0.0002,
+      "loss": 1.7324,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4696058784235138,
+      "grad_norm": 0.36756977438926697,
+      "learning_rate": 0.0002,
+      "loss": 1.7362,
+      "step": 1100
+    },
+    {
+      "epoch": 1.4829659318637274,
+      "grad_norm": 0.4087235927581787,
+      "learning_rate": 0.0002,
+      "loss": 1.7451,
+      "step": 1110
+    },
+    {
+      "epoch": 1.4963259853039412,
+      "grad_norm": 0.3357745110988617,
+      "learning_rate": 0.0002,
+      "loss": 1.7114,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5096860387441549,
+      "grad_norm": 0.37486532330513,
+      "learning_rate": 0.0002,
+      "loss": 1.6877,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5230460921843687,
+      "grad_norm": 0.3387809991836548,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5364061456245826,
+      "grad_norm": 0.37462118268013,
+      "learning_rate": 0.0002,
+      "loss": 1.7169,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5497661990647962,
+      "grad_norm": 0.38575324416160583,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 1160
+    },
+    {
+      "epoch": 1.56312625250501,
+      "grad_norm": 0.3515765964984894,
+      "learning_rate": 0.0002,
+      "loss": 1.7438,
+      "step": 1170
+    },
+    {
+      "epoch": 1.5764863059452239,
+      "grad_norm": 0.39308643341064453,
+      "learning_rate": 0.0002,
+      "loss": 1.7524,
+      "step": 1180
+    },
+    {
+      "epoch": 1.5898463593854375,
+      "grad_norm": 0.3308864235877991,
+      "learning_rate": 0.0002,
+      "loss": 1.6422,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6032064128256514,
+      "grad_norm": 0.3397478461265564,
+      "learning_rate": 0.0002,
+      "loss": 1.7566,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6165664662658652,
+      "grad_norm": 0.3911525309085846,
+      "learning_rate": 0.0002,
+      "loss": 1.7871,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6299265197060788,
+      "grad_norm": 0.3771969974040985,
+      "learning_rate": 0.0002,
+      "loss": 1.7443,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6432865731462925,
+      "grad_norm": 0.35346856713294983,
+      "learning_rate": 0.0002,
+      "loss": 1.7631,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6566466265865063,
+      "grad_norm": 0.41736963391304016,
+      "learning_rate": 0.0002,
+      "loss": 1.7225,
+      "step": 1240
+    },
+    {
+      "epoch": 1.6700066800267201,
+      "grad_norm": 0.3375225067138672,
+      "learning_rate": 0.0002,
+      "loss": 1.7582,
+      "step": 1250
+    },
+    {
+      "epoch": 1.6833667334669338,
+      "grad_norm": 0.3779928982257843,
+      "learning_rate": 0.0002,
+      "loss": 1.6916,
+      "step": 1260
+    },
+    {
+      "epoch": 1.6967267869071476,
+      "grad_norm": 0.35388994216918945,
+      "learning_rate": 0.0002,
+      "loss": 1.728,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7100868403473615,
+      "grad_norm": 0.33884134888648987,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 1280
+    },
+    {
+      "epoch": 1.723446893787575,
+      "grad_norm": 0.35439756512641907,
+      "learning_rate": 0.0002,
+      "loss": 1.7083,
+      "step": 1290
+    },
+    {
+      "epoch": 1.736806947227789,
+      "grad_norm": 0.3766156733036041,
+      "learning_rate": 0.0002,
+      "loss": 1.7389,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7501670006680028,
+      "grad_norm": 0.36148911714553833,
+      "learning_rate": 0.0002,
+      "loss": 1.7847,
+      "step": 1310
+    },
+    {
+      "epoch": 1.7635270541082164,
+      "grad_norm": 0.39687496423721313,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 1320
+    },
+    {
+      "epoch": 1.77688710754843,
+      "grad_norm": 0.35639452934265137,
+      "learning_rate": 0.0002,
+      "loss": 1.7541,
+      "step": 1330
+    },
+    {
+      "epoch": 1.7902471609886441,
+      "grad_norm": 0.38781628012657166,
+      "learning_rate": 0.0002,
+      "loss": 1.7254,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8036072144288577,
+      "grad_norm": 0.42784637212753296,
+      "learning_rate": 0.0002,
+      "loss": 1.7867,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8169672678690714,
+      "grad_norm": 0.40258511900901794,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8303273213092852,
+      "grad_norm": 0.36674195528030396,
+      "learning_rate": 0.0002,
+      "loss": 1.7771,
+      "step": 1370
+    },
+    {
+      "epoch": 1.843687374749499,
+      "grad_norm": 0.4064558446407318,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8570474281897127,
+      "grad_norm": 0.3669849932193756,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1390
+    },
+    {
+      "epoch": 1.8704074816299265,
+      "grad_norm": 0.37569567561149597,
+      "learning_rate": 0.0002,
+      "loss": 1.7924,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8837675350701404,
+      "grad_norm": 0.37307995557785034,
+      "learning_rate": 0.0002,
+      "loss": 1.7885,
+      "step": 1410
+    },
+    {
+      "epoch": 1.897127588510354,
+      "grad_norm": 0.3772695064544678,
+      "learning_rate": 0.0002,
+      "loss": 1.7548,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9104876419505676,
+      "grad_norm": 0.36993589997291565,
+      "learning_rate": 0.0002,
+      "loss": 1.7682,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9238476953907817,
+      "grad_norm": 0.3490557372570038,
+      "learning_rate": 0.0002,
+      "loss": 1.7249,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9372077488309953,
+      "grad_norm": 0.3716149628162384,
+      "learning_rate": 0.0002,
+      "loss": 1.7979,
+      "step": 1450
+    },
+    {
+      "epoch": 1.950567802271209,
+      "grad_norm": 0.39236098527908325,
+      "learning_rate": 0.0002,
+      "loss": 1.6664,
+      "step": 1460
+    },
+    {
+      "epoch": 1.9639278557114228,
+      "grad_norm": 0.37258651852607727,
+      "learning_rate": 0.0002,
+      "loss": 1.6852,
+      "step": 1470
+    },
+    {
+      "epoch": 1.9772879091516367,
+      "grad_norm": 0.36183077096939087,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 1480
+    },
+    {
+      "epoch": 1.9906479625918503,
+      "grad_norm": 0.3956947326660156,
+      "learning_rate": 0.0002,
+      "loss": 1.7055,
+      "step": 1490
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8132041692733765,
+      "eval_runtime": 38.6287,
+      "eval_samples_per_second": 13.332,
+      "eval_steps_per_second": 1.683,
+      "step": 1497
+    },
+    {
+      "epoch": 2.004008016032064,
+      "grad_norm": 0.34480565786361694,
+      "learning_rate": 0.0002,
+      "loss": 1.6791,
+      "step": 1500
+    },
+    {
+      "epoch": 2.017368069472278,
+      "grad_norm": 0.3418028652667999,
+      "learning_rate": 0.0002,
+      "loss": 1.6367,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0307281229124916,
+      "grad_norm": 0.4514467716217041,
+      "learning_rate": 0.0002,
+      "loss": 1.5827,
+      "step": 1520
+    },
+    {
+      "epoch": 2.0440881763527052,
+      "grad_norm": 0.4197506606578827,
+      "learning_rate": 0.0002,
+      "loss": 1.6365,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0574482297929193,
+      "grad_norm": 0.4134170711040497,
+      "learning_rate": 0.0002,
+      "loss": 1.6221,
+      "step": 1540
+    },
+    {
+      "epoch": 2.070808283233133,
+      "grad_norm": 0.43709826469421387,
+      "learning_rate": 0.0002,
+      "loss": 1.6876,
+      "step": 1550
+    },
+    {
+      "epoch": 2.0841683366733466,
+      "grad_norm": 0.4703378677368164,
+      "learning_rate": 0.0002,
+      "loss": 1.5779,
+      "step": 1560
+    },
+    {
+      "epoch": 2.0975283901135606,
+      "grad_norm": 0.4538188576698303,
+      "learning_rate": 0.0002,
+      "loss": 1.599,
+      "step": 1570
+    },
+    {
+      "epoch": 2.1108884435537743,
+      "grad_norm": 0.4649668037891388,
+      "learning_rate": 0.0002,
+      "loss": 1.6464,
+      "step": 1580
+    },
+    {
+      "epoch": 2.124248496993988,
+      "grad_norm": 0.42669883370399475,
+      "learning_rate": 0.0002,
+      "loss": 1.6348,
+      "step": 1590
+    },
+    {
+      "epoch": 2.1376085504342015,
+      "grad_norm": 0.43162038922309875,
+      "learning_rate": 0.0002,
+      "loss": 1.5838,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1509686038744156,
+      "grad_norm": 0.4294586479663849,
+      "learning_rate": 0.0002,
+      "loss": 1.6673,
+      "step": 1610
+    },
+    {
+      "epoch": 2.164328657314629,
+      "grad_norm": 0.4669102132320404,
+      "learning_rate": 0.0002,
+      "loss": 1.6024,
+      "step": 1620
+    },
+    {
+      "epoch": 2.177688710754843,
+      "grad_norm": 0.4188412129878998,
+      "learning_rate": 0.0002,
+      "loss": 1.659,
+      "step": 1630
+    },
+    {
+      "epoch": 2.191048764195057,
+      "grad_norm": 0.4662680923938751,
+      "learning_rate": 0.0002,
+      "loss": 1.625,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2044088176352705,
+      "grad_norm": 0.4020286500453949,
+      "learning_rate": 0.0002,
+      "loss": 1.6699,
+      "step": 1650
+    },
+    {
+      "epoch": 2.217768871075484,
+      "grad_norm": 0.41919606924057007,
+      "learning_rate": 0.0002,
+      "loss": 1.6284,
+      "step": 1660
+    },
+    {
+      "epoch": 2.231128924515698,
+      "grad_norm": 0.4644531309604645,
+      "learning_rate": 0.0002,
+      "loss": 1.6776,
+      "step": 1670
+    },
+    {
+      "epoch": 2.244488977955912,
+      "grad_norm": 0.4526427984237671,
+      "learning_rate": 0.0002,
+      "loss": 1.6711,
+      "step": 1680
+    },
+    {
+      "epoch": 2.2578490313961255,
+      "grad_norm": 0.45953166484832764,
+      "learning_rate": 0.0002,
+      "loss": 1.6058,
+      "step": 1690
+    },
+    {
+      "epoch": 2.2712090848363395,
+      "grad_norm": 0.4701860249042511,
+      "learning_rate": 0.0002,
+      "loss": 1.5979,
+      "step": 1700
+    },
+    {
+      "epoch": 2.284569138276553,
+      "grad_norm": 0.4749310612678528,
+      "learning_rate": 0.0002,
+      "loss": 1.6183,
+      "step": 1710
+    },
+    {
+      "epoch": 2.297929191716767,
+      "grad_norm": 0.45026102662086487,
+      "learning_rate": 0.0002,
+      "loss": 1.6703,
+      "step": 1720
+    },
+    {
+      "epoch": 2.3112892451569804,
+      "grad_norm": 0.4755004048347473,
+      "learning_rate": 0.0002,
+      "loss": 1.6386,
+      "step": 1730
+    },
+    {
+      "epoch": 2.3246492985971945,
+      "grad_norm": 0.4505726993083954,
+      "learning_rate": 0.0002,
+      "loss": 1.6365,
+      "step": 1740
+    },
+    {
+      "epoch": 2.338009352037408,
+      "grad_norm": 0.44464054703712463,
+      "learning_rate": 0.0002,
+      "loss": 1.589,
+      "step": 1750
+    },
+    {
+      "epoch": 2.3513694054776217,
+      "grad_norm": 0.4449476897716522,
+      "learning_rate": 0.0002,
+      "loss": 1.6139,
+      "step": 1760
+    },
+    {
+      "epoch": 2.364729458917836,
+      "grad_norm": 0.4216482937335968,
+      "learning_rate": 0.0002,
+      "loss": 1.7195,
+      "step": 1770
+    },
+    {
+      "epoch": 2.3780895123580494,
+      "grad_norm": 0.4379308521747589,
+      "learning_rate": 0.0002,
+      "loss": 1.7075,
+      "step": 1780
+    },
+    {
+      "epoch": 2.391449565798263,
+      "grad_norm": 0.41670042276382446,
+      "learning_rate": 0.0002,
+      "loss": 1.7024,
+      "step": 1790
+    },
+    {
+      "epoch": 2.404809619238477,
+      "grad_norm": 0.48089510202407837,
+      "learning_rate": 0.0002,
+      "loss": 1.5989,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4181696726786908,
+      "grad_norm": 0.4389738142490387,
+      "learning_rate": 0.0002,
+      "loss": 1.6313,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4315297261189044,
+      "grad_norm": 0.45293036103248596,
+      "learning_rate": 0.0002,
+      "loss": 1.5841,
+      "step": 1820
+    },
+    {
+      "epoch": 2.4448897795591185,
+      "grad_norm": 0.5211683511734009,
+      "learning_rate": 0.0002,
+      "loss": 1.6887,
+      "step": 1830
+    },
+    {
+      "epoch": 2.458249832999332,
+      "grad_norm": 0.4631884694099426,
+      "learning_rate": 0.0002,
+      "loss": 1.6599,
+      "step": 1840
+    },
+    {
+      "epoch": 2.4716098864395457,
+      "grad_norm": 0.4276818335056305,
+      "learning_rate": 0.0002,
+      "loss": 1.6537,
+      "step": 1850
+    },
+    {
+      "epoch": 2.4849699398797593,
+      "grad_norm": 0.477524071931839,
+      "learning_rate": 0.0002,
+      "loss": 1.6836,
+      "step": 1860
+    },
+    {
+      "epoch": 2.4983299933199734,
+      "grad_norm": 0.44860973954200745,
+      "learning_rate": 0.0002,
+      "loss": 1.66,
+      "step": 1870
+    },
+    {
+      "epoch": 2.511690046760187,
+      "grad_norm": 0.46413546800613403,
+      "learning_rate": 0.0002,
+      "loss": 1.6308,
+      "step": 1880
+    },
+    {
+      "epoch": 2.5250501002004007,
+      "grad_norm": 0.42487645149230957,
+      "learning_rate": 0.0002,
+      "loss": 1.6225,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5384101536406147,
+      "grad_norm": 0.4778307378292084,
+      "learning_rate": 0.0002,
+      "loss": 1.6268,
+      "step": 1900
+    },
+    {
+      "epoch": 2.5517702070808284,
+      "grad_norm": 0.45307061076164246,
+      "learning_rate": 0.0002,
+      "loss": 1.6143,
+      "step": 1910
+    },
+    {
+      "epoch": 2.565130260521042,
+      "grad_norm": 0.47886642813682556,
+      "learning_rate": 0.0002,
+      "loss": 1.7279,
+      "step": 1920
+    },
+    {
+      "epoch": 2.5784903139612556,
+      "grad_norm": 0.4839435815811157,
+      "learning_rate": 0.0002,
+      "loss": 1.5931,
+      "step": 1930
+    },
+    {
+      "epoch": 2.5918503674014697,
+      "grad_norm": 0.4388359785079956,
+      "learning_rate": 0.0002,
+      "loss": 1.6089,
+      "step": 1940
+    },
+    {
+      "epoch": 2.6052104208416833,
+      "grad_norm": 0.47859734296798706,
+      "learning_rate": 0.0002,
+      "loss": 1.6828,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6185704742818974,
+      "grad_norm": 0.5526517033576965,
+      "learning_rate": 0.0002,
+      "loss": 1.6014,
+      "step": 1960
+    },
+    {
+      "epoch": 2.631930527722111,
+      "grad_norm": 0.5449170470237732,
+      "learning_rate": 0.0002,
+      "loss": 1.6889,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6452905811623246,
+      "grad_norm": 0.48521968722343445,
+      "learning_rate": 0.0002,
+      "loss": 1.6481,
+      "step": 1980
+    },
+    {
+      "epoch": 2.6586506346025383,
+      "grad_norm": 0.4733737111091614,
+      "learning_rate": 0.0002,
+      "loss": 1.6741,
+      "step": 1990
+    },
+    {
+      "epoch": 2.6720106880427523,
+      "grad_norm": 0.507118284702301,
+      "learning_rate": 0.0002,
+      "loss": 1.662,
+      "step": 2000
+    },
+    {
+      "epoch": 2.685370741482966,
+      "grad_norm": 0.4508971571922302,
+      "learning_rate": 0.0002,
+      "loss": 1.6419,
+      "step": 2010
+    },
+    {
+      "epoch": 2.6987307949231796,
+      "grad_norm": 0.4657728672027588,
+      "learning_rate": 0.0002,
+      "loss": 1.7052,
+      "step": 2020
+    },
+    {
+      "epoch": 2.7120908483633936,
+      "grad_norm": 0.48647549748420715,
+      "learning_rate": 0.0002,
+      "loss": 1.6261,
+      "step": 2030
+    },
+    {
+      "epoch": 2.7254509018036073,
+      "grad_norm": 0.49525555968284607,
+      "learning_rate": 0.0002,
+      "loss": 1.5638,
+      "step": 2040
+    },
+    {
+      "epoch": 2.738810955243821,
+      "grad_norm": 0.4712379276752472,
+      "learning_rate": 0.0002,
+      "loss": 1.658,
+      "step": 2050
+    },
+    {
+      "epoch": 2.7521710086840345,
+      "grad_norm": 0.4846591055393219,
+      "learning_rate": 0.0002,
+      "loss": 1.6464,
+      "step": 2060
+    },
+    {
+      "epoch": 2.7655310621242486,
+      "grad_norm": 0.4823240041732788,
+      "learning_rate": 0.0002,
+      "loss": 1.5641,
+      "step": 2070
+    },
+    {
+      "epoch": 2.778891115564462,
+      "grad_norm": 0.4546685516834259,
+      "learning_rate": 0.0002,
+      "loss": 1.6701,
+      "step": 2080
+    },
+    {
+      "epoch": 2.7922511690046763,
+      "grad_norm": 0.45542681217193604,
+      "learning_rate": 0.0002,
+      "loss": 1.7015,
+      "step": 2090
+    },
+    {
+      "epoch": 2.80561122244489,
+      "grad_norm": 0.42137566208839417,
+      "learning_rate": 0.0002,
+      "loss": 1.6398,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8189712758851035,
+      "grad_norm": 0.6143282055854797,
+      "learning_rate": 0.0002,
+      "loss": 1.6526,
+      "step": 2110
+    },
+    {
+      "epoch": 2.832331329325317,
+      "grad_norm": 0.4828081727027893,
+      "learning_rate": 0.0002,
+      "loss": 1.6955,
+      "step": 2120
+    },
+    {
+      "epoch": 2.845691382765531,
+      "grad_norm": 0.4319005608558655,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 2130
+    },
+    {
+      "epoch": 2.859051436205745,
+      "grad_norm": 0.4297086298465729,
+      "learning_rate": 0.0002,
+      "loss": 1.6717,
+      "step": 2140
+    },
+    {
+      "epoch": 2.8724114896459585,
+      "grad_norm": 0.5011981129646301,
+      "learning_rate": 0.0002,
+      "loss": 1.5968,
+      "step": 2150
+    },
+    {
+      "epoch": 2.8857715430861726,
+      "grad_norm": 0.4401548504829407,
+      "learning_rate": 0.0002,
+      "loss": 1.7181,
+      "step": 2160
+    },
+    {
+      "epoch": 2.899131596526386,
+      "grad_norm": 0.48090746998786926,
+      "learning_rate": 0.0002,
+      "loss": 1.5722,
+      "step": 2170
+    },
+    {
+      "epoch": 2.9124916499666,
+      "grad_norm": 0.4740385413169861,
+      "learning_rate": 0.0002,
+      "loss": 1.6596,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9258517034068134,
+      "grad_norm": 0.5337260365486145,
+      "learning_rate": 0.0002,
+      "loss": 1.6501,
+      "step": 2190
+    },
+    {
+      "epoch": 2.9392117568470275,
+      "grad_norm": 0.4420052766799927,
+      "learning_rate": 0.0002,
+      "loss": 1.6802,
+      "step": 2200
+    },
+    {
+      "epoch": 2.952571810287241,
+      "grad_norm": 0.477512389421463,
+      "learning_rate": 0.0002,
+      "loss": 1.5474,
+      "step": 2210
+    },
+    {
+      "epoch": 2.9659318637274548,
+      "grad_norm": 0.5344052910804749,
+      "learning_rate": 0.0002,
+      "loss": 1.6544,
+      "step": 2220
+    },
+    {
+      "epoch": 2.979291917167669,
+      "grad_norm": 0.4483940303325653,
+      "learning_rate": 0.0002,
+      "loss": 1.6866,
+      "step": 2230
+    },
+    {
+      "epoch": 2.9926519706078825,
+      "grad_norm": 0.4366597831249237,
+      "learning_rate": 0.0002,
+      "loss": 1.6477,
+      "step": 2240
+    },
+    {
+      "epoch": 2.9993319973279893,
+      "eval_loss": 1.834012746810913,
+      "eval_runtime": 38.5659,
+      "eval_samples_per_second": 13.354,
+      "eval_steps_per_second": 1.685,
+      "step": 2245
+    },
+    {
+      "epoch": 3.006012024048096,
+      "grad_norm": 0.428824245929718,
+      "learning_rate": 0.0002,
+      "loss": 1.5582,
+      "step": 2250
+    },
+    {
+      "epoch": 3.01937207748831,
+      "grad_norm": 0.4870174825191498,
+      "learning_rate": 0.0002,
+      "loss": 1.499,
+      "step": 2260
+    },
+    {
+      "epoch": 3.032732130928524,
+      "grad_norm": 0.4684266149997711,
+      "learning_rate": 0.0002,
+      "loss": 1.4872,
+      "step": 2270
+    },
+    {
+      "epoch": 3.0460921843687374,
+      "grad_norm": 0.581604540348053,
+      "learning_rate": 0.0002,
+      "loss": 1.5284,
+      "step": 2280
+    },
+    {
+      "epoch": 3.059452237808951,
+      "grad_norm": 0.5561677813529968,
+      "learning_rate": 0.0002,
+      "loss": 1.4549,
+      "step": 2290
+    },
+    {
+      "epoch": 3.072812291249165,
+      "grad_norm": 0.5750220417976379,
+      "learning_rate": 0.0002,
+      "loss": 1.4903,
+      "step": 2300
+    },
+    {
+      "epoch": 3.0861723446893787,
+      "grad_norm": 0.5704626441001892,
+      "learning_rate": 0.0002,
+      "loss": 1.5903,
+      "step": 2310
+    },
+    {
+      "epoch": 3.0995323981295924,
+      "grad_norm": 0.6242083311080933,
+      "learning_rate": 0.0002,
+      "loss": 1.4292,
+      "step": 2320
+    },
+    {
+      "epoch": 3.1128924515698064,
+      "grad_norm": 0.5174121260643005,
+      "learning_rate": 0.0002,
+      "loss": 1.5092,
+      "step": 2330
+    },
+    {
+      "epoch": 3.12625250501002,
+      "grad_norm": 0.5697633028030396,
+      "learning_rate": 0.0002,
+      "loss": 1.5106,
+      "step": 2340
+    },
+    {
+      "epoch": 3.1396125584502337,
+      "grad_norm": 0.5969541072845459,
+      "learning_rate": 0.0002,
+      "loss": 1.5156,
+      "step": 2350
+    },
+    {
+      "epoch": 3.1529726118904478,
+      "grad_norm": 0.6244304180145264,
+      "learning_rate": 0.0002,
+      "loss": 1.52,
+      "step": 2360
+    },
+    {
+      "epoch": 3.1663326653306614,
+      "grad_norm": 0.5561705827713013,
+      "learning_rate": 0.0002,
+      "loss": 1.5244,
+      "step": 2370
+    },
+    {
+      "epoch": 3.179692718770875,
+      "grad_norm": 0.5401188135147095,
+      "learning_rate": 0.0002,
+      "loss": 1.6169,
+      "step": 2380
+    },
+    {
+      "epoch": 3.1930527722110886,
+      "grad_norm": 0.6450421810150146,
+      "learning_rate": 0.0002,
+      "loss": 1.5387,
+      "step": 2390
+    },
+    {
+      "epoch": 3.2064128256513027,
+      "grad_norm": 0.5741903185844421,
+      "learning_rate": 0.0002,
+      "loss": 1.4839,
+      "step": 2400
+    },
+    {
+      "epoch": 3.2197728790915163,
+      "grad_norm": 0.6337407231330872,
+      "learning_rate": 0.0002,
+      "loss": 1.5584,
+      "step": 2410
+    },
+    {
+      "epoch": 3.23313293253173,
+      "grad_norm": 0.6493517160415649,
+      "learning_rate": 0.0002,
+      "loss": 1.5025,
+      "step": 2420
+    },
+    {
+      "epoch": 3.246492985971944,
+      "grad_norm": 0.6230176091194153,
+      "learning_rate": 0.0002,
+      "loss": 1.5168,
+      "step": 2430
+    },
+    {
+      "epoch": 3.2598530394121576,
+      "grad_norm": 0.680704653263092,
+      "learning_rate": 0.0002,
+      "loss": 1.5408,
+      "step": 2440
+    },
+    {
+      "epoch": 3.2732130928523713,
+      "grad_norm": 0.5279417037963867,
+      "learning_rate": 0.0002,
+      "loss": 1.6005,
+      "step": 2450
+    },
+    {
+      "epoch": 3.2865731462925853,
+      "grad_norm": 0.5601515173912048,
+      "learning_rate": 0.0002,
+      "loss": 1.5231,
+      "step": 2460
+    },
+    {
+      "epoch": 3.299933199732799,
+      "grad_norm": 0.5591090321540833,
+      "learning_rate": 0.0002,
+      "loss": 1.4949,
+      "step": 2470
+    },
+    {
+      "epoch": 3.3132932531730126,
+      "grad_norm": 0.6596529483795166,
+      "learning_rate": 0.0002,
+      "loss": 1.5181,
+      "step": 2480
+    },
+    {
+      "epoch": 3.3266533066132267,
+      "grad_norm": 0.6115918755531311,
+      "learning_rate": 0.0002,
+      "loss": 1.5259,
+      "step": 2490
+    },
+    {
+      "epoch": 3.3400133600534403,
+      "grad_norm": 0.6443548202514648,
+      "learning_rate": 0.0002,
+      "loss": 1.5344,
+      "step": 2500
+    },
+    {
+      "epoch": 3.353373413493654,
+      "grad_norm": 0.5504242181777954,
+      "learning_rate": 0.0002,
+      "loss": 1.5037,
+      "step": 2510
+    },
+    {
+      "epoch": 3.3667334669338675,
+      "grad_norm": 0.6104483604431152,
+      "learning_rate": 0.0002,
+      "loss": 1.5049,
+      "step": 2520
+    },
+    {
+      "epoch": 3.3800935203740816,
+      "grad_norm": 0.8387531638145447,
+      "learning_rate": 0.0002,
+      "loss": 1.587,
+      "step": 2530
+    },
+    {
+      "epoch": 3.3934535738142952,
+      "grad_norm": 0.6346094012260437,
+      "learning_rate": 0.0002,
+      "loss": 1.5227,
+      "step": 2540
+    },
+    {
+      "epoch": 3.406813627254509,
+      "grad_norm": 0.6261265873908997,
+      "learning_rate": 0.0002,
+      "loss": 1.4855,
+      "step": 2550
+    },
+    {
+      "epoch": 3.420173680694723,
+      "grad_norm": 0.5960372090339661,
+      "learning_rate": 0.0002,
+      "loss": 1.5233,
+      "step": 2560
+    },
+    {
+      "epoch": 3.4335337341349366,
+      "grad_norm": 0.5291280746459961,
+      "learning_rate": 0.0002,
+      "loss": 1.5153,
+      "step": 2570
+    },
+    {
+      "epoch": 3.44689378757515,
+      "grad_norm": 0.6133161783218384,
+      "learning_rate": 0.0002,
+      "loss": 1.5152,
+      "step": 2580
+    },
+    {
+      "epoch": 3.460253841015364,
+      "grad_norm": 0.623573362827301,
+      "learning_rate": 0.0002,
+      "loss": 1.5533,
+      "step": 2590
+    },
+    {
+      "epoch": 3.473613894455578,
+      "grad_norm": 0.5959834456443787,
+      "learning_rate": 0.0002,
+      "loss": 1.4935,
+      "step": 2600
+    },
+    {
+      "epoch": 3.4869739478957915,
+      "grad_norm": 0.583332359790802,
+      "learning_rate": 0.0002,
+      "loss": 1.5792,
+      "step": 2610
+    },
+    {
+      "epoch": 3.5003340013360056,
+      "grad_norm": 0.6003559231758118,
+      "learning_rate": 0.0002,
+      "loss": 1.5229,
+      "step": 2620
+    },
+    {
+      "epoch": 3.513694054776219,
+      "grad_norm": 0.5832992196083069,
+      "learning_rate": 0.0002,
+      "loss": 1.4901,
+      "step": 2630
+    },
+    {
+      "epoch": 3.527054108216433,
+      "grad_norm": 0.5942609906196594,
+      "learning_rate": 0.0002,
+      "loss": 1.5005,
+      "step": 2640
+    },
+    {
+      "epoch": 3.5404141616566465,
+      "grad_norm": 0.6087163686752319,
+      "learning_rate": 0.0002,
+      "loss": 1.5213,
+      "step": 2650
+    },
+    {
+      "epoch": 3.5537742150968605,
+      "grad_norm": 0.631948709487915,
+      "learning_rate": 0.0002,
+      "loss": 1.5826,
+      "step": 2660
+    },
+    {
+      "epoch": 3.567134268537074,
+      "grad_norm": 0.6450803279876709,
+      "learning_rate": 0.0002,
+      "loss": 1.5844,
+      "step": 2670
+    },
+    {
+      "epoch": 3.580494321977288,
+      "grad_norm": 0.6507797837257385,
+      "learning_rate": 0.0002,
+      "loss": 1.4981,
+      "step": 2680
+    },
+    {
+      "epoch": 3.593854375417502,
+      "grad_norm": 0.5778017044067383,
+      "learning_rate": 0.0002,
+      "loss": 1.5826,
+      "step": 2690
+    },
+    {
+      "epoch": 3.6072144288577155,
+      "grad_norm": 0.6214032173156738,
+      "learning_rate": 0.0002,
+      "loss": 1.4688,
+      "step": 2700
+    },
+    {
+      "epoch": 3.620574482297929,
+      "grad_norm": 0.5681133270263672,
+      "learning_rate": 0.0002,
+      "loss": 1.5084,
+      "step": 2710
+    },
+    {
+      "epoch": 3.6339345357381427,
+      "grad_norm": 0.6074244976043701,
+      "learning_rate": 0.0002,
+      "loss": 1.471,
+      "step": 2720
+    },
+    {
+      "epoch": 3.647294589178357,
+      "grad_norm": 0.5900560617446899,
+      "learning_rate": 0.0002,
+      "loss": 1.5243,
+      "step": 2730
+    },
+    {
+      "epoch": 3.6606546426185704,
+      "grad_norm": 0.5817505717277527,
+      "learning_rate": 0.0002,
+      "loss": 1.5074,
+      "step": 2740
+    },
+    {
+      "epoch": 3.6740146960587845,
+      "grad_norm": 0.6095547676086426,
+      "learning_rate": 0.0002,
+      "loss": 1.5117,
+      "step": 2750
+    },
+    {
+      "epoch": 3.687374749498998,
+      "grad_norm": 0.612790584564209,
+      "learning_rate": 0.0002,
+      "loss": 1.5117,
+      "step": 2760
+    },
+    {
+      "epoch": 3.7007348029392118,
+      "grad_norm": 0.6574140787124634,
+      "learning_rate": 0.0002,
+      "loss": 1.4976,
+      "step": 2770
+    },
+    {
+      "epoch": 3.7140948563794254,
+      "grad_norm": 0.5643761157989502,
+      "learning_rate": 0.0002,
+      "loss": 1.5306,
+      "step": 2780
+    },
+    {
+      "epoch": 3.727454909819639,
+      "grad_norm": 0.5652621388435364,
+      "learning_rate": 0.0002,
+      "loss": 1.5751,
+      "step": 2790
+    },
+    {
+      "epoch": 3.740814963259853,
+      "grad_norm": 0.5604206323623657,
+      "learning_rate": 0.0002,
+      "loss": 1.5262,
+      "step": 2800
+    },
+    {
+      "epoch": 3.7541750167000667,
+      "grad_norm": 3.911022663116455,
+      "learning_rate": 0.0002,
+      "loss": 1.5013,
+      "step": 2810
+    },
+    {
+      "epoch": 3.7675350701402808,
+      "grad_norm": 0.6148333549499512,
+      "learning_rate": 0.0002,
+      "loss": 1.5793,
+      "step": 2820
+    },
+    {
+      "epoch": 3.7808951235804944,
+      "grad_norm": 0.5605677962303162,
+      "learning_rate": 0.0002,
+      "loss": 1.5122,
+      "step": 2830
+    },
+    {
+      "epoch": 3.794255177020708,
+      "grad_norm": 0.6101965308189392,
+      "learning_rate": 0.0002,
+      "loss": 1.5659,
+      "step": 2840
+    },
+    {
+      "epoch": 3.8076152304609217,
+      "grad_norm": 0.5387342572212219,
+      "learning_rate": 0.0002,
+      "loss": 1.5618,
+      "step": 2850
+    },
+    {
+      "epoch": 3.8209752839011357,
+      "grad_norm": 0.5733087062835693,
+      "learning_rate": 0.0002,
+      "loss": 1.5193,
+      "step": 2860
+    },
+    {
+      "epoch": 3.8343353373413493,
+      "grad_norm": 0.6538485884666443,
+      "learning_rate": 0.0002,
+      "loss": 1.5545,
+      "step": 2870
+    },
+    {
+      "epoch": 3.847695390781563,
+      "grad_norm": 0.6247632503509521,
+      "learning_rate": 0.0002,
+      "loss": 1.523,
+      "step": 2880
+    },
+    {
+      "epoch": 3.861055444221777,
+      "grad_norm": 0.5745735764503479,
+      "learning_rate": 0.0002,
+      "loss": 1.5591,
+      "step": 2890
+    },
+    {
+      "epoch": 3.8744154976619907,
+      "grad_norm": 0.5942763686180115,
+      "learning_rate": 0.0002,
+      "loss": 1.5706,
+      "step": 2900
+    },
+    {
+      "epoch": 3.8877755511022043,
+      "grad_norm": 0.7086281776428223,
+      "learning_rate": 0.0002,
+      "loss": 1.564,
+      "step": 2910
+    },
+    {
+      "epoch": 3.901135604542418,
+      "grad_norm": 0.8825129866600037,
+      "learning_rate": 0.0002,
+      "loss": 1.5526,
+      "step": 2920
+    },
+    {
+      "epoch": 3.914495657982632,
+      "grad_norm": 0.6260842680931091,
+      "learning_rate": 0.0002,
+      "loss": 1.4519,
+      "step": 2930
+    },
+    {
+      "epoch": 3.9278557114228456,
+      "grad_norm": 0.6015968322753906,
+      "learning_rate": 0.0002,
+      "loss": 1.5433,
+      "step": 2940
+    },
+    {
+      "epoch": 3.9412157648630597,
+      "grad_norm": 0.7042809128761292,
+      "learning_rate": 0.0002,
+      "loss": 1.4931,
+      "step": 2950
+    },
+    {
+      "epoch": 3.9545758183032733,
+      "grad_norm": 0.5860083699226379,
+      "learning_rate": 0.0002,
+      "loss": 1.5596,
+      "step": 2960
+    },
+    {
+      "epoch": 3.967935871743487,
+      "grad_norm": 0.5939757823944092,
+      "learning_rate": 0.0002,
+      "loss": 1.565,
+      "step": 2970
+    },
+    {
+      "epoch": 3.9812959251837006,
+      "grad_norm": 0.5523964166641235,
+      "learning_rate": 0.0002,
+      "loss": 1.408,
+      "step": 2980
+    },
+    {
+      "epoch": 3.9946559786239146,
+      "grad_norm": 0.6380264759063721,
+      "learning_rate": 0.0002,
+      "loss": 1.5629,
+      "step": 2990
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.8875294923782349,
+      "eval_runtime": 38.5837,
+      "eval_samples_per_second": 13.348,
+      "eval_steps_per_second": 1.685,
+      "step": 2994
+    },
+    {
+      "epoch": 4.008016032064128,
+      "grad_norm": 0.5478564500808716,
+      "learning_rate": 0.0002,
+      "loss": 1.4002,
+      "step": 3000
+    },
+    {
+      "epoch": 4.021376085504342,
+      "grad_norm": 0.9384379982948303,
+      "learning_rate": 0.0002,
+      "loss": 1.436,
+      "step": 3010
+    },
+    {
+      "epoch": 4.034736138944556,
+      "grad_norm": 0.7819344401359558,
+      "learning_rate": 0.0002,
+      "loss": 1.4127,
+      "step": 3020
+    },
+    {
+      "epoch": 4.04809619238477,
+      "grad_norm": 0.7737417817115784,
+      "learning_rate": 0.0002,
+      "loss": 1.326,
+      "step": 3030
+    },
+    {
+      "epoch": 4.061456245824983,
+      "grad_norm": 0.8893805742263794,
+      "learning_rate": 0.0002,
+      "loss": 1.3203,
+      "step": 3040
+    },
+    {
+      "epoch": 4.074816299265197,
+      "grad_norm": 0.7759843468666077,
+      "learning_rate": 0.0002,
+      "loss": 1.3913,
+      "step": 3050
+    },
+    {
+      "epoch": 4.0881763527054105,
+      "grad_norm": 0.642654538154602,
+      "learning_rate": 0.0002,
+      "loss": 1.2941,
+      "step": 3060
+    },
+    {
+      "epoch": 4.101536406145625,
+      "grad_norm": 0.8515549302101135,
+      "learning_rate": 0.0002,
+      "loss": 1.3204,
+      "step": 3070
+    },
+    {
+      "epoch": 4.114896459585839,
+      "grad_norm": 0.7033658623695374,
+      "learning_rate": 0.0002,
+      "loss": 1.3683,
+      "step": 3080
+    },
+    {
+      "epoch": 4.128256513026052,
+      "grad_norm": 0.7063882946968079,
+      "learning_rate": 0.0002,
+      "loss": 1.4159,
+      "step": 3090
+    },
+    {
+      "epoch": 4.141616566466266,
+      "grad_norm": 0.6946853995323181,
+      "learning_rate": 0.0002,
+      "loss": 1.384,
+      "step": 3100
+    },
+    {
+      "epoch": 4.1549766199064795,
+      "grad_norm": 0.7286741137504578,
+      "learning_rate": 0.0002,
+      "loss": 1.3689,
+      "step": 3110
+    },
+    {
+      "epoch": 4.168336673346693,
+      "grad_norm": 0.7894193530082703,
+      "learning_rate": 0.0002,
+      "loss": 1.3061,
+      "step": 3120
+    },
+    {
+      "epoch": 4.181696726786907,
+      "grad_norm": 0.7005895376205444,
+      "learning_rate": 0.0002,
+      "loss": 1.3346,
+      "step": 3130
+    },
+    {
+      "epoch": 4.195056780227121,
+      "grad_norm": 0.799567461013794,
+      "learning_rate": 0.0002,
+      "loss": 1.3834,
+      "step": 3140
+    },
+    {
+      "epoch": 4.208416833667335,
+      "grad_norm": 0.7010157108306885,
+      "learning_rate": 0.0002,
+      "loss": 1.3813,
+      "step": 3150
+    },
+    {
+      "epoch": 4.2217768871075485,
+      "grad_norm": 0.7489650249481201,
+      "learning_rate": 0.0002,
+      "loss": 1.3637,
+      "step": 3160
+    },
+    {
+      "epoch": 4.235136940547762,
+      "grad_norm": 0.7908048629760742,
+      "learning_rate": 0.0002,
+      "loss": 1.3546,
+      "step": 3170
+    },
+    {
+      "epoch": 4.248496993987976,
+      "grad_norm": 0.7002180814743042,
+      "learning_rate": 0.0002,
+      "loss": 1.3073,
+      "step": 3180
+    },
+    {
+      "epoch": 4.261857047428189,
+      "grad_norm": 0.8339495062828064,
+      "learning_rate": 0.0002,
+      "loss": 1.4525,
+      "step": 3190
+    },
+    {
+      "epoch": 4.275217100868403,
+      "grad_norm": 0.7884618043899536,
+      "learning_rate": 0.0002,
+      "loss": 1.3471,
+      "step": 3200
+    },
+    {
+      "epoch": 4.2885771543086175,
+      "grad_norm": 0.7964122295379639,
+      "learning_rate": 0.0002,
+      "loss": 1.4261,
+      "step": 3210
+    },
+    {
+      "epoch": 4.301937207748831,
+      "grad_norm": 0.838646650314331,
+      "learning_rate": 0.0002,
+      "loss": 1.3506,
+      "step": 3220
+    },
+    {
+      "epoch": 4.315297261189045,
+      "grad_norm": 0.8063107132911682,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 3230
+    },
+    {
+      "epoch": 4.328657314629258,
+      "grad_norm": 0.8147385120391846,
+      "learning_rate": 0.0002,
+      "loss": 1.3769,
+      "step": 3240
+    },
+    {
+      "epoch": 4.342017368069472,
+      "grad_norm": 0.7636798620223999,
+      "learning_rate": 0.0002,
+      "loss": 1.4118,
+      "step": 3250
+    },
+    {
+      "epoch": 4.355377421509686,
+      "grad_norm": 0.7530609965324402,
+      "learning_rate": 0.0002,
+      "loss": 1.3698,
+      "step": 3260
+    },
+    {
+      "epoch": 4.3687374749499,
+      "grad_norm": 0.8853573799133301,
+      "learning_rate": 0.0002,
+      "loss": 1.3507,
+      "step": 3270
+    },
+    {
+      "epoch": 4.382097528390114,
+      "grad_norm": 0.7180975675582886,
+      "learning_rate": 0.0002,
+      "loss": 1.3614,
+      "step": 3280
+    },
+    {
+      "epoch": 4.395457581830327,
+      "grad_norm": 0.837150514125824,
+      "learning_rate": 0.0002,
+      "loss": 1.4119,
+      "step": 3290
+    },
+    {
+      "epoch": 4.408817635270541,
+      "grad_norm": 0.8370638489723206,
+      "learning_rate": 0.0002,
+      "loss": 1.461,
+      "step": 3300
+    },
+    {
+      "epoch": 4.422177688710755,
+      "grad_norm": 0.7738229036331177,
+      "learning_rate": 0.0002,
+      "loss": 1.4478,
+      "step": 3310
+    },
+    {
+      "epoch": 4.435537742150968,
+      "grad_norm": 0.7665290832519531,
+      "learning_rate": 0.0002,
+      "loss": 1.4195,
+      "step": 3320
+    },
+    {
+      "epoch": 4.448897795591183,
+      "grad_norm": 0.7547745704650879,
+      "learning_rate": 0.0002,
+      "loss": 1.3308,
+      "step": 3330
+    },
+    {
+      "epoch": 4.462257849031396,
+      "grad_norm": 0.7421861290931702,
+      "learning_rate": 0.0002,
+      "loss": 1.4165,
+      "step": 3340
+    },
+    {
+      "epoch": 4.47561790247161,
+      "grad_norm": 0.8042104244232178,
+      "learning_rate": 0.0002,
+      "loss": 1.4244,
+      "step": 3350
+    },
+    {
+      "epoch": 4.488977955911824,
+      "grad_norm": 0.8111839890480042,
+      "learning_rate": 0.0002,
+      "loss": 1.365,
+      "step": 3360
+    },
+    {
+      "epoch": 4.502338009352037,
+      "grad_norm": 0.7998340129852295,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 3370
+    },
+    {
+      "epoch": 4.515698062792251,
+      "grad_norm": 0.7668877243995667,
+      "learning_rate": 0.0002,
+      "loss": 1.3812,
+      "step": 3380
+    },
+    {
+      "epoch": 4.529058116232465,
+      "grad_norm": 0.7986718416213989,
+      "learning_rate": 0.0002,
+      "loss": 1.3972,
+      "step": 3390
+    },
+    {
+      "epoch": 4.542418169672679,
+      "grad_norm": 0.6806602478027344,
+      "learning_rate": 0.0002,
+      "loss": 1.3582,
+      "step": 3400
+    },
+    {
+      "epoch": 4.555778223112893,
+      "grad_norm": 0.8788819909095764,
+      "learning_rate": 0.0002,
+      "loss": 1.3942,
+      "step": 3410
+    },
+    {
+      "epoch": 4.569138276553106,
+      "grad_norm": 0.7499664425849915,
+      "learning_rate": 0.0002,
+      "loss": 1.3379,
+      "step": 3420
+    },
+    {
+      "epoch": 4.58249832999332,
+      "grad_norm": 0.7967109084129333,
+      "learning_rate": 0.0002,
+      "loss": 1.3823,
+      "step": 3430
+    },
+    {
+      "epoch": 4.595858383433534,
+      "grad_norm": 0.759639322757721,
+      "learning_rate": 0.0002,
+      "loss": 1.3531,
+      "step": 3440
+    },
+    {
+      "epoch": 4.609218436873747,
+      "grad_norm": 0.8327916264533997,
+      "learning_rate": 0.0002,
+      "loss": 1.3517,
+      "step": 3450
+    },
+    {
+      "epoch": 4.622578490313961,
+      "grad_norm": 0.7400892376899719,
+      "learning_rate": 0.0002,
+      "loss": 1.4619,
+      "step": 3460
+    },
+    {
+      "epoch": 4.635938543754175,
+      "grad_norm": 0.8116602301597595,
+      "learning_rate": 0.0002,
+      "loss": 1.3374,
+      "step": 3470
+    },
+    {
+      "epoch": 4.649298597194389,
+      "grad_norm": 0.7604362368583679,
+      "learning_rate": 0.0002,
+      "loss": 1.4445,
+      "step": 3480
+    },
+    {
+      "epoch": 4.662658650634603,
+      "grad_norm": 0.7397996783256531,
+      "learning_rate": 0.0002,
+      "loss": 1.3724,
+      "step": 3490
+    },
+    {
+      "epoch": 4.676018704074816,
+      "grad_norm": 0.869293749332428,
+      "learning_rate": 0.0002,
+      "loss": 1.4048,
+      "step": 3500
+    },
+    {
+      "epoch": 4.68937875751503,
+      "grad_norm": 0.6854358315467834,
+      "learning_rate": 0.0002,
+      "loss": 1.3873,
+      "step": 3510
+    },
+    {
+      "epoch": 4.7027388109552435,
+      "grad_norm": 0.8326661586761475,
+      "learning_rate": 0.0002,
+      "loss": 1.3413,
+      "step": 3520
+    },
+    {
+      "epoch": 4.716098864395457,
+      "grad_norm": 0.6887506246566772,
+      "learning_rate": 0.0002,
+      "loss": 1.3666,
+      "step": 3530
+    },
+    {
+      "epoch": 4.729458917835672,
+      "grad_norm": 3.837689161300659,
+      "learning_rate": 0.0002,
+      "loss": 1.4508,
+      "step": 3540
+    },
+    {
+      "epoch": 4.742818971275885,
+      "grad_norm": 0.6874563694000244,
+      "learning_rate": 0.0002,
+      "loss": 1.3775,
+      "step": 3550
+    },
+    {
+      "epoch": 4.756179024716099,
+      "grad_norm": 0.8340407609939575,
+      "learning_rate": 0.0002,
+      "loss": 1.3643,
+      "step": 3560
+    },
+    {
+      "epoch": 4.7695390781563125,
+      "grad_norm": 0.7286418676376343,
+      "learning_rate": 0.0002,
+      "loss": 1.3556,
+      "step": 3570
+    },
+    {
+      "epoch": 4.782899131596526,
+      "grad_norm": 0.7239373326301575,
+      "learning_rate": 0.0002,
+      "loss": 1.4338,
+      "step": 3580
+    },
+    {
+      "epoch": 4.796259185036741,
+      "grad_norm": 0.831310510635376,
+      "learning_rate": 0.0002,
+      "loss": 1.4697,
+      "step": 3590
+    },
+    {
+      "epoch": 4.809619238476954,
+      "grad_norm": 0.767715573310852,
+      "learning_rate": 0.0002,
+      "loss": 1.4146,
+      "step": 3600
+    },
+    {
+      "epoch": 4.822979291917168,
+      "grad_norm": 0.9013199210166931,
+      "learning_rate": 0.0002,
+      "loss": 1.4199,
+      "step": 3610
+    },
+    {
+      "epoch": 4.8363393453573815,
+      "grad_norm": 0.7543512582778931,
+      "learning_rate": 0.0002,
+      "loss": 1.4513,
+      "step": 3620
+    },
+    {
+      "epoch": 4.849699398797595,
+      "grad_norm": 0.7626057267189026,
+      "learning_rate": 0.0002,
+      "loss": 1.4218,
+      "step": 3630
+    },
+    {
+      "epoch": 4.863059452237809,
+      "grad_norm": 0.847079336643219,
+      "learning_rate": 0.0002,
+      "loss": 1.4102,
+      "step": 3640
+    },
+    {
+      "epoch": 4.876419505678022,
+      "grad_norm": 0.8273295760154724,
+      "learning_rate": 0.0002,
+      "loss": 1.5014,
+      "step": 3650
+    },
+    {
+      "epoch": 4.889779559118237,
+      "grad_norm": 0.7675244808197021,
+      "learning_rate": 0.0002,
+      "loss": 1.3806,
+      "step": 3660
+    },
+    {
+      "epoch": 4.9031396125584505,
+      "grad_norm": 0.9560356736183167,
+      "learning_rate": 0.0002,
+      "loss": 1.4894,
+      "step": 3670
+    },
+    {
+      "epoch": 4.916499665998664,
+      "grad_norm": 0.7682451605796814,
+      "learning_rate": 0.0002,
+      "loss": 1.4044,
+      "step": 3680
+    },
+    {
+      "epoch": 4.929859719438878,
+      "grad_norm": 0.8113830089569092,
+      "learning_rate": 0.0002,
+      "loss": 1.342,
+      "step": 3690
+    },
+    {
+      "epoch": 4.943219772879091,
+      "grad_norm": 0.7642542719841003,
+      "learning_rate": 0.0002,
+      "loss": 1.3559,
+      "step": 3700
+    },
+    {
+      "epoch": 4.956579826319305,
+      "grad_norm": 0.823863685131073,
+      "learning_rate": 0.0002,
+      "loss": 1.403,
+      "step": 3710
+    },
+    {
+      "epoch": 4.969939879759519,
+      "grad_norm": 0.8287797570228577,
+      "learning_rate": 0.0002,
+      "loss": 1.464,
+      "step": 3720
+    },
+    {
+      "epoch": 4.983299933199733,
+      "grad_norm": 0.778170108795166,
+      "learning_rate": 0.0002,
+      "loss": 1.4139,
+      "step": 3730
+    },
+    {
+      "epoch": 4.996659986639947,
+      "grad_norm": 0.7464073896408081,
+      "learning_rate": 0.0002,
+      "loss": 1.4218,
+      "step": 3740
+    },
+    {
+      "epoch": 4.999331997327989,
+      "eval_loss": 1.9638569355010986,
+      "eval_runtime": 38.5725,
+      "eval_samples_per_second": 13.351,
+      "eval_steps_per_second": 1.685,
+      "step": 3742
+    },
+    {
+      "epoch": 5.01002004008016,
+      "grad_norm": 0.8864085078239441,
+      "learning_rate": 0.0002,
+      "loss": 1.225,
+      "step": 3750
+    },
+    {
+      "epoch": 5.023380093520374,
+      "grad_norm": 0.9191637635231018,
+      "learning_rate": 0.0002,
+      "loss": 1.2056,
+      "step": 3760
+    },
+    {
+      "epoch": 5.036740146960588,
+      "grad_norm": 0.749519407749176,
+      "learning_rate": 0.0002,
+      "loss": 1.2453,
+      "step": 3770
+    },
+    {
+      "epoch": 5.050100200400801,
+      "grad_norm": 0.7916892170906067,
+      "learning_rate": 0.0002,
+      "loss": 1.1959,
+      "step": 3780
+    },
+    {
+      "epoch": 5.063460253841015,
+      "grad_norm": 1.0318909883499146,
+      "learning_rate": 0.0002,
+      "loss": 1.2279,
+      "step": 3790
+    },
+    {
+      "epoch": 5.0768203072812295,
+      "grad_norm": 1.028586745262146,
+      "learning_rate": 0.0002,
+      "loss": 1.2585,
+      "step": 3800
+    },
+    {
+      "epoch": 5.090180360721443,
+      "grad_norm": 1.0568538904190063,
+      "learning_rate": 0.0002,
+      "loss": 1.1769,
+      "step": 3810
+    },
+    {
+      "epoch": 5.103540414161657,
+      "grad_norm": 0.9780595302581787,
+      "learning_rate": 0.0002,
+      "loss": 1.263,
+      "step": 3820
+    },
+    {
+      "epoch": 5.11690046760187,
+      "grad_norm": 1.10311758518219,
+      "learning_rate": 0.0002,
+      "loss": 1.2019,
+      "step": 3830
+    },
+    {
+      "epoch": 5.130260521042084,
+      "grad_norm": 0.9497154355049133,
+      "learning_rate": 0.0002,
+      "loss": 1.2133,
+      "step": 3840
+    },
+    {
+      "epoch": 5.143620574482298,
+      "grad_norm": 0.948279857635498,
+      "learning_rate": 0.0002,
+      "loss": 1.1718,
+      "step": 3850
+    },
+    {
+      "epoch": 5.156980627922512,
+      "grad_norm": 0.9497880339622498,
+      "learning_rate": 0.0002,
+      "loss": 1.2108,
+      "step": 3860
+    },
+    {
+      "epoch": 5.170340681362726,
+      "grad_norm": 1.3213258981704712,
+      "learning_rate": 0.0002,
+      "loss": 1.1876,
+      "step": 3870
+    },
+    {
+      "epoch": 5.183700734802939,
+      "grad_norm": 0.9835752248764038,
+      "learning_rate": 0.0002,
+      "loss": 1.2327,
+      "step": 3880
+    },
+    {
+      "epoch": 5.197060788243153,
+      "grad_norm": 0.8426132202148438,
+      "learning_rate": 0.0002,
+      "loss": 1.2256,
+      "step": 3890
+    },
+    {
+      "epoch": 5.210420841683367,
+      "grad_norm": 1.0343470573425293,
+      "learning_rate": 0.0002,
+      "loss": 1.2066,
+      "step": 3900
+    },
+    {
+      "epoch": 5.22378089512358,
+      "grad_norm": 1.0771924257278442,
+      "learning_rate": 0.0002,
+      "loss": 1.2596,
+      "step": 3910
+    },
+    {
+      "epoch": 5.237140948563794,
+      "grad_norm": 0.8542634844779968,
+      "learning_rate": 0.0002,
+      "loss": 1.2371,
+      "step": 3920
+    },
+    {
+      "epoch": 5.250501002004008,
+      "grad_norm": 1.1021966934204102,
+      "learning_rate": 0.0002,
+      "loss": 1.2264,
+      "step": 3930
+    },
+    {
+      "epoch": 5.263861055444222,
+      "grad_norm": 1.170011281967163,
+      "learning_rate": 0.0002,
+      "loss": 1.2097,
+      "step": 3940
+    },
+    {
+      "epoch": 5.277221108884436,
+      "grad_norm": 0.9787653684616089,
+      "learning_rate": 0.0002,
+      "loss": 1.2101,
+      "step": 3950
+    },
+    {
+      "epoch": 5.290581162324649,
+      "grad_norm": 0.914513885974884,
+      "learning_rate": 0.0002,
+      "loss": 1.24,
+      "step": 3960
+    },
+    {
+      "epoch": 5.303941215764863,
+      "grad_norm": 1.0831562280654907,
+      "learning_rate": 0.0002,
+      "loss": 1.1641,
+      "step": 3970
+    },
+    {
+      "epoch": 5.3173012692050765,
+      "grad_norm": 0.9810112714767456,
+      "learning_rate": 0.0002,
+      "loss": 1.2609,
+      "step": 3980
+    },
+    {
+      "epoch": 5.330661322645291,
+      "grad_norm": 0.9624066948890686,
+      "learning_rate": 0.0002,
+      "loss": 1.1825,
+      "step": 3990
+    },
+    {
+      "epoch": 5.344021376085505,
+      "grad_norm": 1.2296923398971558,
+      "learning_rate": 0.0002,
+      "loss": 1.273,
+      "step": 4000
+    },
+    {
+      "epoch": 5.357381429525718,
+      "grad_norm": 1.011299967765808,
+      "learning_rate": 0.0002,
+      "loss": 1.2452,
+      "step": 4010
+    },
+    {
+      "epoch": 5.370741482965932,
+      "grad_norm": 0.9144132733345032,
+      "learning_rate": 0.0002,
+      "loss": 1.2539,
+      "step": 4020
+    },
+    {
+      "epoch": 5.3841015364061455,
+      "grad_norm": 1.0573601722717285,
+      "learning_rate": 0.0002,
+      "loss": 1.2914,
+      "step": 4030
+    },
+    {
+      "epoch": 5.397461589846359,
+      "grad_norm": 1.1667137145996094,
+      "learning_rate": 0.0002,
+      "loss": 1.2295,
+      "step": 4040
+    },
+    {
+      "epoch": 5.410821643286573,
+      "grad_norm": 1.072070598602295,
+      "learning_rate": 0.0002,
+      "loss": 1.2541,
+      "step": 4050
+    },
+    {
+      "epoch": 5.424181696726787,
+      "grad_norm": 1.1005792617797852,
+      "learning_rate": 0.0002,
+      "loss": 1.2448,
+      "step": 4060
+    },
+    {
+      "epoch": 5.437541750167001,
+      "grad_norm": 1.033581018447876,
+      "learning_rate": 0.0002,
+      "loss": 1.2604,
+      "step": 4070
+    },
+    {
+      "epoch": 5.4509018036072145,
+      "grad_norm": 0.9537439942359924,
+      "learning_rate": 0.0002,
+      "loss": 1.2552,
+      "step": 4080
+    },
+    {
+      "epoch": 5.464261857047428,
+      "grad_norm": 1.0502177476882935,
+      "learning_rate": 0.0002,
+      "loss": 1.2985,
+      "step": 4090
+    },
+    {
+      "epoch": 5.477621910487642,
+      "grad_norm": 0.9098296761512756,
+      "learning_rate": 0.0002,
+      "loss": 1.2424,
+      "step": 4100
+    },
+    {
+      "epoch": 5.490981963927855,
+      "grad_norm": 0.9551953077316284,
+      "learning_rate": 0.0002,
+      "loss": 1.2262,
+      "step": 4110
+    },
+    {
+      "epoch": 5.504342017368069,
+      "grad_norm": 0.9169427156448364,
+      "learning_rate": 0.0002,
+      "loss": 1.2848,
+      "step": 4120
+    },
+    {
+      "epoch": 5.517702070808284,
+      "grad_norm": 0.9430235624313354,
+      "learning_rate": 0.0002,
+      "loss": 1.2572,
+      "step": 4130
+    },
+    {
+      "epoch": 5.531062124248497,
+      "grad_norm": 0.817259669303894,
+      "learning_rate": 0.0002,
+      "loss": 1.2618,
+      "step": 4140
+    },
+    {
+      "epoch": 5.544422177688711,
+      "grad_norm": 1.124152660369873,
+      "learning_rate": 0.0002,
+      "loss": 1.3012,
+      "step": 4150
+    },
+    {
+      "epoch": 5.557782231128924,
+      "grad_norm": 0.9250756502151489,
+      "learning_rate": 0.0002,
+      "loss": 1.2508,
+      "step": 4160
+    },
+    {
+      "epoch": 5.571142284569138,
+      "grad_norm": 0.9582970142364502,
+      "learning_rate": 0.0002,
+      "loss": 1.2492,
+      "step": 4170
+    },
+    {
+      "epoch": 5.584502338009352,
+      "grad_norm": 1.0078704357147217,
+      "learning_rate": 0.0002,
+      "loss": 1.2804,
+      "step": 4180
+    },
+    {
+      "epoch": 5.597862391449565,
+      "grad_norm": 0.9585610032081604,
+      "learning_rate": 0.0002,
+      "loss": 1.1961,
+      "step": 4190
+    },
+    {
+      "epoch": 5.61122244488978,
+      "grad_norm": 1.0150971412658691,
+      "learning_rate": 0.0002,
+      "loss": 1.2522,
+      "step": 4200
+    },
+    {
+      "epoch": 5.6245824983299935,
+      "grad_norm": 0.9943351149559021,
+      "learning_rate": 0.0002,
+      "loss": 1.2275,
+      "step": 4210
+    },
+    {
+      "epoch": 5.637942551770207,
+      "grad_norm": 0.8880936503410339,
+      "learning_rate": 0.0002,
+      "loss": 1.2928,
+      "step": 4220
+    },
+    {
+      "epoch": 5.651302605210421,
+      "grad_norm": 0.9873887896537781,
+      "learning_rate": 0.0002,
+      "loss": 1.2323,
+      "step": 4230
+    },
+    {
+      "epoch": 5.664662658650634,
+      "grad_norm": 0.9185152649879456,
+      "learning_rate": 0.0002,
+      "loss": 1.3391,
+      "step": 4240
+    },
+    {
+      "epoch": 5.678022712090849,
+      "grad_norm": 1.0706779956817627,
+      "learning_rate": 0.0002,
+      "loss": 1.2511,
+      "step": 4250
+    },
+    {
+      "epoch": 5.6913827655310625,
+      "grad_norm": 0.9660224914550781,
+      "learning_rate": 0.0002,
+      "loss": 1.2737,
+      "step": 4260
+    },
+    {
+      "epoch": 5.704742818971276,
+      "grad_norm": 0.8685019612312317,
+      "learning_rate": 0.0002,
+      "loss": 1.2815,
+      "step": 4270
+    },
+    {
+      "epoch": 5.71810287241149,
+      "grad_norm": 1.0390565395355225,
+      "learning_rate": 0.0002,
+      "loss": 1.1559,
+      "step": 4280
+    },
+    {
+      "epoch": 5.731462925851703,
+      "grad_norm": 0.9290478825569153,
+      "learning_rate": 0.0002,
+      "loss": 1.3134,
+      "step": 4290
+    },
+    {
+      "epoch": 5.744822979291917,
+      "grad_norm": 1.0361281633377075,
+      "learning_rate": 0.0002,
+      "loss": 1.2426,
+      "step": 4300
+    },
+    {
+      "epoch": 5.758183032732131,
+      "grad_norm": 0.8804615139961243,
+      "learning_rate": 0.0002,
+      "loss": 1.2688,
+      "step": 4310
+    },
+    {
+      "epoch": 5.771543086172345,
+      "grad_norm": 1.0051425695419312,
+      "learning_rate": 0.0002,
+      "loss": 1.2479,
+      "step": 4320
+    },
+    {
+      "epoch": 5.784903139612559,
+      "grad_norm": 1.0051119327545166,
+      "learning_rate": 0.0002,
+      "loss": 1.1946,
+      "step": 4330
+    },
+    {
+      "epoch": 5.798263193052772,
+      "grad_norm": 0.9961661100387573,
+      "learning_rate": 0.0002,
+      "loss": 1.2571,
+      "step": 4340
+    },
+    {
+      "epoch": 5.811623246492986,
+      "grad_norm": 1.0229419469833374,
+      "learning_rate": 0.0002,
+      "loss": 1.2179,
+      "step": 4350
+    },
+    {
+      "epoch": 5.8249832999332,
+      "grad_norm": 1.1129552125930786,
+      "learning_rate": 0.0002,
+      "loss": 1.2984,
+      "step": 4360
+    },
+    {
+      "epoch": 5.838343353373413,
+      "grad_norm": 1.18964421749115,
+      "learning_rate": 0.0002,
+      "loss": 1.2692,
+      "step": 4370
+    },
+    {
+      "epoch": 5.851703406813627,
+      "grad_norm": 0.9490230083465576,
+      "learning_rate": 0.0002,
+      "loss": 1.1996,
+      "step": 4380
+    },
+    {
+      "epoch": 5.865063460253841,
+      "grad_norm": 0.8734540343284607,
+      "learning_rate": 0.0002,
+      "loss": 1.3177,
+      "step": 4390
+    },
+    {
+      "epoch": 5.878423513694055,
+      "grad_norm": 1.0017802715301514,
+      "learning_rate": 0.0002,
+      "loss": 1.3131,
+      "step": 4400
+    },
+    {
+      "epoch": 5.891783567134269,
+      "grad_norm": 0.953556478023529,
+      "learning_rate": 0.0002,
+      "loss": 1.2649,
+      "step": 4410
+    },
+    {
+      "epoch": 5.905143620574482,
+      "grad_norm": 0.8915258646011353,
+      "learning_rate": 0.0002,
+      "loss": 1.2684,
+      "step": 4420
+    },
+    {
+      "epoch": 5.918503674014696,
+      "grad_norm": 0.9715141654014587,
+      "learning_rate": 0.0002,
+      "loss": 1.2843,
+      "step": 4430
+    },
+    {
+      "epoch": 5.9318637274549095,
+      "grad_norm": 0.9432152509689331,
+      "learning_rate": 0.0002,
+      "loss": 1.2769,
+      "step": 4440
+    },
+    {
+      "epoch": 5.945223780895123,
+      "grad_norm": 0.9473979473114014,
+      "learning_rate": 0.0002,
+      "loss": 1.233,
+      "step": 4450
+    },
+    {
+      "epoch": 5.958583834335338,
+      "grad_norm": 1.104871392250061,
+      "learning_rate": 0.0002,
+      "loss": 1.3209,
+      "step": 4460
+    },
+    {
+      "epoch": 5.971943887775551,
+      "grad_norm": 1.0308905839920044,
+      "learning_rate": 0.0002,
+      "loss": 1.3427,
+      "step": 4470
+    },
+    {
+      "epoch": 5.985303941215765,
+      "grad_norm": 0.8895487189292908,
+      "learning_rate": 0.0002,
+      "loss": 1.1808,
+      "step": 4480
+    },
+    {
+      "epoch": 5.9986639946559785,
+      "grad_norm": 1.0148485898971558,
+      "learning_rate": 0.0002,
+      "loss": 1.2634,
+      "step": 4490
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.0830726623535156,
+      "eval_runtime": 38.5442,
+      "eval_samples_per_second": 13.361,
+      "eval_steps_per_second": 1.686,
+      "step": 4491
+    },
+    {
+      "epoch": 6.012024048096192,
+      "grad_norm": 1.1640599966049194,
+      "learning_rate": 0.0002,
+      "loss": 1.1106,
+      "step": 4500
+    },
+    {
+      "epoch": 6.025384101536406,
+      "grad_norm": 1.213204264640808,
+      "learning_rate": 0.0002,
+      "loss": 1.0436,
+      "step": 4510
+    },
+    {
+      "epoch": 6.03874415497662,
+      "grad_norm": 1.1694388389587402,
+      "learning_rate": 0.0002,
+      "loss": 1.0606,
+      "step": 4520
+    },
+    {
+      "epoch": 6.052104208416834,
+      "grad_norm": 1.1044062376022339,
+      "learning_rate": 0.0002,
+      "loss": 1.0274,
+      "step": 4530
+    },
+    {
+      "epoch": 6.065464261857048,
+      "grad_norm": 1.0701100826263428,
+      "learning_rate": 0.0002,
+      "loss": 1.0552,
+      "step": 4540
+    },
+    {
+      "epoch": 6.078824315297261,
+      "grad_norm": 1.360065221786499,
+      "learning_rate": 0.0002,
+      "loss": 1.0018,
+      "step": 4550
+    },
+    {
+      "epoch": 6.092184368737475,
+      "grad_norm": 1.0648503303527832,
+      "learning_rate": 0.0002,
+      "loss": 1.0189,
+      "step": 4560
+    },
+    {
+      "epoch": 6.1055444221776884,
+      "grad_norm": 1.066245198249817,
+      "learning_rate": 0.0002,
+      "loss": 1.008,
+      "step": 4570
+    },
+    {
+      "epoch": 6.118904475617902,
+      "grad_norm": 1.1483700275421143,
+      "learning_rate": 0.0002,
+      "loss": 1.099,
+      "step": 4580
+    },
+    {
+      "epoch": 6.132264529058117,
+      "grad_norm": 1.334275722503662,
+      "learning_rate": 0.0002,
+      "loss": 1.1043,
+      "step": 4590
+    },
+    {
+      "epoch": 6.14562458249833,
+      "grad_norm": 1.2141029834747314,
+      "learning_rate": 0.0002,
+      "loss": 1.0783,
+      "step": 4600
+    },
+    {
+      "epoch": 6.158984635938544,
+      "grad_norm": 1.2284387350082397,
+      "learning_rate": 0.0002,
+      "loss": 1.0891,
+      "step": 4610
+    },
+    {
+      "epoch": 6.1723446893787575,
+      "grad_norm": 1.2326734066009521,
+      "learning_rate": 0.0002,
+      "loss": 1.122,
+      "step": 4620
+    },
+    {
+      "epoch": 6.185704742818971,
+      "grad_norm": 1.245004653930664,
+      "learning_rate": 0.0002,
+      "loss": 1.1069,
+      "step": 4630
+    },
+    {
+      "epoch": 6.199064796259185,
+      "grad_norm": 0.9685266017913818,
+      "learning_rate": 0.0002,
+      "loss": 1.0821,
+      "step": 4640
+    },
+    {
+      "epoch": 6.212424849699399,
+      "grad_norm": 1.141634464263916,
+      "learning_rate": 0.0002,
+      "loss": 1.0659,
+      "step": 4650
+    },
+    {
+      "epoch": 6.225784903139613,
+      "grad_norm": 1.4279003143310547,
+      "learning_rate": 0.0002,
+      "loss": 1.0971,
+      "step": 4660
+    },
+    {
+      "epoch": 6.2391449565798265,
+      "grad_norm": 1.186668872833252,
+      "learning_rate": 0.0002,
+      "loss": 1.093,
+      "step": 4670
+    },
+    {
+      "epoch": 6.25250501002004,
+      "grad_norm": 1.2656606435775757,
+      "learning_rate": 0.0002,
+      "loss": 1.0522,
+      "step": 4680
+    },
+    {
+      "epoch": 6.265865063460254,
+      "grad_norm": 1.1122987270355225,
+      "learning_rate": 0.0002,
+      "loss": 1.1138,
+      "step": 4690
+    },
+    {
+      "epoch": 6.279225116900467,
+      "grad_norm": 1.190050482749939,
+      "learning_rate": 0.0002,
+      "loss": 1.0906,
+      "step": 4700
+    },
+    {
+      "epoch": 6.292585170340681,
+      "grad_norm": 1.3683340549468994,
+      "learning_rate": 0.0002,
+      "loss": 1.1095,
+      "step": 4710
+    },
+    {
+      "epoch": 6.3059452237808955,
+      "grad_norm": 1.1787203550338745,
+      "learning_rate": 0.0002,
+      "loss": 1.0663,
+      "step": 4720
+    },
+    {
+      "epoch": 6.319305277221109,
+      "grad_norm": 1.3502576351165771,
+      "learning_rate": 0.0002,
+      "loss": 1.0856,
+      "step": 4730
+    },
+    {
+      "epoch": 6.332665330661323,
+      "grad_norm": 1.1958597898483276,
+      "learning_rate": 0.0002,
+      "loss": 1.0999,
+      "step": 4740
+    },
+    {
+      "epoch": 6.346025384101536,
+      "grad_norm": 1.0918327569961548,
+      "learning_rate": 0.0002,
+      "loss": 1.021,
+      "step": 4750
+    },
+    {
+      "epoch": 6.35938543754175,
+      "grad_norm": 1.2624558210372925,
+      "learning_rate": 0.0002,
+      "loss": 1.0484,
+      "step": 4760
+    },
+    {
+      "epoch": 6.372745490981964,
+      "grad_norm": 1.1390577554702759,
+      "learning_rate": 0.0002,
+      "loss": 1.0785,
+      "step": 4770
+    },
+    {
+      "epoch": 6.386105544422177,
+      "grad_norm": 1.041666865348816,
+      "learning_rate": 0.0002,
+      "loss": 1.0979,
+      "step": 4780
+    },
+    {
+      "epoch": 6.399465597862392,
+      "grad_norm": 1.4209141731262207,
+      "learning_rate": 0.0002,
+      "loss": 1.1026,
+      "step": 4790
+    },
+    {
+      "epoch": 6.412825651302605,
+      "grad_norm": 1.1001079082489014,
+      "learning_rate": 0.0002,
+      "loss": 1.119,
+      "step": 4800
+    },
+    {
+      "epoch": 6.426185704742819,
+      "grad_norm": 1.3324936628341675,
+      "learning_rate": 0.0002,
+      "loss": 1.1082,
+      "step": 4810
+    },
+    {
+      "epoch": 6.439545758183033,
+      "grad_norm": 1.1270194053649902,
+      "learning_rate": 0.0002,
+      "loss": 1.0785,
+      "step": 4820
+    },
+    {
+      "epoch": 6.452905811623246,
+      "grad_norm": 1.1961387395858765,
+      "learning_rate": 0.0002,
+      "loss": 1.1338,
+      "step": 4830
+    },
+    {
+      "epoch": 6.46626586506346,
+      "grad_norm": 1.255366563796997,
+      "learning_rate": 0.0002,
+      "loss": 1.0967,
+      "step": 4840
+    },
+    {
+      "epoch": 6.479625918503674,
+      "grad_norm": 1.343855381011963,
+      "learning_rate": 0.0002,
+      "loss": 1.1226,
+      "step": 4850
+    },
+    {
+      "epoch": 6.492985971943888,
+      "grad_norm": 1.3216257095336914,
+      "learning_rate": 0.0002,
+      "loss": 1.1118,
+      "step": 4860
+    },
+    {
+      "epoch": 6.506346025384102,
+      "grad_norm": 1.5244755744934082,
+      "learning_rate": 0.0002,
+      "loss": 1.1664,
+      "step": 4870
+    },
+    {
+      "epoch": 6.519706078824315,
+      "grad_norm": 1.1585701704025269,
+      "learning_rate": 0.0002,
+      "loss": 1.0403,
+      "step": 4880
+    },
+    {
+      "epoch": 6.533066132264529,
+      "grad_norm": 1.0301100015640259,
+      "learning_rate": 0.0002,
+      "loss": 1.1344,
+      "step": 4890
+    },
+    {
+      "epoch": 6.5464261857047426,
+      "grad_norm": 1.5772714614868164,
+      "learning_rate": 0.0002,
+      "loss": 1.1304,
+      "step": 4900
+    },
+    {
+      "epoch": 6.559786239144957,
+      "grad_norm": 1.2015259265899658,
+      "learning_rate": 0.0002,
+      "loss": 1.0953,
+      "step": 4910
+    },
+    {
+      "epoch": 6.573146292585171,
+      "grad_norm": 1.4365423917770386,
+      "learning_rate": 0.0002,
+      "loss": 1.1283,
+      "step": 4920
+    },
+    {
+      "epoch": 6.586506346025384,
+      "grad_norm": 1.2534470558166504,
+      "learning_rate": 0.0002,
+      "loss": 1.0717,
+      "step": 4930
+    },
+    {
+      "epoch": 6.599866399465598,
+      "grad_norm": 1.216138482093811,
+      "learning_rate": 0.0002,
+      "loss": 1.1099,
+      "step": 4940
+    },
+    {
+      "epoch": 6.613226452905812,
+      "grad_norm": 1.144316554069519,
+      "learning_rate": 0.0002,
+      "loss": 1.1744,
+      "step": 4950
+    },
+    {
+      "epoch": 6.626586506346025,
+      "grad_norm": 1.1127740144729614,
+      "learning_rate": 0.0002,
+      "loss": 1.0548,
+      "step": 4960
+    },
+    {
+      "epoch": 6.639946559786239,
+      "grad_norm": 1.1925606727600098,
+      "learning_rate": 0.0002,
+      "loss": 1.0686,
+      "step": 4970
+    },
+    {
+      "epoch": 6.653306613226453,
+      "grad_norm": 1.2500451803207397,
+      "learning_rate": 0.0002,
+      "loss": 1.0684,
+      "step": 4980
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 1.16154944896698,
+      "learning_rate": 0.0002,
+      "loss": 1.1642,
+      "step": 4990
+    },
+    {
+      "epoch": 6.680026720106881,
+      "grad_norm": 1.1921433210372925,
+      "learning_rate": 0.0002,
+      "loss": 1.1003,
+      "step": 5000
+    },
+    {
+      "epoch": 6.693386773547094,
+      "grad_norm": 1.1561170816421509,
+      "learning_rate": 0.0002,
+      "loss": 1.1278,
+      "step": 5010
+    },
+    {
+      "epoch": 6.706746826987308,
+      "grad_norm": 1.2988990545272827,
+      "learning_rate": 0.0002,
+      "loss": 1.0766,
+      "step": 5020
+    },
+    {
+      "epoch": 6.7201068804275215,
+      "grad_norm": 0.9620341062545776,
+      "learning_rate": 0.0002,
+      "loss": 1.1131,
+      "step": 5030
+    },
+    {
+      "epoch": 6.733466933867735,
+      "grad_norm": 1.084228515625,
+      "learning_rate": 0.0002,
+      "loss": 1.109,
+      "step": 5040
+    },
+    {
+      "epoch": 6.74682698730795,
+      "grad_norm": 1.1119431257247925,
+      "learning_rate": 0.0002,
+      "loss": 1.1474,
+      "step": 5050
+    },
+    {
+      "epoch": 6.760187040748163,
+      "grad_norm": 1.1365628242492676,
+      "learning_rate": 0.0002,
+      "loss": 1.179,
+      "step": 5060
+    },
+    {
+      "epoch": 6.773547094188377,
+      "grad_norm": 1.0989075899124146,
+      "learning_rate": 0.0002,
+      "loss": 1.0988,
+      "step": 5070
+    },
+    {
+      "epoch": 6.7869071476285905,
+      "grad_norm": 1.040647268295288,
+      "learning_rate": 0.0002,
+      "loss": 1.127,
+      "step": 5080
+    },
+    {
+      "epoch": 6.800267201068804,
+      "grad_norm": 1.1083087921142578,
+      "learning_rate": 0.0002,
+      "loss": 1.0793,
+      "step": 5090
+    },
+    {
+      "epoch": 6.813627254509018,
+      "grad_norm": 1.3434782028198242,
+      "learning_rate": 0.0002,
+      "loss": 1.1081,
+      "step": 5100
+    },
+    {
+      "epoch": 6.826987307949231,
+      "grad_norm": 1.2493442296981812,
+      "learning_rate": 0.0002,
+      "loss": 1.1243,
+      "step": 5110
+    },
+    {
+      "epoch": 6.840347361389446,
+      "grad_norm": 1.0672307014465332,
+      "learning_rate": 0.0002,
+      "loss": 1.0633,
+      "step": 5120
+    },
+    {
+      "epoch": 6.8537074148296595,
+      "grad_norm": 1.068350911140442,
+      "learning_rate": 0.0002,
+      "loss": 1.1344,
+      "step": 5130
+    },
+    {
