Upload folder using huggingface_hub

.gitattributes

@@ -1534,3 +1534,12 @@ gemma-2-9b-it_int4_arc_challenge-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-
 gemma-2-9b-it_int4_arc_challenge-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-617-sd-4/checkpoint-496/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2-9b-it_int4_arc_challenge-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-617-sd-4/checkpoint-62/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-2-9b-it_int4_arc_challenge-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.6-num-617-sd-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-2053/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-3079/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-4106/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-5132/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-6159/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-7185/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-8208/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f63771989885dd3030480c888f982b482a4f0b6609b4f6205f6bf9b1faaccaf
+size 143153376

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f63771989885dd3030480c888f982b482a4f0b6609b4f6205f6bf9b1faaccaf
+size 143153376

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a14bd7bd809dcf34e3681aa306e3332e2ce2c7c355217ad047c7a5749bf95e6
+size 72886650

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c4eb9f332793c665c686d8296af92d4a1ded65117b574b2bd8d775e5ba49b28
+size 14244

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660ab54d0c298f22afda4a2655936aecd813daf93f4fc040b7d285b3684be4c0
+size 1064

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026/tokenizer_config.json

@@ -0,0 +1,2013 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026/trainer_state.json

@@ -0,0 +1,755 @@
+{
+  "best_metric": 1.8103164434432983,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026",
+  "epoch": 0.9995129079396006,
+  "eval_steps": 10,
+  "global_step": 1026,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00974184120798831,
+      "grad_norm": 0.6537588834762573,
+      "learning_rate": 0.0002,
+      "loss": 3.0782,
+      "step": 10
+    },
+    {
+      "epoch": 0.01948368241597662,
+      "grad_norm": 0.5270306468009949,
+      "learning_rate": 0.0002,
+      "loss": 2.4644,
+      "step": 20
+    },
+    {
+      "epoch": 0.029225523623964928,
+      "grad_norm": 0.6826501488685608,
+      "learning_rate": 0.0002,
+      "loss": 2.2589,
+      "step": 30
+    },
+    {
+      "epoch": 0.03896736483195324,
+      "grad_norm": 0.5061377286911011,
+      "learning_rate": 0.0002,
+      "loss": 2.0141,
+      "step": 40
+    },
+    {
+      "epoch": 0.04870920603994155,
+      "grad_norm": 0.4300410747528076,
+      "learning_rate": 0.0002,
+      "loss": 1.9458,
+      "step": 50
+    },
+    {
+      "epoch": 0.058451047247929856,
+      "grad_norm": 0.5063319802284241,
+      "learning_rate": 0.0002,
+      "loss": 1.983,
+      "step": 60
+    },
+    {
+      "epoch": 0.06819288845591817,
+      "grad_norm": 0.49310117959976196,
+      "learning_rate": 0.0002,
+      "loss": 1.9799,
+      "step": 70
+    },
+    {
+      "epoch": 0.07793472966390648,
+      "grad_norm": 0.4676004648208618,
+      "learning_rate": 0.0002,
+      "loss": 1.9277,
+      "step": 80
+    },
+    {
+      "epoch": 0.08767657087189479,
+      "grad_norm": 0.41647228598594666,
+      "learning_rate": 0.0002,
+      "loss": 1.9147,
+      "step": 90
+    },
+    {
+      "epoch": 0.0974184120798831,
+      "grad_norm": 0.40217313170433044,
+      "learning_rate": 0.0002,
+      "loss": 1.8894,
+      "step": 100
+    },
+    {
+      "epoch": 0.1071602532878714,
+      "grad_norm": 0.4123637080192566,
+      "learning_rate": 0.0002,
+      "loss": 1.9099,
+      "step": 110
+    },
+    {
+      "epoch": 0.11690209449585971,
+      "grad_norm": 0.37414297461509705,
+      "learning_rate": 0.0002,
+      "loss": 1.8471,
+      "step": 120
+    },
+    {
+      "epoch": 0.12664393570384802,
+      "grad_norm": 0.3179326355457306,
+      "learning_rate": 0.0002,
+      "loss": 1.894,
+      "step": 130
+    },
+    {
+      "epoch": 0.13638577691183634,
+      "grad_norm": 0.3548192083835602,
+      "learning_rate": 0.0002,
+      "loss": 1.847,
+      "step": 140
+    },
+    {
+      "epoch": 0.14612761811982464,
+      "grad_norm": 0.3273540139198303,
+      "learning_rate": 0.0002,
+      "loss": 1.7919,
+      "step": 150
+    },
+    {
+      "epoch": 0.15586945932781296,
+      "grad_norm": 0.36500975489616394,
+      "learning_rate": 0.0002,
+      "loss": 1.8496,
+      "step": 160
+    },
+    {
+      "epoch": 0.16561130053580125,
+      "grad_norm": 0.4106619656085968,
+      "learning_rate": 0.0002,
+      "loss": 1.8473,
+      "step": 170
+    },
+    {
+      "epoch": 0.17535314174378958,
+      "grad_norm": 0.41361644864082336,
+      "learning_rate": 0.0002,
+      "loss": 1.841,
+      "step": 180
+    },
+    {
+      "epoch": 0.1850949829517779,
+      "grad_norm": 0.3608580231666565,
+      "learning_rate": 0.0002,
+      "loss": 1.8879,
+      "step": 190
+    },
+    {
+      "epoch": 0.1948368241597662,
+      "grad_norm": 0.4291760325431824,
+      "learning_rate": 0.0002,
+      "loss": 1.7717,
+      "step": 200
+    },
+    {
+      "epoch": 0.20457866536775451,
+      "grad_norm": 0.344184011220932,
+      "learning_rate": 0.0002,
+      "loss": 1.8437,
+      "step": 210
+    },
+    {
+      "epoch": 0.2143205065757428,
+      "grad_norm": 0.3834705650806427,
+      "learning_rate": 0.0002,
+      "loss": 1.8779,
+      "step": 220
+    },
+    {
+      "epoch": 0.22406234778373113,
+      "grad_norm": 0.3738210201263428,
+      "learning_rate": 0.0002,
+      "loss": 1.7533,
+      "step": 230
+    },
+    {
+      "epoch": 0.23380418899171942,
+      "grad_norm": 0.4306780695915222,
+      "learning_rate": 0.0002,
+      "loss": 1.824,
+      "step": 240
+    },
+    {
+      "epoch": 0.24354603019970775,
+      "grad_norm": 0.5066465139389038,
+      "learning_rate": 0.0002,
+      "loss": 1.8519,
+      "step": 250
+    },
+    {
+      "epoch": 0.25328787140769604,
+      "grad_norm": 0.34227681159973145,
+      "learning_rate": 0.0002,
+      "loss": 1.7402,
+      "step": 260
+    },
+    {
+      "epoch": 0.26302971261568436,
+      "grad_norm": 0.3346865475177765,
+      "learning_rate": 0.0002,
+      "loss": 1.8614,
+      "step": 270
+    },
+    {
+      "epoch": 0.2727715538236727,
+      "grad_norm": 0.3639362156391144,
+      "learning_rate": 0.0002,
+      "loss": 1.8502,
+      "step": 280
+    },
+    {
+      "epoch": 0.282513395031661,
+      "grad_norm": 0.33223700523376465,
+      "learning_rate": 0.0002,
+      "loss": 1.8428,
+      "step": 290
+    },
+    {
+      "epoch": 0.2922552362396493,
+      "grad_norm": 0.35176315903663635,
+      "learning_rate": 0.0002,
+      "loss": 1.821,
+      "step": 300
+    },
+    {
+      "epoch": 0.3019970774476376,
+      "grad_norm": 0.3581472635269165,
+      "learning_rate": 0.0002,
+      "loss": 1.7635,
+      "step": 310
+    },
+    {
+      "epoch": 0.3117389186556259,
+      "grad_norm": 0.35943421721458435,
+      "learning_rate": 0.0002,
+      "loss": 1.8262,
+      "step": 320
+    },
+    {
+      "epoch": 0.32148075986361424,
+      "grad_norm": 0.322051078081131,
+      "learning_rate": 0.0002,
+      "loss": 1.8167,
+      "step": 330
+    },
+    {
+      "epoch": 0.3312226010716025,
+      "grad_norm": 0.33904823660850525,
+      "learning_rate": 0.0002,
+      "loss": 1.8221,
+      "step": 340
+    },
+    {
+      "epoch": 0.34096444227959083,
+      "grad_norm": 0.39162731170654297,
+      "learning_rate": 0.0002,
+      "loss": 1.9159,
+      "step": 350
+    },
+    {
+      "epoch": 0.35070628348757915,
+      "grad_norm": 0.330624520778656,
+      "learning_rate": 0.0002,
+      "loss": 1.7966,
+      "step": 360
+    },
+    {
+      "epoch": 0.3604481246955675,
+      "grad_norm": 0.3793248236179352,
+      "learning_rate": 0.0002,
+      "loss": 1.8646,
+      "step": 370
+    },
+    {
+      "epoch": 0.3701899659035558,
+      "grad_norm": 0.3347395658493042,
+      "learning_rate": 0.0002,
+      "loss": 1.8038,
+      "step": 380
+    },
+    {
+      "epoch": 0.37993180711154406,
+      "grad_norm": 0.30527254939079285,
+      "learning_rate": 0.0002,
+      "loss": 1.9244,
+      "step": 390
+    },
+    {
+      "epoch": 0.3896736483195324,
+      "grad_norm": 0.3081390857696533,
+      "learning_rate": 0.0002,
+      "loss": 1.7982,
+      "step": 400
+    },
+    {
+      "epoch": 0.3994154895275207,
+      "grad_norm": 0.3742620050907135,
+      "learning_rate": 0.0002,
+      "loss": 1.8968,
+      "step": 410
+    },
+    {
+      "epoch": 0.40915733073550903,
+      "grad_norm": 0.4080568253993988,
+      "learning_rate": 0.0002,
+      "loss": 1.8095,
+      "step": 420
+    },
+    {
+      "epoch": 0.4188991719434973,
+      "grad_norm": 0.38034746050834656,
+      "learning_rate": 0.0002,
+      "loss": 1.8555,
+      "step": 430
+    },
+    {
+      "epoch": 0.4286410131514856,
+      "grad_norm": 0.34893402457237244,
+      "learning_rate": 0.0002,
+      "loss": 1.8494,
+      "step": 440
+    },
+    {
+      "epoch": 0.43838285435947394,
+      "grad_norm": 0.33285608887672424,
+      "learning_rate": 0.0002,
+      "loss": 1.8481,
+      "step": 450
+    },
+    {
+      "epoch": 0.44812469556746226,
+      "grad_norm": 0.4110095798969269,
+      "learning_rate": 0.0002,
+      "loss": 1.8466,
+      "step": 460
+    },
+    {
+      "epoch": 0.4578665367754506,
+      "grad_norm": 0.3658817410469055,
+      "learning_rate": 0.0002,
+      "loss": 1.7906,
+      "step": 470
+    },
+    {
+      "epoch": 0.46760837798343885,
+      "grad_norm": 0.31350770592689514,
+      "learning_rate": 0.0002,
+      "loss": 1.7589,
+      "step": 480
+    },
+    {
+      "epoch": 0.47735021919142717,
+      "grad_norm": 0.38827991485595703,
+      "learning_rate": 0.0002,
+      "loss": 1.7839,
+      "step": 490
+    },
+    {
+      "epoch": 0.4870920603994155,
+      "grad_norm": 0.3792393207550049,
+      "learning_rate": 0.0002,
+      "loss": 1.8224,
+      "step": 500
+    },
+    {
+      "epoch": 0.4968339016074038,
+      "grad_norm": 0.3004095256328583,
+      "learning_rate": 0.0002,
+      "loss": 1.8028,
+      "step": 510
+    },
+    {
+      "epoch": 0.5065757428153921,
+      "grad_norm": 0.3200063407421112,
+      "learning_rate": 0.0002,
+      "loss": 1.6899,
+      "step": 520
+    },
+    {
+      "epoch": 0.5163175840233805,
+      "grad_norm": 0.3206128478050232,
+      "learning_rate": 0.0002,
+      "loss": 1.8205,
+      "step": 530
+    },
+    {
+      "epoch": 0.5260594252313687,
+      "grad_norm": 0.30258631706237793,
+      "learning_rate": 0.0002,
+      "loss": 1.7725,
+      "step": 540
+    },
+    {
+      "epoch": 0.535801266439357,
+      "grad_norm": 0.28210392594337463,
+      "learning_rate": 0.0002,
+      "loss": 1.7791,
+      "step": 550
+    },
+    {
+      "epoch": 0.5455431076473454,
+      "grad_norm": 0.34854066371917725,
+      "learning_rate": 0.0002,
+      "loss": 1.8221,
+      "step": 560
+    },
+    {
+      "epoch": 0.5552849488553336,
+      "grad_norm": 0.31689873337745667,
+      "learning_rate": 0.0002,
+      "loss": 1.8331,
+      "step": 570
+    },
+    {
+      "epoch": 0.565026790063322,
+      "grad_norm": 0.31253790855407715,
+      "learning_rate": 0.0002,
+      "loss": 1.8311,
+      "step": 580
+    },
+    {
+      "epoch": 0.5747686312713103,
+      "grad_norm": 0.3229721188545227,
+      "learning_rate": 0.0002,
+      "loss": 1.7035,
+      "step": 590
+    },
+    {
+      "epoch": 0.5845104724792985,
+      "grad_norm": 0.3723772466182709,
+      "learning_rate": 0.0002,
+      "loss": 1.766,
+      "step": 600
+    },
+    {
+      "epoch": 0.5942523136872869,
+      "grad_norm": 0.345798522233963,
+      "learning_rate": 0.0002,
+      "loss": 1.8357,
+      "step": 610
+    },
+    {
+      "epoch": 0.6039941548952752,
+      "grad_norm": 0.3440598249435425,
+      "learning_rate": 0.0002,
+      "loss": 1.7266,
+      "step": 620
+    },
+    {
+      "epoch": 0.6137359961032636,
+      "grad_norm": 0.3406416177749634,
+      "learning_rate": 0.0002,
+      "loss": 1.8307,
+      "step": 630
+    },
+    {
+      "epoch": 0.6234778373112518,
+      "grad_norm": 0.3218357264995575,
+      "learning_rate": 0.0002,
+      "loss": 1.8103,
+      "step": 640
+    },
+    {
+      "epoch": 0.6332196785192401,
+      "grad_norm": 0.45319172739982605,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 650
+    },
+    {
+      "epoch": 0.6429615197272285,
+      "grad_norm": 0.2787110507488251,
+      "learning_rate": 0.0002,
+      "loss": 1.8674,
+      "step": 660
+    },
+    {
+      "epoch": 0.6527033609352167,
+      "grad_norm": 0.3064707815647125,
+      "learning_rate": 0.0002,
+      "loss": 1.8426,
+      "step": 670
+    },
+    {
+      "epoch": 0.662445202143205,
+      "grad_norm": 0.2940629720687866,
+      "learning_rate": 0.0002,
+      "loss": 1.846,
+      "step": 680
+    },
+    {
+      "epoch": 0.6721870433511934,
+      "grad_norm": 0.31695225834846497,
+      "learning_rate": 0.0002,
+      "loss": 1.7865,
+      "step": 690
+    },
+    {
+      "epoch": 0.6819288845591817,
+      "grad_norm": 0.29589611291885376,
+      "learning_rate": 0.0002,
+      "loss": 1.8449,
+      "step": 700
+    },
+    {
+      "epoch": 0.69167072576717,
+      "grad_norm": 0.3062121570110321,
+      "learning_rate": 0.0002,
+      "loss": 1.7828,
+      "step": 710
+    },
+    {
+      "epoch": 0.7014125669751583,
+      "grad_norm": 0.3315656781196594,
+      "learning_rate": 0.0002,
+      "loss": 1.8108,
+      "step": 720
+    },
+    {
+      "epoch": 0.7111544081831466,
+      "grad_norm": 0.30353930592536926,
+      "learning_rate": 0.0002,
+      "loss": 1.8056,
+      "step": 730
+    },
+    {
+      "epoch": 0.720896249391135,
+      "grad_norm": 0.28360483050346375,
+      "learning_rate": 0.0002,
+      "loss": 1.7682,
+      "step": 740
+    },
+    {
+      "epoch": 0.7306380905991232,
+      "grad_norm": 0.3362562656402588,
+      "learning_rate": 0.0002,
+      "loss": 1.7386,
+      "step": 750
+    },
+    {
+      "epoch": 0.7403799318071116,
+      "grad_norm": 0.40434667468070984,
+      "learning_rate": 0.0002,
+      "loss": 1.7607,
+      "step": 760
+    },
+    {
+      "epoch": 0.7501217730150999,
+      "grad_norm": 0.2930425703525543,
+      "learning_rate": 0.0002,
+      "loss": 1.8374,
+      "step": 770
+    },
+    {
+      "epoch": 0.7598636142230881,
+      "grad_norm": 0.30177003145217896,
+      "learning_rate": 0.0002,
+      "loss": 1.8216,
+      "step": 780
+    },
+    {
+      "epoch": 0.7696054554310765,
+      "grad_norm": 0.2784474790096283,
+      "learning_rate": 0.0002,
+      "loss": 1.8081,
+      "step": 790
+    },
+    {
+      "epoch": 0.7793472966390648,
+      "grad_norm": 0.35849854350090027,
+      "learning_rate": 0.0002,
+      "loss": 1.7953,
+      "step": 800
+    },
+    {
+      "epoch": 0.7890891378470531,
+      "grad_norm": 0.27329114079475403,
+      "learning_rate": 0.0002,
+      "loss": 1.7896,
+      "step": 810
+    },
+    {
+      "epoch": 0.7988309790550414,
+      "grad_norm": 0.33331671357154846,
+      "learning_rate": 0.0002,
+      "loss": 1.7633,
+      "step": 820
+    },
+    {
+      "epoch": 0.8085728202630297,
+      "grad_norm": 0.28727295994758606,
+      "learning_rate": 0.0002,
+      "loss": 1.7508,
+      "step": 830
+    },
+    {
+      "epoch": 0.8183146614710181,
+      "grad_norm": 0.31391268968582153,
+      "learning_rate": 0.0002,
+      "loss": 1.7541,
+      "step": 840
+    },
+    {
+      "epoch": 0.8280565026790063,
+      "grad_norm": 0.3303709030151367,
+      "learning_rate": 0.0002,
+      "loss": 1.793,
+      "step": 850
+    },
+    {
+      "epoch": 0.8377983438869946,
+      "grad_norm": 0.33772537112236023,
+      "learning_rate": 0.0002,
+      "loss": 1.7479,
+      "step": 860
+    },
+    {
+      "epoch": 0.847540185094983,
+      "grad_norm": 0.32876333594322205,
+      "learning_rate": 0.0002,
+      "loss": 1.7138,
+      "step": 870
+    },
+    {
+      "epoch": 0.8572820263029712,
+      "grad_norm": 0.28444716334342957,
+      "learning_rate": 0.0002,
+      "loss": 1.7832,
+      "step": 880
+    },
+    {
+      "epoch": 0.8670238675109596,
+      "grad_norm": 0.3070019483566284,
+      "learning_rate": 0.0002,
+      "loss": 1.7077,
+      "step": 890
+    },
+    {
+      "epoch": 0.8767657087189479,
+      "grad_norm": 0.29484760761260986,
+      "learning_rate": 0.0002,
+      "loss": 1.7699,
+      "step": 900
+    },
+    {
+      "epoch": 0.8865075499269361,
+      "grad_norm": 0.32373034954071045,
+      "learning_rate": 0.0002,
+      "loss": 1.7211,
+      "step": 910
+    },
+    {
+      "epoch": 0.8962493911349245,
+      "grad_norm": 0.3229396939277649,
+      "learning_rate": 0.0002,
+      "loss": 1.7799,
+      "step": 920
+    },
+    {
+      "epoch": 0.9059912323429128,
+      "grad_norm": 0.33151453733444214,
+      "learning_rate": 0.0002,
+      "loss": 1.8226,
+      "step": 930
+    },
+    {
+      "epoch": 0.9157330735509012,
+      "grad_norm": 0.32037460803985596,
+      "learning_rate": 0.0002,
+      "loss": 1.8339,
+      "step": 940
+    },
+    {
+      "epoch": 0.9254749147588894,
+      "grad_norm": 0.31283533573150635,
+      "learning_rate": 0.0002,
+      "loss": 1.822,
+      "step": 950
+    },
+    {
+      "epoch": 0.9352167559668777,
+      "grad_norm": 0.27984118461608887,
+      "learning_rate": 0.0002,
+      "loss": 1.8233,
+      "step": 960
+    },
+    {
+      "epoch": 0.9449585971748661,
+      "grad_norm": 0.316500186920166,
+      "learning_rate": 0.0002,
+      "loss": 1.7755,
+      "step": 970
+    },
+    {
+      "epoch": 0.9547004383828543,
+      "grad_norm": 0.33708682656288147,
+      "learning_rate": 0.0002,
+      "loss": 1.8032,
+      "step": 980
+    },
+    {
+      "epoch": 0.9644422795908427,
+      "grad_norm": 0.31026017665863037,
+      "learning_rate": 0.0002,
+      "loss": 1.8863,
+      "step": 990
+    },
+    {
+      "epoch": 0.974184120798831,
+      "grad_norm": 0.30874672532081604,
+      "learning_rate": 0.0002,
+      "loss": 1.8458,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9839259620068193,
+      "grad_norm": 0.3257741630077362,
+      "learning_rate": 0.0002,
+      "loss": 1.7975,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9936678032148076,
+      "grad_norm": 0.2865653932094574,
+      "learning_rate": 0.0002,
+      "loss": 1.7936,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9995129079396006,
+      "eval_loss": 1.8103164434432983,
+      "eval_runtime": 56.3917,
+      "eval_samples_per_second": 8.991,
+      "eval_steps_per_second": 1.135,
+      "step": 1026
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 8208,
+  "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": 5.272488488730624e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e8ef519de92b2db62801feef14bb344bb8aa4b619a17c82a1cf2d14a9cfb5a
+size 5560

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-2053/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-2053/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-2053/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a48a7bbe9dd3ba0a69f9915246bc8c09d59eb48fa97982bb17ecae6a0e4574
+size 143153376