+      "epoch": 6.867067468269873,
+      "grad_norm": 1.2880923748016357,
+      "learning_rate": 0.0002,
+      "loss": 1.1942,
+      "step": 5140
+    },
+    {
+      "epoch": 6.880427521710087,
+      "grad_norm": 1.0895041227340698,
+      "learning_rate": 0.0002,
+      "loss": 1.1445,
+      "step": 5150
+    },
+    {
+      "epoch": 6.8937875751503,
+      "grad_norm": 1.2383300065994263,
+      "learning_rate": 0.0002,
+      "loss": 1.1535,
+      "step": 5160
+    },
+    {
+      "epoch": 6.907147628590514,
+      "grad_norm": 1.5274227857589722,
+      "learning_rate": 0.0002,
+      "loss": 1.1653,
+      "step": 5170
+    },
+    {
+      "epoch": 6.920507682030728,
+      "grad_norm": 1.1453371047973633,
+      "learning_rate": 0.0002,
+      "loss": 1.1112,
+      "step": 5180
+    },
+    {
+      "epoch": 6.933867735470942,
+      "grad_norm": 1.171336054801941,
+      "learning_rate": 0.0002,
+      "loss": 1.1808,
+      "step": 5190
+    },
+    {
+      "epoch": 6.947227788911156,
+      "grad_norm": 1.1946955919265747,
+      "learning_rate": 0.0002,
+      "loss": 1.1142,
+      "step": 5200
+    },
+    {
+      "epoch": 6.960587842351369,
+      "grad_norm": 1.2290117740631104,
+      "learning_rate": 0.0002,
+      "loss": 1.1386,
+      "step": 5210
+    },
+    {
+      "epoch": 6.973947895791583,
+      "grad_norm": 1.3134533166885376,
+      "learning_rate": 0.0002,
+      "loss": 1.1573,
+      "step": 5220
+    },
+    {
+      "epoch": 6.987307949231797,
+      "grad_norm": 1.1500377655029297,
+      "learning_rate": 0.0002,
+      "loss": 1.1687,
+      "step": 5230
+    },
+    {
+      "epoch": 6.999331997327989,
+      "eval_loss": 2.2211341857910156,
+      "eval_runtime": 38.5729,
+      "eval_samples_per_second": 13.351,
+      "eval_steps_per_second": 1.685,
+      "step": 5239
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5984,
+  "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": 2.4247232828434022e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7025f98e983b93b4fec0d5370c1456c7adecaf8e
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5239/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e92f0598f349930e52e126f358a3dca045c3c88312ec4b3f814f018a04982a9
+size 5560
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/README.md b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d63cb87eaccf2d81de3cdcfa11d2e99c440c0ea0
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..87df48bf37c4668928b0c9052a1f7a921a0145c6
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6fb205815c6e30651ef6687417ae7ca7da70367d071aeb119db1f9854b7cc4
+size 109069176
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..97c5ef6cfca745aa890fb12ad0f328775fdfaadd
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56db1f9fd5b7d75aa4034ba3491279663f70673c8560ffef5dbb38972dd6f1a3
+size 55532666
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4b16818a83e498fe9241d615ae7138a33c5be269
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67f56643fe11a17640541d1e5aff6bd7405d89271bab8a14518e86ddcbc2e424
+size 14244
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f5b44034653714b5420baa13d6aed5c6a2bd93e5
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ffeac63c7827c6d9ea01ea6d72537e7e5a53d6dd03179472c82dbdb62dc0fc
+size 1064
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/tokenizer_config.json
@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..cf0bee0bbd3820729ac971b52f32308570f5bf23
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/trainer_state.json
@@ -0,0 +1,4283 @@
+{
+  "best_metric": 1.8132041692733765,
+  "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497",
+  "epoch": 7.994655978623914,
+  "eval_steps": 10,
+  "global_step": 5984,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013360053440213761,
+      "grad_norm": 0.5097216367721558,
+      "learning_rate": 0.0002,
+      "loss": 2.6569,
+      "step": 10
+    },
+    {
+      "epoch": 0.026720106880427523,
+      "grad_norm": 0.5924790501594543,
+      "learning_rate": 0.0002,
+      "loss": 2.2557,
+      "step": 20
+    },
+    {
+      "epoch": 0.04008016032064128,
+      "grad_norm": 0.5158102512359619,
+      "learning_rate": 0.0002,
+      "loss": 2.0626,
+      "step": 30
+    },
+    {
+      "epoch": 0.053440213760855046,
+      "grad_norm": 0.5033753514289856,
+      "learning_rate": 0.0002,
+      "loss": 1.9452,
+      "step": 40
+    },
+    {
+      "epoch": 0.06680026720106881,
+      "grad_norm": 0.5390949845314026,
+      "learning_rate": 0.0002,
+      "loss": 1.9128,
+      "step": 50
+    },
+    {
+      "epoch": 0.08016032064128256,
+      "grad_norm": 0.6376217007637024,
+      "learning_rate": 0.0002,
+      "loss": 1.937,
+      "step": 60
+    },
+    {
+      "epoch": 0.09352037408149633,
+      "grad_norm": 0.4202035069465637,
+      "learning_rate": 0.0002,
+      "loss": 1.929,
+      "step": 70
+    },
+    {
+      "epoch": 0.10688042752171009,
+      "grad_norm": 0.4269474744796753,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 80
+    },
+    {
+      "epoch": 0.12024048096192384,
+      "grad_norm": 0.4306574761867523,
+      "learning_rate": 0.0002,
+      "loss": 1.8303,
+      "step": 90
+    },
+    {
+      "epoch": 0.13360053440213762,
+      "grad_norm": 0.5297011137008667,
+      "learning_rate": 0.0002,
+      "loss": 1.8469,
+      "step": 100
+    },
+    {
+      "epoch": 0.14696058784235136,
+      "grad_norm": 1.2313778400421143,
+      "learning_rate": 0.0002,
+      "loss": 1.864,
+      "step": 110
+    },
+    {
+      "epoch": 0.16032064128256512,
+      "grad_norm": 0.5351294279098511,
+      "learning_rate": 0.0002,
+      "loss": 1.8531,
+      "step": 120
+    },
+    {
+      "epoch": 0.1736806947227789,
+      "grad_norm": 0.4848092496395111,
+      "learning_rate": 0.0002,
+      "loss": 1.9232,
+      "step": 130
+    },
+    {
+      "epoch": 0.18704074816299265,
+      "grad_norm": 0.4339500665664673,
+      "learning_rate": 0.0002,
+      "loss": 1.8633,
+      "step": 140
+    },
+    {
+      "epoch": 0.20040080160320642,
+      "grad_norm": 0.46877285838127136,
+      "learning_rate": 0.0002,
+      "loss": 1.816,
+      "step": 150
+    },
+    {
+      "epoch": 0.21376085504342018,
+      "grad_norm": 0.5600412487983704,
+      "learning_rate": 0.0002,
+      "loss": 1.8033,
+      "step": 160
+    },
+    {
+      "epoch": 0.22712090848363392,
+      "grad_norm": 0.3733620345592499,
+      "learning_rate": 0.0002,
+      "loss": 1.8162,
+      "step": 170
+    },
+    {
+      "epoch": 0.24048096192384769,
+      "grad_norm": 0.5116042494773865,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 180
+    },
+    {
+      "epoch": 0.25384101536406145,
+      "grad_norm": 0.4071602523326874,
+      "learning_rate": 0.0002,
+      "loss": 1.915,
+      "step": 190
+    },
+    {
+      "epoch": 0.26720106880427524,
+      "grad_norm": 0.44189608097076416,
+      "learning_rate": 0.0002,
+      "loss": 1.7984,
+      "step": 200
+    },
+    {
+      "epoch": 0.280561122244489,
+      "grad_norm": 0.398699015378952,
+      "learning_rate": 0.0002,
+      "loss": 1.8728,
+      "step": 210
+    },
+    {
+      "epoch": 0.2939211756847027,
+      "grad_norm": 0.3585626482963562,
+      "learning_rate": 0.0002,
+      "loss": 1.8205,
+      "step": 220
+    },
+    {
+      "epoch": 0.3072812291249165,
+      "grad_norm": 0.3811776041984558,
+      "learning_rate": 0.0002,
+      "loss": 1.8861,
+      "step": 230
+    },
+    {
+      "epoch": 0.32064128256513025,
+      "grad_norm": 0.37261509895324707,
+      "learning_rate": 0.0002,
+      "loss": 1.8365,
+      "step": 240
+    },
+    {
+      "epoch": 0.33400133600534404,
+      "grad_norm": 0.39762404561042786,
+      "learning_rate": 0.0002,
+      "loss": 1.9186,
+      "step": 250
+    },
+    {
+      "epoch": 0.3473613894455578,
+      "grad_norm": 0.3509528934955597,
+      "learning_rate": 0.0002,
+      "loss": 1.7965,
+      "step": 260
+    },
+    {
+      "epoch": 0.36072144288577157,
+      "grad_norm": 0.3169104754924774,
+      "learning_rate": 0.0002,
+      "loss": 1.7802,
+      "step": 270
+    },
+    {
+      "epoch": 0.3740814963259853,
+      "grad_norm": 0.33714795112609863,
+      "learning_rate": 0.0002,
+      "loss": 1.8038,
+      "step": 280
+    },
+    {
+      "epoch": 0.38744154976619904,
+      "grad_norm": 1.2936875820159912,
+      "learning_rate": 0.0002,
+      "loss": 1.787,
+      "step": 290
+    },
+    {
+      "epoch": 0.40080160320641284,
+      "grad_norm": 0.3459427058696747,
+      "learning_rate": 0.0002,
+      "loss": 1.7974,
+      "step": 300
+    },
+    {
+      "epoch": 0.4141616566466266,
+      "grad_norm": 0.3380655348300934,
+      "learning_rate": 0.0002,
+      "loss": 1.8879,
+      "step": 310
+    },
+    {
+      "epoch": 0.42752171008684037,
+      "grad_norm": 0.3890381455421448,
+      "learning_rate": 0.0002,
+      "loss": 1.9196,
+      "step": 320
+    },
+    {
+      "epoch": 0.4408817635270541,
+      "grad_norm": 0.432327002286911,
+      "learning_rate": 0.0002,
+      "loss": 1.8034,
+      "step": 330
+    },
+    {
+      "epoch": 0.45424181696726784,
+      "grad_norm": 0.3736560046672821,
+      "learning_rate": 0.0002,
+      "loss": 1.8443,
+      "step": 340
+    },
+    {
+      "epoch": 0.46760187040748163,
+      "grad_norm": 0.3700982630252838,
+      "learning_rate": 0.0002,
+      "loss": 1.8506,
+      "step": 350
+    },
+    {
+      "epoch": 0.48096192384769537,
+      "grad_norm": 0.4533902406692505,
+      "learning_rate": 0.0002,
+      "loss": 1.7978,
+      "step": 360
+    },
+    {
+      "epoch": 0.49432197728790916,
+      "grad_norm": 0.35999053716659546,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 370
+    },
+    {
+      "epoch": 0.5076820307281229,
+      "grad_norm": 0.3490903675556183,
+      "learning_rate": 0.0002,
+      "loss": 1.7995,
+      "step": 380
+    },
+    {
+      "epoch": 0.5210420841683366,
+      "grad_norm": 0.34704291820526123,
+      "learning_rate": 0.0002,
+      "loss": 1.8709,
+      "step": 390
+    },
+    {
+      "epoch": 0.5344021376085505,
+      "grad_norm": 0.343565434217453,
+      "learning_rate": 0.0002,
+      "loss": 1.7948,
+      "step": 400
+    },
+    {
+      "epoch": 0.5477621910487642,
+      "grad_norm": 0.3573552966117859,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 410
+    },
+    {
+      "epoch": 0.561122244488978,
+      "grad_norm": 0.32980719208717346,
+      "learning_rate": 0.0002,
+      "loss": 1.8477,
+      "step": 420
+    },
+    {
+      "epoch": 0.5744822979291917,
+      "grad_norm": 0.356952428817749,
+      "learning_rate": 0.0002,
+      "loss": 1.9233,
+      "step": 430
+    },
+    {
+      "epoch": 0.5878423513694054,
+      "grad_norm": 0.3170869052410126,
+      "learning_rate": 0.0002,
+      "loss": 1.7433,
+      "step": 440
+    },
+    {
+      "epoch": 0.6012024048096193,
+      "grad_norm": 0.35233718156814575,
+      "learning_rate": 0.0002,
+      "loss": 1.7607,
+      "step": 450
+    },
+    {
+      "epoch": 0.614562458249833,
+      "grad_norm": 0.3480125367641449,
+      "learning_rate": 0.0002,
+      "loss": 1.8111,
+      "step": 460
+    },
+    {
+      "epoch": 0.6279225116900468,
+      "grad_norm": 0.4762810468673706,
+      "learning_rate": 0.0002,
+      "loss": 1.8386,
+      "step": 470
+    },
+    {
+      "epoch": 0.6412825651302605,
+      "grad_norm": 0.3907663822174072,
+      "learning_rate": 0.0002,
+      "loss": 1.805,
+      "step": 480
+    },
+    {
+      "epoch": 0.6546426185704742,
+      "grad_norm": 0.36315613985061646,
+      "learning_rate": 0.0002,
+      "loss": 1.8113,
+      "step": 490
+    },
+    {
+      "epoch": 0.6680026720106881,
+      "grad_norm": 0.377796471118927,
+      "learning_rate": 0.0002,
+      "loss": 1.7805,
+      "step": 500
+    },
+    {
+      "epoch": 0.6813627254509018,
+      "grad_norm": 0.34284207224845886,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 510
+    },
+    {
+      "epoch": 0.6947227788911156,
+      "grad_norm": 0.35563018918037415,
+      "learning_rate": 0.0002,
+      "loss": 1.8013,
+      "step": 520
+    },
+    {
+      "epoch": 0.7080828323313293,
+      "grad_norm": 0.37575867772102356,
+      "learning_rate": 0.0002,
+      "loss": 1.8414,
+      "step": 530
+    },
+    {
+      "epoch": 0.7214428857715431,
+      "grad_norm": 0.35719701647758484,
+      "learning_rate": 0.0002,
+      "loss": 1.7993,
+      "step": 540
+    },
+    {
+      "epoch": 0.7348029392117569,
+      "grad_norm": 0.385813444852829,
+      "learning_rate": 0.0002,
+      "loss": 1.7574,
+      "step": 550
+    },
+    {
+      "epoch": 0.7481629926519706,
+      "grad_norm": 0.44509607553482056,
+      "learning_rate": 0.0002,
+      "loss": 1.7985,
+      "step": 560
+    },
+    {
+      "epoch": 0.7615230460921844,
+      "grad_norm": 0.36108464002609253,
+      "learning_rate": 0.0002,
+      "loss": 1.7459,
+      "step": 570
+    },
+    {
+      "epoch": 0.7748830995323981,
+      "grad_norm": 0.3530745804309845,
+      "learning_rate": 0.0002,
+      "loss": 1.8207,
+      "step": 580
+    },
+    {
+      "epoch": 0.7882431529726119,
+      "grad_norm": 0.34888574481010437,
+      "learning_rate": 0.0002,
+      "loss": 1.7479,
+      "step": 590
+    },
+    {
+      "epoch": 0.8016032064128257,
+      "grad_norm": 0.387346476316452,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 600
+    },
+    {
+      "epoch": 0.8149632598530394,
+      "grad_norm": 0.3641138970851898,
+      "learning_rate": 0.0002,
+      "loss": 1.8071,
+      "step": 610
+    },
+    {
+      "epoch": 0.8283233132932531,
+      "grad_norm": 0.33729103207588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7531,
+      "step": 620
+    },
+    {
+      "epoch": 0.8416833667334669,
+      "grad_norm": 0.3652004599571228,
+      "learning_rate": 0.0002,
+      "loss": 1.8613,
+      "step": 630
+    },
+    {
+      "epoch": 0.8550434201736807,
+      "grad_norm": 0.3986643850803375,
+      "learning_rate": 0.0002,
+      "loss": 1.9184,
+      "step": 640
+    },
+    {
+      "epoch": 0.8684034736138945,
+      "grad_norm": 0.3458964228630066,
+      "learning_rate": 0.0002,
+      "loss": 1.8198,
+      "step": 650
+    },
+    {
+      "epoch": 0.8817635270541082,
+      "grad_norm": 0.3559381365776062,
+      "learning_rate": 0.0002,
+      "loss": 1.803,
+      "step": 660
+    },
+    {
+      "epoch": 0.895123580494322,
+      "grad_norm": 0.3612841069698334,
+      "learning_rate": 0.0002,
+      "loss": 1.7641,
+      "step": 670
+    },
+    {
+      "epoch": 0.9084836339345357,
+      "grad_norm": 0.34771719574928284,
+      "learning_rate": 0.0002,
+      "loss": 1.7888,
+      "step": 680
+    },
+    {
+      "epoch": 0.9218436873747495,
+      "grad_norm": 0.3371497094631195,
+      "learning_rate": 0.0002,
+      "loss": 1.8204,
+      "step": 690
+    },
+    {
+      "epoch": 0.9352037408149633,
+      "grad_norm": 0.5596055388450623,
+      "learning_rate": 0.0002,
+      "loss": 1.7848,
+      "step": 700
+    },
+    {
+      "epoch": 0.948563794255177,
+      "grad_norm": 0.311880499124527,
+      "learning_rate": 0.0002,
+      "loss": 1.7794,
+      "step": 710
+    },
+    {
+      "epoch": 0.9619238476953907,
+      "grad_norm": 0.3462068736553192,
+      "learning_rate": 0.0002,
+      "loss": 1.8464,
+      "step": 720
+    },
+    {
+      "epoch": 0.9752839011356046,
+      "grad_norm": 0.29982393980026245,
+      "learning_rate": 0.0002,
+      "loss": 1.8197,
+      "step": 730
+    },
+    {
+      "epoch": 0.9886439545758183,
+      "grad_norm": 0.34606459736824036,
+      "learning_rate": 0.0002,
+      "loss": 1.8503,
+      "step": 740
+    },
+    {
+      "epoch": 0.9993319973279893,
+      "eval_loss": 1.8201380968093872,
+      "eval_runtime": 38.6124,
+      "eval_samples_per_second": 13.338,
+      "eval_steps_per_second": 1.683,
+      "step": 748
+    },
+    {
+      "epoch": 1.002004008016032,
+      "grad_norm": 0.32302048802375793,
+      "learning_rate": 0.0002,
+      "loss": 1.7786,
+      "step": 750
+    },
+    {
+      "epoch": 1.0153640614562458,
+      "grad_norm": 0.37585633993148804,
+      "learning_rate": 0.0002,
+      "loss": 1.7297,
+      "step": 760
+    },
+    {
+      "epoch": 1.0287241148964597,
+      "grad_norm": 0.33826273679733276,
+      "learning_rate": 0.0002,
+      "loss": 1.7008,
+      "step": 770
+    },
+    {
+      "epoch": 1.0420841683366733,
+      "grad_norm": 0.44682955741882324,
+      "learning_rate": 0.0002,
+      "loss": 1.809,
+      "step": 780
+    },
+    {
+      "epoch": 1.0554442217768871,
+      "grad_norm": 0.422188401222229,
+      "learning_rate": 0.0002,
+      "loss": 1.7092,
+      "step": 790
+    },
+    {
+      "epoch": 1.0688042752171008,
+      "grad_norm": 0.3809906244277954,
+      "learning_rate": 0.0002,
+      "loss": 1.7765,
+      "step": 800
+    },
+    {
+      "epoch": 1.0821643286573146,
+      "grad_norm": 0.3454349637031555,
+      "learning_rate": 0.0002,
+      "loss": 1.7431,
+      "step": 810
+    },
+    {
+      "epoch": 1.0955243820975284,
+      "grad_norm": 0.3767355978488922,
+      "learning_rate": 0.0002,
+      "loss": 1.7257,
+      "step": 820
+    },
+    {
+      "epoch": 1.108884435537742,
+      "grad_norm": 0.3361407518386841,
+      "learning_rate": 0.0002,
+      "loss": 1.7224,
+      "step": 830
+    },
+    {
+      "epoch": 1.122244488977956,
+      "grad_norm": 0.3654632568359375,
+      "learning_rate": 0.0002,
+      "loss": 1.7509,
+      "step": 840
+    },
+    {
+      "epoch": 1.1356045424181698,
+      "grad_norm": 0.3822861313819885,
+      "learning_rate": 0.0002,
+      "loss": 1.7151,
+      "step": 850
+    },
+    {
+      "epoch": 1.1489645958583834,
+      "grad_norm": 0.3853831887245178,
+      "learning_rate": 0.0002,
+      "loss": 1.7121,
+      "step": 860
+    },
+    {
+      "epoch": 1.1623246492985972,
+      "grad_norm": 0.35521796345710754,
+      "learning_rate": 0.0002,
+      "loss": 1.7685,
+      "step": 870
+    },
+    {
+      "epoch": 1.1756847027388109,
+      "grad_norm": 0.4107200503349304,
+      "learning_rate": 0.0002,
+      "loss": 1.7735,
+      "step": 880
+    },
+    {
+      "epoch": 1.1890447561790247,
+      "grad_norm": 0.33219534158706665,
+      "learning_rate": 0.0002,
+      "loss": 1.7484,
+      "step": 890
+    },
+    {
+      "epoch": 1.2024048096192386,
+      "grad_norm": 0.3559704124927521,
+      "learning_rate": 0.0002,
+      "loss": 1.7071,
+      "step": 900
+    },
+    {
+      "epoch": 1.2157648630594522,
+      "grad_norm": 0.3700537383556366,
+      "learning_rate": 0.0002,
+      "loss": 1.7535,
+      "step": 910
+    },
+    {
+      "epoch": 1.229124916499666,
+      "grad_norm": 0.3771909475326538,
+      "learning_rate": 0.0002,
+      "loss": 1.7513,
+      "step": 920
+    },
+    {
+      "epoch": 1.2424849699398797,
+      "grad_norm": 0.3136613965034485,
+      "learning_rate": 0.0002,
+      "loss": 1.7566,
+      "step": 930
+    },
+    {
+      "epoch": 1.2558450233800935,
+      "grad_norm": 0.3952099084854126,
+      "learning_rate": 0.0002,
+      "loss": 1.6783,
+      "step": 940
+    },
+    {
+      "epoch": 1.2692050768203074,
+      "grad_norm": 0.36534377932548523,
+      "learning_rate": 0.0002,
+      "loss": 1.7691,
+      "step": 950
+    },
+    {
+      "epoch": 1.282565130260521,
+      "grad_norm": 0.3803492486476898,
+      "learning_rate": 0.0002,
+      "loss": 1.7127,
+      "step": 960
+    },
+    {
+      "epoch": 1.2959251837007348,
+      "grad_norm": 0.3992428183555603,
+      "learning_rate": 0.0002,
+      "loss": 1.7896,
+      "step": 970
+    },
+    {
+      "epoch": 1.3092852371409487,
+      "grad_norm": 0.3627142906188965,
+      "learning_rate": 0.0002,
+      "loss": 1.7343,
+      "step": 980
+    },
+    {
+      "epoch": 1.3226452905811623,
+      "grad_norm": 0.4248180091381073,
+      "learning_rate": 0.0002,
+      "loss": 1.7598,
+      "step": 990
+    },
+    {
+      "epoch": 1.3360053440213762,
+      "grad_norm": 0.4060308039188385,
+      "learning_rate": 0.0002,
+      "loss": 1.6896,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3493653974615898,
+      "grad_norm": 0.3788969814777374,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 1010
+    },
+    {
+      "epoch": 1.3627254509018036,
+      "grad_norm": 0.4174270033836365,
+      "learning_rate": 0.0002,
+      "loss": 1.7111,
+      "step": 1020
+    },
+    {
+      "epoch": 1.3760855043420173,
+      "grad_norm": 0.35500675439834595,
+      "learning_rate": 0.0002,
+      "loss": 1.7975,
+      "step": 1030
+    },
+    {
+      "epoch": 1.389445557782231,
+      "grad_norm": 0.3454059362411499,
+      "learning_rate": 0.0002,
+      "loss": 1.724,
+      "step": 1040
+    },
+    {
+      "epoch": 1.402805611222445,
+      "grad_norm": 0.45807570219039917,
+      "learning_rate": 0.0002,
+      "loss": 1.8299,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4161656646626586,
+      "grad_norm": 0.39338022470474243,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4295257181028724,
+      "grad_norm": 0.3870709240436554,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4428857715430863,
+      "grad_norm": 0.40996190905570984,
+      "learning_rate": 0.0002,
+      "loss": 1.6565,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4562458249833,
+      "grad_norm": 0.38762837648391724,
+      "learning_rate": 0.0002,
+      "loss": 1.7324,
+      "step": 1090
+    },
+    {
+      "epoch": 1.4696058784235138,
+      "grad_norm": 0.36756977438926697,
+      "learning_rate": 0.0002,
+      "loss": 1.7362,
+      "step": 1100
+    },
+    {
+      "epoch": 1.4829659318637274,
+      "grad_norm": 0.4087235927581787,
+      "learning_rate": 0.0002,
+      "loss": 1.7451,
+      "step": 1110
+    },
+    {
+      "epoch": 1.4963259853039412,
+      "grad_norm": 0.3357745110988617,
+      "learning_rate": 0.0002,
+      "loss": 1.7114,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5096860387441549,
+      "grad_norm": 0.37486532330513,
+      "learning_rate": 0.0002,
+      "loss": 1.6877,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5230460921843687,
+      "grad_norm": 0.3387809991836548,
+      "learning_rate": 0.0002,
+      "loss": 1.7252,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5364061456245826,
+      "grad_norm": 0.37462118268013,
+      "learning_rate": 0.0002,
+      "loss": 1.7169,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5497661990647962,
+      "grad_norm": 0.38575324416160583,
+      "learning_rate": 0.0002,
+      "loss": 1.6988,
+      "step": 1160
+    },
+    {
+      "epoch": 1.56312625250501,
+      "grad_norm": 0.3515765964984894,
+      "learning_rate": 0.0002,
+      "loss": 1.7438,
+      "step": 1170
+    },
+    {
+      "epoch": 1.5764863059452239,
+      "grad_norm": 0.39308643341064453,
+      "learning_rate": 0.0002,
+      "loss": 1.7524,
+      "step": 1180
+    },
+    {
+      "epoch": 1.5898463593854375,
+      "grad_norm": 0.3308864235877991,
+      "learning_rate": 0.0002,
+      "loss": 1.6422,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6032064128256514,
+      "grad_norm": 0.3397478461265564,
+      "learning_rate": 0.0002,
+      "loss": 1.7566,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6165664662658652,
+      "grad_norm": 0.3911525309085846,
+      "learning_rate": 0.0002,
+      "loss": 1.7871,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6299265197060788,
+      "grad_norm": 0.3771969974040985,
+      "learning_rate": 0.0002,
+      "loss": 1.7443,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6432865731462925,
+      "grad_norm": 0.35346856713294983,
+      "learning_rate": 0.0002,
+      "loss": 1.7631,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6566466265865063,
+      "grad_norm": 0.41736963391304016,
+      "learning_rate": 0.0002,
+      "loss": 1.7225,
+      "step": 1240
+    },
+    {
+      "epoch": 1.6700066800267201,
+      "grad_norm": 0.3375225067138672,
+      "learning_rate": 0.0002,
+      "loss": 1.7582,
+      "step": 1250
+    },
+    {
+      "epoch": 1.6833667334669338,
+      "grad_norm": 0.3779928982257843,
+      "learning_rate": 0.0002,
+      "loss": 1.6916,
+      "step": 1260
+    },
+    {
+      "epoch": 1.6967267869071476,
+      "grad_norm": 0.35388994216918945,
+      "learning_rate": 0.0002,
+      "loss": 1.728,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7100868403473615,
+      "grad_norm": 0.33884134888648987,
+      "learning_rate": 0.0002,
+      "loss": 1.7461,
+      "step": 1280
+    },
+    {
+      "epoch": 1.723446893787575,
+      "grad_norm": 0.35439756512641907,
+      "learning_rate": 0.0002,
+      "loss": 1.7083,
+      "step": 1290
+    },
+    {
+      "epoch": 1.736806947227789,
+      "grad_norm": 0.3766156733036041,
+      "learning_rate": 0.0002,
+      "loss": 1.7389,
+      "step": 1300
+    },
+    {
+      "epoch": 1.7501670006680028,
+      "grad_norm": 0.36148911714553833,
+      "learning_rate": 0.0002,
+      "loss": 1.7847,
+      "step": 1310
+    },
+    {
+      "epoch": 1.7635270541082164,
+      "grad_norm": 0.39687496423721313,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 1320
+    },
+    {
+      "epoch": 1.77688710754843,
+      "grad_norm": 0.35639452934265137,
+      "learning_rate": 0.0002,
+      "loss": 1.7541,
+      "step": 1330
+    },
+    {
+      "epoch": 1.7902471609886441,
+      "grad_norm": 0.38781628012657166,
+      "learning_rate": 0.0002,
+      "loss": 1.7254,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8036072144288577,
+      "grad_norm": 0.42784637212753296,
+      "learning_rate": 0.0002,
+      "loss": 1.7867,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8169672678690714,
+      "grad_norm": 0.40258511900901794,
+      "learning_rate": 0.0002,
+      "loss": 1.7336,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8303273213092852,
+      "grad_norm": 0.36674195528030396,
+      "learning_rate": 0.0002,
+      "loss": 1.7771,
+      "step": 1370
+    },
+    {
+      "epoch": 1.843687374749499,
+      "grad_norm": 0.4064558446407318,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1380
+    },
+    {
+      "epoch": 1.8570474281897127,
+      "grad_norm": 0.3669849932193756,
+      "learning_rate": 0.0002,
+      "loss": 1.7425,
+      "step": 1390
+    },
+    {
+      "epoch": 1.8704074816299265,
+      "grad_norm": 0.37569567561149597,
+      "learning_rate": 0.0002,
+      "loss": 1.7924,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8837675350701404,
+      "grad_norm": 0.37307995557785034,
+      "learning_rate": 0.0002,
+      "loss": 1.7885,
+      "step": 1410
+    },
+    {
+      "epoch": 1.897127588510354,
+      "grad_norm": 0.3772695064544678,
+      "learning_rate": 0.0002,
+      "loss": 1.7548,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9104876419505676,
+      "grad_norm": 0.36993589997291565,
+      "learning_rate": 0.0002,
+      "loss": 1.7682,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9238476953907817,
+      "grad_norm": 0.3490557372570038,
+      "learning_rate": 0.0002,
+      "loss": 1.7249,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9372077488309953,
+      "grad_norm": 0.3716149628162384,
+      "learning_rate": 0.0002,
+      "loss": 1.7979,
+      "step": 1450
+    },
+    {
+      "epoch": 1.950567802271209,
+      "grad_norm": 0.39236098527908325,
+      "learning_rate": 0.0002,
+      "loss": 1.6664,
+      "step": 1460
+    },
+    {
+      "epoch": 1.9639278557114228,
+      "grad_norm": 0.37258651852607727,
+      "learning_rate": 0.0002,
+      "loss": 1.6852,
+      "step": 1470
+    },
+    {
+      "epoch": 1.9772879091516367,
+      "grad_norm": 0.36183077096939087,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 1480
+    },
+    {
+      "epoch": 1.9906479625918503,
+      "grad_norm": 0.3956947326660156,
+      "learning_rate": 0.0002,
+      "loss": 1.7055,
+      "step": 1490
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8132041692733765,
+      "eval_runtime": 38.6287,
+      "eval_samples_per_second": 13.332,
+      "eval_steps_per_second": 1.683,
+      "step": 1497
+    },
+    {
+      "epoch": 2.004008016032064,
+      "grad_norm": 0.34480565786361694,
+      "learning_rate": 0.0002,
+      "loss": 1.6791,
+      "step": 1500
+    },
+    {
+      "epoch": 2.017368069472278,
+      "grad_norm": 0.3418028652667999,
+      "learning_rate": 0.0002,
+      "loss": 1.6367,
+      "step": 1510
+    },
+    {
+      "epoch": 2.0307281229124916,
+      "grad_norm": 0.4514467716217041,
+      "learning_rate": 0.0002,
+      "loss": 1.5827,
+      "step": 1520
+    },
+    {
+      "epoch": 2.0440881763527052,
+      "grad_norm": 0.4197506606578827,
+      "learning_rate": 0.0002,
+      "loss": 1.6365,
+      "step": 1530
+    },
+    {
+      "epoch": 2.0574482297929193,
+      "grad_norm": 0.4134170711040497,
+      "learning_rate": 0.0002,
+      "loss": 1.6221,
+      "step": 1540
+    },
+    {
+      "epoch": 2.070808283233133,
+      "grad_norm": 0.43709826469421387,
+      "learning_rate": 0.0002,
+      "loss": 1.6876,
+      "step": 1550
+    },
+    {
+      "epoch": 2.0841683366733466,
+      "grad_norm": 0.4703378677368164,
+      "learning_rate": 0.0002,
+      "loss": 1.5779,
+      "step": 1560
+    },
+    {
+      "epoch": 2.0975283901135606,
+      "grad_norm": 0.4538188576698303,
+      "learning_rate": 0.0002,
+      "loss": 1.599,
+      "step": 1570
+    },
+    {
+      "epoch": 2.1108884435537743,
+      "grad_norm": 0.4649668037891388,
+      "learning_rate": 0.0002,
+      "loss": 1.6464,
+      "step": 1580
+    },
+    {
+      "epoch": 2.124248496993988,
+      "grad_norm": 0.42669883370399475,
+      "learning_rate": 0.0002,
+      "loss": 1.6348,
+      "step": 1590
+    },
+    {
+      "epoch": 2.1376085504342015,
+      "grad_norm": 0.43162038922309875,
+      "learning_rate": 0.0002,
+      "loss": 1.5838,
+      "step": 1600
+    },
+    {
+      "epoch": 2.1509686038744156,
+      "grad_norm": 0.4294586479663849,
+      "learning_rate": 0.0002,
+      "loss": 1.6673,
+      "step": 1610
+    },
+    {
+      "epoch": 2.164328657314629,
+      "grad_norm": 0.4669102132320404,
+      "learning_rate": 0.0002,
+      "loss": 1.6024,
+      "step": 1620
+    },
+    {
+      "epoch": 2.177688710754843,
+      "grad_norm": 0.4188412129878998,
+      "learning_rate": 0.0002,
+      "loss": 1.659,
+      "step": 1630
+    },
+    {
+      "epoch": 2.191048764195057,
+      "grad_norm": 0.4662680923938751,
+      "learning_rate": 0.0002,
+      "loss": 1.625,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2044088176352705,
+      "grad_norm": 0.4020286500453949,
+      "learning_rate": 0.0002,
+      "loss": 1.6699,
+      "step": 1650
+    },
+    {
+      "epoch": 2.217768871075484,
+      "grad_norm": 0.41919606924057007,
+      "learning_rate": 0.0002,
+      "loss": 1.6284,
+      "step": 1660
+    },
+    {
+      "epoch": 2.231128924515698,
+      "grad_norm": 0.4644531309604645,
+      "learning_rate": 0.0002,
+      "loss": 1.6776,
+      "step": 1670
+    },
+    {
+      "epoch": 2.244488977955912,
+      "grad_norm": 0.4526427984237671,
+      "learning_rate": 0.0002,
+      "loss": 1.6711,
+      "step": 1680
+    },
+    {
+      "epoch": 2.2578490313961255,
+      "grad_norm": 0.45953166484832764,
+      "learning_rate": 0.0002,
+      "loss": 1.6058,
+      "step": 1690
+    },
+    {
+      "epoch": 2.2712090848363395,
+      "grad_norm": 0.4701860249042511,
+      "learning_rate": 0.0002,
+      "loss": 1.5979,
+      "step": 1700
+    },
+    {
+      "epoch": 2.284569138276553,
+      "grad_norm": 0.4749310612678528,
+      "learning_rate": 0.0002,
+      "loss": 1.6183,
+      "step": 1710
+    },
+    {
+      "epoch": 2.297929191716767,
+      "grad_norm": 0.45026102662086487,
+      "learning_rate": 0.0002,
+      "loss": 1.6703,
+      "step": 1720
+    },
+    {
+      "epoch": 2.3112892451569804,
+      "grad_norm": 0.4755004048347473,
+      "learning_rate": 0.0002,
+      "loss": 1.6386,
+      "step": 1730
+    },
+    {
+      "epoch": 2.3246492985971945,
+      "grad_norm": 0.4505726993083954,
+      "learning_rate": 0.0002,
+      "loss": 1.6365,
+      "step": 1740
+    },
+    {
+      "epoch": 2.338009352037408,
+      "grad_norm": 0.44464054703712463,
+      "learning_rate": 0.0002,
+      "loss": 1.589,
+      "step": 1750
+    },
+    {
+      "epoch": 2.3513694054776217,
+      "grad_norm": 0.4449476897716522,
+      "learning_rate": 0.0002,
+      "loss": 1.6139,
+      "step": 1760
+    },
+    {
+      "epoch": 2.364729458917836,
+      "grad_norm": 0.4216482937335968,
+      "learning_rate": 0.0002,
+      "loss": 1.7195,
+      "step": 1770
+    },
+    {
+      "epoch": 2.3780895123580494,
+      "grad_norm": 0.4379308521747589,
+      "learning_rate": 0.0002,
+      "loss": 1.7075,
+      "step": 1780
+    },
+    {
+      "epoch": 2.391449565798263,
+      "grad_norm": 0.41670042276382446,
+      "learning_rate": 0.0002,
+      "loss": 1.7024,
+      "step": 1790
+    },
+    {
+      "epoch": 2.404809619238477,
+      "grad_norm": 0.48089510202407837,
+      "learning_rate": 0.0002,
+      "loss": 1.5989,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4181696726786908,
+      "grad_norm": 0.4389738142490387,
+      "learning_rate": 0.0002,
+      "loss": 1.6313,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4315297261189044,
+      "grad_norm": 0.45293036103248596,
+      "learning_rate": 0.0002,
+      "loss": 1.5841,
+      "step": 1820
+    },
+    {
+      "epoch": 2.4448897795591185,
+      "grad_norm": 0.5211683511734009,
+      "learning_rate": 0.0002,
+      "loss": 1.6887,
+      "step": 1830
+    },
+    {
+      "epoch": 2.458249832999332,
+      "grad_norm": 0.4631884694099426,
+      "learning_rate": 0.0002,
+      "loss": 1.6599,
+      "step": 1840
+    },
+    {
+      "epoch": 2.4716098864395457,
+      "grad_norm": 0.4276818335056305,
+      "learning_rate": 0.0002,
+      "loss": 1.6537,
+      "step": 1850
+    },
+    {
+      "epoch": 2.4849699398797593,
+      "grad_norm": 0.477524071931839,
+      "learning_rate": 0.0002,
+      "loss": 1.6836,
+      "step": 1860
+    },
+    {
+      "epoch": 2.4983299933199734,
+      "grad_norm": 0.44860973954200745,
+      "learning_rate": 0.0002,
+      "loss": 1.66,
+      "step": 1870
+    },
+    {
+      "epoch": 2.511690046760187,
+      "grad_norm": 0.46413546800613403,
+      "learning_rate": 0.0002,
+      "loss": 1.6308,
+      "step": 1880
+    },
+    {
+      "epoch": 2.5250501002004007,
+      "grad_norm": 0.42487645149230957,
+      "learning_rate": 0.0002,
+      "loss": 1.6225,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5384101536406147,
+      "grad_norm": 0.4778307378292084,
+      "learning_rate": 0.0002,
+      "loss": 1.6268,
+      "step": 1900
+    },
+    {
+      "epoch": 2.5517702070808284,
+      "grad_norm": 0.45307061076164246,
+      "learning_rate": 0.0002,
+      "loss": 1.6143,
+      "step": 1910
+    },
+    {
+      "epoch": 2.565130260521042,
+      "grad_norm": 0.47886642813682556,
+      "learning_rate": 0.0002,
+      "loss": 1.7279,
+      "step": 1920
+    },
+    {
+      "epoch": 2.5784903139612556,
+      "grad_norm": 0.4839435815811157,
+      "learning_rate": 0.0002,
+      "loss": 1.5931,
+      "step": 1930
+    },
+    {
+      "epoch": 2.5918503674014697,
+      "grad_norm": 0.4388359785079956,
+      "learning_rate": 0.0002,
+      "loss": 1.6089,
+      "step": 1940
+    },
+    {
+      "epoch": 2.6052104208416833,
+      "grad_norm": 0.47859734296798706,
+      "learning_rate": 0.0002,
+      "loss": 1.6828,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6185704742818974,
+      "grad_norm": 0.5526517033576965,
+      "learning_rate": 0.0002,
+      "loss": 1.6014,
+      "step": 1960
+    },
+    {
+      "epoch": 2.631930527722111,
+      "grad_norm": 0.5449170470237732,
+      "learning_rate": 0.0002,
+      "loss": 1.6889,
+      "step": 1970
+    },
+    {
+      "epoch": 2.6452905811623246,
+      "grad_norm": 0.48521968722343445,
+      "learning_rate": 0.0002,
+      "loss": 1.6481,
+      "step": 1980
+    },
+    {
+      "epoch": 2.6586506346025383,
+      "grad_norm": 0.4733737111091614,
+      "learning_rate": 0.0002,
+      "loss": 1.6741,
+      "step": 1990
+    },
+    {
+      "epoch": 2.6720106880427523,
+      "grad_norm": 0.507118284702301,
+      "learning_rate": 0.0002,
+      "loss": 1.662,
+      "step": 2000
+    },
+    {
+      "epoch": 2.685370741482966,
+      "grad_norm": 0.4508971571922302,
+      "learning_rate": 0.0002,
+      "loss": 1.6419,
+      "step": 2010
+    },
+    {
+      "epoch": 2.6987307949231796,
+      "grad_norm": 0.4657728672027588,
+      "learning_rate": 0.0002,
+      "loss": 1.7052,
+      "step": 2020
+    },
+    {
+      "epoch": 2.7120908483633936,
+      "grad_norm": 0.48647549748420715,
+      "learning_rate": 0.0002,
+      "loss": 1.6261,
+      "step": 2030
+    },
+    {
+      "epoch": 2.7254509018036073,
+      "grad_norm": 0.49525555968284607,
+      "learning_rate": 0.0002,
+      "loss": 1.5638,
+      "step": 2040
+    },
+    {
+      "epoch": 2.738810955243821,
+      "grad_norm": 0.4712379276752472,
+      "learning_rate": 0.0002,
+      "loss": 1.658,
+      "step": 2050
+    },
+    {
+      "epoch": 2.7521710086840345,
+      "grad_norm": 0.4846591055393219,
+      "learning_rate": 0.0002,
+      "loss": 1.6464,
+      "step": 2060
+    },
+    {
+      "epoch": 2.7655310621242486,
+      "grad_norm": 0.4823240041732788,
+      "learning_rate": 0.0002,
+      "loss": 1.5641,
+      "step": 2070
+    },
+    {
+      "epoch": 2.778891115564462,
+      "grad_norm": 0.4546685516834259,
+      "learning_rate": 0.0002,
+      "loss": 1.6701,
+      "step": 2080
+    },
+    {
+      "epoch": 2.7922511690046763,
+      "grad_norm": 0.45542681217193604,
+      "learning_rate": 0.0002,
+      "loss": 1.7015,
+      "step": 2090
+    },
+    {
+      "epoch": 2.80561122244489,
+      "grad_norm": 0.42137566208839417,
+      "learning_rate": 0.0002,
+      "loss": 1.6398,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8189712758851035,
+      "grad_norm": 0.6143282055854797,
+      "learning_rate": 0.0002,
+      "loss": 1.6526,
+      "step": 2110
+    },
+    {
+      "epoch": 2.832331329325317,
+      "grad_norm": 0.4828081727027893,
+      "learning_rate": 0.0002,
+      "loss": 1.6955,
+      "step": 2120
+    },
+    {
+      "epoch": 2.845691382765531,
+      "grad_norm": 0.4319005608558655,
+      "learning_rate": 0.0002,
+      "loss": 1.744,
+      "step": 2130
+    },
+    {
+      "epoch": 2.859051436205745,
+      "grad_norm": 0.4297086298465729,
+      "learning_rate": 0.0002,
+      "loss": 1.6717,
+      "step": 2140
+    },
+    {
+      "epoch": 2.8724114896459585,
+      "grad_norm": 0.5011981129646301,
+      "learning_rate": 0.0002,
+      "loss": 1.5968,
+      "step": 2150
+    },
+    {
+      "epoch": 2.8857715430861726,
+      "grad_norm": 0.4401548504829407,
+      "learning_rate": 0.0002,
+      "loss": 1.7181,
+      "step": 2160
+    },
+    {
+      "epoch": 2.899131596526386,
+      "grad_norm": 0.48090746998786926,
+      "learning_rate": 0.0002,
+      "loss": 1.5722,
+      "step": 2170
+    },
+    {
+      "epoch": 2.9124916499666,
+      "grad_norm": 0.4740385413169861,
+      "learning_rate": 0.0002,
+      "loss": 1.6596,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9258517034068134,
+      "grad_norm": 0.5337260365486145,
+      "learning_rate": 0.0002,
+      "loss": 1.6501,
+      "step": 2190
+    },
+    {
+      "epoch": 2.9392117568470275,
+      "grad_norm": 0.4420052766799927,
+      "learning_rate": 0.0002,
+      "loss": 1.6802,
+      "step": 2200
+    },
+    {
+      "epoch": 2.952571810287241,
+      "grad_norm": 0.477512389421463,
+      "learning_rate": 0.0002,
+      "loss": 1.5474,
+      "step": 2210
+    },
+    {
+      "epoch": 2.9659318637274548,
+      "grad_norm": 0.5344052910804749,
+      "learning_rate": 0.0002,
+      "loss": 1.6544,
+      "step": 2220
+    },
+    {
+      "epoch": 2.979291917167669,
+      "grad_norm": 0.4483940303325653,
+      "learning_rate": 0.0002,
+      "loss": 1.6866,
+      "step": 2230
+    },
+    {
+      "epoch": 2.9926519706078825,
+      "grad_norm": 0.4366597831249237,
+      "learning_rate": 0.0002,
+      "loss": 1.6477,
+      "step": 2240
+    },
+    {
+      "epoch": 2.9993319973279893,
+      "eval_loss": 1.834012746810913,
+      "eval_runtime": 38.5659,
+      "eval_samples_per_second": 13.354,
+      "eval_steps_per_second": 1.685,
+      "step": 2245
+    },
+    {
+      "epoch": 3.006012024048096,
+      "grad_norm": 0.428824245929718,
+      "learning_rate": 0.0002,
+      "loss": 1.5582,
+      "step": 2250
+    },
+    {
+      "epoch": 3.01937207748831,
+      "grad_norm": 0.4870174825191498,
+      "learning_rate": 0.0002,
+      "loss": 1.499,
+      "step": 2260
+    },
+    {
+      "epoch": 3.032732130928524,
+      "grad_norm": 0.4684266149997711,
+      "learning_rate": 0.0002,
+      "loss": 1.4872,
+      "step": 2270
+    },
+    {
+      "epoch": 3.0460921843687374,
+      "grad_norm": 0.581604540348053,
+      "learning_rate": 0.0002,
+      "loss": 1.5284,
+      "step": 2280
+    },
+    {
+      "epoch": 3.059452237808951,
+      "grad_norm": 0.5561677813529968,
+      "learning_rate": 0.0002,
+      "loss": 1.4549,
+      "step": 2290
+    },
+    {
+      "epoch": 3.072812291249165,
+      "grad_norm": 0.5750220417976379,
+      "learning_rate": 0.0002,
+      "loss": 1.4903,
+      "step": 2300
+    },
+    {
+      "epoch": 3.0861723446893787,
+      "grad_norm": 0.5704626441001892,
+      "learning_rate": 0.0002,
+      "loss": 1.5903,
+      "step": 2310
+    },
+    {
+      "epoch": 3.0995323981295924,
+      "grad_norm": 0.6242083311080933,
+      "learning_rate": 0.0002,
+      "loss": 1.4292,
+      "step": 2320
+    },
+    {
+      "epoch": 3.1128924515698064,
+      "grad_norm": 0.5174121260643005,
+      "learning_rate": 0.0002,
+      "loss": 1.5092,
+      "step": 2330
+    },
+    {
+      "epoch": 3.12625250501002,
+      "grad_norm": 0.5697633028030396,
+      "learning_rate": 0.0002,
+      "loss": 1.5106,
+      "step": 2340
+    },
+    {
+      "epoch": 3.1396125584502337,
+      "grad_norm": 0.5969541072845459,
+      "learning_rate": 0.0002,
+      "loss": 1.5156,
+      "step": 2350
+    },
+    {
+      "epoch": 3.1529726118904478,
+      "grad_norm": 0.6244304180145264,
+      "learning_rate": 0.0002,
+      "loss": 1.52,
+      "step": 2360
+    },
+    {
+      "epoch": 3.1663326653306614,
+      "grad_norm": 0.5561705827713013,
+      "learning_rate": 0.0002,
+      "loss": 1.5244,
+      "step": 2370
+    },
+    {
+      "epoch": 3.179692718770875,
+      "grad_norm": 0.5401188135147095,
+      "learning_rate": 0.0002,
+      "loss": 1.6169,
+      "step": 2380
+    },
+    {
+      "epoch": 3.1930527722110886,
+      "grad_norm": 0.6450421810150146,
+      "learning_rate": 0.0002,
+      "loss": 1.5387,
+      "step": 2390
+    },
+    {
+      "epoch": 3.2064128256513027,
+      "grad_norm": 0.5741903185844421,
+      "learning_rate": 0.0002,
+      "loss": 1.4839,
+      "step": 2400
+    },
+    {
+      "epoch": 3.2197728790915163,
+      "grad_norm": 0.6337407231330872,
+      "learning_rate": 0.0002,
+      "loss": 1.5584,
+      "step": 2410
+    },
+    {
+      "epoch": 3.23313293253173,
+      "grad_norm": 0.6493517160415649,
+      "learning_rate": 0.0002,
+      "loss": 1.5025,
+      "step": 2420
+    },
+    {
+      "epoch": 3.246492985971944,
+      "grad_norm": 0.6230176091194153,
+      "learning_rate": 0.0002,
+      "loss": 1.5168,
+      "step": 2430
+    },
+    {
+      "epoch": 3.2598530394121576,
+      "grad_norm": 0.680704653263092,
+      "learning_rate": 0.0002,
+      "loss": 1.5408,
+      "step": 2440
+    },
+    {
+      "epoch": 3.2732130928523713,
+      "grad_norm": 0.5279417037963867,
+      "learning_rate": 0.0002,
+      "loss": 1.6005,
+      "step": 2450
+    },
+    {
+      "epoch": 3.2865731462925853,
+      "grad_norm": 0.5601515173912048,
+      "learning_rate": 0.0002,
+      "loss": 1.5231,
+      "step": 2460
+    },
+    {
+      "epoch": 3.299933199732799,
+      "grad_norm": 0.5591090321540833,
+      "learning_rate": 0.0002,
+      "loss": 1.4949,
+      "step": 2470
+    },
+    {
+      "epoch": 3.3132932531730126,
+      "grad_norm": 0.6596529483795166,
+      "learning_rate": 0.0002,
+      "loss": 1.5181,
+      "step": 2480
+    },
+    {
+      "epoch": 3.3266533066132267,
+      "grad_norm": 0.6115918755531311,
+      "learning_rate": 0.0002,
+      "loss": 1.5259,
+      "step": 2490
+    },
+    {
+      "epoch": 3.3400133600534403,
+      "grad_norm": 0.6443548202514648,
+      "learning_rate": 0.0002,
+      "loss": 1.5344,
+      "step": 2500
+    },
+    {
+      "epoch": 3.353373413493654,
+      "grad_norm": 0.5504242181777954,
+      "learning_rate": 0.0002,
+      "loss": 1.5037,
+      "step": 2510
+    },
+    {
+      "epoch": 3.3667334669338675,
+      "grad_norm": 0.6104483604431152,
+      "learning_rate": 0.0002,
+      "loss": 1.5049,
+      "step": 2520
+    },
+    {
+      "epoch": 3.3800935203740816,
+      "grad_norm": 0.8387531638145447,
+      "learning_rate": 0.0002,
+      "loss": 1.587,
+      "step": 2530
+    },
+    {
+      "epoch": 3.3934535738142952,
+      "grad_norm": 0.6346094012260437,
+      "learning_rate": 0.0002,
+      "loss": 1.5227,
+      "step": 2540
+    },
+    {
+      "epoch": 3.406813627254509,
+      "grad_norm": 0.6261265873908997,
+      "learning_rate": 0.0002,
+      "loss": 1.4855,
+      "step": 2550
+    },
+    {
+      "epoch": 3.420173680694723,
+      "grad_norm": 0.5960372090339661,
+      "learning_rate": 0.0002,
+      "loss": 1.5233,
+      "step": 2560
+    },
+    {
+      "epoch": 3.4335337341349366,
+      "grad_norm": 0.5291280746459961,
+      "learning_rate": 0.0002,
+      "loss": 1.5153,
+      "step": 2570
+    },
+    {
+      "epoch": 3.44689378757515,
+      "grad_norm": 0.6133161783218384,
+      "learning_rate": 0.0002,
+      "loss": 1.5152,
+      "step": 2580
+    },
+    {
+      "epoch": 3.460253841015364,
+      "grad_norm": 0.623573362827301,
+      "learning_rate": 0.0002,
+      "loss": 1.5533,
+      "step": 2590
+    },
+    {
+      "epoch": 3.473613894455578,
+      "grad_norm": 0.5959834456443787,
+      "learning_rate": 0.0002,
+      "loss": 1.4935,
+      "step": 2600
+    },
+    {
+      "epoch": 3.4869739478957915,
+      "grad_norm": 0.583332359790802,
+      "learning_rate": 0.0002,
+      "loss": 1.5792,
+      "step": 2610
+    },
+    {
+      "epoch": 3.5003340013360056,
+      "grad_norm": 0.6003559231758118,
+      "learning_rate": 0.0002,
+      "loss": 1.5229,
+      "step": 2620
+    },
+    {
+      "epoch": 3.513694054776219,
+      "grad_norm": 0.5832992196083069,
+      "learning_rate": 0.0002,
+      "loss": 1.4901,
+      "step": 2630
+    },
+    {
+      "epoch": 3.527054108216433,
+      "grad_norm": 0.5942609906196594,
+      "learning_rate": 0.0002,
+      "loss": 1.5005,
+      "step": 2640
+    },
+    {
+      "epoch": 3.5404141616566465,
+      "grad_norm": 0.6087163686752319,
+      "learning_rate": 0.0002,
+      "loss": 1.5213,
+      "step": 2650
+    },
+    {
+      "epoch": 3.5537742150968605,
+      "grad_norm": 0.631948709487915,
+      "learning_rate": 0.0002,
+      "loss": 1.5826,
+      "step": 2660
+    },
+    {
+      "epoch": 3.567134268537074,
+      "grad_norm": 0.6450803279876709,
+      "learning_rate": 0.0002,
+      "loss": 1.5844,
+      "step": 2670
+    },
+    {
+      "epoch": 3.580494321977288,
+      "grad_norm": 0.6507797837257385,
+      "learning_rate": 0.0002,
+      "loss": 1.4981,
+      "step": 2680
+    },
+    {
+      "epoch": 3.593854375417502,
+      "grad_norm": 0.5778017044067383,
+      "learning_rate": 0.0002,
+      "loss": 1.5826,
+      "step": 2690
+    },
+    {
+      "epoch": 3.6072144288577155,
+      "grad_norm": 0.6214032173156738,
+      "learning_rate": 0.0002,
+      "loss": 1.4688,
+      "step": 2700
+    },
+    {
+      "epoch": 3.620574482297929,
+      "grad_norm": 0.5681133270263672,
+      "learning_rate": 0.0002,
+      "loss": 1.5084,
+      "step": 2710
+    },
+    {
+      "epoch": 3.6339345357381427,
+      "grad_norm": 0.6074244976043701,
+      "learning_rate": 0.0002,
+      "loss": 1.471,
+      "step": 2720
+    },
+    {
+      "epoch": 3.647294589178357,
+      "grad_norm": 0.5900560617446899,
+      "learning_rate": 0.0002,
+      "loss": 1.5243,
+      "step": 2730
+    },
+    {
+      "epoch": 3.6606546426185704,
+      "grad_norm": 0.5817505717277527,
+      "learning_rate": 0.0002,
+      "loss": 1.5074,
+      "step": 2740
+    },
+    {
+      "epoch": 3.6740146960587845,
+      "grad_norm": 0.6095547676086426,
+      "learning_rate": 0.0002,
+      "loss": 1.5117,
+      "step": 2750
+    },
+    {
+      "epoch": 3.687374749498998,
+      "grad_norm": 0.612790584564209,
+      "learning_rate": 0.0002,
+      "loss": 1.5117,
+      "step": 2760
+    },
+    {
+      "epoch": 3.7007348029392118,
+      "grad_norm": 0.6574140787124634,
+      "learning_rate": 0.0002,
+      "loss": 1.4976,
+      "step": 2770
+    },
+    {
+      "epoch": 3.7140948563794254,
+      "grad_norm": 0.5643761157989502,
+      "learning_rate": 0.0002,
+      "loss": 1.5306,
+      "step": 2780
+    },
+    {
+      "epoch": 3.727454909819639,
+      "grad_norm": 0.5652621388435364,
+      "learning_rate": 0.0002,
+      "loss": 1.5751,
+      "step": 2790
+    },
+    {
+      "epoch": 3.740814963259853,
+      "grad_norm": 0.5604206323623657,
+      "learning_rate": 0.0002,
+      "loss": 1.5262,
+      "step": 2800
+    },
+    {
+      "epoch": 3.7541750167000667,
+      "grad_norm": 3.911022663116455,
+      "learning_rate": 0.0002,
+      "loss": 1.5013,
+      "step": 2810
+    },
+    {
+      "epoch": 3.7675350701402808,
+      "grad_norm": 0.6148333549499512,
+      "learning_rate": 0.0002,
+      "loss": 1.5793,
+      "step": 2820
+    },
+    {
+      "epoch": 3.7808951235804944,
+      "grad_norm": 0.5605677962303162,
+      "learning_rate": 0.0002,
+      "loss": 1.5122,
+      "step": 2830
+    },
+    {
+      "epoch": 3.794255177020708,
+      "grad_norm": 0.6101965308189392,
+      "learning_rate": 0.0002,
+      "loss": 1.5659,
+      "step": 2840
+    },
+    {
+      "epoch": 3.8076152304609217,
+      "grad_norm": 0.5387342572212219,
+      "learning_rate": 0.0002,
+      "loss": 1.5618,
+      "step": 2850
+    },
+    {
+      "epoch": 3.8209752839011357,
+      "grad_norm": 0.5733087062835693,
+      "learning_rate": 0.0002,
+      "loss": 1.5193,
+      "step": 2860
+    },
+    {
+      "epoch": 3.8343353373413493,
+      "grad_norm": 0.6538485884666443,
+      "learning_rate": 0.0002,
+      "loss": 1.5545,
+      "step": 2870
+    },
+    {
+      "epoch": 3.847695390781563,
+      "grad_norm": 0.6247632503509521,
+      "learning_rate": 0.0002,
+      "loss": 1.523,
+      "step": 2880
+    },
+    {
+      "epoch": 3.861055444221777,
+      "grad_norm": 0.5745735764503479,
+      "learning_rate": 0.0002,
+      "loss": 1.5591,
+      "step": 2890
+    },
+    {
+      "epoch": 3.8744154976619907,
+      "grad_norm": 0.5942763686180115,
+      "learning_rate": 0.0002,
+      "loss": 1.5706,
+      "step": 2900
+    },
+    {
+      "epoch": 3.8877755511022043,
+      "grad_norm": 0.7086281776428223,
+      "learning_rate": 0.0002,
+      "loss": 1.564,
+      "step": 2910
+    },
+    {
+      "epoch": 3.901135604542418,
+      "grad_norm": 0.8825129866600037,
+      "learning_rate": 0.0002,
+      "loss": 1.5526,
+      "step": 2920
+    },
+    {
+      "epoch": 3.914495657982632,
+      "grad_norm": 0.6260842680931091,
+      "learning_rate": 0.0002,
+      "loss": 1.4519,
+      "step": 2930
+    },
+    {
+      "epoch": 3.9278557114228456,
+      "grad_norm": 0.6015968322753906,
+      "learning_rate": 0.0002,
+      "loss": 1.5433,
+      "step": 2940
+    },
+    {
+      "epoch": 3.9412157648630597,
+      "grad_norm": 0.7042809128761292,
+      "learning_rate": 0.0002,
+      "loss": 1.4931,
+      "step": 2950
+    },
+    {
+      "epoch": 3.9545758183032733,
+      "grad_norm": 0.5860083699226379,
+      "learning_rate": 0.0002,
+      "loss": 1.5596,
+      "step": 2960
+    },
+    {
+      "epoch": 3.967935871743487,
+      "grad_norm": 0.5939757823944092,
+      "learning_rate": 0.0002,
+      "loss": 1.565,
+      "step": 2970
+    },
+    {
+      "epoch": 3.9812959251837006,
+      "grad_norm": 0.5523964166641235,
+      "learning_rate": 0.0002,
+      "loss": 1.408,
+      "step": 2980
+    },
+    {
+      "epoch": 3.9946559786239146,
+      "grad_norm": 0.6380264759063721,
+      "learning_rate": 0.0002,
+      "loss": 1.5629,
+      "step": 2990
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.8875294923782349,
+      "eval_runtime": 38.5837,
+      "eval_samples_per_second": 13.348,
+      "eval_steps_per_second": 1.685,
+      "step": 2994
+    },
+    {
+      "epoch": 4.008016032064128,
+      "grad_norm": 0.5478564500808716,
+      "learning_rate": 0.0002,
+      "loss": 1.4002,
+      "step": 3000
+    },
+    {
+      "epoch": 4.021376085504342,
+      "grad_norm": 0.9384379982948303,
+      "learning_rate": 0.0002,
+      "loss": 1.436,
+      "step": 3010
+    },
+    {
+      "epoch": 4.034736138944556,
+      "grad_norm": 0.7819344401359558,
+      "learning_rate": 0.0002,
+      "loss": 1.4127,
+      "step": 3020
+    },
+    {
+      "epoch": 4.04809619238477,
+      "grad_norm": 0.7737417817115784,
+      "learning_rate": 0.0002,
+      "loss": 1.326,
+      "step": 3030
+    },
+    {
+      "epoch": 4.061456245824983,
+      "grad_norm": 0.8893805742263794,
+      "learning_rate": 0.0002,
+      "loss": 1.3203,
+      "step": 3040
+    },
+    {
+      "epoch": 4.074816299265197,
+      "grad_norm": 0.7759843468666077,
+      "learning_rate": 0.0002,
+      "loss": 1.3913,
+      "step": 3050
+    },
+    {
+      "epoch": 4.0881763527054105,
+      "grad_norm": 0.642654538154602,
+      "learning_rate": 0.0002,
+      "loss": 1.2941,
+      "step": 3060
+    },
+    {
+      "epoch": 4.101536406145625,
+      "grad_norm": 0.8515549302101135,
+      "learning_rate": 0.0002,
+      "loss": 1.3204,
+      "step": 3070
+    },
+    {
+      "epoch": 4.114896459585839,
+      "grad_norm": 0.7033658623695374,
+      "learning_rate": 0.0002,
+      "loss": 1.3683,
+      "step": 3080
+    },
+    {
+      "epoch": 4.128256513026052,
+      "grad_norm": 0.7063882946968079,
+      "learning_rate": 0.0002,
+      "loss": 1.4159,
+      "step": 3090
+    },
+    {
+      "epoch": 4.141616566466266,
+      "grad_norm": 0.6946853995323181,
+      "learning_rate": 0.0002,
+      "loss": 1.384,
+      "step": 3100
+    },
+    {
+      "epoch": 4.1549766199064795,
+      "grad_norm": 0.7286741137504578,
+      "learning_rate": 0.0002,
+      "loss": 1.3689,
+      "step": 3110
+    },
+    {
+      "epoch": 4.168336673346693,
+      "grad_norm": 0.7894193530082703,
+      "learning_rate": 0.0002,
+      "loss": 1.3061,
+      "step": 3120
+    },
+    {
+      "epoch": 4.181696726786907,
+      "grad_norm": 0.7005895376205444,
+      "learning_rate": 0.0002,
+      "loss": 1.3346,
+      "step": 3130
+    },
+    {
+      "epoch": 4.195056780227121,
+      "grad_norm": 0.799567461013794,
+      "learning_rate": 0.0002,
+      "loss": 1.3834,
+      "step": 3140
+    },
+    {
+      "epoch": 4.208416833667335,
+      "grad_norm": 0.7010157108306885,
+      "learning_rate": 0.0002,
+      "loss": 1.3813,
+      "step": 3150
+    },
+    {
+      "epoch": 4.2217768871075485,
+      "grad_norm": 0.7489650249481201,
+      "learning_rate": 0.0002,
+      "loss": 1.3637,
+      "step": 3160
+    },
+    {
+      "epoch": 4.235136940547762,
+      "grad_norm": 0.7908048629760742,
+      "learning_rate": 0.0002,
+      "loss": 1.3546,
+      "step": 3170
+    },
+    {
+      "epoch": 4.248496993987976,
+      "grad_norm": 0.7002180814743042,
+      "learning_rate": 0.0002,
+      "loss": 1.3073,
+      "step": 3180
+    },
+    {
+      "epoch": 4.261857047428189,
+      "grad_norm": 0.8339495062828064,
+      "learning_rate": 0.0002,
+      "loss": 1.4525,
+      "step": 3190
+    },
+    {
+      "epoch": 4.275217100868403,
+      "grad_norm": 0.7884618043899536,
+      "learning_rate": 0.0002,
+      "loss": 1.3471,
+      "step": 3200
+    },
+    {
+      "epoch": 4.2885771543086175,
+      "grad_norm": 0.7964122295379639,
+      "learning_rate": 0.0002,
+      "loss": 1.4261,
+      "step": 3210
+    },
+    {
+      "epoch": 4.301937207748831,
+      "grad_norm": 0.838646650314331,
+      "learning_rate": 0.0002,
+      "loss": 1.3506,
+      "step": 3220
+    },
+    {
+      "epoch": 4.315297261189045,
+      "grad_norm": 0.8063107132911682,
+      "learning_rate": 0.0002,
+      "loss": 1.3738,
+      "step": 3230
+    },
+    {
+      "epoch": 4.328657314629258,
+      "grad_norm": 0.8147385120391846,
+      "learning_rate": 0.0002,
+      "loss": 1.3769,
+      "step": 3240
+    },
+    {
+      "epoch": 4.342017368069472,
+      "grad_norm": 0.7636798620223999,
+      "learning_rate": 0.0002,
+      "loss": 1.4118,
+      "step": 3250
+    },
+    {
+      "epoch": 4.355377421509686,
+      "grad_norm": 0.7530609965324402,
+      "learning_rate": 0.0002,
+      "loss": 1.3698,
+      "step": 3260
+    },
+    {
+      "epoch": 4.3687374749499,
+      "grad_norm": 0.8853573799133301,
+      "learning_rate": 0.0002,
+      "loss": 1.3507,
+      "step": 3270
+    },
+    {
+      "epoch": 4.382097528390114,
+      "grad_norm": 0.7180975675582886,
+      "learning_rate": 0.0002,
+      "loss": 1.3614,
+      "step": 3280
+    },
+    {
+      "epoch": 4.395457581830327,
+      "grad_norm": 0.837150514125824,
+      "learning_rate": 0.0002,
+      "loss": 1.4119,
+      "step": 3290
+    },
+    {
+      "epoch": 4.408817635270541,
+      "grad_norm": 0.8370638489723206,
+      "learning_rate": 0.0002,
+      "loss": 1.461,
+      "step": 3300
+    },
+    {
+      "epoch": 4.422177688710755,
+      "grad_norm": 0.7738229036331177,
+      "learning_rate": 0.0002,
+      "loss": 1.4478,
+      "step": 3310
+    },
+    {
+      "epoch": 4.435537742150968,
+      "grad_norm": 0.7665290832519531,
+      "learning_rate": 0.0002,
+      "loss": 1.4195,
+      "step": 3320
+    },
+    {
+      "epoch": 4.448897795591183,
+      "grad_norm": 0.7547745704650879,
+      "learning_rate": 0.0002,
+      "loss": 1.3308,
+      "step": 3330
+    },
+    {
+      "epoch": 4.462257849031396,
+      "grad_norm": 0.7421861290931702,
+      "learning_rate": 0.0002,
+      "loss": 1.4165,
+      "step": 3340
+    },
+    {
+      "epoch": 4.47561790247161,
+      "grad_norm": 0.8042104244232178,
+      "learning_rate": 0.0002,
+      "loss": 1.4244,
+      "step": 3350
+    },
+    {
+      "epoch": 4.488977955911824,
+      "grad_norm": 0.8111839890480042,
+      "learning_rate": 0.0002,
+      "loss": 1.365,
+      "step": 3360
+    },
+    {
+      "epoch": 4.502338009352037,
+      "grad_norm": 0.7998340129852295,
+      "learning_rate": 0.0002,
+      "loss": 1.3537,
+      "step": 3370
+    },
+    {
+      "epoch": 4.515698062792251,
+      "grad_norm": 0.7668877243995667,
+      "learning_rate": 0.0002,
+      "loss": 1.3812,
+      "step": 3380
+    },
+    {
+      "epoch": 4.529058116232465,
+      "grad_norm": 0.7986718416213989,
+      "learning_rate": 0.0002,
+      "loss": 1.3972,
+      "step": 3390
+    },
+    {
+      "epoch": 4.542418169672679,
+      "grad_norm": 0.6806602478027344,
+      "learning_rate": 0.0002,
+      "loss": 1.3582,
+      "step": 3400
+    },
+    {
+      "epoch": 4.555778223112893,
+      "grad_norm": 0.8788819909095764,
+      "learning_rate": 0.0002,
+      "loss": 1.3942,
+      "step": 3410
+    },
+    {
+      "epoch": 4.569138276553106,
+      "grad_norm": 0.7499664425849915,
+      "learning_rate": 0.0002,
+      "loss": 1.3379,
+      "step": 3420
+    },
+    {
+      "epoch": 4.58249832999332,
+      "grad_norm": 0.7967109084129333,
+      "learning_rate": 0.0002,
+      "loss": 1.3823,
+      "step": 3430
+    },
+    {
+      "epoch": 4.595858383433534,
+      "grad_norm": 0.759639322757721,
+      "learning_rate": 0.0002,
+      "loss": 1.3531,
+      "step": 3440
+    },
+    {
+      "epoch": 4.609218436873747,
+      "grad_norm": 0.8327916264533997,
+      "learning_rate": 0.0002,
+      "loss": 1.3517,
+      "step": 3450
+    },
+    {
+      "epoch": 4.622578490313961,
+      "grad_norm": 0.7400892376899719,
+      "learning_rate": 0.0002,
+      "loss": 1.4619,
+      "step": 3460
+    },
+    {
+      "epoch": 4.635938543754175,
+      "grad_norm": 0.8116602301597595,
+      "learning_rate": 0.0002,
+      "loss": 1.3374,
+      "step": 3470
+    },
+    {
+      "epoch": 4.649298597194389,
+      "grad_norm": 0.7604362368583679,
+      "learning_rate": 0.0002,
+      "loss": 1.4445,
+      "step": 3480
+    },
+    {
+      "epoch": 4.662658650634603,
+      "grad_norm": 0.7397996783256531,
+      "learning_rate": 0.0002,
+      "loss": 1.3724,
+      "step": 3490
+    },
+    {
+      "epoch": 4.676018704074816,
+      "grad_norm": 0.869293749332428,
+      "learning_rate": 0.0002,
+      "loss": 1.4048,
+      "step": 3500
+    },
+    {
+      "epoch": 4.68937875751503,
+      "grad_norm": 0.6854358315467834,
+      "learning_rate": 0.0002,
+      "loss": 1.3873,
+      "step": 3510
+    },
+    {
+      "epoch": 4.7027388109552435,
+      "grad_norm": 0.8326661586761475,
+      "learning_rate": 0.0002,
+      "loss": 1.3413,
+      "step": 3520
+    },
+    {
+      "epoch": 4.716098864395457,
+      "grad_norm": 0.6887506246566772,
+      "learning_rate": 0.0002,
+      "loss": 1.3666,
+      "step": 3530
+    },
+    {
+      "epoch": 4.729458917835672,
+      "grad_norm": 3.837689161300659,
+      "learning_rate": 0.0002,
+      "loss": 1.4508,
+      "step": 3540
+    },
+    {
+      "epoch": 4.742818971275885,
+      "grad_norm": 0.6874563694000244,
+      "learning_rate": 0.0002,
+      "loss": 1.3775,
+      "step": 3550
+    },
+    {
+      "epoch": 4.756179024716099,
+      "grad_norm": 0.8340407609939575,
+      "learning_rate": 0.0002,
+      "loss": 1.3643,
+      "step": 3560
+    },
+    {
+      "epoch": 4.7695390781563125,
+      "grad_norm": 0.7286418676376343,
+      "learning_rate": 0.0002,
+      "loss": 1.3556,
+      "step": 3570
+    },
+    {
+      "epoch": 4.782899131596526,
+      "grad_norm": 0.7239373326301575,
+      "learning_rate": 0.0002,
+      "loss": 1.4338,
+      "step": 3580
+    },
+    {
+      "epoch": 4.796259185036741,
+      "grad_norm": 0.831310510635376,
+      "learning_rate": 0.0002,
+      "loss": 1.4697,
+      "step": 3590
+    },
+    {
+      "epoch": 4.809619238476954,
+      "grad_norm": 0.767715573310852,
+      "learning_rate": 0.0002,
+      "loss": 1.4146,
+      "step": 3600
+    },
+    {
+      "epoch": 4.822979291917168,
+      "grad_norm": 0.9013199210166931,
+      "learning_rate": 0.0002,
+      "loss": 1.4199,
+      "step": 3610
+    },
+    {
+      "epoch": 4.8363393453573815,
+      "grad_norm": 0.7543512582778931,
+      "learning_rate": 0.0002,
+      "loss": 1.4513,
+      "step": 3620
+    },
+    {
+      "epoch": 4.849699398797595,
+      "grad_norm": 0.7626057267189026,
+      "learning_rate": 0.0002,
+      "loss": 1.4218,
+      "step": 3630
+    },
+    {
+      "epoch": 4.863059452237809,
+      "grad_norm": 0.847079336643219,
+      "learning_rate": 0.0002,
+      "loss": 1.4102,
+      "step": 3640
+    },
+    {
+      "epoch": 4.876419505678022,
+      "grad_norm": 0.8273295760154724,
+      "learning_rate": 0.0002,
+      "loss": 1.5014,
+      "step": 3650
+    },
+    {
+      "epoch": 4.889779559118237,
+      "grad_norm": 0.7675244808197021,
+      "learning_rate": 0.0002,
+      "loss": 1.3806,
+      "step": 3660
+    },
+    {
+      "epoch": 4.9031396125584505,
+      "grad_norm": 0.9560356736183167,
+      "learning_rate": 0.0002,
+      "loss": 1.4894,
+      "step": 3670
+    },
+    {
+      "epoch": 4.916499665998664,
+      "grad_norm": 0.7682451605796814,
+      "learning_rate": 0.0002,
+      "loss": 1.4044,
+      "step": 3680
+    },
+    {
+      "epoch": 4.929859719438878,
+      "grad_norm": 0.8113830089569092,
+      "learning_rate": 0.0002,
+      "loss": 1.342,
+      "step": 3690
+    },
+    {
+      "epoch": 4.943219772879091,
+      "grad_norm": 0.7642542719841003,
+      "learning_rate": 0.0002,
+      "loss": 1.3559,
+      "step": 3700
+    },
+    {
+      "epoch": 4.956579826319305,
+      "grad_norm": 0.823863685131073,
+      "learning_rate": 0.0002,
+      "loss": 1.403,
+      "step": 3710
+    },
+    {
+      "epoch": 4.969939879759519,
+      "grad_norm": 0.8287797570228577,
+      "learning_rate": 0.0002,
+      "loss": 1.464,
+      "step": 3720
+    },
+    {
+      "epoch": 4.983299933199733,
+      "grad_norm": 0.778170108795166,
+      "learning_rate": 0.0002,
+      "loss": 1.4139,
+      "step": 3730
+    },
+    {
+      "epoch": 4.996659986639947,
+      "grad_norm": 0.7464073896408081,
+      "learning_rate": 0.0002,
+      "loss": 1.4218,
+      "step": 3740
+    },
+    {
+      "epoch": 4.999331997327989,
+      "eval_loss": 1.9638569355010986,
+      "eval_runtime": 38.5725,
+      "eval_samples_per_second": 13.351,
+      "eval_steps_per_second": 1.685,
+      "step": 3742
+    },
+    {
+      "epoch": 5.01002004008016,
+      "grad_norm": 0.8864085078239441,
+      "learning_rate": 0.0002,
+      "loss": 1.225,
+      "step": 3750
+    },
+    {
+      "epoch": 5.023380093520374,
+      "grad_norm": 0.9191637635231018,
+      "learning_rate": 0.0002,
+      "loss": 1.2056,
+      "step": 3760
+    },
+    {
+      "epoch": 5.036740146960588,
+      "grad_norm": 0.749519407749176,
+      "learning_rate": 0.0002,
+      "loss": 1.2453,
+      "step": 3770
+    },
+    {
+      "epoch": 5.050100200400801,
+      "grad_norm": 0.7916892170906067,
+      "learning_rate": 0.0002,
+      "loss": 1.1959,
+      "step": 3780
+    },
+    {
+      "epoch": 5.063460253841015,
+      "grad_norm": 1.0318909883499146,
+      "learning_rate": 0.0002,
+      "loss": 1.2279,
+      "step": 3790
+    },
+    {
+      "epoch": 5.0768203072812295,
+      "grad_norm": 1.028586745262146,
+      "learning_rate": 0.0002,
+      "loss": 1.2585,
+      "step": 3800
+    },
+    {
+      "epoch": 5.090180360721443,
+      "grad_norm": 1.0568538904190063,
+      "learning_rate": 0.0002,