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-2053/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3561b40d2f24fb85b054ab9b43e627a22934108af1a380436def56674ca11441
+size 72886650

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-2053/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceaa5adcb527c2f297d40f7bfac956b3d7389765453573b67579e3b48bff060c
+size 14244

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-2053/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ebded2a9aa7f2379ce88e70901f21f9672c01c5b0e90fa087e6a51f5eb1d78
+size 1064

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-2053/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-2053/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-2053/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-2053/tokenizer_config.json

@@ -0,0 +1,2013 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-2053/trainer_state.json

@@ -0,0 +1,1484 @@
+{
+  "best_metric": 1.8103164434432983,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026",
+  "epoch": 2.0,
+  "eval_steps": 10,
+  "global_step": 2053,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00974184120798831,
+      "grad_norm": 0.6537588834762573,
+      "learning_rate": 0.0002,
+      "loss": 3.0782,
+      "step": 10
+    },
+    {
+      "epoch": 0.01948368241597662,
+      "grad_norm": 0.5270306468009949,
+      "learning_rate": 0.0002,
+      "loss": 2.4644,
+      "step": 20
+    },
+    {
+      "epoch": 0.029225523623964928,
+      "grad_norm": 0.6826501488685608,
+      "learning_rate": 0.0002,
+      "loss": 2.2589,
+      "step": 30
+    },
+    {
+      "epoch": 0.03896736483195324,
+      "grad_norm": 0.5061377286911011,
+      "learning_rate": 0.0002,
+      "loss": 2.0141,
+      "step": 40
+    },
+    {
+      "epoch": 0.04870920603994155,
+      "grad_norm": 0.4300410747528076,
+      "learning_rate": 0.0002,
+      "loss": 1.9458,
+      "step": 50
+    },
+    {
+      "epoch": 0.058451047247929856,
+      "grad_norm": 0.5063319802284241,
+      "learning_rate": 0.0002,
+      "loss": 1.983,
+      "step": 60
+    },
+    {
+      "epoch": 0.06819288845591817,
+      "grad_norm": 0.49310117959976196,
+      "learning_rate": 0.0002,
+      "loss": 1.9799,
+      "step": 70
+    },
+    {
+      "epoch": 0.07793472966390648,
+      "grad_norm": 0.4676004648208618,
+      "learning_rate": 0.0002,
+      "loss": 1.9277,
+      "step": 80
+    },
+    {
+      "epoch": 0.08767657087189479,
+      "grad_norm": 0.41647228598594666,
+      "learning_rate": 0.0002,
+      "loss": 1.9147,
+      "step": 90
+    },
+    {
+      "epoch": 0.0974184120798831,
+      "grad_norm": 0.40217313170433044,
+      "learning_rate": 0.0002,
+      "loss": 1.8894,
+      "step": 100
+    },
+    {
+      "epoch": 0.1071602532878714,
+      "grad_norm": 0.4123637080192566,
+      "learning_rate": 0.0002,
+      "loss": 1.9099,
+      "step": 110
+    },
+    {
+      "epoch": 0.11690209449585971,
+      "grad_norm": 0.37414297461509705,
+      "learning_rate": 0.0002,
+      "loss": 1.8471,
+      "step": 120
+    },
+    {
+      "epoch": 0.12664393570384802,
+      "grad_norm": 0.3179326355457306,
+      "learning_rate": 0.0002,
+      "loss": 1.894,
+      "step": 130
+    },
+    {
+      "epoch": 0.13638577691183634,
+      "grad_norm": 0.3548192083835602,
+      "learning_rate": 0.0002,
+      "loss": 1.847,
+      "step": 140
+    },
+    {
+      "epoch": 0.14612761811982464,
+      "grad_norm": 0.3273540139198303,
+      "learning_rate": 0.0002,
+      "loss": 1.7919,
+      "step": 150
+    },
+    {
+      "epoch": 0.15586945932781296,
+      "grad_norm": 0.36500975489616394,
+      "learning_rate": 0.0002,
+      "loss": 1.8496,
+      "step": 160
+    },
+    {
+      "epoch": 0.16561130053580125,
+      "grad_norm": 0.4106619656085968,
+      "learning_rate": 0.0002,
+      "loss": 1.8473,
+      "step": 170
+    },
+    {
+      "epoch": 0.17535314174378958,
+      "grad_norm": 0.41361644864082336,
+      "learning_rate": 0.0002,
+      "loss": 1.841,
+      "step": 180
+    },
+    {
+      "epoch": 0.1850949829517779,
+      "grad_norm": 0.3608580231666565,
+      "learning_rate": 0.0002,
+      "loss": 1.8879,
+      "step": 190
+    },
+    {
+      "epoch": 0.1948368241597662,
+      "grad_norm": 0.4291760325431824,
+      "learning_rate": 0.0002,
+      "loss": 1.7717,
+      "step": 200
+    },
+    {
+      "epoch": 0.20457866536775451,
+      "grad_norm": 0.344184011220932,
+      "learning_rate": 0.0002,
+      "loss": 1.8437,
+      "step": 210
+    },
+    {
+      "epoch": 0.2143205065757428,
+      "grad_norm": 0.3834705650806427,
+      "learning_rate": 0.0002,
+      "loss": 1.8779,
+      "step": 220
+    },
+    {
+      "epoch": 0.22406234778373113,
+      "grad_norm": 0.3738210201263428,
+      "learning_rate": 0.0002,
+      "loss": 1.7533,
+      "step": 230
+    },
+    {
+      "epoch": 0.23380418899171942,
+      "grad_norm": 0.4306780695915222,
+      "learning_rate": 0.0002,
+      "loss": 1.824,
+      "step": 240
+    },
+    {
+      "epoch": 0.24354603019970775,
+      "grad_norm": 0.5066465139389038,
+      "learning_rate": 0.0002,
+      "loss": 1.8519,
+      "step": 250
+    },
+    {
+      "epoch": 0.25328787140769604,
+      "grad_norm": 0.34227681159973145,
+      "learning_rate": 0.0002,
+      "loss": 1.7402,
+      "step": 260
+    },
+    {
+      "epoch": 0.26302971261568436,
+      "grad_norm": 0.3346865475177765,
+      "learning_rate": 0.0002,
+      "loss": 1.8614,
+      "step": 270
+    },
+    {
+      "epoch": 0.2727715538236727,
+      "grad_norm": 0.3639362156391144,
+      "learning_rate": 0.0002,
+      "loss": 1.8502,
+      "step": 280
+    },
+    {
+      "epoch": 0.282513395031661,
+      "grad_norm": 0.33223700523376465,
+      "learning_rate": 0.0002,
+      "loss": 1.8428,
+      "step": 290
+    },
+    {
+      "epoch": 0.2922552362396493,
+      "grad_norm": 0.35176315903663635,
+      "learning_rate": 0.0002,
+      "loss": 1.821,
+      "step": 300
+    },
+    {
+      "epoch": 0.3019970774476376,
+      "grad_norm": 0.3581472635269165,
+      "learning_rate": 0.0002,
+      "loss": 1.7635,
+      "step": 310
+    },
+    {
+      "epoch": 0.3117389186556259,
+      "grad_norm": 0.35943421721458435,
+      "learning_rate": 0.0002,
+      "loss": 1.8262,
+      "step": 320
+    },
+    {
+      "epoch": 0.32148075986361424,
+      "grad_norm": 0.322051078081131,
+      "learning_rate": 0.0002,
+      "loss": 1.8167,
+      "step": 330
+    },
+    {
+      "epoch": 0.3312226010716025,
+      "grad_norm": 0.33904823660850525,
+      "learning_rate": 0.0002,
+      "loss": 1.8221,
+      "step": 340
+    },
+    {
+      "epoch": 0.34096444227959083,
+      "grad_norm": 0.39162731170654297,
+      "learning_rate": 0.0002,
+      "loss": 1.9159,
+      "step": 350
+    },
+    {
+      "epoch": 0.35070628348757915,
+      "grad_norm": 0.330624520778656,
+      "learning_rate": 0.0002,
+      "loss": 1.7966,
+      "step": 360
+    },
+    {
+      "epoch": 0.3604481246955675,
+      "grad_norm": 0.3793248236179352,
+      "learning_rate": 0.0002,
+      "loss": 1.8646,
+      "step": 370
+    },
+    {
+      "epoch": 0.3701899659035558,
+      "grad_norm": 0.3347395658493042,
+      "learning_rate": 0.0002,
+      "loss": 1.8038,
+      "step": 380
+    },
+    {
+      "epoch": 0.37993180711154406,
+      "grad_norm": 0.30527254939079285,
+      "learning_rate": 0.0002,
+      "loss": 1.9244,
+      "step": 390
+    },
+    {
+      "epoch": 0.3896736483195324,
+      "grad_norm": 0.3081390857696533,
+      "learning_rate": 0.0002,
+      "loss": 1.7982,
+      "step": 400
+    },
+    {
+      "epoch": 0.3994154895275207,
+      "grad_norm": 0.3742620050907135,
+      "learning_rate": 0.0002,
+      "loss": 1.8968,
+      "step": 410
+    },
+    {
+      "epoch": 0.40915733073550903,
+      "grad_norm": 0.4080568253993988,
+      "learning_rate": 0.0002,
+      "loss": 1.8095,
+      "step": 420
+    },
+    {
+      "epoch": 0.4188991719434973,
+      "grad_norm": 0.38034746050834656,
+      "learning_rate": 0.0002,
+      "loss": 1.8555,
+      "step": 430
+    },
+    {
+      "epoch": 0.4286410131514856,
+      "grad_norm": 0.34893402457237244,
+      "learning_rate": 0.0002,
+      "loss": 1.8494,
+      "step": 440
+    },
+    {
+      "epoch": 0.43838285435947394,
+      "grad_norm": 0.33285608887672424,
+      "learning_rate": 0.0002,
+      "loss": 1.8481,
+      "step": 450
+    },
+    {
+      "epoch": 0.44812469556746226,
+      "grad_norm": 0.4110095798969269,
+      "learning_rate": 0.0002,
+      "loss": 1.8466,
+      "step": 460
+    },
+    {
+      "epoch": 0.4578665367754506,
+      "grad_norm": 0.3658817410469055,
+      "learning_rate": 0.0002,
+      "loss": 1.7906,
+      "step": 470
+    },
+    {
+      "epoch": 0.46760837798343885,
+      "grad_norm": 0.31350770592689514,
+      "learning_rate": 0.0002,
+      "loss": 1.7589,
+      "step": 480
+    },
+    {
+      "epoch": 0.47735021919142717,
+      "grad_norm": 0.38827991485595703,
+      "learning_rate": 0.0002,
+      "loss": 1.7839,
+      "step": 490
+    },
+    {
+      "epoch": 0.4870920603994155,
+      "grad_norm": 0.3792393207550049,
+      "learning_rate": 0.0002,
+      "loss": 1.8224,
+      "step": 500
+    },
+    {
+      "epoch": 0.4968339016074038,
+      "grad_norm": 0.3004095256328583,
+      "learning_rate": 0.0002,
+      "loss": 1.8028,
+      "step": 510
+    },
+    {
+      "epoch": 0.5065757428153921,
+      "grad_norm": 0.3200063407421112,
+      "learning_rate": 0.0002,
+      "loss": 1.6899,
+      "step": 520
+    },
+    {
+      "epoch": 0.5163175840233805,
+      "grad_norm": 0.3206128478050232,
+      "learning_rate": 0.0002,
+      "loss": 1.8205,
+      "step": 530
+    },
+    {
+      "epoch": 0.5260594252313687,
+      "grad_norm": 0.30258631706237793,
+      "learning_rate": 0.0002,
+      "loss": 1.7725,
+      "step": 540
+    },
+    {
+      "epoch": 0.535801266439357,
+      "grad_norm": 0.28210392594337463,
+      "learning_rate": 0.0002,
+      "loss": 1.7791,
+      "step": 550
+    },
+    {
+      "epoch": 0.5455431076473454,
+      "grad_norm": 0.34854066371917725,
+      "learning_rate": 0.0002,
+      "loss": 1.8221,
+      "step": 560
+    },
+    {
+      "epoch": 0.5552849488553336,
+      "grad_norm": 0.31689873337745667,
+      "learning_rate": 0.0002,
+      "loss": 1.8331,
+      "step": 570
+    },
+    {
+      "epoch": 0.565026790063322,
+      "grad_norm": 0.31253790855407715,
+      "learning_rate": 0.0002,
+      "loss": 1.8311,
+      "step": 580
+    },
+    {
+      "epoch": 0.5747686312713103,
+      "grad_norm": 0.3229721188545227,
+      "learning_rate": 0.0002,
+      "loss": 1.7035,
+      "step": 590
+    },
+    {
+      "epoch": 0.5845104724792985,
+      "grad_norm": 0.3723772466182709,
+      "learning_rate": 0.0002,
+      "loss": 1.766,
+      "step": 600
+    },
+    {
+      "epoch": 0.5942523136872869,
+      "grad_norm": 0.345798522233963,
+      "learning_rate": 0.0002,
+      "loss": 1.8357,
+      "step": 610
+    },
+    {
+      "epoch": 0.6039941548952752,
+      "grad_norm": 0.3440598249435425,
+      "learning_rate": 0.0002,
+      "loss": 1.7266,
+      "step": 620
+    },
+    {
+      "epoch": 0.6137359961032636,
+      "grad_norm": 0.3406416177749634,
+      "learning_rate": 0.0002,
+      "loss": 1.8307,
+      "step": 630
+    },
+    {
+      "epoch": 0.6234778373112518,
+      "grad_norm": 0.3218357264995575,
+      "learning_rate": 0.0002,
+      "loss": 1.8103,
+      "step": 640
+    },
+    {
+      "epoch": 0.6332196785192401,
+      "grad_norm": 0.45319172739982605,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 650
+    },
+    {
+      "epoch": 0.6429615197272285,
+      "grad_norm": 0.2787110507488251,
+      "learning_rate": 0.0002,
+      "loss": 1.8674,
+      "step": 660
+    },
+    {
+      "epoch": 0.6527033609352167,
+      "grad_norm": 0.3064707815647125,
+      "learning_rate": 0.0002,
+      "loss": 1.8426,
+      "step": 670
+    },
+    {
+      "epoch": 0.662445202143205,
+      "grad_norm": 0.2940629720687866,
+      "learning_rate": 0.0002,
+      "loss": 1.846,
+      "step": 680
+    },
+    {
+      "epoch": 0.6721870433511934,
+      "grad_norm": 0.31695225834846497,
+      "learning_rate": 0.0002,
+      "loss": 1.7865,
+      "step": 690
+    },
+    {
+      "epoch": 0.6819288845591817,
+      "grad_norm": 0.29589611291885376,
+      "learning_rate": 0.0002,
+      "loss": 1.8449,
+      "step": 700
+    },
+    {
+      "epoch": 0.69167072576717,
+      "grad_norm": 0.3062121570110321,
+      "learning_rate": 0.0002,
+      "loss": 1.7828,
+      "step": 710
+    },
+    {
+      "epoch": 0.7014125669751583,
+      "grad_norm": 0.3315656781196594,
+      "learning_rate": 0.0002,
+      "loss": 1.8108,
+      "step": 720
+    },
+    {
+      "epoch": 0.7111544081831466,
+      "grad_norm": 0.30353930592536926,
+      "learning_rate": 0.0002,
+      "loss": 1.8056,
+      "step": 730
+    },
+    {
+      "epoch": 0.720896249391135,
+      "grad_norm": 0.28360483050346375,
+      "learning_rate": 0.0002,
+      "loss": 1.7682,
+      "step": 740
+    },
+    {
+      "epoch": 0.7306380905991232,
+      "grad_norm": 0.3362562656402588,
+      "learning_rate": 0.0002,
+      "loss": 1.7386,
+      "step": 750
+    },
+    {
+      "epoch": 0.7403799318071116,
+      "grad_norm": 0.40434667468070984,
+      "learning_rate": 0.0002,
+      "loss": 1.7607,
+      "step": 760
+    },
+    {
+      "epoch": 0.7501217730150999,
+      "grad_norm": 0.2930425703525543,
+      "learning_rate": 0.0002,
+      "loss": 1.8374,
+      "step": 770
+    },
+    {
+      "epoch": 0.7598636142230881,
+      "grad_norm": 0.30177003145217896,
+      "learning_rate": 0.0002,
+      "loss": 1.8216,
+      "step": 780
+    },
+    {
+      "epoch": 0.7696054554310765,
+      "grad_norm": 0.2784474790096283,
+      "learning_rate": 0.0002,
+      "loss": 1.8081,
+      "step": 790
+    },
+    {
+      "epoch": 0.7793472966390648,
+      "grad_norm": 0.35849854350090027,
+      "learning_rate": 0.0002,
+      "loss": 1.7953,
+      "step": 800
+    },
+    {
+      "epoch": 0.7890891378470531,
+      "grad_norm": 0.27329114079475403,
+      "learning_rate": 0.0002,
+      "loss": 1.7896,
+      "step": 810
+    },
+    {
+      "epoch": 0.7988309790550414,
+      "grad_norm": 0.33331671357154846,
+      "learning_rate": 0.0002,
+      "loss": 1.7633,
+      "step": 820
+    },
+    {
+      "epoch": 0.8085728202630297,
+      "grad_norm": 0.28727295994758606,
+      "learning_rate": 0.0002,
+      "loss": 1.7508,
+      "step": 830
+    },
+    {
+      "epoch": 0.8183146614710181,
+      "grad_norm": 0.31391268968582153,
+      "learning_rate": 0.0002,
+      "loss": 1.7541,
+      "step": 840
+    },
+    {
+      "epoch": 0.8280565026790063,
+      "grad_norm": 0.3303709030151367,
+      "learning_rate": 0.0002,
+      "loss": 1.793,
+      "step": 850
+    },
+    {
+      "epoch": 0.8377983438869946,
+      "grad_norm": 0.33772537112236023,
+      "learning_rate": 0.0002,
+      "loss": 1.7479,
+      "step": 860
+    },
+    {
+      "epoch": 0.847540185094983,
+      "grad_norm": 0.32876333594322205,
+      "learning_rate": 0.0002,
+      "loss": 1.7138,
+      "step": 870
+    },
+    {
+      "epoch": 0.8572820263029712,
+      "grad_norm": 0.28444716334342957,
+      "learning_rate": 0.0002,
+      "loss": 1.7832,
+      "step": 880
+    },
+    {
+      "epoch": 0.8670238675109596,
+      "grad_norm": 0.3070019483566284,
+      "learning_rate": 0.0002,
+      "loss": 1.7077,
+      "step": 890
+    },
+    {
+      "epoch": 0.8767657087189479,
+      "grad_norm": 0.29484760761260986,
+      "learning_rate": 0.0002,
+      "loss": 1.7699,
+      "step": 900
+    },
+    {
+      "epoch": 0.8865075499269361,
+      "grad_norm": 0.32373034954071045,
+      "learning_rate": 0.0002,
+      "loss": 1.7211,
+      "step": 910
+    },
+    {
+      "epoch": 0.8962493911349245,
+      "grad_norm": 0.3229396939277649,
+      "learning_rate": 0.0002,
+      "loss": 1.7799,
+      "step": 920
+    },
+    {
+      "epoch": 0.9059912323429128,
+      "grad_norm": 0.33151453733444214,
+      "learning_rate": 0.0002,
+      "loss": 1.8226,
+      "step": 930
+    },
+    {
+      "epoch": 0.9157330735509012,
+      "grad_norm": 0.32037460803985596,
+      "learning_rate": 0.0002,
+      "loss": 1.8339,
+      "step": 940
+    },
+    {
+      "epoch": 0.9254749147588894,
+      "grad_norm": 0.31283533573150635,
+      "learning_rate": 0.0002,
+      "loss": 1.822,
+      "step": 950
+    },
+    {
+      "epoch": 0.9352167559668777,
+      "grad_norm": 0.27984118461608887,
+      "learning_rate": 0.0002,
+      "loss": 1.8233,
+      "step": 960
+    },
+    {
+      "epoch": 0.9449585971748661,
+      "grad_norm": 0.316500186920166,
+      "learning_rate": 0.0002,
+      "loss": 1.7755,
+      "step": 970
+    },
+    {
+      "epoch": 0.9547004383828543,
+      "grad_norm": 0.33708682656288147,
+      "learning_rate": 0.0002,
+      "loss": 1.8032,
+      "step": 980
+    },
+    {
+      "epoch": 0.9644422795908427,
+      "grad_norm": 0.31026017665863037,
+      "learning_rate": 0.0002,
+      "loss": 1.8863,
+      "step": 990
+    },
+    {
+      "epoch": 0.974184120798831,
+      "grad_norm": 0.30874672532081604,
+      "learning_rate": 0.0002,
+      "loss": 1.8458,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9839259620068193,
+      "grad_norm": 0.3257741630077362,
+      "learning_rate": 0.0002,
+      "loss": 1.7975,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9936678032148076,
+      "grad_norm": 0.2865653932094574,