+      "loss": 1.1769,
+      "step": 3810
+    },
+    {
+      "epoch": 5.103540414161657,
+      "grad_norm": 0.9780595302581787,
+      "learning_rate": 0.0002,
+      "loss": 1.263,
+      "step": 3820
+    },
+    {
+      "epoch": 5.11690046760187,
+      "grad_norm": 1.10311758518219,
+      "learning_rate": 0.0002,
+      "loss": 1.2019,
+      "step": 3830
+    },
+    {
+      "epoch": 5.130260521042084,
+      "grad_norm": 0.9497154355049133,
+      "learning_rate": 0.0002,
+      "loss": 1.2133,
+      "step": 3840
+    },
+    {
+      "epoch": 5.143620574482298,
+      "grad_norm": 0.948279857635498,
+      "learning_rate": 0.0002,
+      "loss": 1.1718,
+      "step": 3850
+    },
+    {
+      "epoch": 5.156980627922512,
+      "grad_norm": 0.9497880339622498,
+      "learning_rate": 0.0002,
+      "loss": 1.2108,
+      "step": 3860
+    },
+    {
+      "epoch": 5.170340681362726,
+      "grad_norm": 1.3213258981704712,
+      "learning_rate": 0.0002,
+      "loss": 1.1876,
+      "step": 3870
+    },
+    {
+      "epoch": 5.183700734802939,
+      "grad_norm": 0.9835752248764038,
+      "learning_rate": 0.0002,
+      "loss": 1.2327,
+      "step": 3880
+    },
+    {
+      "epoch": 5.197060788243153,
+      "grad_norm": 0.8426132202148438,
+      "learning_rate": 0.0002,
+      "loss": 1.2256,
+      "step": 3890
+    },
+    {
+      "epoch": 5.210420841683367,
+      "grad_norm": 1.0343470573425293,
+      "learning_rate": 0.0002,
+      "loss": 1.2066,
+      "step": 3900
+    },
+    {
+      "epoch": 5.22378089512358,
+      "grad_norm": 1.0771924257278442,
+      "learning_rate": 0.0002,
+      "loss": 1.2596,
+      "step": 3910
+    },
+    {
+      "epoch": 5.237140948563794,
+      "grad_norm": 0.8542634844779968,
+      "learning_rate": 0.0002,
+      "loss": 1.2371,
+      "step": 3920
+    },
+    {
+      "epoch": 5.250501002004008,
+      "grad_norm": 1.1021966934204102,
+      "learning_rate": 0.0002,
+      "loss": 1.2264,
+      "step": 3930
+    },
+    {
+      "epoch": 5.263861055444222,
+      "grad_norm": 1.170011281967163,
+      "learning_rate": 0.0002,
+      "loss": 1.2097,
+      "step": 3940
+    },
+    {
+      "epoch": 5.277221108884436,
+      "grad_norm": 0.9787653684616089,
+      "learning_rate": 0.0002,
+      "loss": 1.2101,
+      "step": 3950
+    },
+    {
+      "epoch": 5.290581162324649,
+      "grad_norm": 0.914513885974884,
+      "learning_rate": 0.0002,
+      "loss": 1.24,
+      "step": 3960
+    },
+    {
+      "epoch": 5.303941215764863,
+      "grad_norm": 1.0831562280654907,
+      "learning_rate": 0.0002,
+      "loss": 1.1641,
+      "step": 3970
+    },
+    {
+      "epoch": 5.3173012692050765,
+      "grad_norm": 0.9810112714767456,
+      "learning_rate": 0.0002,
+      "loss": 1.2609,
+      "step": 3980
+    },
+    {
+      "epoch": 5.330661322645291,
+      "grad_norm": 0.9624066948890686,
+      "learning_rate": 0.0002,
+      "loss": 1.1825,
+      "step": 3990
+    },
+    {
+      "epoch": 5.344021376085505,
+      "grad_norm": 1.2296923398971558,
+      "learning_rate": 0.0002,
+      "loss": 1.273,
+      "step": 4000
+    },
+    {
+      "epoch": 5.357381429525718,
+      "grad_norm": 1.011299967765808,
+      "learning_rate": 0.0002,
+      "loss": 1.2452,
+      "step": 4010
+    },
+    {
+      "epoch": 5.370741482965932,
+      "grad_norm": 0.9144132733345032,
+      "learning_rate": 0.0002,
+      "loss": 1.2539,
+      "step": 4020
+    },
+    {
+      "epoch": 5.3841015364061455,
+      "grad_norm": 1.0573601722717285,
+      "learning_rate": 0.0002,
+      "loss": 1.2914,
+      "step": 4030
+    },
+    {
+      "epoch": 5.397461589846359,
+      "grad_norm": 1.1667137145996094,
+      "learning_rate": 0.0002,
+      "loss": 1.2295,
+      "step": 4040
+    },
+    {
+      "epoch": 5.410821643286573,
+      "grad_norm": 1.072070598602295,
+      "learning_rate": 0.0002,
+      "loss": 1.2541,
+      "step": 4050
+    },
+    {
+      "epoch": 5.424181696726787,
+      "grad_norm": 1.1005792617797852,
+      "learning_rate": 0.0002,
+      "loss": 1.2448,
+      "step": 4060
+    },
+    {
+      "epoch": 5.437541750167001,
+      "grad_norm": 1.033581018447876,
+      "learning_rate": 0.0002,
+      "loss": 1.2604,
+      "step": 4070
+    },
+    {
+      "epoch": 5.4509018036072145,
+      "grad_norm": 0.9537439942359924,
+      "learning_rate": 0.0002,
+      "loss": 1.2552,
+      "step": 4080
+    },
+    {
+      "epoch": 5.464261857047428,
+      "grad_norm": 1.0502177476882935,
+      "learning_rate": 0.0002,
+      "loss": 1.2985,
+      "step": 4090
+    },
+    {
+      "epoch": 5.477621910487642,
+      "grad_norm": 0.9098296761512756,
+      "learning_rate": 0.0002,
+      "loss": 1.2424,
+      "step": 4100
+    },
+    {
+      "epoch": 5.490981963927855,
+      "grad_norm": 0.9551953077316284,
+      "learning_rate": 0.0002,
+      "loss": 1.2262,
+      "step": 4110
+    },
+    {
+      "epoch": 5.504342017368069,
+      "grad_norm": 0.9169427156448364,
+      "learning_rate": 0.0002,
+      "loss": 1.2848,
+      "step": 4120
+    },
+    {
+      "epoch": 5.517702070808284,
+      "grad_norm": 0.9430235624313354,
+      "learning_rate": 0.0002,
+      "loss": 1.2572,
+      "step": 4130
+    },
+    {
+      "epoch": 5.531062124248497,
+      "grad_norm": 0.817259669303894,
+      "learning_rate": 0.0002,
+      "loss": 1.2618,
+      "step": 4140
+    },
+    {
+      "epoch": 5.544422177688711,
+      "grad_norm": 1.124152660369873,
+      "learning_rate": 0.0002,
+      "loss": 1.3012,
+      "step": 4150
+    },
+    {
+      "epoch": 5.557782231128924,
+      "grad_norm": 0.9250756502151489,
+      "learning_rate": 0.0002,
+      "loss": 1.2508,
+      "step": 4160
+    },
+    {
+      "epoch": 5.571142284569138,
+      "grad_norm": 0.9582970142364502,
+      "learning_rate": 0.0002,
+      "loss": 1.2492,
+      "step": 4170
+    },
+    {
+      "epoch": 5.584502338009352,
+      "grad_norm": 1.0078704357147217,
+      "learning_rate": 0.0002,
+      "loss": 1.2804,
+      "step": 4180
+    },
+    {
+      "epoch": 5.597862391449565,
+      "grad_norm": 0.9585610032081604,
+      "learning_rate": 0.0002,
+      "loss": 1.1961,
+      "step": 4190
+    },
+    {
+      "epoch": 5.61122244488978,
+      "grad_norm": 1.0150971412658691,
+      "learning_rate": 0.0002,
+      "loss": 1.2522,
+      "step": 4200
+    },
+    {
+      "epoch": 5.6245824983299935,
+      "grad_norm": 0.9943351149559021,
+      "learning_rate": 0.0002,
+      "loss": 1.2275,
+      "step": 4210
+    },
+    {
+      "epoch": 5.637942551770207,
+      "grad_norm": 0.8880936503410339,
+      "learning_rate": 0.0002,
+      "loss": 1.2928,
+      "step": 4220
+    },
+    {
+      "epoch": 5.651302605210421,
+      "grad_norm": 0.9873887896537781,
+      "learning_rate": 0.0002,
+      "loss": 1.2323,
+      "step": 4230
+    },
+    {
+      "epoch": 5.664662658650634,
+      "grad_norm": 0.9185152649879456,
+      "learning_rate": 0.0002,
+      "loss": 1.3391,
+      "step": 4240
+    },
+    {
+      "epoch": 5.678022712090849,
+      "grad_norm": 1.0706779956817627,
+      "learning_rate": 0.0002,
+      "loss": 1.2511,
+      "step": 4250
+    },
+    {
+      "epoch": 5.6913827655310625,
+      "grad_norm": 0.9660224914550781,
+      "learning_rate": 0.0002,
+      "loss": 1.2737,
+      "step": 4260
+    },
+    {
+      "epoch": 5.704742818971276,
+      "grad_norm": 0.8685019612312317,
+      "learning_rate": 0.0002,
+      "loss": 1.2815,
+      "step": 4270
+    },
+    {
+      "epoch": 5.71810287241149,
+      "grad_norm": 1.0390565395355225,
+      "learning_rate": 0.0002,
+      "loss": 1.1559,
+      "step": 4280
+    },
+    {
+      "epoch": 5.731462925851703,
+      "grad_norm": 0.9290478825569153,
+      "learning_rate": 0.0002,
+      "loss": 1.3134,
+      "step": 4290
+    },
+    {
+      "epoch": 5.744822979291917,
+      "grad_norm": 1.0361281633377075,
+      "learning_rate": 0.0002,
+      "loss": 1.2426,
+      "step": 4300
+    },
+    {
+      "epoch": 5.758183032732131,
+      "grad_norm": 0.8804615139961243,
+      "learning_rate": 0.0002,
+      "loss": 1.2688,
+      "step": 4310
+    },
+    {
+      "epoch": 5.771543086172345,
+      "grad_norm": 1.0051425695419312,
+      "learning_rate": 0.0002,
+      "loss": 1.2479,
+      "step": 4320
+    },
+    {
+      "epoch": 5.784903139612559,
+      "grad_norm": 1.0051119327545166,
+      "learning_rate": 0.0002,
+      "loss": 1.1946,
+      "step": 4330
+    },
+    {
+      "epoch": 5.798263193052772,
+      "grad_norm": 0.9961661100387573,
+      "learning_rate": 0.0002,
+      "loss": 1.2571,
+      "step": 4340
+    },
+    {
+      "epoch": 5.811623246492986,
+      "grad_norm": 1.0229419469833374,
+      "learning_rate": 0.0002,
+      "loss": 1.2179,
+      "step": 4350
+    },
+    {
+      "epoch": 5.8249832999332,
+      "grad_norm": 1.1129552125930786,
+      "learning_rate": 0.0002,
+      "loss": 1.2984,
+      "step": 4360
+    },
+    {
+      "epoch": 5.838343353373413,
+      "grad_norm": 1.18964421749115,
+      "learning_rate": 0.0002,
+      "loss": 1.2692,
+      "step": 4370
+    },
+    {
+      "epoch": 5.851703406813627,
+      "grad_norm": 0.9490230083465576,
+      "learning_rate": 0.0002,
+      "loss": 1.1996,
+      "step": 4380
+    },
+    {
+      "epoch": 5.865063460253841,
+      "grad_norm": 0.8734540343284607,
+      "learning_rate": 0.0002,
+      "loss": 1.3177,
+      "step": 4390
+    },
+    {
+      "epoch": 5.878423513694055,
+      "grad_norm": 1.0017802715301514,
+      "learning_rate": 0.0002,
+      "loss": 1.3131,
+      "step": 4400
+    },
+    {
+      "epoch": 5.891783567134269,
+      "grad_norm": 0.953556478023529,
+      "learning_rate": 0.0002,
+      "loss": 1.2649,
+      "step": 4410
+    },
+    {
+      "epoch": 5.905143620574482,
+      "grad_norm": 0.8915258646011353,
+      "learning_rate": 0.0002,
+      "loss": 1.2684,
+      "step": 4420
+    },
+    {
+      "epoch": 5.918503674014696,
+      "grad_norm": 0.9715141654014587,
+      "learning_rate": 0.0002,
+      "loss": 1.2843,
+      "step": 4430
+    },
+    {
+      "epoch": 5.9318637274549095,
+      "grad_norm": 0.9432152509689331,
+      "learning_rate": 0.0002,
+      "loss": 1.2769,
+      "step": 4440
+    },
+    {
+      "epoch": 5.945223780895123,
+      "grad_norm": 0.9473979473114014,
+      "learning_rate": 0.0002,
+      "loss": 1.233,
+      "step": 4450
+    },
+    {
+      "epoch": 5.958583834335338,
+      "grad_norm": 1.104871392250061,
+      "learning_rate": 0.0002,
+      "loss": 1.3209,
+      "step": 4460
+    },
+    {
+      "epoch": 5.971943887775551,
+      "grad_norm": 1.0308905839920044,
+      "learning_rate": 0.0002,
+      "loss": 1.3427,
+      "step": 4470
+    },
+    {
+      "epoch": 5.985303941215765,
+      "grad_norm": 0.8895487189292908,
+      "learning_rate": 0.0002,
+      "loss": 1.1808,
+      "step": 4480
+    },
+    {
+      "epoch": 5.9986639946559785,
+      "grad_norm": 1.0148485898971558,
+      "learning_rate": 0.0002,
+      "loss": 1.2634,
+      "step": 4490
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.0830726623535156,
+      "eval_runtime": 38.5442,
+      "eval_samples_per_second": 13.361,
+      "eval_steps_per_second": 1.686,
+      "step": 4491
+    },
+    {
+      "epoch": 6.012024048096192,
+      "grad_norm": 1.1640599966049194,
+      "learning_rate": 0.0002,
+      "loss": 1.1106,
+      "step": 4500
+    },
+    {
+      "epoch": 6.025384101536406,
+      "grad_norm": 1.213204264640808,
+      "learning_rate": 0.0002,
+      "loss": 1.0436,
+      "step": 4510
+    },
+    {
+      "epoch": 6.03874415497662,
+      "grad_norm": 1.1694388389587402,
+      "learning_rate": 0.0002,
+      "loss": 1.0606,
+      "step": 4520
+    },
+    {
+      "epoch": 6.052104208416834,
+      "grad_norm": 1.1044062376022339,
+      "learning_rate": 0.0002,
+      "loss": 1.0274,
+      "step": 4530
+    },
+    {
+      "epoch": 6.065464261857048,
+      "grad_norm": 1.0701100826263428,
+      "learning_rate": 0.0002,
+      "loss": 1.0552,
+      "step": 4540
+    },
+    {
+      "epoch": 6.078824315297261,
+      "grad_norm": 1.360065221786499,
+      "learning_rate": 0.0002,
+      "loss": 1.0018,
+      "step": 4550
+    },
+    {
+      "epoch": 6.092184368737475,
+      "grad_norm": 1.0648503303527832,
+      "learning_rate": 0.0002,
+      "loss": 1.0189,
+      "step": 4560
+    },
+    {
+      "epoch": 6.1055444221776884,
+      "grad_norm": 1.066245198249817,
+      "learning_rate": 0.0002,
+      "loss": 1.008,
+      "step": 4570
+    },
+    {
+      "epoch": 6.118904475617902,
+      "grad_norm": 1.1483700275421143,
+      "learning_rate": 0.0002,
+      "loss": 1.099,
+      "step": 4580
+    },
+    {
+      "epoch": 6.132264529058117,
+      "grad_norm": 1.334275722503662,
+      "learning_rate": 0.0002,
+      "loss": 1.1043,
+      "step": 4590
+    },
+    {
+      "epoch": 6.14562458249833,
+      "grad_norm": 1.2141029834747314,
+      "learning_rate": 0.0002,
+      "loss": 1.0783,
+      "step": 4600
+    },
+    {
+      "epoch": 6.158984635938544,
+      "grad_norm": 1.2284387350082397,
+      "learning_rate": 0.0002,
+      "loss": 1.0891,
+      "step": 4610
+    },
+    {
+      "epoch": 6.1723446893787575,
+      "grad_norm": 1.2326734066009521,
+      "learning_rate": 0.0002,
+      "loss": 1.122,
+      "step": 4620
+    },
+    {
+      "epoch": 6.185704742818971,
+      "grad_norm": 1.245004653930664,
+      "learning_rate": 0.0002,
+      "loss": 1.1069,
+      "step": 4630
+    },
+    {
+      "epoch": 6.199064796259185,
+      "grad_norm": 0.9685266017913818,
+      "learning_rate": 0.0002,
+      "loss": 1.0821,
+      "step": 4640
+    },
+    {
+      "epoch": 6.212424849699399,
+      "grad_norm": 1.141634464263916,
+      "learning_rate": 0.0002,
+      "loss": 1.0659,
+      "step": 4650
+    },
+    {
+      "epoch": 6.225784903139613,
+      "grad_norm": 1.4279003143310547,
+      "learning_rate": 0.0002,
+      "loss": 1.0971,
+      "step": 4660
+    },
+    {
+      "epoch": 6.2391449565798265,
+      "grad_norm": 1.186668872833252,
+      "learning_rate": 0.0002,
+      "loss": 1.093,
+      "step": 4670
+    },
+    {
+      "epoch": 6.25250501002004,
+      "grad_norm": 1.2656606435775757,
+      "learning_rate": 0.0002,
+      "loss": 1.0522,
+      "step": 4680
+    },
+    {
+      "epoch": 6.265865063460254,
+      "grad_norm": 1.1122987270355225,
+      "learning_rate": 0.0002,
+      "loss": 1.1138,
+      "step": 4690
+    },
+    {
+      "epoch": 6.279225116900467,
+      "grad_norm": 1.190050482749939,
+      "learning_rate": 0.0002,
+      "loss": 1.0906,
+      "step": 4700
+    },
+    {
+      "epoch": 6.292585170340681,
+      "grad_norm": 1.3683340549468994,
+      "learning_rate": 0.0002,
+      "loss": 1.1095,
+      "step": 4710
+    },
+    {
+      "epoch": 6.3059452237808955,
+      "grad_norm": 1.1787203550338745,
+      "learning_rate": 0.0002,
+      "loss": 1.0663,
+      "step": 4720
+    },
+    {
+      "epoch": 6.319305277221109,
+      "grad_norm": 1.3502576351165771,
+      "learning_rate": 0.0002,
+      "loss": 1.0856,
+      "step": 4730
+    },
+    {
+      "epoch": 6.332665330661323,
+      "grad_norm": 1.1958597898483276,
+      "learning_rate": 0.0002,
+      "loss": 1.0999,
+      "step": 4740
+    },
+    {
+      "epoch": 6.346025384101536,
+      "grad_norm": 1.0918327569961548,
+      "learning_rate": 0.0002,
+      "loss": 1.021,
+      "step": 4750
+    },
+    {
+      "epoch": 6.35938543754175,
+      "grad_norm": 1.2624558210372925,
+      "learning_rate": 0.0002,
+      "loss": 1.0484,
+      "step": 4760
+    },
+    {
+      "epoch": 6.372745490981964,
+      "grad_norm": 1.1390577554702759,
+      "learning_rate": 0.0002,
+      "loss": 1.0785,
+      "step": 4770
+    },
+    {
+      "epoch": 6.386105544422177,
+      "grad_norm": 1.041666865348816,
+      "learning_rate": 0.0002,
+      "loss": 1.0979,
+      "step": 4780
+    },
+    {
+      "epoch": 6.399465597862392,
+      "grad_norm": 1.4209141731262207,
+      "learning_rate": 0.0002,
+      "loss": 1.1026,
+      "step": 4790
+    },
+    {
+      "epoch": 6.412825651302605,
+      "grad_norm": 1.1001079082489014,
+      "learning_rate": 0.0002,
+      "loss": 1.119,
+      "step": 4800
+    },
+    {
+      "epoch": 6.426185704742819,
+      "grad_norm": 1.3324936628341675,
+      "learning_rate": 0.0002,
+      "loss": 1.1082,
+      "step": 4810
+    },
+    {
+      "epoch": 6.439545758183033,
+      "grad_norm": 1.1270194053649902,
+      "learning_rate": 0.0002,
+      "loss": 1.0785,
+      "step": 4820
+    },
+    {
+      "epoch": 6.452905811623246,
+      "grad_norm": 1.1961387395858765,
+      "learning_rate": 0.0002,
+      "loss": 1.1338,
+      "step": 4830
+    },
+    {
+      "epoch": 6.46626586506346,
+      "grad_norm": 1.255366563796997,
+      "learning_rate": 0.0002,
+      "loss": 1.0967,
+      "step": 4840
+    },
+    {
+      "epoch": 6.479625918503674,
+      "grad_norm": 1.343855381011963,
+      "learning_rate": 0.0002,
+      "loss": 1.1226,
+      "step": 4850
+    },
+    {
+      "epoch": 6.492985971943888,
+      "grad_norm": 1.3216257095336914,
+      "learning_rate": 0.0002,
+      "loss": 1.1118,
+      "step": 4860
+    },
+    {
+      "epoch": 6.506346025384102,
+      "grad_norm": 1.5244755744934082,
+      "learning_rate": 0.0002,
+      "loss": 1.1664,
+      "step": 4870
+    },
+    {
+      "epoch": 6.519706078824315,
+      "grad_norm": 1.1585701704025269,
+      "learning_rate": 0.0002,
+      "loss": 1.0403,
+      "step": 4880
+    },
+    {
+      "epoch": 6.533066132264529,
+      "grad_norm": 1.0301100015640259,
+      "learning_rate": 0.0002,
+      "loss": 1.1344,
+      "step": 4890
+    },
+    {
+      "epoch": 6.5464261857047426,
+      "grad_norm": 1.5772714614868164,
+      "learning_rate": 0.0002,
+      "loss": 1.1304,
+      "step": 4900
+    },
+    {
+      "epoch": 6.559786239144957,
+      "grad_norm": 1.2015259265899658,
+      "learning_rate": 0.0002,
+      "loss": 1.0953,
+      "step": 4910
+    },
+    {
+      "epoch": 6.573146292585171,
+      "grad_norm": 1.4365423917770386,
+      "learning_rate": 0.0002,
+      "loss": 1.1283,
+      "step": 4920
+    },
+    {
+      "epoch": 6.586506346025384,
+      "grad_norm": 1.2534470558166504,
+      "learning_rate": 0.0002,
+      "loss": 1.0717,
+      "step": 4930
+    },
+    {
+      "epoch": 6.599866399465598,
+      "grad_norm": 1.216138482093811,
+      "learning_rate": 0.0002,
+      "loss": 1.1099,
+      "step": 4940
+    },
+    {
+      "epoch": 6.613226452905812,
+      "grad_norm": 1.144316554069519,
+      "learning_rate": 0.0002,
+      "loss": 1.1744,
+      "step": 4950
+    },
+    {
+      "epoch": 6.626586506346025,
+      "grad_norm": 1.1127740144729614,
+      "learning_rate": 0.0002,
+      "loss": 1.0548,
+      "step": 4960
+    },
+    {
+      "epoch": 6.639946559786239,
+      "grad_norm": 1.1925606727600098,
+      "learning_rate": 0.0002,
+      "loss": 1.0686,
+      "step": 4970
+    },
+    {
+      "epoch": 6.653306613226453,
+      "grad_norm": 1.2500451803207397,
+      "learning_rate": 0.0002,
+      "loss": 1.0684,
+      "step": 4980
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 1.16154944896698,
+      "learning_rate": 0.0002,
+      "loss": 1.1642,
+      "step": 4990
+    },
+    {
+      "epoch": 6.680026720106881,
+      "grad_norm": 1.1921433210372925,
+      "learning_rate": 0.0002,
+      "loss": 1.1003,
+      "step": 5000
+    },
+    {
+      "epoch": 6.693386773547094,
+      "grad_norm": 1.1561170816421509,
+      "learning_rate": 0.0002,
+      "loss": 1.1278,
+      "step": 5010
+    },
+    {
+      "epoch": 6.706746826987308,
+      "grad_norm": 1.2988990545272827,
+      "learning_rate": 0.0002,
+      "loss": 1.0766,
+      "step": 5020
+    },
+    {
+      "epoch": 6.7201068804275215,
+      "grad_norm": 0.9620341062545776,
+      "learning_rate": 0.0002,
+      "loss": 1.1131,
+      "step": 5030
+    },
+    {
+      "epoch": 6.733466933867735,
+      "grad_norm": 1.084228515625,
+      "learning_rate": 0.0002,
+      "loss": 1.109,
+      "step": 5040
+    },
+    {
+      "epoch": 6.74682698730795,
+      "grad_norm": 1.1119431257247925,
+      "learning_rate": 0.0002,
+      "loss": 1.1474,
+      "step": 5050
+    },
+    {
+      "epoch": 6.760187040748163,
+      "grad_norm": 1.1365628242492676,
+      "learning_rate": 0.0002,
+      "loss": 1.179,
+      "step": 5060
+    },
+    {
+      "epoch": 6.773547094188377,
+      "grad_norm": 1.0989075899124146,
+      "learning_rate": 0.0002,
+      "loss": 1.0988,
+      "step": 5070
+    },
+    {
+      "epoch": 6.7869071476285905,
+      "grad_norm": 1.040647268295288,
+      "learning_rate": 0.0002,
+      "loss": 1.127,
+      "step": 5080
+    },
+    {
+      "epoch": 6.800267201068804,
+      "grad_norm": 1.1083087921142578,
+      "learning_rate": 0.0002,
+      "loss": 1.0793,
+      "step": 5090
+    },
+    {
+      "epoch": 6.813627254509018,
+      "grad_norm": 1.3434782028198242,
+      "learning_rate": 0.0002,
+      "loss": 1.1081,
+      "step": 5100
+    },
+    {
+      "epoch": 6.826987307949231,
+      "grad_norm": 1.2493442296981812,
+      "learning_rate": 0.0002,
+      "loss": 1.1243,
+      "step": 5110
+    },
+    {
+      "epoch": 6.840347361389446,
+      "grad_norm": 1.0672307014465332,
+      "learning_rate": 0.0002,
+      "loss": 1.0633,
+      "step": 5120
+    },
+    {
+      "epoch": 6.8537074148296595,
+      "grad_norm": 1.068350911140442,
+      "learning_rate": 0.0002,
+      "loss": 1.1344,
+      "step": 5130
+    },
+    {
+      "epoch": 6.867067468269873,
+      "grad_norm": 1.2880923748016357,
+      "learning_rate": 0.0002,
+      "loss": 1.1942,
+      "step": 5140
+    },
+    {
+      "epoch": 6.880427521710087,
+      "grad_norm": 1.0895041227340698,
+      "learning_rate": 0.0002,
+      "loss": 1.1445,
+      "step": 5150
+    },
+    {
+      "epoch": 6.8937875751503,
+      "grad_norm": 1.2383300065994263,
+      "learning_rate": 0.0002,
+      "loss": 1.1535,
+      "step": 5160
+    },
+    {
+      "epoch": 6.907147628590514,
+      "grad_norm": 1.5274227857589722,
+      "learning_rate": 0.0002,
+      "loss": 1.1653,
+      "step": 5170
+    },
+    {
+      "epoch": 6.920507682030728,
+      "grad_norm": 1.1453371047973633,
+      "learning_rate": 0.0002,
+      "loss": 1.1112,
+      "step": 5180
+    },
+    {
+      "epoch": 6.933867735470942,
+      "grad_norm": 1.171336054801941,
+      "learning_rate": 0.0002,
+      "loss": 1.1808,
+      "step": 5190
+    },
+    {
+      "epoch": 6.947227788911156,
+      "grad_norm": 1.1946955919265747,
+      "learning_rate": 0.0002,
+      "loss": 1.1142,
+      "step": 5200
+    },
+    {
+      "epoch": 6.960587842351369,
+      "grad_norm": 1.2290117740631104,
+      "learning_rate": 0.0002,
+      "loss": 1.1386,
+      "step": 5210
+    },
+    {
+      "epoch": 6.973947895791583,
+      "grad_norm": 1.3134533166885376,
+      "learning_rate": 0.0002,
+      "loss": 1.1573,
+      "step": 5220
+    },
+    {
+      "epoch": 6.987307949231797,
+      "grad_norm": 1.1500377655029297,
+      "learning_rate": 0.0002,
+      "loss": 1.1687,
+      "step": 5230
+    },
+    {
+      "epoch": 6.999331997327989,
+      "eval_loss": 2.2211341857910156,
+      "eval_runtime": 38.5729,
+      "eval_samples_per_second": 13.351,
+      "eval_steps_per_second": 1.685,
+      "step": 5239
+    },
+    {
+      "epoch": 7.00066800267201,
+      "grad_norm": 1.1143344640731812,
+      "learning_rate": 0.0002,
+      "loss": 1.1235,
+      "step": 5240
+    },
+    {
+      "epoch": 7.014028056112225,
+      "grad_norm": 1.5164896249771118,
+      "learning_rate": 0.0002,
+      "loss": 0.9203,
+      "step": 5250
+    },
+    {
+      "epoch": 7.027388109552438,
+      "grad_norm": 1.3737165927886963,
+      "learning_rate": 0.0002,
+      "loss": 0.9605,
+      "step": 5260
+    },
+    {
+      "epoch": 7.040748162992652,
+      "grad_norm": 1.2159202098846436,
+      "learning_rate": 0.0002,
+      "loss": 0.8599,
+      "step": 5270
+    },
+    {
+      "epoch": 7.054108216432866,
+      "grad_norm": 1.4183212518692017,
+      "learning_rate": 0.0002,
+      "loss": 0.9469,
+      "step": 5280
+    },
+    {
+      "epoch": 7.067468269873079,
+      "grad_norm": 1.4752920866012573,
+      "learning_rate": 0.0002,
+      "loss": 0.9188,
+      "step": 5290
+    },
+    {
+      "epoch": 7.080828323313293,
+      "grad_norm": 1.398065447807312,
+      "learning_rate": 0.0002,
+      "loss": 0.873,
+      "step": 5300
+    },
+    {
+      "epoch": 7.094188376753507,
+      "grad_norm": 1.4385913610458374,
+      "learning_rate": 0.0002,
+      "loss": 0.9434,
+      "step": 5310
+    },
+    {
+      "epoch": 7.107548430193721,
+      "grad_norm": 1.3779526948928833,
+      "learning_rate": 0.0002,
+      "loss": 0.8527,
+      "step": 5320
+    },
+    {
+      "epoch": 7.120908483633935,
+      "grad_norm": 1.5290347337722778,
+      "learning_rate": 0.0002,
+      "loss": 0.9139,
+      "step": 5330
+    },
+    {
+      "epoch": 7.134268537074148,
+      "grad_norm": 1.2389367818832397,
+      "learning_rate": 0.0002,
+      "loss": 0.8769,
+      "step": 5340
+    },
+    {
+      "epoch": 7.147628590514362,
+      "grad_norm": 1.4514659643173218,
+      "learning_rate": 0.0002,
+      "loss": 0.9396,
+      "step": 5350
+    },
+    {
+      "epoch": 7.160988643954576,
+      "grad_norm": 1.3247307538986206,
+      "learning_rate": 0.0002,
+      "loss": 0.9303,
+      "step": 5360
+    },
+    {
+      "epoch": 7.174348697394789,
+      "grad_norm": 1.1711286306381226,
+      "learning_rate": 0.0002,
+      "loss": 0.9218,
+      "step": 5370
+    },
+    {
+      "epoch": 7.187708750835004,
+      "grad_norm": 1.4408347606658936,
+      "learning_rate": 0.0002,
+      "loss": 0.944,
+      "step": 5380
+    },
+    {
+      "epoch": 7.201068804275217,
+      "grad_norm": 1.4405876398086548,
+      "learning_rate": 0.0002,
+      "loss": 0.9509,
+      "step": 5390
+    },
+    {
+      "epoch": 7.214428857715431,
+      "grad_norm": 1.233242154121399,
+      "learning_rate": 0.0002,
+      "loss": 0.9428,
+      "step": 5400
+    },
+    {
+      "epoch": 7.227788911155645,
+      "grad_norm": 1.734960675239563,
+      "learning_rate": 0.0002,
+      "loss": 0.9401,
+      "step": 5410
+    },
+    {
+      "epoch": 7.241148964595858,
+      "grad_norm": 1.5165163278579712,
+      "learning_rate": 0.0002,
+      "loss": 0.9232,
+      "step": 5420
+    },
+    {
+      "epoch": 7.254509018036072,
+      "grad_norm": 1.4353035688400269,
+      "learning_rate": 0.0002,
+      "loss": 0.949,
+      "step": 5430
+    },
+    {
+      "epoch": 7.2678690714762855,
+      "grad_norm": 1.4540636539459229,
+      "learning_rate": 0.0002,
+      "loss": 0.9029,
+      "step": 5440
+    },
+    {
+      "epoch": 7.2812291249165,
+      "grad_norm": 1.2676037549972534,
+      "learning_rate": 0.0002,
+      "loss": 0.9117,
+      "step": 5450
+    },
+    {
+      "epoch": 7.294589178356714,
+      "grad_norm": 1.2626118659973145,
+      "learning_rate": 0.0002,
+      "loss": 1.0148,
+      "step": 5460
+    },
+    {
+      "epoch": 7.307949231796927,
+      "grad_norm": 1.4866795539855957,
+      "learning_rate": 0.0002,
+      "loss": 0.9373,
+      "step": 5470
+    },
+    {
+      "epoch": 7.321309285237141,
+      "grad_norm": 1.2464289665222168,
+      "learning_rate": 0.0002,
+      "loss": 0.9474,
+      "step": 5480
+    },
+    {
+      "epoch": 7.3346693386773545,
+      "grad_norm": 1.2815988063812256,
+      "learning_rate": 0.0002,
+      "loss": 0.896,
+      "step": 5490
+    },
+    {
+      "epoch": 7.348029392117568,
+      "grad_norm": 1.282402753829956,
+      "learning_rate": 0.0002,
+      "loss": 0.9733,
+      "step": 5500
+    },
+    {
+      "epoch": 7.361389445557783,
+      "grad_norm": 1.5422425270080566,
+      "learning_rate": 0.0002,
+      "loss": 0.9427,
+      "step": 5510
+    },
+    {
+      "epoch": 7.374749498997996,
+      "grad_norm": 1.4137073755264282,
+      "learning_rate": 0.0002,
+      "loss": 1.0067,
+      "step": 5520
+    },
+    {
+      "epoch": 7.38810955243821,
+      "grad_norm": 1.4875508546829224,
+      "learning_rate": 0.0002,
+      "loss": 0.8669,
+      "step": 5530
+    },
+    {
+      "epoch": 7.4014696058784235,
+      "grad_norm": 1.292340874671936,
+      "learning_rate": 0.0002,
+      "loss": 0.9576,
+      "step": 5540
+    },
+    {
+      "epoch": 7.414829659318637,
+      "grad_norm": 1.5553388595581055,
+      "learning_rate": 0.0002,
+      "loss": 0.9031,
+      "step": 5550
+    },
+    {
+      "epoch": 7.428189712758851,
+      "grad_norm": 1.394142746925354,
+      "learning_rate": 0.0002,
+      "loss": 1.005,
+      "step": 5560
+    },
+    {
+      "epoch": 7.441549766199064,
+      "grad_norm": 1.3249385356903076,
+      "learning_rate": 0.0002,
+      "loss": 0.9493,
+      "step": 5570
+    },
+    {
+      "epoch": 7.454909819639279,
+      "grad_norm": 1.3204814195632935,
+      "learning_rate": 0.0002,
+      "loss": 0.9806,
+      "step": 5580
+    },
+    {
+      "epoch": 7.4682698730794925,
+      "grad_norm": 1.4062745571136475,
+      "learning_rate": 0.0002,
+      "loss": 0.9182,
+      "step": 5590
+    },
+    {
+      "epoch": 7.481629926519706,
+      "grad_norm": 1.2828562259674072,
+      "learning_rate": 0.0002,
+      "loss": 0.9429,
+      "step": 5600
+    },
+    {
+      "epoch": 7.49498997995992,
+      "grad_norm": 1.440412998199463,
+      "learning_rate": 0.0002,
+      "loss": 0.9498,
+      "step": 5610
+    },
+    {
+      "epoch": 7.508350033400133,
+      "grad_norm": 1.4771733283996582,
+      "learning_rate": 0.0002,
+      "loss": 1.0005,
+      "step": 5620
+    },
+    {
+      "epoch": 7.521710086840347,
+      "grad_norm": 1.329460620880127,
+      "learning_rate": 0.0002,
+      "loss": 0.9472,
+      "step": 5630
+    },
+    {
+      "epoch": 7.5350701402805615,
+      "grad_norm": 1.2443828582763672,
+      "learning_rate": 0.0002,
+      "loss": 0.9635,
+      "step": 5640
+    },
+    {
+      "epoch": 7.548430193720775,
+      "grad_norm": 1.3739941120147705,
+      "learning_rate": 0.0002,
+      "loss": 0.9785,
+      "step": 5650
+    },
+    {
+      "epoch": 7.561790247160989,
+      "grad_norm": 1.5168178081512451,
+      "learning_rate": 0.0002,
+      "loss": 0.9538,
+      "step": 5660
+    },
+    {
+      "epoch": 7.575150300601202,
+      "grad_norm": 1.3648325204849243,
+      "learning_rate": 0.0002,
+      "loss": 0.9381,
+      "step": 5670
+    },
+    {
+      "epoch": 7.588510354041416,
+      "grad_norm": 1.308164119720459,
+      "learning_rate": 0.0002,
+      "loss": 0.9696,
+      "step": 5680
+    },
+    {
+      "epoch": 7.60187040748163,
+      "grad_norm": 1.3583498001098633,
+      "learning_rate": 0.0002,
+      "loss": 0.9889,
+      "step": 5690
+    },
+    {
+      "epoch": 7.615230460921843,
+      "grad_norm": 1.4746732711791992,
+      "learning_rate": 0.0002,
+      "loss": 0.9566,
+      "step": 5700
+    },
+    {
+      "epoch": 7.628590514362058,
+      "grad_norm": 1.3042285442352295,
+      "learning_rate": 0.0002,
+      "loss": 0.9462,
+      "step": 5710
+    },
+    {
+      "epoch": 7.641950567802271,
+      "grad_norm": 1.5272791385650635,
+      "learning_rate": 0.0002,
+      "loss": 1.0146,
+      "step": 5720
+    },
+    {
+      "epoch": 7.655310621242485,
+      "grad_norm": 1.1505831480026245,
+      "learning_rate": 0.0002,
+      "loss": 0.9795,
+      "step": 5730
+    },
+    {
+      "epoch": 7.668670674682699,
+      "grad_norm": 1.3690030574798584,
+      "learning_rate": 0.0002,
+      "loss": 0.9758,
+      "step": 5740
+    },
+    {
+      "epoch": 7.682030728122912,
+      "grad_norm": 1.3092460632324219,
+      "learning_rate": 0.0002,
+      "loss": 0.9565,
+      "step": 5750
+    },
+    {
+      "epoch": 7.695390781563126,
+      "grad_norm": 1.7011737823486328,
+      "learning_rate": 0.0002,
+      "loss": 1.0147,
+      "step": 5760
+    },
+    {
+      "epoch": 7.70875083500334,
+      "grad_norm": 1.4010082483291626,
+      "learning_rate": 0.0002,
+      "loss": 1.0261,
+      "step": 5770
+    },
+    {
+      "epoch": 7.722110888443554,
+      "grad_norm": 1.63649582862854,
+      "learning_rate": 0.0002,
+      "loss": 1.0288,
+      "step": 5780
+    },
+    {
+      "epoch": 7.735470941883768,
+      "grad_norm": 1.5091519355773926,
+      "learning_rate": 0.0002,
+      "loss": 0.9496,
+      "step": 5790
+    },
+    {
+      "epoch": 7.748830995323981,
+      "grad_norm": 1.345441460609436,
+      "learning_rate": 0.0002,
+      "loss": 0.9627,
+      "step": 5800
+    },
+    {
+      "epoch": 7.762191048764195,
+      "grad_norm": 1.461037278175354,
+      "learning_rate": 0.0002,
+      "loss": 0.9518,
+      "step": 5810
+    },
+    {
+      "epoch": 7.775551102204409,
+      "grad_norm": 1.3914507627487183,
+      "learning_rate": 0.0002,
+      "loss": 0.9544,
+      "step": 5820
+    },
+    {
+      "epoch": 7.788911155644622,
+      "grad_norm": 1.293625831604004,
+      "learning_rate": 0.0002,
+      "loss": 0.9946,
+      "step": 5830
+    },
+    {
+      "epoch": 7.802271209084836,
+      "grad_norm": 1.5641531944274902,
+      "learning_rate": 0.0002,
+      "loss": 0.9732,
+      "step": 5840
+    },
+    {
+      "epoch": 7.81563126252505,
+      "grad_norm": 1.2400811910629272,
+      "learning_rate": 0.0002,
+      "loss": 0.9952,
+      "step": 5850
+    },
+    {
+      "epoch": 7.828991315965264,
+      "grad_norm": 1.335532546043396,
+      "learning_rate": 0.0002,
+      "loss": 0.9841,
+      "step": 5860
+    },
+    {
+      "epoch": 7.842351369405478,
+      "grad_norm": 1.4629961252212524,
+      "learning_rate": 0.0002,
+      "loss": 0.9609,
+      "step": 5870
+    },
+    {
+      "epoch": 7.855711422845691,
+      "grad_norm": 1.3005847930908203,
+      "learning_rate": 0.0002,
+      "loss": 1.0813,
+      "step": 5880
+    },
+    {
+      "epoch": 7.869071476285905,
+      "grad_norm": 1.6970791816711426,
+      "learning_rate": 0.0002,
+      "loss": 1.0466,
+      "step": 5890
+    },
+    {
+      "epoch": 7.882431529726119,
+      "grad_norm": 1.6887991428375244,
+      "learning_rate": 0.0002,
+      "loss": 0.9399,
+      "step": 5900
+    },
+    {
+      "epoch": 7.895791583166333,
+      "grad_norm": 1.4156445264816284,
+      "learning_rate": 0.0002,
+      "loss": 1.0364,
+      "step": 5910
+    },
+    {
+      "epoch": 7.909151636606547,
+      "grad_norm": 1.2695387601852417,
+      "learning_rate": 0.0002,
+      "loss": 0.9856,
+      "step": 5920
+    },
+    {
+      "epoch": 7.92251169004676,
+      "grad_norm": 1.4491169452667236,
+      "learning_rate": 0.0002,
+      "loss": 0.9902,
+      "step": 5930
+    },
+    {
+      "epoch": 7.935871743486974,
+      "grad_norm": 1.4262619018554688,
+      "learning_rate": 0.0002,
+      "loss": 1.047,
+      "step": 5940
+    },
+    {
+      "epoch": 7.9492317969271875,
+      "grad_norm": 1.5128049850463867,
+      "learning_rate": 0.0002,
+      "loss": 1.0889,
+      "step": 5950
+    },
+    {
+      "epoch": 7.962591850367401,
+      "grad_norm": 1.3630818128585815,
+      "learning_rate": 0.0002,
+      "loss": 0.9721,
+      "step": 5960
+    },
+    {
+      "epoch": 7.975951903807616,
+      "grad_norm": 1.410461187362671,
+      "learning_rate": 0.0002,
+      "loss": 1.0154,
+      "step": 5970
+    },
+    {
+      "epoch": 7.989311957247829,
+      "grad_norm": 1.4158549308776855,
+      "learning_rate": 0.0002,
+      "loss": 1.0192,
+      "step": 5980
+    },
+    {
+      "epoch": 7.994655978623914,
+      "eval_loss": 2.348383903503418,
+      "eval_runtime": 38.6667,
+      "eval_samples_per_second": 13.319,
+      "eval_steps_per_second": 1.681,
+      "step": 5984
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5984,
+  "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": 2.76926121281323e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7025f98e983b93b4fec0d5370c1456c7adecaf8e
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-5984/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e92f0598f349930e52e126f358a3dca045c3c88312ec4b3f814f018a04982a9
+size 5560
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/README.md b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..835e31ab8469ee39ddc8b2b6b2143a8c66dad510
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/adapter_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d63cb87eaccf2d81de3cdcfa11d2e99c440c0ea0
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/adapter_config.json
@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "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/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/adapter_model.safetensors b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4990b8b186514ae90c063249835a6a29e09a1ee8
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ce501cc4f45630cbcfbd87207b09cb69e3d8e89b6cc1e4f1c36d4de0ef02f3
+size 109069176
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/optimizer.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7d2de8c0683b4ef92085aebc369583bd5a714d41
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3719cffecade4ebad3224eb133f26d219594c8081a7c8652a1ab9c7eb9fc20
+size 55532666
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/rng_state.pth b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..79bb4713fe2b3401b996333e5c279df16227df43
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de9c5fc0e036cdd81b791ad579709aba7b58fe21596b8ec7a21bc2fc20bc6820
+size 14244
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/scheduler.pt b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8f96b594f266e3eac04bbb3ede8e998deec2987d
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d522cd2bba0b823893f0bc5610468bcc90c44a25295cdeeb1ed477e2c2fd955
+size 1064
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/tokenizer_config.json
@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/trainer_state.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..f8d92c3fb5cedd95fdc005242a2be638b8785461
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/trainer_state.json
@@ -0,0 +1,559 @@
+{
+  "best_metric": 1.8201380968093872,
+  "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748",
+  "epoch": 0.9993319973279893,
+  "eval_steps": 10,
+  "global_step": 748,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013360053440213761,
+      "grad_norm": 0.5097216367721558,
+      "learning_rate": 0.0002,
+      "loss": 2.6569,
+      "step": 10
+    },
+    {
+      "epoch": 0.026720106880427523,
+      "grad_norm": 0.5924790501594543,
+      "learning_rate": 0.0002,
+      "loss": 2.2557,
+      "step": 20
+    },
+    {
+      "epoch": 0.04008016032064128,
+      "grad_norm": 0.5158102512359619,
+      "learning_rate": 0.0002,
+      "loss": 2.0626,
+      "step": 30
+    },
+    {
+      "epoch": 0.053440213760855046,
+      "grad_norm": 0.5033753514289856,
+      "learning_rate": 0.0002,
+      "loss": 1.9452,
+      "step": 40
+    },
+    {
+      "epoch": 0.06680026720106881,
+      "grad_norm": 0.5390949845314026,
+      "learning_rate": 0.0002,
+      "loss": 1.9128,
+      "step": 50
+    },
+    {
+      "epoch": 0.08016032064128256,
+      "grad_norm": 0.6376217007637024,
+      "learning_rate": 0.0002,
+      "loss": 1.937,
+      "step": 60
+    },
+    {
+      "epoch": 0.09352037408149633,
+      "grad_norm": 0.4202035069465637,
+      "learning_rate": 0.0002,
+      "loss": 1.929,
+      "step": 70
+    },
+    {
+      "epoch": 0.10688042752171009,
+      "grad_norm": 0.4269474744796753,
+      "learning_rate": 0.0002,
+      "loss": 1.811,
+      "step": 80
+    },
+    {
+      "epoch": 0.12024048096192384,
+      "grad_norm": 0.4306574761867523,
+      "learning_rate": 0.0002,
+      "loss": 1.8303,
+      "step": 90
+    },
+    {
+      "epoch": 0.13360053440213762,
+      "grad_norm": 0.5297011137008667,
+      "learning_rate": 0.0002,
+      "loss": 1.8469,
+      "step": 100
+    },
+    {
+      "epoch": 0.14696058784235136,
+      "grad_norm": 1.2313778400421143,
+      "learning_rate": 0.0002,
+      "loss": 1.864,
+      "step": 110
+    },
+    {
+      "epoch": 0.16032064128256512,
+      "grad_norm": 0.5351294279098511,
+      "learning_rate": 0.0002,
+      "loss": 1.8531,
+      "step": 120
+    },
+    {
+      "epoch": 0.1736806947227789,
+      "grad_norm": 0.4848092496395111,
+      "learning_rate": 0.0002,
+      "loss": 1.9232,
+      "step": 130
+    },
+    {
+      "epoch": 0.18704074816299265,
+      "grad_norm": 0.4339500665664673,
+      "learning_rate": 0.0002,
+      "loss": 1.8633,
+      "step": 140
+    },
+    {
+      "epoch": 0.20040080160320642,
+      "grad_norm": 0.46877285838127136,
+      "learning_rate": 0.0002,
+      "loss": 1.816,
+      "step": 150
+    },
+    {
+      "epoch": 0.21376085504342018,
+      "grad_norm": 0.5600412487983704,
+      "learning_rate": 0.0002,
+      "loss": 1.8033,
+      "step": 160
+    },
+    {
+      "epoch": 0.22712090848363392,
+      "grad_norm": 0.3733620345592499,
+      "learning_rate": 0.0002,
+      "loss": 1.8162,
+      "step": 170
+    },
+    {
+      "epoch": 0.24048096192384769,
+      "grad_norm": 0.5116042494773865,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 180
+    },
+    {
+      "epoch": 0.25384101536406145,
+      "grad_norm": 0.4071602523326874,
+      "learning_rate": 0.0002,
+      "loss": 1.915,
+      "step": 190
+    },
+    {
+      "epoch": 0.26720106880427524,
+      "grad_norm": 0.44189608097076416,
+      "learning_rate": 0.0002,
+      "loss": 1.7984,
+      "step": 200
+    },
+    {
+      "epoch": 0.280561122244489,
+      "grad_norm": 0.398699015378952,
+      "learning_rate": 0.0002,
+      "loss": 1.8728,
+      "step": 210
+    },
+    {
+      "epoch": 0.2939211756847027,
+      "grad_norm": 0.3585626482963562,
+      "learning_rate": 0.0002,
+      "loss": 1.8205,
+      "step": 220
+    },
+    {
+      "epoch": 0.3072812291249165,
+      "grad_norm": 0.3811776041984558,
+      "learning_rate": 0.0002,
+      "loss": 1.8861,
+      "step": 230
+    },
+    {
+      "epoch": 0.32064128256513025,
+      "grad_norm": 0.37261509895324707,
+      "learning_rate": 0.0002,
+      "loss": 1.8365,
+      "step": 240
+    },
+    {
+      "epoch": 0.33400133600534404,
+      "grad_norm": 0.39762404561042786,
+      "learning_rate": 0.0002,
+      "loss": 1.9186,
+      "step": 250
+    },
+    {
+      "epoch": 0.3473613894455578,
+      "grad_norm": 0.3509528934955597,
+      "learning_rate": 0.0002,
+      "loss": 1.7965,
+      "step": 260
+    },
+    {
+      "epoch": 0.36072144288577157,
+      "grad_norm": 0.3169104754924774,
+      "learning_rate": 0.0002,
+      "loss": 1.7802,
+      "step": 270
+    },
+    {
+      "epoch": 0.3740814963259853,
+      "grad_norm": 0.33714795112609863,
+      "learning_rate": 0.0002,
+      "loss": 1.8038,
+      "step": 280
+    },
+    {
+      "epoch": 0.38744154976619904,
+      "grad_norm": 1.2936875820159912,
+      "learning_rate": 0.0002,
+      "loss": 1.787,
+      "step": 290
+    },
+    {
+      "epoch": 0.40080160320641284,
+      "grad_norm": 0.3459427058696747,
+      "learning_rate": 0.0002,
+      "loss": 1.7974,
+      "step": 300
+    },
+    {
+      "epoch": 0.4141616566466266,
+      "grad_norm": 0.3380655348300934,
+      "learning_rate": 0.0002,
+      "loss": 1.8879,
+      "step": 310
+    },
+    {
+      "epoch": 0.42752171008684037,
+      "grad_norm": 0.3890381455421448,
+      "learning_rate": 0.0002,
+      "loss": 1.9196,
+      "step": 320
+    },
+    {
+      "epoch": 0.4408817635270541,
+      "grad_norm": 0.432327002286911,
+      "learning_rate": 0.0002,
+      "loss": 1.8034,
+      "step": 330
+    },
+    {
+      "epoch": 0.45424181696726784,
+      "grad_norm": 0.3736560046672821,
+      "learning_rate": 0.0002,
+      "loss": 1.8443,
+      "step": 340
+    },
+    {
+      "epoch": 0.46760187040748163,
+      "grad_norm": 0.3700982630252838,
+      "learning_rate": 0.0002,
+      "loss": 1.8506,
+      "step": 350
+    },
+    {
+      "epoch": 0.48096192384769537,
+      "grad_norm": 0.4533902406692505,
+      "learning_rate": 0.0002,
+      "loss": 1.7978,
+      "step": 360
+    },
+    {
+      "epoch": 0.49432197728790916,
+      "grad_norm": 0.35999053716659546,
+      "learning_rate": 0.0002,
+      "loss": 1.7427,
+      "step": 370
+    },
+    {
+      "epoch": 0.5076820307281229,
+      "grad_norm": 0.3490903675556183,
+      "learning_rate": 0.0002,
+      "loss": 1.7995,
+      "step": 380
+    },
+    {
+      "epoch": 0.5210420841683366,
+      "grad_norm": 0.34704291820526123,
+      "learning_rate": 0.0002,
+      "loss": 1.8709,
+      "step": 390
+    },
+    {
+      "epoch": 0.5344021376085505,
+      "grad_norm": 0.343565434217453,
+      "learning_rate": 0.0002,
+      "loss": 1.7948,
+      "step": 400
+    },
+    {
+      "epoch": 0.5477621910487642,
+      "grad_norm": 0.3573552966117859,
+      "learning_rate": 0.0002,
+      "loss": 1.8564,
+      "step": 410
+    },
+    {
+      "epoch": 0.561122244488978,
+      "grad_norm": 0.32980719208717346,
+      "learning_rate": 0.0002,
+      "loss": 1.8477,
+      "step": 420
+    },
+    {
+      "epoch": 0.5744822979291917,
+      "grad_norm": 0.356952428817749,
+      "learning_rate": 0.0002,
+      "loss": 1.9233,
+      "step": 430
+    },
+    {
+      "epoch": 0.5878423513694054,
+      "grad_norm": 0.3170869052410126,
+      "learning_rate": 0.0002,
+      "loss": 1.7433,
+      "step": 440
+    },
+    {
+      "epoch": 0.6012024048096193,
+      "grad_norm": 0.35233718156814575,
+      "learning_rate": 0.0002,
+      "loss": 1.7607,
+      "step": 450
+    },
+    {
+      "epoch": 0.614562458249833,
+      "grad_norm": 0.3480125367641449,
+      "learning_rate": 0.0002,
+      "loss": 1.8111,
+      "step": 460
+    },
+    {
+      "epoch": 0.6279225116900468,
+      "grad_norm": 0.4762810468673706,
+      "learning_rate": 0.0002,
+      "loss": 1.8386,
+      "step": 470
+    },
+    {
+      "epoch": 0.6412825651302605,
+      "grad_norm": 0.3907663822174072,
+      "learning_rate": 0.0002,
+      "loss": 1.805,
+      "step": 480
+    },
+    {
+      "epoch": 0.6546426185704742,
+      "grad_norm": 0.36315613985061646,
+      "learning_rate": 0.0002,
+      "loss": 1.8113,
+      "step": 490
+    },
+    {
+      "epoch": 0.6680026720106881,
+      "grad_norm": 0.377796471118927,
+      "learning_rate": 0.0002,
+      "loss": 1.7805,
+      "step": 500
+    },
+    {
+      "epoch": 0.6813627254509018,
+      "grad_norm": 0.34284207224845886,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 510
+    },
+    {
+      "epoch": 0.6947227788911156,
+      "grad_norm": 0.35563018918037415,
+      "learning_rate": 0.0002,
+      "loss": 1.8013,
+      "step": 520
+    },
+    {
+      "epoch": 0.7080828323313293,
+      "grad_norm": 0.37575867772102356,
+      "learning_rate": 0.0002,
+      "loss": 1.8414,
+      "step": 530
+    },
+    {
+      "epoch": 0.7214428857715431,
+      "grad_norm": 0.35719701647758484,
+      "learning_rate": 0.0002,
+      "loss": 1.7993,
+      "step": 540
+    },
+    {
+      "epoch": 0.7348029392117569,
+      "grad_norm": 0.385813444852829,
+      "learning_rate": 0.0002,
+      "loss": 1.7574,
+      "step": 550
+    },
+    {
+      "epoch": 0.7481629926519706,
+      "grad_norm": 0.44509607553482056,
+      "learning_rate": 0.0002,
+      "loss": 1.7985,
+      "step": 560
+    },
+    {
+      "epoch": 0.7615230460921844,
+      "grad_norm": 0.36108464002609253,
+      "learning_rate": 0.0002,
+      "loss": 1.7459,
+      "step": 570
+    },
+    {
+      "epoch": 0.7748830995323981,
+      "grad_norm": 0.3530745804309845,
+      "learning_rate": 0.0002,
+      "loss": 1.8207,
+      "step": 580
+    },
+    {
+      "epoch": 0.7882431529726119,
+      "grad_norm": 0.34888574481010437,
+      "learning_rate": 0.0002,
+      "loss": 1.7479,
+      "step": 590
+    },
+    {
+      "epoch": 0.8016032064128257,
+      "grad_norm": 0.387346476316452,
+      "learning_rate": 0.0002,
+      "loss": 1.8656,
+      "step": 600
+    },
+    {
+      "epoch": 0.8149632598530394,
+      "grad_norm": 0.3641138970851898,
+      "learning_rate": 0.0002,
+      "loss": 1.8071,
+      "step": 610
+    },
+    {
+      "epoch": 0.8283233132932531,
+      "grad_norm": 0.33729103207588196,
+      "learning_rate": 0.0002,
+      "loss": 1.7531,
+      "step": 620
+    },
+    {
+      "epoch": 0.8416833667334669,
+      "grad_norm": 0.3652004599571228,
+      "learning_rate": 0.0002,
+      "loss": 1.8613,
+      "step": 630
+    },
+    {
+      "epoch": 0.8550434201736807,
+      "grad_norm": 0.3986643850803375,
+      "learning_rate": 0.0002,
+      "loss": 1.9184,
+      "step": 640
+    },
+    {
+      "epoch": 0.8684034736138945,
+      "grad_norm": 0.3458964228630066,
+      "learning_rate": 0.0002,
+      "loss": 1.8198,
+      "step": 650
+    },
+    {
+      "epoch": 0.8817635270541082,
+      "grad_norm": 0.3559381365776062,
+      "learning_rate": 0.0002,
+      "loss": 1.803,
+      "step": 660
+    },
+    {
+      "epoch": 0.895123580494322,
+      "grad_norm": 0.3612841069698334,
+      "learning_rate": 0.0002,
+      "loss": 1.7641,
+      "step": 670
+    },
+    {
+      "epoch": 0.9084836339345357,
+      "grad_norm": 0.34771719574928284,
+      "learning_rate": 0.0002,
+      "loss": 1.7888,
+      "step": 680
+    },
+    {
+      "epoch": 0.9218436873747495,
+      "grad_norm": 0.3371497094631195,
+      "learning_rate": 0.0002,
+      "loss": 1.8204,
+      "step": 690
+    },
+    {
+      "epoch": 0.9352037408149633,
+      "grad_norm": 0.5596055388450623,
+      "learning_rate": 0.0002,
+      "loss": 1.7848,
+      "step": 700
+    },
+    {
+      "epoch": 0.948563794255177,
+      "grad_norm": 0.311880499124527,
+      "learning_rate": 0.0002,
+      "loss": 1.7794,
+      "step": 710
+    },
+    {
+      "epoch": 0.9619238476953907,
+      "grad_norm": 0.3462068736553192,
+      "learning_rate": 0.0002,
+      "loss": 1.8464,
+      "step": 720
+    },
+    {
+      "epoch": 0.9752839011356046,
+      "grad_norm": 0.29982393980026245,
+      "learning_rate": 0.0002,
+      "loss": 1.8197,
+      "step": 730
+    },
+    {
+      "epoch": 0.9886439545758183,
+      "grad_norm": 0.34606459736824036,
+      "learning_rate": 0.0002,
+      "loss": 1.8503,
+      "step": 740
+    },
+    {
+      "epoch": 0.9993319973279893,
+      "eval_loss": 1.8201380968093872,
+      "eval_runtime": 38.6124,
+      "eval_samples_per_second": 13.338,
+      "eval_steps_per_second": 1.683,
+      "step": 748
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5984,
+  "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": 3.463890404062003e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7025f98e983b93b4fec0d5370c1456c7adecaf8e
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e92f0598f349930e52e126f358a3dca045c3c88312ec4b3f814f018a04982a9
+size 5560
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/special_tokens_map.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/tokenizer.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/tokenizer_config.json b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..061e40d9db3253624f86e8e364c15ef546527c9d
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/tokenizer_config.json
@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/training_args.bin b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7025f98e983b93b4fec0d5370c1456c7adecaf8e
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e92f0598f349930e52e126f358a3dca045c3c88312ec4b3f814f018a04982a9
+size 5560
diff --git a/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/training_log.jsonl b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/training_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..b41df7b8c98cf1ed2ef666b0cb5947b2f922af93
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/training_log.jsonl
@@ -0,0 +1,10 @@
+{"epoch": 0.9993319973279893, "step": 748, "epoch_duration": 1492.3190751075745, "total_accumulated_duration": 1492.3190751075745, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7672.4541015625}, "peak_memory_usage": {"GPU_0": 9688.99365234375}, "avg_memory_reserved": {"GPU_0": 10406.0}, "peak_memory_reserved": {"GPU_0": 10406.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.6557, "grad_norm": 0.5145056247711182, "learning_rate": 0.0002, "epoch": 0.013360053440213761, "step": 10}, {"loss": 2.2534, "grad_norm": 0.5996711850166321, "learning_rate": 0.0002, "epoch": 0.026720106880427523, "step": 20}, {"loss": 2.0618, "grad_norm": 0.6517987251281738, "learning_rate": 0.0002, "epoch": 0.04008016032064128, "step": 30}, {"loss": 1.9439, "grad_norm": 0.5026489496231079, "learning_rate": 0.0002, "epoch": 0.053440213760855046, "step": 40}, {"loss": 1.9116, "grad_norm": 0.5164623856544495, "learning_rate": 0.0002, "epoch": 0.06680026720106881, "step": 50}, {"loss": 1.9361, "grad_norm": 0.6341000199317932, "learning_rate": 0.0002, "epoch": 0.08016032064128256, "step": 60}, {"loss": 1.9283, "grad_norm": 0.41312524676322937, "learning_rate": 0.0002, "epoch": 0.09352037408149633, "step": 70}, {"loss": 1.8119, "grad_norm": 0.4311992824077606, "learning_rate": 0.0002, "epoch": 0.10688042752171009, "step": 80}, {"loss": 1.831, "grad_norm": 0.4293884038925171, "learning_rate": 0.0002, "epoch": 0.12024048096192384, "step": 90}, {"loss": 1.8465, "grad_norm": 0.544420063495636, "learning_rate": 0.0002, "epoch": 0.13360053440213762, "step": 100}, {"loss": 1.8629, "grad_norm": 1.107458233833313, "learning_rate": 0.0002, "epoch": 0.14696058784235136, "step": 110}, {"loss": 1.8529, "grad_norm": 0.5141991972923279, "learning_rate": 0.0002, "epoch": 0.16032064128256512, "step": 120}, {"loss": 1.9222, "grad_norm": 0.46840447187423706, "learning_rate": 0.0002, "epoch": 0.1736806947227789, "step": 130}, {"loss": 1.8624, "grad_norm": 0.4327720105648041, "learning_rate": 0.0002, "epoch": 0.18704074816299265, "step": 140}, {"loss": 1.8151, "grad_norm": 0.4583268463611603, "learning_rate": 0.0002, "epoch": 0.20040080160320642, "step": 150}, {"loss": 1.8032, "grad_norm": 0.5514822006225586, "learning_rate": 0.0002, "epoch": 0.21376085504342018, "step": 160}, {"loss": 1.8161, "grad_norm": 0.36940041184425354, "learning_rate": 0.0002, "epoch": 0.22712090848363392, "step": 170}, {"loss": 1.8553, "grad_norm": 0.4596315622329712, "learning_rate": 0.0002, "epoch": 0.24048096192384769, "step": 180}, {"loss": 1.9108, "grad_norm": 0.4041196405887604, "learning_rate": 0.0002, "epoch": 0.25384101536406145, "step": 190}, {"loss": 1.7961, "grad_norm": 0.6554355621337891, "learning_rate": 0.0002, "epoch": 0.26720106880427524, "step": 200}, {"loss": 1.8736, "grad_norm": 0.42680826783180237, "learning_rate": 0.0002, "epoch": 0.280561122244489, "step": 210}, {"loss": 1.8198, "grad_norm": 0.36290431022644043, "learning_rate": 0.0002, "epoch": 0.2939211756847027, "step": 220}, {"loss": 1.8859, "grad_norm": 0.38558459281921387, "learning_rate": 0.0002, "epoch": 0.3072812291249165, "step": 230}, {"loss": 1.8367, "grad_norm": 0.3701355755329132, "learning_rate": 0.0002, "epoch": 0.32064128256513025, "step": 240}, {"loss": 1.9172, "grad_norm": 0.39881789684295654, "learning_rate": 0.0002, "epoch": 0.33400133600534404, "step": 250}, {"loss": 1.7959, "grad_norm": 0.33923494815826416, "learning_rate": 0.0002, "epoch": 0.3473613894455578, "step": 260}, {"loss": 1.7813, "grad_norm": 0.31573089957237244, "learning_rate": 0.0002, "epoch": 0.36072144288577157, "step": 270}, {"loss": 1.8025, "grad_norm": 0.3342670202255249, "learning_rate": 0.0002, "epoch": 0.3740814963259853, "step": 280}, {"loss": 1.786, "grad_norm": 0.4824513792991638, "learning_rate": 0.0002, "epoch": 0.38744154976619904, "step": 290}, {"loss": 1.797, "grad_norm": 0.5301131010055542, "learning_rate": 0.0002, "epoch": 0.40080160320641284, "step": 300}, {"loss": 1.8865, "grad_norm": 0.34163719415664673, "learning_rate": 0.0002, "epoch": 0.4141616566466266, "step": 310}, {"loss": 1.9192, "grad_norm": 0.4014457166194916, "learning_rate": 0.0002, "epoch": 0.42752171008684037, "step": 320}, {"loss": 1.8017, "grad_norm": 0.4126872420310974, "learning_rate": 0.0002, "epoch": 0.4408817635270541, "step": 330}, {"loss": 1.8411, "grad_norm": 0.40941300988197327, "learning_rate": 0.0002, "epoch": 0.45424181696726784, "step": 340}, {"loss": 1.8493, "grad_norm": 0.3820064663887024, "learning_rate": 0.0002, "epoch": 0.46760187040748163, "step": 350}, {"loss": 1.7975, "grad_norm": 0.4614120125770569, "learning_rate": 0.0002, "epoch": 0.48096192384769537, "step": 360}, {"loss": 1.7427, "grad_norm": 0.35886332392692566, "learning_rate": 0.0002, "epoch": 0.49432197728790916, "step": 370}, {"loss": 1.7974, "grad_norm": 0.32689186930656433, "learning_rate": 0.0002, "epoch": 0.5076820307281229, "step": 380}, {"loss": 1.8698, "grad_norm": 0.36681291460990906, "learning_rate": 0.0002, "epoch": 0.5210420841683366, "step": 390}, {"loss": 1.7943, "grad_norm": 0.3464324176311493, "learning_rate": 0.0002, "epoch": 0.5344021376085505, "step": 400}, {"loss": 1.8571, "grad_norm": 0.37786048650741577, "learning_rate": 0.0002, "epoch": 0.5477621910487642, "step": 410}, {"loss": 1.8476, "grad_norm": 0.3381720781326294, "learning_rate": 0.0002, "epoch": 0.561122244488978, "step": 420}, {"loss": 1.9237, "grad_norm": 0.3579493463039398, "learning_rate": 0.0002, "epoch": 0.5744822979291917, "step": 430}, {"loss": 1.7435, "grad_norm": 0.31530654430389404, "learning_rate": 0.0002, "epoch": 0.5878423513694054, "step": 440}, {"loss": 1.7607, "grad_norm": 0.355329304933548, "learning_rate": 0.0002, "epoch": 0.6012024048096193, "step": 450}, {"loss": 1.8077, "grad_norm": 0.35699936747550964, "learning_rate": 0.0002, "epoch": 0.614562458249833, "step": 460}, {"loss": 1.8346, "grad_norm": 0.3523382842540741, "learning_rate": 0.0002, "epoch": 0.6279225116900468, "step": 470}, {"loss": 1.8057, "grad_norm": 0.3932587504386902, "learning_rate": 0.0002, "epoch": 0.6412825651302605, "step": 480}, {"loss": 1.81, "grad_norm": 0.3593502640724182, "learning_rate": 0.0002, "epoch": 0.6546426185704742, "step": 490}, {"loss": 1.779, "grad_norm": 0.3738945722579956, "learning_rate": 0.0002, "epoch": 0.6680026720106881, "step": 500}, {"loss": 1.7453, "grad_norm": 0.34351104497909546, "learning_rate": 0.0002, "epoch": 0.6813627254509018, "step": 510}, {"loss": 1.8013, "grad_norm": 0.3606947660446167, "learning_rate": 0.0002, "epoch": 0.6947227788911156, "step": 520}, {"loss": 1.8421, "grad_norm": 0.3633013367652893, "learning_rate": 0.0002, "epoch": 0.7080828323313293, "step": 530}, {"loss": 1.7987, "grad_norm": 0.35114890336990356, "learning_rate": 0.0002, "epoch": 0.7214428857715431, "step": 540}, {"loss": 1.7566, "grad_norm": 0.39301058650016785, "learning_rate": 0.0002, "epoch": 0.7348029392117569, "step": 550}, {"loss": 1.8001, "grad_norm": 0.4035342037677765, "learning_rate": 0.0002, "epoch": 0.7481629926519706, "step": 560}, {"loss": 1.7469, "grad_norm": 0.39972934126853943, "learning_rate": 0.0002, "epoch": 0.7615230460921844, "step": 570}, {"loss": 1.8235, "grad_norm": 0.3460000157356262, "learning_rate": 0.0002, "epoch": 0.7748830995323981, "step": 580}, {"loss": 1.7485, "grad_norm": 0.35099920630455017, "learning_rate": 0.0002, "epoch": 0.7882431529726119, "step": 590}, {"loss": 1.8635, "grad_norm": 0.3802923560142517, "learning_rate": 0.0002, "epoch": 0.8016032064128257, "step": 600}, {"loss": 1.806, "grad_norm": 0.36409080028533936, "learning_rate": 0.0002, "epoch": 0.8149632598530394, "step": 610}, {"loss": 1.7529, "grad_norm": 0.3338017165660858, "learning_rate": 0.0002, "epoch": 0.8283233132932531, "step": 620}, {"loss": 1.8597, "grad_norm": 0.3630930781364441, "learning_rate": 0.0002, "epoch": 0.8416833667334669, "step": 630}, {"loss": 1.9177, "grad_norm": 0.36975711584091187, "learning_rate": 0.0002, "epoch": 0.8550434201736807, "step": 640}, {"loss": 1.818, "grad_norm": 0.34457138180732727, "learning_rate": 0.0002, "epoch": 0.8684034736138945, "step": 650}, {"loss": 1.8031, "grad_norm": 0.37342599034309387, "learning_rate": 0.0002, "epoch": 0.8817635270541082, "step": 660}, {"loss": 1.7642, "grad_norm": 0.3463771343231201, "learning_rate": 0.0002, "epoch": 0.895123580494322, "step": 670}, {"loss": 1.7878, "grad_norm": 0.35239866375923157, "learning_rate": 0.0002, "epoch": 0.9084836339345357, "step": 680}, {"loss": 1.8201, "grad_norm": 0.3397367596626282, "learning_rate": 0.0002, "epoch": 0.9218436873747495, "step": 690}, {"loss": 1.7846, "grad_norm": 0.4075145721435547, "learning_rate": 0.0002, "epoch": 0.9352037408149633, "step": 700}, {"loss": 1.7798, "grad_norm": 0.3126145005226135, "learning_rate": 0.0002, "epoch": 0.948563794255177, "step": 710}, {"loss": 1.8469, "grad_norm": 0.3454380929470062, "learning_rate": 0.0002, "epoch": 0.9619238476953907, "step": 720}, {"loss": 1.8187, "grad_norm": 0.3040635883808136, "learning_rate": 0.0002, "epoch": 0.9752839011356046, "step": 730}, {"loss": 1.8506, "grad_norm": 0.343362420797348, "learning_rate": 0.0002, "epoch": 0.9886439545758183, "step": 740}]}