+      "learning_rate": 0.0002,
+      "loss": 1.7936,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9995129079396006,
+      "eval_loss": 1.8103164434432983,
+      "eval_runtime": 56.3917,
+      "eval_samples_per_second": 8.991,
+      "eval_steps_per_second": 1.135,
+      "step": 1026
+    },
+    {
+      "epoch": 1.003409644422796,
+      "grad_norm": 0.2860608398914337,
+      "learning_rate": 0.0002,
+      "loss": 1.7013,
+      "step": 1030
+    },
+    {
+      "epoch": 1.0131514856307842,
+      "grad_norm": 0.3156210780143738,
+      "learning_rate": 0.0002,
+      "loss": 1.7521,
+      "step": 1040
+    },
+    {
+      "epoch": 1.0228933268387725,
+      "grad_norm": 0.26126575469970703,
+      "learning_rate": 0.0002,
+      "loss": 1.6182,
+      "step": 1050
+    },
+    {
+      "epoch": 1.032635168046761,
+      "grad_norm": 0.3019633889198303,
+      "learning_rate": 0.0002,
+      "loss": 1.7546,
+      "step": 1060
+    },
+    {
+      "epoch": 1.042377009254749,
+      "grad_norm": 0.534140944480896,
+      "learning_rate": 0.0002,
+      "loss": 1.7096,
+      "step": 1070
+    },
+    {
+      "epoch": 1.0521188504627375,
+      "grad_norm": 0.311872661113739,
+      "learning_rate": 0.0002,
+      "loss": 1.664,
+      "step": 1080
+    },
+    {
+      "epoch": 1.0618606916707258,
+      "grad_norm": 0.3276001513004303,
+      "learning_rate": 0.0002,
+      "loss": 1.7056,
+      "step": 1090
+    },
+    {
+      "epoch": 1.071602532878714,
+      "grad_norm": 0.35227468609809875,
+      "learning_rate": 0.0002,
+      "loss": 1.7943,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0813443740867024,
+      "grad_norm": 0.3597564995288849,
+      "learning_rate": 0.0002,
+      "loss": 1.7079,
+      "step": 1110
+    },
+    {
+      "epoch": 1.0910862152946907,
+      "grad_norm": 0.3547225296497345,
+      "learning_rate": 0.0002,
+      "loss": 1.7635,
+      "step": 1120
+    },
+    {
+      "epoch": 1.100828056502679,
+      "grad_norm": 0.3399786353111267,
+      "learning_rate": 0.0002,
+      "loss": 1.6859,
+      "step": 1130
+    },
+    {
+      "epoch": 1.1105698977106673,
+      "grad_norm": 0.3309086263179779,
+      "learning_rate": 0.0002,
+      "loss": 1.7478,
+      "step": 1140
+    },
+    {
+      "epoch": 1.1203117389186557,
+      "grad_norm": 0.39330706000328064,
+      "learning_rate": 0.0002,
+      "loss": 1.7372,
+      "step": 1150
+    },
+    {
+      "epoch": 1.130053580126644,
+      "grad_norm": 0.3628021776676178,
+      "learning_rate": 0.0002,
+      "loss": 1.6236,
+      "step": 1160
+    },
+    {
+      "epoch": 1.1397954213346322,
+      "grad_norm": 0.32995012402534485,
+      "learning_rate": 0.0002,
+      "loss": 1.8022,
+      "step": 1170
+    },
+    {
+      "epoch": 1.1495372625426206,
+      "grad_norm": 0.36292821168899536,
+      "learning_rate": 0.0002,
+      "loss": 1.636,
+      "step": 1180
+    },
+    {
+      "epoch": 1.159279103750609,
+      "grad_norm": 0.3470092713832855,
+      "learning_rate": 0.0002,
+      "loss": 1.7156,
+      "step": 1190
+    },
+    {
+      "epoch": 1.169020944958597,
+      "grad_norm": 0.3496156334877014,
+      "learning_rate": 0.0002,
+      "loss": 1.7001,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1787627861665855,
+      "grad_norm": 0.3442084789276123,
+      "learning_rate": 0.0002,
+      "loss": 1.716,
+      "step": 1210
+    },
+    {
+      "epoch": 1.1885046273745739,
+      "grad_norm": 0.34983909130096436,
+      "learning_rate": 0.0002,
+      "loss": 1.7763,
+      "step": 1220
+    },
+    {
+      "epoch": 1.198246468582562,
+      "grad_norm": 0.36505937576293945,
+      "learning_rate": 0.0002,
+      "loss": 1.6964,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2079883097905504,
+      "grad_norm": 0.31624770164489746,
+      "learning_rate": 0.0002,
+      "loss": 1.7382,
+      "step": 1240
+    },
+    {
+      "epoch": 1.2177301509985388,
+      "grad_norm": 0.3528020679950714,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 1250
+    },
+    {
+      "epoch": 1.2274719922065271,
+      "grad_norm": 0.29294025897979736,
+      "learning_rate": 0.0002,
+      "loss": 1.752,
+      "step": 1260
+    },
+    {
+      "epoch": 1.2372138334145153,
+      "grad_norm": 0.35048434138298035,
+      "learning_rate": 0.0002,
+      "loss": 1.719,
+      "step": 1270
+    },
+    {
+      "epoch": 1.2469556746225037,
+      "grad_norm": 0.35224461555480957,
+      "learning_rate": 0.0002,
+      "loss": 1.6806,
+      "step": 1280
+    },
+    {
+      "epoch": 1.256697515830492,
+      "grad_norm": 0.4041554629802704,
+      "learning_rate": 0.0002,
+      "loss": 1.6836,
+      "step": 1290
+    },
+    {
+      "epoch": 1.2664393570384802,
+      "grad_norm": 0.3447791039943695,
+      "learning_rate": 0.0002,
+      "loss": 1.6999,
+      "step": 1300
+    },
+    {
+      "epoch": 1.2761811982464686,
+      "grad_norm": 0.3315333425998688,
+      "learning_rate": 0.0002,
+      "loss": 1.7601,
+      "step": 1310
+    },
+    {
+      "epoch": 1.285923039454457,
+      "grad_norm": 0.3587741255760193,
+      "learning_rate": 0.0002,
+      "loss": 1.7325,
+      "step": 1320
+    },
+    {
+      "epoch": 1.2956648806624451,
+      "grad_norm": 0.3704394996166229,
+      "learning_rate": 0.0002,
+      "loss": 1.6707,
+      "step": 1330
+    },
+    {
+      "epoch": 1.3054067218704335,
+      "grad_norm": 0.38131803274154663,
+      "learning_rate": 0.0002,
+      "loss": 1.7374,
+      "step": 1340
+    },
+    {
+      "epoch": 1.3151485630784219,
+      "grad_norm": 0.36109617352485657,
+      "learning_rate": 0.0002,
+      "loss": 1.5956,
+      "step": 1350
+    },
+    {
+      "epoch": 1.32489040428641,
+      "grad_norm": 0.37283554673194885,
+      "learning_rate": 0.0002,
+      "loss": 1.682,
+      "step": 1360
+    },
+    {
+      "epoch": 1.3346322454943984,
+      "grad_norm": 0.31808891892433167,
+      "learning_rate": 0.0002,
+      "loss": 1.7351,
+      "step": 1370
+    },
+    {
+      "epoch": 1.3443740867023868,
+      "grad_norm": 0.3370385766029358,
+      "learning_rate": 0.0002,
+      "loss": 1.8368,
+      "step": 1380
+    },
+    {
+      "epoch": 1.354115927910375,
+      "grad_norm": 0.3568558394908905,
+      "learning_rate": 0.0002,
+      "loss": 1.6922,
+      "step": 1390
+    },
+    {
+      "epoch": 1.3638577691183633,
+      "grad_norm": 0.3537410497665405,
+      "learning_rate": 0.0002,
+      "loss": 1.7301,
+      "step": 1400
+    },
+    {
+      "epoch": 1.3735996103263517,
+      "grad_norm": 0.3536544144153595,
+      "learning_rate": 0.0002,
+      "loss": 1.6534,
+      "step": 1410
+    },
+    {
+      "epoch": 1.38334145153434,
+      "grad_norm": 0.3772895038127899,
+      "learning_rate": 0.0002,
+      "loss": 1.6829,
+      "step": 1420
+    },
+    {
+      "epoch": 1.3930832927423282,
+      "grad_norm": 0.38079720735549927,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 1430
+    },
+    {
+      "epoch": 1.4028251339503166,
+      "grad_norm": 0.3811109662055969,
+      "learning_rate": 0.0002,
+      "loss": 1.7121,
+      "step": 1440
+    },
+    {
+      "epoch": 1.412566975158305,
+      "grad_norm": 0.38586318492889404,
+      "learning_rate": 0.0002,
+      "loss": 1.6424,
+      "step": 1450
+    },
+    {
+      "epoch": 1.4223088163662934,
+      "grad_norm": 0.3405744135379791,
+      "learning_rate": 0.0002,
+      "loss": 1.7438,
+      "step": 1460
+    },
+    {
+      "epoch": 1.4320506575742815,
+      "grad_norm": 0.39527642726898193,
+      "learning_rate": 0.0002,
+      "loss": 1.7483,
+      "step": 1470
+    },
+    {
+      "epoch": 1.44179249878227,
+      "grad_norm": 0.4494728744029999,
+      "learning_rate": 0.0002,
+      "loss": 1.7927,
+      "step": 1480
+    },
+    {
+      "epoch": 1.4515343399902583,
+      "grad_norm": 0.34068453311920166,
+      "learning_rate": 0.0002,
+      "loss": 1.5993,
+      "step": 1490
+    },
+    {
+      "epoch": 1.4612761811982464,
+      "grad_norm": 0.36169710755348206,
+      "learning_rate": 0.0002,
+      "loss": 1.73,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4710180224062348,
+      "grad_norm": 0.31519418954849243,
+      "learning_rate": 0.0002,
+      "loss": 1.7189,
+      "step": 1510
+    },
+    {
+      "epoch": 1.4807598636142232,
+      "grad_norm": 0.35117292404174805,
+      "learning_rate": 0.0002,
+      "loss": 1.7533,
+      "step": 1520
+    },
+    {
+      "epoch": 1.4905017048222113,
+      "grad_norm": 0.40951141715049744,
+      "learning_rate": 0.0002,
+      "loss": 1.6662,
+      "step": 1530
+    },
+    {
+      "epoch": 1.5002435460301997,
+      "grad_norm": 0.37542906403541565,
+      "learning_rate": 0.0002,
+      "loss": 1.764,
+      "step": 1540
+    },
+    {
+      "epoch": 1.509985387238188,
+      "grad_norm": 0.35395753383636475,
+      "learning_rate": 0.0002,
+      "loss": 1.6563,
+      "step": 1550
+    },
+    {
+      "epoch": 1.5197272284461762,
+      "grad_norm": 0.35497018694877625,
+      "learning_rate": 0.0002,
+      "loss": 1.6517,
+      "step": 1560
+    },
+    {
+      "epoch": 1.5294690696541646,
+      "grad_norm": 0.3693031072616577,
+      "learning_rate": 0.0002,
+      "loss": 1.697,
+      "step": 1570
+    },
+    {
+      "epoch": 1.539210910862153,
+      "grad_norm": 0.34013301134109497,
+      "learning_rate": 0.0002,
+      "loss": 1.7193,
+      "step": 1580
+    },
+    {
+      "epoch": 1.5489527520701412,
+      "grad_norm": 0.37312784790992737,
+      "learning_rate": 0.0002,
+      "loss": 1.7364,
+      "step": 1590
+    },
+    {
+      "epoch": 1.5586945932781295,
+      "grad_norm": 0.357496440410614,
+      "learning_rate": 0.0002,
+      "loss": 1.6698,
+      "step": 1600
+    },
+    {
+      "epoch": 1.568436434486118,
+      "grad_norm": 0.35192370414733887,
+      "learning_rate": 0.0002,
+      "loss": 1.7113,
+      "step": 1610
+    },
+    {
+      "epoch": 1.578178275694106,
+      "grad_norm": 0.34144821763038635,
+      "learning_rate": 0.0002,
+      "loss": 1.7505,
+      "step": 1620
+    },
+    {
+      "epoch": 1.5879201169020944,
+      "grad_norm": 0.3320509195327759,
+      "learning_rate": 0.0002,
+      "loss": 1.6353,
+      "step": 1630
+    },
+    {
+      "epoch": 1.5976619581100828,
+      "grad_norm": 0.34178847074508667,
+      "learning_rate": 0.0002,
+      "loss": 1.6781,
+      "step": 1640
+    },
+    {
+      "epoch": 1.607403799318071,
+      "grad_norm": 0.36567580699920654,
+      "learning_rate": 0.0002,
+      "loss": 1.7318,
+      "step": 1650
+    },
+    {
+      "epoch": 1.6171456405260596,
+      "grad_norm": 0.35599812865257263,
+      "learning_rate": 0.0002,
+      "loss": 1.6971,
+      "step": 1660
+    },
+    {
+      "epoch": 1.6268874817340477,
+      "grad_norm": 0.33765384554862976,
+      "learning_rate": 0.0002,
+      "loss": 1.7256,
+      "step": 1670
+    },
+    {
+      "epoch": 1.636629322942036,
+      "grad_norm": 0.33142679929733276,
+      "learning_rate": 0.0002,
+      "loss": 1.7396,
+      "step": 1680
+    },
+    {
+      "epoch": 1.6463711641500245,
+      "grad_norm": 0.6959079504013062,
+      "learning_rate": 0.0002,
+      "loss": 1.7143,
+      "step": 1690
+    },
+    {
+      "epoch": 1.6561130053580126,
+      "grad_norm": 0.35073819756507874,
+      "learning_rate": 0.0002,
+      "loss": 1.7665,
+      "step": 1700
+    },
+    {
+      "epoch": 1.665854846566001,
+      "grad_norm": 0.3461478352546692,
+      "learning_rate": 0.0002,
+      "loss": 1.7571,
+      "step": 1710
+    },
+    {
+      "epoch": 1.6755966877739894,
+      "grad_norm": 0.3697752058506012,
+      "learning_rate": 0.0002,
+      "loss": 1.6608,
+      "step": 1720
+    },
+    {
+      "epoch": 1.6853385289819776,
+      "grad_norm": 0.3755154609680176,
+      "learning_rate": 0.0002,
+      "loss": 1.729,
+      "step": 1730
+    },
+    {
+      "epoch": 1.695080370189966,
+      "grad_norm": 0.33977627754211426,
+      "learning_rate": 0.0002,
+      "loss": 1.6618,
+      "step": 1740
+    },
+    {
+      "epoch": 1.7048222113979543,
+      "grad_norm": 0.4001041650772095,
+      "learning_rate": 0.0002,
+      "loss": 1.7207,
+      "step": 1750
+    },
+    {
+      "epoch": 1.7145640526059425,
+      "grad_norm": 0.36998286843299866,
+      "learning_rate": 0.0002,
+      "loss": 1.6756,
+      "step": 1760
+    },
+    {
+      "epoch": 1.7243058938139308,
+      "grad_norm": 0.39944565296173096,
+      "learning_rate": 0.0002,
+      "loss": 1.7506,
+      "step": 1770
+    },
+    {
+      "epoch": 1.7340477350219192,
+      "grad_norm": 0.4002859890460968,
+      "learning_rate": 0.0002,
+      "loss": 1.6725,
+      "step": 1780
+    },
+    {
+      "epoch": 1.7437895762299074,
+      "grad_norm": 0.33336859941482544,
+      "learning_rate": 0.0002,
+      "loss": 1.768,
+      "step": 1790
+    },
+    {
+      "epoch": 1.7535314174378958,
+      "grad_norm": 0.35853952169418335,
+      "learning_rate": 0.0002,
+      "loss": 1.7816,
+      "step": 1800
+    },
+    {
+      "epoch": 1.7632732586458841,
+      "grad_norm": 0.35876700282096863,
+      "learning_rate": 0.0002,
+      "loss": 1.7135,
+      "step": 1810
+    },
+    {
+      "epoch": 1.7730150998538723,
+      "grad_norm": 0.3497968912124634,
+      "learning_rate": 0.0002,
+      "loss": 1.7327,
+      "step": 1820
+    },
+    {
+      "epoch": 1.7827569410618607,
+      "grad_norm": 0.33182016015052795,
+      "learning_rate": 0.0002,
+      "loss": 1.7128,
+      "step": 1830
+    },
+    {
+      "epoch": 1.792498782269849,
+      "grad_norm": 0.33359771966934204,
+      "learning_rate": 0.0002,
+      "loss": 1.7594,
+      "step": 1840
+    },
+    {
+      "epoch": 1.8022406234778372,
+      "grad_norm": 0.38070961833000183,
+      "learning_rate": 0.0002,
+      "loss": 1.8611,
+      "step": 1850
+    },
+    {
+      "epoch": 1.8119824646858256,
+      "grad_norm": 0.34111160039901733,
+      "learning_rate": 0.0002,
+      "loss": 1.7576,
+      "step": 1860
+    },
+    {
+      "epoch": 1.821724305893814,
+      "grad_norm": 0.4439302980899811,
+      "learning_rate": 0.0002,
+      "loss": 1.7533,
+      "step": 1870
+    },
+    {
+      "epoch": 1.8314661471018021,
+      "grad_norm": 0.37065210938453674,
+      "learning_rate": 0.0002,
+      "loss": 1.7931,
+      "step": 1880
+    },
+    {
+      "epoch": 1.8412079883097907,
+      "grad_norm": 0.33630406856536865,
+      "learning_rate": 0.0002,
+      "loss": 1.7392,
+      "step": 1890
+    },
+    {
+      "epoch": 1.8509498295177789,
+      "grad_norm": 0.334553986787796,
+      "learning_rate": 0.0002,
+      "loss": 1.6369,
+      "step": 1900
+    },
+    {
+      "epoch": 1.860691670725767,
+      "grad_norm": 0.3603808879852295,
+      "learning_rate": 0.0002,
+      "loss": 1.7271,
+      "step": 1910
+    },
+    {
+      "epoch": 1.8704335119337556,
+      "grad_norm": 0.4307343363761902,
+      "learning_rate": 0.0002,
+      "loss": 1.6777,
+      "step": 1920
+    },
+    {
+      "epoch": 1.8801753531417438,
+      "grad_norm": 0.455602765083313,
+      "learning_rate": 0.0002,
+      "loss": 1.75,
+      "step": 1930
+    },
+    {
+      "epoch": 1.8899171943497322,
+      "grad_norm": 0.35242316126823425,
+      "learning_rate": 0.0002,
+      "loss": 1.6898,
+      "step": 1940
+    },
+    {
+      "epoch": 1.8996590355577205,
+      "grad_norm": 0.3589116632938385,
+      "learning_rate": 0.0002,
+      "loss": 1.7152,
+      "step": 1950
+    },
+    {
+      "epoch": 1.9094008767657087,
+      "grad_norm": 0.3540741801261902,
+      "learning_rate": 0.0002,
+      "loss": 1.7125,
+      "step": 1960
+    },
+    {
+      "epoch": 1.919142717973697,
+      "grad_norm": 0.3547612428665161,
+      "learning_rate": 0.0002,
+      "loss": 1.6873,
+      "step": 1970
+    },
+    {
+      "epoch": 1.9288845591816854,
+      "grad_norm": 0.3485773503780365,
+      "learning_rate": 0.0002,
+      "loss": 1.6995,
+      "step": 1980
+    },
+    {
+      "epoch": 1.9386264003896736,
+      "grad_norm": 0.3560304641723633,
+      "learning_rate": 0.0002,
+      "loss": 1.7301,
+      "step": 1990
+    },
+    {
+      "epoch": 1.948368241597662,
+      "grad_norm": 0.33299335837364197,
+      "learning_rate": 0.0002,
+      "loss": 1.748,
+      "step": 2000
+    },
+    {
+      "epoch": 1.9581100828056504,
+      "grad_norm": 0.35622233152389526,
+      "learning_rate": 0.0002,
+      "loss": 1.7397,
+      "step": 2010
+    },
+    {
+      "epoch": 1.9678519240136385,
+      "grad_norm": 0.3681301474571228,
+      "learning_rate": 0.0002,
+      "loss": 1.7201,
+      "step": 2020
+    },
+    {
+      "epoch": 1.9775937652216269,
+      "grad_norm": 0.36158084869384766,
+      "learning_rate": 0.0002,
+      "loss": 1.717,
+      "step": 2030
+    },
+    {
+      "epoch": 1.9873356064296153,
+      "grad_norm": 0.32560569047927856,
+      "learning_rate": 0.0002,
+      "loss": 1.6332,
+      "step": 2040
+    },
+    {
+      "epoch": 1.9970774476376034,
+      "grad_norm": 0.37404149770736694,
+      "learning_rate": 0.0002,
+      "loss": 1.6958,
+      "step": 2050
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8119343519210815,
+      "eval_runtime": 96.0045,
+      "eval_samples_per_second": 5.281,
+      "eval_steps_per_second": 0.667,
+      "step": 2053
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 8208,
+  "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": 1.0544976977461248e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-2053/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e8ef519de92b2db62801feef14bb344bb8aa4b619a17c82a1cf2d14a9cfb5a
+size 5560