+{"epoch": 2.0, "step": 1497, "epoch_duration": 1945.510260105133, "total_accumulated_duration": 3437.8293352127075, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7568.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.6557, "grad_norm": 0.5145056247711182, "learning_rate": 0.0002, "epoch": 0.013360053440213761, "step": 10}, {"loss": 2.2534, "grad_norm": 0.5996711850166321, "learning_rate": 0.0002, "epoch": 0.026720106880427523, "step": 20}, {"loss": 2.0618, "grad_norm": 0.6517987251281738, "learning_rate": 0.0002, "epoch": 0.04008016032064128, "step": 30}, {"loss": 1.9439, "grad_norm": 0.5026489496231079, "learning_rate": 0.0002, "epoch": 0.053440213760855046, "step": 40}, {"loss": 1.9116, "grad_norm": 0.5164623856544495, "learning_rate": 0.0002, "epoch": 0.06680026720106881, "step": 50}, {"loss": 1.9361, "grad_norm": 0.6341000199317932, "learning_rate": 0.0002, "epoch": 0.08016032064128256, "step": 60}, {"loss": 1.9283, "grad_norm": 0.41312524676322937, "learning_rate": 0.0002, "epoch": 0.09352037408149633, "step": 70}, {"loss": 1.8119, "grad_norm": 0.4311992824077606, "learning_rate": 0.0002, "epoch": 0.10688042752171009, "step": 80}, {"loss": 1.831, "grad_norm": 0.4293884038925171, "learning_rate": 0.0002, "epoch": 0.12024048096192384, "step": 90}, {"loss": 1.8465, "grad_norm": 0.544420063495636, "learning_rate": 0.0002, "epoch": 0.13360053440213762, "step": 100}, {"loss": 1.8629, "grad_norm": 1.107458233833313, "learning_rate": 0.0002, "epoch": 0.14696058784235136, "step": 110}, {"loss": 1.8529, "grad_norm": 0.5141991972923279, "learning_rate": 0.0002, "epoch": 0.16032064128256512, "step": 120}, {"loss": 1.9222, "grad_norm": 0.46840447187423706, "learning_rate": 0.0002, "epoch": 0.1736806947227789, "step": 130}, {"loss": 1.8624, "grad_norm": 0.4327720105648041, "learning_rate": 0.0002, "epoch": 0.18704074816299265, "step": 140}, {"loss": 1.8151, "grad_norm": 0.4583268463611603, "learning_rate": 0.0002, "epoch": 0.20040080160320642, "step": 150}, {"loss": 1.8032, "grad_norm": 0.5514822006225586, "learning_rate": 0.0002, "epoch": 0.21376085504342018, "step": 160}, {"loss": 1.8161, "grad_norm": 0.36940041184425354, "learning_rate": 0.0002, "epoch": 0.22712090848363392, "step": 170}, {"loss": 1.8553, "grad_norm": 0.4596315622329712, "learning_rate": 0.0002, "epoch": 0.24048096192384769, "step": 180}, {"loss": 1.9108, "grad_norm": 0.4041196405887604, "learning_rate": 0.0002, "epoch": 0.25384101536406145, "step": 190}, {"loss": 1.7961, "grad_norm": 0.6554355621337891, "learning_rate": 0.0002, "epoch": 0.26720106880427524, "step": 200}, {"loss": 1.8736, "grad_norm": 0.42680826783180237, "learning_rate": 0.0002, "epoch": 0.280561122244489, "step": 210}, {"loss": 1.8198, "grad_norm": 0.36290431022644043, "learning_rate": 0.0002, "epoch": 0.2939211756847027, "step": 220}, {"loss": 1.8859, "grad_norm": 0.38558459281921387, "learning_rate": 0.0002, "epoch": 0.3072812291249165, "step": 230}, {"loss": 1.8367, "grad_norm": 0.3701355755329132, "learning_rate": 0.0002, "epoch": 0.32064128256513025, "step": 240}, {"loss": 1.9172, "grad_norm": 0.39881789684295654, "learning_rate": 0.0002, "epoch": 0.33400133600534404, "step": 250}, {"loss": 1.7959, "grad_norm": 0.33923494815826416, "learning_rate": 0.0002, "epoch": 0.3473613894455578, "step": 260}, {"loss": 1.7813, "grad_norm": 0.31573089957237244, "learning_rate": 0.0002, "epoch": 0.36072144288577157, "step": 270}, {"loss": 1.8025, "grad_norm": 0.3342670202255249, "learning_rate": 0.0002, "epoch": 0.3740814963259853, "step": 280}, {"loss": 1.786, "grad_norm": 0.4824513792991638, "learning_rate": 0.0002, "epoch": 0.38744154976619904, "step": 290}, {"loss": 1.797, "grad_norm": 0.5301131010055542, "learning_rate": 0.0002, "epoch": 0.40080160320641284, "step": 300}, {"loss": 1.8865, "grad_norm": 0.34163719415664673, "learning_rate": 0.0002, "epoch": 0.4141616566466266, "step": 310}, {"loss": 1.9192, "grad_norm": 0.4014457166194916, "learning_rate": 0.0002, "epoch": 0.42752171008684037, "step": 320}, {"loss": 1.8017, "grad_norm": 0.4126872420310974, "learning_rate": 0.0002, "epoch": 0.4408817635270541, "step": 330}, {"loss": 1.8411, "grad_norm": 0.40941300988197327, "learning_rate": 0.0002, "epoch": 0.45424181696726784, "step": 340}, {"loss": 1.8493, "grad_norm": 0.3820064663887024, "learning_rate": 0.0002, "epoch": 0.46760187040748163, "step": 350}, {"loss": 1.7975, "grad_norm": 0.4614120125770569, "learning_rate": 0.0002, "epoch": 0.48096192384769537, "step": 360}, {"loss": 1.7427, "grad_norm": 0.35886332392692566, "learning_rate": 0.0002, "epoch": 0.49432197728790916, "step": 370}, {"loss": 1.7974, "grad_norm": 0.32689186930656433, "learning_rate": 0.0002, "epoch": 0.5076820307281229, "step": 380}, {"loss": 1.8698, "grad_norm": 0.36681291460990906, "learning_rate": 0.0002, "epoch": 0.5210420841683366, "step": 390}, {"loss": 1.7943, "grad_norm": 0.3464324176311493, "learning_rate": 0.0002, "epoch": 0.5344021376085505, "step": 400}, {"loss": 1.8571, "grad_norm": 0.37786048650741577, "learning_rate": 0.0002, "epoch": 0.5477621910487642, "step": 410}, {"loss": 1.8476, "grad_norm": 0.3381720781326294, "learning_rate": 0.0002, "epoch": 0.561122244488978, "step": 420}, {"loss": 1.9237, "grad_norm": 0.3579493463039398, "learning_rate": 0.0002, "epoch": 0.5744822979291917, "step": 430}, {"loss": 1.7435, "grad_norm": 0.31530654430389404, "learning_rate": 0.0002, "epoch": 0.5878423513694054, "step": 440}, {"loss": 1.7607, "grad_norm": 0.355329304933548, "learning_rate": 0.0002, "epoch": 0.6012024048096193, "step": 450}, {"loss": 1.8077, "grad_norm": 0.35699936747550964, "learning_rate": 0.0002, "epoch": 0.614562458249833, "step": 460}, {"loss": 1.8346, "grad_norm": 0.3523382842540741, "learning_rate": 0.0002, "epoch": 0.6279225116900468, "step": 470}, {"loss": 1.8057, "grad_norm": 0.3932587504386902, "learning_rate": 0.0002, "epoch": 0.6412825651302605, "step": 480}, {"loss": 1.81, "grad_norm": 0.3593502640724182, "learning_rate": 0.0002, "epoch": 0.6546426185704742, "step": 490}, {"loss": 1.779, "grad_norm": 0.3738945722579956, "learning_rate": 0.0002, "epoch": 0.6680026720106881, "step": 500}, {"loss": 1.7453, "grad_norm": 0.34351104497909546, "learning_rate": 0.0002, "epoch": 0.6813627254509018, "step": 510}, {"loss": 1.8013, "grad_norm": 0.3606947660446167, "learning_rate": 0.0002, "epoch": 0.6947227788911156, "step": 520}, {"loss": 1.8421, "grad_norm": 0.3633013367652893, "learning_rate": 0.0002, "epoch": 0.7080828323313293, "step": 530}, {"loss": 1.7987, "grad_norm": 0.35114890336990356, "learning_rate": 0.0002, "epoch": 0.7214428857715431, "step": 540}, {"loss": 1.7566, "grad_norm": 0.39301058650016785, "learning_rate": 0.0002, "epoch": 0.7348029392117569, "step": 550}, {"loss": 1.8001, "grad_norm": 0.4035342037677765, "learning_rate": 0.0002, "epoch": 0.7481629926519706, "step": 560}, {"loss": 1.7469, "grad_norm": 0.39972934126853943, "learning_rate": 0.0002, "epoch": 0.7615230460921844, "step": 570}, {"loss": 1.8235, "grad_norm": 0.3460000157356262, "learning_rate": 0.0002, "epoch": 0.7748830995323981, "step": 580}, {"loss": 1.7485, "grad_norm": 0.35099920630455017, "learning_rate": 0.0002, "epoch": 0.7882431529726119, "step": 590}, {"loss": 1.8635, "grad_norm": 0.3802923560142517, "learning_rate": 0.0002, "epoch": 0.8016032064128257, "step": 600}, {"loss": 1.806, "grad_norm": 0.36409080028533936, "learning_rate": 0.0002, "epoch": 0.8149632598530394, "step": 610}, {"loss": 1.7529, "grad_norm": 0.3338017165660858, "learning_rate": 0.0002, "epoch": 0.8283233132932531, "step": 620}, {"loss": 1.8597, "grad_norm": 0.3630930781364441, "learning_rate": 0.0002, "epoch": 0.8416833667334669, "step": 630}, {"loss": 1.9177, "grad_norm": 0.36975711584091187, "learning_rate": 0.0002, "epoch": 0.8550434201736807, "step": 640}, {"loss": 1.818, "grad_norm": 0.34457138180732727, "learning_rate": 0.0002, "epoch": 0.8684034736138945, "step": 650}, {"loss": 1.8031, "grad_norm": 0.37342599034309387, "learning_rate": 0.0002, "epoch": 0.8817635270541082, "step": 660}, {"loss": 1.7642, "grad_norm": 0.3463771343231201, "learning_rate": 0.0002, "epoch": 0.895123580494322, "step": 670}, {"loss": 1.7878, "grad_norm": 0.35239866375923157, "learning_rate": 0.0002, "epoch": 0.9084836339345357, "step": 680}, {"loss": 1.8201, "grad_norm": 0.3397367596626282, "learning_rate": 0.0002, "epoch": 0.9218436873747495, "step": 690}, {"loss": 1.7846, "grad_norm": 0.4075145721435547, "learning_rate": 0.0002, "epoch": 0.9352037408149633, "step": 700}, {"loss": 1.7798, "grad_norm": 0.3126145005226135, "learning_rate": 0.0002, "epoch": 0.948563794255177, "step": 710}, {"loss": 1.8469, "grad_norm": 0.3454380929470062, "learning_rate": 0.0002, "epoch": 0.9619238476953907, "step": 720}, {"loss": 1.8187, "grad_norm": 0.3040635883808136, "learning_rate": 0.0002, "epoch": 0.9752839011356046, "step": 730}, {"loss": 1.8506, "grad_norm": 0.343362420797348, "learning_rate": 0.0002, "epoch": 0.9886439545758183, "step": 740}, {"eval_loss": 1.818781852722168, "eval_runtime": 59.4981, "eval_samples_per_second": 8.656, "eval_steps_per_second": 1.092, "epoch": 0.9993319973279893, "step": 748}, {"loss": 1.7778, "grad_norm": 0.3213261663913727, "learning_rate": 0.0002, "epoch": 1.002004008016032, "step": 750}, {"loss": 1.7283, "grad_norm": 0.3322339653968811, "learning_rate": 0.0002, "epoch": 1.0153640614562458, "step": 760}, {"loss": 1.6998, "grad_norm": 0.3345193564891815, "learning_rate": 0.0002, "epoch": 1.0287241148964597, "step": 770}, {"loss": 1.8098, "grad_norm": 0.40045303106307983, "learning_rate": 0.0002, "epoch": 1.0420841683366733, "step": 780}, {"loss": 1.7087, "grad_norm": 0.33195099234580994, "learning_rate": 0.0002, "epoch": 1.0554442217768871, "step": 790}, {"loss": 1.7752, "grad_norm": 0.403153657913208, "learning_rate": 0.0002, "epoch": 1.0688042752171008, "step": 800}, {"loss": 1.7418, "grad_norm": 0.3418046832084656, "learning_rate": 0.0002, "epoch": 1.0821643286573146, "step": 810}, {"loss": 1.7246, "grad_norm": 0.3740319013595581, "learning_rate": 0.0002, "epoch": 1.0955243820975284, "step": 820}, {"loss": 1.7219, "grad_norm": 0.33727121353149414, "learning_rate": 0.0002, "epoch": 1.108884435537742, "step": 830}, {"loss": 1.7535, "grad_norm": 0.37017568945884705, "learning_rate": 0.0002, "epoch": 1.122244488977956, "step": 840}, {"loss": 1.7158, "grad_norm": 0.37981611490249634, "learning_rate": 0.0002, "epoch": 1.1356045424181698, "step": 850}, {"loss": 1.7144, "grad_norm": 0.38836708664894104, "learning_rate": 0.0002, "epoch": 1.1489645958583834, "step": 860}, {"loss": 1.7685, "grad_norm": 0.35578230023384094, "learning_rate": 0.0002, "epoch": 1.1623246492985972, "step": 870}, {"loss": 1.7763, "grad_norm": 0.3892936408519745, "learning_rate": 0.0002, "epoch": 1.1756847027388109, "step": 880}, {"loss": 1.7497, "grad_norm": 0.3329775631427765, "learning_rate": 0.0002, "epoch": 1.1890447561790247, "step": 890}, {"loss": 1.7117, "grad_norm": 0.36562827229499817, "learning_rate": 0.0002, "epoch": 1.2024048096192386, "step": 900}, {"loss": 1.7547, "grad_norm": 0.3779258728027344, "learning_rate": 0.0002, "epoch": 1.2157648630594522, "step": 910}, {"loss": 1.7502, "grad_norm": 0.3782391846179962, "learning_rate": 0.0002, "epoch": 1.229124916499666, "step": 920}, {"loss": 1.7587, "grad_norm": 0.3202662467956543, "learning_rate": 0.0002, "epoch": 1.2424849699398797, "step": 930}, {"loss": 1.677, "grad_norm": 0.38925567269325256, "learning_rate": 0.0002, "epoch": 1.2558450233800935, "step": 940}, {"loss": 1.7717, "grad_norm": 0.3602938950061798, "learning_rate": 0.0002, "epoch": 1.2692050768203074, "step": 950}, {"loss": 1.7146, "grad_norm": 0.35788992047309875, "learning_rate": 0.0002, "epoch": 1.282565130260521, "step": 960}, {"loss": 1.7896, "grad_norm": 0.3859518766403198, "learning_rate": 0.0002, "epoch": 1.2959251837007348, "step": 970}, {"loss": 1.7358, "grad_norm": 0.3629772365093231, "learning_rate": 0.0002, "epoch": 1.3092852371409487, "step": 980}, {"loss": 1.7604, "grad_norm": 0.4093330502510071, "learning_rate": 0.0002, "epoch": 1.3226452905811623, "step": 990}, {"loss": 1.6922, "grad_norm": 0.398992121219635, "learning_rate": 0.0002, "epoch": 1.3360053440213762, "step": 1000}, {"loss": 1.744, "grad_norm": 0.3655536472797394, "learning_rate": 0.0002, "epoch": 1.3493653974615898, "step": 1010}, {"loss": 1.7131, "grad_norm": 0.42729514837265015, "learning_rate": 0.0002, "epoch": 1.3627254509018036, "step": 1020}, {"loss": 1.8029, "grad_norm": 0.36032676696777344, "learning_rate": 0.0002, "epoch": 1.3760855043420173, "step": 1030}, {"loss": 1.7247, "grad_norm": 0.3375038802623749, "learning_rate": 0.0002, "epoch": 1.389445557782231, "step": 1040}, {"loss": 1.8208, "grad_norm": 0.3981837332248688, "learning_rate": 0.0002, "epoch": 1.402805611222445, "step": 1050}, {"loss": 1.7419, "grad_norm": 0.38041386008262634, "learning_rate": 0.0002, "epoch": 1.4161656646626586, "step": 1060}, {"loss": 1.7461, "grad_norm": 0.3807733952999115, "learning_rate": 0.0002, "epoch": 1.4295257181028724, "step": 1070}, {"loss": 1.6568, "grad_norm": 0.4061289131641388, "learning_rate": 0.0002, "epoch": 1.4428857715430863, "step": 1080}, {"loss": 1.7307, "grad_norm": 0.3604201078414917, "learning_rate": 0.0002, "epoch": 1.4562458249833, "step": 1090}, {"loss": 1.7333, "grad_norm": 0.36671286821365356, "learning_rate": 0.0002, "epoch": 1.4696058784235138, "step": 1100}, {"loss": 1.7449, "grad_norm": 0.4039835035800934, "learning_rate": 0.0002, "epoch": 1.4829659318637274, "step": 1110}, {"loss": 1.7124, "grad_norm": 0.3332546651363373, "learning_rate": 0.0002, "epoch": 1.4963259853039412, "step": 1120}, {"loss": 1.6899, "grad_norm": 0.37804311513900757, "learning_rate": 0.0002, "epoch": 1.5096860387441549, "step": 1130}, {"loss": 1.7225, "grad_norm": 0.33254241943359375, "learning_rate": 0.0002, "epoch": 1.5230460921843687, "step": 1140}, {"loss": 1.7158, "grad_norm": 0.3753426969051361, "learning_rate": 0.0002, "epoch": 1.5364061456245826, "step": 1150}, {"loss": 1.6973, "grad_norm": 0.37859225273132324, "learning_rate": 0.0002, "epoch": 1.5497661990647962, "step": 1160}, {"loss": 1.7431, "grad_norm": 0.34741416573524475, "learning_rate": 0.0002, "epoch": 1.56312625250501, "step": 1170}, {"loss": 1.7526, "grad_norm": 0.4349542558193207, "learning_rate": 0.0002, "epoch": 1.5764863059452239, "step": 1180}, {"loss": 1.6441, "grad_norm": 0.33280444145202637, "learning_rate": 0.0002, "epoch": 1.5898463593854375, "step": 1190}, {"loss": 1.7583, "grad_norm": 0.3488023579120636, "learning_rate": 0.0002, "epoch": 1.6032064128256514, "step": 1200}, {"loss": 1.7822, "grad_norm": 0.3879616856575012, "learning_rate": 0.0002, "epoch": 1.6165664662658652, "step": 1210}, {"loss": 1.7458, "grad_norm": 0.3678235411643982, "learning_rate": 0.0002, "epoch": 1.6299265197060788, "step": 1220}, {"loss": 1.7598, "grad_norm": 0.35086360573768616, "learning_rate": 0.0002, "epoch": 1.6432865731462925, "step": 1230}, {"loss": 1.7182, "grad_norm": 0.418790727853775, "learning_rate": 0.0002, "epoch": 1.6566466265865063, "step": 1240}, {"loss": 1.7579, "grad_norm": 0.33470529317855835, "learning_rate": 0.0002, "epoch": 1.6700066800267201, "step": 1250}, {"loss": 1.6941, "grad_norm": 0.36641785502433777, "learning_rate": 0.0002, "epoch": 1.6833667334669338, "step": 1260}, {"loss": 1.7267, "grad_norm": 0.35484573245048523, "learning_rate": 0.0002, "epoch": 1.6967267869071476, "step": 1270}, {"loss": 1.7464, "grad_norm": 0.3373892605304718, "learning_rate": 0.0002, "epoch": 1.7100868403473615, "step": 1280}, {"loss": 1.7104, "grad_norm": 0.35930702090263367, "learning_rate": 0.0002, "epoch": 1.723446893787575, "step": 1290}, {"loss": 1.7409, "grad_norm": 0.37268316745758057, "learning_rate": 0.0002, "epoch": 1.736806947227789, "step": 1300}, {"loss": 1.7859, "grad_norm": 0.36591675877571106, "learning_rate": 0.0002, "epoch": 1.7501670006680028, "step": 1310}, {"loss": 1.735, "grad_norm": 0.38185861706733704, "learning_rate": 0.0002, "epoch": 1.7635270541082164, "step": 1320}, {"loss": 1.7543, "grad_norm": 0.3542157709598541, "learning_rate": 0.0002, "epoch": 1.77688710754843, "step": 1330}, {"loss": 1.7247, "grad_norm": 0.3794424533843994, "learning_rate": 0.0002, "epoch": 1.7902471609886441, "step": 1340}, {"loss": 1.7868, "grad_norm": 0.43353381752967834, "learning_rate": 0.0002, "epoch": 1.8036072144288577, "step": 1350}, {"loss": 1.7332, "grad_norm": 0.42096200585365295, "learning_rate": 0.0002, "epoch": 1.8169672678690714, "step": 1360}, {"loss": 1.7775, "grad_norm": 0.367298424243927, "learning_rate": 0.0002, "epoch": 1.8303273213092852, "step": 1370}, {"loss": 1.7419, "grad_norm": 0.404933899641037, "learning_rate": 0.0002, "epoch": 1.843687374749499, "step": 1380}, {"loss": 1.7422, "grad_norm": 0.36570486426353455, "learning_rate": 0.0002, "epoch": 1.8570474281897127, "step": 1390}, {"loss": 1.7942, "grad_norm": 0.37176936864852905, "learning_rate": 0.0002, "epoch": 1.8704074816299265, "step": 1400}, {"loss": 1.7882, "grad_norm": 0.36557459831237793, "learning_rate": 0.0002, "epoch": 1.8837675350701404, "step": 1410}, {"loss": 1.7531, "grad_norm": 0.3741154968738556, "learning_rate": 0.0002, "epoch": 1.897127588510354, "step": 1420}, {"loss": 1.7695, "grad_norm": 0.3762620985507965, "learning_rate": 0.0002, "epoch": 1.9104876419505676, "step": 1430}, {"loss": 1.7243, "grad_norm": 0.3563912808895111, "learning_rate": 0.0002, "epoch": 1.9238476953907817, "step": 1440}, {"loss": 1.7986, "grad_norm": 0.37095218896865845, "learning_rate": 0.0002, "epoch": 1.9372077488309953, "step": 1450}, {"loss": 1.6697, "grad_norm": 0.3762151002883911, "learning_rate": 0.0002, "epoch": 1.950567802271209, "step": 1460}, {"loss": 1.6828, "grad_norm": 0.37596359848976135, "learning_rate": 0.0002, "epoch": 1.9639278557114228, "step": 1470}, {"loss": 1.7444, "grad_norm": 0.36733531951904297, "learning_rate": 0.0002, "epoch": 1.9772879091516367, "step": 1480}, {"loss": 1.7042, "grad_norm": 0.38418638706207275, "learning_rate": 0.0002, "epoch": 1.9906479625918503, "step": 1490}]}
+{"epoch": 0.9993319973279893, "step": 748, "epoch_duration": 823.8140847682953, "total_accumulated_duration": 823.8140847682953, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7672.4541015625}, "peak_memory_usage": {"GPU_0": 9688.99365234375}, "avg_memory_reserved": {"GPU_0": 10406.0}, "peak_memory_reserved": {"GPU_0": 10406.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.6569, "grad_norm": 0.5097216367721558, "learning_rate": 0.0002, "epoch": 0.013360053440213761, "step": 10}, {"loss": 2.2557, "grad_norm": 0.5924790501594543, "learning_rate": 0.0002, "epoch": 0.026720106880427523, "step": 20}, {"loss": 2.0626, "grad_norm": 0.5158102512359619, "learning_rate": 0.0002, "epoch": 0.04008016032064128, "step": 30}, {"loss": 1.9452, "grad_norm": 0.5033753514289856, "learning_rate": 0.0002, "epoch": 0.053440213760855046, "step": 40}, {"loss": 1.9128, "grad_norm": 0.5390949845314026, "learning_rate": 0.0002, "epoch": 0.06680026720106881, "step": 50}, {"loss": 1.937, "grad_norm": 0.6376217007637024, "learning_rate": 0.0002, "epoch": 0.08016032064128256, "step": 60}, {"loss": 1.929, "grad_norm": 0.4202035069465637, "learning_rate": 0.0002, "epoch": 0.09352037408149633, "step": 70}, {"loss": 1.811, "grad_norm": 0.4269474744796753, "learning_rate": 0.0002, "epoch": 0.10688042752171009, "step": 80}, {"loss": 1.8303, "grad_norm": 0.4306574761867523, "learning_rate": 0.0002, "epoch": 0.12024048096192384, "step": 90}, {"loss": 1.8469, "grad_norm": 0.5297011137008667, "learning_rate": 0.0002, "epoch": 0.13360053440213762, "step": 100}, {"loss": 1.864, "grad_norm": 1.2313778400421143, "learning_rate": 0.0002, "epoch": 0.14696058784235136, "step": 110}, {"loss": 1.8531, "grad_norm": 0.5351294279098511, "learning_rate": 0.0002, "epoch": 0.16032064128256512, "step": 120}, {"loss": 1.9232, "grad_norm": 0.4848092496395111, "learning_rate": 0.0002, "epoch": 0.1736806947227789, "step": 130}, {"loss": 1.8633, "grad_norm": 0.4339500665664673, "learning_rate": 0.0002, "epoch": 0.18704074816299265, "step": 140}, {"loss": 1.816, "grad_norm": 0.46877285838127136, "learning_rate": 0.0002, "epoch": 0.20040080160320642, "step": 150}, {"loss": 1.8033, "grad_norm": 0.5600412487983704, "learning_rate": 0.0002, "epoch": 0.21376085504342018, "step": 160}, {"loss": 1.8162, "grad_norm": 0.3733620345592499, "learning_rate": 0.0002, "epoch": 0.22712090848363392, "step": 170}, {"loss": 1.8564, "grad_norm": 0.5116042494773865, "learning_rate": 0.0002, "epoch": 0.24048096192384769, "step": 180}, {"loss": 1.915, "grad_norm": 0.4071602523326874, "learning_rate": 0.0002, "epoch": 0.25384101536406145, "step": 190}, {"loss": 1.7984, "grad_norm": 0.44189608097076416, "learning_rate": 0.0002, "epoch": 0.26720106880427524, "step": 200}, {"loss": 1.8728, "grad_norm": 0.398699015378952, "learning_rate": 0.0002, "epoch": 0.280561122244489, "step": 210}, {"loss": 1.8205, "grad_norm": 0.3585626482963562, "learning_rate": 0.0002, "epoch": 0.2939211756847027, "step": 220}, {"loss": 1.8861, "grad_norm": 0.3811776041984558, "learning_rate": 0.0002, "epoch": 0.3072812291249165, "step": 230}, {"loss": 1.8365, "grad_norm": 0.37261509895324707, "learning_rate": 0.0002, "epoch": 0.32064128256513025, "step": 240}, {"loss": 1.9186, "grad_norm": 0.39762404561042786, "learning_rate": 0.0002, "epoch": 0.33400133600534404, "step": 250}, {"loss": 1.7965, "grad_norm": 0.3509528934955597, "learning_rate": 0.0002, "epoch": 0.3473613894455578, "step": 260}, {"loss": 1.7802, "grad_norm": 0.3169104754924774, "learning_rate": 0.0002, "epoch": 0.36072144288577157, "step": 270}, {"loss": 1.8038, "grad_norm": 0.33714795112609863, "learning_rate": 0.0002, "epoch": 0.3740814963259853, "step": 280}, {"loss": 1.787, "grad_norm": 1.2936875820159912, "learning_rate": 0.0002, "epoch": 0.38744154976619904, "step": 290}, {"loss": 1.7974, "grad_norm": 0.3459427058696747, "learning_rate": 0.0002, "epoch": 0.40080160320641284, "step": 300}, {"loss": 1.8879, "grad_norm": 0.3380655348300934, "learning_rate": 0.0002, "epoch": 0.4141616566466266, "step": 310}, {"loss": 1.9196, "grad_norm": 0.3890381455421448, "learning_rate": 0.0002, "epoch": 0.42752171008684037, "step": 320}, {"loss": 1.8034, "grad_norm": 0.432327002286911, "learning_rate": 0.0002, "epoch": 0.4408817635270541, "step": 330}, {"loss": 1.8443, "grad_norm": 0.3736560046672821, "learning_rate": 0.0002, "epoch": 0.45424181696726784, "step": 340}, {"loss": 1.8506, "grad_norm": 0.3700982630252838, "learning_rate": 0.0002, "epoch": 0.46760187040748163, "step": 350}, {"loss": 1.7978, "grad_norm": 0.4533902406692505, "learning_rate": 0.0002, "epoch": 0.48096192384769537, "step": 360}, {"loss": 1.7427, "grad_norm": 0.35999053716659546, "learning_rate": 0.0002, "epoch": 0.49432197728790916, "step": 370}, {"loss": 1.7995, "grad_norm": 0.3490903675556183, "learning_rate": 0.0002, "epoch": 0.5076820307281229, "step": 380}, {"loss": 1.8709, "grad_norm": 0.34704291820526123, "learning_rate": 0.0002, "epoch": 0.5210420841683366, "step": 390}, {"loss": 1.7948, "grad_norm": 0.343565434217453, "learning_rate": 0.0002, "epoch": 0.5344021376085505, "step": 400}, {"loss": 1.8564, "grad_norm": 0.3573552966117859, "learning_rate": 0.0002, "epoch": 0.5477621910487642, "step": 410}, {"loss": 1.8477, "grad_norm": 0.32980719208717346, "learning_rate": 0.0002, "epoch": 0.561122244488978, "step": 420}, {"loss": 1.9233, "grad_norm": 0.356952428817749, "learning_rate": 0.0002, "epoch": 0.5744822979291917, "step": 430}, {"loss": 1.7433, "grad_norm": 0.3170869052410126, "learning_rate": 0.0002, "epoch": 0.5878423513694054, "step": 440}, {"loss": 1.7607, "grad_norm": 0.35233718156814575, "learning_rate": 0.0002, "epoch": 0.6012024048096193, "step": 450}, {"loss": 1.8111, "grad_norm": 0.3480125367641449, "learning_rate": 0.0002, "epoch": 0.614562458249833, "step": 460}, {"loss": 1.8386, "grad_norm": 0.4762810468673706, "learning_rate": 0.0002, "epoch": 0.6279225116900468, "step": 470}, {"loss": 1.805, "grad_norm": 0.3907663822174072, "learning_rate": 0.0002, "epoch": 0.6412825651302605, "step": 480}, {"loss": 1.8113, "grad_norm": 0.36315613985061646, "learning_rate": 0.0002, "epoch": 0.6546426185704742, "step": 490}, {"loss": 1.7805, "grad_norm": 0.377796471118927, "learning_rate": 0.0002, "epoch": 0.6680026720106881, "step": 500}, {"loss": 1.7457, "grad_norm": 0.34284207224845886, "learning_rate": 0.0002, "epoch": 0.6813627254509018, "step": 510}, {"loss": 1.8013, "grad_norm": 0.35563018918037415, "learning_rate": 0.0002, "epoch": 0.6947227788911156, "step": 520}, {"loss": 1.8414, "grad_norm": 0.37575867772102356, "learning_rate": 0.0002, "epoch": 0.7080828323313293, "step": 530}, {"loss": 1.7993, "grad_norm": 0.35719701647758484, "learning_rate": 0.0002, "epoch": 0.7214428857715431, "step": 540}, {"loss": 1.7574, "grad_norm": 0.385813444852829, "learning_rate": 0.0002, "epoch": 0.7348029392117569, "step": 550}, {"loss": 1.7985, "grad_norm": 0.44509607553482056, "learning_rate": 0.0002, "epoch": 0.7481629926519706, "step": 560}, {"loss": 1.7459, "grad_norm": 0.36108464002609253, "learning_rate": 0.0002, "epoch": 0.7615230460921844, "step": 570}, {"loss": 1.8207, "grad_norm": 0.3530745804309845, "learning_rate": 0.0002, "epoch": 0.7748830995323981, "step": 580}, {"loss": 1.7479, "grad_norm": 0.34888574481010437, "learning_rate": 0.0002, "epoch": 0.7882431529726119, "step": 590}, {"loss": 1.8656, "grad_norm": 0.387346476316452, "learning_rate": 0.0002, "epoch": 0.8016032064128257, "step": 600}, {"loss": 1.8071, "grad_norm": 0.3641138970851898, "learning_rate": 0.0002, "epoch": 0.8149632598530394, "step": 610}, {"loss": 1.7531, "grad_norm": 0.33729103207588196, "learning_rate": 0.0002, "epoch": 0.8283233132932531, "step": 620}, {"loss": 1.8613, "grad_norm": 0.3652004599571228, "learning_rate": 0.0002, "epoch": 0.8416833667334669, "step": 630}, {"loss": 1.9184, "grad_norm": 0.3986643850803375, "learning_rate": 0.0002, "epoch": 0.8550434201736807, "step": 640}, {"loss": 1.8198, "grad_norm": 0.3458964228630066, "learning_rate": 0.0002, "epoch": 0.8684034736138945, "step": 650}, {"loss": 1.803, "grad_norm": 0.3559381365776062, "learning_rate": 0.0002, "epoch": 0.8817635270541082, "step": 660}, {"loss": 1.7641, "grad_norm": 0.3612841069698334, "learning_rate": 0.0002, "epoch": 0.895123580494322, "step": 670}, {"loss": 1.7888, "grad_norm": 0.34771719574928284, "learning_rate": 0.0002, "epoch": 0.9084836339345357, "step": 680}, {"loss": 1.8204, "grad_norm": 0.3371497094631195, "learning_rate": 0.0002, "epoch": 0.9218436873747495, "step": 690}, {"loss": 1.7848, "grad_norm": 0.5596055388450623, "learning_rate": 0.0002, "epoch": 0.9352037408149633, "step": 700}, {"loss": 1.7794, "grad_norm": 0.311880499124527, "learning_rate": 0.0002, "epoch": 0.948563794255177, "step": 710}, {"loss": 1.8464, "grad_norm": 0.3462068736553192, "learning_rate": 0.0002, "epoch": 0.9619238476953907, "step": 720}, {"loss": 1.8197, "grad_norm": 0.29982393980026245, "learning_rate": 0.0002, "epoch": 0.9752839011356046, "step": 730}, {"loss": 1.8503, "grad_norm": 0.34606459736824036, "learning_rate": 0.0002, "epoch": 0.9886439545758183, "step": 740}]}
+{"epoch": 2.0, "step": 1497, "epoch_duration": 845.7833571434021, "total_accumulated_duration": 1669.5974419116974, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7568.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-748", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.6569, "grad_norm": 0.5097216367721558, "learning_rate": 0.0002, "epoch": 0.013360053440213761, "step": 10}, {"loss": 2.2557, "grad_norm": 0.5924790501594543, "learning_rate": 0.0002, "epoch": 0.026720106880427523, "step": 20}, {"loss": 2.0626, "grad_norm": 0.5158102512359619, "learning_rate": 0.0002, "epoch": 0.04008016032064128, "step": 30}, {"loss": 1.9452, "grad_norm": 0.5033753514289856, "learning_rate": 0.0002, "epoch": 0.053440213760855046, "step": 40}, {"loss": 1.9128, "grad_norm": 0.5390949845314026, "learning_rate": 0.0002, "epoch": 0.06680026720106881, "step": 50}, {"loss": 1.937, "grad_norm": 0.6376217007637024, "learning_rate": 0.0002, "epoch": 0.08016032064128256, "step": 60}, {"loss": 1.929, "grad_norm": 0.4202035069465637, "learning_rate": 0.0002, "epoch": 0.09352037408149633, "step": 70}, {"loss": 1.811, "grad_norm": 0.4269474744796753, "learning_rate": 0.0002, "epoch": 0.10688042752171009, "step": 80}, {"loss": 1.8303, "grad_norm": 0.4306574761867523, "learning_rate": 0.0002, "epoch": 0.12024048096192384, "step": 90}, {"loss": 1.8469, "grad_norm": 0.5297011137008667, "learning_rate": 0.0002, "epoch": 0.13360053440213762, "step": 100}, {"loss": 1.864, "grad_norm": 1.2313778400421143, "learning_rate": 0.0002, "epoch": 0.14696058784235136, "step": 110}, {"loss": 1.8531, "grad_norm": 0.5351294279098511, "learning_rate": 0.0002, "epoch": 0.16032064128256512, "step": 120}, {"loss": 1.9232, "grad_norm": 0.4848092496395111, "learning_rate": 0.0002, "epoch": 0.1736806947227789, "step": 130}, {"loss": 1.8633, "grad_norm": 0.4339500665664673, "learning_rate": 0.0002, "epoch": 0.18704074816299265, "step": 140}, {"loss": 1.816, "grad_norm": 0.46877285838127136, "learning_rate": 0.0002, "epoch": 0.20040080160320642, "step": 150}, {"loss": 1.8033, "grad_norm": 0.5600412487983704, "learning_rate": 0.0002, "epoch": 0.21376085504342018, "step": 160}, {"loss": 1.8162, "grad_norm": 0.3733620345592499, "learning_rate": 0.0002, "epoch": 0.22712090848363392, "step": 170}, {"loss": 1.8564, "grad_norm": 0.5116042494773865, "learning_rate": 0.0002, "epoch": 0.24048096192384769, "step": 180}, {"loss": 1.915, "grad_norm": 0.4071602523326874, "learning_rate": 0.0002, "epoch": 0.25384101536406145, "step": 190}, {"loss": 1.7984, "grad_norm": 0.44189608097076416, "learning_rate": 0.0002, "epoch": 0.26720106880427524, "step": 200}, {"loss": 1.8728, "grad_norm": 0.398699015378952, "learning_rate": 0.0002, "epoch": 0.280561122244489, "step": 210}, {"loss": 1.8205, "grad_norm": 0.3585626482963562, "learning_rate": 0.0002, "epoch": 0.2939211756847027, "step": 220}, {"loss": 1.8861, "grad_norm": 0.3811776041984558, "learning_rate": 0.0002, "epoch": 0.3072812291249165, "step": 230}, {"loss": 1.8365, "grad_norm": 0.37261509895324707, "learning_rate": 0.0002, "epoch": 0.32064128256513025, "step": 240}, {"loss": 1.9186, "grad_norm": 0.39762404561042786, "learning_rate": 0.0002, "epoch": 0.33400133600534404, "step": 250}, {"loss": 1.7965, "grad_norm": 0.3509528934955597, "learning_rate": 0.0002, "epoch": 0.3473613894455578, "step": 260}, {"loss": 1.7802, "grad_norm": 0.3169104754924774, "learning_rate": 0.0002, "epoch": 0.36072144288577157, "step": 270}, {"loss": 1.8038, "grad_norm": 0.33714795112609863, "learning_rate": 0.0002, "epoch": 0.3740814963259853, "step": 280}, {"loss": 1.787, "grad_norm": 1.2936875820159912, "learning_rate": 0.0002, "epoch": 0.38744154976619904, "step": 290}, {"loss": 1.7974, "grad_norm": 0.3459427058696747, "learning_rate": 0.0002, "epoch": 0.40080160320641284, "step": 300}, {"loss": 1.8879, "grad_norm": 0.3380655348300934, "learning_rate": 0.0002, "epoch": 0.4141616566466266, "step": 310}, {"loss": 1.9196, "grad_norm": 0.3890381455421448, "learning_rate": 0.0002, "epoch": 0.42752171008684037, "step": 320}, {"loss": 1.8034, "grad_norm": 0.432327002286911, "learning_rate": 0.0002, "epoch": 0.4408817635270541, "step": 330}, {"loss": 1.8443, "grad_norm": 0.3736560046672821, "learning_rate": 0.0002, "epoch": 0.45424181696726784, "step": 340}, {"loss": 1.8506, "grad_norm": 0.3700982630252838, "learning_rate": 0.0002, "epoch": 0.46760187040748163, "step": 350}, {"loss": 1.7978, "grad_norm": 0.4533902406692505, "learning_rate": 0.0002, "epoch": 0.48096192384769537, "step": 360}, {"loss": 1.7427, "grad_norm": 0.35999053716659546, "learning_rate": 0.0002, "epoch": 0.49432197728790916, "step": 370}, {"loss": 1.7995, "grad_norm": 0.3490903675556183, "learning_rate": 0.0002, "epoch": 0.5076820307281229, "step": 380}, {"loss": 1.8709, "grad_norm": 0.34704291820526123, "learning_rate": 0.0002, "epoch": 0.5210420841683366, "step": 390}, {"loss": 1.7948, "grad_norm": 0.343565434217453, "learning_rate": 0.0002, "epoch": 0.5344021376085505, "step": 400}, {"loss": 1.8564, "grad_norm": 0.3573552966117859, "learning_rate": 0.0002, "epoch": 0.5477621910487642, "step": 410}, {"loss": 1.8477, "grad_norm": 0.32980719208717346, "learning_rate": 0.0002, "epoch": 0.561122244488978, "step": 420}, {"loss": 1.9233, "grad_norm": 0.356952428817749, "learning_rate": 0.0002, "epoch": 0.5744822979291917, "step": 430}, {"loss": 1.7433, "grad_norm": 0.3170869052410126, "learning_rate": 0.0002, "epoch": 0.5878423513694054, "step": 440}, {"loss": 1.7607, "grad_norm": 0.35233718156814575, "learning_rate": 0.0002, "epoch": 0.6012024048096193, "step": 450}, {"loss": 1.8111, "grad_norm": 0.3480125367641449, "learning_rate": 0.0002, "epoch": 0.614562458249833, "step": 460}, {"loss": 1.8386, "grad_norm": 0.4762810468673706, "learning_rate": 0.0002, "epoch": 0.6279225116900468, "step": 470}, {"loss": 1.805, "grad_norm": 0.3907663822174072, "learning_rate": 0.0002, "epoch": 0.6412825651302605, "step": 480}, {"loss": 1.8113, "grad_norm": 0.36315613985061646, "learning_rate": 0.0002, "epoch": 0.6546426185704742, "step": 490}, {"loss": 1.7805, "grad_norm": 0.377796471118927, "learning_rate": 0.0002, "epoch": 0.6680026720106881, "step": 500}, {"loss": 1.7457, "grad_norm": 0.34284207224845886, "learning_rate": 0.0002, "epoch": 0.6813627254509018, "step": 510}, {"loss": 1.8013, "grad_norm": 0.35563018918037415, "learning_rate": 0.0002, "epoch": 0.6947227788911156, "step": 520}, {"loss": 1.8414, "grad_norm": 0.37575867772102356, "learning_rate": 0.0002, "epoch": 0.7080828323313293, "step": 530}, {"loss": 1.7993, "grad_norm": 0.35719701647758484, "learning_rate": 0.0002, "epoch": 0.7214428857715431, "step": 540}, {"loss": 1.7574, "grad_norm": 0.385813444852829, "learning_rate": 0.0002, "epoch": 0.7348029392117569, "step": 550}, {"loss": 1.7985, "grad_norm": 0.44509607553482056, "learning_rate": 0.0002, "epoch": 0.7481629926519706, "step": 560}, {"loss": 1.7459, "grad_norm": 0.36108464002609253, "learning_rate": 0.0002, "epoch": 0.7615230460921844, "step": 570}, {"loss": 1.8207, "grad_norm": 0.3530745804309845, "learning_rate": 0.0002, "epoch": 0.7748830995323981, "step": 580}, {"loss": 1.7479, "grad_norm": 0.34888574481010437, "learning_rate": 0.0002, "epoch": 0.7882431529726119, "step": 590}, {"loss": 1.8656, "grad_norm": 0.387346476316452, "learning_rate": 0.0002, "epoch": 0.8016032064128257, "step": 600}, {"loss": 1.8071, "grad_norm": 0.3641138970851898, "learning_rate": 0.0002, "epoch": 0.8149632598530394, "step": 610}, {"loss": 1.7531, "grad_norm": 0.33729103207588196, "learning_rate": 0.0002, "epoch": 0.8283233132932531, "step": 620}, {"loss": 1.8613, "grad_norm": 0.3652004599571228, "learning_rate": 0.0002, "epoch": 0.8416833667334669, "step": 630}, {"loss": 1.9184, "grad_norm": 0.3986643850803375, "learning_rate": 0.0002, "epoch": 0.8550434201736807, "step": 640}, {"loss": 1.8198, "grad_norm": 0.3458964228630066, "learning_rate": 0.0002, "epoch": 0.8684034736138945, "step": 650}, {"loss": 1.803, "grad_norm": 0.3559381365776062, "learning_rate": 0.0002, "epoch": 0.8817635270541082, "step": 660}, {"loss": 1.7641, "grad_norm": 0.3612841069698334, "learning_rate": 0.0002, "epoch": 0.895123580494322, "step": 670}, {"loss": 1.7888, "grad_norm": 0.34771719574928284, "learning_rate": 0.0002, "epoch": 0.9084836339345357, "step": 680}, {"loss": 1.8204, "grad_norm": 0.3371497094631195, "learning_rate": 0.0002, "epoch": 0.9218436873747495, "step": 690}, {"loss": 1.7848, "grad_norm": 0.5596055388450623, "learning_rate": 0.0002, "epoch": 0.9352037408149633, "step": 700}, {"loss": 1.7794, "grad_norm": 0.311880499124527, "learning_rate": 0.0002, "epoch": 0.948563794255177, "step": 710}, {"loss": 1.8464, "grad_norm": 0.3462068736553192, "learning_rate": 0.0002, "epoch": 0.9619238476953907, "step": 720}, {"loss": 1.8197, "grad_norm": 0.29982393980026245, "learning_rate": 0.0002, "epoch": 0.9752839011356046, "step": 730}, {"loss": 1.8503, "grad_norm": 0.34606459736824036, "learning_rate": 0.0002, "epoch": 0.9886439545758183, "step": 740}, {"eval_loss": 1.8201380968093872, "eval_runtime": 38.6124, "eval_samples_per_second": 13.338, "eval_steps_per_second": 1.683, "epoch": 0.9993319973279893, "step": 748}, {"loss": 1.7786, "grad_norm": 0.32302048802375793, "learning_rate": 0.0002, "epoch": 1.002004008016032, "step": 750}, {"loss": 1.7297, "grad_norm": 0.37585633993148804, "learning_rate": 0.0002, "epoch": 1.0153640614562458, "step": 760}, {"loss": 1.7008, "grad_norm": 0.33826273679733276, "learning_rate": 0.0002, "epoch": 1.0287241148964597, "step": 770}, {"loss": 1.809, "grad_norm": 0.44682955741882324, "learning_rate": 0.0002, "epoch": 1.0420841683366733, "step": 780}, {"loss": 1.7092, "grad_norm": 0.422188401222229, "learning_rate": 0.0002, "epoch": 1.0554442217768871, "step": 790}, {"loss": 1.7765, "grad_norm": 0.3809906244277954, "learning_rate": 0.0002, "epoch": 1.0688042752171008, "step": 800}, {"loss": 1.7431, "grad_norm": 0.3454349637031555, "learning_rate": 0.0002, "epoch": 1.0821643286573146, "step": 810}, {"loss": 1.7257, "grad_norm": 0.3767355978488922, "learning_rate": 0.0002, "epoch": 1.0955243820975284, "step": 820}, {"loss": 1.7224, "grad_norm": 0.3361407518386841, "learning_rate": 0.0002, "epoch": 1.108884435537742, "step": 830}, {"loss": 1.7509, "grad_norm": 0.3654632568359375, "learning_rate": 0.0002, "epoch": 1.122244488977956, "step": 840}, {"loss": 1.7151, "grad_norm": 0.3822861313819885, "learning_rate": 0.0002, "epoch": 1.1356045424181698, "step": 850}, {"loss": 1.7121, "grad_norm": 0.3853831887245178, "learning_rate": 0.0002, "epoch": 1.1489645958583834, "step": 860}, {"loss": 1.7685, "grad_norm": 0.35521796345710754, "learning_rate": 0.0002, "epoch": 1.1623246492985972, "step": 870}, {"loss": 1.7735, "grad_norm": 0.4107200503349304, "learning_rate": 0.0002, "epoch": 1.1756847027388109, "step": 880}, {"loss": 1.7484, "grad_norm": 0.33219534158706665, "learning_rate": 0.0002, "epoch": 1.1890447561790247, "step": 890}, {"loss": 1.7071, "grad_norm": 0.3559704124927521, "learning_rate": 0.0002, "epoch": 1.2024048096192386, "step": 900}, {"loss": 1.7535, "grad_norm": 0.3700537383556366, "learning_rate": 0.0002, "epoch": 1.2157648630594522, "step": 910}, {"loss": 1.7513, "grad_norm": 0.3771909475326538, "learning_rate": 0.0002, "epoch": 1.229124916499666, "step": 920}, {"loss": 1.7566, "grad_norm": 0.3136613965034485, "learning_rate": 0.0002, "epoch": 1.2424849699398797, "step": 930}, {"loss": 1.6783, "grad_norm": 0.3952099084854126, "learning_rate": 0.0002, "epoch": 1.2558450233800935, "step": 940}, {"loss": 1.7691, "grad_norm": 0.36534377932548523, "learning_rate": 0.0002, "epoch": 1.2692050768203074, "step": 950}, {"loss": 1.7127, "grad_norm": 0.3803492486476898, "learning_rate": 0.0002, "epoch": 1.282565130260521, "step": 960}, {"loss": 1.7896, "grad_norm": 0.3992428183555603, "learning_rate": 0.0002, "epoch": 1.2959251837007348, "step": 970}, {"loss": 1.7343, "grad_norm": 0.3627142906188965, "learning_rate": 0.0002, "epoch": 1.3092852371409487, "step": 980}, {"loss": 1.7598, "grad_norm": 0.4248180091381073, "learning_rate": 0.0002, "epoch": 1.3226452905811623, "step": 990}, {"loss": 1.6896, "grad_norm": 0.4060308039188385, "learning_rate": 0.0002, "epoch": 1.3360053440213762, "step": 1000}, {"loss": 1.7457, "grad_norm": 0.3788969814777374, "learning_rate": 0.0002, "epoch": 1.3493653974615898, "step": 1010}, {"loss": 1.7111, "grad_norm": 0.4174270033836365, "learning_rate": 0.0002, "epoch": 1.3627254509018036, "step": 1020}, {"loss": 1.7975, "grad_norm": 0.35500675439834595, "learning_rate": 0.0002, "epoch": 1.3760855043420173, "step": 1030}, {"loss": 1.724, "grad_norm": 0.3454059362411499, "learning_rate": 0.0002, "epoch": 1.389445557782231, "step": 1040}, {"loss": 1.8299, "grad_norm": 0.45807570219039917, "learning_rate": 0.0002, "epoch": 1.402805611222445, "step": 1050}, {"loss": 1.7425, "grad_norm": 0.39338022470474243, "learning_rate": 0.0002, "epoch": 1.4161656646626586, "step": 1060}, {"loss": 1.7457, "grad_norm": 0.3870709240436554, "learning_rate": 0.0002, "epoch": 1.4295257181028724, "step": 1070}, {"loss": 1.6565, "grad_norm": 0.40996190905570984, "learning_rate": 0.0002, "epoch": 1.4428857715430863, "step": 1080}, {"loss": 1.7324, "grad_norm": 0.38762837648391724, "learning_rate": 0.0002, "epoch": 1.4562458249833, "step": 1090}, {"loss": 1.7362, "grad_norm": 0.36756977438926697, "learning_rate": 0.0002, "epoch": 1.4696058784235138, "step": 1100}, {"loss": 1.7451, "grad_norm": 0.4087235927581787, "learning_rate": 0.0002, "epoch": 1.4829659318637274, "step": 1110}, {"loss": 1.7114, "grad_norm": 0.3357745110988617, "learning_rate": 0.0002, "epoch": 1.4963259853039412, "step": 1120}, {"loss": 1.6877, "grad_norm": 0.37486532330513, "learning_rate": 0.0002, "epoch": 1.5096860387441549, "step": 1130}, {"loss": 1.7252, "grad_norm": 0.3387809991836548, "learning_rate": 0.0002, "epoch": 1.5230460921843687, "step": 1140}, {"loss": 1.7169, "grad_norm": 0.37462118268013, "learning_rate": 0.0002, "epoch": 1.5364061456245826, "step": 1150}, {"loss": 1.6988, "grad_norm": 0.38575324416160583, "learning_rate": 0.0002, "epoch": 1.5497661990647962, "step": 1160}, {"loss": 1.7438, "grad_norm": 0.3515765964984894, "learning_rate": 0.0002, "epoch": 1.56312625250501, "step": 1170}, {"loss": 1.7524, "grad_norm": 0.39308643341064453, "learning_rate": 0.0002, "epoch": 1.5764863059452239, "step": 1180}, {"loss": 1.6422, "grad_norm": 0.3308864235877991, "learning_rate": 0.0002, "epoch": 1.5898463593854375, "step": 1190}, {"loss": 1.7566, "grad_norm": 0.3397478461265564, "learning_rate": 0.0002, "epoch": 1.6032064128256514, "step": 1200}, {"loss": 1.7871, "grad_norm": 0.3911525309085846, "learning_rate": 0.0002, "epoch": 1.6165664662658652, "step": 1210}, {"loss": 1.7443, "grad_norm": 0.3771969974040985, "learning_rate": 0.0002, "epoch": 1.6299265197060788, "step": 1220}, {"loss": 1.7631, "grad_norm": 0.35346856713294983, "learning_rate": 0.0002, "epoch": 1.6432865731462925, "step": 1230}, {"loss": 1.7225, "grad_norm": 0.41736963391304016, "learning_rate": 0.0002, "epoch": 1.6566466265865063, "step": 1240}, {"loss": 1.7582, "grad_norm": 0.3375225067138672, "learning_rate": 0.0002, "epoch": 1.6700066800267201, "step": 1250}, {"loss": 1.6916, "grad_norm": 0.3779928982257843, "learning_rate": 0.0002, "epoch": 1.6833667334669338, "step": 1260}, {"loss": 1.728, "grad_norm": 0.35388994216918945, "learning_rate": 0.0002, "epoch": 1.6967267869071476, "step": 1270}, {"loss": 1.7461, "grad_norm": 0.33884134888648987, "learning_rate": 0.0002, "epoch": 1.7100868403473615, "step": 1280}, {"loss": 1.7083, "grad_norm": 0.35439756512641907, "learning_rate": 0.0002, "epoch": 1.723446893787575, "step": 1290}, {"loss": 1.7389, "grad_norm": 0.3766156733036041, "learning_rate": 0.0002, "epoch": 1.736806947227789, "step": 1300}, {"loss": 1.7847, "grad_norm": 0.36148911714553833, "learning_rate": 0.0002, "epoch": 1.7501670006680028, "step": 1310}, {"loss": 1.7344, "grad_norm": 0.39687496423721313, "learning_rate": 0.0002, "epoch": 1.7635270541082164, "step": 1320}, {"loss": 1.7541, "grad_norm": 0.35639452934265137, "learning_rate": 0.0002, "epoch": 1.77688710754843, "step": 1330}, {"loss": 1.7254, "grad_norm": 0.38781628012657166, "learning_rate": 0.0002, "epoch": 1.7902471609886441, "step": 1340}, {"loss": 1.7867, "grad_norm": 0.42784637212753296, "learning_rate": 0.0002, "epoch": 1.8036072144288577, "step": 1350}, {"loss": 1.7336, "grad_norm": 0.40258511900901794, "learning_rate": 0.0002, "epoch": 1.8169672678690714, "step": 1360}, {"loss": 1.7771, "grad_norm": 0.36674195528030396, "learning_rate": 0.0002, "epoch": 1.8303273213092852, "step": 1370}, {"loss": 1.7425, "grad_norm": 0.4064558446407318, "learning_rate": 0.0002, "epoch": 1.843687374749499, "step": 1380}, {"loss": 1.7425, "grad_norm": 0.3669849932193756, "learning_rate": 0.0002, "epoch": 1.8570474281897127, "step": 1390}, {"loss": 1.7924, "grad_norm": 0.37569567561149597, "learning_rate": 0.0002, "epoch": 1.8704074816299265, "step": 1400}, {"loss": 1.7885, "grad_norm": 0.37307995557785034, "learning_rate": 0.0002, "epoch": 1.8837675350701404, "step": 1410}, {"loss": 1.7548, "grad_norm": 0.3772695064544678, "learning_rate": 0.0002, "epoch": 1.897127588510354, "step": 1420}, {"loss": 1.7682, "grad_norm": 0.36993589997291565, "learning_rate": 0.0002, "epoch": 1.9104876419505676, "step": 1430}, {"loss": 1.7249, "grad_norm": 0.3490557372570038, "learning_rate": 0.0002, "epoch": 1.9238476953907817, "step": 1440}, {"loss": 1.7979, "grad_norm": 0.3716149628162384, "learning_rate": 0.0002, "epoch": 1.9372077488309953, "step": 1450}, {"loss": 1.6664, "grad_norm": 0.39236098527908325, "learning_rate": 0.0002, "epoch": 1.950567802271209, "step": 1460}, {"loss": 1.6852, "grad_norm": 0.37258651852607727, "learning_rate": 0.0002, "epoch": 1.9639278557114228, "step": 1470}, {"loss": 1.7427, "grad_norm": 0.36183077096939087, "learning_rate": 0.0002, "epoch": 1.9772879091516367, "step": 1480}, {"loss": 1.7055, "grad_norm": 0.3956947326660156, "learning_rate": 0.0002, "epoch": 1.9906479625918503, "step": 1490}]}
+{"epoch": 2.9993319973279893, "step": 2245, "epoch_duration": 812.8899757862091, "total_accumulated_duration": 2482.4874176979065, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7672.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.6569, "grad_norm": 0.5097216367721558, "learning_rate": 0.0002, "epoch": 0.013360053440213761, "step": 10}, {"loss": 2.2557, "grad_norm": 0.5924790501594543, "learning_rate": 0.0002, "epoch": 0.026720106880427523, "step": 20}, {"loss": 2.0626, "grad_norm": 0.5158102512359619, "learning_rate": 0.0002, "epoch": 0.04008016032064128, "step": 30}, {"loss": 1.9452, "grad_norm": 0.5033753514289856, "learning_rate": 0.0002, "epoch": 0.053440213760855046, "step": 40}, {"loss": 1.9128, "grad_norm": 0.5390949845314026, "learning_rate": 0.0002, "epoch": 0.06680026720106881, "step": 50}, {"loss": 1.937, "grad_norm": 0.6376217007637024, "learning_rate": 0.0002, "epoch": 0.08016032064128256, "step": 60}, {"loss": 1.929, "grad_norm": 0.4202035069465637, "learning_rate": 0.0002, "epoch": 0.09352037408149633, "step": 70}, {"loss": 1.811, "grad_norm": 0.4269474744796753, "learning_rate": 0.0002, "epoch": 0.10688042752171009, "step": 80}, {"loss": 1.8303, "grad_norm": 0.4306574761867523, "learning_rate": 0.0002, "epoch": 0.12024048096192384, "step": 90}, {"loss": 1.8469, "grad_norm": 0.5297011137008667, "learning_rate": 0.0002, "epoch": 0.13360053440213762, "step": 100}, {"loss": 1.864, "grad_norm": 1.2313778400421143, "learning_rate": 0.0002, "epoch": 0.14696058784235136, "step": 110}, {"loss": 1.8531, "grad_norm": 0.5351294279098511, "learning_rate": 0.0002, "epoch": 0.16032064128256512, "step": 120}, {"loss": 1.9232, "grad_norm": 0.4848092496395111, "learning_rate": 0.0002, "epoch": 0.1736806947227789, "step": 130}, {"loss": 1.8633, "grad_norm": 0.4339500665664673, "learning_rate": 0.0002, "epoch": 0.18704074816299265, "step": 140}, {"loss": 1.816, "grad_norm": 0.46877285838127136, "learning_rate": 0.0002, "epoch": 0.20040080160320642, "step": 150}, {"loss": 1.8033, "grad_norm": 0.5600412487983704, "learning_rate": 0.0002, "epoch": 0.21376085504342018, "step": 160}, {"loss": 1.8162, "grad_norm": 0.3733620345592499, "learning_rate": 0.0002, "epoch": 0.22712090848363392, "step": 170}, {"loss": 1.8564, "grad_norm": 0.5116042494773865, "learning_rate": 0.0002, "epoch": 0.24048096192384769, "step": 180}, {"loss": 1.915, "grad_norm": 0.4071602523326874, "learning_rate": 0.0002, "epoch": 0.25384101536406145, "step": 190}, {"loss": 1.7984, "grad_norm": 0.44189608097076416, "learning_rate": 0.0002, "epoch": 0.26720106880427524, "step": 200}, {"loss": 1.8728, "grad_norm": 0.398699015378952, "learning_rate": 0.0002, "epoch": 0.280561122244489, "step": 210}, {"loss": 1.8205, "grad_norm": 0.3585626482963562, "learning_rate": 0.0002, "epoch": 0.2939211756847027, "step": 220}, {"loss": 1.8861, "grad_norm": 0.3811776041984558, "learning_rate": 0.0002, "epoch": 0.3072812291249165, "step": 230}, {"loss": 1.8365, "grad_norm": 0.37261509895324707, "learning_rate": 0.0002, "epoch": 0.32064128256513025, "step": 240}, {"loss": 1.9186, "grad_norm": 0.39762404561042786, "learning_rate": 0.0002, "epoch": 0.33400133600534404, "step": 250}, {"loss": 1.7965, "grad_norm": 0.3509528934955597, "learning_rate": 0.0002, "epoch": 0.3473613894455578, "step": 260}, {"loss": 1.7802, "grad_norm": 0.3169104754924774, "learning_rate": 0.0002, "epoch": 0.36072144288577157, "step": 270}, {"loss": 1.8038, "grad_norm": 0.33714795112609863, "learning_rate": 0.0002, "epoch": 0.3740814963259853, "step": 280}, {"loss": 1.787, "grad_norm": 1.2936875820159912, "learning_rate": 0.0002, "epoch": 0.38744154976619904, "step": 290}, {"loss": 1.7974, "grad_norm": 0.3459427058696747, "learning_rate": 0.0002, "epoch": 0.40080160320641284, "step": 300}, {"loss": 1.8879, "grad_norm": 0.3380655348300934, "learning_rate": 0.0002, "epoch": 0.4141616566466266, "step": 310}, {"loss": 1.9196, "grad_norm": 0.3890381455421448, "learning_rate": 0.0002, "epoch": 0.42752171008684037, "step": 320}, {"loss": 1.8034, "grad_norm": 0.432327002286911, "learning_rate": 0.0002, "epoch": 0.4408817635270541, "step": 330}, {"loss": 1.8443, "grad_norm": 0.3736560046672821, "learning_rate": 0.0002, "epoch": 0.45424181696726784, "step": 340}, {"loss": 1.8506, "grad_norm": 0.3700982630252838, "learning_rate": 0.0002, "epoch": 0.46760187040748163, "step": 350}, {"loss": 1.7978, "grad_norm": 0.4533902406692505, "learning_rate": 0.0002, "epoch": 0.48096192384769537, "step": 360}, {"loss": 1.7427, "grad_norm": 0.35999053716659546, "learning_rate": 0.0002, "epoch": 0.49432197728790916, "step": 370}, {"loss": 1.7995, "grad_norm": 0.3490903675556183, "learning_rate": 0.0002, "epoch": 0.5076820307281229, "step": 380}, {"loss": 1.8709, "grad_norm": 0.34704291820526123, "learning_rate": 0.0002, "epoch": 0.5210420841683366, "step": 390}, {"loss": 1.7948, "grad_norm": 0.343565434217453, "learning_rate": 0.0002, "epoch": 0.5344021376085505, "step": 400}, {"loss": 1.8564, "grad_norm": 0.3573552966117859, "learning_rate": 0.0002, "epoch": 0.5477621910487642, "step": 410}, {"loss": 1.8477, "grad_norm": 0.32980719208717346, "learning_rate": 0.0002, "epoch": 0.561122244488978, "step": 420}, {"loss": 1.9233, "grad_norm": 0.356952428817749, "learning_rate": 0.0002, "epoch": 0.5744822979291917, "step": 430}, {"loss": 1.7433, "grad_norm": 0.3170869052410126, "learning_rate": 0.0002, "epoch": 0.5878423513694054, "step": 440}, {"loss": 1.7607, "grad_norm": 0.35233718156814575, "learning_rate": 0.0002, "epoch": 0.6012024048096193, "step": 450}, {"loss": 1.8111, "grad_norm": 0.3480125367641449, "learning_rate": 0.0002, "epoch": 0.614562458249833, "step": 460}, {"loss": 1.8386, "grad_norm": 0.4762810468673706, "learning_rate": 0.0002, "epoch": 0.6279225116900468, "step": 470}, {"loss": 1.805, "grad_norm": 0.3907663822174072, "learning_rate": 0.0002, "epoch": 0.6412825651302605, "step": 480}, {"loss": 1.8113, "grad_norm": 0.36315613985061646, "learning_rate": 0.0002, "epoch": 0.6546426185704742, "step": 490}, {"loss": 1.7805, "grad_norm": 0.377796471118927, "learning_rate": 0.0002, "epoch": 0.6680026720106881, "step": 500}, {"loss": 1.7457, "grad_norm": 0.34284207224845886, "learning_rate": 0.0002, "epoch": 0.6813627254509018, "step": 510}, {"loss": 1.8013, "grad_norm": 0.35563018918037415, "learning_rate": 0.0002, "epoch": 0.6947227788911156, "step": 520}, {"loss": 1.8414, "grad_norm": 0.37575867772102356, "learning_rate": 0.0002, "epoch": 0.7080828323313293, "step": 530}, {"loss": 1.7993, "grad_norm": 0.35719701647758484, "learning_rate": 0.0002, "epoch": 0.7214428857715431, "step": 540}, {"loss": 1.7574, "grad_norm": 0.385813444852829, "learning_rate": 0.0002, "epoch": 0.7348029392117569, "step": 550}, {"loss": 1.7985, "grad_norm": 0.44509607553482056, "learning_rate": 0.0002, "epoch": 0.7481629926519706, "step": 560}, {"loss": 1.7459, "grad_norm": 0.36108464002609253, "learning_rate": 0.0002, "epoch": 0.7615230460921844, "step": 570}, {"loss": 1.8207, "grad_norm": 0.3530745804309845, "learning_rate": 0.0002, "epoch": 0.7748830995323981, "step": 580}, {"loss": 1.7479, "grad_norm": 0.34888574481010437, "learning_rate": 0.0002, "epoch": 0.7882431529726119, "step": 590}, {"loss": 1.8656, "grad_norm": 0.387346476316452, "learning_rate": 0.0002, "epoch": 0.8016032064128257, "step": 600}, {"loss": 1.8071, "grad_norm": 0.3641138970851898, "learning_rate": 0.0002, "epoch": 0.8149632598530394, "step": 610}, {"loss": 1.7531, "grad_norm": 0.33729103207588196, "learning_rate": 0.0002, "epoch": 0.8283233132932531, "step": 620}, {"loss": 1.8613, "grad_norm": 0.3652004599571228, "learning_rate": 0.0002, "epoch": 0.8416833667334669, "step": 630}, {"loss": 1.9184, "grad_norm": 0.3986643850803375, "learning_rate": 0.0002, "epoch": 0.8550434201736807, "step": 640}, {"loss": 1.8198, "grad_norm": 0.3458964228630066, "learning_rate": 0.0002, "epoch": 0.8684034736138945, "step": 650}, {"loss": 1.803, "grad_norm": 0.3559381365776062, "learning_rate": 0.0002, "epoch": 0.8817635270541082, "step": 660}, {"loss": 1.7641, "grad_norm": 0.3612841069698334, "learning_rate": 0.0002, "epoch": 0.895123580494322, "step": 670}, {"loss": 1.7888, "grad_norm": 0.34771719574928284, "learning_rate": 0.0002, "epoch": 0.9084836339345357, "step": 680}, {"loss": 1.8204, "grad_norm": 0.3371497094631195, "learning_rate": 0.0002, "epoch": 0.9218436873747495, "step": 690}, {"loss": 1.7848, "grad_norm": 0.5596055388450623, "learning_rate": 0.0002, "epoch": 0.9352037408149633, "step": 700}, {"loss": 1.7794, "grad_norm": 0.311880499124527, "learning_rate": 0.0002, "epoch": 0.948563794255177, "step": 710}, {"loss": 1.8464, "grad_norm": 0.3462068736553192, "learning_rate": 0.0002, "epoch": 0.9619238476953907, "step": 720}, {"loss": 1.8197, "grad_norm": 0.29982393980026245, "learning_rate": 0.0002, "epoch": 0.9752839011356046, "step": 730}, {"loss": 1.8503, "grad_norm": 0.34606459736824036, "learning_rate": 0.0002, "epoch": 0.9886439545758183, "step": 740}, {"eval_loss": 1.8201380968093872, "eval_runtime": 38.6124, "eval_samples_per_second": 13.338, "eval_steps_per_second": 1.683, "epoch": 0.9993319973279893, "step": 748}, {"loss": 1.7786, "grad_norm": 0.32302048802375793, "learning_rate": 0.0002, "epoch": 1.002004008016032, "step": 750}, {"loss": 1.7297, "grad_norm": 0.37585633993148804, "learning_rate": 0.0002, "epoch": 1.0153640614562458, "step": 760}, {"loss": 1.7008, "grad_norm": 0.33826273679733276, "learning_rate": 0.0002, "epoch": 1.0287241148964597, "step": 770}, {"loss": 1.809, "grad_norm": 0.44682955741882324, "learning_rate": 0.0002, "epoch": 1.0420841683366733, "step": 780}, {"loss": 1.7092, "grad_norm": 0.422188401222229, "learning_rate": 0.0002, "epoch": 1.0554442217768871, "step": 790}, {"loss": 1.7765, "grad_norm": 0.3809906244277954, "learning_rate": 0.0002, "epoch": 1.0688042752171008, "step": 800}, {"loss": 1.7431, "grad_norm": 0.3454349637031555, "learning_rate": 0.0002, "epoch": 1.0821643286573146, "step": 810}, {"loss": 1.7257, "grad_norm": 0.3767355978488922, "learning_rate": 0.0002, "epoch": 1.0955243820975284, "step": 820}, {"loss": 1.7224, "grad_norm": 0.3361407518386841, "learning_rate": 0.0002, "epoch": 1.108884435537742, "step": 830}, {"loss": 1.7509, "grad_norm": 0.3654632568359375, "learning_rate": 0.0002, "epoch": 1.122244488977956, "step": 840}, {"loss": 1.7151, "grad_norm": 0.3822861313819885, "learning_rate": 0.0002, "epoch": 1.1356045424181698, "step": 850}, {"loss": 1.7121, "grad_norm": 0.3853831887245178, "learning_rate": 0.0002, "epoch": 1.1489645958583834, "step": 860}, {"loss": 1.7685, "grad_norm": 0.35521796345710754, "learning_rate": 0.0002, "epoch": 1.1623246492985972, "step": 870}, {"loss": 1.7735, "grad_norm": 0.4107200503349304, "learning_rate": 0.0002, "epoch": 1.1756847027388109, "step": 880}, {"loss": 1.7484, "grad_norm": 0.33219534158706665, "learning_rate": 0.0002, "epoch": 1.1890447561790247, "step": 890}, {"loss": 1.7071, "grad_norm": 0.3559704124927521, "learning_rate": 0.0002, "epoch": 1.2024048096192386, "step": 900}, {"loss": 1.7535, "grad_norm": 0.3700537383556366, "learning_rate": 0.0002, "epoch": 1.2157648630594522, "step": 910}, {"loss": 1.7513, "grad_norm": 0.3771909475326538, "learning_rate": 0.0002, "epoch": 1.229124916499666, "step": 920}, {"loss": 1.7566, "grad_norm": 0.3136613965034485, "learning_rate": 0.0002, "epoch": 1.2424849699398797, "step": 930}, {"loss": 1.6783, "grad_norm": 0.3952099084854126, "learning_rate": 0.0002, "epoch": 1.2558450233800935, "step": 940}, {"loss": 1.7691, "grad_norm": 0.36534377932548523, "learning_rate": 0.0002, "epoch": 1.2692050768203074, "step": 950}, {"loss": 1.7127, "grad_norm": 0.3803492486476898, "learning_rate": 0.0002, "epoch": 1.282565130260521, "step": 960}, {"loss": 1.7896, "grad_norm": 0.3992428183555603, "learning_rate": 0.0002, "epoch": 1.2959251837007348, "step": 970}, {"loss": 1.7343, "grad_norm": 0.3627142906188965, "learning_rate": 0.0002, "epoch": 1.3092852371409487, "step": 980}, {"loss": 1.7598, "grad_norm": 0.4248180091381073, "learning_rate": 0.0002, "epoch": 1.3226452905811623, "step": 990}, {"loss": 1.6896, "grad_norm": 0.4060308039188385, "learning_rate": 0.0002, "epoch": 1.3360053440213762, "step": 1000}, {"loss": 1.7457, "grad_norm": 0.3788969814777374, "learning_rate": 0.0002, "epoch": 1.3493653974615898, "step": 1010}, {"loss": 1.7111, "grad_norm": 0.4174270033836365, "learning_rate": 0.0002, "epoch": 1.3627254509018036, "step": 1020}, {"loss": 1.7975, "grad_norm": 0.35500675439834595, "learning_rate": 0.0002, "epoch": 1.3760855043420173, "step": 1030}, {"loss": 1.724, "grad_norm": 0.3454059362411499, "learning_rate": 0.0002, "epoch": 1.389445557782231, "step": 1040}, {"loss": 1.8299, "grad_norm": 0.45807570219039917, "learning_rate": 0.0002, "epoch": 1.402805611222445, "step": 1050}, {"loss": 1.7425, "grad_norm": 0.39338022470474243, "learning_rate": 0.0002, "epoch": 1.4161656646626586, "step": 1060}, {"loss": 1.7457, "grad_norm": 0.3870709240436554, "learning_rate": 0.0002, "epoch": 1.4295257181028724, "step": 1070}, {"loss": 1.6565, "grad_norm": 0.40996190905570984, "learning_rate": 0.0002, "epoch": 1.4428857715430863, "step": 1080}, {"loss": 1.7324, "grad_norm": 0.38762837648391724, "learning_rate": 0.0002, "epoch": 1.4562458249833, "step": 1090}, {"loss": 1.7362, "grad_norm": 0.36756977438926697, "learning_rate": 0.0002, "epoch": 1.4696058784235138, "step": 1100}, {"loss": 1.7451, "grad_norm": 0.4087235927581787, "learning_rate": 0.0002, "epoch": 1.4829659318637274, "step": 1110}, {"loss": 1.7114, "grad_norm": 0.3357745110988617, "learning_rate": 0.0002, "epoch": 1.4963259853039412, "step": 1120}, {"loss": 1.6877, "grad_norm": 0.37486532330513, "learning_rate": 0.0002, "epoch": 1.5096860387441549, "step": 1130}, {"loss": 1.7252, "grad_norm": 0.3387809991836548, "learning_rate": 0.0002, "epoch": 1.5230460921843687, "step": 1140}, {"loss": 1.7169, "grad_norm": 0.37462118268013, "learning_rate": 0.0002, "epoch": 1.5364061456245826, "step": 1150}, {"loss": 1.6988, "grad_norm": 0.38575324416160583, "learning_rate": 0.0002, "epoch": 1.5497661990647962, "step": 1160}, {"loss": 1.7438, "grad_norm": 0.3515765964984894, "learning_rate": 0.0002, "epoch": 1.56312625250501, "step": 1170}, {"loss": 1.7524, "grad_norm": 0.39308643341064453, "learning_rate": 0.0002, "epoch": 1.5764863059452239, "step": 1180}, {"loss": 1.6422, "grad_norm": 0.3308864235877991, "learning_rate": 0.0002, "epoch": 1.5898463593854375, "step": 1190}, {"loss": 1.7566, "grad_norm": 0.3397478461265564, "learning_rate": 0.0002, "epoch": 1.6032064128256514, "step": 1200}, {"loss": 1.7871, "grad_norm": 0.3911525309085846, "learning_rate": 0.0002, "epoch": 1.6165664662658652, "step": 1210}, {"loss": 1.7443, "grad_norm": 0.3771969974040985, "learning_rate": 0.0002, "epoch": 1.6299265197060788, "step": 1220}, {"loss": 1.7631, "grad_norm": 0.35346856713294983, "learning_rate": 0.0002, "epoch": 1.6432865731462925, "step": 1230}, {"loss": 1.7225, "grad_norm": 0.41736963391304016, "learning_rate": 0.0002, "epoch": 1.6566466265865063, "step": 1240}, {"loss": 1.7582, "grad_norm": 0.3375225067138672, "learning_rate": 0.0002, "epoch": 1.6700066800267201, "step": 1250}, {"loss": 1.6916, "grad_norm": 0.3779928982257843, "learning_rate": 0.0002, "epoch": 1.6833667334669338, "step": 1260}, {"loss": 1.728, "grad_norm": 0.35388994216918945, "learning_rate": 0.0002, "epoch": 1.6967267869071476, "step": 1270}, {"loss": 1.7461, "grad_norm": 0.33884134888648987, "learning_rate": 0.0002, "epoch": 1.7100868403473615, "step": 1280}, {"loss": 1.7083, "grad_norm": 0.35439756512641907, "learning_rate": 0.0002, "epoch": 1.723446893787575, "step": 1290}, {"loss": 1.7389, "grad_norm": 0.3766156733036041, "learning_rate": 0.0002, "epoch": 1.736806947227789, "step": 1300}, {"loss": 1.7847, "grad_norm": 0.36148911714553833, "learning_rate": 0.0002, "epoch": 1.7501670006680028, "step": 1310}, {"loss": 1.7344, "grad_norm": 0.39687496423721313, "learning_rate": 0.0002, "epoch": 1.7635270541082164, "step": 1320}, {"loss": 1.7541, "grad_norm": 0.35639452934265137, "learning_rate": 0.0002, "epoch": 1.77688710754843, "step": 1330}, {"loss": 1.7254, "grad_norm": 0.38781628012657166, "learning_rate": 0.0002, "epoch": 1.7902471609886441, "step": 1340}, {"loss": 1.7867, "grad_norm": 0.42784637212753296, "learning_rate": 0.0002, "epoch": 1.8036072144288577, "step": 1350}, {"loss": 1.7336, "grad_norm": 0.40258511900901794, "learning_rate": 0.0002, "epoch": 1.8169672678690714, "step": 1360}, {"loss": 1.7771, "grad_norm": 0.36674195528030396, "learning_rate": 0.0002, "epoch": 1.8303273213092852, "step": 1370}, {"loss": 1.7425, "grad_norm": 0.4064558446407318, "learning_rate": 0.0002, "epoch": 1.843687374749499, "step": 1380}, {"loss": 1.7425, "grad_norm": 0.3669849932193756, "learning_rate": 0.0002, "epoch": 1.8570474281897127, "step": 1390}, {"loss": 1.7924, "grad_norm": 0.37569567561149597, "learning_rate": 0.0002, "epoch": 1.8704074816299265, "step": 1400}, {"loss": 1.7885, "grad_norm": 0.37307995557785034, "learning_rate": 0.0002, "epoch": 1.8837675350701404, "step": 1410}, {"loss": 1.7548, "grad_norm": 0.3772695064544678, "learning_rate": 0.0002, "epoch": 1.897127588510354, "step": 1420}, {"loss": 1.7682, "grad_norm": 0.36993589997291565, "learning_rate": 0.0002, "epoch": 1.9104876419505676, "step": 1430}, {"loss": 1.7249, "grad_norm": 0.3490557372570038, "learning_rate": 0.0002, "epoch": 1.9238476953907817, "step": 1440}, {"loss": 1.7979, "grad_norm": 0.3716149628162384, "learning_rate": 0.0002, "epoch": 1.9372077488309953, "step": 1450}, {"loss": 1.6664, "grad_norm": 0.39236098527908325, "learning_rate": 0.0002, "epoch": 1.950567802271209, "step": 1460}, {"loss": 1.6852, "grad_norm": 0.37258651852607727, "learning_rate": 0.0002, "epoch": 1.9639278557114228, "step": 1470}, {"loss": 1.7427, "grad_norm": 0.36183077096939087, "learning_rate": 0.0002, "epoch": 1.9772879091516367, "step": 1480}, {"loss": 1.7055, "grad_norm": 0.3956947326660156, "learning_rate": 0.0002, "epoch": 1.9906479625918503, "step": 1490}, {"eval_loss": 1.8132041692733765, "eval_runtime": 38.6287, "eval_samples_per_second": 13.332, "eval_steps_per_second": 1.683, "epoch": 2.0, "step": 1497}, {"loss": 1.6791, "grad_norm": 0.34480565786361694, "learning_rate": 0.0002, "epoch": 2.004008016032064, "step": 1500}, {"loss": 1.6367, "grad_norm": 0.3418028652667999, "learning_rate": 0.0002, "epoch": 2.017368069472278, "step": 1510}, {"loss": 1.5827, "grad_norm": 0.4514467716217041, "learning_rate": 0.0002, "epoch": 2.0307281229124916, "step": 1520}, {"loss": 1.6365, "grad_norm": 0.4197506606578827, "learning_rate": 0.0002, "epoch": 2.0440881763527052, "step": 1530}, {"loss": 1.6221, "grad_norm": 0.4134170711040497, "learning_rate": 0.0002, "epoch": 2.0574482297929193, "step": 1540}, {"loss": 1.6876, "grad_norm": 0.43709826469421387, "learning_rate": 0.0002, "epoch": 2.070808283233133, "step": 1550}, {"loss": 1.5779, "grad_norm": 0.4703378677368164, "learning_rate": 0.0002, "epoch": 2.0841683366733466, "step": 1560}, {"loss": 1.599, "grad_norm": 0.4538188576698303, "learning_rate": 0.0002, "epoch": 2.0975283901135606, "step": 1570}, {"loss": 1.6464, "grad_norm": 0.4649668037891388, "learning_rate": 0.0002, "epoch": 2.1108884435537743, "step": 1580}, {"loss": 1.6348, "grad_norm": 0.42669883370399475, "learning_rate": 0.0002, "epoch": 2.124248496993988, "step": 1590}, {"loss": 1.5838, "grad_norm": 0.43162038922309875, "learning_rate": 0.0002, "epoch": 2.1376085504342015, "step": 1600}, {"loss": 1.6673, "grad_norm": 0.4294586479663849, "learning_rate": 0.0002, "epoch": 2.1509686038744156, "step": 1610}, {"loss": 1.6024, "grad_norm": 0.4669102132320404, "learning_rate": 0.0002, "epoch": 2.164328657314629, "step": 1620}, {"loss": 1.659, "grad_norm": 0.4188412129878998, "learning_rate": 0.0002, "epoch": 2.177688710754843, "step": 1630}, {"loss": 1.625, "grad_norm": 0.4662680923938751, "learning_rate": 0.0002, "epoch": 2.191048764195057, "step": 1640}, {"loss": 1.6699, "grad_norm": 0.4020286500453949, "learning_rate": 0.0002, "epoch": 2.2044088176352705, "step": 1650}, {"loss": 1.6284, "grad_norm": 0.41919606924057007, "learning_rate": 0.0002, "epoch": 2.217768871075484, "step": 1660}, {"loss": 1.6776, "grad_norm": 0.4644531309604645, "learning_rate": 0.0002, "epoch": 2.231128924515698, "step": 1670}, {"loss": 1.6711, "grad_norm": 0.4526427984237671, "learning_rate": 0.0002, "epoch": 2.244488977955912, "step": 1680}, {"loss": 1.6058, "grad_norm": 0.45953166484832764, "learning_rate": 0.0002, "epoch": 2.2578490313961255, "step": 1690}, {"loss": 1.5979, "grad_norm": 0.4701860249042511, "learning_rate": 0.0002, "epoch": 2.2712090848363395, "step": 1700}, {"loss": 1.6183, "grad_norm": 0.4749310612678528, "learning_rate": 0.0002, "epoch": 2.284569138276553, "step": 1710}, {"loss": 1.6703, "grad_norm": 0.45026102662086487, "learning_rate": 0.0002, "epoch": 2.297929191716767, "step": 1720}, {"loss": 1.6386, "grad_norm": 0.4755004048347473, "learning_rate": 0.0002, "epoch": 2.3112892451569804, "step": 1730}, {"loss": 1.6365, "grad_norm": 0.4505726993083954, "learning_rate": 0.0002, "epoch": 2.3246492985971945, "step": 1740}, {"loss": 1.589, "grad_norm": 0.44464054703712463, "learning_rate": 0.0002, "epoch": 2.338009352037408, "step": 1750}, {"loss": 1.6139, "grad_norm": 0.4449476897716522, "learning_rate": 0.0002, "epoch": 2.3513694054776217, "step": 1760}, {"loss": 1.7195, "grad_norm": 0.4216482937335968, "learning_rate": 0.0002, "epoch": 2.364729458917836, "step": 1770}, {"loss": 1.7075, "grad_norm": 0.4379308521747589, "learning_rate": 0.0002, "epoch": 2.3780895123580494, "step": 1780}, {"loss": 1.7024, "grad_norm": 0.41670042276382446, "learning_rate": 0.0002, "epoch": 2.391449565798263, "step": 1790}, {"loss": 1.5989, "grad_norm": 0.48089510202407837, "learning_rate": 0.0002, "epoch": 2.404809619238477, "step": 1800}, {"loss": 1.6313, "grad_norm": 0.4389738142490387, "learning_rate": 0.0002, "epoch": 2.4181696726786908, "step": 1810}, {"loss": 1.5841, "grad_norm": 0.45293036103248596, "learning_rate": 0.0002, "epoch": 2.4315297261189044, "step": 1820}, {"loss": 1.6887, "grad_norm": 0.5211683511734009, "learning_rate": 0.0002, "epoch": 2.4448897795591185, "step": 1830}, {"loss": 1.6599, "grad_norm": 0.4631884694099426, "learning_rate": 0.0002, "epoch": 2.458249832999332, "step": 1840}, {"loss": 1.6537, "grad_norm": 0.4276818335056305, "learning_rate": 0.0002, "epoch": 2.4716098864395457, "step": 1850}, {"loss": 1.6836, "grad_norm": 0.477524071931839, "learning_rate": 0.0002, "epoch": 2.4849699398797593, "step": 1860}, {"loss": 1.66, "grad_norm": 0.44860973954200745, "learning_rate": 0.0002, "epoch": 2.4983299933199734, "step": 1870}, {"loss": 1.6308, "grad_norm": 0.46413546800613403, "learning_rate": 0.0002, "epoch": 2.511690046760187, "step": 1880}, {"loss": 1.6225, "grad_norm": 0.42487645149230957, "learning_rate": 0.0002, "epoch": 2.5250501002004007, "step": 1890}, {"loss": 1.6268, "grad_norm": 0.4778307378292084, "learning_rate": 0.0002, "epoch": 2.5384101536406147, "step": 1900}, {"loss": 1.6143, "grad_norm": 0.45307061076164246, "learning_rate": 0.0002, "epoch": 2.5517702070808284, "step": 1910}, {"loss": 1.7279, "grad_norm": 0.47886642813682556, "learning_rate": 0.0002, "epoch": 2.565130260521042, "step": 1920}, {"loss": 1.5931, "grad_norm": 0.4839435815811157, "learning_rate": 0.0002, "epoch": 2.5784903139612556, "step": 1930}, {"loss": 1.6089, "grad_norm": 0.4388359785079956, "learning_rate": 0.0002, "epoch": 2.5918503674014697, "step": 1940}, {"loss": 1.6828, "grad_norm": 0.47859734296798706, "learning_rate": 0.0002, "epoch": 2.6052104208416833, "step": 1950}, {"loss": 1.6014, "grad_norm": 0.5526517033576965, "learning_rate": 0.0002, "epoch": 2.6185704742818974, "step": 1960}, {"loss": 1.6889, "grad_norm": 0.5449170470237732, "learning_rate": 0.0002, "epoch": 2.631930527722111, "step": 1970}, {"loss": 1.6481, "grad_norm": 0.48521968722343445, "learning_rate": 0.0002, "epoch": 2.6452905811623246, "step": 1980}, {"loss": 1.6741, "grad_norm": 0.4733737111091614, "learning_rate": 0.0002, "epoch": 2.6586506346025383, "step": 1990}, {"loss": 1.662, "grad_norm": 0.507118284702301, "learning_rate": 0.0002, "epoch": 2.6720106880427523, "step": 2000}, {"loss": 1.6419, "grad_norm": 0.4508971571922302, "learning_rate": 0.0002, "epoch": 2.685370741482966, "step": 2010}, {"loss": 1.7052, "grad_norm": 0.4657728672027588, "learning_rate": 0.0002, "epoch": 2.6987307949231796, "step": 2020}, {"loss": 1.6261, "grad_norm": 0.48647549748420715, "learning_rate": 0.0002, "epoch": 2.7120908483633936, "step": 2030}, {"loss": 1.5638, "grad_norm": 0.49525555968284607, "learning_rate": 0.0002, "epoch": 2.7254509018036073, "step": 2040}, {"loss": 1.658, "grad_norm": 0.4712379276752472, "learning_rate": 0.0002, "epoch": 2.738810955243821, "step": 2050}, {"loss": 1.6464, "grad_norm": 0.4846591055393219, "learning_rate": 0.0002, "epoch": 2.7521710086840345, "step": 2060}, {"loss": 1.5641, "grad_norm": 0.4823240041732788, "learning_rate": 0.0002, "epoch": 2.7655310621242486, "step": 2070}, {"loss": 1.6701, "grad_norm": 0.4546685516834259, "learning_rate": 0.0002, "epoch": 2.778891115564462, "step": 2080}, {"loss": 1.7015, "grad_norm": 0.45542681217193604, "learning_rate": 0.0002, "epoch": 2.7922511690046763, "step": 2090}, {"loss": 1.6398, "grad_norm": 0.42137566208839417, "learning_rate": 0.0002, "epoch": 2.80561122244489, "step": 2100}, {"loss": 1.6526, "grad_norm": 0.6143282055854797, "learning_rate": 0.0002, "epoch": 2.8189712758851035, "step": 2110}, {"loss": 1.6955, "grad_norm": 0.4828081727027893, "learning_rate": 0.0002, "epoch": 2.832331329325317, "step": 2120}, {"loss": 1.744, "grad_norm": 0.4319005608558655, "learning_rate": 0.0002, "epoch": 2.845691382765531, "step": 2130}, {"loss": 1.6717, "grad_norm": 0.4297086298465729, "learning_rate": 0.0002, "epoch": 2.859051436205745, "step": 2140}, {"loss": 1.5968, "grad_norm": 0.5011981129646301, "learning_rate": 0.0002, "epoch": 2.8724114896459585, "step": 2150}, {"loss": 1.7181, "grad_norm": 0.4401548504829407, "learning_rate": 0.0002, "epoch": 2.8857715430861726, "step": 2160}, {"loss": 1.5722, "grad_norm": 0.48090746998786926, "learning_rate": 0.0002, "epoch": 2.899131596526386, "step": 2170}, {"loss": 1.6596, "grad_norm": 0.4740385413169861, "learning_rate": 0.0002, "epoch": 2.9124916499666, "step": 2180}, {"loss": 1.6501, "grad_norm": 0.5337260365486145, "learning_rate": 0.0002, "epoch": 2.9258517034068134, "step": 2190}, {"loss": 1.6802, "grad_norm": 0.4420052766799927, "learning_rate": 0.0002, "epoch": 2.9392117568470275, "step": 2200}, {"loss": 1.5474, "grad_norm": 0.477512389421463, "learning_rate": 0.0002, "epoch": 2.952571810287241, "step": 2210}, {"loss": 1.6544, "grad_norm": 0.5344052910804749, "learning_rate": 0.0002, "epoch": 2.9659318637274548, "step": 2220}, {"loss": 1.6866, "grad_norm": 0.4483940303325653, "learning_rate": 0.0002, "epoch": 2.979291917167669, "step": 2230}, {"loss": 1.6477, "grad_norm": 0.4366597831249237, "learning_rate": 0.0002, "epoch": 2.9926519706078825, "step": 2240}]}