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-3079/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-3079/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-3079/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb5e11916d1dac910d80aeb5e2e29db4a82ddf794e374a22fe3426b5f5037067
+size 143153376

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-3079/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c930d03d2d48904855c717f28e9f06f0cb2b65b44e88d53f235435c21b001df
+size 72886650

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-3079/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d766ed32a27c4226af4dbeab8fff7fa52d389f2c0263d7c8cc30e1892c1893e
+size 14244

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-3079/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024b0220d9692f849dabe772d5f3ffd009410a23eae736dd4e3dfd454a3e41f0
+size 1064

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-3079/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-3079/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-3079/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-3079/tokenizer_config.json

@@ -0,0 +1,2013 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-3079/trainer_state.json

@@ -0,0 +1,2206 @@
+{
+  "best_metric": 1.8103164434432983,
+  "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-1026",
+  "epoch": 2.9995129079396006,
+  "eval_steps": 10,
+  "global_step": 3079,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00974184120798831,
+      "grad_norm": 0.6537588834762573,
+      "learning_rate": 0.0002,
+      "loss": 3.0782,
+      "step": 10
+    },
+    {
+      "epoch": 0.01948368241597662,
+      "grad_norm": 0.5270306468009949,
+      "learning_rate": 0.0002,
+      "loss": 2.4644,
+      "step": 20
+    },
+    {
+      "epoch": 0.029225523623964928,
+      "grad_norm": 0.6826501488685608,
+      "learning_rate": 0.0002,
+      "loss": 2.2589,
+      "step": 30
+    },
+    {
+      "epoch": 0.03896736483195324,
+      "grad_norm": 0.5061377286911011,
+      "learning_rate": 0.0002,
+      "loss": 2.0141,
+      "step": 40
+    },
+    {
+      "epoch": 0.04870920603994155,
+      "grad_norm": 0.4300410747528076,
+      "learning_rate": 0.0002,
+      "loss": 1.9458,
+      "step": 50
+    },
+    {
+      "epoch": 0.058451047247929856,
+      "grad_norm": 0.5063319802284241,
+      "learning_rate": 0.0002,
+      "loss": 1.983,
+      "step": 60
+    },
+    {
+      "epoch": 0.06819288845591817,
+      "grad_norm": 0.49310117959976196,
+      "learning_rate": 0.0002,
+      "loss": 1.9799,
+      "step": 70
+    },
+    {
+      "epoch": 0.07793472966390648,
+      "grad_norm": 0.4676004648208618,
+      "learning_rate": 0.0002,
+      "loss": 1.9277,
+      "step": 80
+    },
+    {
+      "epoch": 0.08767657087189479,
+      "grad_norm": 0.41647228598594666,
+      "learning_rate": 0.0002,
+      "loss": 1.9147,
+      "step": 90
+    },
+    {
+      "epoch": 0.0974184120798831,
+      "grad_norm": 0.40217313170433044,
+      "learning_rate": 0.0002,
+      "loss": 1.8894,
+      "step": 100
+    },
+    {
+      "epoch": 0.1071602532878714,
+      "grad_norm": 0.4123637080192566,
+      "learning_rate": 0.0002,
+      "loss": 1.9099,
+      "step": 110
+    },
+    {
+      "epoch": 0.11690209449585971,
+      "grad_norm": 0.37414297461509705,
+      "learning_rate": 0.0002,
+      "loss": 1.8471,
+      "step": 120
+    },
+    {
+      "epoch": 0.12664393570384802,
+      "grad_norm": 0.3179326355457306,
+      "learning_rate": 0.0002,
+      "loss": 1.894,
+      "step": 130
+    },
+    {
+      "epoch": 0.13638577691183634,
+      "grad_norm": 0.3548192083835602,
+      "learning_rate": 0.0002,
+      "loss": 1.847,
+      "step": 140
+    },
+    {
+      "epoch": 0.14612761811982464,
+      "grad_norm": 0.3273540139198303,
+      "learning_rate": 0.0002,
+      "loss": 1.7919,
+      "step": 150
+    },
+    {
+      "epoch": 0.15586945932781296,
+      "grad_norm": 0.36500975489616394,
+      "learning_rate": 0.0002,
+      "loss": 1.8496,
+      "step": 160
+    },
+    {
+      "epoch": 0.16561130053580125,
+      "grad_norm": 0.4106619656085968,
+      "learning_rate": 0.0002,
+      "loss": 1.8473,
+      "step": 170
+    },
+    {
+      "epoch": 0.17535314174378958,
+      "grad_norm": 0.41361644864082336,
+      "learning_rate": 0.0002,
+      "loss": 1.841,
+      "step": 180
+    },
+    {
+      "epoch": 0.1850949829517779,
+      "grad_norm": 0.3608580231666565,
+      "learning_rate": 0.0002,
+      "loss": 1.8879,
+      "step": 190
+    },
+    {
+      "epoch": 0.1948368241597662,
+      "grad_norm": 0.4291760325431824,
+      "learning_rate": 0.0002,
+      "loss": 1.7717,
+      "step": 200
+    },
+    {
+      "epoch": 0.20457866536775451,
+      "grad_norm": 0.344184011220932,
+      "learning_rate": 0.0002,
+      "loss": 1.8437,
+      "step": 210
+    },
+    {
+      "epoch": 0.2143205065757428,
+      "grad_norm": 0.3834705650806427,
+      "learning_rate": 0.0002,
+      "loss": 1.8779,
+      "step": 220
+    },
+    {
+      "epoch": 0.22406234778373113,
+      "grad_norm": 0.3738210201263428,
+      "learning_rate": 0.0002,
+      "loss": 1.7533,
+      "step": 230
+    },
+    {
+      "epoch": 0.23380418899171942,
+      "grad_norm": 0.4306780695915222,
+      "learning_rate": 0.0002,
+      "loss": 1.824,
+      "step": 240
+    },
+    {
+      "epoch": 0.24354603019970775,
+      "grad_norm": 0.5066465139389038,
+      "learning_rate": 0.0002,
+      "loss": 1.8519,
+      "step": 250
+    },
+    {
+      "epoch": 0.25328787140769604,
+      "grad_norm": 0.34227681159973145,
+      "learning_rate": 0.0002,
+      "loss": 1.7402,
+      "step": 260
+    },
+    {
+      "epoch": 0.26302971261568436,
+      "grad_norm": 0.3346865475177765,
+      "learning_rate": 0.0002,
+      "loss": 1.8614,
+      "step": 270
+    },
+    {
+      "epoch": 0.2727715538236727,
+      "grad_norm": 0.3639362156391144,
+      "learning_rate": 0.0002,
+      "loss": 1.8502,
+      "step": 280
+    },
+    {
+      "epoch": 0.282513395031661,
+      "grad_norm": 0.33223700523376465,
+      "learning_rate": 0.0002,
+      "loss": 1.8428,
+      "step": 290
+    },
+    {
+      "epoch": 0.2922552362396493,
+      "grad_norm": 0.35176315903663635,
+      "learning_rate": 0.0002,
+      "loss": 1.821,
+      "step": 300
+    },
+    {
+      "epoch": 0.3019970774476376,
+      "grad_norm": 0.3581472635269165,
+      "learning_rate": 0.0002,
+      "loss": 1.7635,
+      "step": 310
+    },
+    {
+      "epoch": 0.3117389186556259,
+      "grad_norm": 0.35943421721458435,
+      "learning_rate": 0.0002,
+      "loss": 1.8262,
+      "step": 320
+    },
+    {
+      "epoch": 0.32148075986361424,
+      "grad_norm": 0.322051078081131,
+      "learning_rate": 0.0002,
+      "loss": 1.8167,
+      "step": 330
+    },
+    {
+      "epoch": 0.3312226010716025,
+      "grad_norm": 0.33904823660850525,
+      "learning_rate": 0.0002,
+      "loss": 1.8221,
+      "step": 340
+    },
+    {
+      "epoch": 0.34096444227959083,
+      "grad_norm": 0.39162731170654297,
+      "learning_rate": 0.0002,
+      "loss": 1.9159,
+      "step": 350
+    },
+    {
+      "epoch": 0.35070628348757915,
+      "grad_norm": 0.330624520778656,
+      "learning_rate": 0.0002,
+      "loss": 1.7966,
+      "step": 360
+    },
+    {
+      "epoch": 0.3604481246955675,
+      "grad_norm": 0.3793248236179352,
+      "learning_rate": 0.0002,
+      "loss": 1.8646,
+      "step": 370
+    },
+    {
+      "epoch": 0.3701899659035558,
+      "grad_norm": 0.3347395658493042,
+      "learning_rate": 0.0002,
+      "loss": 1.8038,
+      "step": 380
+    },
+    {
+      "epoch": 0.37993180711154406,
+      "grad_norm": 0.30527254939079285,
+      "learning_rate": 0.0002,
+      "loss": 1.9244,
+      "step": 390
+    },
+    {
+      "epoch": 0.3896736483195324,
+      "grad_norm": 0.3081390857696533,
+      "learning_rate": 0.0002,
+      "loss": 1.7982,
+      "step": 400
+    },
+    {
+      "epoch": 0.3994154895275207,
+      "grad_norm": 0.3742620050907135,
+      "learning_rate": 0.0002,
+      "loss": 1.8968,
+      "step": 410
+    },
+    {
+      "epoch": 0.40915733073550903,
+      "grad_norm": 0.4080568253993988,
+      "learning_rate": 0.0002,
+      "loss": 1.8095,
+      "step": 420
+    },
+    {
+      "epoch": 0.4188991719434973,
+      "grad_norm": 0.38034746050834656,
+      "learning_rate": 0.0002,
+      "loss": 1.8555,
+      "step": 430
+    },
+    {
+      "epoch": 0.4286410131514856,
+      "grad_norm": 0.34893402457237244,
+      "learning_rate": 0.0002,
+      "loss": 1.8494,
+      "step": 440
+    },
+    {
+      "epoch": 0.43838285435947394,
+      "grad_norm": 0.33285608887672424,
+      "learning_rate": 0.0002,
+      "loss": 1.8481,
+      "step": 450
+    },
+    {
+      "epoch": 0.44812469556746226,
+      "grad_norm": 0.4110095798969269,
+      "learning_rate": 0.0002,
+      "loss": 1.8466,
+      "step": 460
+    },
+    {
+      "epoch": 0.4578665367754506,
+      "grad_norm": 0.3658817410469055,
+      "learning_rate": 0.0002,
+      "loss": 1.7906,
+      "step": 470
+    },
+    {
+      "epoch": 0.46760837798343885,
+      "grad_norm": 0.31350770592689514,
+      "learning_rate": 0.0002,
+      "loss": 1.7589,
+      "step": 480
+    },
+    {
+      "epoch": 0.47735021919142717,
+      "grad_norm": 0.38827991485595703,
+      "learning_rate": 0.0002,
+      "loss": 1.7839,
+      "step": 490
+    },
+    {
+      "epoch": 0.4870920603994155,
+      "grad_norm": 0.3792393207550049,
+      "learning_rate": 0.0002,
+      "loss": 1.8224,
+      "step": 500
+    },
+    {
+      "epoch": 0.4968339016074038,
+      "grad_norm": 0.3004095256328583,
+      "learning_rate": 0.0002,
+      "loss": 1.8028,
+      "step": 510
+    },
+    {
+      "epoch": 0.5065757428153921,
+      "grad_norm": 0.3200063407421112,
+      "learning_rate": 0.0002,
+      "loss": 1.6899,
+      "step": 520
+    },
+    {
+      "epoch": 0.5163175840233805,
+      "grad_norm": 0.3206128478050232,
+      "learning_rate": 0.0002,
+      "loss": 1.8205,
+      "step": 530
+    },
+    {
+      "epoch": 0.5260594252313687,
+      "grad_norm": 0.30258631706237793,
+      "learning_rate": 0.0002,
+      "loss": 1.7725,
+      "step": 540
+    },
+    {
+      "epoch": 0.535801266439357,
+      "grad_norm": 0.28210392594337463,
+      "learning_rate": 0.0002,