+{"epoch": 4.0, "step": 2994, "epoch_duration": 823.2370874881744, "total_accumulated_duration": 3305.724505186081, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7568.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.6569, "grad_norm": 0.5097216367721558, "learning_rate": 0.0002, "epoch": 0.013360053440213761, "step": 10}, {"loss": 2.2557, "grad_norm": 0.5924790501594543, "learning_rate": 0.0002, "epoch": 0.026720106880427523, "step": 20}, {"loss": 2.0626, "grad_norm": 0.5158102512359619, "learning_rate": 0.0002, "epoch": 0.04008016032064128, "step": 30}, {"loss": 1.9452, "grad_norm": 0.5033753514289856, "learning_rate": 0.0002, "epoch": 0.053440213760855046, "step": 40}, {"loss": 1.9128, "grad_norm": 0.5390949845314026, "learning_rate": 0.0002, "epoch": 0.06680026720106881, "step": 50}, {"loss": 1.937, "grad_norm": 0.6376217007637024, "learning_rate": 0.0002, "epoch": 0.08016032064128256, "step": 60}, {"loss": 1.929, "grad_norm": 0.4202035069465637, "learning_rate": 0.0002, "epoch": 0.09352037408149633, "step": 70}, {"loss": 1.811, "grad_norm": 0.4269474744796753, "learning_rate": 0.0002, "epoch": 0.10688042752171009, "step": 80}, {"loss": 1.8303, "grad_norm": 0.4306574761867523, "learning_rate": 0.0002, "epoch": 0.12024048096192384, "step": 90}, {"loss": 1.8469, "grad_norm": 0.5297011137008667, "learning_rate": 0.0002, "epoch": 0.13360053440213762, "step": 100}, {"loss": 1.864, "grad_norm": 1.2313778400421143, "learning_rate": 0.0002, "epoch": 0.14696058784235136, "step": 110}, {"loss": 1.8531, "grad_norm": 0.5351294279098511, "learning_rate": 0.0002, "epoch": 0.16032064128256512, "step": 120}, {"loss": 1.9232, "grad_norm": 0.4848092496395111, "learning_rate": 0.0002, "epoch": 0.1736806947227789, "step": 130}, {"loss": 1.8633, "grad_norm": 0.4339500665664673, "learning_rate": 0.0002, "epoch": 0.18704074816299265, "step": 140}, {"loss": 1.816, "grad_norm": 0.46877285838127136, "learning_rate": 0.0002, "epoch": 0.20040080160320642, "step": 150}, {"loss": 1.8033, "grad_norm": 0.5600412487983704, "learning_rate": 0.0002, "epoch": 0.21376085504342018, "step": 160}, {"loss": 1.8162, "grad_norm": 0.3733620345592499, "learning_rate": 0.0002, "epoch": 0.22712090848363392, "step": 170}, {"loss": 1.8564, "grad_norm": 0.5116042494773865, "learning_rate": 0.0002, "epoch": 0.24048096192384769, "step": 180}, {"loss": 1.915, "grad_norm": 0.4071602523326874, "learning_rate": 0.0002, "epoch": 0.25384101536406145, "step": 190}, {"loss": 1.7984, "grad_norm": 0.44189608097076416, "learning_rate": 0.0002, "epoch": 0.26720106880427524, "step": 200}, {"loss": 1.8728, "grad_norm": 0.398699015378952, "learning_rate": 0.0002, "epoch": 0.280561122244489, "step": 210}, {"loss": 1.8205, "grad_norm": 0.3585626482963562, "learning_rate": 0.0002, "epoch": 0.2939211756847027, "step": 220}, {"loss": 1.8861, "grad_norm": 0.3811776041984558, "learning_rate": 0.0002, "epoch": 0.3072812291249165, "step": 230}, {"loss": 1.8365, "grad_norm": 0.37261509895324707, "learning_rate": 0.0002, "epoch": 0.32064128256513025, "step": 240}, {"loss": 1.9186, "grad_norm": 0.39762404561042786, "learning_rate": 0.0002, "epoch": 0.33400133600534404, "step": 250}, {"loss": 1.7965, "grad_norm": 0.3509528934955597, "learning_rate": 0.0002, "epoch": 0.3473613894455578, "step": 260}, {"loss": 1.7802, "grad_norm": 0.3169104754924774, "learning_rate": 0.0002, "epoch": 0.36072144288577157, "step": 270}, {"loss": 1.8038, "grad_norm": 0.33714795112609863, "learning_rate": 0.0002, "epoch": 0.3740814963259853, "step": 280}, {"loss": 1.787, "grad_norm": 1.2936875820159912, "learning_rate": 0.0002, "epoch": 0.38744154976619904, "step": 290}, {"loss": 1.7974, "grad_norm": 0.3459427058696747, "learning_rate": 0.0002, "epoch": 0.40080160320641284, "step": 300}, {"loss": 1.8879, "grad_norm": 0.3380655348300934, "learning_rate": 0.0002, "epoch": 0.4141616566466266, "step": 310}, {"loss": 1.9196, "grad_norm": 0.3890381455421448, "learning_rate": 0.0002, "epoch": 0.42752171008684037, "step": 320}, {"loss": 1.8034, "grad_norm": 0.432327002286911, "learning_rate": 0.0002, "epoch": 0.4408817635270541, "step": 330}, {"loss": 1.8443, "grad_norm": 0.3736560046672821, "learning_rate": 0.0002, "epoch": 0.45424181696726784, "step": 340}, {"loss": 1.8506, "grad_norm": 0.3700982630252838, "learning_rate": 0.0002, "epoch": 0.46760187040748163, "step": 350}, {"loss": 1.7978, "grad_norm": 0.4533902406692505, "learning_rate": 0.0002, "epoch": 0.48096192384769537, "step": 360}, {"loss": 1.7427, "grad_norm": 0.35999053716659546, "learning_rate": 0.0002, "epoch": 0.49432197728790916, "step": 370}, {"loss": 1.7995, "grad_norm": 0.3490903675556183, "learning_rate": 0.0002, "epoch": 0.5076820307281229, "step": 380}, {"loss": 1.8709, "grad_norm": 0.34704291820526123, "learning_rate": 0.0002, "epoch": 0.5210420841683366, "step": 390}, {"loss": 1.7948, "grad_norm": 0.343565434217453, "learning_rate": 0.0002, "epoch": 0.5344021376085505, "step": 400}, {"loss": 1.8564, "grad_norm": 0.3573552966117859, "learning_rate": 0.0002, "epoch": 0.5477621910487642, "step": 410}, {"loss": 1.8477, "grad_norm": 0.32980719208717346, "learning_rate": 0.0002, "epoch": 0.561122244488978, "step": 420}, {"loss": 1.9233, "grad_norm": 0.356952428817749, "learning_rate": 0.0002, "epoch": 0.5744822979291917, "step": 430}, {"loss": 1.7433, "grad_norm": 0.3170869052410126, "learning_rate": 0.0002, "epoch": 0.5878423513694054, "step": 440}, {"loss": 1.7607, "grad_norm": 0.35233718156814575, "learning_rate": 0.0002, "epoch": 0.6012024048096193, "step": 450}, {"loss": 1.8111, "grad_norm": 0.3480125367641449, "learning_rate": 0.0002, "epoch": 0.614562458249833, "step": 460}, {"loss": 1.8386, "grad_norm": 0.4762810468673706, "learning_rate": 0.0002, "epoch": 0.6279225116900468, "step": 470}, {"loss": 1.805, "grad_norm": 0.3907663822174072, "learning_rate": 0.0002, "epoch": 0.6412825651302605, "step": 480}, {"loss": 1.8113, "grad_norm": 0.36315613985061646, "learning_rate": 0.0002, "epoch": 0.6546426185704742, "step": 490}, {"loss": 1.7805, "grad_norm": 0.377796471118927, "learning_rate": 0.0002, "epoch": 0.6680026720106881, "step": 500}, {"loss": 1.7457, "grad_norm": 0.34284207224845886, "learning_rate": 0.0002, "epoch": 0.6813627254509018, "step": 510}, {"loss": 1.8013, "grad_norm": 0.35563018918037415, "learning_rate": 0.0002, "epoch": 0.6947227788911156, "step": 520}, {"loss": 1.8414, "grad_norm": 0.37575867772102356, "learning_rate": 0.0002, "epoch": 0.7080828323313293, "step": 530}, {"loss": 1.7993, "grad_norm": 0.35719701647758484, "learning_rate": 0.0002, "epoch": 0.7214428857715431, "step": 540}, {"loss": 1.7574, "grad_norm": 0.385813444852829, "learning_rate": 0.0002, "epoch": 0.7348029392117569, "step": 550}, {"loss": 1.7985, "grad_norm": 0.44509607553482056, "learning_rate": 0.0002, "epoch": 0.7481629926519706, "step": 560}, {"loss": 1.7459, "grad_norm": 0.36108464002609253, "learning_rate": 0.0002, "epoch": 0.7615230460921844, "step": 570}, {"loss": 1.8207, "grad_norm": 0.3530745804309845, "learning_rate": 0.0002, "epoch": 0.7748830995323981, "step": 580}, {"loss": 1.7479, "grad_norm": 0.34888574481010437, "learning_rate": 0.0002, "epoch": 0.7882431529726119, "step": 590}, {"loss": 1.8656, "grad_norm": 0.387346476316452, "learning_rate": 0.0002, "epoch": 0.8016032064128257, "step": 600}, {"loss": 1.8071, "grad_norm": 0.3641138970851898, "learning_rate": 0.0002, "epoch": 0.8149632598530394, "step": 610}, {"loss": 1.7531, "grad_norm": 0.33729103207588196, "learning_rate": 0.0002, "epoch": 0.8283233132932531, "step": 620}, {"loss": 1.8613, "grad_norm": 0.3652004599571228, "learning_rate": 0.0002, "epoch": 0.8416833667334669, "step": 630}, {"loss": 1.9184, "grad_norm": 0.3986643850803375, "learning_rate": 0.0002, "epoch": 0.8550434201736807, "step": 640}, {"loss": 1.8198, "grad_norm": 0.3458964228630066, "learning_rate": 0.0002, "epoch": 0.8684034736138945, "step": 650}, {"loss": 1.803, "grad_norm": 0.3559381365776062, "learning_rate": 0.0002, "epoch": 0.8817635270541082, "step": 660}, {"loss": 1.7641, "grad_norm": 0.3612841069698334, "learning_rate": 0.0002, "epoch": 0.895123580494322, "step": 670}, {"loss": 1.7888, "grad_norm": 0.34771719574928284, "learning_rate": 0.0002, "epoch": 0.9084836339345357, "step": 680}, {"loss": 1.8204, "grad_norm": 0.3371497094631195, "learning_rate": 0.0002, "epoch": 0.9218436873747495, "step": 690}, {"loss": 1.7848, "grad_norm": 0.5596055388450623, "learning_rate": 0.0002, "epoch": 0.9352037408149633, "step": 700}, {"loss": 1.7794, "grad_norm": 0.311880499124527, "learning_rate": 0.0002, "epoch": 0.948563794255177, "step": 710}, {"loss": 1.8464, "grad_norm": 0.3462068736553192, "learning_rate": 0.0002, "epoch": 0.9619238476953907, "step": 720}, {"loss": 1.8197, "grad_norm": 0.29982393980026245, "learning_rate": 0.0002, "epoch": 0.9752839011356046, "step": 730}, {"loss": 1.8503, "grad_norm": 0.34606459736824036, "learning_rate": 0.0002, "epoch": 0.9886439545758183, "step": 740}, {"eval_loss": 1.8201380968093872, "eval_runtime": 38.6124, "eval_samples_per_second": 13.338, "eval_steps_per_second": 1.683, "epoch": 0.9993319973279893, "step": 748}, {"loss": 1.7786, "grad_norm": 0.32302048802375793, "learning_rate": 0.0002, "epoch": 1.002004008016032, "step": 750}, {"loss": 1.7297, "grad_norm": 0.37585633993148804, "learning_rate": 0.0002, "epoch": 1.0153640614562458, "step": 760}, {"loss": 1.7008, "grad_norm": 0.33826273679733276, "learning_rate": 0.0002, "epoch": 1.0287241148964597, "step": 770}, {"loss": 1.809, "grad_norm": 0.44682955741882324, "learning_rate": 0.0002, "epoch": 1.0420841683366733, "step": 780}, {"loss": 1.7092, "grad_norm": 0.422188401222229, "learning_rate": 0.0002, "epoch": 1.0554442217768871, "step": 790}, {"loss": 1.7765, "grad_norm": 0.3809906244277954, "learning_rate": 0.0002, "epoch": 1.0688042752171008, "step": 800}, {"loss": 1.7431, "grad_norm": 0.3454349637031555, "learning_rate": 0.0002, "epoch": 1.0821643286573146, "step": 810}, {"loss": 1.7257, "grad_norm": 0.3767355978488922, "learning_rate": 0.0002, "epoch": 1.0955243820975284, "step": 820}, {"loss": 1.7224, "grad_norm": 0.3361407518386841, "learning_rate": 0.0002, "epoch": 1.108884435537742, "step": 830}, {"loss": 1.7509, "grad_norm": 0.3654632568359375, "learning_rate": 0.0002, "epoch": 1.122244488977956, "step": 840}, {"loss": 1.7151, "grad_norm": 0.3822861313819885, "learning_rate": 0.0002, "epoch": 1.1356045424181698, "step": 850}, {"loss": 1.7121, "grad_norm": 0.3853831887245178, "learning_rate": 0.0002, "epoch": 1.1489645958583834, "step": 860}, {"loss": 1.7685, "grad_norm": 0.35521796345710754, "learning_rate": 0.0002, "epoch": 1.1623246492985972, "step": 870}, {"loss": 1.7735, "grad_norm": 0.4107200503349304, "learning_rate": 0.0002, "epoch": 1.1756847027388109, "step": 880}, {"loss": 1.7484, "grad_norm": 0.33219534158706665, "learning_rate": 0.0002, "epoch": 1.1890447561790247, "step": 890}, {"loss": 1.7071, "grad_norm": 0.3559704124927521, "learning_rate": 0.0002, "epoch": 1.2024048096192386, "step": 900}, {"loss": 1.7535, "grad_norm": 0.3700537383556366, "learning_rate": 0.0002, "epoch": 1.2157648630594522, "step": 910}, {"loss": 1.7513, "grad_norm": 0.3771909475326538, "learning_rate": 0.0002, "epoch": 1.229124916499666, "step": 920}, {"loss": 1.7566, "grad_norm": 0.3136613965034485, "learning_rate": 0.0002, "epoch": 1.2424849699398797, "step": 930}, {"loss": 1.6783, "grad_norm": 0.3952099084854126, "learning_rate": 0.0002, "epoch": 1.2558450233800935, "step": 940}, {"loss": 1.7691, "grad_norm": 0.36534377932548523, "learning_rate": 0.0002, "epoch": 1.2692050768203074, "step": 950}, {"loss": 1.7127, "grad_norm": 0.3803492486476898, "learning_rate": 0.0002, "epoch": 1.282565130260521, "step": 960}, {"loss": 1.7896, "grad_norm": 0.3992428183555603, "learning_rate": 0.0002, "epoch": 1.2959251837007348, "step": 970}, {"loss": 1.7343, "grad_norm": 0.3627142906188965, "learning_rate": 0.0002, "epoch": 1.3092852371409487, "step": 980}, {"loss": 1.7598, "grad_norm": 0.4248180091381073, "learning_rate": 0.0002, "epoch": 1.3226452905811623, "step": 990}, {"loss": 1.6896, "grad_norm": 0.4060308039188385, "learning_rate": 0.0002, "epoch": 1.3360053440213762, "step": 1000}, {"loss": 1.7457, "grad_norm": 0.3788969814777374, "learning_rate": 0.0002, "epoch": 1.3493653974615898, "step": 1010}, {"loss": 1.7111, "grad_norm": 0.4174270033836365, "learning_rate": 0.0002, "epoch": 1.3627254509018036, "step": 1020}, {"loss": 1.7975, "grad_norm": 0.35500675439834595, "learning_rate": 0.0002, "epoch": 1.3760855043420173, "step": 1030}, {"loss": 1.724, "grad_norm": 0.3454059362411499, "learning_rate": 0.0002, "epoch": 1.389445557782231, "step": 1040}, {"loss": 1.8299, "grad_norm": 0.45807570219039917, "learning_rate": 0.0002, "epoch": 1.402805611222445, "step": 1050}, {"loss": 1.7425, "grad_norm": 0.39338022470474243, "learning_rate": 0.0002, "epoch": 1.4161656646626586, "step": 1060}, {"loss": 1.7457, "grad_norm": 0.3870709240436554, "learning_rate": 0.0002, "epoch": 1.4295257181028724, "step": 1070}, {"loss": 1.6565, "grad_norm": 0.40996190905570984, "learning_rate": 0.0002, "epoch": 1.4428857715430863, "step": 1080}, {"loss": 1.7324, "grad_norm": 0.38762837648391724, "learning_rate": 0.0002, "epoch": 1.4562458249833, "step": 1090}, {"loss": 1.7362, "grad_norm": 0.36756977438926697, "learning_rate": 0.0002, "epoch": 1.4696058784235138, "step": 1100}, {"loss": 1.7451, "grad_norm": 0.4087235927581787, "learning_rate": 0.0002, "epoch": 1.4829659318637274, "step": 1110}, {"loss": 1.7114, "grad_norm": 0.3357745110988617, "learning_rate": 0.0002, "epoch": 1.4963259853039412, "step": 1120}, {"loss": 1.6877, "grad_norm": 0.37486532330513, "learning_rate": 0.0002, "epoch": 1.5096860387441549, "step": 1130}, {"loss": 1.7252, "grad_norm": 0.3387809991836548, "learning_rate": 0.0002, "epoch": 1.5230460921843687, "step": 1140}, {"loss": 1.7169, "grad_norm": 0.37462118268013, "learning_rate": 0.0002, "epoch": 1.5364061456245826, "step": 1150}, {"loss": 1.6988, "grad_norm": 0.38575324416160583, "learning_rate": 0.0002, "epoch": 1.5497661990647962, "step": 1160}, {"loss": 1.7438, "grad_norm": 0.3515765964984894, "learning_rate": 0.0002, "epoch": 1.56312625250501, "step": 1170}, {"loss": 1.7524, "grad_norm": 0.39308643341064453, "learning_rate": 0.0002, "epoch": 1.5764863059452239, "step": 1180}, {"loss": 1.6422, "grad_norm": 0.3308864235877991, "learning_rate": 0.0002, "epoch": 1.5898463593854375, "step": 1190}, {"loss": 1.7566, "grad_norm": 0.3397478461265564, "learning_rate": 0.0002, "epoch": 1.6032064128256514, "step": 1200}, {"loss": 1.7871, "grad_norm": 0.3911525309085846, "learning_rate": 0.0002, "epoch": 1.6165664662658652, "step": 1210}, {"loss": 1.7443, "grad_norm": 0.3771969974040985, "learning_rate": 0.0002, "epoch": 1.6299265197060788, "step": 1220}, {"loss": 1.7631, "grad_norm": 0.35346856713294983, "learning_rate": 0.0002, "epoch": 1.6432865731462925, "step": 1230}, {"loss": 1.7225, "grad_norm": 0.41736963391304016, "learning_rate": 0.0002, "epoch": 1.6566466265865063, "step": 1240}, {"loss": 1.7582, "grad_norm": 0.3375225067138672, "learning_rate": 0.0002, "epoch": 1.6700066800267201, "step": 1250}, {"loss": 1.6916, "grad_norm": 0.3779928982257843, "learning_rate": 0.0002, "epoch": 1.6833667334669338, "step": 1260}, {"loss": 1.728, "grad_norm": 0.35388994216918945, "learning_rate": 0.0002, "epoch": 1.6967267869071476, "step": 1270}, {"loss": 1.7461, "grad_norm": 0.33884134888648987, "learning_rate": 0.0002, "epoch": 1.7100868403473615, "step": 1280}, {"loss": 1.7083, "grad_norm": 0.35439756512641907, "learning_rate": 0.0002, "epoch": 1.723446893787575, "step": 1290}, {"loss": 1.7389, "grad_norm": 0.3766156733036041, "learning_rate": 0.0002, "epoch": 1.736806947227789, "step": 1300}, {"loss": 1.7847, "grad_norm": 0.36148911714553833, "learning_rate": 0.0002, "epoch": 1.7501670006680028, "step": 1310}, {"loss": 1.7344, "grad_norm": 0.39687496423721313, "learning_rate": 0.0002, "epoch": 1.7635270541082164, "step": 1320}, {"loss": 1.7541, "grad_norm": 0.35639452934265137, "learning_rate": 0.0002, "epoch": 1.77688710754843, "step": 1330}, {"loss": 1.7254, "grad_norm": 0.38781628012657166, "learning_rate": 0.0002, "epoch": 1.7902471609886441, "step": 1340}, {"loss": 1.7867, "grad_norm": 0.42784637212753296, "learning_rate": 0.0002, "epoch": 1.8036072144288577, "step": 1350}, {"loss": 1.7336, "grad_norm": 0.40258511900901794, "learning_rate": 0.0002, "epoch": 1.8169672678690714, "step": 1360}, {"loss": 1.7771, "grad_norm": 0.36674195528030396, "learning_rate": 0.0002, "epoch": 1.8303273213092852, "step": 1370}, {"loss": 1.7425, "grad_norm": 0.4064558446407318, "learning_rate": 0.0002, "epoch": 1.843687374749499, "step": 1380}, {"loss": 1.7425, "grad_norm": 0.3669849932193756, "learning_rate": 0.0002, "epoch": 1.8570474281897127, "step": 1390}, {"loss": 1.7924, "grad_norm": 0.37569567561149597, "learning_rate": 0.0002, "epoch": 1.8704074816299265, "step": 1400}, {"loss": 1.7885, "grad_norm": 0.37307995557785034, "learning_rate": 0.0002, "epoch": 1.8837675350701404, "step": 1410}, {"loss": 1.7548, "grad_norm": 0.3772695064544678, "learning_rate": 0.0002, "epoch": 1.897127588510354, "step": 1420}, {"loss": 1.7682, "grad_norm": 0.36993589997291565, "learning_rate": 0.0002, "epoch": 1.9104876419505676, "step": 1430}, {"loss": 1.7249, "grad_norm": 0.3490557372570038, "learning_rate": 0.0002, "epoch": 1.9238476953907817, "step": 1440}, {"loss": 1.7979, "grad_norm": 0.3716149628162384, "learning_rate": 0.0002, "epoch": 1.9372077488309953, "step": 1450}, {"loss": 1.6664, "grad_norm": 0.39236098527908325, "learning_rate": 0.0002, "epoch": 1.950567802271209, "step": 1460}, {"loss": 1.6852, "grad_norm": 0.37258651852607727, "learning_rate": 0.0002, "epoch": 1.9639278557114228, "step": 1470}, {"loss": 1.7427, "grad_norm": 0.36183077096939087, "learning_rate": 0.0002, "epoch": 1.9772879091516367, "step": 1480}, {"loss": 1.7055, "grad_norm": 0.3956947326660156, "learning_rate": 0.0002, "epoch": 1.9906479625918503, "step": 1490}, {"eval_loss": 1.8132041692733765, "eval_runtime": 38.6287, "eval_samples_per_second": 13.332, "eval_steps_per_second": 1.683, "epoch": 2.0, "step": 1497}, {"loss": 1.6791, "grad_norm": 0.34480565786361694, "learning_rate": 0.0002, "epoch": 2.004008016032064, "step": 1500}, {"loss": 1.6367, "grad_norm": 0.3418028652667999, "learning_rate": 0.0002, "epoch": 2.017368069472278, "step": 1510}, {"loss": 1.5827, "grad_norm": 0.4514467716217041, "learning_rate": 0.0002, "epoch": 2.0307281229124916, "step": 1520}, {"loss": 1.6365, "grad_norm": 0.4197506606578827, "learning_rate": 0.0002, "epoch": 2.0440881763527052, "step": 1530}, {"loss": 1.6221, "grad_norm": 0.4134170711040497, "learning_rate": 0.0002, "epoch": 2.0574482297929193, "step": 1540}, {"loss": 1.6876, "grad_norm": 0.43709826469421387, "learning_rate": 0.0002, "epoch": 2.070808283233133, "step": 1550}, {"loss": 1.5779, "grad_norm": 0.4703378677368164, "learning_rate": 0.0002, "epoch": 2.0841683366733466, "step": 1560}, {"loss": 1.599, "grad_norm": 0.4538188576698303, "learning_rate": 0.0002, "epoch": 2.0975283901135606, "step": 1570}, {"loss": 1.6464, "grad_norm": 0.4649668037891388, "learning_rate": 0.0002, "epoch": 2.1108884435537743, "step": 1580}, {"loss": 1.6348, "grad_norm": 0.42669883370399475, "learning_rate": 0.0002, "epoch": 2.124248496993988, "step": 1590}, {"loss": 1.5838, "grad_norm": 0.43162038922309875, "learning_rate": 0.0002, "epoch": 2.1376085504342015, "step": 1600}, {"loss": 1.6673, "grad_norm": 0.4294586479663849, "learning_rate": 0.0002, "epoch": 2.1509686038744156, "step": 1610}, {"loss": 1.6024, "grad_norm": 0.4669102132320404, "learning_rate": 0.0002, "epoch": 2.164328657314629, "step": 1620}, {"loss": 1.659, "grad_norm": 0.4188412129878998, "learning_rate": 0.0002, "epoch": 2.177688710754843, "step": 1630}, {"loss": 1.625, "grad_norm": 0.4662680923938751, "learning_rate": 0.0002, "epoch": 2.191048764195057, "step": 1640}, {"loss": 1.6699, "grad_norm": 0.4020286500453949, "learning_rate": 0.0002, "epoch": 2.2044088176352705, "step": 1650}, {"loss": 1.6284, "grad_norm": 0.41919606924057007, "learning_rate": 0.0002, "epoch": 2.217768871075484, "step": 1660}, {"loss": 1.6776, "grad_norm": 0.4644531309604645, "learning_rate": 0.0002, "epoch": 2.231128924515698, "step": 1670}, {"loss": 1.6711, "grad_norm": 0.4526427984237671, "learning_rate": 0.0002, "epoch": 2.244488977955912, "step": 1680}, {"loss": 1.6058, "grad_norm": 0.45953166484832764, "learning_rate": 0.0002, "epoch": 2.2578490313961255, "step": 1690}, {"loss": 1.5979, "grad_norm": 0.4701860249042511, "learning_rate": 0.0002, "epoch": 2.2712090848363395, "step": 1700}, {"loss": 1.6183, "grad_norm": 0.4749310612678528, "learning_rate": 0.0002, "epoch": 2.284569138276553, "step": 1710}, {"loss": 1.6703, "grad_norm": 0.45026102662086487, "learning_rate": 0.0002, "epoch": 2.297929191716767, "step": 1720}, {"loss": 1.6386, "grad_norm": 0.4755004048347473, "learning_rate": 0.0002, "epoch": 2.3112892451569804, "step": 1730}, {"loss": 1.6365, "grad_norm": 0.4505726993083954, "learning_rate": 0.0002, "epoch": 2.3246492985971945, "step": 1740}, {"loss": 1.589, "grad_norm": 0.44464054703712463, "learning_rate": 0.0002, "epoch": 2.338009352037408, "step": 1750}, {"loss": 1.6139, "grad_norm": 0.4449476897716522, "learning_rate": 0.0002, "epoch": 2.3513694054776217, "step": 1760}, {"loss": 1.7195, "grad_norm": 0.4216482937335968, "learning_rate": 0.0002, "epoch": 2.364729458917836, "step": 1770}, {"loss": 1.7075, "grad_norm": 0.4379308521747589, "learning_rate": 0.0002, "epoch": 2.3780895123580494, "step": 1780}, {"loss": 1.7024, "grad_norm": 0.41670042276382446, "learning_rate": 0.0002, "epoch": 2.391449565798263, "step": 1790}, {"loss": 1.5989, "grad_norm": 0.48089510202407837, "learning_rate": 0.0002, "epoch": 2.404809619238477, "step": 1800}, {"loss": 1.6313, "grad_norm": 0.4389738142490387, "learning_rate": 0.0002, "epoch": 2.4181696726786908, "step": 1810}, {"loss": 1.5841, "grad_norm": 0.45293036103248596, "learning_rate": 0.0002, "epoch": 2.4315297261189044, "step": 1820}, {"loss": 1.6887, "grad_norm": 0.5211683511734009, "learning_rate": 0.0002, "epoch": 2.4448897795591185, "step": 1830}, {"loss": 1.6599, "grad_norm": 0.4631884694099426, "learning_rate": 0.0002, "epoch": 2.458249832999332, "step": 1840}, {"loss": 1.6537, "grad_norm": 0.4276818335056305, "learning_rate": 0.0002, "epoch": 2.4716098864395457, "step": 1850}, {"loss": 1.6836, "grad_norm": 0.477524071931839, "learning_rate": 0.0002, "epoch": 2.4849699398797593, "step": 1860}, {"loss": 1.66, "grad_norm": 0.44860973954200745, "learning_rate": 0.0002, "epoch": 2.4983299933199734, "step": 1870}, {"loss": 1.6308, "grad_norm": 0.46413546800613403, "learning_rate": 0.0002, "epoch": 2.511690046760187, "step": 1880}, {"loss": 1.6225, "grad_norm": 0.42487645149230957, "learning_rate": 0.0002, "epoch": 2.5250501002004007, "step": 1890}, {"loss": 1.6268, "grad_norm": 0.4778307378292084, "learning_rate": 0.0002, "epoch": 2.5384101536406147, "step": 1900}, {"loss": 1.6143, "grad_norm": 0.45307061076164246, "learning_rate": 0.0002, "epoch": 2.5517702070808284, "step": 1910}, {"loss": 1.7279, "grad_norm": 0.47886642813682556, "learning_rate": 0.0002, "epoch": 2.565130260521042, "step": 1920}, {"loss": 1.5931, "grad_norm": 0.4839435815811157, "learning_rate": 0.0002, "epoch": 2.5784903139612556, "step": 1930}, {"loss": 1.6089, "grad_norm": 0.4388359785079956, "learning_rate": 0.0002, "epoch": 2.5918503674014697, "step": 1940}, {"loss": 1.6828, "grad_norm": 0.47859734296798706, "learning_rate": 0.0002, "epoch": 2.6052104208416833, "step": 1950}, {"loss": 1.6014, "grad_norm": 0.5526517033576965, "learning_rate": 0.0002, "epoch": 2.6185704742818974, "step": 1960}, {"loss": 1.6889, "grad_norm": 0.5449170470237732, "learning_rate": 0.0002, "epoch": 2.631930527722111, "step": 1970}, {"loss": 1.6481, "grad_norm": 0.48521968722343445, "learning_rate": 0.0002, "epoch": 2.6452905811623246, "step": 1980}, {"loss": 1.6741, "grad_norm": 0.4733737111091614, "learning_rate": 0.0002, "epoch": 2.6586506346025383, "step": 1990}, {"loss": 1.662, "grad_norm": 0.507118284702301, "learning_rate": 0.0002, "epoch": 2.6720106880427523, "step": 2000}, {"loss": 1.6419, "grad_norm": 0.4508971571922302, "learning_rate": 0.0002, "epoch": 2.685370741482966, "step": 2010}, {"loss": 1.7052, "grad_norm": 0.4657728672027588, "learning_rate": 0.0002, "epoch": 2.6987307949231796, "step": 2020}, {"loss": 1.6261, "grad_norm": 0.48647549748420715, "learning_rate": 0.0002, "epoch": 2.7120908483633936, "step": 2030}, {"loss": 1.5638, "grad_norm": 0.49525555968284607, "learning_rate": 0.0002, "epoch": 2.7254509018036073, "step": 2040}, {"loss": 1.658, "grad_norm": 0.4712379276752472, "learning_rate": 0.0002, "epoch": 2.738810955243821, "step": 2050}, {"loss": 1.6464, "grad_norm": 0.4846591055393219, "learning_rate": 0.0002, "epoch": 2.7521710086840345, "step": 2060}, {"loss": 1.5641, "grad_norm": 0.4823240041732788, "learning_rate": 0.0002, "epoch": 2.7655310621242486, "step": 2070}, {"loss": 1.6701, "grad_norm": 0.4546685516834259, "learning_rate": 0.0002, "epoch": 2.778891115564462, "step": 2080}, {"loss": 1.7015, "grad_norm": 0.45542681217193604, "learning_rate": 0.0002, "epoch": 2.7922511690046763, "step": 2090}, {"loss": 1.6398, "grad_norm": 0.42137566208839417, "learning_rate": 0.0002, "epoch": 2.80561122244489, "step": 2100}, {"loss": 1.6526, "grad_norm": 0.6143282055854797, "learning_rate": 0.0002, "epoch": 2.8189712758851035, "step": 2110}, {"loss": 1.6955, "grad_norm": 0.4828081727027893, "learning_rate": 0.0002, "epoch": 2.832331329325317, "step": 2120}, {"loss": 1.744, "grad_norm": 0.4319005608558655, "learning_rate": 0.0002, "epoch": 2.845691382765531, "step": 2130}, {"loss": 1.6717, "grad_norm": 0.4297086298465729, "learning_rate": 0.0002, "epoch": 2.859051436205745, "step": 2140}, {"loss": 1.5968, "grad_norm": 0.5011981129646301, "learning_rate": 0.0002, "epoch": 2.8724114896459585, "step": 2150}, {"loss": 1.7181, "grad_norm": 0.4401548504829407, "learning_rate": 0.0002, "epoch": 2.8857715430861726, "step": 2160}, {"loss": 1.5722, "grad_norm": 0.48090746998786926, "learning_rate": 0.0002, "epoch": 2.899131596526386, "step": 2170}, {"loss": 1.6596, "grad_norm": 0.4740385413169861, "learning_rate": 0.0002, "epoch": 2.9124916499666, "step": 2180}, {"loss": 1.6501, "grad_norm": 0.5337260365486145, "learning_rate": 0.0002, "epoch": 2.9258517034068134, "step": 2190}, {"loss": 1.6802, "grad_norm": 0.4420052766799927, "learning_rate": 0.0002, "epoch": 2.9392117568470275, "step": 2200}, {"loss": 1.5474, "grad_norm": 0.477512389421463, "learning_rate": 0.0002, "epoch": 2.952571810287241, "step": 2210}, {"loss": 1.6544, "grad_norm": 0.5344052910804749, "learning_rate": 0.0002, "epoch": 2.9659318637274548, "step": 2220}, {"loss": 1.6866, "grad_norm": 0.4483940303325653, "learning_rate": 0.0002, "epoch": 2.979291917167669, "step": 2230}, {"loss": 1.6477, "grad_norm": 0.4366597831249237, "learning_rate": 0.0002, "epoch": 2.9926519706078825, "step": 2240}, {"eval_loss": 1.834012746810913, "eval_runtime": 38.5659, "eval_samples_per_second": 13.354, "eval_steps_per_second": 1.685, "epoch": 2.9993319973279893, "step": 2245}, {"loss": 1.5582, "grad_norm": 0.428824245929718, "learning_rate": 0.0002, "epoch": 3.006012024048096, "step": 2250}, {"loss": 1.499, "grad_norm": 0.4870174825191498, "learning_rate": 0.0002, "epoch": 3.01937207748831, "step": 2260}, {"loss": 1.4872, "grad_norm": 0.4684266149997711, "learning_rate": 0.0002, "epoch": 3.032732130928524, "step": 2270}, {"loss": 1.5284, "grad_norm": 0.581604540348053, "learning_rate": 0.0002, "epoch": 3.0460921843687374, "step": 2280}, {"loss": 1.4549, "grad_norm": 0.5561677813529968, "learning_rate": 0.0002, "epoch": 3.059452237808951, "step": 2290}, {"loss": 1.4903, "grad_norm": 0.5750220417976379, "learning_rate": 0.0002, "epoch": 3.072812291249165, "step": 2300}, {"loss": 1.5903, "grad_norm": 0.5704626441001892, "learning_rate": 0.0002, "epoch": 3.0861723446893787, "step": 2310}, {"loss": 1.4292, "grad_norm": 0.6242083311080933, "learning_rate": 0.0002, "epoch": 3.0995323981295924, "step": 2320}, {"loss": 1.5092, "grad_norm": 0.5174121260643005, "learning_rate": 0.0002, "epoch": 3.1128924515698064, "step": 2330}, {"loss": 1.5106, "grad_norm": 0.5697633028030396, "learning_rate": 0.0002, "epoch": 3.12625250501002, "step": 2340}, {"loss": 1.5156, "grad_norm": 0.5969541072845459, "learning_rate": 0.0002, "epoch": 3.1396125584502337, "step": 2350}, {"loss": 1.52, "grad_norm": 0.6244304180145264, "learning_rate": 0.0002, "epoch": 3.1529726118904478, "step": 2360}, {"loss": 1.5244, "grad_norm": 0.5561705827713013, "learning_rate": 0.0002, "epoch": 3.1663326653306614, "step": 2370}, {"loss": 1.6169, "grad_norm": 0.5401188135147095, "learning_rate": 0.0002, "epoch": 3.179692718770875, "step": 2380}, {"loss": 1.5387, "grad_norm": 0.6450421810150146, "learning_rate": 0.0002, "epoch": 3.1930527722110886, "step": 2390}, {"loss": 1.4839, "grad_norm": 0.5741903185844421, "learning_rate": 0.0002, "epoch": 3.2064128256513027, "step": 2400}, {"loss": 1.5584, "grad_norm": 0.6337407231330872, "learning_rate": 0.0002, "epoch": 3.2197728790915163, "step": 2410}, {"loss": 1.5025, "grad_norm": 0.6493517160415649, "learning_rate": 0.0002, "epoch": 3.23313293253173, "step": 2420}, {"loss": 1.5168, "grad_norm": 0.6230176091194153, "learning_rate": 0.0002, "epoch": 3.246492985971944, "step": 2430}, {"loss": 1.5408, "grad_norm": 0.680704653263092, "learning_rate": 0.0002, "epoch": 3.2598530394121576, "step": 2440}, {"loss": 1.6005, "grad_norm": 0.5279417037963867, "learning_rate": 0.0002, "epoch": 3.2732130928523713, "step": 2450}, {"loss": 1.5231, "grad_norm": 0.5601515173912048, "learning_rate": 0.0002, "epoch": 3.2865731462925853, "step": 2460}, {"loss": 1.4949, "grad_norm": 0.5591090321540833, "learning_rate": 0.0002, "epoch": 3.299933199732799, "step": 2470}, {"loss": 1.5181, "grad_norm": 0.6596529483795166, "learning_rate": 0.0002, "epoch": 3.3132932531730126, "step": 2480}, {"loss": 1.5259, "grad_norm": 0.6115918755531311, "learning_rate": 0.0002, "epoch": 3.3266533066132267, "step": 2490}, {"loss": 1.5344, "grad_norm": 0.6443548202514648, "learning_rate": 0.0002, "epoch": 3.3400133600534403, "step": 2500}, {"loss": 1.5037, "grad_norm": 0.5504242181777954, "learning_rate": 0.0002, "epoch": 3.353373413493654, "step": 2510}, {"loss": 1.5049, "grad_norm": 0.6104483604431152, "learning_rate": 0.0002, "epoch": 3.3667334669338675, "step": 2520}, {"loss": 1.587, "grad_norm": 0.8387531638145447, "learning_rate": 0.0002, "epoch": 3.3800935203740816, "step": 2530}, {"loss": 1.5227, "grad_norm": 0.6346094012260437, "learning_rate": 0.0002, "epoch": 3.3934535738142952, "step": 2540}, {"loss": 1.4855, "grad_norm": 0.6261265873908997, "learning_rate": 0.0002, "epoch": 3.406813627254509, "step": 2550}, {"loss": 1.5233, "grad_norm": 0.5960372090339661, "learning_rate": 0.0002, "epoch": 3.420173680694723, "step": 2560}, {"loss": 1.5153, "grad_norm": 0.5291280746459961, "learning_rate": 0.0002, "epoch": 3.4335337341349366, "step": 2570}, {"loss": 1.5152, "grad_norm": 0.6133161783218384, "learning_rate": 0.0002, "epoch": 3.44689378757515, "step": 2580}, {"loss": 1.5533, "grad_norm": 0.623573362827301, "learning_rate": 0.0002, "epoch": 3.460253841015364, "step": 2590}, {"loss": 1.4935, "grad_norm": 0.5959834456443787, "learning_rate": 0.0002, "epoch": 3.473613894455578, "step": 2600}, {"loss": 1.5792, "grad_norm": 0.583332359790802, "learning_rate": 0.0002, "epoch": 3.4869739478957915, "step": 2610}, {"loss": 1.5229, "grad_norm": 0.6003559231758118, "learning_rate": 0.0002, "epoch": 3.5003340013360056, "step": 2620}, {"loss": 1.4901, "grad_norm": 0.5832992196083069, "learning_rate": 0.0002, "epoch": 3.513694054776219, "step": 2630}, {"loss": 1.5005, "grad_norm": 0.5942609906196594, "learning_rate": 0.0002, "epoch": 3.527054108216433, "step": 2640}, {"loss": 1.5213, "grad_norm": 0.6087163686752319, "learning_rate": 0.0002, "epoch": 3.5404141616566465, "step": 2650}, {"loss": 1.5826, "grad_norm": 0.631948709487915, "learning_rate": 0.0002, "epoch": 3.5537742150968605, "step": 2660}, {"loss": 1.5844, "grad_norm": 0.6450803279876709, "learning_rate": 0.0002, "epoch": 3.567134268537074, "step": 2670}, {"loss": 1.4981, "grad_norm": 0.6507797837257385, "learning_rate": 0.0002, "epoch": 3.580494321977288, "step": 2680}, {"loss": 1.5826, "grad_norm": 0.5778017044067383, "learning_rate": 0.0002, "epoch": 3.593854375417502, "step": 2690}, {"loss": 1.4688, "grad_norm": 0.6214032173156738, "learning_rate": 0.0002, "epoch": 3.6072144288577155, "step": 2700}, {"loss": 1.5084, "grad_norm": 0.5681133270263672, "learning_rate": 0.0002, "epoch": 3.620574482297929, "step": 2710}, {"loss": 1.471, "grad_norm": 0.6074244976043701, "learning_rate": 0.0002, "epoch": 3.6339345357381427, "step": 2720}, {"loss": 1.5243, "grad_norm": 0.5900560617446899, "learning_rate": 0.0002, "epoch": 3.647294589178357, "step": 2730}, {"loss": 1.5074, "grad_norm": 0.5817505717277527, "learning_rate": 0.0002, "epoch": 3.6606546426185704, "step": 2740}, {"loss": 1.5117, "grad_norm": 0.6095547676086426, "learning_rate": 0.0002, "epoch": 3.6740146960587845, "step": 2750}, {"loss": 1.5117, "grad_norm": 0.612790584564209, "learning_rate": 0.0002, "epoch": 3.687374749498998, "step": 2760}, {"loss": 1.4976, "grad_norm": 0.6574140787124634, "learning_rate": 0.0002, "epoch": 3.7007348029392118, "step": 2770}, {"loss": 1.5306, "grad_norm": 0.5643761157989502, "learning_rate": 0.0002, "epoch": 3.7140948563794254, "step": 2780}, {"loss": 1.5751, "grad_norm": 0.5652621388435364, "learning_rate": 0.0002, "epoch": 3.727454909819639, "step": 2790}, {"loss": 1.5262, "grad_norm": 0.5604206323623657, "learning_rate": 0.0002, "epoch": 3.740814963259853, "step": 2800}, {"loss": 1.5013, "grad_norm": 3.911022663116455, "learning_rate": 0.0002, "epoch": 3.7541750167000667, "step": 2810}, {"loss": 1.5793, "grad_norm": 0.6148333549499512, "learning_rate": 0.0002, "epoch": 3.7675350701402808, "step": 2820}, {"loss": 1.5122, "grad_norm": 0.5605677962303162, "learning_rate": 0.0002, "epoch": 3.7808951235804944, "step": 2830}, {"loss": 1.5659, "grad_norm": 0.6101965308189392, "learning_rate": 0.0002, "epoch": 3.794255177020708, "step": 2840}, {"loss": 1.5618, "grad_norm": 0.5387342572212219, "learning_rate": 0.0002, "epoch": 3.8076152304609217, "step": 2850}, {"loss": 1.5193, "grad_norm": 0.5733087062835693, "learning_rate": 0.0002, "epoch": 3.8209752839011357, "step": 2860}, {"loss": 1.5545, "grad_norm": 0.6538485884666443, "learning_rate": 0.0002, "epoch": 3.8343353373413493, "step": 2870}, {"loss": 1.523, "grad_norm": 0.6247632503509521, "learning_rate": 0.0002, "epoch": 3.847695390781563, "step": 2880}, {"loss": 1.5591, "grad_norm": 0.5745735764503479, "learning_rate": 0.0002, "epoch": 3.861055444221777, "step": 2890}, {"loss": 1.5706, "grad_norm": 0.5942763686180115, "learning_rate": 0.0002, "epoch": 3.8744154976619907, "step": 2900}, {"loss": 1.564, "grad_norm": 0.7086281776428223, "learning_rate": 0.0002, "epoch": 3.8877755511022043, "step": 2910}, {"loss": 1.5526, "grad_norm": 0.8825129866600037, "learning_rate": 0.0002, "epoch": 3.901135604542418, "step": 2920}, {"loss": 1.4519, "grad_norm": 0.6260842680931091, "learning_rate": 0.0002, "epoch": 3.914495657982632, "step": 2930}, {"loss": 1.5433, "grad_norm": 0.6015968322753906, "learning_rate": 0.0002, "epoch": 3.9278557114228456, "step": 2940}, {"loss": 1.4931, "grad_norm": 0.7042809128761292, "learning_rate": 0.0002, "epoch": 3.9412157648630597, "step": 2950}, {"loss": 1.5596, "grad_norm": 0.5860083699226379, "learning_rate": 0.0002, "epoch": 3.9545758183032733, "step": 2960}, {"loss": 1.565, "grad_norm": 0.5939757823944092, "learning_rate": 0.0002, "epoch": 3.967935871743487, "step": 2970}, {"loss": 1.408, "grad_norm": 0.5523964166641235, "learning_rate": 0.0002, "epoch": 3.9812959251837006, "step": 2980}, {"loss": 1.5629, "grad_norm": 0.6380264759063721, "learning_rate": 0.0002, "epoch": 3.9946559786239146, "step": 2990}]}
+{"epoch": 4.999331997327989, "step": 3742, "epoch_duration": 847.4992234706879, "total_accumulated_duration": 4153.223728656769, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7672.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.6569, "grad_norm": 0.5097216367721558, "learning_rate": 0.0002, "epoch": 0.013360053440213761, "step": 10}, {"loss": 2.2557, "grad_norm": 0.5924790501594543, "learning_rate": 0.0002, "epoch": 0.026720106880427523, "step": 20}, {"loss": 2.0626, "grad_norm": 0.5158102512359619, "learning_rate": 0.0002, "epoch": 0.04008016032064128, "step": 30}, {"loss": 1.9452, "grad_norm": 0.5033753514289856, "learning_rate": 0.0002, "epoch": 0.053440213760855046, "step": 40}, {"loss": 1.9128, "grad_norm": 0.5390949845314026, "learning_rate": 0.0002, "epoch": 0.06680026720106881, "step": 50}, {"loss": 1.937, "grad_norm": 0.6376217007637024, "learning_rate": 0.0002, "epoch": 0.08016032064128256, "step": 60}, {"loss": 1.929, "grad_norm": 0.4202035069465637, "learning_rate": 0.0002, "epoch": 0.09352037408149633, "step": 70}, {"loss": 1.811, "grad_norm": 0.4269474744796753, "learning_rate": 0.0002, "epoch": 0.10688042752171009, "step": 80}, {"loss": 1.8303, "grad_norm": 0.4306574761867523, "learning_rate": 0.0002, "epoch": 0.12024048096192384, "step": 90}, {"loss": 1.8469, "grad_norm": 0.5297011137008667, "learning_rate": 0.0002, "epoch": 0.13360053440213762, "step": 100}, {"loss": 1.864, "grad_norm": 1.2313778400421143, "learning_rate": 0.0002, "epoch": 0.14696058784235136, "step": 110}, {"loss": 1.8531, "grad_norm": 0.5351294279098511, "learning_rate": 0.0002, "epoch": 0.16032064128256512, "step": 120}, {"loss": 1.9232, "grad_norm": 0.4848092496395111, "learning_rate": 0.0002, "epoch": 0.1736806947227789, "step": 130}, {"loss": 1.8633, "grad_norm": 0.4339500665664673, "learning_rate": 0.0002, "epoch": 0.18704074816299265, "step": 140}, {"loss": 1.816, "grad_norm": 0.46877285838127136, "learning_rate": 0.0002, "epoch": 0.20040080160320642, "step": 150}, {"loss": 1.8033, "grad_norm": 0.5600412487983704, "learning_rate": 0.0002, "epoch": 0.21376085504342018, "step": 160}, {"loss": 1.8162, "grad_norm": 0.3733620345592499, "learning_rate": 0.0002, "epoch": 0.22712090848363392, "step": 170}, {"loss": 1.8564, "grad_norm": 0.5116042494773865, "learning_rate": 0.0002, "epoch": 0.24048096192384769, "step": 180}, {"loss": 1.915, "grad_norm": 0.4071602523326874, "learning_rate": 0.0002, "epoch": 0.25384101536406145, "step": 190}, {"loss": 1.7984, "grad_norm": 0.44189608097076416, "learning_rate": 0.0002, "epoch": 0.26720106880427524, "step": 200}, {"loss": 1.8728, "grad_norm": 0.398699015378952, "learning_rate": 0.0002, "epoch": 0.280561122244489, "step": 210}, {"loss": 1.8205, "grad_norm": 0.3585626482963562, "learning_rate": 0.0002, "epoch": 0.2939211756847027, "step": 220}, {"loss": 1.8861, "grad_norm": 0.3811776041984558, "learning_rate": 0.0002, "epoch": 0.3072812291249165, "step": 230}, {"loss": 1.8365, "grad_norm": 0.37261509895324707, "learning_rate": 0.0002, "epoch": 0.32064128256513025, "step": 240}, {"loss": 1.9186, "grad_norm": 0.39762404561042786, "learning_rate": 0.0002, "epoch": 0.33400133600534404, "step": 250}, {"loss": 1.7965, "grad_norm": 0.3509528934955597, "learning_rate": 0.0002, "epoch": 0.3473613894455578, "step": 260}, {"loss": 1.7802, "grad_norm": 0.3169104754924774, "learning_rate": 0.0002, "epoch": 0.36072144288577157, "step": 270}, {"loss": 1.8038, "grad_norm": 0.33714795112609863, "learning_rate": 0.0002, "epoch": 0.3740814963259853, "step": 280}, {"loss": 1.787, "grad_norm": 1.2936875820159912, "learning_rate": 0.0002, "epoch": 0.38744154976619904, "step": 290}, {"loss": 1.7974, "grad_norm": 0.3459427058696747, "learning_rate": 0.0002, "epoch": 0.40080160320641284, "step": 300}, {"loss": 1.8879, "grad_norm": 0.3380655348300934, "learning_rate": 0.0002, "epoch": 0.4141616566466266, "step": 310}, {"loss": 1.9196, "grad_norm": 0.3890381455421448, "learning_rate": 0.0002, "epoch": 0.42752171008684037, "step": 320}, {"loss": 1.8034, "grad_norm": 0.432327002286911, "learning_rate": 0.0002, "epoch": 0.4408817635270541, "step": 330}, {"loss": 1.8443, "grad_norm": 0.3736560046672821, "learning_rate": 0.0002, "epoch": 0.45424181696726784, "step": 340}, {"loss": 1.8506, "grad_norm": 0.3700982630252838, "learning_rate": 0.0002, "epoch": 0.46760187040748163, "step": 350}, {"loss": 1.7978, "grad_norm": 0.4533902406692505, "learning_rate": 0.0002, "epoch": 0.48096192384769537, "step": 360}, {"loss": 1.7427, "grad_norm": 0.35999053716659546, "learning_rate": 0.0002, "epoch": 0.49432197728790916, "step": 370}, {"loss": 1.7995, "grad_norm": 0.3490903675556183, "learning_rate": 0.0002, "epoch": 0.5076820307281229, "step": 380}, {"loss": 1.8709, "grad_norm": 0.34704291820526123, "learning_rate": 0.0002, "epoch": 0.5210420841683366, "step": 390}, {"loss": 1.7948, "grad_norm": 0.343565434217453, "learning_rate": 0.0002, "epoch": 0.5344021376085505, "step": 400}, {"loss": 1.8564, "grad_norm": 0.3573552966117859, "learning_rate": 0.0002, "epoch": 0.5477621910487642, "step": 410}, {"loss": 1.8477, "grad_norm": 0.32980719208717346, "learning_rate": 0.0002, "epoch": 0.561122244488978, "step": 420}, {"loss": 1.9233, "grad_norm": 0.356952428817749, "learning_rate": 0.0002, "epoch": 0.5744822979291917, "step": 430}, {"loss": 1.7433, "grad_norm": 0.3170869052410126, "learning_rate": 0.0002, "epoch": 0.5878423513694054, "step": 440}, {"loss": 1.7607, "grad_norm": 0.35233718156814575, "learning_rate": 0.0002, "epoch": 0.6012024048096193, "step": 450}, {"loss": 1.8111, "grad_norm": 0.3480125367641449, "learning_rate": 0.0002, "epoch": 0.614562458249833, "step": 460}, {"loss": 1.8386, "grad_norm": 0.4762810468673706, "learning_rate": 0.0002, "epoch": 0.6279225116900468, "step": 470}, {"loss": 1.805, "grad_norm": 0.3907663822174072, "learning_rate": 0.0002, "epoch": 0.6412825651302605, "step": 480}, {"loss": 1.8113, "grad_norm": 0.36315613985061646, "learning_rate": 0.0002, "epoch": 0.6546426185704742, "step": 490}, {"loss": 1.7805, "grad_norm": 0.377796471118927, "learning_rate": 0.0002, "epoch": 0.6680026720106881, "step": 500}, {"loss": 1.7457, "grad_norm": 0.34284207224845886, "learning_rate": 0.0002, "epoch": 0.6813627254509018, "step": 510}, {"loss": 1.8013, "grad_norm": 0.35563018918037415, "learning_rate": 0.0002, "epoch": 0.6947227788911156, "step": 520}, {"loss": 1.8414, "grad_norm": 0.37575867772102356, "learning_rate": 0.0002, "epoch": 0.7080828323313293, "step": 530}, {"loss": 1.7993, "grad_norm": 0.35719701647758484, "learning_rate": 0.0002, "epoch": 0.7214428857715431, "step": 540}, {"loss": 1.7574, "grad_norm": 0.385813444852829, "learning_rate": 0.0002, "epoch": 0.7348029392117569, "step": 550}, {"loss": 1.7985, "grad_norm": 0.44509607553482056, "learning_rate": 0.0002, "epoch": 0.7481629926519706, "step": 560}, {"loss": 1.7459, "grad_norm": 0.36108464002609253, "learning_rate": 0.0002, "epoch": 0.7615230460921844, "step": 570}, {"loss": 1.8207, "grad_norm": 0.3530745804309845, "learning_rate": 0.0002, "epoch": 0.7748830995323981, "step": 580}, {"loss": 1.7479, "grad_norm": 0.34888574481010437, "learning_rate": 0.0002, "epoch": 0.7882431529726119, "step": 590}, {"loss": 1.8656, "grad_norm": 0.387346476316452, "learning_rate": 0.0002, "epoch": 0.8016032064128257, "step": 600}, {"loss": 1.8071, "grad_norm": 0.3641138970851898, "learning_rate": 0.0002, "epoch": 0.8149632598530394, "step": 610}, {"loss": 1.7531, "grad_norm": 0.33729103207588196, "learning_rate": 0.0002, "epoch": 0.8283233132932531, "step": 620}, {"loss": 1.8613, "grad_norm": 0.3652004599571228, "learning_rate": 0.0002, "epoch": 0.8416833667334669, "step": 630}, {"loss": 1.9184, "grad_norm": 0.3986643850803375, "learning_rate": 0.0002, "epoch": 0.8550434201736807, "step": 640}, {"loss": 1.8198, "grad_norm": 0.3458964228630066, "learning_rate": 0.0002, "epoch": 0.8684034736138945, "step": 650}, {"loss": 1.803, "grad_norm": 0.3559381365776062, "learning_rate": 0.0002, "epoch": 0.8817635270541082, "step": 660}, {"loss": 1.7641, "grad_norm": 0.3612841069698334, "learning_rate": 0.0002, "epoch": 0.895123580494322, "step": 670}, {"loss": 1.7888, "grad_norm": 0.34771719574928284, "learning_rate": 0.0002, "epoch": 0.9084836339345357, "step": 680}, {"loss": 1.8204, "grad_norm": 0.3371497094631195, "learning_rate": 0.0002, "epoch": 0.9218436873747495, "step": 690}, {"loss": 1.7848, "grad_norm": 0.5596055388450623, "learning_rate": 0.0002, "epoch": 0.9352037408149633, "step": 700}, {"loss": 1.7794, "grad_norm": 0.311880499124527, "learning_rate": 0.0002, "epoch": 0.948563794255177, "step": 710}, {"loss": 1.8464, "grad_norm": 0.3462068736553192, "learning_rate": 0.0002, "epoch": 0.9619238476953907, "step": 720}, {"loss": 1.8197, "grad_norm": 0.29982393980026245, "learning_rate": 0.0002, "epoch": 0.9752839011356046, "step": 730}, {"loss": 1.8503, "grad_norm": 0.34606459736824036, "learning_rate": 0.0002, "epoch": 0.9886439545758183, "step": 740}, {"eval_loss": 1.8201380968093872, "eval_runtime": 38.6124, "eval_samples_per_second": 13.338, "eval_steps_per_second": 1.683, "epoch": 0.9993319973279893, "step": 748}, {"loss": 1.7786, "grad_norm": 0.32302048802375793, "learning_rate": 0.0002, "epoch": 1.002004008016032, "step": 750}, {"loss": 1.7297, "grad_norm": 0.37585633993148804, "learning_rate": 0.0002, "epoch": 1.0153640614562458, "step": 760}, {"loss": 1.7008, "grad_norm": 0.33826273679733276, "learning_rate": 0.0002, "epoch": 1.0287241148964597, "step": 770}, {"loss": 1.809, "grad_norm": 0.44682955741882324, "learning_rate": 0.0002, "epoch": 1.0420841683366733, "step": 780}, {"loss": 1.7092, "grad_norm": 0.422188401222229, "learning_rate": 0.0002, "epoch": 1.0554442217768871, "step": 790}, {"loss": 1.7765, "grad_norm": 0.3809906244277954, "learning_rate": 0.0002, "epoch": 1.0688042752171008, "step": 800}, {"loss": 1.7431, "grad_norm": 0.3454349637031555, "learning_rate": 0.0002, "epoch": 1.0821643286573146, "step": 810}, {"loss": 1.7257, "grad_norm": 0.3767355978488922, "learning_rate": 0.0002, "epoch": 1.0955243820975284, "step": 820}, {"loss": 1.7224, "grad_norm": 0.3361407518386841, "learning_rate": 0.0002, "epoch": 1.108884435537742, "step": 830}, {"loss": 1.7509, "grad_norm": 0.3654632568359375, "learning_rate": 0.0002, "epoch": 1.122244488977956, "step": 840}, {"loss": 1.7151, "grad_norm": 0.3822861313819885, "learning_rate": 0.0002, "epoch": 1.1356045424181698, "step": 850}, {"loss": 1.7121, "grad_norm": 0.3853831887245178, "learning_rate": 0.0002, "epoch": 1.1489645958583834, "step": 860}, {"loss": 1.7685, "grad_norm": 0.35521796345710754, "learning_rate": 0.0002, "epoch": 1.1623246492985972, "step": 870}, {"loss": 1.7735, "grad_norm": 0.4107200503349304, "learning_rate": 0.0002, "epoch": 1.1756847027388109, "step": 880}, {"loss": 1.7484, "grad_norm": 0.33219534158706665, "learning_rate": 0.0002, "epoch": 1.1890447561790247, "step": 890}, {"loss": 1.7071, "grad_norm": 0.3559704124927521, "learning_rate": 0.0002, "epoch": 1.2024048096192386, "step": 900}, {"loss": 1.7535, "grad_norm": 0.3700537383556366, "learning_rate": 0.0002, "epoch": 1.2157648630594522, "step": 910}, {"loss": 1.7513, "grad_norm": 0.3771909475326538, "learning_rate": 0.0002, "epoch": 1.229124916499666, "step": 920}, {"loss": 1.7566, "grad_norm": 0.3136613965034485, "learning_rate": 0.0002, "epoch": 1.2424849699398797, "step": 930}, {"loss": 1.6783, "grad_norm": 0.3952099084854126, "learning_rate": 0.0002, "epoch": 1.2558450233800935, "step": 940}, {"loss": 1.7691, "grad_norm": 0.36534377932548523, "learning_rate": 0.0002, "epoch": 1.2692050768203074, "step": 950}, {"loss": 1.7127, "grad_norm": 0.3803492486476898, "learning_rate": 0.0002, "epoch": 1.282565130260521, "step": 960}, {"loss": 1.7896, "grad_norm": 0.3992428183555603, "learning_rate": 0.0002, "epoch": 1.2959251837007348, "step": 970}, {"loss": 1.7343, "grad_norm": 0.3627142906188965, "learning_rate": 0.0002, "epoch": 1.3092852371409487, "step": 980}, {"loss": 1.7598, "grad_norm": 0.4248180091381073, "learning_rate": 0.0002, "epoch": 1.3226452905811623, "step": 990}, {"loss": 1.6896, "grad_norm": 0.4060308039188385, "learning_rate": 0.0002, "epoch": 1.3360053440213762, "step": 1000}, {"loss": 1.7457, "grad_norm": 0.3788969814777374, "learning_rate": 0.0002, "epoch": 1.3493653974615898, "step": 1010}, {"loss": 1.7111, "grad_norm": 0.4174270033836365, "learning_rate": 0.0002, "epoch": 1.3627254509018036, "step": 1020}, {"loss": 1.7975, "grad_norm": 0.35500675439834595, "learning_rate": 0.0002, "epoch": 1.3760855043420173, "step": 1030}, {"loss": 1.724, "grad_norm": 0.3454059362411499, "learning_rate": 0.0002, "epoch": 1.389445557782231, "step": 1040}, {"loss": 1.8299, "grad_norm": 0.45807570219039917, "learning_rate": 0.0002, "epoch": 1.402805611222445, "step": 1050}, {"loss": 1.7425, "grad_norm": 0.39338022470474243, "learning_rate": 0.0002, "epoch": 1.4161656646626586, "step": 1060}, {"loss": 1.7457, "grad_norm": 0.3870709240436554, "learning_rate": 0.0002, "epoch": 1.4295257181028724, "step": 1070}, {"loss": 1.6565, "grad_norm": 0.40996190905570984, "learning_rate": 0.0002, "epoch": 1.4428857715430863, "step": 1080}, {"loss": 1.7324, "grad_norm": 0.38762837648391724, "learning_rate": 0.0002, "epoch": 1.4562458249833, "step": 1090}, {"loss": 1.7362, "grad_norm": 0.36756977438926697, "learning_rate": 0.0002, "epoch": 1.4696058784235138, "step": 1100}, {"loss": 1.7451, "grad_norm": 0.4087235927581787, "learning_rate": 0.0002, "epoch": 1.4829659318637274, "step": 1110}, {"loss": 1.7114, "grad_norm": 0.3357745110988617, "learning_rate": 0.0002, "epoch": 1.4963259853039412, "step": 1120}, {"loss": 1.6877, "grad_norm": 0.37486532330513, "learning_rate": 0.0002, "epoch": 1.5096860387441549, "step": 1130}, {"loss": 1.7252, "grad_norm": 0.3387809991836548, "learning_rate": 0.0002, "epoch": 1.5230460921843687, "step": 1140}, {"loss": 1.7169, "grad_norm": 0.37462118268013, "learning_rate": 0.0002, "epoch": 1.5364061456245826, "step": 1150}, {"loss": 1.6988, "grad_norm": 0.38575324416160583, "learning_rate": 0.0002, "epoch": 1.5497661990647962, "step": 1160}, {"loss": 1.7438, "grad_norm": 0.3515765964984894, "learning_rate": 0.0002, "epoch": 1.56312625250501, "step": 1170}, {"loss": 1.7524, "grad_norm": 0.39308643341064453, "learning_rate": 0.0002, "epoch": 1.5764863059452239, "step": 1180}, {"loss": 1.6422, "grad_norm": 0.3308864235877991, "learning_rate": 0.0002, "epoch": 1.5898463593854375, "step": 1190}, {"loss": 1.7566, "grad_norm": 0.3397478461265564, "learning_rate": 0.0002, "epoch": 1.6032064128256514, "step": 1200}, {"loss": 1.7871, "grad_norm": 0.3911525309085846, "learning_rate": 0.0002, "epoch": 1.6165664662658652, "step": 1210}, {"loss": 1.7443, "grad_norm": 0.3771969974040985, "learning_rate": 0.0002, "epoch": 1.6299265197060788, "step": 1220}, {"loss": 1.7631, "grad_norm": 0.35346856713294983, "learning_rate": 0.0002, "epoch": 1.6432865731462925, "step": 1230}, {"loss": 1.7225, "grad_norm": 0.41736963391304016, "learning_rate": 0.0002, "epoch": 1.6566466265865063, "step": 1240}, {"loss": 1.7582, "grad_norm": 0.3375225067138672, "learning_rate": 0.0002, "epoch": 1.6700066800267201, "step": 1250}, {"loss": 1.6916, "grad_norm": 0.3779928982257843, "learning_rate": 0.0002, "epoch": 1.6833667334669338, "step": 1260}, {"loss": 1.728, "grad_norm": 0.35388994216918945, "learning_rate": 0.0002, "epoch": 1.6967267869071476, "step": 1270}, {"loss": 1.7461, "grad_norm": 0.33884134888648987, "learning_rate": 0.0002, "epoch": 1.7100868403473615, "step": 1280}, {"loss": 1.7083, "grad_norm": 0.35439756512641907, "learning_rate": 0.0002, "epoch": 1.723446893787575, "step": 1290}, {"loss": 1.7389, "grad_norm": 0.3766156733036041, "learning_rate": 0.0002, "epoch": 1.736806947227789, "step": 1300}, {"loss": 1.7847, "grad_norm": 0.36148911714553833, "learning_rate": 0.0002, "epoch": 1.7501670006680028, "step": 1310}, {"loss": 1.7344, "grad_norm": 0.39687496423721313, "learning_rate": 0.0002, "epoch": 1.7635270541082164, "step": 1320}, {"loss": 1.7541, "grad_norm": 0.35639452934265137, "learning_rate": 0.0002, "epoch": 1.77688710754843, "step": 1330}, {"loss": 1.7254, "grad_norm": 0.38781628012657166, "learning_rate": 0.0002, "epoch": 1.7902471609886441, "step": 1340}, {"loss": 1.7867, "grad_norm": 0.42784637212753296, "learning_rate": 0.0002, "epoch": 1.8036072144288577, "step": 1350}, {"loss": 1.7336, "grad_norm": 0.40258511900901794, "learning_rate": 0.0002, "epoch": 1.8169672678690714, "step": 1360}, {"loss": 1.7771, "grad_norm": 0.36674195528030396, "learning_rate": 0.0002, "epoch": 1.8303273213092852, "step": 1370}, {"loss": 1.7425, "grad_norm": 0.4064558446407318, "learning_rate": 0.0002, "epoch": 1.843687374749499, "step": 1380}, {"loss": 1.7425, "grad_norm": 0.3669849932193756, "learning_rate": 0.0002, "epoch": 1.8570474281897127, "step": 1390}, {"loss": 1.7924, "grad_norm": 0.37569567561149597, "learning_rate": 0.0002, "epoch": 1.8704074816299265, "step": 1400}, {"loss": 1.7885, "grad_norm": 0.37307995557785034, "learning_rate": 0.0002, "epoch": 1.8837675350701404, "step": 1410}, {"loss": 1.7548, "grad_norm": 0.3772695064544678, "learning_rate": 0.0002, "epoch": 1.897127588510354, "step": 1420}, {"loss": 1.7682, "grad_norm": 0.36993589997291565, "learning_rate": 0.0002, "epoch": 1.9104876419505676, "step": 1430}, {"loss": 1.7249, "grad_norm": 0.3490557372570038, "learning_rate": 0.0002, "epoch": 1.9238476953907817, "step": 1440}, {"loss": 1.7979, "grad_norm": 0.3716149628162384, "learning_rate": 0.0002, "epoch": 1.9372077488309953, "step": 1450}, {"loss": 1.6664, "grad_norm": 0.39236098527908325, "learning_rate": 0.0002, "epoch": 1.950567802271209, "step": 1460}, {"loss": 1.6852, "grad_norm": 0.37258651852607727, "learning_rate": 0.0002, "epoch": 1.9639278557114228, "step": 1470}, {"loss": 1.7427, "grad_norm": 0.36183077096939087, "learning_rate": 0.0002, "epoch": 1.9772879091516367, "step": 1480}, {"loss": 1.7055, "grad_norm": 0.3956947326660156, "learning_rate": 0.0002, "epoch": 1.9906479625918503, "step": 1490}, {"eval_loss": 1.8132041692733765, "eval_runtime": 38.6287, "eval_samples_per_second": 13.332, "eval_steps_per_second": 1.683, "epoch": 2.0, "step": 1497}, {"loss": 1.6791, "grad_norm": 0.34480565786361694, "learning_rate": 0.0002, "epoch": 2.004008016032064, "step": 1500}, {"loss": 1.6367, "grad_norm": 0.3418028652667999, "learning_rate": 0.0002, "epoch": 2.017368069472278, "step": 1510}, {"loss": 1.5827, "grad_norm": 0.4514467716217041, "learning_rate": 0.0002, "epoch": 2.0307281229124916, "step": 1520}, {"loss": 1.6365, "grad_norm": 0.4197506606578827, "learning_rate": 0.0002, "epoch": 2.0440881763527052, "step": 1530}, {"loss": 1.6221, "grad_norm": 0.4134170711040497, "learning_rate": 0.0002, "epoch": 2.0574482297929193, "step": 1540}, {"loss": 1.6876, "grad_norm": 0.43709826469421387, "learning_rate": 0.0002, "epoch": 2.070808283233133, "step": 1550}, {"loss": 1.5779, "grad_norm": 0.4703378677368164, "learning_rate": 0.0002, "epoch": 2.0841683366733466, "step": 1560}, {"loss": 1.599, "grad_norm": 0.4538188576698303, "learning_rate": 0.0002, "epoch": 2.0975283901135606, "step": 1570}, {"loss": 1.6464, "grad_norm": 0.4649668037891388, "learning_rate": 0.0002, "epoch": 2.1108884435537743, "step": 1580}, {"loss": 1.6348, "grad_norm": 0.42669883370399475, "learning_rate": 0.0002, "epoch": 2.124248496993988, "step": 1590}, {"loss": 1.5838, "grad_norm": 0.43162038922309875, "learning_rate": 0.0002, "epoch": 2.1376085504342015, "step": 1600}, {"loss": 1.6673, "grad_norm": 0.4294586479663849, "learning_rate": 0.0002, "epoch": 2.1509686038744156, "step": 1610}, {"loss": 1.6024, "grad_norm": 0.4669102132320404, "learning_rate": 0.0002, "epoch": 2.164328657314629, "step": 1620}, {"loss": 1.659, "grad_norm": 0.4188412129878998, "learning_rate": 0.0002, "epoch": 2.177688710754843, "step": 1630}, {"loss": 1.625, "grad_norm": 0.4662680923938751, "learning_rate": 0.0002, "epoch": 2.191048764195057, "step": 1640}, {"loss": 1.6699, "grad_norm": 0.4020286500453949, "learning_rate": 0.0002, "epoch": 2.2044088176352705, "step": 1650}, {"loss": 1.6284, "grad_norm": 0.41919606924057007, "learning_rate": 0.0002, "epoch": 2.217768871075484, "step": 1660}, {"loss": 1.6776, "grad_norm": 0.4644531309604645, "learning_rate": 0.0002, "epoch": 2.231128924515698, "step": 1670}, {"loss": 1.6711, "grad_norm": 0.4526427984237671, "learning_rate": 0.0002, "epoch": 2.244488977955912, "step": 1680}, {"loss": 1.6058, "grad_norm": 0.45953166484832764, "learning_rate": 0.0002, "epoch": 2.2578490313961255, "step": 1690}, {"loss": 1.5979, "grad_norm": 0.4701860249042511, "learning_rate": 0.0002, "epoch": 2.2712090848363395, "step": 1700}, {"loss": 1.6183, "grad_norm": 0.4749310612678528, "learning_rate": 0.0002, "epoch": 2.284569138276553, "step": 1710}, {"loss": 1.6703, "grad_norm": 0.45026102662086487, "learning_rate": 0.0002, "epoch": 2.297929191716767, "step": 1720}, {"loss": 1.6386, "grad_norm": 0.4755004048347473, "learning_rate": 0.0002, "epoch": 2.3112892451569804, "step": 1730}, {"loss": 1.6365, "grad_norm": 0.4505726993083954, "learning_rate": 0.0002, "epoch": 2.3246492985971945, "step": 1740}, {"loss": 1.589, "grad_norm": 0.44464054703712463, "learning_rate": 0.0002, "epoch": 2.338009352037408, "step": 1750}, {"loss": 1.6139, "grad_norm": 0.4449476897716522, "learning_rate": 0.0002, "epoch": 2.3513694054776217, "step": 1760}, {"loss": 1.7195, "grad_norm": 0.4216482937335968, "learning_rate": 0.0002, "epoch": 2.364729458917836, "step": 1770}, {"loss": 1.7075, "grad_norm": 0.4379308521747589, "learning_rate": 0.0002, "epoch": 2.3780895123580494, "step": 1780}, {"loss": 1.7024, "grad_norm": 0.41670042276382446, "learning_rate": 0.0002, "epoch": 2.391449565798263, "step": 1790}, {"loss": 1.5989, "grad_norm": 0.48089510202407837, "learning_rate": 0.0002, "epoch": 2.404809619238477, "step": 1800}, {"loss": 1.6313, "grad_norm": 0.4389738142490387, "learning_rate": 0.0002, "epoch": 2.4181696726786908, "step": 1810}, {"loss": 1.5841, "grad_norm": 0.45293036103248596, "learning_rate": 0.0002, "epoch": 2.4315297261189044, "step": 1820}, {"loss": 1.6887, "grad_norm": 0.5211683511734009, "learning_rate": 0.0002, "epoch": 2.4448897795591185, "step": 1830}, {"loss": 1.6599, "grad_norm": 0.4631884694099426, "learning_rate": 0.0002, "epoch": 2.458249832999332, "step": 1840}, {"loss": 1.6537, "grad_norm": 0.4276818335056305, "learning_rate": 0.0002, "epoch": 2.4716098864395457, "step": 1850}, {"loss": 1.6836, "grad_norm": 0.477524071931839, "learning_rate": 0.0002, "epoch": 2.4849699398797593, "step": 1860}, {"loss": 1.66, "grad_norm": 0.44860973954200745, "learning_rate": 0.0002, "epoch": 2.4983299933199734, "step": 1870}, {"loss": 1.6308, "grad_norm": 0.46413546800613403, "learning_rate": 0.0002, "epoch": 2.511690046760187, "step": 1880}, {"loss": 1.6225, "grad_norm": 0.42487645149230957, "learning_rate": 0.0002, "epoch": 2.5250501002004007, "step": 1890}, {"loss": 1.6268, "grad_norm": 0.4778307378292084, "learning_rate": 0.0002, "epoch": 2.5384101536406147, "step": 1900}, {"loss": 1.6143, "grad_norm": 0.45307061076164246, "learning_rate": 0.0002, "epoch": 2.5517702070808284, "step": 1910}, {"loss": 1.7279, "grad_norm": 0.47886642813682556, "learning_rate": 0.0002, "epoch": 2.565130260521042, "step": 1920}, {"loss": 1.5931, "grad_norm": 0.4839435815811157, "learning_rate": 0.0002, "epoch": 2.5784903139612556, "step": 1930}, {"loss": 1.6089, "grad_norm": 0.4388359785079956, "learning_rate": 0.0002, "epoch": 2.5918503674014697, "step": 1940}, {"loss": 1.6828, "grad_norm": 0.47859734296798706, "learning_rate": 0.0002, "epoch": 2.6052104208416833, "step": 1950}, {"loss": 1.6014, "grad_norm": 0.5526517033576965, "learning_rate": 0.0002, "epoch": 2.6185704742818974, "step": 1960}, {"loss": 1.6889, "grad_norm": 0.5449170470237732, "learning_rate": 0.0002, "epoch": 2.631930527722111, "step": 1970}, {"loss": 1.6481, "grad_norm": 0.48521968722343445, "learning_rate": 0.0002, "epoch": 2.6452905811623246, "step": 1980}, {"loss": 1.6741, "grad_norm": 0.4733737111091614, "learning_rate": 0.0002, "epoch": 2.6586506346025383, "step": 1990}, {"loss": 1.662, "grad_norm": 0.507118284702301, "learning_rate": 0.0002, "epoch": 2.6720106880427523, "step": 2000}, {"loss": 1.6419, "grad_norm": 0.4508971571922302, "learning_rate": 0.0002, "epoch": 2.685370741482966, "step": 2010}, {"loss": 1.7052, "grad_norm": 0.4657728672027588, "learning_rate": 0.0002, "epoch": 2.6987307949231796, "step": 2020}, {"loss": 1.6261, "grad_norm": 0.48647549748420715, "learning_rate": 0.0002, "epoch": 2.7120908483633936, "step": 2030}, {"loss": 1.5638, "grad_norm": 0.49525555968284607, "learning_rate": 0.0002, "epoch": 2.7254509018036073, "step": 2040}, {"loss": 1.658, "grad_norm": 0.4712379276752472, "learning_rate": 0.0002, "epoch": 2.738810955243821, "step": 2050}, {"loss": 1.6464, "grad_norm": 0.4846591055393219, "learning_rate": 0.0002, "epoch": 2.7521710086840345, "step": 2060}, {"loss": 1.5641, "grad_norm": 0.4823240041732788, "learning_rate": 0.0002, "epoch": 2.7655310621242486, "step": 2070}, {"loss": 1.6701, "grad_norm": 0.4546685516834259, "learning_rate": 0.0002, "epoch": 2.778891115564462, "step": 2080}, {"loss": 1.7015, "grad_norm": 0.45542681217193604, "learning_rate": 0.0002, "epoch": 2.7922511690046763, "step": 2090}, {"loss": 1.6398, "grad_norm": 0.42137566208839417, "learning_rate": 0.0002, "epoch": 2.80561122244489, "step": 2100}, {"loss": 1.6526, "grad_norm": 0.6143282055854797, "learning_rate": 0.0002, "epoch": 2.8189712758851035, "step": 2110}, {"loss": 1.6955, "grad_norm": 0.4828081727027893, "learning_rate": 0.0002, "epoch": 2.832331329325317, "step": 2120}, {"loss": 1.744, "grad_norm": 0.4319005608558655, "learning_rate": 0.0002, "epoch": 2.845691382765531, "step": 2130}, {"loss": 1.6717, "grad_norm": 0.4297086298465729, "learning_rate": 0.0002, "epoch": 2.859051436205745, "step": 2140}, {"loss": 1.5968, "grad_norm": 0.5011981129646301, "learning_rate": 0.0002, "epoch": 2.8724114896459585, "step": 2150}, {"loss": 1.7181, "grad_norm": 0.4401548504829407, "learning_rate": 0.0002, "epoch": 2.8857715430861726, "step": 2160}, {"loss": 1.5722, "grad_norm": 0.48090746998786926, "learning_rate": 0.0002, "epoch": 2.899131596526386, "step": 2170}, {"loss": 1.6596, "grad_norm": 0.4740385413169861, "learning_rate": 0.0002, "epoch": 2.9124916499666, "step": 2180}, {"loss": 1.6501, "grad_norm": 0.5337260365486145, "learning_rate": 0.0002, "epoch": 2.9258517034068134, "step": 2190}, {"loss": 1.6802, "grad_norm": 0.4420052766799927, "learning_rate": 0.0002, "epoch": 2.9392117568470275, "step": 2200}, {"loss": 1.5474, "grad_norm": 0.477512389421463, "learning_rate": 0.0002, "epoch": 2.952571810287241, "step": 2210}, {"loss": 1.6544, "grad_norm": 0.5344052910804749, "learning_rate": 0.0002, "epoch": 2.9659318637274548, "step": 2220}, {"loss": 1.6866, "grad_norm": 0.4483940303325653, "learning_rate": 0.0002, "epoch": 2.979291917167669, "step": 2230}, {"loss": 1.6477, "grad_norm": 0.4366597831249237, "learning_rate": 0.0002, "epoch": 2.9926519706078825, "step": 2240}, {"eval_loss": 1.834012746810913, "eval_runtime": 38.5659, "eval_samples_per_second": 13.354, "eval_steps_per_second": 1.685, "epoch": 2.9993319973279893, "step": 2245}, {"loss": 1.5582, "grad_norm": 0.428824245929718, "learning_rate": 0.0002, "epoch": 3.006012024048096, "step": 2250}, {"loss": 1.499, "grad_norm": 0.4870174825191498, "learning_rate": 0.0002, "epoch": 3.01937207748831, "step": 2260}, {"loss": 1.4872, "grad_norm": 0.4684266149997711, "learning_rate": 0.0002, "epoch": 3.032732130928524, "step": 2270}, {"loss": 1.5284, "grad_norm": 0.581604540348053, "learning_rate": 0.0002, "epoch": 3.0460921843687374, "step": 2280}, {"loss": 1.4549, "grad_norm": 0.5561677813529968, "learning_rate": 0.0002, "epoch": 3.059452237808951, "step": 2290}, {"loss": 1.4903, "grad_norm": 0.5750220417976379, "learning_rate": 0.0002, "epoch": 3.072812291249165, "step": 2300}, {"loss": 1.5903, "grad_norm": 0.5704626441001892, "learning_rate": 0.0002, "epoch": 3.0861723446893787, "step": 2310}, {"loss": 1.4292, "grad_norm": 0.6242083311080933, "learning_rate": 0.0002, "epoch": 3.0995323981295924, "step": 2320}, {"loss": 1.5092, "grad_norm": 0.5174121260643005, "learning_rate": 0.0002, "epoch": 3.1128924515698064, "step": 2330}, {"loss": 1.5106, "grad_norm": 0.5697633028030396, "learning_rate": 0.0002, "epoch": 3.12625250501002, "step": 2340}, {"loss": 1.5156, "grad_norm": 0.5969541072845459, "learning_rate": 0.0002, "epoch": 3.1396125584502337, "step": 2350}, {"loss": 1.52, "grad_norm": 0.6244304180145264, "learning_rate": 0.0002, "epoch": 3.1529726118904478, "step": 2360}, {"loss": 1.5244, "grad_norm": 0.5561705827713013, "learning_rate": 0.0002, "epoch": 3.1663326653306614, "step": 2370}, {"loss": 1.6169, "grad_norm": 0.5401188135147095, "learning_rate": 0.0002, "epoch": 3.179692718770875, "step": 2380}, {"loss": 1.5387, "grad_norm": 0.6450421810150146, "learning_rate": 0.0002, "epoch": 3.1930527722110886, "step": 2390}, {"loss": 1.4839, "grad_norm": 0.5741903185844421, "learning_rate": 0.0002, "epoch": 3.2064128256513027, "step": 2400}, {"loss": 1.5584, "grad_norm": 0.6337407231330872, "learning_rate": 0.0002, "epoch": 3.2197728790915163, "step": 2410}, {"loss": 1.5025, "grad_norm": 0.6493517160415649, "learning_rate": 0.0002, "epoch": 3.23313293253173, "step": 2420}, {"loss": 1.5168, "grad_norm": 0.6230176091194153, "learning_rate": 0.0002, "epoch": 3.246492985971944, "step": 2430}, {"loss": 1.5408, "grad_norm": 0.680704653263092, "learning_rate": 0.0002, "epoch": 3.2598530394121576, "step": 2440}, {"loss": 1.6005, "grad_norm": 0.5279417037963867, "learning_rate": 0.0002, "epoch": 3.2732130928523713, "step": 2450}, {"loss": 1.5231, "grad_norm": 0.5601515173912048, "learning_rate": 0.0002, "epoch": 3.2865731462925853, "step": 2460}, {"loss": 1.4949, "grad_norm": 0.5591090321540833, "learning_rate": 0.0002, "epoch": 3.299933199732799, "step": 2470}, {"loss": 1.5181, "grad_norm": 0.6596529483795166, "learning_rate": 0.0002, "epoch": 3.3132932531730126, "step": 2480}, {"loss": 1.5259, "grad_norm": 0.6115918755531311, "learning_rate": 0.0002, "epoch": 3.3266533066132267, "step": 2490}, {"loss": 1.5344, "grad_norm": 0.6443548202514648, "learning_rate": 0.0002, "epoch": 3.3400133600534403, "step": 2500}, {"loss": 1.5037, "grad_norm": 0.5504242181777954, "learning_rate": 0.0002, "epoch": 3.353373413493654, "step": 2510}, {"loss": 1.5049, "grad_norm": 0.6104483604431152, "learning_rate": 0.0002, "epoch": 3.3667334669338675, "step": 2520}, {"loss": 1.587, "grad_norm": 0.8387531638145447, "learning_rate": 0.0002, "epoch": 3.3800935203740816, "step": 2530}, {"loss": 1.5227, "grad_norm": 0.6346094012260437, "learning_rate": 0.0002, "epoch": 3.3934535738142952, "step": 2540}, {"loss": 1.4855, "grad_norm": 0.6261265873908997, "learning_rate": 0.0002, "epoch": 3.406813627254509, "step": 2550}, {"loss": 1.5233, "grad_norm": 0.5960372090339661, "learning_rate": 0.0002, "epoch": 3.420173680694723, "step": 2560}, {"loss": 1.5153, "grad_norm": 0.5291280746459961, "learning_rate": 0.0002, "epoch": 3.4335337341349366, "step": 2570}, {"loss": 1.5152, "grad_norm": 0.6133161783218384, "learning_rate": 0.0002, "epoch": 3.44689378757515, "step": 2580}, {"loss": 1.5533, "grad_norm": 0.623573362827301, "learning_rate": 0.0002, "epoch": 3.460253841015364, "step": 2590}, {"loss": 1.4935, "grad_norm": 0.5959834456443787, "learning_rate": 0.0002, "epoch": 3.473613894455578, "step": 2600}, {"loss": 1.5792, "grad_norm": 0.583332359790802, "learning_rate": 0.0002, "epoch": 3.4869739478957915, "step": 2610}, {"loss": 1.5229, "grad_norm": 0.6003559231758118, "learning_rate": 0.0002, "epoch": 3.5003340013360056, "step": 2620}, {"loss": 1.4901, "grad_norm": 0.5832992196083069, "learning_rate": 0.0002, "epoch": 3.513694054776219, "step": 2630}, {"loss": 1.5005, "grad_norm": 0.5942609906196594, "learning_rate": 0.0002, "epoch": 3.527054108216433, "step": 2640}, {"loss": 1.5213, "grad_norm": 0.6087163686752319, "learning_rate": 0.0002, "epoch": 3.5404141616566465, "step": 2650}, {"loss": 1.5826, "grad_norm": 0.631948709487915, "learning_rate": 0.0002, "epoch": 3.5537742150968605, "step": 2660}, {"loss": 1.5844, "grad_norm": 0.6450803279876709, "learning_rate": 0.0002, "epoch": 3.567134268537074, "step": 2670}, {"loss": 1.4981, "grad_norm": 0.6507797837257385, "learning_rate": 0.0002, "epoch": 3.580494321977288, "step": 2680}, {"loss": 1.5826, "grad_norm": 0.5778017044067383, "learning_rate": 0.0002, "epoch": 3.593854375417502, "step": 2690}, {"loss": 1.4688, "grad_norm": 0.6214032173156738, "learning_rate": 0.0002, "epoch": 3.6072144288577155, "step": 2700}, {"loss": 1.5084, "grad_norm": 0.5681133270263672, "learning_rate": 0.0002, "epoch": 3.620574482297929, "step": 2710}, {"loss": 1.471, "grad_norm": 0.6074244976043701, "learning_rate": 0.0002, "epoch": 3.6339345357381427, "step": 2720}, {"loss": 1.5243, "grad_norm": 0.5900560617446899, "learning_rate": 0.0002, "epoch": 3.647294589178357, "step": 2730}, {"loss": 1.5074, "grad_norm": 0.5817505717277527, "learning_rate": 0.0002, "epoch": 3.6606546426185704, "step": 2740}, {"loss": 1.5117, "grad_norm": 0.6095547676086426, "learning_rate": 0.0002, "epoch": 3.6740146960587845, "step": 2750}, {"loss": 1.5117, "grad_norm": 0.612790584564209, "learning_rate": 0.0002, "epoch": 3.687374749498998, "step": 2760}, {"loss": 1.4976, "grad_norm": 0.6574140787124634, "learning_rate": 0.0002, "epoch": 3.7007348029392118, "step": 2770}, {"loss": 1.5306, "grad_norm": 0.5643761157989502, "learning_rate": 0.0002, "epoch": 3.7140948563794254, "step": 2780}, {"loss": 1.5751, "grad_norm": 0.5652621388435364, "learning_rate": 0.0002, "epoch": 3.727454909819639, "step": 2790}, {"loss": 1.5262, "grad_norm": 0.5604206323623657, "learning_rate": 0.0002, "epoch": 3.740814963259853, "step": 2800}, {"loss": 1.5013, "grad_norm": 3.911022663116455, "learning_rate": 0.0002, "epoch": 3.7541750167000667, "step": 2810}, {"loss": 1.5793, "grad_norm": 0.6148333549499512, "learning_rate": 0.0002, "epoch": 3.7675350701402808, "step": 2820}, {"loss": 1.5122, "grad_norm": 0.5605677962303162, "learning_rate": 0.0002, "epoch": 3.7808951235804944, "step": 2830}, {"loss": 1.5659, "grad_norm": 0.6101965308189392, "learning_rate": 0.0002, "epoch": 3.794255177020708, "step": 2840}, {"loss": 1.5618, "grad_norm": 0.5387342572212219, "learning_rate": 0.0002, "epoch": 3.8076152304609217, "step": 2850}, {"loss": 1.5193, "grad_norm": 0.5733087062835693, "learning_rate": 0.0002, "epoch": 3.8209752839011357, "step": 2860}, {"loss": 1.5545, "grad_norm": 0.6538485884666443, "learning_rate": 0.0002, "epoch": 3.8343353373413493, "step": 2870}, {"loss": 1.523, "grad_norm": 0.6247632503509521, "learning_rate": 0.0002, "epoch": 3.847695390781563, "step": 2880}, {"loss": 1.5591, "grad_norm": 0.5745735764503479, "learning_rate": 0.0002, "epoch": 3.861055444221777, "step": 2890}, {"loss": 1.5706, "grad_norm": 0.5942763686180115, "learning_rate": 0.0002, "epoch": 3.8744154976619907, "step": 2900}, {"loss": 1.564, "grad_norm": 0.7086281776428223, "learning_rate": 0.0002, "epoch": 3.8877755511022043, "step": 2910}, {"loss": 1.5526, "grad_norm": 0.8825129866600037, "learning_rate": 0.0002, "epoch": 3.901135604542418, "step": 2920}, {"loss": 1.4519, "grad_norm": 0.6260842680931091, "learning_rate": 0.0002, "epoch": 3.914495657982632, "step": 2930}, {"loss": 1.5433, "grad_norm": 0.6015968322753906, "learning_rate": 0.0002, "epoch": 3.9278557114228456, "step": 2940}, {"loss": 1.4931, "grad_norm": 0.7042809128761292, "learning_rate": 0.0002, "epoch": 3.9412157648630597, "step": 2950}, {"loss": 1.5596, "grad_norm": 0.5860083699226379, "learning_rate": 0.0002, "epoch": 3.9545758183032733, "step": 2960}, {"loss": 1.565, "grad_norm": 0.5939757823944092, "learning_rate": 0.0002, "epoch": 3.967935871743487, "step": 2970}, {"loss": 1.408, "grad_norm": 0.5523964166641235, "learning_rate": 0.0002, "epoch": 3.9812959251837006, "step": 2980}, {"loss": 1.5629, "grad_norm": 0.6380264759063721, "learning_rate": 0.0002, "epoch": 3.9946559786239146, "step": 2990}, {"eval_loss": 1.8875294923782349, "eval_runtime": 38.5837, "eval_samples_per_second": 13.348, "eval_steps_per_second": 1.685, "epoch": 4.0, "step": 2994}, {"loss": 1.4002, "grad_norm": 0.5478564500808716, "learning_rate": 0.0002, "epoch": 4.008016032064128, "step": 3000}, {"loss": 1.436, "grad_norm": 0.9384379982948303, "learning_rate": 0.0002, "epoch": 4.021376085504342, "step": 3010}, {"loss": 1.4127, "grad_norm": 0.7819344401359558, "learning_rate": 0.0002, "epoch": 4.034736138944556, "step": 3020}, {"loss": 1.326, "grad_norm": 0.7737417817115784, "learning_rate": 0.0002, "epoch": 4.04809619238477, "step": 3030}, {"loss": 1.3203, "grad_norm": 0.8893805742263794, "learning_rate": 0.0002, "epoch": 4.061456245824983, "step": 3040}, {"loss": 1.3913, "grad_norm": 0.7759843468666077, "learning_rate": 0.0002, "epoch": 4.074816299265197, "step": 3050}, {"loss": 1.2941, "grad_norm": 0.642654538154602, "learning_rate": 0.0002, "epoch": 4.0881763527054105, "step": 3060}, {"loss": 1.3204, "grad_norm": 0.8515549302101135, "learning_rate": 0.0002, "epoch": 4.101536406145625, "step": 3070}, {"loss": 1.3683, "grad_norm": 0.7033658623695374, "learning_rate": 0.0002, "epoch": 4.114896459585839, "step": 3080}, {"loss": 1.4159, "grad_norm": 0.7063882946968079, "learning_rate": 0.0002, "epoch": 4.128256513026052, "step": 3090}, {"loss": 1.384, "grad_norm": 0.6946853995323181, "learning_rate": 0.0002, "epoch": 4.141616566466266, "step": 3100}, {"loss": 1.3689, "grad_norm": 0.7286741137504578, "learning_rate": 0.0002, "epoch": 4.1549766199064795, "step": 3110}, {"loss": 1.3061, "grad_norm": 0.7894193530082703, "learning_rate": 0.0002, "epoch": 4.168336673346693, "step": 3120}, {"loss": 1.3346, "grad_norm": 0.7005895376205444, "learning_rate": 0.0002, "epoch": 4.181696726786907, "step": 3130}, {"loss": 1.3834, "grad_norm": 0.799567461013794, "learning_rate": 0.0002, "epoch": 4.195056780227121, "step": 3140}, {"loss": 1.3813, "grad_norm": 0.7010157108306885, "learning_rate": 0.0002, "epoch": 4.208416833667335, "step": 3150}, {"loss": 1.3637, "grad_norm": 0.7489650249481201, "learning_rate": 0.0002, "epoch": 4.2217768871075485, "step": 3160}, {"loss": 1.3546, "grad_norm": 0.7908048629760742, "learning_rate": 0.0002, "epoch": 4.235136940547762, "step": 3170}, {"loss": 1.3073, "grad_norm": 0.7002180814743042, "learning_rate": 0.0002, "epoch": 4.248496993987976, "step": 3180}, {"loss": 1.4525, "grad_norm": 0.8339495062828064, "learning_rate": 0.0002, "epoch": 4.261857047428189, "step": 3190}, {"loss": 1.3471, "grad_norm": 0.7884618043899536, "learning_rate": 0.0002, "epoch": 4.275217100868403, "step": 3200}, {"loss": 1.4261, "grad_norm": 0.7964122295379639, "learning_rate": 0.0002, "epoch": 4.2885771543086175, "step": 3210}, {"loss": 1.3506, "grad_norm": 0.838646650314331, "learning_rate": 0.0002, "epoch": 4.301937207748831, "step": 3220}, {"loss": 1.3738, "grad_norm": 0.8063107132911682, "learning_rate": 0.0002, "epoch": 4.315297261189045, "step": 3230}, {"loss": 1.3769, "grad_norm": 0.8147385120391846, "learning_rate": 0.0002, "epoch": 4.328657314629258, "step": 3240}, {"loss": 1.4118, "grad_norm": 0.7636798620223999, "learning_rate": 0.0002, "epoch": 4.342017368069472, "step": 3250}, {"loss": 1.3698, "grad_norm": 0.7530609965324402, "learning_rate": 0.0002, "epoch": 4.355377421509686, "step": 3260}, {"loss": 1.3507, "grad_norm": 0.8853573799133301, "learning_rate": 0.0002, "epoch": 4.3687374749499, "step": 3270}, {"loss": 1.3614, "grad_norm": 0.7180975675582886, "learning_rate": 0.0002, "epoch": 4.382097528390114, "step": 3280}, {"loss": 1.4119, "grad_norm": 0.837150514125824, "learning_rate": 0.0002, "epoch": 4.395457581830327, "step": 3290}, {"loss": 1.461, "grad_norm": 0.8370638489723206, "learning_rate": 0.0002, "epoch": 4.408817635270541, "step": 3300}, {"loss": 1.4478, "grad_norm": 0.7738229036331177, "learning_rate": 0.0002, "epoch": 4.422177688710755, "step": 3310}, {"loss": 1.4195, "grad_norm": 0.7665290832519531, "learning_rate": 0.0002, "epoch": 4.435537742150968, "step": 3320}, {"loss": 1.3308, "grad_norm": 0.7547745704650879, "learning_rate": 0.0002, "epoch": 4.448897795591183, "step": 3330}, {"loss": 1.4165, "grad_norm": 0.7421861290931702, "learning_rate": 0.0002, "epoch": 4.462257849031396, "step": 3340}, {"loss": 1.4244, "grad_norm": 0.8042104244232178, "learning_rate": 0.0002, "epoch": 4.47561790247161, "step": 3350}, {"loss": 1.365, "grad_norm": 0.8111839890480042, "learning_rate": 0.0002, "epoch": 4.488977955911824, "step": 3360}, {"loss": 1.3537, "grad_norm": 0.7998340129852295, "learning_rate": 0.0002, "epoch": 4.502338009352037, "step": 3370}, {"loss": 1.3812, "grad_norm": 0.7668877243995667, "learning_rate": 0.0002, "epoch": 4.515698062792251, "step": 3380}, {"loss": 1.3972, "grad_norm": 0.7986718416213989, "learning_rate": 0.0002, "epoch": 4.529058116232465, "step": 3390}, {"loss": 1.3582, "grad_norm": 0.6806602478027344, "learning_rate": 0.0002, "epoch": 4.542418169672679, "step": 3400}, {"loss": 1.3942, "grad_norm": 0.8788819909095764, "learning_rate": 0.0002, "epoch": 4.555778223112893, "step": 3410}, {"loss": 1.3379, "grad_norm": 0.7499664425849915, "learning_rate": 0.0002, "epoch": 4.569138276553106, "step": 3420}, {"loss": 1.3823, "grad_norm": 0.7967109084129333, "learning_rate": 0.0002, "epoch": 4.58249832999332, "step": 3430}, {"loss": 1.3531, "grad_norm": 0.759639322757721, "learning_rate": 0.0002, "epoch": 4.595858383433534, "step": 3440}, {"loss": 1.3517, "grad_norm": 0.8327916264533997, "learning_rate": 0.0002, "epoch": 4.609218436873747, "step": 3450}, {"loss": 1.4619, "grad_norm": 0.7400892376899719, "learning_rate": 0.0002, "epoch": 4.622578490313961, "step": 3460}, {"loss": 1.3374, "grad_norm": 0.8116602301597595, "learning_rate": 0.0002, "epoch": 4.635938543754175, "step": 3470}, {"loss": 1.4445, "grad_norm": 0.7604362368583679, "learning_rate": 0.0002, "epoch": 4.649298597194389, "step": 3480}, {"loss": 1.3724, "grad_norm": 0.7397996783256531, "learning_rate": 0.0002, "epoch": 4.662658650634603, "step": 3490}, {"loss": 1.4048, "grad_norm": 0.869293749332428, "learning_rate": 0.0002, "epoch": 4.676018704074816, "step": 3500}, {"loss": 1.3873, "grad_norm": 0.6854358315467834, "learning_rate": 0.0002, "epoch": 4.68937875751503, "step": 3510}, {"loss": 1.3413, "grad_norm": 0.8326661586761475, "learning_rate": 0.0002, "epoch": 4.7027388109552435, "step": 3520}, {"loss": 1.3666, "grad_norm": 0.6887506246566772, "learning_rate": 0.0002, "epoch": 4.716098864395457, "step": 3530}, {"loss": 1.4508, "grad_norm": 3.837689161300659, "learning_rate": 0.0002, "epoch": 4.729458917835672, "step": 3540}, {"loss": 1.3775, "grad_norm": 0.6874563694000244, "learning_rate": 0.0002, "epoch": 4.742818971275885, "step": 3550}, {"loss": 1.3643, "grad_norm": 0.8340407609939575, "learning_rate": 0.0002, "epoch": 4.756179024716099, "step": 3560}, {"loss": 1.3556, "grad_norm": 0.7286418676376343, "learning_rate": 0.0002, "epoch": 4.7695390781563125, "step": 3570}, {"loss": 1.4338, "grad_norm": 0.7239373326301575, "learning_rate": 0.0002, "epoch": 4.782899131596526, "step": 3580}, {"loss": 1.4697, "grad_norm": 0.831310510635376, "learning_rate": 0.0002, "epoch": 4.796259185036741, "step": 3590}, {"loss": 1.4146, "grad_norm": 0.767715573310852, "learning_rate": 0.0002, "epoch": 4.809619238476954, "step": 3600}, {"loss": 1.4199, "grad_norm": 0.9013199210166931, "learning_rate": 0.0002, "epoch": 4.822979291917168, "step": 3610}, {"loss": 1.4513, "grad_norm": 0.7543512582778931, "learning_rate": 0.0002, "epoch": 4.8363393453573815, "step": 3620}, {"loss": 1.4218, "grad_norm": 0.7626057267189026, "learning_rate": 0.0002, "epoch": 4.849699398797595, "step": 3630}, {"loss": 1.4102, "grad_norm": 0.847079336643219, "learning_rate": 0.0002, "epoch": 4.863059452237809, "step": 3640}, {"loss": 1.5014, "grad_norm": 0.8273295760154724, "learning_rate": 0.0002, "epoch": 4.876419505678022, "step": 3650}, {"loss": 1.3806, "grad_norm": 0.7675244808197021, "learning_rate": 0.0002, "epoch": 4.889779559118237, "step": 3660}, {"loss": 1.4894, "grad_norm": 0.9560356736183167, "learning_rate": 0.0002, "epoch": 4.9031396125584505, "step": 3670}, {"loss": 1.4044, "grad_norm": 0.7682451605796814, "learning_rate": 0.0002, "epoch": 4.916499665998664, "step": 3680}, {"loss": 1.342, "grad_norm": 0.8113830089569092, "learning_rate": 0.0002, "epoch": 4.929859719438878, "step": 3690}, {"loss": 1.3559, "grad_norm": 0.7642542719841003, "learning_rate": 0.0002, "epoch": 4.943219772879091, "step": 3700}, {"loss": 1.403, "grad_norm": 0.823863685131073, "learning_rate": 0.0002, "epoch": 4.956579826319305, "step": 3710}, {"loss": 1.464, "grad_norm": 0.8287797570228577, "learning_rate": 0.0002, "epoch": 4.969939879759519, "step": 3720}, {"loss": 1.4139, "grad_norm": 0.778170108795166, "learning_rate": 0.0002, "epoch": 4.983299933199733, "step": 3730}, {"loss": 1.4218, "grad_norm": 0.7464073896408081, "learning_rate": 0.0002, "epoch": 4.996659986639947, "step": 3740}]}
+{"epoch": 6.0, "step": 4491, "epoch_duration": 811.1629409790039, "total_accumulated_duration": 4964.386669635773, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7568.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.6569, "grad_norm": 0.5097216367721558, "learning_rate": 0.0002, "epoch": 0.013360053440213761, "step": 10}, {"loss": 2.2557, "grad_norm": 0.5924790501594543, "learning_rate": 0.0002, "epoch": 0.026720106880427523, "step": 20}, {"loss": 2.0626, "grad_norm": 0.5158102512359619, "learning_rate": 0.0002, "epoch": 0.04008016032064128, "step": 30}, {"loss": 1.9452, "grad_norm": 0.5033753514289856, "learning_rate": 0.0002, "epoch": 0.053440213760855046, "step": 40}, {"loss": 1.9128, "grad_norm": 0.5390949845314026, "learning_rate": 0.0002, "epoch": 0.06680026720106881, "step": 50}, {"loss": 1.937, "grad_norm": 0.6376217007637024, "learning_rate": 0.0002, "epoch": 0.08016032064128256, "step": 60}, {"loss": 1.929, "grad_norm": 0.4202035069465637, "learning_rate": 0.0002, "epoch": 0.09352037408149633, "step": 70}, {"loss": 1.811, "grad_norm": 0.4269474744796753, "learning_rate": 0.0002, "epoch": 0.10688042752171009, "step": 80}, {"loss": 1.8303, "grad_norm": 0.4306574761867523, "learning_rate": 0.0002, "epoch": 0.12024048096192384, "step": 90}, {"loss": 1.8469, "grad_norm": 0.5297011137008667, "learning_rate": 0.0002, "epoch": 0.13360053440213762, "step": 100}, {"loss": 1.864, "grad_norm": 1.2313778400421143, "learning_rate": 0.0002, "epoch": 0.14696058784235136, "step": 110}, {"loss": 1.8531, "grad_norm": 0.5351294279098511, "learning_rate": 0.0002, "epoch": 0.16032064128256512, "step": 120}, {"loss": 1.9232, "grad_norm": 0.4848092496395111, "learning_rate": 0.0002, "epoch": 0.1736806947227789, "step": 130}, {"loss": 1.8633, "grad_norm": 0.4339500665664673, "learning_rate": 0.0002, "epoch": 0.18704074816299265, "step": 140}, {"loss": 1.816, "grad_norm": 0.46877285838127136, "learning_rate": 0.0002, "epoch": 0.20040080160320642, "step": 150}, {"loss": 1.8033, "grad_norm": 0.5600412487983704, "learning_rate": 0.0002, "epoch": 0.21376085504342018, "step": 160}, {"loss": 1.8162, "grad_norm": 0.3733620345592499, "learning_rate": 0.0002, "epoch": 0.22712090848363392, "step": 170}, {"loss": 1.8564, "grad_norm": 0.5116042494773865, "learning_rate": 0.0002, "epoch": 0.24048096192384769, "step": 180}, {"loss": 1.915, "grad_norm": 0.4071602523326874, "learning_rate": 0.0002, "epoch": 0.25384101536406145, "step": 190}, {"loss": 1.7984, "grad_norm": 0.44189608097076416, "learning_rate": 0.0002, "epoch": 0.26720106880427524, "step": 200}, {"loss": 1.8728, "grad_norm": 0.398699015378952, "learning_rate": 0.0002, "epoch": 0.280561122244489, "step": 210}, {"loss": 1.8205, "grad_norm": 0.3585626482963562, "learning_rate": 0.0002, "epoch": 0.2939211756847027, "step": 220}, {"loss": 1.8861, "grad_norm": 0.3811776041984558, "learning_rate": 0.0002, "epoch": 0.3072812291249165, "step": 230}, {"loss": 1.8365, "grad_norm": 0.37261509895324707, "learning_rate": 0.0002, "epoch": 0.32064128256513025, "step": 240}, {"loss": 1.9186, "grad_norm": 0.39762404561042786, "learning_rate": 0.0002, "epoch": 0.33400133600534404, "step": 250}, {"loss": 1.7965, "grad_norm": 0.3509528934955597, "learning_rate": 0.0002, "epoch": 0.3473613894455578, "step": 260}, {"loss": 1.7802, "grad_norm": 0.3169104754924774, "learning_rate": 0.0002, "epoch": 0.36072144288577157, "step": 270}, {"loss": 1.8038, "grad_norm": 0.33714795112609863, "learning_rate": 0.0002, "epoch": 0.3740814963259853, "step": 280}, {"loss": 1.787, "grad_norm": 1.2936875820159912, "learning_rate": 0.0002, "epoch": 0.38744154976619904, "step": 290}, {"loss": 1.7974, "grad_norm": 0.3459427058696747, "learning_rate": 0.0002, "epoch": 0.40080160320641284, "step": 300}, {"loss": 1.8879, "grad_norm": 0.3380655348300934, "learning_rate": 0.0002, "epoch": 0.4141616566466266, "step": 310}, {"loss": 1.9196, "grad_norm": 0.3890381455421448, "learning_rate": 0.0002, "epoch": 0.42752171008684037, "step": 320}, {"loss": 1.8034, "grad_norm": 0.432327002286911, "learning_rate": 0.0002, "epoch": 0.4408817635270541, "step": 330}, {"loss": 1.8443, "grad_norm": 0.3736560046672821, "learning_rate": 0.0002, "epoch": 0.45424181696726784, "step": 340}, {"loss": 1.8506, "grad_norm": 0.3700982630252838, "learning_rate": 0.0002, "epoch": 0.46760187040748163, "step": 350}, {"loss": 1.7978, "grad_norm": 0.4533902406692505, "learning_rate": 0.0002, "epoch": 0.48096192384769537, "step": 360}, {"loss": 1.7427, "grad_norm": 0.35999053716659546, "learning_rate": 0.0002, "epoch": 0.49432197728790916, "step": 370}, {"loss": 1.7995, "grad_norm": 0.3490903675556183, "learning_rate": 0.0002, "epoch": 0.5076820307281229, "step": 380}, {"loss": 1.8709, "grad_norm": 0.34704291820526123, "learning_rate": 0.0002, "epoch": 0.5210420841683366, "step": 390}, {"loss": 1.7948, "grad_norm": 0.343565434217453, "learning_rate": 0.0002, "epoch": 0.5344021376085505, "step": 400}, {"loss": 1.8564, "grad_norm": 0.3573552966117859, "learning_rate": 0.0002, "epoch": 0.5477621910487642, "step": 410}, {"loss": 1.8477, "grad_norm": 0.32980719208717346, "learning_rate": 0.0002, "epoch": 0.561122244488978, "step": 420}, {"loss": 1.9233, "grad_norm": 0.356952428817749, "learning_rate": 0.0002, "epoch": 0.5744822979291917, "step": 430}, {"loss": 1.7433, "grad_norm": 0.3170869052410126, "learning_rate": 0.0002, "epoch": 0.5878423513694054, "step": 440}, {"loss": 1.7607, "grad_norm": 0.35233718156814575, "learning_rate": 0.0002, "epoch": 0.6012024048096193, "step": 450}, {"loss": 1.8111, "grad_norm": 0.3480125367641449, "learning_rate": 0.0002, "epoch": 0.614562458249833, "step": 460}, {"loss": 1.8386, "grad_norm": 0.4762810468673706, "learning_rate": 0.0002, "epoch": 0.6279225116900468, "step": 470}, {"loss": 1.805, "grad_norm": 0.3907663822174072, "learning_rate": 0.0002, "epoch": 0.6412825651302605, "step": 480}, {"loss": 1.8113, "grad_norm": 0.36315613985061646, "learning_rate": 0.0002, "epoch": 0.6546426185704742, "step": 490}, {"loss": 1.7805, "grad_norm": 0.377796471118927, "learning_rate": 0.0002, "epoch": 0.6680026720106881, "step": 500}, {"loss": 1.7457, "grad_norm": 0.34284207224845886, "learning_rate": 0.0002, "epoch": 0.6813627254509018, "step": 510}, {"loss": 1.8013, "grad_norm": 0.35563018918037415, "learning_rate": 0.0002, "epoch": 0.6947227788911156, "step": 520}, {"loss": 1.8414, "grad_norm": 0.37575867772102356, "learning_rate": 0.0002, "epoch": 0.7080828323313293, "step": 530}, {"loss": 1.7993, "grad_norm": 0.35719701647758484, "learning_rate": 0.0002, "epoch": 0.7214428857715431, "step": 540}, {"loss": 1.7574, "grad_norm": 0.385813444852829, "learning_rate": 0.0002, "epoch": 0.7348029392117569, "step": 550}, {"loss": 1.7985, "grad_norm": 0.44509607553482056, "learning_rate": 0.0002, "epoch": 0.7481629926519706, "step": 560}, {"loss": 1.7459, "grad_norm": 0.36108464002609253, "learning_rate": 0.0002, "epoch": 0.7615230460921844, "step": 570}, {"loss": 1.8207, "grad_norm": 0.3530745804309845, "learning_rate": 0.0002, "epoch": 0.7748830995323981, "step": 580}, {"loss": 1.7479, "grad_norm": 0.34888574481010437, "learning_rate": 0.0002, "epoch": 0.7882431529726119, "step": 590}, {"loss": 1.8656, "grad_norm": 0.387346476316452, "learning_rate": 0.0002, "epoch": 0.8016032064128257, "step": 600}, {"loss": 1.8071, "grad_norm": 0.3641138970851898, "learning_rate": 0.0002, "epoch": 0.8149632598530394, "step": 610}, {"loss": 1.7531, "grad_norm": 0.33729103207588196, "learning_rate": 0.0002, "epoch": 0.8283233132932531, "step": 620}, {"loss": 1.8613, "grad_norm": 0.3652004599571228, "learning_rate": 0.0002, "epoch": 0.8416833667334669, "step": 630}, {"loss": 1.9184, "grad_norm": 0.3986643850803375, "learning_rate": 0.0002, "epoch": 0.8550434201736807, "step": 640}, {"loss": 1.8198, "grad_norm": 0.3458964228630066, "learning_rate": 0.0002, "epoch": 0.8684034736138945, "step": 650}, {"loss": 1.803, "grad_norm": 0.3559381365776062, "learning_rate": 0.0002, "epoch": 0.8817635270541082, "step": 660}, {"loss": 1.7641, "grad_norm": 0.3612841069698334, "learning_rate": 0.0002, "epoch": 0.895123580494322, "step": 670}, {"loss": 1.7888, "grad_norm": 0.34771719574928284, "learning_rate": 0.0002, "epoch": 0.9084836339345357, "step": 680}, {"loss": 1.8204, "grad_norm": 0.3371497094631195, "learning_rate": 0.0002, "epoch": 0.9218436873747495, "step": 690}, {"loss": 1.7848, "grad_norm": 0.5596055388450623, "learning_rate": 0.0002, "epoch": 0.9352037408149633, "step": 700}, {"loss": 1.7794, "grad_norm": 0.311880499124527, "learning_rate": 0.0002, "epoch": 0.948563794255177, "step": 710}, {"loss": 1.8464, "grad_norm": 0.3462068736553192, "learning_rate": 0.0002, "epoch": 0.9619238476953907, "step": 720}, {"loss": 1.8197, "grad_norm": 0.29982393980026245, "learning_rate": 0.0002, "epoch": 0.9752839011356046, "step": 730}, {"loss": 1.8503, "grad_norm": 0.34606459736824036, "learning_rate": 0.0002, "epoch": 0.9886439545758183, "step": 740}, {"eval_loss": 1.8201380968093872, "eval_runtime": 38.6124, "eval_samples_per_second": 13.338, "eval_steps_per_second": 1.683, "epoch": 0.9993319973279893, "step": 748}, {"loss": 1.7786, "grad_norm": 0.32302048802375793, "learning_rate": 0.0002, "epoch": 1.002004008016032, "step": 750}, {"loss": 1.7297, "grad_norm": 0.37585633993148804, "learning_rate": 0.0002, "epoch": 1.0153640614562458, "step": 760}, {"loss": 1.7008, "grad_norm": 0.33826273679733276, "learning_rate": 0.0002, "epoch": 1.0287241148964597, "step": 770}, {"loss": 1.809, "grad_norm": 0.44682955741882324, "learning_rate": 0.0002, "epoch": 1.0420841683366733, "step": 780}, {"loss": 1.7092, "grad_norm": 0.422188401222229, "learning_rate": 0.0002, "epoch": 1.0554442217768871, "step": 790}, {"loss": 1.7765, "grad_norm": 0.3809906244277954, "learning_rate": 0.0002, "epoch": 1.0688042752171008, "step": 800}, {"loss": 1.7431, "grad_norm": 0.3454349637031555, "learning_rate": 0.0002, "epoch": 1.0821643286573146, "step": 810}, {"loss": 1.7257, "grad_norm": 0.3767355978488922, "learning_rate": 0.0002, "epoch": 1.0955243820975284, "step": 820}, {"loss": 1.7224, "grad_norm": 0.3361407518386841, "learning_rate": 0.0002, "epoch": 1.108884435537742, "step": 830}, {"loss": 1.7509, "grad_norm": 0.3654632568359375, "learning_rate": 0.0002, "epoch": 1.122244488977956, "step": 840}, {"loss": 1.7151, "grad_norm": 0.3822861313819885, "learning_rate": 0.0002, "epoch": 1.1356045424181698, "step": 850}, {"loss": 1.7121, "grad_norm": 0.3853831887245178, "learning_rate": 0.0002, "epoch": 1.1489645958583834, "step": 860}, {"loss": 1.7685, "grad_norm": 0.35521796345710754, "learning_rate": 0.0002, "epoch": 1.1623246492985972, "step": 870}, {"loss": 1.7735, "grad_norm": 0.4107200503349304, "learning_rate": 0.0002, "epoch": 1.1756847027388109, "step": 880}, {"loss": 1.7484, "grad_norm": 0.33219534158706665, "learning_rate": 0.0002, "epoch": 1.1890447561790247, "step": 890}, {"loss": 1.7071, "grad_norm": 0.3559704124927521, "learning_rate": 0.0002, "epoch": 1.2024048096192386, "step": 900}, {"loss": 1.7535, "grad_norm": 0.3700537383556366, "learning_rate": 0.0002, "epoch": 1.2157648630594522, "step": 910}, {"loss": 1.7513, "grad_norm": 0.3771909475326538, "learning_rate": 0.0002, "epoch": 1.229124916499666, "step": 920}, {"loss": 1.7566, "grad_norm": 0.3136613965034485, "learning_rate": 0.0002, "epoch": 1.2424849699398797, "step": 930}, {"loss": 1.6783, "grad_norm": 0.3952099084854126, "learning_rate": 0.0002, "epoch": 1.2558450233800935, "step": 940}, {"loss": 1.7691, "grad_norm": 0.36534377932548523, "learning_rate": 0.0002, "epoch": 1.2692050768203074, "step": 950}, {"loss": 1.7127, "grad_norm": 0.3803492486476898, "learning_rate": 0.0002, "epoch": 1.282565130260521, "step": 960}, {"loss": 1.7896, "grad_norm": 0.3992428183555603, "learning_rate": 0.0002, "epoch": 1.2959251837007348, "step": 970}, {"loss": 1.7343, "grad_norm": 0.3627142906188965, "learning_rate": 0.0002, "epoch": 1.3092852371409487, "step": 980}, {"loss": 1.7598, "grad_norm": 0.4248180091381073, "learning_rate": 0.0002, "epoch": 1.3226452905811623, "step": 990}, {"loss": 1.6896, "grad_norm": 0.4060308039188385, "learning_rate": 0.0002, "epoch": 1.3360053440213762, "step": 1000}, {"loss": 1.7457, "grad_norm": 0.3788969814777374, "learning_rate": 0.0002, "epoch": 1.3493653974615898, "step": 1010}, {"loss": 1.7111, "grad_norm": 0.4174270033836365, "learning_rate": 0.0002, "epoch": 1.3627254509018036, "step": 1020}, {"loss": 1.7975, "grad_norm": 0.35500675439834595, "learning_rate": 0.0002, "epoch": 1.3760855043420173, "step": 1030}, {"loss": 1.724, "grad_norm": 0.3454059362411499, "learning_rate": 0.0002, "epoch": 1.389445557782231, "step": 1040}, {"loss": 1.8299, "grad_norm": 0.45807570219039917, "learning_rate": 0.0002, "epoch": 1.402805611222445, "step": 1050}, {"loss": 1.7425, "grad_norm": 0.39338022470474243, "learning_rate": 0.0002, "epoch": 1.4161656646626586, "step": 1060}, {"loss": 1.7457, "grad_norm": 0.3870709240436554, "learning_rate": 0.0002, "epoch": 1.4295257181028724, "step": 1070}, {"loss": 1.6565, "grad_norm": 0.40996190905570984, "learning_rate": 0.0002, "epoch": 1.4428857715430863, "step": 1080}, {"loss": 1.7324, "grad_norm": 0.38762837648391724, "learning_rate": 0.0002, "epoch": 1.4562458249833, "step": 1090}, {"loss": 1.7362, "grad_norm": 0.36756977438926697, "learning_rate": 0.0002, "epoch": 1.4696058784235138, "step": 1100}, {"loss": 1.7451, "grad_norm": 0.4087235927581787, "learning_rate": 0.0002, "epoch": 1.4829659318637274, "step": 1110}, {"loss": 1.7114, "grad_norm": 0.3357745110988617, "learning_rate": 0.0002, "epoch": 1.4963259853039412, "step": 1120}, {"loss": 1.6877, "grad_norm": 0.37486532330513, "learning_rate": 0.0002, "epoch": 1.5096860387441549, "step": 1130}, {"loss": 1.7252, "grad_norm": 0.3387809991836548, "learning_rate": 0.0002, "epoch": 1.5230460921843687, "step": 1140}, {"loss": 1.7169, "grad_norm": 0.37462118268013, "learning_rate": 0.0002, "epoch": 1.5364061456245826, "step": 1150}, {"loss": 1.6988, "grad_norm": 0.38575324416160583, "learning_rate": 0.0002, "epoch": 1.5497661990647962, "step": 1160}, {"loss": 1.7438, "grad_norm": 0.3515765964984894, "learning_rate": 0.0002, "epoch": 1.56312625250501, "step": 1170}, {"loss": 1.7524, "grad_norm": 0.39308643341064453, "learning_rate": 0.0002, "epoch": 1.5764863059452239, "step": 1180}, {"loss": 1.6422, "grad_norm": 0.3308864235877991, "learning_rate": 0.0002, "epoch": 1.5898463593854375, "step": 1190}, {"loss": 1.7566, "grad_norm": 0.3397478461265564, "learning_rate": 0.0002, "epoch": 1.6032064128256514, "step": 1200}, {"loss": 1.7871, "grad_norm": 0.3911525309085846, "learning_rate": 0.0002, "epoch": 1.6165664662658652, "step": 1210}, {"loss": 1.7443, "grad_norm": 0.3771969974040985, "learning_rate": 0.0002, "epoch": 1.6299265197060788, "step": 1220}, {"loss": 1.7631, "grad_norm": 0.35346856713294983, "learning_rate": 0.0002, "epoch": 1.6432865731462925, "step": 1230}, {"loss": 1.7225, "grad_norm": 0.41736963391304016, "learning_rate": 0.0002, "epoch": 1.6566466265865063, "step": 1240}, {"loss": 1.7582, "grad_norm": 0.3375225067138672, "learning_rate": 0.0002, "epoch": 1.6700066800267201, "step": 1250}, {"loss": 1.6916, "grad_norm": 0.3779928982257843, "learning_rate": 0.0002, "epoch": 1.6833667334669338, "step": 1260}, {"loss": 1.728, "grad_norm": 0.35388994216918945, "learning_rate": 0.0002, "epoch": 1.6967267869071476, "step": 1270}, {"loss": 1.7461, "grad_norm": 0.33884134888648987, "learning_rate": 0.0002, "epoch": 1.7100868403473615, "step": 1280}, {"loss": 1.7083, "grad_norm": 0.35439756512641907, "learning_rate": 0.0002, "epoch": 1.723446893787575, "step": 1290}, {"loss": 1.7389, "grad_norm": 0.3766156733036041, "learning_rate": 0.0002, "epoch": 1.736806947227789, "step": 1300}, {"loss": 1.7847, "grad_norm": 0.36148911714553833, "learning_rate": 0.0002, "epoch": 1.7501670006680028, "step": 1310}, {"loss": 1.7344, "grad_norm": 0.39687496423721313, "learning_rate": 0.0002, "epoch": 1.7635270541082164, "step": 1320}, {"loss": 1.7541, "grad_norm": 0.35639452934265137, "learning_rate": 0.0002, "epoch": 1.77688710754843, "step": 1330}, {"loss": 1.7254, "grad_norm": 0.38781628012657166, "learning_rate": 0.0002, "epoch": 1.7902471609886441, "step": 1340}, {"loss": 1.7867, "grad_norm": 0.42784637212753296, "learning_rate": 0.0002, "epoch": 1.8036072144288577, "step": 1350}, {"loss": 1.7336, "grad_norm": 0.40258511900901794, "learning_rate": 0.0002, "epoch": 1.8169672678690714, "step": 1360}, {"loss": 1.7771, "grad_norm": 0.36674195528030396, "learning_rate": 0.0002, "epoch": 1.8303273213092852, "step": 1370}, {"loss": 1.7425, "grad_norm": 0.4064558446407318, "learning_rate": 0.0002, "epoch": 1.843687374749499, "step": 1380}, {"loss": 1.7425, "grad_norm": 0.3669849932193756, "learning_rate": 0.0002, "epoch": 1.8570474281897127, "step": 1390}, {"loss": 1.7924, "grad_norm": 0.37569567561149597, "learning_rate": 0.0002, "epoch": 1.8704074816299265, "step": 1400}, {"loss": 1.7885, "grad_norm": 0.37307995557785034, "learning_rate": 0.0002, "epoch": 1.8837675350701404, "step": 1410}, {"loss": 1.7548, "grad_norm": 0.3772695064544678, "learning_rate": 0.0002, "epoch": 1.897127588510354, "step": 1420}, {"loss": 1.7682, "grad_norm": 0.36993589997291565, "learning_rate": 0.0002, "epoch": 1.9104876419505676, "step": 1430}, {"loss": 1.7249, "grad_norm": 0.3490557372570038, "learning_rate": 0.0002, "epoch": 1.9238476953907817, "step": 1440}, {"loss": 1.7979, "grad_norm": 0.3716149628162384, "learning_rate": 0.0002, "epoch": 1.9372077488309953, "step": 1450}, {"loss": 1.6664, "grad_norm": 0.39236098527908325, "learning_rate": 0.0002, "epoch": 1.950567802271209, "step": 1460}, {"loss": 1.6852, "grad_norm": 0.37258651852607727, "learning_rate": 0.0002, "epoch": 1.9639278557114228, "step": 1470}, {"loss": 1.7427, "grad_norm": 0.36183077096939087, "learning_rate": 0.0002, "epoch": 1.9772879091516367, "step": 1480}, {"loss": 1.7055, "grad_norm": 0.3956947326660156, "learning_rate": 0.0002, "epoch": 1.9906479625918503, "step": 1490}, {"eval_loss": 1.8132041692733765, "eval_runtime": 38.6287, "eval_samples_per_second": 13.332, "eval_steps_per_second": 1.683, "epoch": 2.0, "step": 1497}, {"loss": 1.6791, "grad_norm": 0.34480565786361694, "learning_rate": 0.0002, "epoch": 2.004008016032064, "step": 1500}, {"loss": 1.6367, "grad_norm": 0.3418028652667999, "learning_rate": 0.0002, "epoch": 2.017368069472278, "step": 1510}, {"loss": 1.5827, "grad_norm": 0.4514467716217041, "learning_rate": 0.0002, "epoch": 2.0307281229124916, "step": 1520}, {"loss": 1.6365, "grad_norm": 0.4197506606578827, "learning_rate": 0.0002, "epoch": 2.0440881763527052, "step": 1530}, {"loss": 1.6221, "grad_norm": 0.4134170711040497, "learning_rate": 0.0002, "epoch": 2.0574482297929193, "step": 1540}, {"loss": 1.6876, "grad_norm": 0.43709826469421387, "learning_rate": 0.0002, "epoch": 2.070808283233133, "step": 1550}, {"loss": 1.5779, "grad_norm": 0.4703378677368164, "learning_rate": 0.0002, "epoch": 2.0841683366733466, "step": 1560}, {"loss": 1.599, "grad_norm": 0.4538188576698303, "learning_rate": 0.0002, "epoch": 2.0975283901135606, "step": 1570}, {"loss": 1.6464, "grad_norm": 0.4649668037891388, "learning_rate": 0.0002, "epoch": 2.1108884435537743, "step": 1580}, {"loss": 1.6348, "grad_norm": 0.42669883370399475, "learning_rate": 0.0002, "epoch": 2.124248496993988, "step": 1590}, {"loss": 1.5838, "grad_norm": 0.43162038922309875, "learning_rate": 0.0002, "epoch": 2.1376085504342015, "step": 1600}, {"loss": 1.6673, "grad_norm": 0.4294586479663849, "learning_rate": 0.0002, "epoch": 2.1509686038744156, "step": 1610}, {"loss": 1.6024, "grad_norm": 0.4669102132320404, "learning_rate": 0.0002, "epoch": 2.164328657314629, "step": 1620}, {"loss": 1.659, "grad_norm": 0.4188412129878998, "learning_rate": 0.0002, "epoch": 2.177688710754843, "step": 1630}, {"loss": 1.625, "grad_norm": 0.4662680923938751, "learning_rate": 0.0002, "epoch": 2.191048764195057, "step": 1640}, {"loss": 1.6699, "grad_norm": 0.4020286500453949, "learning_rate": 0.0002, "epoch": 2.2044088176352705, "step": 1650}, {"loss": 1.6284, "grad_norm": 0.41919606924057007, "learning_rate": 0.0002, "epoch": 2.217768871075484, "step": 1660}, {"loss": 1.6776, "grad_norm": 0.4644531309604645, "learning_rate": 0.0002, "epoch": 2.231128924515698, "step": 1670}, {"loss": 1.6711, "grad_norm": 0.4526427984237671, "learning_rate": 0.0002, "epoch": 2.244488977955912, "step": 1680}, {"loss": 1.6058, "grad_norm": 0.45953166484832764, "learning_rate": 0.0002, "epoch": 2.2578490313961255, "step": 1690}, {"loss": 1.5979, "grad_norm": 0.4701860249042511, "learning_rate": 0.0002, "epoch": 2.2712090848363395, "step": 1700}, {"loss": 1.6183, "grad_norm": 0.4749310612678528, "learning_rate": 0.0002, "epoch": 2.284569138276553, "step": 1710}, {"loss": 1.6703, "grad_norm": 0.45026102662086487, "learning_rate": 0.0002, "epoch": 2.297929191716767, "step": 1720}, {"loss": 1.6386, "grad_norm": 0.4755004048347473, "learning_rate": 0.0002, "epoch": 2.3112892451569804, "step": 1730}, {"loss": 1.6365, "grad_norm": 0.4505726993083954, "learning_rate": 0.0002, "epoch": 2.3246492985971945, "step": 1740}, {"loss": 1.589, "grad_norm": 0.44464054703712463, "learning_rate": 0.0002, "epoch": 2.338009352037408, "step": 1750}, {"loss": 1.6139, "grad_norm": 0.4449476897716522, "learning_rate": 0.0002, "epoch": 2.3513694054776217, "step": 1760}, {"loss": 1.7195, "grad_norm": 0.4216482937335968, "learning_rate": 0.0002, "epoch": 2.364729458917836, "step": 1770}, {"loss": 1.7075, "grad_norm": 0.4379308521747589, "learning_rate": 0.0002, "epoch": 2.3780895123580494, "step": 1780}, {"loss": 1.7024, "grad_norm": 0.41670042276382446, "learning_rate": 0.0002, "epoch": 2.391449565798263, "step": 1790}, {"loss": 1.5989, "grad_norm": 0.48089510202407837, "learning_rate": 0.0002, "epoch": 2.404809619238477, "step": 1800}, {"loss": 1.6313, "grad_norm": 0.4389738142490387, "learning_rate": 0.0002, "epoch": 2.4181696726786908, "step": 1810}, {"loss": 1.5841, "grad_norm": 0.45293036103248596, "learning_rate": 0.0002, "epoch": 2.4315297261189044, "step": 1820}, {"loss": 1.6887, "grad_norm": 0.5211683511734009, "learning_rate": 0.0002, "epoch": 2.4448897795591185, "step": 1830}, {"loss": 1.6599, "grad_norm": 0.4631884694099426, "learning_rate": 0.0002, "epoch": 2.458249832999332, "step": 1840}, {"loss": 1.6537, "grad_norm": 0.4276818335056305, "learning_rate": 0.0002, "epoch": 2.4716098864395457, "step": 1850}, {"loss": 1.6836, "grad_norm": 0.477524071931839, "learning_rate": 0.0002, "epoch": 2.4849699398797593, "step": 1860}, {"loss": 1.66, "grad_norm": 0.44860973954200745, "learning_rate": 0.0002, "epoch": 2.4983299933199734, "step": 1870}, {"loss": 1.6308, "grad_norm": 0.46413546800613403, "learning_rate": 0.0002, "epoch": 2.511690046760187, "step": 1880}, {"loss": 1.6225, "grad_norm": 0.42487645149230957, "learning_rate": 0.0002, "epoch": 2.5250501002004007, "step": 1890}, {"loss": 1.6268, "grad_norm": 0.4778307378292084, "learning_rate": 0.0002, "epoch": 2.5384101536406147, "step": 1900}, {"loss": 1.6143, "grad_norm": 0.45307061076164246, "learning_rate": 0.0002, "epoch": 2.5517702070808284, "step": 1910}, {"loss": 1.7279, "grad_norm": 0.47886642813682556, "learning_rate": 0.0002, "epoch": 2.565130260521042, "step": 1920}, {"loss": 1.5931, "grad_norm": 0.4839435815811157, "learning_rate": 0.0002, "epoch": 2.5784903139612556, "step": 1930}, {"loss": 1.6089, "grad_norm": 0.4388359785079956, "learning_rate": 0.0002, "epoch": 2.5918503674014697, "step": 1940}, {"loss": 1.6828, "grad_norm": 0.47859734296798706, "learning_rate": 0.0002, "epoch": 2.6052104208416833, "step": 1950}, {"loss": 1.6014, "grad_norm": 0.5526517033576965, "learning_rate": 0.0002, "epoch": 2.6185704742818974, "step": 1960}, {"loss": 1.6889, "grad_norm": 0.5449170470237732, "learning_rate": 0.0002, "epoch": 2.631930527722111, "step": 1970}, {"loss": 1.6481, "grad_norm": 0.48521968722343445, "learning_rate": 0.0002, "epoch": 2.6452905811623246, "step": 1980}, {"loss": 1.6741, "grad_norm": 0.4733737111091614, "learning_rate": 0.0002, "epoch": 2.6586506346025383, "step": 1990}, {"loss": 1.662, "grad_norm": 0.507118284702301, "learning_rate": 0.0002, "epoch": 2.6720106880427523, "step": 2000}, {"loss": 1.6419, "grad_norm": 0.4508971571922302, "learning_rate": 0.0002, "epoch": 2.685370741482966, "step": 2010}, {"loss": 1.7052, "grad_norm": 0.4657728672027588, "learning_rate": 0.0002, "epoch": 2.6987307949231796, "step": 2020}, {"loss": 1.6261, "grad_norm": 0.48647549748420715, "learning_rate": 0.0002, "epoch": 2.7120908483633936, "step": 2030}, {"loss": 1.5638, "grad_norm": 0.49525555968284607, "learning_rate": 0.0002, "epoch": 2.7254509018036073, "step": 2040}, {"loss": 1.658, "grad_norm": 0.4712379276752472, "learning_rate": 0.0002, "epoch": 2.738810955243821, "step": 2050}, {"loss": 1.6464, "grad_norm": 0.4846591055393219, "learning_rate": 0.0002, "epoch": 2.7521710086840345, "step": 2060}, {"loss": 1.5641, "grad_norm": 0.4823240041732788, "learning_rate": 0.0002, "epoch": 2.7655310621242486, "step": 2070}, {"loss": 1.6701, "grad_norm": 0.4546685516834259, "learning_rate": 0.0002, "epoch": 2.778891115564462, "step": 2080}, {"loss": 1.7015, "grad_norm": 0.45542681217193604, "learning_rate": 0.0002, "epoch": 2.7922511690046763, "step": 2090}, {"loss": 1.6398, "grad_norm": 0.42137566208839417, "learning_rate": 0.0002, "epoch": 2.80561122244489, "step": 2100}, {"loss": 1.6526, "grad_norm": 0.6143282055854797, "learning_rate": 0.0002, "epoch": 2.8189712758851035, "step": 2110}, {"loss": 1.6955, "grad_norm": 0.4828081727027893, "learning_rate": 0.0002, "epoch": 2.832331329325317, "step": 2120}, {"loss": 1.744, "grad_norm": 0.4319005608558655, "learning_rate": 0.0002, "epoch": 2.845691382765531, "step": 2130}, {"loss": 1.6717, "grad_norm": 0.4297086298465729, "learning_rate": 0.0002, "epoch": 2.859051436205745, "step": 2140}, {"loss": 1.5968, "grad_norm": 0.5011981129646301, "learning_rate": 0.0002, "epoch": 2.8724114896459585, "step": 2150}, {"loss": 1.7181, "grad_norm": 0.4401548504829407, "learning_rate": 0.0002, "epoch": 2.8857715430861726, "step": 2160}, {"loss": 1.5722, "grad_norm": 0.48090746998786926, "learning_rate": 0.0002, "epoch": 2.899131596526386, "step": 2170}, {"loss": 1.6596, "grad_norm": 0.4740385413169861, "learning_rate": 0.0002, "epoch": 2.9124916499666, "step": 2180}, {"loss": 1.6501, "grad_norm": 0.5337260365486145, "learning_rate": 0.0002, "epoch": 2.9258517034068134, "step": 2190}, {"loss": 1.6802, "grad_norm": 0.4420052766799927, "learning_rate": 0.0002, "epoch": 2.9392117568470275, "step": 2200}, {"loss": 1.5474, "grad_norm": 0.477512389421463, "learning_rate": 0.0002, "epoch": 2.952571810287241, "step": 2210}, {"loss": 1.6544, "grad_norm": 0.5344052910804749, "learning_rate": 0.0002, "epoch": 2.9659318637274548, "step": 2220}, {"loss": 1.6866, "grad_norm": 0.4483940303325653, "learning_rate": 0.0002, "epoch": 2.979291917167669, "step": 2230}, {"loss": 1.6477, "grad_norm": 0.4366597831249237, "learning_rate": 0.0002, "epoch": 2.9926519706078825, "step": 2240}, {"eval_loss": 1.834012746810913, "eval_runtime": 38.5659, "eval_samples_per_second": 13.354, "eval_steps_per_second": 1.685, "epoch": 2.9993319973279893, "step": 2245}, {"loss": 1.5582, "grad_norm": 0.428824245929718, "learning_rate": 0.0002, "epoch": 3.006012024048096, "step": 2250}, {"loss": 1.499, "grad_norm": 0.4870174825191498, "learning_rate": 0.0002, "epoch": 3.01937207748831, "step": 2260}, {"loss": 1.4872, "grad_norm": 0.4684266149997711, "learning_rate": 0.0002, "epoch": 3.032732130928524, "step": 2270}, {"loss": 1.5284, "grad_norm": 0.581604540348053, "learning_rate": 0.0002, "epoch": 3.0460921843687374, "step": 2280}, {"loss": 1.4549, "grad_norm": 0.5561677813529968, "learning_rate": 0.0002, "epoch": 3.059452237808951, "step": 2290}, {"loss": 1.4903, "grad_norm": 0.5750220417976379, "learning_rate": 0.0002, "epoch": 3.072812291249165, "step": 2300}, {"loss": 1.5903, "grad_norm": 0.5704626441001892, "learning_rate": 0.0002, "epoch": 3.0861723446893787, "step": 2310}, {"loss": 1.4292, "grad_norm": 0.6242083311080933, "learning_rate": 0.0002, "epoch": 3.0995323981295924, "step": 2320}, {"loss": 1.5092, "grad_norm": 0.5174121260643005, "learning_rate": 0.0002, "epoch": 3.1128924515698064, "step": 2330}, {"loss": 1.5106, "grad_norm": 0.5697633028030396, "learning_rate": 0.0002, "epoch": 3.12625250501002, "step": 2340}, {"loss": 1.5156, "grad_norm": 0.5969541072845459, "learning_rate": 0.0002, "epoch": 3.1396125584502337, "step": 2350}, {"loss": 1.52, "grad_norm": 0.6244304180145264, "learning_rate": 0.0002, "epoch": 3.1529726118904478, "step": 2360}, {"loss": 1.5244, "grad_norm": 0.5561705827713013, "learning_rate": 0.0002, "epoch": 3.1663326653306614, "step": 2370}, {"loss": 1.6169, "grad_norm": 0.5401188135147095, "learning_rate": 0.0002, "epoch": 3.179692718770875, "step": 2380}, {"loss": 1.5387, "grad_norm": 0.6450421810150146, "learning_rate": 0.0002, "epoch": 3.1930527722110886, "step": 2390}, {"loss": 1.4839, "grad_norm": 0.5741903185844421, "learning_rate": 0.0002, "epoch": 3.2064128256513027, "step": 2400}, {"loss": 1.5584, "grad_norm": 0.6337407231330872, "learning_rate": 0.0002, "epoch": 3.2197728790915163, "step": 2410}, {"loss": 1.5025, "grad_norm": 0.6493517160415649, "learning_rate": 0.0002, "epoch": 3.23313293253173, "step": 2420}, {"loss": 1.5168, "grad_norm": 0.6230176091194153, "learning_rate": 0.0002, "epoch": 3.246492985971944, "step": 2430}, {"loss": 1.5408, "grad_norm": 0.680704653263092, "learning_rate": 0.0002, "epoch": 3.2598530394121576, "step": 2440}, {"loss": 1.6005, "grad_norm": 0.5279417037963867, "learning_rate": 0.0002, "epoch": 3.2732130928523713, "step": 2450}, {"loss": 1.5231, "grad_norm": 0.5601515173912048, "learning_rate": 0.0002, "epoch": 3.2865731462925853, "step": 2460}, {"loss": 1.4949, "grad_norm": 0.5591090321540833, "learning_rate": 0.0002, "epoch": 3.299933199732799, "step": 2470}, {"loss": 1.5181, "grad_norm": 0.6596529483795166, "learning_rate": 0.0002, "epoch": 3.3132932531730126, "step": 2480}, {"loss": 1.5259, "grad_norm": 0.6115918755531311, "learning_rate": 0.0002, "epoch": 3.3266533066132267, "step": 2490}, {"loss": 1.5344, "grad_norm": 0.6443548202514648, "learning_rate": 0.0002, "epoch": 3.3400133600534403, "step": 2500}, {"loss": 1.5037, "grad_norm": 0.5504242181777954, "learning_rate": 0.0002, "epoch": 3.353373413493654, "step": 2510}, {"loss": 1.5049, "grad_norm": 0.6104483604431152, "learning_rate": 0.0002, "epoch": 3.3667334669338675, "step": 2520}, {"loss": 1.587, "grad_norm": 0.8387531638145447, "learning_rate": 0.0002, "epoch": 3.3800935203740816, "step": 2530}, {"loss": 1.5227, "grad_norm": 0.6346094012260437, "learning_rate": 0.0002, "epoch": 3.3934535738142952, "step": 2540}, {"loss": 1.4855, "grad_norm": 0.6261265873908997, "learning_rate": 0.0002, "epoch": 3.406813627254509, "step": 2550}, {"loss": 1.5233, "grad_norm": 0.5960372090339661, "learning_rate": 0.0002, "epoch": 3.420173680694723, "step": 2560}, {"loss": 1.5153, "grad_norm": 0.5291280746459961, "learning_rate": 0.0002, "epoch": 3.4335337341349366, "step": 2570}, {"loss": 1.5152, "grad_norm": 0.6133161783218384, "learning_rate": 0.0002, "epoch": 3.44689378757515, "step": 2580}, {"loss": 1.5533, "grad_norm": 0.623573362827301, "learning_rate": 0.0002, "epoch": 3.460253841015364, "step": 2590}, {"loss": 1.4935, "grad_norm": 0.5959834456443787, "learning_rate": 0.0002, "epoch": 3.473613894455578, "step": 2600}, {"loss": 1.5792, "grad_norm": 0.583332359790802, "learning_rate": 0.0002, "epoch": 3.4869739478957915, "step": 2610}, {"loss": 1.5229, "grad_norm": 0.6003559231758118, "learning_rate": 0.0002, "epoch": 3.5003340013360056, "step": 2620}, {"loss": 1.4901, "grad_norm": 0.5832992196083069, "learning_rate": 0.0002, "epoch": 3.513694054776219, "step": 2630}, {"loss": 1.5005, "grad_norm": 0.5942609906196594, "learning_rate": 0.0002, "epoch": 3.527054108216433, "step": 2640}, {"loss": 1.5213, "grad_norm": 0.6087163686752319, "learning_rate": 0.0002, "epoch": 3.5404141616566465, "step": 2650}, {"loss": 1.5826, "grad_norm": 0.631948709487915, "learning_rate": 0.0002, "epoch": 3.5537742150968605, "step": 2660}, {"loss": 1.5844, "grad_norm": 0.6450803279876709, "learning_rate": 0.0002, "epoch": 3.567134268537074, "step": 2670}, {"loss": 1.4981, "grad_norm": 0.6507797837257385, "learning_rate": 0.0002, "epoch": 3.580494321977288, "step": 2680}, {"loss": 1.5826, "grad_norm": 0.5778017044067383, "learning_rate": 0.0002, "epoch": 3.593854375417502, "step": 2690}, {"loss": 1.4688, "grad_norm": 0.6214032173156738, "learning_rate": 0.0002, "epoch": 3.6072144288577155, "step": 2700}, {"loss": 1.5084, "grad_norm": 0.5681133270263672, "learning_rate": 0.0002, "epoch": 3.620574482297929, "step": 2710}, {"loss": 1.471, "grad_norm": 0.6074244976043701, "learning_rate": 0.0002, "epoch": 3.6339345357381427, "step": 2720}, {"loss": 1.5243, "grad_norm": 0.5900560617446899, "learning_rate": 0.0002, "epoch": 3.647294589178357, "step": 2730}, {"loss": 1.5074, "grad_norm": 0.5817505717277527, "learning_rate": 0.0002, "epoch": 3.6606546426185704, "step": 2740}, {"loss": 1.5117, "grad_norm": 0.6095547676086426, "learning_rate": 0.0002, "epoch": 3.6740146960587845, "step": 2750}, {"loss": 1.5117, "grad_norm": 0.612790584564209, "learning_rate": 0.0002, "epoch": 3.687374749498998, "step": 2760}, {"loss": 1.4976, "grad_norm": 0.6574140787124634, "learning_rate": 0.0002, "epoch": 3.7007348029392118, "step": 2770}, {"loss": 1.5306, "grad_norm": 0.5643761157989502, "learning_rate": 0.0002, "epoch": 3.7140948563794254, "step": 2780}, {"loss": 1.5751, "grad_norm": 0.5652621388435364, "learning_rate": 0.0002, "epoch": 3.727454909819639, "step": 2790}, {"loss": 1.5262, "grad_norm": 0.5604206323623657, "learning_rate": 0.0002, "epoch": 3.740814963259853, "step": 2800}, {"loss": 1.5013, "grad_norm": 3.911022663116455, "learning_rate": 0.0002, "epoch": 3.7541750167000667, "step": 2810}, {"loss": 1.5793, "grad_norm": 0.6148333549499512, "learning_rate": 0.0002, "epoch": 3.7675350701402808, "step": 2820}, {"loss": 1.5122, "grad_norm": 0.5605677962303162, "learning_rate": 0.0002, "epoch": 3.7808951235804944, "step": 2830}, {"loss": 1.5659, "grad_norm": 0.6101965308189392, "learning_rate": 0.0002, "epoch": 3.794255177020708, "step": 2840}, {"loss": 1.5618, "grad_norm": 0.5387342572212219, "learning_rate": 0.0002, "epoch": 3.8076152304609217, "step": 2850}, {"loss": 1.5193, "grad_norm": 0.5733087062835693, "learning_rate": 0.0002, "epoch": 3.8209752839011357, "step": 2860}, {"loss": 1.5545, "grad_norm": 0.6538485884666443, "learning_rate": 0.0002, "epoch": 3.8343353373413493, "step": 2870}, {"loss": 1.523, "grad_norm": 0.6247632503509521, "learning_rate": 0.0002, "epoch": 3.847695390781563, "step": 2880}, {"loss": 1.5591, "grad_norm": 0.5745735764503479, "learning_rate": 0.0002, "epoch": 3.861055444221777, "step": 2890}, {"loss": 1.5706, "grad_norm": 0.5942763686180115, "learning_rate": 0.0002, "epoch": 3.8744154976619907, "step": 2900}, {"loss": 1.564, "grad_norm": 0.7086281776428223, "learning_rate": 0.0002, "epoch": 3.8877755511022043, "step": 2910}, {"loss": 1.5526, "grad_norm": 0.8825129866600037, "learning_rate": 0.0002, "epoch": 3.901135604542418, "step": 2920}, {"loss": 1.4519, "grad_norm": 0.6260842680931091, "learning_rate": 0.0002, "epoch": 3.914495657982632, "step": 2930}, {"loss": 1.5433, "grad_norm": 0.6015968322753906, "learning_rate": 0.0002, "epoch": 3.9278557114228456, "step": 2940}, {"loss": 1.4931, "grad_norm": 0.7042809128761292, "learning_rate": 0.0002, "epoch": 3.9412157648630597, "step": 2950}, {"loss": 1.5596, "grad_norm": 0.5860083699226379, "learning_rate": 0.0002, "epoch": 3.9545758183032733, "step": 2960}, {"loss": 1.565, "grad_norm": 0.5939757823944092, "learning_rate": 0.0002, "epoch": 3.967935871743487, "step": 2970}, {"loss": 1.408, "grad_norm": 0.5523964166641235, "learning_rate": 0.0002, "epoch": 3.9812959251837006, "step": 2980}, {"loss": 1.5629, "grad_norm": 0.6380264759063721, "learning_rate": 0.0002, "epoch": 3.9946559786239146, "step": 2990}, {"eval_loss": 1.8875294923782349, "eval_runtime": 38.5837, "eval_samples_per_second": 13.348, "eval_steps_per_second": 1.685, "epoch": 4.0, "step": 2994}, {"loss": 1.4002, "grad_norm": 0.5478564500808716, "learning_rate": 0.0002, "epoch": 4.008016032064128, "step": 3000}, {"loss": 1.436, "grad_norm": 0.9384379982948303, "learning_rate": 0.0002, "epoch": 4.021376085504342, "step": 3010}, {"loss": 1.4127, "grad_norm": 0.7819344401359558, "learning_rate": 0.0002, "epoch": 4.034736138944556, "step": 3020}, {"loss": 1.326, "grad_norm": 0.7737417817115784, "learning_rate": 0.0002, "epoch": 4.04809619238477, "step": 3030}, {"loss": 1.3203, "grad_norm": 0.8893805742263794, "learning_rate": 0.0002, "epoch": 4.061456245824983, "step": 3040}, {"loss": 1.3913, "grad_norm": 0.7759843468666077, "learning_rate": 0.0002, "epoch": 4.074816299265197, "step": 3050}, {"loss": 1.2941, "grad_norm": 0.642654538154602, "learning_rate": 0.0002, "epoch": 4.0881763527054105, "step": 3060}, {"loss": 1.3204, "grad_norm": 0.8515549302101135, "learning_rate": 0.0002, "epoch": 4.101536406145625, "step": 3070}, {"loss": 1.3683, "grad_norm": 0.7033658623695374, "learning_rate": 0.0002, "epoch": 4.114896459585839, "step": 3080}, {"loss": 1.4159, "grad_norm": 0.7063882946968079, "learning_rate": 0.0002, "epoch": 4.128256513026052, "step": 3090}, {"loss": 1.384, "grad_norm": 0.6946853995323181, "learning_rate": 0.0002, "epoch": 4.141616566466266, "step": 3100}, {"loss": 1.3689, "grad_norm": 0.7286741137504578, "learning_rate": 0.0002, "epoch": 4.1549766199064795, "step": 3110}, {"loss": 1.3061, "grad_norm": 0.7894193530082703, "learning_rate": 0.0002, "epoch": 4.168336673346693, "step": 3120}, {"loss": 1.3346, "grad_norm": 0.7005895376205444, "learning_rate": 0.0002, "epoch": 4.181696726786907, "step": 3130}, {"loss": 1.3834, "grad_norm": 0.799567461013794, "learning_rate": 0.0002, "epoch": 4.195056780227121, "step": 3140}, {"loss": 1.3813, "grad_norm": 0.7010157108306885, "learning_rate": 0.0002, "epoch": 4.208416833667335, "step": 3150}, {"loss": 1.3637, "grad_norm": 0.7489650249481201, "learning_rate": 0.0002, "epoch": 4.2217768871075485, "step": 3160}, {"loss": 1.3546, "grad_norm": 0.7908048629760742, "learning_rate": 0.0002, "epoch": 4.235136940547762, "step": 3170}, {"loss": 1.3073, "grad_norm": 0.7002180814743042, "learning_rate": 0.0002, "epoch": 4.248496993987976, "step": 3180}, {"loss": 1.4525, "grad_norm": 0.8339495062828064, "learning_rate": 0.0002, "epoch": 4.261857047428189, "step": 3190}, {"loss": 1.3471, "grad_norm": 0.7884618043899536, "learning_rate": 0.0002, "epoch": 4.275217100868403, "step": 3200}, {"loss": 1.4261, "grad_norm": 0.7964122295379639, "learning_rate": 0.0002, "epoch": 4.2885771543086175, "step": 3210}, {"loss": 1.3506, "grad_norm": 0.838646650314331, "learning_rate": 0.0002, "epoch": 4.301937207748831, "step": 3220}, {"loss": 1.3738, "grad_norm": 0.8063107132911682, "learning_rate": 0.0002, "epoch": 4.315297261189045, "step": 3230}, {"loss": 1.3769, "grad_norm": 0.8147385120391846, "learning_rate": 0.0002, "epoch": 4.328657314629258, "step": 3240}, {"loss": 1.4118, "grad_norm": 0.7636798620223999, "learning_rate": 0.0002, "epoch": 4.342017368069472, "step": 3250}, {"loss": 1.3698, "grad_norm": 0.7530609965324402, "learning_rate": 0.0002, "epoch": 4.355377421509686, "step": 3260}, {"loss": 1.3507, "grad_norm": 0.8853573799133301, "learning_rate": 0.0002, "epoch": 4.3687374749499, "step": 3270}, {"loss": 1.3614, "grad_norm": 0.7180975675582886, "learning_rate": 0.0002, "epoch": 4.382097528390114, "step": 3280}, {"loss": 1.4119, "grad_norm": 0.837150514125824, "learning_rate": 0.0002, "epoch": 4.395457581830327, "step": 3290}, {"loss": 1.461, "grad_norm": 0.8370638489723206, "learning_rate": 0.0002, "epoch": 4.408817635270541, "step": 3300}, {"loss": 1.4478, "grad_norm": 0.7738229036331177, "learning_rate": 0.0002, "epoch": 4.422177688710755, "step": 3310}, {"loss": 1.4195, "grad_norm": 0.7665290832519531, "learning_rate": 0.0002, "epoch": 4.435537742150968, "step": 3320}, {"loss": 1.3308, "grad_norm": 0.7547745704650879, "learning_rate": 0.0002, "epoch": 4.448897795591183, "step": 3330}, {"loss": 1.4165, "grad_norm": 0.7421861290931702, "learning_rate": 0.0002, "epoch": 4.462257849031396, "step": 3340}, {"loss": 1.4244, "grad_norm": 0.8042104244232178, "learning_rate": 0.0002, "epoch": 4.47561790247161, "step": 3350}, {"loss": 1.365, "grad_norm": 0.8111839890480042, "learning_rate": 0.0002, "epoch": 4.488977955911824, "step": 3360}, {"loss": 1.3537, "grad_norm": 0.7998340129852295, "learning_rate": 0.0002, "epoch": 4.502338009352037, "step": 3370}, {"loss": 1.3812, "grad_norm": 0.7668877243995667, "learning_rate": 0.0002, "epoch": 4.515698062792251, "step": 3380}, {"loss": 1.3972, "grad_norm": 0.7986718416213989, "learning_rate": 0.0002, "epoch": 4.529058116232465, "step": 3390}, {"loss": 1.3582, "grad_norm": 0.6806602478027344, "learning_rate": 0.0002, "epoch": 4.542418169672679, "step": 3400}, {"loss": 1.3942, "grad_norm": 0.8788819909095764, "learning_rate": 0.0002, "epoch": 4.555778223112893, "step": 3410}, {"loss": 1.3379, "grad_norm": 0.7499664425849915, "learning_rate": 0.0002, "epoch": 4.569138276553106, "step": 3420}, {"loss": 1.3823, "grad_norm": 0.7967109084129333, "learning_rate": 0.0002, "epoch": 4.58249832999332, "step": 3430}, {"loss": 1.3531, "grad_norm": 0.759639322757721, "learning_rate": 0.0002, "epoch": 4.595858383433534, "step": 3440}, {"loss": 1.3517, "grad_norm": 0.8327916264533997, "learning_rate": 0.0002, "epoch": 4.609218436873747, "step": 3450}, {"loss": 1.4619, "grad_norm": 0.7400892376899719, "learning_rate": 0.0002, "epoch": 4.622578490313961, "step": 3460}, {"loss": 1.3374, "grad_norm": 0.8116602301597595, "learning_rate": 0.0002, "epoch": 4.635938543754175, "step": 3470}, {"loss": 1.4445, "grad_norm": 0.7604362368583679, "learning_rate": 0.0002, "epoch": 4.649298597194389, "step": 3480}, {"loss": 1.3724, "grad_norm": 0.7397996783256531, "learning_rate": 0.0002, "epoch": 4.662658650634603, "step": 3490}, {"loss": 1.4048, "grad_norm": 0.869293749332428, "learning_rate": 0.0002, "epoch": 4.676018704074816, "step": 3500}, {"loss": 1.3873, "grad_norm": 0.6854358315467834, "learning_rate": 0.0002, "epoch": 4.68937875751503, "step": 3510}, {"loss": 1.3413, "grad_norm": 0.8326661586761475, "learning_rate": 0.0002, "epoch": 4.7027388109552435, "step": 3520}, {"loss": 1.3666, "grad_norm": 0.6887506246566772, "learning_rate": 0.0002, "epoch": 4.716098864395457, "step": 3530}, {"loss": 1.4508, "grad_norm": 3.837689161300659, "learning_rate": 0.0002, "epoch": 4.729458917835672, "step": 3540}, {"loss": 1.3775, "grad_norm": 0.6874563694000244, "learning_rate": 0.0002, "epoch": 4.742818971275885, "step": 3550}, {"loss": 1.3643, "grad_norm": 0.8340407609939575, "learning_rate": 0.0002, "epoch": 4.756179024716099, "step": 3560}, {"loss": 1.3556, "grad_norm": 0.7286418676376343, "learning_rate": 0.0002, "epoch": 4.7695390781563125, "step": 3570}, {"loss": 1.4338, "grad_norm": 0.7239373326301575, "learning_rate": 0.0002, "epoch": 4.782899131596526, "step": 3580}, {"loss": 1.4697, "grad_norm": 0.831310510635376, "learning_rate": 0.0002, "epoch": 4.796259185036741, "step": 3590}, {"loss": 1.4146, "grad_norm": 0.767715573310852, "learning_rate": 0.0002, "epoch": 4.809619238476954, "step": 3600}, {"loss": 1.4199, "grad_norm": 0.9013199210166931, "learning_rate": 0.0002, "epoch": 4.822979291917168, "step": 3610}, {"loss": 1.4513, "grad_norm": 0.7543512582778931, "learning_rate": 0.0002, "epoch": 4.8363393453573815, "step": 3620}, {"loss": 1.4218, "grad_norm": 0.7626057267189026, "learning_rate": 0.0002, "epoch": 4.849699398797595, "step": 3630}, {"loss": 1.4102, "grad_norm": 0.847079336643219, "learning_rate": 0.0002, "epoch": 4.863059452237809, "step": 3640}, {"loss": 1.5014, "grad_norm": 0.8273295760154724, "learning_rate": 0.0002, "epoch": 4.876419505678022, "step": 3650}, {"loss": 1.3806, "grad_norm": 0.7675244808197021, "learning_rate": 0.0002, "epoch": 4.889779559118237, "step": 3660}, {"loss": 1.4894, "grad_norm": 0.9560356736183167, "learning_rate": 0.0002, "epoch": 4.9031396125584505, "step": 3670}, {"loss": 1.4044, "grad_norm": 0.7682451605796814, "learning_rate": 0.0002, "epoch": 4.916499665998664, "step": 3680}, {"loss": 1.342, "grad_norm": 0.8113830089569092, "learning_rate": 0.0002, "epoch": 4.929859719438878, "step": 3690}, {"loss": 1.3559, "grad_norm": 0.7642542719841003, "learning_rate": 0.0002, "epoch": 4.943219772879091, "step": 3700}, {"loss": 1.403, "grad_norm": 0.823863685131073, "learning_rate": 0.0002, "epoch": 4.956579826319305, "step": 3710}, {"loss": 1.464, "grad_norm": 0.8287797570228577, "learning_rate": 0.0002, "epoch": 4.969939879759519, "step": 3720}, {"loss": 1.4139, "grad_norm": 0.778170108795166, "learning_rate": 0.0002, "epoch": 4.983299933199733, "step": 3730}, {"loss": 1.4218, "grad_norm": 0.7464073896408081, "learning_rate": 0.0002, "epoch": 4.996659986639947, "step": 3740}, {"eval_loss": 1.9638569355010986, "eval_runtime": 38.5725, "eval_samples_per_second": 13.351, "eval_steps_per_second": 1.685, "epoch": 4.999331997327989, "step": 3742}, {"loss": 1.225, "grad_norm": 0.8864085078239441, "learning_rate": 0.0002, "epoch": 5.01002004008016, "step": 3750}, {"loss": 1.2056, "grad_norm": 0.9191637635231018, "learning_rate": 0.0002, "epoch": 5.023380093520374, "step": 3760}, {"loss": 1.2453, "grad_norm": 0.749519407749176, "learning_rate": 0.0002, "epoch": 5.036740146960588, "step": 3770}, {"loss": 1.1959, "grad_norm": 0.7916892170906067, "learning_rate": 0.0002, "epoch": 5.050100200400801, "step": 3780}, {"loss": 1.2279, "grad_norm": 1.0318909883499146, "learning_rate": 0.0002, "epoch": 5.063460253841015, "step": 3790}, {"loss": 1.2585, "grad_norm": 1.028586745262146, "learning_rate": 0.0002, "epoch": 5.0768203072812295, "step": 3800}, {"loss": 1.1769, "grad_norm": 1.0568538904190063, "learning_rate": 0.0002, "epoch": 5.090180360721443, "step": 3810}, {"loss": 1.263, "grad_norm": 0.9780595302581787, "learning_rate": 0.0002, "epoch": 5.103540414161657, "step": 3820}, {"loss": 1.2019, "grad_norm": 1.10311758518219, "learning_rate": 0.0002, "epoch": 5.11690046760187, "step": 3830}, {"loss": 1.2133, "grad_norm": 0.9497154355049133, "learning_rate": 0.0002, "epoch": 5.130260521042084, "step": 3840}, {"loss": 1.1718, "grad_norm": 0.948279857635498, "learning_rate": 0.0002, "epoch": 5.143620574482298, "step": 3850}, {"loss": 1.2108, "grad_norm": 0.9497880339622498, "learning_rate": 0.0002, "epoch": 5.156980627922512, "step": 3860}, {"loss": 1.1876, "grad_norm": 1.3213258981704712, "learning_rate": 0.0002, "epoch": 5.170340681362726, "step": 3870}, {"loss": 1.2327, "grad_norm": 0.9835752248764038, "learning_rate": 0.0002, "epoch": 5.183700734802939, "step": 3880}, {"loss": 1.2256, "grad_norm": 0.8426132202148438, "learning_rate": 0.0002, "epoch": 5.197060788243153, "step": 3890}, {"loss": 1.2066, "grad_norm": 1.0343470573425293, "learning_rate": 0.0002, "epoch": 5.210420841683367, "step": 3900}, {"loss": 1.2596, "grad_norm": 1.0771924257278442, "learning_rate": 0.0002, "epoch": 5.22378089512358, "step": 3910}, {"loss": 1.2371, "grad_norm": 0.8542634844779968, "learning_rate": 0.0002, "epoch": 5.237140948563794, "step": 3920}, {"loss": 1.2264, "grad_norm": 1.1021966934204102, "learning_rate": 0.0002, "epoch": 5.250501002004008, "step": 3930}, {"loss": 1.2097, "grad_norm": 1.170011281967163, "learning_rate": 0.0002, "epoch": 5.263861055444222, "step": 3940}, {"loss": 1.2101, "grad_norm": 0.9787653684616089, "learning_rate": 0.0002, "epoch": 5.277221108884436, "step": 3950}, {"loss": 1.24, "grad_norm": 0.914513885974884, "learning_rate": 0.0002, "epoch": 5.290581162324649, "step": 3960}, {"loss": 1.1641, "grad_norm": 1.0831562280654907, "learning_rate": 0.0002, "epoch": 5.303941215764863, "step": 3970}, {"loss": 1.2609, "grad_norm": 0.9810112714767456, "learning_rate": 0.0002, "epoch": 5.3173012692050765, "step": 3980}, {"loss": 1.1825, "grad_norm": 0.9624066948890686, "learning_rate": 0.0002, "epoch": 5.330661322645291, "step": 3990}, {"loss": 1.273, "grad_norm": 1.2296923398971558, "learning_rate": 0.0002, "epoch": 5.344021376085505, "step": 4000}, {"loss": 1.2452, "grad_norm": 1.011299967765808, "learning_rate": 0.0002, "epoch": 5.357381429525718, "step": 4010}, {"loss": 1.2539, "grad_norm": 0.9144132733345032, "learning_rate": 0.0002, "epoch": 5.370741482965932, "step": 4020}, {"loss": 1.2914, "grad_norm": 1.0573601722717285, "learning_rate": 0.0002, "epoch": 5.3841015364061455, "step": 4030}, {"loss": 1.2295, "grad_norm": 1.1667137145996094, "learning_rate": 0.0002, "epoch": 5.397461589846359, "step": 4040}, {"loss": 1.2541, "grad_norm": 1.072070598602295, "learning_rate": 0.0002, "epoch": 5.410821643286573, "step": 4050}, {"loss": 1.2448, "grad_norm": 1.1005792617797852, "learning_rate": 0.0002, "epoch": 5.424181696726787, "step": 4060}, {"loss": 1.2604, "grad_norm": 1.033581018447876, "learning_rate": 0.0002, "epoch": 5.437541750167001, "step": 4070}, {"loss": 1.2552, "grad_norm": 0.9537439942359924, "learning_rate": 0.0002, "epoch": 5.4509018036072145, "step": 4080}, {"loss": 1.2985, "grad_norm": 1.0502177476882935, "learning_rate": 0.0002, "epoch": 5.464261857047428, "step": 4090}, {"loss": 1.2424, "grad_norm": 0.9098296761512756, "learning_rate": 0.0002, "epoch": 5.477621910487642, "step": 4100}, {"loss": 1.2262, "grad_norm": 0.9551953077316284, "learning_rate": 0.0002, "epoch": 5.490981963927855, "step": 4110}, {"loss": 1.2848, "grad_norm": 0.9169427156448364, "learning_rate": 0.0002, "epoch": 5.504342017368069, "step": 4120}, {"loss": 1.2572, "grad_norm": 0.9430235624313354, "learning_rate": 0.0002, "epoch": 5.517702070808284, "step": 4130}, {"loss": 1.2618, "grad_norm": 0.817259669303894, "learning_rate": 0.0002, "epoch": 5.531062124248497, "step": 4140}, {"loss": 1.3012, "grad_norm": 1.124152660369873, "learning_rate": 0.0002, "epoch": 5.544422177688711, "step": 4150}, {"loss": 1.2508, "grad_norm": 0.9250756502151489, "learning_rate": 0.0002, "epoch": 5.557782231128924, "step": 4160}, {"loss": 1.2492, "grad_norm": 0.9582970142364502, "learning_rate": 0.0002, "epoch": 5.571142284569138, "step": 4170}, {"loss": 1.2804, "grad_norm": 1.0078704357147217, "learning_rate": 0.0002, "epoch": 5.584502338009352, "step": 4180}, {"loss": 1.1961, "grad_norm": 0.9585610032081604, "learning_rate": 0.0002, "epoch": 5.597862391449565, "step": 4190}, {"loss": 1.2522, "grad_norm": 1.0150971412658691, "learning_rate": 0.0002, "epoch": 5.61122244488978, "step": 4200}, {"loss": 1.2275, "grad_norm": 0.9943351149559021, "learning_rate": 0.0002, "epoch": 5.6245824983299935, "step": 4210}, {"loss": 1.2928, "grad_norm": 0.8880936503410339, "learning_rate": 0.0002, "epoch": 5.637942551770207, "step": 4220}, {"loss": 1.2323, "grad_norm": 0.9873887896537781, "learning_rate": 0.0002, "epoch": 5.651302605210421, "step": 4230}, {"loss": 1.3391, "grad_norm": 0.9185152649879456, "learning_rate": 0.0002, "epoch": 5.664662658650634, "step": 4240}, {"loss": 1.2511, "grad_norm": 1.0706779956817627, "learning_rate": 0.0002, "epoch": 5.678022712090849, "step": 4250}, {"loss": 1.2737, "grad_norm": 0.9660224914550781, "learning_rate": 0.0002, "epoch": 5.6913827655310625, "step": 4260}, {"loss": 1.2815, "grad_norm": 0.8685019612312317, "learning_rate": 0.0002, "epoch": 5.704742818971276, "step": 4270}, {"loss": 1.1559, "grad_norm": 1.0390565395355225, "learning_rate": 0.0002, "epoch": 5.71810287241149, "step": 4280}, {"loss": 1.3134, "grad_norm": 0.9290478825569153, "learning_rate": 0.0002, "epoch": 5.731462925851703, "step": 4290}, {"loss": 1.2426, "grad_norm": 1.0361281633377075, "learning_rate": 0.0002, "epoch": 5.744822979291917, "step": 4300}, {"loss": 1.2688, "grad_norm": 0.8804615139961243, "learning_rate": 0.0002, "epoch": 5.758183032732131, "step": 4310}, {"loss": 1.2479, "grad_norm": 1.0051425695419312, "learning_rate": 0.0002, "epoch": 5.771543086172345, "step": 4320}, {"loss": 1.1946, "grad_norm": 1.0051119327545166, "learning_rate": 0.0002, "epoch": 5.784903139612559, "step": 4330}, {"loss": 1.2571, "grad_norm": 0.9961661100387573, "learning_rate": 0.0002, "epoch": 5.798263193052772, "step": 4340}, {"loss": 1.2179, "grad_norm": 1.0229419469833374, "learning_rate": 0.0002, "epoch": 5.811623246492986, "step": 4350}, {"loss": 1.2984, "grad_norm": 1.1129552125930786, "learning_rate": 0.0002, "epoch": 5.8249832999332, "step": 4360}, {"loss": 1.2692, "grad_norm": 1.18964421749115, "learning_rate": 0.0002, "epoch": 5.838343353373413, "step": 4370}, {"loss": 1.1996, "grad_norm": 0.9490230083465576, "learning_rate": 0.0002, "epoch": 5.851703406813627, "step": 4380}, {"loss": 1.3177, "grad_norm": 0.8734540343284607, "learning_rate": 0.0002, "epoch": 5.865063460253841, "step": 4390}, {"loss": 1.3131, "grad_norm": 1.0017802715301514, "learning_rate": 0.0002, "epoch": 5.878423513694055, "step": 4400}, {"loss": 1.2649, "grad_norm": 0.953556478023529, "learning_rate": 0.0002, "epoch": 5.891783567134269, "step": 4410}, {"loss": 1.2684, "grad_norm": 0.8915258646011353, "learning_rate": 0.0002, "epoch": 5.905143620574482, "step": 4420}, {"loss": 1.2843, "grad_norm": 0.9715141654014587, "learning_rate": 0.0002, "epoch": 5.918503674014696, "step": 4430}, {"loss": 1.2769, "grad_norm": 0.9432152509689331, "learning_rate": 0.0002, "epoch": 5.9318637274549095, "step": 4440}, {"loss": 1.233, "grad_norm": 0.9473979473114014, "learning_rate": 0.0002, "epoch": 5.945223780895123, "step": 4450}, {"loss": 1.3209, "grad_norm": 1.104871392250061, "learning_rate": 0.0002, "epoch": 5.958583834335338, "step": 4460}, {"loss": 1.3427, "grad_norm": 1.0308905839920044, "learning_rate": 0.0002, "epoch": 5.971943887775551, "step": 4470}, {"loss": 1.1808, "grad_norm": 0.8895487189292908, "learning_rate": 0.0002, "epoch": 5.985303941215765, "step": 4480}, {"loss": 1.2634, "grad_norm": 1.0148485898971558, "learning_rate": 0.0002, "epoch": 5.9986639946559785, "step": 4490}]}
+{"epoch": 6.999331997327989, "step": 5239, "epoch_duration": 812.9917500019073, "total_accumulated_duration": 5777.37841963768, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7672.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.6569, "grad_norm": 0.5097216367721558, "learning_rate": 0.0002, "epoch": 0.013360053440213761, "step": 10}, {"loss": 2.2557, "grad_norm": 0.5924790501594543, "learning_rate": 0.0002, "epoch": 0.026720106880427523, "step": 20}, {"loss": 2.0626, "grad_norm": 0.5158102512359619, "learning_rate": 0.0002, "epoch": 0.04008016032064128, "step": 30}, {"loss": 1.9452, "grad_norm": 0.5033753514289856, "learning_rate": 0.0002, "epoch": 0.053440213760855046, "step": 40}, {"loss": 1.9128, "grad_norm": 0.5390949845314026, "learning_rate": 0.0002, "epoch": 0.06680026720106881, "step": 50}, {"loss": 1.937, "grad_norm": 0.6376217007637024, "learning_rate": 0.0002, "epoch": 0.08016032064128256, "step": 60}, {"loss": 1.929, "grad_norm": 0.4202035069465637, "learning_rate": 0.0002, "epoch": 0.09352037408149633, "step": 70}, {"loss": 1.811, "grad_norm": 0.4269474744796753, "learning_rate": 0.0002, "epoch": 0.10688042752171009, "step": 80}, {"loss": 1.8303, "grad_norm": 0.4306574761867523, "learning_rate": 0.0002, "epoch": 0.12024048096192384, "step": 90}, {"loss": 1.8469, "grad_norm": 0.5297011137008667, "learning_rate": 0.0002, "epoch": 0.13360053440213762, "step": 100}, {"loss": 1.864, "grad_norm": 1.2313778400421143, "learning_rate": 0.0002, "epoch": 0.14696058784235136, "step": 110}, {"loss": 1.8531, "grad_norm": 0.5351294279098511, "learning_rate": 0.0002, "epoch": 0.16032064128256512, "step": 120}, {"loss": 1.9232, "grad_norm": 0.4848092496395111, "learning_rate": 0.0002, "epoch": 0.1736806947227789, "step": 130}, {"loss": 1.8633, "grad_norm": 0.4339500665664673, "learning_rate": 0.0002, "epoch": 0.18704074816299265, "step": 140}, {"loss": 1.816, "grad_norm": 0.46877285838127136, "learning_rate": 0.0002, "epoch": 0.20040080160320642, "step": 150}, {"loss": 1.8033, "grad_norm": 0.5600412487983704, "learning_rate": 0.0002, "epoch": 0.21376085504342018, "step": 160}, {"loss": 1.8162, "grad_norm": 0.3733620345592499, "learning_rate": 0.0002, "epoch": 0.22712090848363392, "step": 170}, {"loss": 1.8564, "grad_norm": 0.5116042494773865, "learning_rate": 0.0002, "epoch": 0.24048096192384769, "step": 180}, {"loss": 1.915, "grad_norm": 0.4071602523326874, "learning_rate": 0.0002, "epoch": 0.25384101536406145, "step": 190}, {"loss": 1.7984, "grad_norm": 0.44189608097076416, "learning_rate": 0.0002, "epoch": 0.26720106880427524, "step": 200}, {"loss": 1.8728, "grad_norm": 0.398699015378952, "learning_rate": 0.0002, "epoch": 0.280561122244489, "step": 210}, {"loss": 1.8205, "grad_norm": 0.3585626482963562, "learning_rate": 0.0002, "epoch": 0.2939211756847027, "step": 220}, {"loss": 1.8861, "grad_norm": 0.3811776041984558, "learning_rate": 0.0002, "epoch": 0.3072812291249165, "step": 230}, {"loss": 1.8365, "grad_norm": 0.37261509895324707, "learning_rate": 0.0002, "epoch": 0.32064128256513025, "step": 240}, {"loss": 1.9186, "grad_norm": 0.39762404561042786, "learning_rate": 0.0002, "epoch": 0.33400133600534404, "step": 250}, {"loss": 1.7965, "grad_norm": 0.3509528934955597, "learning_rate": 0.0002, "epoch": 0.3473613894455578, "step": 260}, {"loss": 1.7802, "grad_norm": 0.3169104754924774, "learning_rate": 0.0002, "epoch": 0.36072144288577157, "step": 270}, {"loss": 1.8038, "grad_norm": 0.33714795112609863, "learning_rate": 0.0002, "epoch": 0.3740814963259853, "step": 280}, {"loss": 1.787, "grad_norm": 1.2936875820159912, "learning_rate": 0.0002, "epoch": 0.38744154976619904, "step": 290}, {"loss": 1.7974, "grad_norm": 0.3459427058696747, "learning_rate": 0.0002, "epoch": 0.40080160320641284, "step": 300}, {"loss": 1.8879, "grad_norm": 0.3380655348300934, "learning_rate": 0.0002, "epoch": 0.4141616566466266, "step": 310}, {"loss": 1.9196, "grad_norm": 0.3890381455421448, "learning_rate": 0.0002, "epoch": 0.42752171008684037, "step": 320}, {"loss": 1.8034, "grad_norm": 0.432327002286911, "learning_rate": 0.0002, "epoch": 0.4408817635270541, "step": 330}, {"loss": 1.8443, "grad_norm": 0.3736560046672821, "learning_rate": 0.0002, "epoch": 0.45424181696726784, "step": 340}, {"loss": 1.8506, "grad_norm": 0.3700982630252838, "learning_rate": 0.0002, "epoch": 0.46760187040748163, "step": 350}, {"loss": 1.7978, "grad_norm": 0.4533902406692505, "learning_rate": 0.0002, "epoch": 0.48096192384769537, "step": 360}, {"loss": 1.7427, "grad_norm": 0.35999053716659546, "learning_rate": 0.0002, "epoch": 0.49432197728790916, "step": 370}, {"loss": 1.7995, "grad_norm": 0.3490903675556183, "learning_rate": 0.0002, "epoch": 0.5076820307281229, "step": 380}, {"loss": 1.8709, "grad_norm": 0.34704291820526123, "learning_rate": 0.0002, "epoch": 0.5210420841683366, "step": 390}, {"loss": 1.7948, "grad_norm": 0.343565434217453, "learning_rate": 0.0002, "epoch": 0.5344021376085505, "step": 400}, {"loss": 1.8564, "grad_norm": 0.3573552966117859, "learning_rate": 0.0002, "epoch": 0.5477621910487642, "step": 410}, {"loss": 1.8477, "grad_norm": 0.32980719208717346, "learning_rate": 0.0002, "epoch": 0.561122244488978, "step": 420}, {"loss": 1.9233, "grad_norm": 0.356952428817749, "learning_rate": 0.0002, "epoch": 0.5744822979291917, "step": 430}, {"loss": 1.7433, "grad_norm": 0.3170869052410126, "learning_rate": 0.0002, "epoch": 0.5878423513694054, "step": 440}, {"loss": 1.7607, "grad_norm": 0.35233718156814575, "learning_rate": 0.0002, "epoch": 0.6012024048096193, "step": 450}, {"loss": 1.8111, "grad_norm": 0.3480125367641449, "learning_rate": 0.0002, "epoch": 0.614562458249833, "step": 460}, {"loss": 1.8386, "grad_norm": 0.4762810468673706, "learning_rate": 0.0002, "epoch": 0.6279225116900468, "step": 470}, {"loss": 1.805, "grad_norm": 0.3907663822174072, "learning_rate": 0.0002, "epoch": 0.6412825651302605, "step": 480}, {"loss": 1.8113, "grad_norm": 0.36315613985061646, "learning_rate": 0.0002, "epoch": 0.6546426185704742, "step": 490}, {"loss": 1.7805, "grad_norm": 0.377796471118927, "learning_rate": 0.0002, "epoch": 0.6680026720106881, "step": 500}, {"loss": 1.7457, "grad_norm": 0.34284207224845886, "learning_rate": 0.0002, "epoch": 0.6813627254509018, "step": 510}, {"loss": 1.8013, "grad_norm": 0.35563018918037415, "learning_rate": 0.0002, "epoch": 0.6947227788911156, "step": 520}, {"loss": 1.8414, "grad_norm": 0.37575867772102356, "learning_rate": 0.0002, "epoch": 0.7080828323313293, "step": 530}, {"loss": 1.7993, "grad_norm": 0.35719701647758484, "learning_rate": 0.0002, "epoch": 0.7214428857715431, "step": 540}, {"loss": 1.7574, "grad_norm": 0.385813444852829, "learning_rate": 0.0002, "epoch": 0.7348029392117569, "step": 550}, {"loss": 1.7985, "grad_norm": 0.44509607553482056, "learning_rate": 0.0002, "epoch": 0.7481629926519706, "step": 560}, {"loss": 1.7459, "grad_norm": 0.36108464002609253, "learning_rate": 0.0002, "epoch": 0.7615230460921844, "step": 570}, {"loss": 1.8207, "grad_norm": 0.3530745804309845, "learning_rate": 0.0002, "epoch": 0.7748830995323981, "step": 580}, {"loss": 1.7479, "grad_norm": 0.34888574481010437, "learning_rate": 0.0002, "epoch": 0.7882431529726119, "step": 590}, {"loss": 1.8656, "grad_norm": 0.387346476316452, "learning_rate": 0.0002, "epoch": 0.8016032064128257, "step": 600}, {"loss": 1.8071, "grad_norm": 0.3641138970851898, "learning_rate": 0.0002, "epoch": 0.8149632598530394, "step": 610}, {"loss": 1.7531, "grad_norm": 0.33729103207588196, "learning_rate": 0.0002, "epoch": 0.8283233132932531, "step": 620}, {"loss": 1.8613, "grad_norm": 0.3652004599571228, "learning_rate": 0.0002, "epoch": 0.8416833667334669, "step": 630}, {"loss": 1.9184, "grad_norm": 0.3986643850803375, "learning_rate": 0.0002, "epoch": 0.8550434201736807, "step": 640}, {"loss": 1.8198, "grad_norm": 0.3458964228630066, "learning_rate": 0.0002, "epoch": 0.8684034736138945, "step": 650}, {"loss": 1.803, "grad_norm": 0.3559381365776062, "learning_rate": 0.0002, "epoch": 0.8817635270541082, "step": 660}, {"loss": 1.7641, "grad_norm": 0.3612841069698334, "learning_rate": 0.0002, "epoch": 0.895123580494322, "step": 670}, {"loss": 1.7888, "grad_norm": 0.34771719574928284, "learning_rate": 0.0002, "epoch": 0.9084836339345357, "step": 680}, {"loss": 1.8204, "grad_norm": 0.3371497094631195, "learning_rate": 0.0002, "epoch": 0.9218436873747495, "step": 690}, {"loss": 1.7848, "grad_norm": 0.5596055388450623, "learning_rate": 0.0002, "epoch": 0.9352037408149633, "step": 700}, {"loss": 1.7794, "grad_norm": 0.311880499124527, "learning_rate": 0.0002, "epoch": 0.948563794255177, "step": 710}, {"loss": 1.8464, "grad_norm": 0.3462068736553192, "learning_rate": 0.0002, "epoch": 0.9619238476953907, "step": 720}, {"loss": 1.8197, "grad_norm": 0.29982393980026245, "learning_rate": 0.0002, "epoch": 0.9752839011356046, "step": 730}, {"loss": 1.8503, "grad_norm": 0.34606459736824036, "learning_rate": 0.0002, "epoch": 0.9886439545758183, "step": 740}, {"eval_loss": 1.8201380968093872, "eval_runtime": 38.6124, "eval_samples_per_second": 13.338, "eval_steps_per_second": 1.683, "epoch": 0.9993319973279893, "step": 748}, {"loss": 1.7786, "grad_norm": 0.32302048802375793, "learning_rate": 0.0002, "epoch": 1.002004008016032, "step": 750}, {"loss": 1.7297, "grad_norm": 0.37585633993148804, "learning_rate": 0.0002, "epoch": 1.0153640614562458, "step": 760}, {"loss": 1.7008, "grad_norm": 0.33826273679733276, "learning_rate": 0.0002, "epoch": 1.0287241148964597, "step": 770}, {"loss": 1.809, "grad_norm": 0.44682955741882324, "learning_rate": 0.0002, "epoch": 1.0420841683366733, "step": 780}, {"loss": 1.7092, "grad_norm": 0.422188401222229, "learning_rate": 0.0002, "epoch": 1.0554442217768871, "step": 790}, {"loss": 1.7765, "grad_norm": 0.3809906244277954, "learning_rate": 0.0002, "epoch": 1.0688042752171008, "step": 800}, {"loss": 1.7431, "grad_norm": 0.3454349637031555, "learning_rate": 0.0002, "epoch": 1.0821643286573146, "step": 810}, {"loss": 1.7257, "grad_norm": 0.3767355978488922, "learning_rate": 0.0002, "epoch": 1.0955243820975284, "step": 820}, {"loss": 1.7224, "grad_norm": 0.3361407518386841, "learning_rate": 0.0002, "epoch": 1.108884435537742, "step": 830}, {"loss": 1.7509, "grad_norm": 0.3654632568359375, "learning_rate": 0.0002, "epoch": 1.122244488977956, "step": 840}, {"loss": 1.7151, "grad_norm": 0.3822861313819885, "learning_rate": 0.0002, "epoch": 1.1356045424181698, "step": 850}, {"loss": 1.7121, "grad_norm": 0.3853831887245178, "learning_rate": 0.0002, "epoch": 1.1489645958583834, "step": 860}, {"loss": 1.7685, "grad_norm": 0.35521796345710754, "learning_rate": 0.0002, "epoch": 1.1623246492985972, "step": 870}, {"loss": 1.7735, "grad_norm": 0.4107200503349304, "learning_rate": 0.0002, "epoch": 1.1756847027388109, "step": 880}, {"loss": 1.7484, "grad_norm": 0.33219534158706665, "learning_rate": 0.0002, "epoch": 1.1890447561790247, "step": 890}, {"loss": 1.7071, "grad_norm": 0.3559704124927521, "learning_rate": 0.0002, "epoch": 1.2024048096192386, "step": 900}, {"loss": 1.7535, "grad_norm": 0.3700537383556366, "learning_rate": 0.0002, "epoch": 1.2157648630594522, "step": 910}, {"loss": 1.7513, "grad_norm": 0.3771909475326538, "learning_rate": 0.0002, "epoch": 1.229124916499666, "step": 920}, {"loss": 1.7566, "grad_norm": 0.3136613965034485, "learning_rate": 0.0002, "epoch": 1.2424849699398797, "step": 930}, {"loss": 1.6783, "grad_norm": 0.3952099084854126, "learning_rate": 0.0002, "epoch": 1.2558450233800935, "step": 940}, {"loss": 1.7691, "grad_norm": 0.36534377932548523, "learning_rate": 0.0002, "epoch": 1.2692050768203074, "step": 950}, {"loss": 1.7127, "grad_norm": 0.3803492486476898, "learning_rate": 0.0002, "epoch": 1.282565130260521, "step": 960}, {"loss": 1.7896, "grad_norm": 0.3992428183555603, "learning_rate": 0.0002, "epoch": 1.2959251837007348, "step": 970}, {"loss": 1.7343, "grad_norm": 0.3627142906188965, "learning_rate": 0.0002, "epoch": 1.3092852371409487, "step": 980}, {"loss": 1.7598, "grad_norm": 0.4248180091381073, "learning_rate": 0.0002, "epoch": 1.3226452905811623, "step": 990}, {"loss": 1.6896, "grad_norm": 0.4060308039188385, "learning_rate": 0.0002, "epoch": 1.3360053440213762, "step": 1000}, {"loss": 1.7457, "grad_norm": 0.3788969814777374, "learning_rate": 0.0002, "epoch": 1.3493653974615898, "step": 1010}, {"loss": 1.7111, "grad_norm": 0.4174270033836365, "learning_rate": 0.0002, "epoch": 1.3627254509018036, "step": 1020}, {"loss": 1.7975, "grad_norm": 0.35500675439834595, "learning_rate": 0.0002, "epoch": 1.3760855043420173, "step": 1030}, {"loss": 1.724, "grad_norm": 0.3454059362411499, "learning_rate": 0.0002, "epoch": 1.389445557782231, "step": 1040}, {"loss": 1.8299, "grad_norm": 0.45807570219039917, "learning_rate": 0.0002, "epoch": 1.402805611222445, "step": 1050}, {"loss": 1.7425, "grad_norm": 0.39338022470474243, "learning_rate": 0.0002, "epoch": 1.4161656646626586, "step": 1060}, {"loss": 1.7457, "grad_norm": 0.3870709240436554, "learning_rate": 0.0002, "epoch": 1.4295257181028724, "step": 1070}, {"loss": 1.6565, "grad_norm": 0.40996190905570984, "learning_rate": 0.0002, "epoch": 1.4428857715430863, "step": 1080}, {"loss": 1.7324, "grad_norm": 0.38762837648391724, "learning_rate": 0.0002, "epoch": 1.4562458249833, "step": 1090}, {"loss": 1.7362, "grad_norm": 0.36756977438926697, "learning_rate": 0.0002, "epoch": 1.4696058784235138, "step": 1100}, {"loss": 1.7451, "grad_norm": 0.4087235927581787, "learning_rate": 0.0002, "epoch": 1.4829659318637274, "step": 1110}, {"loss": 1.7114, "grad_norm": 0.3357745110988617, "learning_rate": 0.0002, "epoch": 1.4963259853039412, "step": 1120}, {"loss": 1.6877, "grad_norm": 0.37486532330513, "learning_rate": 0.0002, "epoch": 1.5096860387441549, "step": 1130}, {"loss": 1.7252, "grad_norm": 0.3387809991836548, "learning_rate": 0.0002, "epoch": 1.5230460921843687, "step": 1140}, {"loss": 1.7169, "grad_norm": 0.37462118268013, "learning_rate": 0.0002, "epoch": 1.5364061456245826, "step": 1150}, {"loss": 1.6988, "grad_norm": 0.38575324416160583, "learning_rate": 0.0002, "epoch": 1.5497661990647962, "step": 1160}, {"loss": 1.7438, "grad_norm": 0.3515765964984894, "learning_rate": 0.0002, "epoch": 1.56312625250501, "step": 1170}, {"loss": 1.7524, "grad_norm": 0.39308643341064453, "learning_rate": 0.0002, "epoch": 1.5764863059452239, "step": 1180}, {"loss": 1.6422, "grad_norm": 0.3308864235877991, "learning_rate": 0.0002, "epoch": 1.5898463593854375, "step": 1190}, {"loss": 1.7566, "grad_norm": 0.3397478461265564, "learning_rate": 0.0002, "epoch": 1.6032064128256514, "step": 1200}, {"loss": 1.7871, "grad_norm": 0.3911525309085846, "learning_rate": 0.0002, "epoch": 1.6165664662658652, "step": 1210}, {"loss": 1.7443, "grad_norm": 0.3771969974040985, "learning_rate": 0.0002, "epoch": 1.6299265197060788, "step": 1220}, {"loss": 1.7631, "grad_norm": 0.35346856713294983, "learning_rate": 0.0002, "epoch": 1.6432865731462925, "step": 1230}, {"loss": 1.7225, "grad_norm": 0.41736963391304016, "learning_rate": 0.0002, "epoch": 1.6566466265865063, "step": 1240}, {"loss": 1.7582, "grad_norm": 0.3375225067138672, "learning_rate": 0.0002, "epoch": 1.6700066800267201, "step": 1250}, {"loss": 1.6916, "grad_norm": 0.3779928982257843, "learning_rate": 0.0002, "epoch": 1.6833667334669338, "step": 1260}, {"loss": 1.728, "grad_norm": 0.35388994216918945, "learning_rate": 0.0002, "epoch": 1.6967267869071476, "step": 1270}, {"loss": 1.7461, "grad_norm": 0.33884134888648987, "learning_rate": 0.0002, "epoch": 1.7100868403473615, "step": 1280}, {"loss": 1.7083, "grad_norm": 0.35439756512641907, "learning_rate": 0.0002, "epoch": 1.723446893787575, "step": 1290}, {"loss": 1.7389, "grad_norm": 0.3766156733036041, "learning_rate": 0.0002, "epoch": 1.736806947227789, "step": 1300}, {"loss": 1.7847, "grad_norm": 0.36148911714553833, "learning_rate": 0.0002, "epoch": 1.7501670006680028, "step": 1310}, {"loss": 1.7344, "grad_norm": 0.39687496423721313, "learning_rate": 0.0002, "epoch": 1.7635270541082164, "step": 1320}, {"loss": 1.7541, "grad_norm": 0.35639452934265137, "learning_rate": 0.0002, "epoch": 1.77688710754843, "step": 1330}, {"loss": 1.7254, "grad_norm": 0.38781628012657166, "learning_rate": 0.0002, "epoch": 1.7902471609886441, "step": 1340}, {"loss": 1.7867, "grad_norm": 0.42784637212753296, "learning_rate": 0.0002, "epoch": 1.8036072144288577, "step": 1350}, {"loss": 1.7336, "grad_norm": 0.40258511900901794, "learning_rate": 0.0002, "epoch": 1.8169672678690714, "step": 1360}, {"loss": 1.7771, "grad_norm": 0.36674195528030396, "learning_rate": 0.0002, "epoch": 1.8303273213092852, "step": 1370}, {"loss": 1.7425, "grad_norm": 0.4064558446407318, "learning_rate": 0.0002, "epoch": 1.843687374749499, "step": 1380}, {"loss": 1.7425, "grad_norm": 0.3669849932193756, "learning_rate": 0.0002, "epoch": 1.8570474281897127, "step": 1390}, {"loss": 1.7924, "grad_norm": 0.37569567561149597, "learning_rate": 0.0002, "epoch": 1.8704074816299265, "step": 1400}, {"loss": 1.7885, "grad_norm": 0.37307995557785034, "learning_rate": 0.0002, "epoch": 1.8837675350701404, "step": 1410}, {"loss": 1.7548, "grad_norm": 0.3772695064544678, "learning_rate": 0.0002, "epoch": 1.897127588510354, "step": 1420}, {"loss": 1.7682, "grad_norm": 0.36993589997291565, "learning_rate": 0.0002, "epoch": 1.9104876419505676, "step": 1430}, {"loss": 1.7249, "grad_norm": 0.3490557372570038, "learning_rate": 0.0002, "epoch": 1.9238476953907817, "step": 1440}, {"loss": 1.7979, "grad_norm": 0.3716149628162384, "learning_rate": 0.0002, "epoch": 1.9372077488309953, "step": 1450}, {"loss": 1.6664, "grad_norm": 0.39236098527908325, "learning_rate": 0.0002, "epoch": 1.950567802271209, "step": 1460}, {"loss": 1.6852, "grad_norm": 0.37258651852607727, "learning_rate": 0.0002, "epoch": 1.9639278557114228, "step": 1470}, {"loss": 1.7427, "grad_norm": 0.36183077096939087, "learning_rate": 0.0002, "epoch": 1.9772879091516367, "step": 1480}, {"loss": 1.7055, "grad_norm": 0.3956947326660156, "learning_rate": 0.0002, "epoch": 1.9906479625918503, "step": 1490}, {"eval_loss": 1.8132041692733765, "eval_runtime": 38.6287, "eval_samples_per_second": 13.332, "eval_steps_per_second": 1.683, "epoch": 2.0, "step": 1497}, {"loss": 1.6791, "grad_norm": 0.34480565786361694, "learning_rate": 0.0002, "epoch": 2.004008016032064, "step": 1500}, {"loss": 1.6367, "grad_norm": 0.3418028652667999, "learning_rate": 0.0002, "epoch": 2.017368069472278, "step": 1510}, {"loss": 1.5827, "grad_norm": 0.4514467716217041, "learning_rate": 0.0002, "epoch": 2.0307281229124916, "step": 1520}, {"loss": 1.6365, "grad_norm": 0.4197506606578827, "learning_rate": 0.0002, "epoch": 2.0440881763527052, "step": 1530}, {"loss": 1.6221, "grad_norm": 0.4134170711040497, "learning_rate": 0.0002, "epoch": 2.0574482297929193, "step": 1540}, {"loss": 1.6876, "grad_norm": 0.43709826469421387, "learning_rate": 0.0002, "epoch": 2.070808283233133, "step": 1550}, {"loss": 1.5779, "grad_norm": 0.4703378677368164, "learning_rate": 0.0002, "epoch": 2.0841683366733466, "step": 1560}, {"loss": 1.599, "grad_norm": 0.4538188576698303, "learning_rate": 0.0002, "epoch": 2.0975283901135606, "step": 1570}, {"loss": 1.6464, "grad_norm": 0.4649668037891388, "learning_rate": 0.0002, "epoch": 2.1108884435537743, "step": 1580}, {"loss": 1.6348, "grad_norm": 0.42669883370399475, "learning_rate": 0.0002, "epoch": 2.124248496993988, "step": 1590}, {"loss": 1.5838, "grad_norm": 0.43162038922309875, "learning_rate": 0.0002, "epoch": 2.1376085504342015, "step": 1600}, {"loss": 1.6673, "grad_norm": 0.4294586479663849, "learning_rate": 0.0002, "epoch": 2.1509686038744156, "step": 1610}, {"loss": 1.6024, "grad_norm": 0.4669102132320404, "learning_rate": 0.0002, "epoch": 2.164328657314629, "step": 1620}, {"loss": 1.659, "grad_norm": 0.4188412129878998, "learning_rate": 0.0002, "epoch": 2.177688710754843, "step": 1630}, {"loss": 1.625, "grad_norm": 0.4662680923938751, "learning_rate": 0.0002, "epoch": 2.191048764195057, "step": 1640}, {"loss": 1.6699, "grad_norm": 0.4020286500453949, "learning_rate": 0.0002, "epoch": 2.2044088176352705, "step": 1650}, {"loss": 1.6284, "grad_norm": 0.41919606924057007, "learning_rate": 0.0002, "epoch": 2.217768871075484, "step": 1660}, {"loss": 1.6776, "grad_norm": 0.4644531309604645, "learning_rate": 0.0002, "epoch": 2.231128924515698, "step": 1670}, {"loss": 1.6711, "grad_norm": 0.4526427984237671, "learning_rate": 0.0002, "epoch": 2.244488977955912, "step": 1680}, {"loss": 1.6058, "grad_norm": 0.45953166484832764, "learning_rate": 0.0002, "epoch": 2.2578490313961255, "step": 1690}, {"loss": 1.5979, "grad_norm": 0.4701860249042511, "learning_rate": 0.0002, "epoch": 2.2712090848363395, "step": 1700}, {"loss": 1.6183, "grad_norm": 0.4749310612678528, "learning_rate": 0.0002, "epoch": 2.284569138276553, "step": 1710}, {"loss": 1.6703, "grad_norm": 0.45026102662086487, "learning_rate": 0.0002, "epoch": 2.297929191716767, "step": 1720}, {"loss": 1.6386, "grad_norm": 0.4755004048347473, "learning_rate": 0.0002, "epoch": 2.3112892451569804, "step": 1730}, {"loss": 1.6365, "grad_norm": 0.4505726993083954, "learning_rate": 0.0002, "epoch": 2.3246492985971945, "step": 1740}, {"loss": 1.589, "grad_norm": 0.44464054703712463, "learning_rate": 0.0002, "epoch": 2.338009352037408, "step": 1750}, {"loss": 1.6139, "grad_norm": 0.4449476897716522, "learning_rate": 0.0002, "epoch": 2.3513694054776217, "step": 1760}, {"loss": 1.7195, "grad_norm": 0.4216482937335968, "learning_rate": 0.0002, "epoch": 2.364729458917836, "step": 1770}, {"loss": 1.7075, "grad_norm": 0.4379308521747589, "learning_rate": 0.0002, "epoch": 2.3780895123580494, "step": 1780}, {"loss": 1.7024, "grad_norm": 0.41670042276382446, "learning_rate": 0.0002, "epoch": 2.391449565798263, "step": 1790}, {"loss": 1.5989, "grad_norm": 0.48089510202407837, "learning_rate": 0.0002, "epoch": 2.404809619238477, "step": 1800}, {"loss": 1.6313, "grad_norm": 0.4389738142490387, "learning_rate": 0.0002, "epoch": 2.4181696726786908, "step": 1810}, {"loss": 1.5841, "grad_norm": 0.45293036103248596, "learning_rate": 0.0002, "epoch": 2.4315297261189044, "step": 1820}, {"loss": 1.6887, "grad_norm": 0.5211683511734009, "learning_rate": 0.0002, "epoch": 2.4448897795591185, "step": 1830}, {"loss": 1.6599, "grad_norm": 0.4631884694099426, "learning_rate": 0.0002, "epoch": 2.458249832999332, "step": 1840}, {"loss": 1.6537, "grad_norm": 0.4276818335056305, "learning_rate": 0.0002, "epoch": 2.4716098864395457, "step": 1850}, {"loss": 1.6836, "grad_norm": 0.477524071931839, "learning_rate": 0.0002, "epoch": 2.4849699398797593, "step": 1860}, {"loss": 1.66, "grad_norm": 0.44860973954200745, "learning_rate": 0.0002, "epoch": 2.4983299933199734, "step": 1870}, {"loss": 1.6308, "grad_norm": 0.46413546800613403, "learning_rate": 0.0002, "epoch": 2.511690046760187, "step": 1880}, {"loss": 1.6225, "grad_norm": 0.42487645149230957, "learning_rate": 0.0002, "epoch": 2.5250501002004007, "step": 1890}, {"loss": 1.6268, "grad_norm": 0.4778307378292084, "learning_rate": 0.0002, "epoch": 2.5384101536406147, "step": 1900}, {"loss": 1.6143, "grad_norm": 0.45307061076164246, "learning_rate": 0.0002, "epoch": 2.5517702070808284, "step": 1910}, {"loss": 1.7279, "grad_norm": 0.47886642813682556, "learning_rate": 0.0002, "epoch": 2.565130260521042, "step": 1920}, {"loss": 1.5931, "grad_norm": 0.4839435815811157, "learning_rate": 0.0002, "epoch": 2.5784903139612556, "step": 1930}, {"loss": 1.6089, "grad_norm": 0.4388359785079956, "learning_rate": 0.0002, "epoch": 2.5918503674014697, "step": 1940}, {"loss": 1.6828, "grad_norm": 0.47859734296798706, "learning_rate": 0.0002, "epoch": 2.6052104208416833, "step": 1950}, {"loss": 1.6014, "grad_norm": 0.5526517033576965, "learning_rate": 0.0002, "epoch": 2.6185704742818974, "step": 1960}, {"loss": 1.6889, "grad_norm": 0.5449170470237732, "learning_rate": 0.0002, "epoch": 2.631930527722111, "step": 1970}, {"loss": 1.6481, "grad_norm": 0.48521968722343445, "learning_rate": 0.0002, "epoch": 2.6452905811623246, "step": 1980}, {"loss": 1.6741, "grad_norm": 0.4733737111091614, "learning_rate": 0.0002, "epoch": 2.6586506346025383, "step": 1990}, {"loss": 1.662, "grad_norm": 0.507118284702301, "learning_rate": 0.0002, "epoch": 2.6720106880427523, "step": 2000}, {"loss": 1.6419, "grad_norm": 0.4508971571922302, "learning_rate": 0.0002, "epoch": 2.685370741482966, "step": 2010}, {"loss": 1.7052, "grad_norm": 0.4657728672027588, "learning_rate": 0.0002, "epoch": 2.6987307949231796, "step": 2020}, {"loss": 1.6261, "grad_norm": 0.48647549748420715, "learning_rate": 0.0002, "epoch": 2.7120908483633936, "step": 2030}, {"loss": 1.5638, "grad_norm": 0.49525555968284607, "learning_rate": 0.0002, "epoch": 2.7254509018036073, "step": 2040}, {"loss": 1.658, "grad_norm": 0.4712379276752472, "learning_rate": 0.0002, "epoch": 2.738810955243821, "step": 2050}, {"loss": 1.6464, "grad_norm": 0.4846591055393219, "learning_rate": 0.0002, "epoch": 2.7521710086840345, "step": 2060}, {"loss": 1.5641, "grad_norm": 0.4823240041732788, "learning_rate": 0.0002, "epoch": 2.7655310621242486, "step": 2070}, {"loss": 1.6701, "grad_norm": 0.4546685516834259, "learning_rate": 0.0002, "epoch": 2.778891115564462, "step": 2080}, {"loss": 1.7015, "grad_norm": 0.45542681217193604, "learning_rate": 0.0002, "epoch": 2.7922511690046763, "step": 2090}, {"loss": 1.6398, "grad_norm": 0.42137566208839417, "learning_rate": 0.0002, "epoch": 2.80561122244489, "step": 2100}, {"loss": 1.6526, "grad_norm": 0.6143282055854797, "learning_rate": 0.0002, "epoch": 2.8189712758851035, "step": 2110}, {"loss": 1.6955, "grad_norm": 0.4828081727027893, "learning_rate": 0.0002, "epoch": 2.832331329325317, "step": 2120}, {"loss": 1.744, "grad_norm": 0.4319005608558655, "learning_rate": 0.0002, "epoch": 2.845691382765531, "step": 2130}, {"loss": 1.6717, "grad_norm": 0.4297086298465729, "learning_rate": 0.0002, "epoch": 2.859051436205745, "step": 2140}, {"loss": 1.5968, "grad_norm": 0.5011981129646301, "learning_rate": 0.0002, "epoch": 2.8724114896459585, "step": 2150}, {"loss": 1.7181, "grad_norm": 0.4401548504829407, "learning_rate": 0.0002, "epoch": 2.8857715430861726, "step": 2160}, {"loss": 1.5722, "grad_norm": 0.48090746998786926, "learning_rate": 0.0002, "epoch": 2.899131596526386, "step": 2170}, {"loss": 1.6596, "grad_norm": 0.4740385413169861, "learning_rate": 0.0002, "epoch": 2.9124916499666, "step": 2180}, {"loss": 1.6501, "grad_norm": 0.5337260365486145, "learning_rate": 0.0002, "epoch": 2.9258517034068134, "step": 2190}, {"loss": 1.6802, "grad_norm": 0.4420052766799927, "learning_rate": 0.0002, "epoch": 2.9392117568470275, "step": 2200}, {"loss": 1.5474, "grad_norm": 0.477512389421463, "learning_rate": 0.0002, "epoch": 2.952571810287241, "step": 2210}, {"loss": 1.6544, "grad_norm": 0.5344052910804749, "learning_rate": 0.0002, "epoch": 2.9659318637274548, "step": 2220}, {"loss": 1.6866, "grad_norm": 0.4483940303325653, "learning_rate": 0.0002, "epoch": 2.979291917167669, "step": 2230}, {"loss": 1.6477, "grad_norm": 0.4366597831249237, "learning_rate": 0.0002, "epoch": 2.9926519706078825, "step": 2240}, {"eval_loss": 1.834012746810913, "eval_runtime": 38.5659, "eval_samples_per_second": 13.354, "eval_steps_per_second": 1.685, "epoch": 2.9993319973279893, "step": 2245}, {"loss": 1.5582, "grad_norm": 0.428824245929718, "learning_rate": 0.0002, "epoch": 3.006012024048096, "step": 2250}, {"loss": 1.499, "grad_norm": 0.4870174825191498, "learning_rate": 0.0002, "epoch": 3.01937207748831, "step": 2260}, {"loss": 1.4872, "grad_norm": 0.4684266149997711, "learning_rate": 0.0002, "epoch": 3.032732130928524, "step": 2270}, {"loss": 1.5284, "grad_norm": 0.581604540348053, "learning_rate": 0.0002, "epoch": 3.0460921843687374, "step": 2280}, {"loss": 1.4549, "grad_norm": 0.5561677813529968, "learning_rate": 0.0002, "epoch": 3.059452237808951, "step": 2290}, {"loss": 1.4903, "grad_norm": 0.5750220417976379, "learning_rate": 0.0002, "epoch": 3.072812291249165, "step": 2300}, {"loss": 1.5903, "grad_norm": 0.5704626441001892, "learning_rate": 0.0002, "epoch": 3.0861723446893787, "step": 2310}, {"loss": 1.4292, "grad_norm": 0.6242083311080933, "learning_rate": 0.0002, "epoch": 3.0995323981295924, "step": 2320}, {"loss": 1.5092, "grad_norm": 0.5174121260643005, "learning_rate": 0.0002, "epoch": 3.1128924515698064, "step": 2330}, {"loss": 1.5106, "grad_norm": 0.5697633028030396, "learning_rate": 0.0002, "epoch": 3.12625250501002, "step": 2340}, {"loss": 1.5156, "grad_norm": 0.5969541072845459, "learning_rate": 0.0002, "epoch": 3.1396125584502337, "step": 2350}, {"loss": 1.52, "grad_norm": 0.6244304180145264, "learning_rate": 0.0002, "epoch": 3.1529726118904478, "step": 2360}, {"loss": 1.5244, "grad_norm": 0.5561705827713013, "learning_rate": 0.0002, "epoch": 3.1663326653306614, "step": 2370}, {"loss": 1.6169, "grad_norm": 0.5401188135147095, "learning_rate": 0.0002, "epoch": 3.179692718770875, "step": 2380}, {"loss": 1.5387, "grad_norm": 0.6450421810150146, "learning_rate": 0.0002, "epoch": 3.1930527722110886, "step": 2390}, {"loss": 1.4839, "grad_norm": 0.5741903185844421, "learning_rate": 0.0002, "epoch": 3.2064128256513027, "step": 2400}, {"loss": 1.5584, "grad_norm": 0.6337407231330872, "learning_rate": 0.0002, "epoch": 3.2197728790915163, "step": 2410}, {"loss": 1.5025, "grad_norm": 0.6493517160415649, "learning_rate": 0.0002, "epoch": 3.23313293253173, "step": 2420}, {"loss": 1.5168, "grad_norm": 0.6230176091194153, "learning_rate": 0.0002, "epoch": 3.246492985971944, "step": 2430}, {"loss": 1.5408, "grad_norm": 0.680704653263092, "learning_rate": 0.0002, "epoch": 3.2598530394121576, "step": 2440}, {"loss": 1.6005, "grad_norm": 0.5279417037963867, "learning_rate": 0.0002, "epoch": 3.2732130928523713, "step": 2450}, {"loss": 1.5231, "grad_norm": 0.5601515173912048, "learning_rate": 0.0002, "epoch": 3.2865731462925853, "step": 2460}, {"loss": 1.4949, "grad_norm": 0.5591090321540833, "learning_rate": 0.0002, "epoch": 3.299933199732799, "step": 2470}, {"loss": 1.5181, "grad_norm": 0.6596529483795166, "learning_rate": 0.0002, "epoch": 3.3132932531730126, "step": 2480}, {"loss": 1.5259, "grad_norm": 0.6115918755531311, "learning_rate": 0.0002, "epoch": 3.3266533066132267, "step": 2490}, {"loss": 1.5344, "grad_norm": 0.6443548202514648, "learning_rate": 0.0002, "epoch": 3.3400133600534403, "step": 2500}, {"loss": 1.5037, "grad_norm": 0.5504242181777954, "learning_rate": 0.0002, "epoch": 3.353373413493654, "step": 2510}, {"loss": 1.5049, "grad_norm": 0.6104483604431152, "learning_rate": 0.0002, "epoch": 3.3667334669338675, "step": 2520}, {"loss": 1.587, "grad_norm": 0.8387531638145447, "learning_rate": 0.0002, "epoch": 3.3800935203740816, "step": 2530}, {"loss": 1.5227, "grad_norm": 0.6346094012260437, "learning_rate": 0.0002, "epoch": 3.3934535738142952, "step": 2540}, {"loss": 1.4855, "grad_norm": 0.6261265873908997, "learning_rate": 0.0002, "epoch": 3.406813627254509, "step": 2550}, {"loss": 1.5233, "grad_norm": 0.5960372090339661, "learning_rate": 0.0002, "epoch": 3.420173680694723, "step": 2560}, {"loss": 1.5153, "grad_norm": 0.5291280746459961, "learning_rate": 0.0002, "epoch": 3.4335337341349366, "step": 2570}, {"loss": 1.5152, "grad_norm": 0.6133161783218384, "learning_rate": 0.0002, "epoch": 3.44689378757515, "step": 2580}, {"loss": 1.5533, "grad_norm": 0.623573362827301, "learning_rate": 0.0002, "epoch": 3.460253841015364, "step": 2590}, {"loss": 1.4935, "grad_norm": 0.5959834456443787, "learning_rate": 0.0002, "epoch": 3.473613894455578, "step": 2600}, {"loss": 1.5792, "grad_norm": 0.583332359790802, "learning_rate": 0.0002, "epoch": 3.4869739478957915, "step": 2610}, {"loss": 1.5229, "grad_norm": 0.6003559231758118, "learning_rate": 0.0002, "epoch": 3.5003340013360056, "step": 2620}, {"loss": 1.4901, "grad_norm": 0.5832992196083069, "learning_rate": 0.0002, "epoch": 3.513694054776219, "step": 2630}, {"loss": 1.5005, "grad_norm": 0.5942609906196594, "learning_rate": 0.0002, "epoch": 3.527054108216433, "step": 2640}, {"loss": 1.5213, "grad_norm": 0.6087163686752319, "learning_rate": 0.0002, "epoch": 3.5404141616566465, "step": 2650}, {"loss": 1.5826, "grad_norm": 0.631948709487915, "learning_rate": 0.0002, "epoch": 3.5537742150968605, "step": 2660}, {"loss": 1.5844, "grad_norm": 0.6450803279876709, "learning_rate": 0.0002, "epoch": 3.567134268537074, "step": 2670}, {"loss": 1.4981, "grad_norm": 0.6507797837257385, "learning_rate": 0.0002, "epoch": 3.580494321977288, "step": 2680}, {"loss": 1.5826, "grad_norm": 0.5778017044067383, "learning_rate": 0.0002, "epoch": 3.593854375417502, "step": 2690}, {"loss": 1.4688, "grad_norm": 0.6214032173156738, "learning_rate": 0.0002, "epoch": 3.6072144288577155, "step": 2700}, {"loss": 1.5084, "grad_norm": 0.5681133270263672, "learning_rate": 0.0002, "epoch": 3.620574482297929, "step": 2710}, {"loss": 1.471, "grad_norm": 0.6074244976043701, "learning_rate": 0.0002, "epoch": 3.6339345357381427, "step": 2720}, {"loss": 1.5243, "grad_norm": 0.5900560617446899, "learning_rate": 0.0002, "epoch": 3.647294589178357, "step": 2730}, {"loss": 1.5074, "grad_norm": 0.5817505717277527, "learning_rate": 0.0002, "epoch": 3.6606546426185704, "step": 2740}, {"loss": 1.5117, "grad_norm": 0.6095547676086426, "learning_rate": 0.0002, "epoch": 3.6740146960587845, "step": 2750}, {"loss": 1.5117, "grad_norm": 0.612790584564209, "learning_rate": 0.0002, "epoch": 3.687374749498998, "step": 2760}, {"loss": 1.4976, "grad_norm": 0.6574140787124634, "learning_rate": 0.0002, "epoch": 3.7007348029392118, "step": 2770}, {"loss": 1.5306, "grad_norm": 0.5643761157989502, "learning_rate": 0.0002, "epoch": 3.7140948563794254, "step": 2780}, {"loss": 1.5751, "grad_norm": 0.5652621388435364, "learning_rate": 0.0002, "epoch": 3.727454909819639, "step": 2790}, {"loss": 1.5262, "grad_norm": 0.5604206323623657, "learning_rate": 0.0002, "epoch": 3.740814963259853, "step": 2800}, {"loss": 1.5013, "grad_norm": 3.911022663116455, "learning_rate": 0.0002, "epoch": 3.7541750167000667, "step": 2810}, {"loss": 1.5793, "grad_norm": 0.6148333549499512, "learning_rate": 0.0002, "epoch": 3.7675350701402808, "step": 2820}, {"loss": 1.5122, "grad_norm": 0.5605677962303162, "learning_rate": 0.0002, "epoch": 3.7808951235804944, "step": 2830}, {"loss": 1.5659, "grad_norm": 0.6101965308189392, "learning_rate": 0.0002, "epoch": 3.794255177020708, "step": 2840}, {"loss": 1.5618, "grad_norm": 0.5387342572212219, "learning_rate": 0.0002, "epoch": 3.8076152304609217, "step": 2850}, {"loss": 1.5193, "grad_norm": 0.5733087062835693, "learning_rate": 0.0002, "epoch": 3.8209752839011357, "step": 2860}, {"loss": 1.5545, "grad_norm": 0.6538485884666443, "learning_rate": 0.0002, "epoch": 3.8343353373413493, "step": 2870}, {"loss": 1.523, "grad_norm": 0.6247632503509521, "learning_rate": 0.0002, "epoch": 3.847695390781563, "step": 2880}, {"loss": 1.5591, "grad_norm": 0.5745735764503479, "learning_rate": 0.0002, "epoch": 3.861055444221777, "step": 2890}, {"loss": 1.5706, "grad_norm": 0.5942763686180115, "learning_rate": 0.0002, "epoch": 3.8744154976619907, "step": 2900}, {"loss": 1.564, "grad_norm": 0.7086281776428223, "learning_rate": 0.0002, "epoch": 3.8877755511022043, "step": 2910}, {"loss": 1.5526, "grad_norm": 0.8825129866600037, "learning_rate": 0.0002, "epoch": 3.901135604542418, "step": 2920}, {"loss": 1.4519, "grad_norm": 0.6260842680931091, "learning_rate": 0.0002, "epoch": 3.914495657982632, "step": 2930}, {"loss": 1.5433, "grad_norm": 0.6015968322753906, "learning_rate": 0.0002, "epoch": 3.9278557114228456, "step": 2940}, {"loss": 1.4931, "grad_norm": 0.7042809128761292, "learning_rate": 0.0002, "epoch": 3.9412157648630597, "step": 2950}, {"loss": 1.5596, "grad_norm": 0.5860083699226379, "learning_rate": 0.0002, "epoch": 3.9545758183032733, "step": 2960}, {"loss": 1.565, "grad_norm": 0.5939757823944092, "learning_rate": 0.0002, "epoch": 3.967935871743487, "step": 2970}, {"loss": 1.408, "grad_norm": 0.5523964166641235, "learning_rate": 0.0002, "epoch": 3.9812959251837006, "step": 2980}, {"loss": 1.5629, "grad_norm": 0.6380264759063721, "learning_rate": 0.0002, "epoch": 3.9946559786239146, "step": 2990}, {"eval_loss": 1.8875294923782349, "eval_runtime": 38.5837, "eval_samples_per_second": 13.348, "eval_steps_per_second": 1.685, "epoch": 4.0, "step": 2994}, {"loss": 1.4002, "grad_norm": 0.5478564500808716, "learning_rate": 0.0002, "epoch": 4.008016032064128, "step": 3000}, {"loss": 1.436, "grad_norm": 0.9384379982948303, "learning_rate": 0.0002, "epoch": 4.021376085504342, "step": 3010}, {"loss": 1.4127, "grad_norm": 0.7819344401359558, "learning_rate": 0.0002, "epoch": 4.034736138944556, "step": 3020}, {"loss": 1.326, "grad_norm": 0.7737417817115784, "learning_rate": 0.0002, "epoch": 4.04809619238477, "step": 3030}, {"loss": 1.3203, "grad_norm": 0.8893805742263794, "learning_rate": 0.0002, "epoch": 4.061456245824983, "step": 3040}, {"loss": 1.3913, "grad_norm": 0.7759843468666077, "learning_rate": 0.0002, "epoch": 4.074816299265197, "step": 3050}, {"loss": 1.2941, "grad_norm": 0.642654538154602, "learning_rate": 0.0002, "epoch": 4.0881763527054105, "step": 3060}, {"loss": 1.3204, "grad_norm": 0.8515549302101135, "learning_rate": 0.0002, "epoch": 4.101536406145625, "step": 3070}, {"loss": 1.3683, "grad_norm": 0.7033658623695374, "learning_rate": 0.0002, "epoch": 4.114896459585839, "step": 3080}, {"loss": 1.4159, "grad_norm": 0.7063882946968079, "learning_rate": 0.0002, "epoch": 4.128256513026052, "step": 3090}, {"loss": 1.384, "grad_norm": 0.6946853995323181, "learning_rate": 0.0002, "epoch": 4.141616566466266, "step": 3100}, {"loss": 1.3689, "grad_norm": 0.7286741137504578, "learning_rate": 0.0002, "epoch": 4.1549766199064795, "step": 3110}, {"loss": 1.3061, "grad_norm": 0.7894193530082703, "learning_rate": 0.0002, "epoch": 4.168336673346693, "step": 3120}, {"loss": 1.3346, "grad_norm": 0.7005895376205444, "learning_rate": 0.0002, "epoch": 4.181696726786907, "step": 3130}, {"loss": 1.3834, "grad_norm": 0.799567461013794, "learning_rate": 0.0002, "epoch": 4.195056780227121, "step": 3140}, {"loss": 1.3813, "grad_norm": 0.7010157108306885, "learning_rate": 0.0002, "epoch": 4.208416833667335, "step": 3150}, {"loss": 1.3637, "grad_norm": 0.7489650249481201, "learning_rate": 0.0002, "epoch": 4.2217768871075485, "step": 3160}, {"loss": 1.3546, "grad_norm": 0.7908048629760742, "learning_rate": 0.0002, "epoch": 4.235136940547762, "step": 3170}, {"loss": 1.3073, "grad_norm": 0.7002180814743042, "learning_rate": 0.0002, "epoch": 4.248496993987976, "step": 3180}, {"loss": 1.4525, "grad_norm": 0.8339495062828064, "learning_rate": 0.0002, "epoch": 4.261857047428189, "step": 3190}, {"loss": 1.3471, "grad_norm": 0.7884618043899536, "learning_rate": 0.0002, "epoch": 4.275217100868403, "step": 3200}, {"loss": 1.4261, "grad_norm": 0.7964122295379639, "learning_rate": 0.0002, "epoch": 4.2885771543086175, "step": 3210}, {"loss": 1.3506, "grad_norm": 0.838646650314331, "learning_rate": 0.0002, "epoch": 4.301937207748831, "step": 3220}, {"loss": 1.3738, "grad_norm": 0.8063107132911682, "learning_rate": 0.0002, "epoch": 4.315297261189045, "step": 3230}, {"loss": 1.3769, "grad_norm": 0.8147385120391846, "learning_rate": 0.0002, "epoch": 4.328657314629258, "step": 3240}, {"loss": 1.4118, "grad_norm": 0.7636798620223999, "learning_rate": 0.0002, "epoch": 4.342017368069472, "step": 3250}, {"loss": 1.3698, "grad_norm": 0.7530609965324402, "learning_rate": 0.0002, "epoch": 4.355377421509686, "step": 3260}, {"loss": 1.3507, "grad_norm": 0.8853573799133301, "learning_rate": 0.0002, "epoch": 4.3687374749499, "step": 3270}, {"loss": 1.3614, "grad_norm": 0.7180975675582886, "learning_rate": 0.0002, "epoch": 4.382097528390114, "step": 3280}, {"loss": 1.4119, "grad_norm": 0.837150514125824, "learning_rate": 0.0002, "epoch": 4.395457581830327, "step": 3290}, {"loss": 1.461, "grad_norm": 0.8370638489723206, "learning_rate": 0.0002, "epoch": 4.408817635270541, "step": 3300}, {"loss": 1.4478, "grad_norm": 0.7738229036331177, "learning_rate": 0.0002, "epoch": 4.422177688710755, "step": 3310}, {"loss": 1.4195, "grad_norm": 0.7665290832519531, "learning_rate": 0.0002, "epoch": 4.435537742150968, "step": 3320}, {"loss": 1.3308, "grad_norm": 0.7547745704650879, "learning_rate": 0.0002, "epoch": 4.448897795591183, "step": 3330}, {"loss": 1.4165, "grad_norm": 0.7421861290931702, "learning_rate": 0.0002, "epoch": 4.462257849031396, "step": 3340}, {"loss": 1.4244, "grad_norm": 0.8042104244232178, "learning_rate": 0.0002, "epoch": 4.47561790247161, "step": 3350}, {"loss": 1.365, "grad_norm": 0.8111839890480042, "learning_rate": 0.0002, "epoch": 4.488977955911824, "step": 3360}, {"loss": 1.3537, "grad_norm": 0.7998340129852295, "learning_rate": 0.0002, "epoch": 4.502338009352037, "step": 3370}, {"loss": 1.3812, "grad_norm": 0.7668877243995667, "learning_rate": 0.0002, "epoch": 4.515698062792251, "step": 3380}, {"loss": 1.3972, "grad_norm": 0.7986718416213989, "learning_rate": 0.0002, "epoch": 4.529058116232465, "step": 3390}, {"loss": 1.3582, "grad_norm": 0.6806602478027344, "learning_rate": 0.0002, "epoch": 4.542418169672679, "step": 3400}, {"loss": 1.3942, "grad_norm": 0.8788819909095764, "learning_rate": 0.0002, "epoch": 4.555778223112893, "step": 3410}, {"loss": 1.3379, "grad_norm": 0.7499664425849915, "learning_rate": 0.0002, "epoch": 4.569138276553106, "step": 3420}, {"loss": 1.3823, "grad_norm": 0.7967109084129333, "learning_rate": 0.0002, "epoch": 4.58249832999332, "step": 3430}, {"loss": 1.3531, "grad_norm": 0.759639322757721, "learning_rate": 0.0002, "epoch": 4.595858383433534, "step": 3440}, {"loss": 1.3517, "grad_norm": 0.8327916264533997, "learning_rate": 0.0002, "epoch": 4.609218436873747, "step": 3450}, {"loss": 1.4619, "grad_norm": 0.7400892376899719, "learning_rate": 0.0002, "epoch": 4.622578490313961, "step": 3460}, {"loss": 1.3374, "grad_norm": 0.8116602301597595, "learning_rate": 0.0002, "epoch": 4.635938543754175, "step": 3470}, {"loss": 1.4445, "grad_norm": 0.7604362368583679, "learning_rate": 0.0002, "epoch": 4.649298597194389, "step": 3480}, {"loss": 1.3724, "grad_norm": 0.7397996783256531, "learning_rate": 0.0002, "epoch": 4.662658650634603, "step": 3490}, {"loss": 1.4048, "grad_norm": 0.869293749332428, "learning_rate": 0.0002, "epoch": 4.676018704074816, "step": 3500}, {"loss": 1.3873, "grad_norm": 0.6854358315467834, "learning_rate": 0.0002, "epoch": 4.68937875751503, "step": 3510}, {"loss": 1.3413, "grad_norm": 0.8326661586761475, "learning_rate": 0.0002, "epoch": 4.7027388109552435, "step": 3520}, {"loss": 1.3666, "grad_norm": 0.6887506246566772, "learning_rate": 0.0002, "epoch": 4.716098864395457, "step": 3530}, {"loss": 1.4508, "grad_norm": 3.837689161300659, "learning_rate": 0.0002, "epoch": 4.729458917835672, "step": 3540}, {"loss": 1.3775, "grad_norm": 0.6874563694000244, "learning_rate": 0.0002, "epoch": 4.742818971275885, "step": 3550}, {"loss": 1.3643, "grad_norm": 0.8340407609939575, "learning_rate": 0.0002, "epoch": 4.756179024716099, "step": 3560}, {"loss": 1.3556, "grad_norm": 0.7286418676376343, "learning_rate": 0.0002, "epoch": 4.7695390781563125, "step": 3570}, {"loss": 1.4338, "grad_norm": 0.7239373326301575, "learning_rate": 0.0002, "epoch": 4.782899131596526, "step": 3580}, {"loss": 1.4697, "grad_norm": 0.831310510635376, "learning_rate": 0.0002, "epoch": 4.796259185036741, "step": 3590}, {"loss": 1.4146, "grad_norm": 0.767715573310852, "learning_rate": 0.0002, "epoch": 4.809619238476954, "step": 3600}, {"loss": 1.4199, "grad_norm": 0.9013199210166931, "learning_rate": 0.0002, "epoch": 4.822979291917168, "step": 3610}, {"loss": 1.4513, "grad_norm": 0.7543512582778931, "learning_rate": 0.0002, "epoch": 4.8363393453573815, "step": 3620}, {"loss": 1.4218, "grad_norm": 0.7626057267189026, "learning_rate": 0.0002, "epoch": 4.849699398797595, "step": 3630}, {"loss": 1.4102, "grad_norm": 0.847079336643219, "learning_rate": 0.0002, "epoch": 4.863059452237809, "step": 3640}, {"loss": 1.5014, "grad_norm": 0.8273295760154724, "learning_rate": 0.0002, "epoch": 4.876419505678022, "step": 3650}, {"loss": 1.3806, "grad_norm": 0.7675244808197021, "learning_rate": 0.0002, "epoch": 4.889779559118237, "step": 3660}, {"loss": 1.4894, "grad_norm": 0.9560356736183167, "learning_rate": 0.0002, "epoch": 4.9031396125584505, "step": 3670}, {"loss": 1.4044, "grad_norm": 0.7682451605796814, "learning_rate": 0.0002, "epoch": 4.916499665998664, "step": 3680}, {"loss": 1.342, "grad_norm": 0.8113830089569092, "learning_rate": 0.0002, "epoch": 4.929859719438878, "step": 3690}, {"loss": 1.3559, "grad_norm": 0.7642542719841003, "learning_rate": 0.0002, "epoch": 4.943219772879091, "step": 3700}, {"loss": 1.403, "grad_norm": 0.823863685131073, "learning_rate": 0.0002, "epoch": 4.956579826319305, "step": 3710}, {"loss": 1.464, "grad_norm": 0.8287797570228577, "learning_rate": 0.0002, "epoch": 4.969939879759519, "step": 3720}, {"loss": 1.4139, "grad_norm": 0.778170108795166, "learning_rate": 0.0002, "epoch": 4.983299933199733, "step": 3730}, {"loss": 1.4218, "grad_norm": 0.7464073896408081, "learning_rate": 0.0002, "epoch": 4.996659986639947, "step": 3740}, {"eval_loss": 1.9638569355010986, "eval_runtime": 38.5725, "eval_samples_per_second": 13.351, "eval_steps_per_second": 1.685, "epoch": 4.999331997327989, "step": 3742}, {"loss": 1.225, "grad_norm": 0.8864085078239441, "learning_rate": 0.0002, "epoch": 5.01002004008016, "step": 3750}, {"loss": 1.2056, "grad_norm": 0.9191637635231018, "learning_rate": 0.0002, "epoch": 5.023380093520374, "step": 3760}, {"loss": 1.2453, "grad_norm": 0.749519407749176, "learning_rate": 0.0002, "epoch": 5.036740146960588, "step": 3770}, {"loss": 1.1959, "grad_norm": 0.7916892170906067, "learning_rate": 0.0002, "epoch": 5.050100200400801, "step": 3780}, {"loss": 1.2279, "grad_norm": 1.0318909883499146, "learning_rate": 0.0002, "epoch": 5.063460253841015, "step": 3790}, {"loss": 1.2585, "grad_norm": 1.028586745262146, "learning_rate": 0.0002, "epoch": 5.0768203072812295, "step": 3800}, {"loss": 1.1769, "grad_norm": 1.0568538904190063, "learning_rate": 0.0002, "epoch": 5.090180360721443, "step": 3810}, {"loss": 1.263, "grad_norm": 0.9780595302581787, "learning_rate": 0.0002, "epoch": 5.103540414161657, "step": 3820}, {"loss": 1.2019, "grad_norm": 1.10311758518219, "learning_rate": 0.0002, "epoch": 5.11690046760187, "step": 3830}, {"loss": 1.2133, "grad_norm": 0.9497154355049133, "learning_rate": 0.0002, "epoch": 5.130260521042084, "step": 3840}, {"loss": 1.1718, "grad_norm": 0.948279857635498, "learning_rate": 0.0002, "epoch": 5.143620574482298, "step": 3850}, {"loss": 1.2108, "grad_norm": 0.9497880339622498, "learning_rate": 0.0002, "epoch": 5.156980627922512, "step": 3860}, {"loss": 1.1876, "grad_norm": 1.3213258981704712, "learning_rate": 0.0002, "epoch": 5.170340681362726, "step": 3870}, {"loss": 1.2327, "grad_norm": 0.9835752248764038, "learning_rate": 0.0002, "epoch": 5.183700734802939, "step": 3880}, {"loss": 1.2256, "grad_norm": 0.8426132202148438, "learning_rate": 0.0002, "epoch": 5.197060788243153, "step": 3890}, {"loss": 1.2066, "grad_norm": 1.0343470573425293, "learning_rate": 0.0002, "epoch": 5.210420841683367, "step": 3900}, {"loss": 1.2596, "grad_norm": 1.0771924257278442, "learning_rate": 0.0002, "epoch": 5.22378089512358, "step": 3910}, {"loss": 1.2371, "grad_norm": 0.8542634844779968, "learning_rate": 0.0002, "epoch": 5.237140948563794, "step": 3920}, {"loss": 1.2264, "grad_norm": 1.1021966934204102, "learning_rate": 0.0002, "epoch": 5.250501002004008, "step": 3930}, {"loss": 1.2097, "grad_norm": 1.170011281967163, "learning_rate": 0.0002, "epoch": 5.263861055444222, "step": 3940}, {"loss": 1.2101, "grad_norm": 0.9787653684616089, "learning_rate": 0.0002, "epoch": 5.277221108884436, "step": 3950}, {"loss": 1.24, "grad_norm": 0.914513885974884, "learning_rate": 0.0002, "epoch": 5.290581162324649, "step": 3960}, {"loss": 1.1641, "grad_norm": 1.0831562280654907, "learning_rate": 0.0002, "epoch": 5.303941215764863, "step": 3970}, {"loss": 1.2609, "grad_norm": 0.9810112714767456, "learning_rate": 0.0002, "epoch": 5.3173012692050765, "step": 3980}, {"loss": 1.1825, "grad_norm": 0.9624066948890686, "learning_rate": 0.0002, "epoch": 5.330661322645291, "step": 3990}, {"loss": 1.273, "grad_norm": 1.2296923398971558, "learning_rate": 0.0002, "epoch": 5.344021376085505, "step": 4000}, {"loss": 1.2452, "grad_norm": 1.011299967765808, "learning_rate": 0.0002, "epoch": 5.357381429525718, "step": 4010}, {"loss": 1.2539, "grad_norm": 0.9144132733345032, "learning_rate": 0.0002, "epoch": 5.370741482965932, "step": 4020}, {"loss": 1.2914, "grad_norm": 1.0573601722717285, "learning_rate": 0.0002, "epoch": 5.3841015364061455, "step": 4030}, {"loss": 1.2295, "grad_norm": 1.1667137145996094, "learning_rate": 0.0002, "epoch": 5.397461589846359, "step": 4040}, {"loss": 1.2541, "grad_norm": 1.072070598602295, "learning_rate": 0.0002, "epoch": 5.410821643286573, "step": 4050}, {"loss": 1.2448, "grad_norm": 1.1005792617797852, "learning_rate": 0.0002, "epoch": 5.424181696726787, "step": 4060}, {"loss": 1.2604, "grad_norm": 1.033581018447876, "learning_rate": 0.0002, "epoch": 5.437541750167001, "step": 4070}, {"loss": 1.2552, "grad_norm": 0.9537439942359924, "learning_rate": 0.0002, "epoch": 5.4509018036072145, "step": 4080}, {"loss": 1.2985, "grad_norm": 1.0502177476882935, "learning_rate": 0.0002, "epoch": 5.464261857047428, "step": 4090}, {"loss": 1.2424, "grad_norm": 0.9098296761512756, "learning_rate": 0.0002, "epoch": 5.477621910487642, "step": 4100}, {"loss": 1.2262, "grad_norm": 0.9551953077316284, "learning_rate": 0.0002, "epoch": 5.490981963927855, "step": 4110}, {"loss": 1.2848, "grad_norm": 0.9169427156448364, "learning_rate": 0.0002, "epoch": 5.504342017368069, "step": 4120}, {"loss": 1.2572, "grad_norm": 0.9430235624313354, "learning_rate": 0.0002, "epoch": 5.517702070808284, "step": 4130}, {"loss": 1.2618, "grad_norm": 0.817259669303894, "learning_rate": 0.0002, "epoch": 5.531062124248497, "step": 4140}, {"loss": 1.3012, "grad_norm": 1.124152660369873, "learning_rate": 0.0002, "epoch": 5.544422177688711, "step": 4150}, {"loss": 1.2508, "grad_norm": 0.9250756502151489, "learning_rate": 0.0002, "epoch": 5.557782231128924, "step": 4160}, {"loss": 1.2492, "grad_norm": 0.9582970142364502, "learning_rate": 0.0002, "epoch": 5.571142284569138, "step": 4170}, {"loss": 1.2804, "grad_norm": 1.0078704357147217, "learning_rate": 0.0002, "epoch": 5.584502338009352, "step": 4180}, {"loss": 1.1961, "grad_norm": 0.9585610032081604, "learning_rate": 0.0002, "epoch": 5.597862391449565, "step": 4190}, {"loss": 1.2522, "grad_norm": 1.0150971412658691, "learning_rate": 0.0002, "epoch": 5.61122244488978, "step": 4200}, {"loss": 1.2275, "grad_norm": 0.9943351149559021, "learning_rate": 0.0002, "epoch": 5.6245824983299935, "step": 4210}, {"loss": 1.2928, "grad_norm": 0.8880936503410339, "learning_rate": 0.0002, "epoch": 5.637942551770207, "step": 4220}, {"loss": 1.2323, "grad_norm": 0.9873887896537781, "learning_rate": 0.0002, "epoch": 5.651302605210421, "step": 4230}, {"loss": 1.3391, "grad_norm": 0.9185152649879456, "learning_rate": 0.0002, "epoch": 5.664662658650634, "step": 4240}, {"loss": 1.2511, "grad_norm": 1.0706779956817627, "learning_rate": 0.0002, "epoch": 5.678022712090849, "step": 4250}, {"loss": 1.2737, "grad_norm": 0.9660224914550781, "learning_rate": 0.0002, "epoch": 5.6913827655310625, "step": 4260}, {"loss": 1.2815, "grad_norm": 0.8685019612312317, "learning_rate": 0.0002, "epoch": 5.704742818971276, "step": 4270}, {"loss": 1.1559, "grad_norm": 1.0390565395355225, "learning_rate": 0.0002, "epoch": 5.71810287241149, "step": 4280}, {"loss": 1.3134, "grad_norm": 0.9290478825569153, "learning_rate": 0.0002, "epoch": 5.731462925851703, "step": 4290}, {"loss": 1.2426, "grad_norm": 1.0361281633377075, "learning_rate": 0.0002, "epoch": 5.744822979291917, "step": 4300}, {"loss": 1.2688, "grad_norm": 0.8804615139961243, "learning_rate": 0.0002, "epoch": 5.758183032732131, "step": 4310}, {"loss": 1.2479, "grad_norm": 1.0051425695419312, "learning_rate": 0.0002, "epoch": 5.771543086172345, "step": 4320}, {"loss": 1.1946, "grad_norm": 1.0051119327545166, "learning_rate": 0.0002, "epoch": 5.784903139612559, "step": 4330}, {"loss": 1.2571, "grad_norm": 0.9961661100387573, "learning_rate": 0.0002, "epoch": 5.798263193052772, "step": 4340}, {"loss": 1.2179, "grad_norm": 1.0229419469833374, "learning_rate": 0.0002, "epoch": 5.811623246492986, "step": 4350}, {"loss": 1.2984, "grad_norm": 1.1129552125930786, "learning_rate": 0.0002, "epoch": 5.8249832999332, "step": 4360}, {"loss": 1.2692, "grad_norm": 1.18964421749115, "learning_rate": 0.0002, "epoch": 5.838343353373413, "step": 4370}, {"loss": 1.1996, "grad_norm": 0.9490230083465576, "learning_rate": 0.0002, "epoch": 5.851703406813627, "step": 4380}, {"loss": 1.3177, "grad_norm": 0.8734540343284607, "learning_rate": 0.0002, "epoch": 5.865063460253841, "step": 4390}, {"loss": 1.3131, "grad_norm": 1.0017802715301514, "learning_rate": 0.0002, "epoch": 5.878423513694055, "step": 4400}, {"loss": 1.2649, "grad_norm": 0.953556478023529, "learning_rate": 0.0002, "epoch": 5.891783567134269, "step": 4410}, {"loss": 1.2684, "grad_norm": 0.8915258646011353, "learning_rate": 0.0002, "epoch": 5.905143620574482, "step": 4420}, {"loss": 1.2843, "grad_norm": 0.9715141654014587, "learning_rate": 0.0002, "epoch": 5.918503674014696, "step": 4430}, {"loss": 1.2769, "grad_norm": 0.9432152509689331, "learning_rate": 0.0002, "epoch": 5.9318637274549095, "step": 4440}, {"loss": 1.233, "grad_norm": 0.9473979473114014, "learning_rate": 0.0002, "epoch": 5.945223780895123, "step": 4450}, {"loss": 1.3209, "grad_norm": 1.104871392250061, "learning_rate": 0.0002, "epoch": 5.958583834335338, "step": 4460}, {"loss": 1.3427, "grad_norm": 1.0308905839920044, "learning_rate": 0.0002, "epoch": 5.971943887775551, "step": 4470}, {"loss": 1.1808, "grad_norm": 0.8895487189292908, "learning_rate": 0.0002, "epoch": 5.985303941215765, "step": 4480}, {"loss": 1.2634, "grad_norm": 1.0148485898971558, "learning_rate": 0.0002, "epoch": 5.9986639946559785, "step": 4490}, {"eval_loss": 2.0830726623535156, "eval_runtime": 38.5442, "eval_samples_per_second": 13.361, "eval_steps_per_second": 1.686, "epoch": 6.0, "step": 4491}, {"loss": 1.1106, "grad_norm": 1.1640599966049194, "learning_rate": 0.0002, "epoch": 6.012024048096192, "step": 4500}, {"loss": 1.0436, "grad_norm": 1.213204264640808, "learning_rate": 0.0002, "epoch": 6.025384101536406, "step": 4510}, {"loss": 1.0606, "grad_norm": 1.1694388389587402, "learning_rate": 0.0002, "epoch": 6.03874415497662, "step": 4520}, {"loss": 1.0274, "grad_norm": 1.1044062376022339, "learning_rate": 0.0002, "epoch": 6.052104208416834, "step": 4530}, {"loss": 1.0552, "grad_norm": 1.0701100826263428, "learning_rate": 0.0002, "epoch": 6.065464261857048, "step": 4540}, {"loss": 1.0018, "grad_norm": 1.360065221786499, "learning_rate": 0.0002, "epoch": 6.078824315297261, "step": 4550}, {"loss": 1.0189, "grad_norm": 1.0648503303527832, "learning_rate": 0.0002, "epoch": 6.092184368737475, "step": 4560}, {"loss": 1.008, "grad_norm": 1.066245198249817, "learning_rate": 0.0002, "epoch": 6.1055444221776884, "step": 4570}, {"loss": 1.099, "grad_norm": 1.1483700275421143, "learning_rate": 0.0002, "epoch": 6.118904475617902, "step": 4580}, {"loss": 1.1043, "grad_norm": 1.334275722503662, "learning_rate": 0.0002, "epoch": 6.132264529058117, "step": 4590}, {"loss": 1.0783, "grad_norm": 1.2141029834747314, "learning_rate": 0.0002, "epoch": 6.14562458249833, "step": 4600}, {"loss": 1.0891, "grad_norm": 1.2284387350082397, "learning_rate": 0.0002, "epoch": 6.158984635938544, "step": 4610}, {"loss": 1.122, "grad_norm": 1.2326734066009521, "learning_rate": 0.0002, "epoch": 6.1723446893787575, "step": 4620}, {"loss": 1.1069, "grad_norm": 1.245004653930664, "learning_rate": 0.0002, "epoch": 6.185704742818971, "step": 4630}, {"loss": 1.0821, "grad_norm": 0.9685266017913818, "learning_rate": 0.0002, "epoch": 6.199064796259185, "step": 4640}, {"loss": 1.0659, "grad_norm": 1.141634464263916, "learning_rate": 0.0002, "epoch": 6.212424849699399, "step": 4650}, {"loss": 1.0971, "grad_norm": 1.4279003143310547, "learning_rate": 0.0002, "epoch": 6.225784903139613, "step": 4660}, {"loss": 1.093, "grad_norm": 1.186668872833252, "learning_rate": 0.0002, "epoch": 6.2391449565798265, "step": 4670}, {"loss": 1.0522, "grad_norm": 1.2656606435775757, "learning_rate": 0.0002, "epoch": 6.25250501002004, "step": 4680}, {"loss": 1.1138, "grad_norm": 1.1122987270355225, "learning_rate": 0.0002, "epoch": 6.265865063460254, "step": 4690}, {"loss": 1.0906, "grad_norm": 1.190050482749939, "learning_rate": 0.0002, "epoch": 6.279225116900467, "step": 4700}, {"loss": 1.1095, "grad_norm": 1.3683340549468994, "learning_rate": 0.0002, "epoch": 6.292585170340681, "step": 4710}, {"loss": 1.0663, "grad_norm": 1.1787203550338745, "learning_rate": 0.0002, "epoch": 6.3059452237808955, "step": 4720}, {"loss": 1.0856, "grad_norm": 1.3502576351165771, "learning_rate": 0.0002, "epoch": 6.319305277221109, "step": 4730}, {"loss": 1.0999, "grad_norm": 1.1958597898483276, "learning_rate": 0.0002, "epoch": 6.332665330661323, "step": 4740}, {"loss": 1.021, "grad_norm": 1.0918327569961548, "learning_rate": 0.0002, "epoch": 6.346025384101536, "step": 4750}, {"loss": 1.0484, "grad_norm": 1.2624558210372925, "learning_rate": 0.0002, "epoch": 6.35938543754175, "step": 4760}, {"loss": 1.0785, "grad_norm": 1.1390577554702759, "learning_rate": 0.0002, "epoch": 6.372745490981964, "step": 4770}, {"loss": 1.0979, "grad_norm": 1.041666865348816, "learning_rate": 0.0002, "epoch": 6.386105544422177, "step": 4780}, {"loss": 1.1026, "grad_norm": 1.4209141731262207, "learning_rate": 0.0002, "epoch": 6.399465597862392, "step": 4790}, {"loss": 1.119, "grad_norm": 1.1001079082489014, "learning_rate": 0.0002, "epoch": 6.412825651302605, "step": 4800}, {"loss": 1.1082, "grad_norm": 1.3324936628341675, "learning_rate": 0.0002, "epoch": 6.426185704742819, "step": 4810}, {"loss": 1.0785, "grad_norm": 1.1270194053649902, "learning_rate": 0.0002, "epoch": 6.439545758183033, "step": 4820}, {"loss": 1.1338, "grad_norm": 1.1961387395858765, "learning_rate": 0.0002, "epoch": 6.452905811623246, "step": 4830}, {"loss": 1.0967, "grad_norm": 1.255366563796997, "learning_rate": 0.0002, "epoch": 6.46626586506346, "step": 4840}, {"loss": 1.1226, "grad_norm": 1.343855381011963, "learning_rate": 0.0002, "epoch": 6.479625918503674, "step": 4850}, {"loss": 1.1118, "grad_norm": 1.3216257095336914, "learning_rate": 0.0002, "epoch": 6.492985971943888, "step": 4860}, {"loss": 1.1664, "grad_norm": 1.5244755744934082, "learning_rate": 0.0002, "epoch": 6.506346025384102, "step": 4870}, {"loss": 1.0403, "grad_norm": 1.1585701704025269, "learning_rate": 0.0002, "epoch": 6.519706078824315, "step": 4880}, {"loss": 1.1344, "grad_norm": 1.0301100015640259, "learning_rate": 0.0002, "epoch": 6.533066132264529, "step": 4890}, {"loss": 1.1304, "grad_norm": 1.5772714614868164, "learning_rate": 0.0002, "epoch": 6.5464261857047426, "step": 4900}, {"loss": 1.0953, "grad_norm": 1.2015259265899658, "learning_rate": 0.0002, "epoch": 6.559786239144957, "step": 4910}, {"loss": 1.1283, "grad_norm": 1.4365423917770386, "learning_rate": 0.0002, "epoch": 6.573146292585171, "step": 4920}, {"loss": 1.0717, "grad_norm": 1.2534470558166504, "learning_rate": 0.0002, "epoch": 6.586506346025384, "step": 4930}, {"loss": 1.1099, "grad_norm": 1.216138482093811, "learning_rate": 0.0002, "epoch": 6.599866399465598, "step": 4940}, {"loss": 1.1744, "grad_norm": 1.144316554069519, "learning_rate": 0.0002, "epoch": 6.613226452905812, "step": 4950}, {"loss": 1.0548, "grad_norm": 1.1127740144729614, "learning_rate": 0.0002, "epoch": 6.626586506346025, "step": 4960}, {"loss": 1.0686, "grad_norm": 1.1925606727600098, "learning_rate": 0.0002, "epoch": 6.639946559786239, "step": 4970}, {"loss": 1.0684, "grad_norm": 1.2500451803207397, "learning_rate": 0.0002, "epoch": 6.653306613226453, "step": 4980}, {"loss": 1.1642, "grad_norm": 1.16154944896698, "learning_rate": 0.0002, "epoch": 6.666666666666667, "step": 4990}, {"loss": 1.1003, "grad_norm": 1.1921433210372925, "learning_rate": 0.0002, "epoch": 6.680026720106881, "step": 5000}, {"loss": 1.1278, "grad_norm": 1.1561170816421509, "learning_rate": 0.0002, "epoch": 6.693386773547094, "step": 5010}, {"loss": 1.0766, "grad_norm": 1.2988990545272827, "learning_rate": 0.0002, "epoch": 6.706746826987308, "step": 5020}, {"loss": 1.1131, "grad_norm": 0.9620341062545776, "learning_rate": 0.0002, "epoch": 6.7201068804275215, "step": 5030}, {"loss": 1.109, "grad_norm": 1.084228515625, "learning_rate": 0.0002, "epoch": 6.733466933867735, "step": 5040}, {"loss": 1.1474, "grad_norm": 1.1119431257247925, "learning_rate": 0.0002, "epoch": 6.74682698730795, "step": 5050}, {"loss": 1.179, "grad_norm": 1.1365628242492676, "learning_rate": 0.0002, "epoch": 6.760187040748163, "step": 5060}, {"loss": 1.0988, "grad_norm": 1.0989075899124146, "learning_rate": 0.0002, "epoch": 6.773547094188377, "step": 5070}, {"loss": 1.127, "grad_norm": 1.040647268295288, "learning_rate": 0.0002, "epoch": 6.7869071476285905, "step": 5080}, {"loss": 1.0793, "grad_norm": 1.1083087921142578, "learning_rate": 0.0002, "epoch": 6.800267201068804, "step": 5090}, {"loss": 1.1081, "grad_norm": 1.3434782028198242, "learning_rate": 0.0002, "epoch": 6.813627254509018, "step": 5100}, {"loss": 1.1243, "grad_norm": 1.2493442296981812, "learning_rate": 0.0002, "epoch": 6.826987307949231, "step": 5110}, {"loss": 1.0633, "grad_norm": 1.0672307014465332, "learning_rate": 0.0002, "epoch": 6.840347361389446, "step": 5120}, {"loss": 1.1344, "grad_norm": 1.068350911140442, "learning_rate": 0.0002, "epoch": 6.8537074148296595, "step": 5130}, {"loss": 1.1942, "grad_norm": 1.2880923748016357, "learning_rate": 0.0002, "epoch": 6.867067468269873, "step": 5140}, {"loss": 1.1445, "grad_norm": 1.0895041227340698, "learning_rate": 0.0002, "epoch": 6.880427521710087, "step": 5150}, {"loss": 1.1535, "grad_norm": 1.2383300065994263, "learning_rate": 0.0002, "epoch": 6.8937875751503, "step": 5160}, {"loss": 1.1653, "grad_norm": 1.5274227857589722, "learning_rate": 0.0002, "epoch": 6.907147628590514, "step": 5170}, {"loss": 1.1112, "grad_norm": 1.1453371047973633, "learning_rate": 0.0002, "epoch": 6.920507682030728, "step": 5180}, {"loss": 1.1808, "grad_norm": 1.171336054801941, "learning_rate": 0.0002, "epoch": 6.933867735470942, "step": 5190}, {"loss": 1.1142, "grad_norm": 1.1946955919265747, "learning_rate": 0.0002, "epoch": 6.947227788911156, "step": 5200}, {"loss": 1.1386, "grad_norm": 1.2290117740631104, "learning_rate": 0.0002, "epoch": 6.960587842351369, "step": 5210}, {"loss": 1.1573, "grad_norm": 1.3134533166885376, "learning_rate": 0.0002, "epoch": 6.973947895791583, "step": 5220}, {"loss": 1.1687, "grad_norm": 1.1500377655029297, "learning_rate": 0.0002, "epoch": 6.987307949231797, "step": 5230}]}
+{"epoch": 7.994655978623914, "step": 5984, "epoch_duration": 819.5618627071381, "total_accumulated_duration": 6596.940282344818, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7568.4541015625}, "peak_memory_usage": {"GPU_0": 13792.75439453125}, "avg_memory_reserved": {"GPU_0": 17416.0}, "peak_memory_reserved": {"GPU_0": 17416.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-3514-sd-0/checkpoint-1497", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.6569, "grad_norm": 0.5097216367721558, "learning_rate": 0.0002, "epoch": 0.013360053440213761, "step": 10}, {"loss": 2.2557, "grad_norm": 0.5924790501594543, "learning_rate": 0.0002, "epoch": 0.026720106880427523, "step": 20}, {"loss": 2.0626, "grad_norm": 0.5158102512359619, "learning_rate": 0.0002, "epoch": 0.04008016032064128, "step": 30}, {"loss": 1.9452, "grad_norm": 0.5033753514289856, "learning_rate": 0.0002, "epoch": 0.053440213760855046, "step": 40}, {"loss": 1.9128, "grad_norm": 0.5390949845314026, "learning_rate": 0.0002, "epoch": 0.06680026720106881, "step": 50}, {"loss": 1.937, "grad_norm": 0.6376217007637024, "learning_rate": 0.0002, "epoch": 0.08016032064128256, "step": 60}, {"loss": 1.929, "grad_norm": 0.4202035069465637, "learning_rate": 0.0002, "epoch": 0.09352037408149633, "step": 70}, {"loss": 1.811, "grad_norm": 0.4269474744796753, "learning_rate": 0.0002, "epoch": 0.10688042752171009, "step": 80}, {"loss": 1.8303, "grad_norm": 0.4306574761867523, "learning_rate": 0.0002, "epoch": 0.12024048096192384, "step": 90}, {"loss": 1.8469, "grad_norm": 0.5297011137008667, "learning_rate": 0.0002, "epoch": 0.13360053440213762, "step": 100}, {"loss": 1.864, "grad_norm": 1.2313778400421143, "learning_rate": 0.0002, "epoch": 0.14696058784235136, "step": 110}, {"loss": 1.8531, "grad_norm": 0.5351294279098511, "learning_rate": 0.0002, "epoch": 0.16032064128256512, "step": 120}, {"loss": 1.9232, "grad_norm": 0.4848092496395111, "learning_rate": 0.0002, "epoch": 0.1736806947227789, "step": 130}, {"loss": 1.8633, "grad_norm": 0.4339500665664673, "learning_rate": 0.0002, "epoch": 0.18704074816299265, "step": 140}, {"loss": 1.816, "grad_norm": 0.46877285838127136, "learning_rate": 0.0002, "epoch": 0.20040080160320642, "step": 150}, {"loss": 1.8033, "grad_norm": 0.5600412487983704, "learning_rate": 0.0002, "epoch": 0.21376085504342018, "step": 160}, {"loss": 1.8162, "grad_norm": 0.3733620345592499, "learning_rate": 0.0002, "epoch": 0.22712090848363392, "step": 170}, {"loss": 1.8564, "grad_norm": 0.5116042494773865, "learning_rate": 0.0002, "epoch": 0.24048096192384769, "step": 180}, {"loss": 1.915, "grad_norm": 0.4071602523326874, "learning_rate": 0.0002, "epoch": 0.25384101536406145, "step": 190}, {"loss": 1.7984, "grad_norm": 0.44189608097076416, "learning_rate": 0.0002, "epoch": 0.26720106880427524, "step": 200}, {"loss": 1.8728, "grad_norm": 0.398699015378952, "learning_rate": 0.0002, "epoch": 0.280561122244489, "step": 210}, {"loss": 1.8205, "grad_norm": 0.3585626482963562, "learning_rate": 0.0002, "epoch": 0.2939211756847027, "step": 220}, {"loss": 1.8861, "grad_norm": 0.3811776041984558, "learning_rate": 0.0002, "epoch": 0.3072812291249165, "step": 230}, {"loss": 1.8365, "grad_norm": 0.37261509895324707, "learning_rate": 0.0002, "epoch": 0.32064128256513025, "step": 240}, {"loss": 1.9186, "grad_norm": 0.39762404561042786, "learning_rate": 0.0002, "epoch": 0.33400133600534404, "step": 250}, {"loss": 1.7965, "grad_norm": 0.3509528934955597, "learning_rate": 0.0002, "epoch": 0.3473613894455578, "step": 260}, {"loss": 1.7802, "grad_norm": 0.3169104754924774, "learning_rate": 0.0002, "epoch": 0.36072144288577157, "step": 270}, {"loss": 1.8038, "grad_norm": 0.33714795112609863, "learning_rate": 0.0002, "epoch": 0.3740814963259853, "step": 280}, {"loss": 1.787, "grad_norm": 1.2936875820159912, "learning_rate": 0.0002, "epoch": 0.38744154976619904, "step": 290}, {"loss": 1.7974, "grad_norm": 0.3459427058696747, "learning_rate": 0.0002, "epoch": 0.40080160320641284, "step": 300}, {"loss": 1.8879, "grad_norm": 0.3380655348300934, "learning_rate": 0.0002, "epoch": 0.4141616566466266, "step": 310}, {"loss": 1.9196, "grad_norm": 0.3890381455421448, "learning_rate": 0.0002, "epoch": 0.42752171008684037, "step": 320}, {"loss": 1.8034, "grad_norm": 0.432327002286911, "learning_rate": 0.0002, "epoch": 0.4408817635270541, "step": 330}, {"loss": 1.8443, "grad_norm": 0.3736560046672821, "learning_rate": 0.0002, "epoch": 0.45424181696726784, "step": 340}, {"loss": 1.8506, "grad_norm": 0.3700982630252838, "learning_rate": 0.0002, "epoch": 0.46760187040748163, "step": 350}, {"loss": 1.7978, "grad_norm": 0.4533902406692505, "learning_rate": 0.0002, "epoch": 0.48096192384769537, "step": 360}, {"loss": 1.7427, "grad_norm": 0.35999053716659546, "learning_rate": 0.0002, "epoch": 0.49432197728790916, "step": 370}, {"loss": 1.7995, "grad_norm": 0.3490903675556183, "learning_rate": 0.0002, "epoch": 0.5076820307281229, "step": 380}, {"loss": 1.8709, "grad_norm": 0.34704291820526123, "learning_rate": 0.0002, "epoch": 0.5210420841683366, "step": 390}, {"loss": 1.7948, "grad_norm": 0.343565434217453, "learning_rate": 0.0002, "epoch": 0.5344021376085505, "step": 400}, {"loss": 1.8564, "grad_norm": 0.3573552966117859, "learning_rate": 0.0002, "epoch": 0.5477621910487642, "step": 410}, {"loss": 1.8477, "grad_norm": 0.32980719208717346, "learning_rate": 0.0002, "epoch": 0.561122244488978, "step": 420}, {"loss": 1.9233, "grad_norm": 0.356952428817749, "learning_rate": 0.0002, "epoch": 0.5744822979291917, "step": 430}, {"loss": 1.7433, "grad_norm": 0.3170869052410126, "learning_rate": 0.0002, "epoch": 0.5878423513694054, "step": 440}, {"loss": 1.7607, "grad_norm": 0.35233718156814575, "learning_rate": 0.0002, "epoch": 0.6012024048096193, "step": 450}, {"loss": 1.8111, "grad_norm": 0.3480125367641449, "learning_rate": 0.0002, "epoch": 0.614562458249833, "step": 460}, {"loss": 1.8386, "grad_norm": 0.4762810468673706, "learning_rate": 0.0002, "epoch": 0.6279225116900468, "step": 470}, {"loss": 1.805, "grad_norm": 0.3907663822174072, "learning_rate": 0.0002, "epoch": 0.6412825651302605, "step": 480}, {"loss": 1.8113, "grad_norm": 0.36315613985061646, "learning_rate": 0.0002, "epoch": 0.6546426185704742, "step": 490}, {"loss": 1.7805, "grad_norm": 0.377796471118927, "learning_rate": 0.0002, "epoch": 0.6680026720106881, "step": 500}, {"loss": 1.7457, "grad_norm": 0.34284207224845886, "learning_rate": 0.0002, "epoch": 0.6813627254509018, "step": 510}, {"loss": 1.8013, "grad_norm": 0.35563018918037415, "learning_rate": 0.0002, "epoch": 0.6947227788911156, "step": 520}, {"loss": 1.8414, "grad_norm": 0.37575867772102356, "learning_rate": 0.0002, "epoch": 0.7080828323313293, "step": 530}, {"loss": 1.7993, "grad_norm": 0.35719701647758484, "learning_rate": 0.0002, "epoch": 0.7214428857715431, "step": 540}, {"loss": 1.7574, "grad_norm": 0.385813444852829, "learning_rate": 0.0002, "epoch": 0.7348029392117569, "step": 550}, {"loss": 1.7985, "grad_norm": 0.44509607553482056, "learning_rate": 0.0002, "epoch": 0.7481629926519706, "step": 560}, {"loss": 1.7459, "grad_norm": 0.36108464002609253, "learning_rate": 0.0002, "epoch": 0.7615230460921844, "step": 570}, {"loss": 1.8207, "grad_norm": 0.3530745804309845, "learning_rate": 0.0002, "epoch": 0.7748830995323981, "step": 580}, {"loss": 1.7479, "grad_norm": 0.34888574481010437, "learning_rate": 0.0002, "epoch": 0.7882431529726119, "step": 590}, {"loss": 1.8656, "grad_norm": 0.387346476316452, "learning_rate": 0.0002, "epoch": 0.8016032064128257, "step": 600}, {"loss": 1.8071, "grad_norm": 0.3641138970851898, "learning_rate": 0.0002, "epoch": 0.8149632598530394, "step": 610}, {"loss": 1.7531, "grad_norm": 0.33729103207588196, "learning_rate": 0.0002, "epoch": 0.8283233132932531, "step": 620}, {"loss": 1.8613, "grad_norm": 0.3652004599571228, "learning_rate": 0.0002, "epoch": 0.8416833667334669, "step": 630}, {"loss": 1.9184, "grad_norm": 0.3986643850803375, "learning_rate": 0.0002, "epoch": 0.8550434201736807, "step": 640}, {"loss": 1.8198, "grad_norm": 0.3458964228630066, "learning_rate": 0.0002, "epoch": 0.8684034736138945, "step": 650}, {"loss": 1.803, "grad_norm": 0.3559381365776062, "learning_rate": 0.0002, "epoch": 0.8817635270541082, "step": 660}, {"loss": 1.7641, "grad_norm": 0.3612841069698334, "learning_rate": 0.0002, "epoch": 0.895123580494322, "step": 670}, {"loss": 1.7888, "grad_norm": 0.34771719574928284, "learning_rate": 0.0002, "epoch": 0.9084836339345357, "step": 680}, {"loss": 1.8204, "grad_norm": 0.3371497094631195, "learning_rate": 0.0002, "epoch": 0.9218436873747495, "step": 690}, {"loss": 1.7848, "grad_norm": 0.5596055388450623, "learning_rate": 0.0002, "epoch": 0.9352037408149633, "step": 700}, {"loss": 1.7794, "grad_norm": 0.311880499124527, "learning_rate": 0.0002, "epoch": 0.948563794255177, "step": 710}, {"loss": 1.8464, "grad_norm": 0.3462068736553192, "learning_rate": 0.0002, "epoch": 0.9619238476953907, "step": 720}, {"loss": 1.8197, "grad_norm": 0.29982393980026245, "learning_rate": 0.0002, "epoch": 0.9752839011356046, "step": 730}, {"loss": 1.8503, "grad_norm": 0.34606459736824036, "learning_rate": 0.0002, "epoch": 0.9886439545758183, "step": 740}, {"eval_loss": 1.8201380968093872, "eval_runtime": 38.6124, "eval_samples_per_second": 13.338, "eval_steps_per_second": 1.683, "epoch": 0.9993319973279893, "step": 748}, {"loss": 1.7786, "grad_norm": 0.32302048802375793, "learning_rate": 0.0002, "epoch": 1.002004008016032, "step": 750}, {"loss": 1.7297, "grad_norm": 0.37585633993148804, "learning_rate": 0.0002, "epoch": 1.0153640614562458, "step": 760}, {"loss": 1.7008, "grad_norm": 0.33826273679733276, "learning_rate": 0.0002, "epoch": 1.0287241148964597, "step": 770}, {"loss": 1.809, "grad_norm": 0.44682955741882324, "learning_rate": 0.0002, "epoch": 1.0420841683366733, "step": 780}, {"loss": 1.7092, "grad_norm": 0.422188401222229, "learning_rate": 0.0002, "epoch": 1.0554442217768871, "step": 790}, {"loss": 1.7765, "grad_norm": 0.3809906244277954, "learning_rate": 0.0002, "epoch": 1.0688042752171008, "step": 800}, {"loss": 1.7431, "grad_norm": 0.3454349637031555, "learning_rate": 0.0002, "epoch": 1.0821643286573146, "step": 810}, {"loss": 1.7257, "grad_norm": 0.3767355978488922, "learning_rate": 0.0002, "epoch": 1.0955243820975284, "step": 820}, {"loss": 1.7224, "grad_norm": 0.3361407518386841, "learning_rate": 0.0002, "epoch": 1.108884435537742, "step": 830}, {"loss": 1.7509, "grad_norm": 0.3654632568359375, "learning_rate": 0.0002, "epoch": 1.122244488977956, "step": 840}, {"loss": 1.7151, "grad_norm": 0.3822861313819885, "learning_rate": 0.0002, "epoch": 1.1356045424181698, "step": 850}, {"loss": 1.7121, "grad_norm": 0.3853831887245178, "learning_rate": 0.0002, "epoch": 1.1489645958583834, "step": 860}, {"loss": 1.7685, "grad_norm": 0.35521796345710754, "learning_rate": 0.0002, "epoch": 1.1623246492985972, "step": 870}, {"loss": 1.7735, "grad_norm": 0.4107200503349304, "learning_rate": 0.0002, "epoch": 1.1756847027388109, "step": 880}, {"loss": 1.7484, "grad_norm": 0.33219534158706665, "learning_rate": 0.0002, "epoch": 1.1890447561790247, "step": 890}, {"loss": 1.7071, "grad_norm": 0.3559704124927521, "learning_rate": 0.0002, "epoch": 1.2024048096192386, "step": 900}, {"loss": 1.7535, "grad_norm": 0.3700537383556366, "learning_rate": 0.0002, "epoch": 1.2157648630594522, "step": 910}, {"loss": 1.7513, "grad_norm": 0.3771909475326538, "learning_rate": 0.0002, "epoch": 1.229124916499666, "step": 920}, {"loss": 1.7566, "grad_norm": 0.3136613965034485, "learning_rate": 0.0002, "epoch": 1.2424849699398797, "step": 930}, {"loss": 1.6783, "grad_norm": 0.3952099084854126, "learning_rate": 0.0002, "epoch": 1.2558450233800935, "step": 940}, {"loss": 1.7691, "grad_norm": 0.36534377932548523, "learning_rate": 0.0002, "epoch": 1.2692050768203074, "step": 950}, {"loss": 1.7127, "grad_norm": 0.3803492486476898, "learning_rate": 0.0002, "epoch": 1.282565130260521, "step": 960}, {"loss": 1.7896, "grad_norm": 0.3992428183555603, "learning_rate": 0.0002, "epoch": 1.2959251837007348, "step": 970}, {"loss": 1.7343, "grad_norm": 0.3627142906188965, "learning_rate": 0.0002, "epoch": 1.3092852371409487, "step": 980}, {"loss": 1.7598, "grad_norm": 0.4248180091381073, "learning_rate": 0.0002, "epoch": 1.3226452905811623, "step": 990}, {"loss": 1.6896, "grad_norm": 0.4060308039188385, "learning_rate": 0.0002, "epoch": 1.3360053440213762, "step": 1000}, {"loss": 1.7457, "grad_norm": 0.3788969814777374, "learning_rate": 0.0002, "epoch": 1.3493653974615898, "step": 1010}, {"loss": 1.7111, "grad_norm": 0.4174270033836365, "learning_rate": 0.0002, "epoch": 1.3627254509018036, "step": 1020}, {"loss": 1.7975, "grad_norm": 0.35500675439834595, "learning_rate": 0.0002, "epoch": 1.3760855043420173, "step": 1030}, {"loss": 1.724, "grad_norm": 0.3454059362411499, "learning_rate": 0.0002, "epoch": 1.389445557782231, "step": 1040}, {"loss": 1.8299, "grad_norm": 0.45807570219039917, "learning_rate": 0.0002, "epoch": 1.402805611222445, "step": 1050}, {"loss": 1.7425, "grad_norm": 0.39338022470474243, "learning_rate": 0.0002, "epoch": 1.4161656646626586, "step": 1060}, {"loss": 1.7457, "grad_norm": 0.3870709240436554, "learning_rate": 0.0002, "epoch": 1.4295257181028724, "step": 1070}, {"loss": 1.6565, "grad_norm": 0.40996190905570984, "learning_rate": 0.0002, "epoch": 1.4428857715430863, "step": 1080}, {"loss": 1.7324, "grad_norm": 0.38762837648391724, "learning_rate": 0.0002, "epoch": 1.4562458249833, "step": 1090}, {"loss": 1.7362, "grad_norm": 0.36756977438926697, "learning_rate": 0.0002, "epoch": 1.4696058784235138, "step": 1100}, {"loss": 1.7451, "grad_norm": 0.4087235927581787, "learning_rate": 0.0002, "epoch": 1.4829659318637274, "step": 1110}, {"loss": 1.7114, "grad_norm": 0.3357745110988617, "learning_rate": 0.0002, "epoch": 1.4963259853039412, "step": 1120}, {"loss": 1.6877, "grad_norm": 0.37486532330513, "learning_rate": 0.0002, "epoch": 1.5096860387441549, "step": 1130}, {"loss": 1.7252, "grad_norm": 0.3387809991836548, "learning_rate": 0.0002, "epoch": 1.5230460921843687, "step": 1140}, {"loss": 1.7169, "grad_norm": 0.37462118268013, "learning_rate": 0.0002, "epoch": 1.5364061456245826, "step": 1150}, {"loss": 1.6988, "grad_norm": 0.38575324416160583, "learning_rate": 0.0002, "epoch": 1.5497661990647962, "step": 1160}, {"loss": 1.7438, "grad_norm": 0.3515765964984894, "learning_rate": 0.0002, "epoch": 1.56312625250501, "step": 1170}, {"loss": 1.7524, "grad_norm": 0.39308643341064453, "learning_rate": 0.0002, "epoch": 1.5764863059452239, "step": 1180}, {"loss": 1.6422, "grad_norm": 0.3308864235877991, "learning_rate": 0.0002, "epoch": 1.5898463593854375, "step": 1190}, {"loss": 1.7566, "grad_norm": 0.3397478461265564, "learning_rate": 0.0002, "epoch": 1.6032064128256514, "step": 1200}, {"loss": 1.7871, "grad_norm": 0.3911525309085846, "learning_rate": 0.0002, "epoch": 1.6165664662658652, "step": 1210}, {"loss": 1.7443, "grad_norm": 0.3771969974040985, "learning_rate": 0.0002, "epoch": 1.6299265197060788, "step": 1220}, {"loss": 1.7631, "grad_norm": 0.35346856713294983, "learning_rate": 0.0002, "epoch": 1.6432865731462925, "step": 1230}, {"loss": 1.7225, "grad_norm": 0.41736963391304016, "learning_rate": 0.0002, "epoch": 1.6566466265865063, "step": 1240}, {"loss": 1.7582, "grad_norm": 0.3375225067138672, "learning_rate": 0.0002, "epoch": 1.6700066800267201, "step": 1250}, {"loss": 1.6916, "grad_norm": 0.3779928982257843, "learning_rate": 0.0002, "epoch": 1.6833667334669338, "step": 1260}, {"loss": 1.728, "grad_norm": 0.35388994216918945, "learning_rate": 0.0002, "epoch": 1.6967267869071476, "step": 1270}, {"loss": 1.7461, "grad_norm": 0.33884134888648987, "learning_rate": 0.0002, "epoch": 1.7100868403473615, "step": 1280}, {"loss": 1.7083, "grad_norm": 0.35439756512641907, "learning_rate": 0.0002, "epoch": 1.723446893787575, "step": 1290}, {"loss": 1.7389, "grad_norm": 0.3766156733036041, "learning_rate": 0.0002, "epoch": 1.736806947227789, "step": 1300}, {"loss": 1.7847, "grad_norm": 0.36148911714553833, "learning_rate": 0.0002, "epoch": 1.7501670006680028, "step": 1310}, {"loss": 1.7344, "grad_norm": 0.39687496423721313, "learning_rate": 0.0002, "epoch": 1.7635270541082164, "step": 1320}, {"loss": 1.7541, "grad_norm": 0.35639452934265137, "learning_rate": 0.0002, "epoch": 1.77688710754843, "step": 1330}, {"loss": 1.7254, "grad_norm": 0.38781628012657166, "learning_rate": 0.0002, "epoch": 1.7902471609886441, "step": 1340}, {"loss": 1.7867, "grad_norm": 0.42784637212753296, "learning_rate": 0.0002, "epoch": 1.8036072144288577, "step": 1350}, {"loss": 1.7336, "grad_norm": 0.40258511900901794, "learning_rate": 0.0002, "epoch": 1.8169672678690714, "step": 1360}, {"loss": 1.7771, "grad_norm": 0.36674195528030396, "learning_rate": 0.0002, "epoch": 1.8303273213092852, "step": 1370}, {"loss": 1.7425, "grad_norm": 0.4064558446407318, "learning_rate": 0.0002, "epoch": 1.843687374749499, "step": 1380}, {"loss": 1.7425, "grad_norm": 0.3669849932193756, "learning_rate": 0.0002, "epoch": 1.8570474281897127, "step": 1390}, {"loss": 1.7924, "grad_norm": 0.37569567561149597, "learning_rate": 0.0002, "epoch": 1.8704074816299265, "step": 1400}, {"loss": 1.7885, "grad_norm": 0.37307995557785034, "learning_rate": 0.0002, "epoch": 1.8837675350701404, "step": 1410}, {"loss": 1.7548, "grad_norm": 0.3772695064544678, "learning_rate": 0.0002, "epoch": 1.897127588510354, "step": 1420}, {"loss": 1.7682, "grad_norm": 0.36993589997291565, "learning_rate": 0.0002, "epoch": 1.9104876419505676, "step": 1430}, {"loss": 1.7249, "grad_norm": 0.3490557372570038, "learning_rate": 0.0002, "epoch": 1.9238476953907817, "step": 1440}, {"loss": 1.7979, "grad_norm": 0.3716149628162384, "learning_rate": 0.0002, "epoch": 1.9372077488309953, "step": 1450}, {"loss": 1.6664, "grad_norm": 0.39236098527908325, "learning_rate": 0.0002, "epoch": 1.950567802271209, "step": 1460}, {"loss": 1.6852, "grad_norm": 0.37258651852607727, "learning_rate": 0.0002, "epoch": 1.9639278557114228, "step": 1470}, {"loss": 1.7427, "grad_norm": 0.36183077096939087, "learning_rate": 0.0002, "epoch": 1.9772879091516367, "step": 1480}, {"loss": 1.7055, "grad_norm": 0.3956947326660156, "learning_rate": 0.0002, "epoch": 1.9906479625918503, "step": 1490}, {"eval_loss": 1.8132041692733765, "eval_runtime": 38.6287, "eval_samples_per_second": 13.332, "eval_steps_per_second": 1.683, "epoch": 2.0, "step": 1497}, {"loss": 1.6791, "grad_norm": 0.34480565786361694, "learning_rate": 0.0002, "epoch": 2.004008016032064, "step": 1500}, {"loss": 1.6367, "grad_norm": 0.3418028652667999, "learning_rate": 0.0002, "epoch": 2.017368069472278, "step": 1510}, {"loss": 1.5827, "grad_norm": 0.4514467716217041, "learning_rate": 0.0002, "epoch": 2.0307281229124916, "step": 1520}, {"loss": 1.6365, "grad_norm": 0.4197506606578827, "learning_rate": 0.0002, "epoch": 2.0440881763527052, "step": 1530}, {"loss": 1.6221, "grad_norm": 0.4134170711040497, "learning_rate": 0.0002, "epoch": 2.0574482297929193, "step": 1540}, {"loss": 1.6876, "grad_norm": 0.43709826469421387, "learning_rate": 0.0002, "epoch": 2.070808283233133, "step": 1550}, {"loss": 1.5779, "grad_norm": 0.4703378677368164, "learning_rate": 0.0002, "epoch": 2.0841683366733466, "step": 1560}, {"loss": 1.599, "grad_norm": 0.4538188576698303, "learning_rate": 0.0002, "epoch": 2.0975283901135606, "step": 1570}, {"loss": 1.6464, "grad_norm": 0.4649668037891388, "learning_rate": 0.0002, "epoch": 2.1108884435537743, "step": 1580}, {"loss": 1.6348, "grad_norm": 0.42669883370399475, "learning_rate": 0.0002, "epoch": 2.124248496993988, "step": 1590}, {"loss": 1.5838, "grad_norm": 0.43162038922309875, "learning_rate": 0.0002, "epoch": 2.1376085504342015, "step": 1600}, {"loss": 1.6673, "grad_norm": 0.4294586479663849, "learning_rate": 0.0002, "epoch": 2.1509686038744156, "step": 1610}, {"loss": 1.6024, "grad_norm": 0.4669102132320404, "learning_rate": 0.0002, "epoch": 2.164328657314629, "step": 1620}, {"loss": 1.659, "grad_norm": 0.4188412129878998, "learning_rate": 0.0002, "epoch": 2.177688710754843, "step": 1630}, {"loss": 1.625, "grad_norm": 0.4662680923938751, "learning_rate": 0.0002, "epoch": 2.191048764195057, "step": 1640}, {"loss": 1.6699, "grad_norm": 0.4020286500453949, "learning_rate": 0.0002, "epoch": 2.2044088176352705, "step": 1650}, {"loss": 1.6284, "grad_norm": 0.41919606924057007, "learning_rate": 0.0002, "epoch": 2.217768871075484, "step": 1660}, {"loss": 1.6776, "grad_norm": 0.4644531309604645, "learning_rate": 0.0002, "epoch": 2.231128924515698, "step": 1670}, {"loss": 1.6711, "grad_norm": 0.4526427984237671, "learning_rate": 0.0002, "epoch": 2.244488977955912, "step": 1680}, {"loss": 1.6058, "grad_norm": 0.45953166484832764, "learning_rate": 0.0002, "epoch": 2.2578490313961255, "step": 1690}, {"loss": 1.5979, "grad_norm": 0.4701860249042511, "learning_rate": 0.0002, "epoch": 2.2712090848363395, "step": 1700}, {"loss": 1.6183, "grad_norm": 0.4749310612678528, "learning_rate": 0.0002, "epoch": 2.284569138276553, "step": 1710}, {"loss": 1.6703, "grad_norm": 0.45026102662086487, "learning_rate": 0.0002, "epoch": 2.297929191716767, "step": 1720}, {"loss": 1.6386, "grad_norm": 0.4755004048347473, "learning_rate": 0.0002, "epoch": 2.3112892451569804, "step": 1730}, {"loss": 1.6365, "grad_norm": 0.4505726993083954, "learning_rate": 0.0002, "epoch": 2.3246492985971945, "step": 1740}, {"loss": 1.589, "grad_norm": 0.44464054703712463, "learning_rate": 0.0002, "epoch": 2.338009352037408, "step": 1750}, {"loss": 1.6139, "grad_norm": 0.4449476897716522, "learning_rate": 0.0002, "epoch": 2.3513694054776217, "step": 1760}, {"loss": 1.7195, "grad_norm": 0.4216482937335968, "learning_rate": 0.0002, "epoch": 2.364729458917836, "step": 1770}, {"loss": 1.7075, "grad_norm": 0.4379308521747589, "learning_rate": 0.0002, "epoch": 2.3780895123580494, "step": 1780}, {"loss": 1.7024, "grad_norm": 0.41670042276382446, "learning_rate": 0.0002, "epoch": 2.391449565798263, "step": 1790}, {"loss": 1.5989, "grad_norm": 0.48089510202407837, "learning_rate": 0.0002, "epoch": 2.404809619238477, "step": 1800}, {"loss": 1.6313, "grad_norm": 0.4389738142490387, "learning_rate": 0.0002, "epoch": 2.4181696726786908, "step": 1810}, {"loss": 1.5841, "grad_norm": 0.45293036103248596, "learning_rate": 0.0002, "epoch": 2.4315297261189044, "step": 1820}, {"loss": 1.6887, "grad_norm": 0.5211683511734009, "learning_rate": 0.0002, "epoch": 2.4448897795591185, "step": 1830}, {"loss": 1.6599, "grad_norm": 0.4631884694099426, "learning_rate": 0.0002, "epoch": 2.458249832999332, "step": 1840}, {"loss": 1.6537, "grad_norm": 0.4276818335056305, "learning_rate": 0.0002, "epoch": 2.4716098864395457, "step": 1850}, {"loss": 1.6836, "grad_norm": 0.477524071931839, "learning_rate": 0.0002, "epoch": 2.4849699398797593, "step": 1860}, {"loss": 1.66, "grad_norm": 0.44860973954200745, "learning_rate": 0.0002, "epoch": 2.4983299933199734, "step": 1870}, {"loss": 1.6308, "grad_norm": 0.46413546800613403, "learning_rate": 0.0002, "epoch": 2.511690046760187, "step": 1880}, {"loss": 1.6225, "grad_norm": 0.42487645149230957, "learning_rate": 0.0002, "epoch": 2.5250501002004007, "step": 1890}, {"loss": 1.6268, "grad_norm": 0.4778307378292084, "learning_rate": 0.0002, "epoch": 2.5384101536406147, "step": 1900}, {"loss": 1.6143, "grad_norm": 0.45307061076164246, "learning_rate": 0.0002, "epoch": 2.5517702070808284, "step": 1910}, {"loss": 1.7279, "grad_norm": 0.47886642813682556, "learning_rate": 0.0002, "epoch": 2.565130260521042, "step": 1920}, {"loss": 1.5931, "grad_norm": 0.4839435815811157, "learning_rate": 0.0002, "epoch": 2.5784903139612556, "step": 1930}, {"loss": 1.6089, "grad_norm": 0.4388359785079956, "learning_rate": 0.0002, "epoch": 2.5918503674014697, "step": 1940}, {"loss": 1.6828, "grad_norm": 0.47859734296798706, "learning_rate": 0.0002, "epoch": 2.6052104208416833, "step": 1950}, {"loss": 1.6014, "grad_norm": 0.5526517033576965, "learning_rate": 0.0002, "epoch": 2.6185704742818974, "step": 1960}, {"loss": 1.6889, "grad_norm": 0.5449170470237732, "learning_rate": 0.0002, "epoch": 2.631930527722111, "step": 1970}, {"loss": 1.6481, "grad_norm": 0.48521968722343445, "learning_rate": 0.0002, "epoch": 2.6452905811623246, "step": 1980}, {"loss": 1.6741, "grad_norm": 0.4733737111091614, "learning_rate": 0.0002, "epoch": 2.6586506346025383, "step": 1990}, {"loss": 1.662, "grad_norm": 0.507118284702301, "learning_rate": 0.0002, "epoch": 2.6720106880427523, "step": 2000}, {"loss": 1.6419, "grad_norm": 0.4508971571922302, "learning_rate": 0.0002, "epoch": 2.685370741482966, "step": 2010}, {"loss": 1.7052, "grad_norm": 0.4657728672027588, "learning_rate": 0.0002, "epoch": 2.6987307949231796, "step": 2020}, {"loss": 1.6261, "grad_norm": 0.48647549748420715, "learning_rate": 0.0002, "epoch": 2.7120908483633936, "step": 2030}, {"loss": 1.5638, "grad_norm": 0.49525555968284607, "learning_rate": 0.0002, "epoch": 2.7254509018036073, "step": 2040}, {"loss": 1.658, "grad_norm": 0.4712379276752472, "learning_rate": 0.0002, "epoch": 2.738810955243821, "step": 2050}, {"loss": 1.6464, "grad_norm": 0.4846591055393219, "learning_rate": 0.0002, "epoch": 2.7521710086840345, "step": 2060}, {"loss": 1.5641, "grad_norm": 0.4823240041732788, "learning_rate": 0.0002, "epoch": 2.7655310621242486, "step": 2070}, {"loss": 1.6701, "grad_norm": 0.4546685516834259, "learning_rate": 0.0002, "epoch": 2.778891115564462, "step": 2080}, {"loss": 1.7015, "grad_norm": 0.45542681217193604, "learning_rate": 0.0002, "epoch": 2.7922511690046763, "step": 2090}, {"loss": 1.6398, "grad_norm": 0.42137566208839417, "learning_rate": 0.0002, "epoch": 2.80561122244489, "step": 2100}, {"loss": 1.6526, "grad_norm": 0.6143282055854797, "learning_rate": 0.0002, "epoch": 2.8189712758851035, "step": 2110}, {"loss": 1.6955, "grad_norm": 0.4828081727027893, "learning_rate": 0.0002, "epoch": 2.832331329325317, "step": 2120}, {"loss": 1.744, "grad_norm": 0.4319005608558655, "learning_rate": 0.0002, "epoch": 2.845691382765531, "step": 2130}, {"loss": 1.6717, "grad_norm": 0.4297086298465729, "learning_rate": 0.0002, "epoch": 2.859051436205745, "step": 2140}, {"loss": 1.5968, "grad_norm": 0.5011981129646301, "learning_rate": 0.0002, "epoch": 2.8724114896459585, "step": 2150}, {"loss": 1.7181, "grad_norm": 0.4401548504829407, "learning_rate": 0.0002, "epoch": 2.8857715430861726, "step": 2160}, {"loss": 1.5722, "grad_norm": 0.48090746998786926, "learning_rate": 0.0002, "epoch": 2.899131596526386, "step": 2170}, {"loss": 1.6596, "grad_norm": 0.4740385413169861, "learning_rate": 0.0002, "epoch": 2.9124916499666, "step": 2180}, {"loss": 1.6501, "grad_norm": 0.5337260365486145, "learning_rate": 0.0002, "epoch": 2.9258517034068134, "step": 2190}, {"loss": 1.6802, "grad_norm": 0.4420052766799927, "learning_rate": 0.0002, "epoch": 2.9392117568470275, "step": 2200}, {"loss": 1.5474, "grad_norm": 0.477512389421463, "learning_rate": 0.0002, "epoch": 2.952571810287241, "step": 2210}, {"loss": 1.6544, "grad_norm": 0.5344052910804749, "learning_rate": 0.0002, "epoch": 2.9659318637274548, "step": 2220}, {"loss": 1.6866, "grad_norm": 0.4483940303325653, "learning_rate": 0.0002, "epoch": 2.979291917167669, "step": 2230}, {"loss": 1.6477, "grad_norm": 0.4366597831249237, "learning_rate": 0.0002, "epoch": 2.9926519706078825, "step": 2240}, {"eval_loss": 1.834012746810913, "eval_runtime": 38.5659, "eval_samples_per_second": 13.354, "eval_steps_per_second": 1.685, "epoch": 2.9993319973279893, "step": 2245}, {"loss": 1.5582, "grad_norm": 0.428824245929718, "learning_rate": 0.0002, "epoch": 3.006012024048096, "step": 2250}, {"loss": 1.499, "grad_norm": 0.4870174825191498, "learning_rate": 0.0002, "epoch": 3.01937207748831, "step": 2260}, {"loss": 1.4872, "grad_norm": 0.4684266149997711, "learning_rate": 0.0002, "epoch": 3.032732130928524, "step": 2270}, {"loss": 1.5284, "grad_norm": 0.581604540348053, "learning_rate": 0.0002, "epoch": 3.0460921843687374, "step": 2280}, {"loss": 1.4549, "grad_norm": 0.5561677813529968, "learning_rate": 0.0002, "epoch": 3.059452237808951, "step": 2290}, {"loss": 1.4903, "grad_norm": 0.5750220417976379, "learning_rate": 0.0002, "epoch": 3.072812291249165, "step": 2300}, {"loss": 1.5903, "grad_norm": 0.5704626441001892, "learning_rate": 0.0002, "epoch": 3.0861723446893787, "step": 2310}, {"loss": 1.4292, "grad_norm": 0.6242083311080933, "learning_rate": 0.0002, "epoch": 3.0995323981295924, "step": 2320}, {"loss": 1.5092, "grad_norm": 0.5174121260643005, "learning_rate": 0.0002, "epoch": 3.1128924515698064, "step": 2330}, {"loss": 1.5106, "grad_norm": 0.5697633028030396, "learning_rate": 0.0002, "epoch": 3.12625250501002, "step": 2340}, {"loss": 1.5156, "grad_norm": 0.5969541072845459, "learning_rate": 0.0002, "epoch": 3.1396125584502337, "step": 2350}, {"loss": 1.52, "grad_norm": 0.6244304180145264, "learning_rate": 0.0002, "epoch": 3.1529726118904478, "step": 2360}, {"loss": 1.5244, "grad_norm": 0.5561705827713013, "learning_rate": 0.0002, "epoch": 3.1663326653306614, "step": 2370}, {"loss": 1.6169, "grad_norm": 0.5401188135147095, "learning_rate": 0.0002, "epoch": 3.179692718770875, "step": 2380}, {"loss": 1.5387, "grad_norm": 0.6450421810150146, "learning_rate": 0.0002, "epoch": 3.1930527722110886, "step": 2390}, {"loss": 1.4839, "grad_norm": 0.5741903185844421, "learning_rate": 0.0002, "epoch": 3.2064128256513027, "step": 2400}, {"loss": 1.5584, "grad_norm": 0.6337407231330872, "learning_rate": 0.0002, "epoch": 3.2197728790915163, "step": 2410}, {"loss": 1.5025, "grad_norm": 0.6493517160415649, "learning_rate": 0.0002, "epoch": 3.23313293253173, "step": 2420}, {"loss": 1.5168, "grad_norm": 0.6230176091194153, "learning_rate": 0.0002, "epoch": 3.246492985971944, "step": 2430}, {"loss": 1.5408, "grad_norm": 0.680704653263092, "learning_rate": 0.0002, "epoch": 3.2598530394121576, "step": 2440}, {"loss": 1.6005, "grad_norm": 0.5279417037963867, "learning_rate": 0.0002, "epoch": 3.2732130928523713, "step": 2450}, {"loss": 1.5231, "grad_norm": 0.5601515173912048, "learning_rate": 0.0002, "epoch": 3.2865731462925853, "step": 2460}, {"loss": 1.4949, "grad_norm": 0.5591090321540833, "learning_rate": 0.0002, "epoch": 3.299933199732799, "step": 2470}, {"loss": 1.5181, "grad_norm": 0.6596529483795166, "learning_rate": 0.0002, "epoch": 3.3132932531730126, "step": 2480}, {"loss": 1.5259, "grad_norm": 0.6115918755531311, "learning_rate": 0.0002, "epoch": 3.3266533066132267, "step": 2490}, {"loss": 1.5344, "grad_norm": 0.6443548202514648, "learning_rate": 0.0002, "epoch": 3.3400133600534403, "step": 2500}, {"loss": 1.5037, "grad_norm": 0.5504242181777954, "learning_rate": 0.0002, "epoch": 3.353373413493654, "step": 2510}, {"loss": 1.5049, "grad_norm": 0.6104483604431152, "learning_rate": 0.0002, "epoch": 3.3667334669338675, "step": 2520}, {"loss": 1.587, "grad_norm": 0.8387531638145447, "learning_rate": 0.0002, "epoch": 3.3800935203740816, "step": 2530}, {"loss": 1.5227, "grad_norm": 0.6346094012260437, "learning_rate": 0.0002, "epoch": 3.3934535738142952, "step": 2540}, {"loss": 1.4855, "grad_norm": 0.6261265873908997, "learning_rate": 0.0002, "epoch": 3.406813627254509, "step": 2550}, {"loss": 1.5233, "grad_norm": 0.5960372090339661, "learning_rate": 0.0002, "epoch": 3.420173680694723, "step": 2560}, {"loss": 1.5153, "grad_norm": 0.5291280746459961, "learning_rate": 0.0002, "epoch": 3.4335337341349366, "step": 2570}, {"loss": 1.5152, "grad_norm": 0.6133161783218384, "learning_rate": 0.0002, "epoch": 3.44689378757515, "step": 2580}, {"loss": 1.5533, "grad_norm": 0.623573362827301, "learning_rate": 0.0002, "epoch": 3.460253841015364, "step": 2590}, {"loss": 1.4935, "grad_norm": 0.5959834456443787, "learning_rate": 0.0002, "epoch": 3.473613894455578, "step": 2600}, {"loss": 1.5792, "grad_norm": 0.583332359790802, "learning_rate": 0.0002, "epoch": 3.4869739478957915, "step": 2610}, {"loss": 1.5229, "grad_norm": 0.6003559231758118, "learning_rate": 0.0002, "epoch": 3.5003340013360056, "step": 2620}, {"loss": 1.4901, "grad_norm": 0.5832992196083069, "learning_rate": 0.0002, "epoch": 3.513694054776219, "step": 2630}, {"loss": 1.5005, "grad_norm": 0.5942609906196594, "learning_rate": 0.0002, "epoch": 3.527054108216433, "step": 2640}, {"loss": 1.5213, "grad_norm": 0.6087163686752319, "learning_rate": 0.0002, "epoch": 3.5404141616566465, "step": 2650}, {"loss": 1.5826, "grad_norm": 0.631948709487915, "learning_rate": 0.0002, "epoch": 3.5537742150968605, "step": 2660}, {"loss": 1.5844, "grad_norm": 0.6450803279876709, "learning_rate": 0.0002, "epoch": 3.567134268537074, "step": 2670}, {"loss": 1.4981, "grad_norm": 0.6507797837257385, "learning_rate": 0.0002, "epoch": 3.580494321977288, "step": 2680}, {"loss": 1.5826, "grad_norm": 0.5778017044067383, "learning_rate": 0.0002, "epoch": 3.593854375417502, "step": 2690}, {"loss": 1.4688, "grad_norm": 0.6214032173156738, "learning_rate": 0.0002, "epoch": 3.6072144288577155, "step": 2700}, {"loss": 1.5084, "grad_norm": 0.5681133270263672, "learning_rate": 0.0002, "epoch": 3.620574482297929, "step": 2710}, {"loss": 1.471, "grad_norm": 0.6074244976043701, "learning_rate": 0.0002, "epoch": 3.6339345357381427, "step": 2720}, {"loss": 1.5243, "grad_norm": 0.5900560617446899, "learning_rate": 0.0002, "epoch": 3.647294589178357, "step": 2730}, {"loss": 1.5074, "grad_norm": 0.5817505717277527, "learning_rate": 0.0002, "epoch": 3.6606546426185704, "step": 2740}, {"loss": 1.5117, "grad_norm": 0.6095547676086426, "learning_rate": 0.0002, "epoch": 3.6740146960587845, "step": 2750}, {"loss": 1.5117, "grad_norm": 0.612790584564209, "learning_rate": 0.0002, "epoch": 3.687374749498998, "step": 2760}, {"loss": 1.4976, "grad_norm": 0.6574140787124634, "learning_rate": 0.0002, "epoch": 3.7007348029392118, "step": 2770}, {"loss": 1.5306, "grad_norm": 0.5643761157989502, "learning_rate": 0.0002, "epoch": 3.7140948563794254, "step": 2780}, {"loss": 1.5751, "grad_norm": 0.5652621388435364, "learning_rate": 0.0002, "epoch": 3.727454909819639, "step": 2790}, {"loss": 1.5262, "grad_norm": 0.5604206323623657, "learning_rate": 0.0002, "epoch": 3.740814963259853, "step": 2800}, {"loss": 1.5013, "grad_norm": 3.911022663116455, "learning_rate": 0.0002, "epoch": 3.7541750167000667, "step": 2810}, {"loss": 1.5793, "grad_norm": 0.6148333549499512, "learning_rate": 0.0002, "epoch": 3.7675350701402808, "step": 2820}, {"loss": 1.5122, "grad_norm": 0.5605677962303162, "learning_rate": 0.0002, "epoch": 3.7808951235804944, "step": 2830}, {"loss": 1.5659, "grad_norm": 0.6101965308189392, "learning_rate": 0.0002, "epoch": 3.794255177020708, "step": 2840}, {"loss": 1.5618, "grad_norm": 0.5387342572212219, "learning_rate": 0.0002, "epoch": 3.8076152304609217, "step": 2850}, {"loss": 1.5193, "grad_norm": 0.5733087062835693, "learning_rate": 0.0002, "epoch": 3.8209752839011357, "step": 2860}, {"loss": 1.5545, "grad_norm": 0.6538485884666443, "learning_rate": 0.0002, "epoch": 3.8343353373413493, "step": 2870}, {"loss": 1.523, "grad_norm": 0.6247632503509521, "learning_rate": 0.0002, "epoch": 3.847695390781563, "step": 2880}, {"loss": 1.5591, "grad_norm": 0.5745735764503479, "learning_rate": 0.0002, "epoch": 3.861055444221777, "step": 2890}, {"loss": 1.5706, "grad_norm": 0.5942763686180115, "learning_rate": 0.0002, "epoch": 3.8744154976619907, "step": 2900}, {"loss": 1.564, "grad_norm": 0.7086281776428223, "learning_rate": 0.0002, "epoch": 3.8877755511022043, "step": 2910}, {"loss": 1.5526, "grad_norm": 0.8825129866600037, "learning_rate": 0.0002, "epoch": 3.901135604542418, "step": 2920}, {"loss": 1.4519, "grad_norm": 0.6260842680931091, "learning_rate": 0.0002, "epoch": 3.914495657982632, "step": 2930}, {"loss": 1.5433, "grad_norm": 0.6015968322753906, "learning_rate": 0.0002, "epoch": 3.9278557114228456, "step": 2940}, {"loss": 1.4931, "grad_norm": 0.7042809128761292, "learning_rate": 0.0002, "epoch": 3.9412157648630597, "step": 2950}, {"loss": 1.5596, "grad_norm": 0.5860083699226379, "learning_rate": 0.0002, "epoch": 3.9545758183032733, "step": 2960}, {"loss": 1.565, "grad_norm": 0.5939757823944092, "learning_rate": 0.0002, "epoch": 3.967935871743487, "step": 2970}, {"loss": 1.408, "grad_norm": 0.5523964166641235, "learning_rate": 0.0002, "epoch": 3.9812959251837006, "step": 2980}, {"loss": 1.5629, "grad_norm": 0.6380264759063721, "learning_rate": 0.0002, "epoch": 3.9946559786239146, "step": 2990}, {"eval_loss": 1.8875294923782349, "eval_runtime": 38.5837, "eval_samples_per_second": 13.348, "eval_steps_per_second": 1.685, "epoch": 4.0, "step": 2994}, {"loss": 1.4002, "grad_norm": 0.5478564500808716, "learning_rate": 0.0002, "epoch": 4.008016032064128, "step": 3000}, {"loss": 1.436, "grad_norm": 0.9384379982948303, "learning_rate": 0.0002, "epoch": 4.021376085504342, "step": 3010}, {"loss": 1.4127, "grad_norm": 0.7819344401359558, "learning_rate": 0.0002, "epoch": 4.034736138944556, "step": 3020}, {"loss": 1.326, "grad_norm": 0.7737417817115784, "learning_rate": 0.0002, "epoch": 4.04809619238477, "step": 3030}, {"loss": 1.3203, "grad_norm": 0.8893805742263794, "learning_rate": 0.0002, "epoch": 4.061456245824983, "step": 3040}, {"loss": 1.3913, "grad_norm": 0.7759843468666077, "learning_rate": 0.0002, "epoch": 4.074816299265197, "step": 3050}, {"loss": 1.2941, "grad_norm": 0.642654538154602, "learning_rate": 0.0002, "epoch": 4.0881763527054105, "step": 3060}, {"loss": 1.3204, "grad_norm": 0.8515549302101135, "learning_rate": 0.0002, "epoch": 4.101536406145625, "step": 3070}, {"loss": 1.3683, "grad_norm": 0.7033658623695374, "learning_rate": 0.0002, "epoch": 4.114896459585839, "step": 3080}, {"loss": 1.4159, "grad_norm": 0.7063882946968079, "learning_rate": 0.0002, "epoch": 4.128256513026052, "step": 3090}, {"loss": 1.384, "grad_norm": 0.6946853995323181, "learning_rate": 0.0002, "epoch": 4.141616566466266, "step": 3100}, {"loss": 1.3689, "grad_norm": 0.7286741137504578, "learning_rate": 0.0002, "epoch": 4.1549766199064795, "step": 3110}, {"loss": 1.3061, "grad_norm": 0.7894193530082703, "learning_rate": 0.0002, "epoch": 4.168336673346693, "step": 3120}, {"loss": 1.3346, "grad_norm": 0.7005895376205444, "learning_rate": 0.0002, "epoch": 4.181696726786907, "step": 3130}, {"loss": 1.3834, "grad_norm": 0.799567461013794, "learning_rate": 0.0002, "epoch": 4.195056780227121, "step": 3140}, {"loss": 1.3813, "grad_norm": 0.7010157108306885, "learning_rate": 0.0002, "epoch": 4.208416833667335, "step": 3150}, {"loss": 1.3637, "grad_norm": 0.7489650249481201, "learning_rate": 0.0002, "epoch": 4.2217768871075485, "step": 3160}, {"loss": 1.3546, "grad_norm": 0.7908048629760742, "learning_rate": 0.0002, "epoch": 4.235136940547762, "step": 3170}, {"loss": 1.3073, "grad_norm": 0.7002180814743042, "learning_rate": 0.0002, "epoch": 4.248496993987976, "step": 3180}, {"loss": 1.4525, "grad_norm": 0.8339495062828064, "learning_rate": 0.0002, "epoch": 4.261857047428189, "step": 3190}, {"loss": 1.3471, "grad_norm": 0.7884618043899536, "learning_rate": 0.0002, "epoch": 4.275217100868403, "step": 3200}, {"loss": 1.4261, "grad_norm": 0.7964122295379639, "learning_rate": 0.0002, "epoch": 4.2885771543086175, "step": 3210}, {"loss": 1.3506, "grad_norm": 0.838646650314331, "learning_rate": 0.0002, "epoch": 4.301937207748831, "step": 3220}, {"loss": 1.3738, "grad_norm": 0.8063107132911682, "learning_rate": 0.0002, "epoch": 4.315297261189045, "step": 3230}, {"loss": 1.3769, "grad_norm": 0.8147385120391846, "learning_rate": 0.0002, "epoch": 4.328657314629258, "step": 3240}, {"loss": 1.4118, "grad_norm": 0.7636798620223999, "learning_rate": 0.0002, "epoch": 4.342017368069472, "step": 3250}, {"loss": 1.3698, "grad_norm": 0.7530609965324402, "learning_rate": 0.0002, "epoch": 4.355377421509686, "step": 3260}, {"loss": 1.3507, "grad_norm": 0.8853573799133301, "learning_rate": 0.0002, "epoch": 4.3687374749499, "step": 3270}, {"loss": 1.3614, "grad_norm": 0.7180975675582886, "learning_rate": 0.0002, "epoch": 4.382097528390114, "step": 3280}, {"loss": 1.4119, "grad_norm": 0.837150514125824, "learning_rate": 0.0002, "epoch": 4.395457581830327, "step": 3290}, {"loss": 1.461, "grad_norm": 0.8370638489723206, "learning_rate": 0.0002, "epoch": 4.408817635270541, "step": 3300}, {"loss": 1.4478, "grad_norm": 0.7738229036331177, "learning_rate": 0.0002, "epoch": 4.422177688710755, "step": 3310}, {"loss": 1.4195, "grad_norm": 0.7665290832519531, "learning_rate": 0.0002, "epoch": 4.435537742150968, "step": 3320}, {"loss": 1.3308, "grad_norm": 0.7547745704650879, "learning_rate": 0.0002, "epoch": 4.448897795591183, "step": 3330}, {"loss": 1.4165, "grad_norm": 0.7421861290931702, "learning_rate": 0.0002, "epoch": 4.462257849031396, "step": 3340}, {"loss": 1.4244, "grad_norm": 0.8042104244232178, "learning_rate": 0.0002, "epoch": 4.47561790247161, "step": 3350}, {"loss": 1.365, "grad_norm": 0.8111839890480042, "learning_rate": 0.0002, "epoch": 4.488977955911824, "step": 3360}, {"loss": 1.3537, "grad_norm": 0.7998340129852295, "learning_rate": 0.0002, "epoch": 4.502338009352037, "step": 3370}, {"loss": 1.3812, "grad_norm": 0.7668877243995667, "learning_rate": 0.0002, "epoch": 4.515698062792251, "step": 3380}, {"loss": 1.3972, "grad_norm": 0.7986718416213989, "learning_rate": 0.0002, "epoch": 4.529058116232465, "step": 3390}, {"loss": 1.3582, "grad_norm": 0.6806602478027344, "learning_rate": 0.0002, "epoch": 4.542418169672679, "step": 3400}, {"loss": 1.3942, "grad_norm": 0.8788819909095764, "learning_rate": 0.0002, "epoch": 4.555778223112893, "step": 3410}, {"loss": 1.3379, "grad_norm": 0.7499664425849915, "learning_rate": 0.0002, "epoch": 4.569138276553106, "step": 3420}, {"loss": 1.3823, "grad_norm": 0.7967109084129333, "learning_rate": 0.0002, "epoch": 4.58249832999332, "step": 3430}, {"loss": 1.3531, "grad_norm": 0.759639322757721, "learning_rate": 0.0002, "epoch": 4.595858383433534, "step": 3440}, {"loss": 1.3517, "grad_norm": 0.8327916264533997, "learning_rate": 0.0002, "epoch": 4.609218436873747, "step": 3450}, {"loss": 1.4619, "grad_norm": 0.7400892376899719, "learning_rate": 0.0002, "epoch": 4.622578490313961, "step": 3460}, {"loss": 1.3374, "grad_norm": 0.8116602301597595, "learning_rate": 0.0002, "epoch": 4.635938543754175, "step": 3470}, {"loss": 1.4445, "grad_norm": 0.7604362368583679, "learning_rate": 0.0002, "epoch": 4.649298597194389, "step": 3480}, {"loss": 1.3724, "grad_norm": 0.7397996783256531, "learning_rate": 0.0002, "epoch": 4.662658650634603, "step": 3490}, {"loss": 1.4048, "grad_norm": 0.869293749332428, "learning_rate": 0.0002, "epoch": 4.676018704074816, "step": 3500}, {"loss": 1.3873, "grad_norm": 0.6854358315467834, "learning_rate": 0.0002, "epoch": 4.68937875751503, "step": 3510}, {"loss": 1.3413, "grad_norm": 0.8326661586761475, "learning_rate": 0.0002, "epoch": 4.7027388109552435, "step": 3520}, {"loss": 1.3666, "grad_norm": 0.6887506246566772, "learning_rate": 0.0002, "epoch": 4.716098864395457, "step": 3530}, {"loss": 1.4508, "grad_norm": 3.837689161300659, "learning_rate": 0.0002, "epoch": 4.729458917835672, "step": 3540}, {"loss": 1.3775, "grad_norm": 0.6874563694000244, "learning_rate": 0.0002, "epoch": 4.742818971275885, "step": 3550}, {"loss": 1.3643, "grad_norm": 0.8340407609939575, "learning_rate": 0.0002, "epoch": 4.756179024716099, "step": 3560}, {"loss": 1.3556, "grad_norm": 0.7286418676376343, "learning_rate": 0.0002, "epoch": 4.7695390781563125, "step": 3570}, {"loss": 1.4338, "grad_norm": 0.7239373326301575, "learning_rate": 0.0002, "epoch": 4.782899131596526, "step": 3580}, {"loss": 1.4697, "grad_norm": 0.831310510635376, "learning_rate": 0.0002, "epoch": 4.796259185036741, "step": 3590}, {"loss": 1.4146, "grad_norm": 0.767715573310852, "learning_rate": 0.0002, "epoch": 4.809619238476954, "step": 3600}, {"loss": 1.4199, "grad_norm": 0.9013199210166931, "learning_rate": 0.0002, "epoch": 4.822979291917168, "step": 3610}, {"loss": 1.4513, "grad_norm": 0.7543512582778931, "learning_rate": 0.0002, "epoch": 4.8363393453573815, "step": 3620}, {"loss": 1.4218, "grad_norm": 0.7626057267189026, "learning_rate": 0.0002, "epoch": 4.849699398797595, "step": 3630}, {"loss": 1.4102, "grad_norm": 0.847079336643219, "learning_rate": 0.0002, "epoch": 4.863059452237809, "step": 3640}, {"loss": 1.5014, "grad_norm": 0.8273295760154724, "learning_rate": 0.0002, "epoch": 4.876419505678022, "step": 3650}, {"loss": 1.3806, "grad_norm": 0.7675244808197021, "learning_rate": 0.0002, "epoch": 4.889779559118237, "step": 3660}, {"loss": 1.4894, "grad_norm": 0.9560356736183167, "learning_rate": 0.0002, "epoch": 4.9031396125584505, "step": 3670}, {"loss": 1.4044, "grad_norm": 0.7682451605796814, "learning_rate": 0.0002, "epoch": 4.916499665998664, "step": 3680}, {"loss": 1.342, "grad_norm": 0.8113830089569092, "learning_rate": 0.0002, "epoch": 4.929859719438878, "step": 3690}, {"loss": 1.3559, "grad_norm": 0.7642542719841003, "learning_rate": 0.0002, "epoch": 4.943219772879091, "step": 3700}, {"loss": 1.403, "grad_norm": 0.823863685131073, "learning_rate": 0.0002, "epoch": 4.956579826319305, "step": 3710}, {"loss": 1.464, "grad_norm": 0.8287797570228577, "learning_rate": 0.0002, "epoch": 4.969939879759519, "step": 3720}, {"loss": 1.4139, "grad_norm": 0.778170108795166, "learning_rate": 0.0002, "epoch": 4.983299933199733, "step": 3730}, {"loss": 1.4218, "grad_norm": 0.7464073896408081, "learning_rate": 0.0002, "epoch": 4.996659986639947, "step": 3740}, {"eval_loss": 1.9638569355010986, "eval_runtime": 38.5725, "eval_samples_per_second": 13.351, "eval_steps_per_second": 1.685, "epoch": 4.999331997327989, "step": 3742}, {"loss": 1.225, "grad_norm": 0.8864085078239441, "learning_rate": 0.0002, "epoch": 5.01002004008016, "step": 3750}, {"loss": 1.2056, "grad_norm": 0.9191637635231018, "learning_rate": 0.0002, "epoch": 5.023380093520374, "step": 3760}, {"loss": 1.2453, "grad_norm": 0.749519407749176, "learning_rate": 0.0002, "epoch": 5.036740146960588, "step": 3770}, {"loss": 1.1959, "grad_norm": 0.7916892170906067, "learning_rate": 0.0002, "epoch": 5.050100200400801, "step": 3780}, {"loss": 1.2279, "grad_norm": 1.0318909883499146, "learning_rate": 0.0002, "epoch": 5.063460253841015, "step": 3790}, {"loss": 1.2585, "grad_norm": 1.028586745262146, "learning_rate": 0.0002, "epoch": 5.0768203072812295, "step": 3800}, {"loss": 1.1769, "grad_norm": 1.0568538904190063, "learning_rate": 0.0002, "epoch": 5.090180360721443, "step": 3810}, {"loss": 1.263, "grad_norm": 0.9780595302581787, "learning_rate": 0.0002, "epoch": 5.103540414161657, "step": 3820}, {"loss": 1.2019, "grad_norm": 1.10311758518219, "learning_rate": 0.0002, "epoch": 5.11690046760187, "step": 3830}, {"loss": 1.2133, "grad_norm": 0.9497154355049133, "learning_rate": 0.0002, "epoch": 5.130260521042084, "step": 3840}, {"loss": 1.1718, "grad_norm": 0.948279857635498, "learning_rate": 0.0002, "epoch": 5.143620574482298, "step": 3850}, {"loss": 1.2108, "grad_norm": 0.9497880339622498, "learning_rate": 0.0002, "epoch": 5.156980627922512, "step": 3860}, {"loss": 1.1876, "grad_norm": 1.3213258981704712, "learning_rate": 0.0002, "epoch": 5.170340681362726, "step": 3870}, {"loss": 1.2327, "grad_norm": 0.9835752248764038, "learning_rate": 0.0002, "epoch": 5.183700734802939, "step": 3880}, {"loss": 1.2256, "grad_norm": 0.8426132202148438, "learning_rate": 0.0002, "epoch": 5.197060788243153, "step": 3890}, {"loss": 1.2066, "grad_norm": 1.0343470573425293, "learning_rate": 0.0002, "epoch": 5.210420841683367, "step": 3900}, {"loss": 1.2596, "grad_norm": 1.0771924257278442, "learning_rate": 0.0002, "epoch": 5.22378089512358, "step": 3910}, {"loss": 1.2371, "grad_norm": 0.8542634844779968, "learning_rate": 0.0002, "epoch": 5.237140948563794, "step": 3920}, {"loss": 1.2264, "grad_norm": 1.1021966934204102, "learning_rate": 0.0002, "epoch": 5.250501002004008, "step": 3930}, {"loss": 1.2097, "grad_norm": 1.170011281967163, "learning_rate": 0.0002, "epoch": 5.263861055444222, "step": 3940}, {"loss": 1.2101, "grad_norm": 0.9787653684616089, "learning_rate": 0.0002, "epoch": 5.277221108884436, "step": 3950}, {"loss": 1.24, "grad_norm": 0.914513885974884, "learning_rate": 0.0002, "epoch": 5.290581162324649, "step": 3960}, {"loss": 1.1641, "grad_norm": 1.0831562280654907, "learning_rate": 0.0002, "epoch": 5.303941215764863, "step": 3970}, {"loss": 1.2609, "grad_norm": 0.9810112714767456, "learning_rate": 0.0002, "epoch": 5.3173012692050765, "step": 3980}, {"loss": 1.1825, "grad_norm": 0.9624066948890686, "learning_rate": 0.0002, "epoch": 5.330661322645291, "step": 3990}, {"loss": 1.273, "grad_norm": 1.2296923398971558, "learning_rate": 0.0002, "epoch": 5.344021376085505, "step": 4000}, {"loss": 1.2452, "grad_norm": 1.011299967765808, "learning_rate": 0.0002, "epoch": 5.357381429525718, "step": 4010}, {"loss": 1.2539, "grad_norm": 0.9144132733345032, "learning_rate": 0.0002, "epoch": 5.370741482965932, "step": 4020}, {"loss": 1.2914, "grad_norm": 1.0573601722717285, "learning_rate": 0.0002, "epoch": 5.3841015364061455, "step": 4030}, {"loss": 1.2295, "grad_norm": 1.1667137145996094, "learning_rate": 0.0002, "epoch": 5.397461589846359, "step": 4040}, {"loss": 1.2541, "grad_norm": 1.072070598602295, "learning_rate": 0.0002, "epoch": 5.410821643286573, "step": 4050}, {"loss": 1.2448, "grad_norm": 1.1005792617797852, "learning_rate": 0.0002, "epoch": 5.424181696726787, "step": 4060}, {"loss": 1.2604, "grad_norm": 1.033581018447876, "learning_rate": 0.0002, "epoch": 5.437541750167001, "step": 4070}, {"loss": 1.2552, "grad_norm": 0.9537439942359924, "learning_rate": 0.0002, "epoch": 5.4509018036072145, "step": 4080}, {"loss": 1.2985, "grad_norm": 1.0502177476882935, "learning_rate": 0.0002, "epoch": 5.464261857047428, "step": 4090}, {"loss": 1.2424, "grad_norm": 0.9098296761512756, "learning_rate": 0.0002, "epoch": 5.477621910487642, "step": 4100}, {"loss": 1.2262, "grad_norm": 0.9551953077316284, "learning_rate": 0.0002, "epoch": 5.490981963927855, "step": 4110}, {"loss": 1.2848, "grad_norm": 0.9169427156448364, "learning_rate": 0.0002, "epoch": 5.504342017368069, "step": 4120}, {"loss": 1.2572, "grad_norm": 0.9430235624313354, "learning_rate": 0.0002, "epoch": 5.517702070808284, "step": 4130}, {"loss": 1.2618, "grad_norm": 0.817259669303894, "learning_rate": 0.0002, "epoch": 5.531062124248497, "step": 4140}, {"loss": 1.3012, "grad_norm": 1.124152660369873, "learning_rate": 0.0002, "epoch": 5.544422177688711, "step": 4150}, {"loss": 1.2508, "grad_norm": 0.9250756502151489, "learning_rate": 0.0002, "epoch": 5.557782231128924, "step": 4160}, {"loss": 1.2492, "grad_norm": 0.9582970142364502, "learning_rate": 0.0002, "epoch": 5.571142284569138, "step": 4170}, {"loss": 1.2804, "grad_norm": 1.0078704357147217, "learning_rate": 0.0002, "epoch": 5.584502338009352, "step": 4180}, {"loss": 1.1961, "grad_norm": 0.9585610032081604, "learning_rate": 0.0002, "epoch": 5.597862391449565, "step": 4190}, {"loss": 1.2522, "grad_norm": 1.0150971412658691, "learning_rate": 0.0002, "epoch": 5.61122244488978, "step": 4200}, {"loss": 1.2275, "grad_norm": 0.9943351149559021, "learning_rate": 0.0002, "epoch": 5.6245824983299935, "step": 4210}, {"loss": 1.2928, "grad_norm": 0.8880936503410339, "learning_rate": 0.0002, "epoch": 5.637942551770207, "step": 4220}, {"loss": 1.2323, "grad_norm": 0.9873887896537781, "learning_rate": 0.0002, "epoch": 5.651302605210421, "step": 4230}, {"loss": 1.3391, "grad_norm": 0.9185152649879456, "learning_rate": 0.0002, "epoch": 5.664662658650634, "step": 4240}, {"loss": 1.2511, "grad_norm": 1.0706779956817627, "learning_rate": 0.0002, "epoch": 5.678022712090849, "step": 4250}, {"loss": 1.2737, "grad_norm": 0.9660224914550781, "learning_rate": 0.0002, "epoch": 5.6913827655310625, "step": 4260}, {"loss": 1.2815, "grad_norm": 0.8685019612312317, "learning_rate": 0.0002, "epoch": 5.704742818971276, "step": 4270}, {"loss": 1.1559, "grad_norm": 1.0390565395355225, "learning_rate": 0.0002, "epoch": 5.71810287241149, "step": 4280}, {"loss": 1.3134, "grad_norm": 0.9290478825569153, "learning_rate": 0.0002, "epoch": 5.731462925851703, "step": 4290}, {"loss": 1.2426, "grad_norm": 1.0361281633377075, "learning_rate": 0.0002, "epoch": 5.744822979291917, "step": 4300}, {"loss": 1.2688, "grad_norm": 0.8804615139961243, "learning_rate": 0.0002, "epoch": 5.758183032732131, "step": 4310}, {"loss": 1.2479, "grad_norm": 1.0051425695419312, "learning_rate": 0.0002, "epoch": 5.771543086172345, "step": 4320}, {"loss": 1.1946, "grad_norm": 1.0051119327545166, "learning_rate": 0.0002, "epoch": 5.784903139612559, "step": 4330}, {"loss": 1.2571, "grad_norm": 0.9961661100387573, "learning_rate": 0.0002, "epoch": 5.798263193052772, "step": 4340}, {"loss": 1.2179, "grad_norm": 1.0229419469833374, "learning_rate": 0.0002, "epoch": 5.811623246492986, "step": 4350}, {"loss": 1.2984, "grad_norm": 1.1129552125930786, "learning_rate": 0.0002, "epoch": 5.8249832999332, "step": 4360}, {"loss": 1.2692, "grad_norm": 1.18964421749115, "learning_rate": 0.0002, "epoch": 5.838343353373413, "step": 4370}, {"loss": 1.1996, "grad_norm": 0.9490230083465576, "learning_rate": 0.0002, "epoch": 5.851703406813627, "step": 4380}, {"loss": 1.3177, "grad_norm": 0.8734540343284607, "learning_rate": 0.0002, "epoch": 5.865063460253841, "step": 4390}, {"loss": 1.3131, "grad_norm": 1.0017802715301514, "learning_rate": 0.0002, "epoch": 5.878423513694055, "step": 4400}, {"loss": 1.2649, "grad_norm": 0.953556478023529, "learning_rate": 0.0002, "epoch": 5.891783567134269, "step": 4410}, {"loss": 1.2684, "grad_norm": 0.8915258646011353, "learning_rate": 0.0002, "epoch": 5.905143620574482, "step": 4420}, {"loss": 1.2843, "grad_norm": 0.9715141654014587, "learning_rate": 0.0002, "epoch": 5.918503674014696, "step": 4430}, {"loss": 1.2769, "grad_norm": 0.9432152509689331, "learning_rate": 0.0002, "epoch": 5.9318637274549095, "step": 4440}, {"loss": 1.233, "grad_norm": 0.9473979473114014, "learning_rate": 0.0002, "epoch": 5.945223780895123, "step": 4450}, {"loss": 1.3209, "grad_norm": 1.104871392250061, "learning_rate": 0.0002, "epoch": 5.958583834335338, "step": 4460}, {"loss": 1.3427, "grad_norm": 1.0308905839920044, "learning_rate": 0.0002, "epoch": 5.971943887775551, "step": 4470}, {"loss": 1.1808, "grad_norm": 0.8895487189292908, "learning_rate": 0.0002, "epoch": 5.985303941215765, "step": 4480}, {"loss": 1.2634, "grad_norm": 1.0148485898971558, "learning_rate": 0.0002, "epoch": 5.9986639946559785, "step": 4490}, {"eval_loss": 2.0830726623535156, "eval_runtime": 38.5442, "eval_samples_per_second": 13.361, "eval_steps_per_second": 1.686, "epoch": 6.0, "step": 4491}, {"loss": 1.1106, "grad_norm": 1.1640599966049194, "learning_rate": 0.0002, "epoch": 6.012024048096192, "step": 4500}, {"loss": 1.0436, "grad_norm": 1.213204264640808, "learning_rate": 0.0002, "epoch": 6.025384101536406, "step": 4510}, {"loss": 1.0606, "grad_norm": 1.1694388389587402, "learning_rate": 0.0002, "epoch": 6.03874415497662, "step": 4520}, {"loss": 1.0274, "grad_norm": 1.1044062376022339, "learning_rate": 0.0002, "epoch": 6.052104208416834, "step": 4530}, {"loss": 1.0552, "grad_norm": 1.0701100826263428, "learning_rate": 0.0002, "epoch": 6.065464261857048, "step": 4540}, {"loss": 1.0018, "grad_norm": 1.360065221786499, "learning_rate": 0.0002, "epoch": 6.078824315297261, "step": 4550}, {"loss": 1.0189, "grad_norm": 1.0648503303527832, "learning_rate": 0.0002, "epoch": 6.092184368737475, "step": 4560}, {"loss": 1.008, "grad_norm": 1.066245198249817, "learning_rate": 0.0002, "epoch": 6.1055444221776884, "step": 4570}, {"loss": 1.099, "grad_norm": 1.1483700275421143, "learning_rate": 0.0002, "epoch": 6.118904475617902, "step": 4580}, {"loss": 1.1043, "grad_norm": 1.334275722503662, "learning_rate": 0.0002, "epoch": 6.132264529058117, "step": 4590}, {"loss": 1.0783, "grad_norm": 1.2141029834747314, "learning_rate": 0.0002, "epoch": 6.14562458249833, "step": 4600}, {"loss": 1.0891, "grad_norm": 1.2284387350082397, "learning_rate": 0.0002, "epoch": 6.158984635938544, "step": 4610}, {"loss": 1.122, "grad_norm": 1.2326734066009521, "learning_rate": 0.0002, "epoch": 6.1723446893787575, "step": 4620}, {"loss": 1.1069, "grad_norm": 1.245004653930664, "learning_rate": 0.0002, "epoch": 6.185704742818971, "step": 4630}, {"loss": 1.0821, "grad_norm": 0.9685266017913818, "learning_rate": 0.0002, "epoch": 6.199064796259185, "step": 4640}, {"loss": 1.0659, "grad_norm": 1.141634464263916, "learning_rate": 0.0002, "epoch": 6.212424849699399, "step": 4650}, {"loss": 1.0971, "grad_norm": 1.4279003143310547, "learning_rate": 0.0002, "epoch": 6.225784903139613, "step": 4660}, {"loss": 1.093, "grad_norm": 1.186668872833252, "learning_rate": 0.0002, "epoch": 6.2391449565798265, "step": 4670}, {"loss": 1.0522, "grad_norm": 1.2656606435775757, "learning_rate": 0.0002, "epoch": 6.25250501002004, "step": 4680}, {"loss": 1.1138, "grad_norm": 1.1122987270355225, "learning_rate": 0.0002, "epoch": 6.265865063460254, "step": 4690}, {"loss": 1.0906, "grad_norm": 1.190050482749939, "learning_rate": 0.0002, "epoch": 6.279225116900467, "step": 4700}, {"loss": 1.1095, "grad_norm": 1.3683340549468994, "learning_rate": 0.0002, "epoch": 6.292585170340681, "step": 4710}, {"loss": 1.0663, "grad_norm": 1.1787203550338745, "learning_rate": 0.0002, "epoch": 6.3059452237808955, "step": 4720}, {"loss": 1.0856, "grad_norm": 1.3502576351165771, "learning_rate": 0.0002, "epoch": 6.319305277221109, "step": 4730}, {"loss": 1.0999, "grad_norm": 1.1958597898483276, "learning_rate": 0.0002, "epoch": 6.332665330661323, "step": 4740}, {"loss": 1.021, "grad_norm": 1.0918327569961548, "learning_rate": 0.0002, "epoch": 6.346025384101536, "step": 4750}, {"loss": 1.0484, "grad_norm": 1.2624558210372925, "learning_rate": 0.0002, "epoch": 6.35938543754175, "step": 4760}, {"loss": 1.0785, "grad_norm": 1.1390577554702759, "learning_rate": 0.0002, "epoch": 6.372745490981964, "step": 4770}, {"loss": 1.0979, "grad_norm": 1.041666865348816, "learning_rate": 0.0002, "epoch": 6.386105544422177, "step": 4780}, {"loss": 1.1026, "grad_norm": 1.4209141731262207, "learning_rate": 0.0002, "epoch": 6.399465597862392, "step": 4790}, {"loss": 1.119, "grad_norm": 1.1001079082489014, "learning_rate": 0.0002, "epoch": 6.412825651302605, "step": 4800}, {"loss": 1.1082, "grad_norm": 1.3324936628341675, "learning_rate": 0.0002, "epoch": 6.426185704742819, "step": 4810}, {"loss": 1.0785, "grad_norm": 1.1270194053649902, "learning_rate": 0.0002, "epoch": 6.439545758183033, "step": 4820}, {"loss": 1.1338, "grad_norm": 1.1961387395858765, "learning_rate": 0.0002, "epoch": 6.452905811623246, "step": 4830}, {"loss": 1.0967, "grad_norm": 1.255366563796997, "learning_rate": 0.0002, "epoch": 6.46626586506346, "step": 4840}, {"loss": 1.1226, "grad_norm": 1.343855381011963, "learning_rate": 0.0002, "epoch": 6.479625918503674, "step": 4850}, {"loss": 1.1118, "grad_norm": 1.3216257095336914, "learning_rate": 0.0002, "epoch": 6.492985971943888, "step": 4860}, {"loss": 1.1664, "grad_norm": 1.5244755744934082, "learning_rate": 0.0002, "epoch": 6.506346025384102, "step": 4870}, {"loss": 1.0403, "grad_norm": 1.1585701704025269, "learning_rate": 0.0002, "epoch": 6.519706078824315, "step": 4880}, {"loss": 1.1344, "grad_norm": 1.0301100015640259, "learning_rate": 0.0002, "epoch": 6.533066132264529, "step": 4890}, {"loss": 1.1304, "grad_norm": 1.5772714614868164, "learning_rate": 0.0002, "epoch": 6.5464261857047426, "step": 4900}, {"loss": 1.0953, "grad_norm": 1.2015259265899658, "learning_rate": 0.0002, "epoch": 6.559786239144957, "step": 4910}, {"loss": 1.1283, "grad_norm": 1.4365423917770386, "learning_rate": 0.0002, "epoch": 6.573146292585171, "step": 4920}, {"loss": 1.0717, "grad_norm": 1.2534470558166504, "learning_rate": 0.0002, "epoch": 6.586506346025384, "step": 4930}, {"loss": 1.1099, "grad_norm": 1.216138482093811, "learning_rate": 0.0002, "epoch": 6.599866399465598, "step": 4940}, {"loss": 1.1744, "grad_norm": 1.144316554069519, "learning_rate": 0.0002, "epoch": 6.613226452905812, "step": 4950}, {"loss": 1.0548, "grad_norm": 1.1127740144729614, "learning_rate": 0.0002, "epoch": 6.626586506346025, "step": 4960}, {"loss": 1.0686, "grad_norm": 1.1925606727600098, "learning_rate": 0.0002, "epoch": 6.639946559786239, "step": 4970}, {"loss": 1.0684, "grad_norm": 1.2500451803207397, "learning_rate": 0.0002, "epoch": 6.653306613226453, "step": 4980}, {"loss": 1.1642, "grad_norm": 1.16154944896698, "learning_rate": 0.0002, "epoch": 6.666666666666667, "step": 4990}, {"loss": 1.1003, "grad_norm": 1.1921433210372925, "learning_rate": 0.0002, "epoch": 6.680026720106881, "step": 5000}, {"loss": 1.1278, "grad_norm": 1.1561170816421509, "learning_rate": 0.0002, "epoch": 6.693386773547094, "step": 5010}, {"loss": 1.0766, "grad_norm": 1.2988990545272827, "learning_rate": 0.0002, "epoch": 6.706746826987308, "step": 5020}, {"loss": 1.1131, "grad_norm": 0.9620341062545776, "learning_rate": 0.0002, "epoch": 6.7201068804275215, "step": 5030}, {"loss": 1.109, "grad_norm": 1.084228515625, "learning_rate": 0.0002, "epoch": 6.733466933867735, "step": 5040}, {"loss": 1.1474, "grad_norm": 1.1119431257247925, "learning_rate": 0.0002, "epoch": 6.74682698730795, "step": 5050}, {"loss": 1.179, "grad_norm": 1.1365628242492676, "learning_rate": 0.0002, "epoch": 6.760187040748163, "step": 5060}, {"loss": 1.0988, "grad_norm": 1.0989075899124146, "learning_rate": 0.0002, "epoch": 6.773547094188377, "step": 5070}, {"loss": 1.127, "grad_norm": 1.040647268295288, "learning_rate": 0.0002, "epoch": 6.7869071476285905, "step": 5080}, {"loss": 1.0793, "grad_norm": 1.1083087921142578, "learning_rate": 0.0002, "epoch": 6.800267201068804, "step": 5090}, {"loss": 1.1081, "grad_norm": 1.3434782028198242, "learning_rate": 0.0002, "epoch": 6.813627254509018, "step": 5100}, {"loss": 1.1243, "grad_norm": 1.2493442296981812, "learning_rate": 0.0002, "epoch": 6.826987307949231, "step": 5110}, {"loss": 1.0633, "grad_norm": 1.0672307014465332, "learning_rate": 0.0002, "epoch": 6.840347361389446, "step": 5120}, {"loss": 1.1344, "grad_norm": 1.068350911140442, "learning_rate": 0.0002, "epoch": 6.8537074148296595, "step": 5130}, {"loss": 1.1942, "grad_norm": 1.2880923748016357, "learning_rate": 0.0002, "epoch": 6.867067468269873, "step": 5140}, {"loss": 1.1445, "grad_norm": 1.0895041227340698, "learning_rate": 0.0002, "epoch": 6.880427521710087, "step": 5150}, {"loss": 1.1535, "grad_norm": 1.2383300065994263, "learning_rate": 0.0002, "epoch": 6.8937875751503, "step": 5160}, {"loss": 1.1653, "grad_norm": 1.5274227857589722, "learning_rate": 0.0002, "epoch": 6.907147628590514, "step": 5170}, {"loss": 1.1112, "grad_norm": 1.1453371047973633, "learning_rate": 0.0002, "epoch": 6.920507682030728, "step": 5180}, {"loss": 1.1808, "grad_norm": 1.171336054801941, "learning_rate": 0.0002, "epoch": 6.933867735470942, "step": 5190}, {"loss": 1.1142, "grad_norm": 1.1946955919265747, "learning_rate": 0.0002, "epoch": 6.947227788911156, "step": 5200}, {"loss": 1.1386, "grad_norm": 1.2290117740631104, "learning_rate": 0.0002, "epoch": 6.960587842351369, "step": 5210}, {"loss": 1.1573, "grad_norm": 1.3134533166885376, "learning_rate": 0.0002, "epoch": 6.973947895791583, "step": 5220}, {"loss": 1.1687, "grad_norm": 1.1500377655029297, "learning_rate": 0.0002, "epoch": 6.987307949231797, "step": 5230}, {"eval_loss": 2.2211341857910156, "eval_runtime": 38.5729, "eval_samples_per_second": 13.351, "eval_steps_per_second": 1.685, "epoch": 6.999331997327989, "step": 5239}, {"loss": 1.1235, "grad_norm": 1.1143344640731812, "learning_rate": 0.0002, "epoch": 7.00066800267201, "step": 5240}, {"loss": 0.9203, "grad_norm": 1.5164896249771118, "learning_rate": 0.0002, "epoch": 7.014028056112225, "step": 5250}, {"loss": 0.9605, "grad_norm": 1.3737165927886963, "learning_rate": 0.0002, "epoch": 7.027388109552438, "step": 5260}, {"loss": 0.8599, "grad_norm": 1.2159202098846436, "learning_rate": 0.0002, "epoch": 7.040748162992652, "step": 5270}, {"loss": 0.9469, "grad_norm": 1.4183212518692017, "learning_rate": 0.0002, "epoch": 7.054108216432866, "step": 5280}, {"loss": 0.9188, "grad_norm": 1.4752920866012573, "learning_rate": 0.0002, "epoch": 7.067468269873079, "step": 5290}, {"loss": 0.873, "grad_norm": 1.398065447807312, "learning_rate": 0.0002, "epoch": 7.080828323313293, "step": 5300}, {"loss": 0.9434, "grad_norm": 1.4385913610458374, "learning_rate": 0.0002, "epoch": 7.094188376753507, "step": 5310}, {"loss": 0.8527, "grad_norm": 1.3779526948928833, "learning_rate": 0.0002, "epoch": 7.107548430193721, "step": 5320}, {"loss": 0.9139, "grad_norm": 1.5290347337722778, "learning_rate": 0.0002, "epoch": 7.120908483633935, "step": 5330}, {"loss": 0.8769, "grad_norm": 1.2389367818832397, "learning_rate": 0.0002, "epoch": 7.134268537074148, "step": 5340}, {"loss": 0.9396, "grad_norm": 1.4514659643173218, "learning_rate": 0.0002, "epoch": 7.147628590514362, "step": 5350}, {"loss": 0.9303, "grad_norm": 1.3247307538986206, "learning_rate": 0.0002, "epoch": 7.160988643954576, "step": 5360}, {"loss": 0.9218, "grad_norm": 1.1711286306381226, "learning_rate": 0.0002, "epoch": 7.174348697394789, "step": 5370}, {"loss": 0.944, "grad_norm": 1.4408347606658936, "learning_rate": 0.0002, "epoch": 7.187708750835004, "step": 5380}, {"loss": 0.9509, "grad_norm": 1.4405876398086548, "learning_rate": 0.0002, "epoch": 7.201068804275217, "step": 5390}, {"loss": 0.9428, "grad_norm": 1.233242154121399, "learning_rate": 0.0002, "epoch": 7.214428857715431, "step": 5400}, {"loss": 0.9401, "grad_norm": 1.734960675239563, "learning_rate": 0.0002, "epoch": 7.227788911155645, "step": 5410}, {"loss": 0.9232, "grad_norm": 1.5165163278579712, "learning_rate": 0.0002, "epoch": 7.241148964595858, "step": 5420}, {"loss": 0.949, "grad_norm": 1.4353035688400269, "learning_rate": 0.0002, "epoch": 7.254509018036072, "step": 5430}, {"loss": 0.9029, "grad_norm": 1.4540636539459229, "learning_rate": 0.0002, "epoch": 7.2678690714762855, "step": 5440}, {"loss": 0.9117, "grad_norm": 1.2676037549972534, "learning_rate": 0.0002, "epoch": 7.2812291249165, "step": 5450}, {"loss": 1.0148, "grad_norm": 1.2626118659973145, "learning_rate": 0.0002, "epoch": 7.294589178356714, "step": 5460}, {"loss": 0.9373, "grad_norm": 1.4866795539855957, "learning_rate": 0.0002, "epoch": 7.307949231796927, "step": 5470}, {"loss": 0.9474, "grad_norm": 1.2464289665222168, "learning_rate": 0.0002, "epoch": 7.321309285237141, "step": 5480}, {"loss": 0.896, "grad_norm": 1.2815988063812256, "learning_rate": 0.0002, "epoch": 7.3346693386773545, "step": 5490}, {"loss": 0.9733, "grad_norm": 1.282402753829956, "learning_rate": 0.0002, "epoch": 7.348029392117568, "step": 5500}, {"loss": 0.9427, "grad_norm": 1.5422425270080566, "learning_rate": 0.0002, "epoch": 7.361389445557783, "step": 5510}, {"loss": 1.0067, "grad_norm": 1.4137073755264282, "learning_rate": 0.0002, "epoch": 7.374749498997996, "step": 5520}, {"loss": 0.8669, "grad_norm": 1.4875508546829224, "learning_rate": 0.0002, "epoch": 7.38810955243821, "step": 5530}, {"loss": 0.9576, "grad_norm": 1.292340874671936, "learning_rate": 0.0002, "epoch": 7.4014696058784235, "step": 5540}, {"loss": 0.9031, "grad_norm": 1.5553388595581055, "learning_rate": 0.0002, "epoch": 7.414829659318637, "step": 5550}, {"loss": 1.005, "grad_norm": 1.394142746925354, "learning_rate": 0.0002, "epoch": 7.428189712758851, "step": 5560}, {"loss": 0.9493, "grad_norm": 1.3249385356903076, "learning_rate": 0.0002, "epoch": 7.441549766199064, "step": 5570}, {"loss": 0.9806, "grad_norm": 1.3204814195632935, "learning_rate": 0.0002, "epoch": 7.454909819639279, "step": 5580}, {"loss": 0.9182, "grad_norm": 1.4062745571136475, "learning_rate": 0.0002, "epoch": 7.4682698730794925, "step": 5590}, {"loss": 0.9429, "grad_norm": 1.2828562259674072, "learning_rate": 0.0002, "epoch": 7.481629926519706, "step": 5600}, {"loss": 0.9498, "grad_norm": 1.440412998199463, "learning_rate": 0.0002, "epoch": 7.49498997995992, "step": 5610}, {"loss": 1.0005, "grad_norm": 1.4771733283996582, "learning_rate": 0.0002, "epoch": 7.508350033400133, "step": 5620}, {"loss": 0.9472, "grad_norm": 1.329460620880127, "learning_rate": 0.0002, "epoch": 7.521710086840347, "step": 5630}, {"loss": 0.9635, "grad_norm": 1.2443828582763672, "learning_rate": 0.0002, "epoch": 7.5350701402805615, "step": 5640}, {"loss": 0.9785, "grad_norm": 1.3739941120147705, "learning_rate": 0.0002, "epoch": 7.548430193720775, "step": 5650}, {"loss": 0.9538, "grad_norm": 1.5168178081512451, "learning_rate": 0.0002, "epoch": 7.561790247160989, "step": 5660}, {"loss": 0.9381, "grad_norm": 1.3648325204849243, "learning_rate": 0.0002, "epoch": 7.575150300601202, "step": 5670}, {"loss": 0.9696, "grad_norm": 1.308164119720459, "learning_rate": 0.0002, "epoch": 7.588510354041416, "step": 5680}, {"loss": 0.9889, "grad_norm": 1.3583498001098633, "learning_rate": 0.0002, "epoch": 7.60187040748163, "step": 5690}, {"loss": 0.9566, "grad_norm": 1.4746732711791992, "learning_rate": 0.0002, "epoch": 7.615230460921843, "step": 5700}, {"loss": 0.9462, "grad_norm": 1.3042285442352295, "learning_rate": 0.0002, "epoch": 7.628590514362058, "step": 5710}, {"loss": 1.0146, "grad_norm": 1.5272791385650635, "learning_rate": 0.0002, "epoch": 7.641950567802271, "step": 5720}, {"loss": 0.9795, "grad_norm": 1.1505831480026245, "learning_rate": 0.0002, "epoch": 7.655310621242485, "step": 5730}, {"loss": 0.9758, "grad_norm": 1.3690030574798584, "learning_rate": 0.0002, "epoch": 7.668670674682699, "step": 5740}, {"loss": 0.9565, "grad_norm": 1.3092460632324219, "learning_rate": 0.0002, "epoch": 7.682030728122912, "step": 5750}, {"loss": 1.0147, "grad_norm": 1.7011737823486328, "learning_rate": 0.0002, "epoch": 7.695390781563126, "step": 5760}, {"loss": 1.0261, "grad_norm": 1.4010082483291626, "learning_rate": 0.0002, "epoch": 7.70875083500334, "step": 5770}, {"loss": 1.0288, "grad_norm": 1.63649582862854, "learning_rate": 0.0002, "epoch": 7.722110888443554, "step": 5780}, {"loss": 0.9496, "grad_norm": 1.5091519355773926, "learning_rate": 0.0002, "epoch": 7.735470941883768, "step": 5790}, {"loss": 0.9627, "grad_norm": 1.345441460609436, "learning_rate": 0.0002, "epoch": 7.748830995323981, "step": 5800}, {"loss": 0.9518, "grad_norm": 1.461037278175354, "learning_rate": 0.0002, "epoch": 7.762191048764195, "step": 5810}, {"loss": 0.9544, "grad_norm": 1.3914507627487183, "learning_rate": 0.0002, "epoch": 7.775551102204409, "step": 5820}, {"loss": 0.9946, "grad_norm": 1.293625831604004, "learning_rate": 0.0002, "epoch": 7.788911155644622, "step": 5830}, {"loss": 0.9732, "grad_norm": 1.5641531944274902, "learning_rate": 0.0002, "epoch": 7.802271209084836, "step": 5840}, {"loss": 0.9952, "grad_norm": 1.2400811910629272, "learning_rate": 0.0002, "epoch": 7.81563126252505, "step": 5850}, {"loss": 0.9841, "grad_norm": 1.335532546043396, "learning_rate": 0.0002, "epoch": 7.828991315965264, "step": 5860}, {"loss": 0.9609, "grad_norm": 1.4629961252212524, "learning_rate": 0.0002, "epoch": 7.842351369405478, "step": 5870}, {"loss": 1.0813, "grad_norm": 1.3005847930908203, "learning_rate": 0.0002, "epoch": 7.855711422845691, "step": 5880}, {"loss": 1.0466, "grad_norm": 1.6970791816711426, "learning_rate": 0.0002, "epoch": 7.869071476285905, "step": 5890}, {"loss": 0.9399, "grad_norm": 1.6887991428375244, "learning_rate": 0.0002, "epoch": 7.882431529726119, "step": 5900}, {"loss": 1.0364, "grad_norm": 1.4156445264816284, "learning_rate": 0.0002, "epoch": 7.895791583166333, "step": 5910}, {"loss": 0.9856, "grad_norm": 1.2695387601852417, "learning_rate": 0.0002, "epoch": 7.909151636606547, "step": 5920}, {"loss": 0.9902, "grad_norm": 1.4491169452667236, "learning_rate": 0.0002, "epoch": 7.92251169004676, "step": 5930}, {"loss": 1.047, "grad_norm": 1.4262619018554688, "learning_rate": 0.0002, "epoch": 7.935871743486974, "step": 5940}, {"loss": 1.0889, "grad_norm": 1.5128049850463867, "learning_rate": 0.0002, "epoch": 7.9492317969271875, "step": 5950}, {"loss": 0.9721, "grad_norm": 1.3630818128585815, "learning_rate": 0.0002, "epoch": 7.962591850367401, "step": 5960}, {"loss": 1.0154, "grad_norm": 1.410461187362671, "learning_rate": 0.0002, "epoch": 7.975951903807616, "step": 5970}, {"loss": 1.0192, "grad_norm": 1.4158549308776855, "learning_rate": 0.0002, "epoch": 7.989311957247829, "step": 5980}]}