+      "loss": 1.7791,
+      "step": 550
+    },
+    {
+      "epoch": 0.5455431076473454,
+      "grad_norm": 0.34854066371917725,
+      "learning_rate": 0.0002,
+      "loss": 1.8221,
+      "step": 560
+    },
+    {
+      "epoch": 0.5552849488553336,
+      "grad_norm": 0.31689873337745667,
+      "learning_rate": 0.0002,
+      "loss": 1.8331,
+      "step": 570
+    },
+    {
+      "epoch": 0.565026790063322,
+      "grad_norm": 0.31253790855407715,
+      "learning_rate": 0.0002,
+      "loss": 1.8311,
+      "step": 580
+    },
+    {
+      "epoch": 0.5747686312713103,
+      "grad_norm": 0.3229721188545227,
+      "learning_rate": 0.0002,
+      "loss": 1.7035,
+      "step": 590
+    },
+    {
+      "epoch": 0.5845104724792985,
+      "grad_norm": 0.3723772466182709,
+      "learning_rate": 0.0002,
+      "loss": 1.766,
+      "step": 600
+    },
+    {
+      "epoch": 0.5942523136872869,
+      "grad_norm": 0.345798522233963,
+      "learning_rate": 0.0002,
+      "loss": 1.8357,
+      "step": 610
+    },
+    {
+      "epoch": 0.6039941548952752,
+      "grad_norm": 0.3440598249435425,
+      "learning_rate": 0.0002,
+      "loss": 1.7266,
+      "step": 620
+    },
+    {
+      "epoch": 0.6137359961032636,
+      "grad_norm": 0.3406416177749634,
+      "learning_rate": 0.0002,
+      "loss": 1.8307,
+      "step": 630
+    },
+    {
+      "epoch": 0.6234778373112518,
+      "grad_norm": 0.3218357264995575,
+      "learning_rate": 0.0002,
+      "loss": 1.8103,
+      "step": 640
+    },
+    {
+      "epoch": 0.6332196785192401,
+      "grad_norm": 0.45319172739982605,
+      "learning_rate": 0.0002,
+      "loss": 1.7457,
+      "step": 650
+    },
+    {
+      "epoch": 0.6429615197272285,
+      "grad_norm": 0.2787110507488251,
+      "learning_rate": 0.0002,
+      "loss": 1.8674,
+      "step": 660
+    },
+    {
+      "epoch": 0.6527033609352167,
+      "grad_norm": 0.3064707815647125,
+      "learning_rate": 0.0002,
+      "loss": 1.8426,
+      "step": 670
+    },
+    {
+      "epoch": 0.662445202143205,
+      "grad_norm": 0.2940629720687866,
+      "learning_rate": 0.0002,
+      "loss": 1.846,
+      "step": 680
+    },
+    {
+      "epoch": 0.6721870433511934,
+      "grad_norm": 0.31695225834846497,
+      "learning_rate": 0.0002,
+      "loss": 1.7865,
+      "step": 690
+    },
+    {
+      "epoch": 0.6819288845591817,
+      "grad_norm": 0.29589611291885376,
+      "learning_rate": 0.0002,
+      "loss": 1.8449,
+      "step": 700
+    },
+    {
+      "epoch": 0.69167072576717,
+      "grad_norm": 0.3062121570110321,
+      "learning_rate": 0.0002,
+      "loss": 1.7828,
+      "step": 710
+    },
+    {
+      "epoch": 0.7014125669751583,
+      "grad_norm": 0.3315656781196594,
+      "learning_rate": 0.0002,
+      "loss": 1.8108,
+      "step": 720
+    },
+    {
+      "epoch": 0.7111544081831466,
+      "grad_norm": 0.30353930592536926,
+      "learning_rate": 0.0002,
+      "loss": 1.8056,
+      "step": 730
+    },
+    {
+      "epoch": 0.720896249391135,
+      "grad_norm": 0.28360483050346375,
+      "learning_rate": 0.0002,
+      "loss": 1.7682,
+      "step": 740
+    },
+    {
+      "epoch": 0.7306380905991232,
+      "grad_norm": 0.3362562656402588,
+      "learning_rate": 0.0002,
+      "loss": 1.7386,
+      "step": 750
+    },
+    {
+      "epoch": 0.7403799318071116,
+      "grad_norm": 0.40434667468070984,
+      "learning_rate": 0.0002,
+      "loss": 1.7607,
+      "step": 760
+    },
+    {
+      "epoch": 0.7501217730150999,
+      "grad_norm": 0.2930425703525543,
+      "learning_rate": 0.0002,
+      "loss": 1.8374,
+      "step": 770
+    },
+    {
+      "epoch": 0.7598636142230881,
+      "grad_norm": 0.30177003145217896,
+      "learning_rate": 0.0002,
+      "loss": 1.8216,
+      "step": 780
+    },
+    {
+      "epoch": 0.7696054554310765,
+      "grad_norm": 0.2784474790096283,
+      "learning_rate": 0.0002,
+      "loss": 1.8081,
+      "step": 790
+    },
+    {
+      "epoch": 0.7793472966390648,
+      "grad_norm": 0.35849854350090027,
+      "learning_rate": 0.0002,
+      "loss": 1.7953,
+      "step": 800
+    },
+    {
+      "epoch": 0.7890891378470531,
+      "grad_norm": 0.27329114079475403,
+      "learning_rate": 0.0002,
+      "loss": 1.7896,
+      "step": 810
+    },
+    {
+      "epoch": 0.7988309790550414,
+      "grad_norm": 0.33331671357154846,
+      "learning_rate": 0.0002,
+      "loss": 1.7633,
+      "step": 820
+    },
+    {
+      "epoch": 0.8085728202630297,
+      "grad_norm": 0.28727295994758606,
+      "learning_rate": 0.0002,
+      "loss": 1.7508,
+      "step": 830
+    },
+    {
+      "epoch": 0.8183146614710181,
+      "grad_norm": 0.31391268968582153,
+      "learning_rate": 0.0002,
+      "loss": 1.7541,
+      "step": 840
+    },
+    {
+      "epoch": 0.8280565026790063,
+      "grad_norm": 0.3303709030151367,
+      "learning_rate": 0.0002,
+      "loss": 1.793,
+      "step": 850
+    },
+    {
+      "epoch": 0.8377983438869946,
+      "grad_norm": 0.33772537112236023,
+      "learning_rate": 0.0002,
+      "loss": 1.7479,
+      "step": 860
+    },
+    {
+      "epoch": 0.847540185094983,
+      "grad_norm": 0.32876333594322205,
+      "learning_rate": 0.0002,
+      "loss": 1.7138,
+      "step": 870
+    },
+    {
+      "epoch": 0.8572820263029712,
+      "grad_norm": 0.28444716334342957,
+      "learning_rate": 0.0002,
+      "loss": 1.7832,
+      "step": 880
+    },
+    {
+      "epoch": 0.8670238675109596,
+      "grad_norm": 0.3070019483566284,
+      "learning_rate": 0.0002,
+      "loss": 1.7077,
+      "step": 890
+    },
+    {
+      "epoch": 0.8767657087189479,
+      "grad_norm": 0.29484760761260986,
+      "learning_rate": 0.0002,
+      "loss": 1.7699,
+      "step": 900
+    },
+    {
+      "epoch": 0.8865075499269361,
+      "grad_norm": 0.32373034954071045,
+      "learning_rate": 0.0002,
+      "loss": 1.7211,
+      "step": 910
+    },
+    {
+      "epoch": 0.8962493911349245,
+      "grad_norm": 0.3229396939277649,
+      "learning_rate": 0.0002,
+      "loss": 1.7799,
+      "step": 920
+    },
+    {
+      "epoch": 0.9059912323429128,
+      "grad_norm": 0.33151453733444214,
+      "learning_rate": 0.0002,
+      "loss": 1.8226,
+      "step": 930
+    },
+    {
+      "epoch": 0.9157330735509012,
+      "grad_norm": 0.32037460803985596,
+      "learning_rate": 0.0002,
+      "loss": 1.8339,
+      "step": 940
+    },
+    {
+      "epoch": 0.9254749147588894,
+      "grad_norm": 0.31283533573150635,
+      "learning_rate": 0.0002,
+      "loss": 1.822,
+      "step": 950
+    },
+    {
+      "epoch": 0.9352167559668777,
+      "grad_norm": 0.27984118461608887,
+      "learning_rate": 0.0002,
+      "loss": 1.8233,
+      "step": 960
+    },
+    {
+      "epoch": 0.9449585971748661,
+      "grad_norm": 0.316500186920166,
+      "learning_rate": 0.0002,
+      "loss": 1.7755,
+      "step": 970
+    },
+    {
+      "epoch": 0.9547004383828543,
+      "grad_norm": 0.33708682656288147,
+      "learning_rate": 0.0002,
+      "loss": 1.8032,
+      "step": 980
+    },
+    {
+      "epoch": 0.9644422795908427,
+      "grad_norm": 0.31026017665863037,
+      "learning_rate": 0.0002,
+      "loss": 1.8863,
+      "step": 990
+    },
+    {
+      "epoch": 0.974184120798831,
+      "grad_norm": 0.30874672532081604,
+      "learning_rate": 0.0002,
+      "loss": 1.8458,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9839259620068193,
+      "grad_norm": 0.3257741630077362,
+      "learning_rate": 0.0002,
+      "loss": 1.7975,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9936678032148076,
+      "grad_norm": 0.2865653932094574,
+      "learning_rate": 0.0002,
+      "loss": 1.7936,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9995129079396006,
+      "eval_loss": 1.8103164434432983,
+      "eval_runtime": 56.3917,
+      "eval_samples_per_second": 8.991,
+      "eval_steps_per_second": 1.135,
+      "step": 1026
+    },
+    {
+      "epoch": 1.003409644422796,
+      "grad_norm": 0.2860608398914337,
+      "learning_rate": 0.0002,
+      "loss": 1.7013,
+      "step": 1030
+    },
+    {
+      "epoch": 1.0131514856307842,
+      "grad_norm": 0.3156210780143738,
+      "learning_rate": 0.0002,
+      "loss": 1.7521,
+      "step": 1040
+    },
+    {
+      "epoch": 1.0228933268387725,
+      "grad_norm": 0.26126575469970703,
+      "learning_rate": 0.0002,
+      "loss": 1.6182,
+      "step": 1050
+    },
+    {
+      "epoch": 1.032635168046761,
+      "grad_norm": 0.3019633889198303,
+      "learning_rate": 0.0002,
+      "loss": 1.7546,
+      "step": 1060
+    },
+    {
+      "epoch": 1.042377009254749,
+      "grad_norm": 0.534140944480896,
+      "learning_rate": 0.0002,
+      "loss": 1.7096,
+      "step": 1070
+    },
+    {
+      "epoch": 1.0521188504627375,
+      "grad_norm": 0.311872661113739,
+      "learning_rate": 0.0002,
+      "loss": 1.664,
+      "step": 1080
+    },
+    {
+      "epoch": 1.0618606916707258,
+      "grad_norm": 0.3276001513004303,
+      "learning_rate": 0.0002,
+      "loss": 1.7056,
+      "step": 1090
+    },
+    {
+      "epoch": 1.071602532878714,
+      "grad_norm": 0.35227468609809875,
+      "learning_rate": 0.0002,
+      "loss": 1.7943,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0813443740867024,
+      "grad_norm": 0.3597564995288849,
+      "learning_rate": 0.0002,
+      "loss": 1.7079,
+      "step": 1110
+    },
+    {
+      "epoch": 1.0910862152946907,
+      "grad_norm": 0.3547225296497345,
+      "learning_rate": 0.0002,
+      "loss": 1.7635,
+      "step": 1120
+    },
+    {
+      "epoch": 1.100828056502679,
+      "grad_norm": 0.3399786353111267,
+      "learning_rate": 0.0002,
+      "loss": 1.6859,
+      "step": 1130
+    },
+    {
+      "epoch": 1.1105698977106673,
+      "grad_norm": 0.3309086263179779,
+      "learning_rate": 0.0002,
+      "loss": 1.7478,
+      "step": 1140
+    },
+    {
+      "epoch": 1.1203117389186557,
+      "grad_norm": 0.39330706000328064,
+      "learning_rate": 0.0002,
+      "loss": 1.7372,
+      "step": 1150
+    },
+    {
+      "epoch": 1.130053580126644,
+      "grad_norm": 0.3628021776676178,
+      "learning_rate": 0.0002,
+      "loss": 1.6236,
+      "step": 1160
+    },
+    {
+      "epoch": 1.1397954213346322,
+      "grad_norm": 0.32995012402534485,
+      "learning_rate": 0.0002,
+      "loss": 1.8022,
+      "step": 1170
+    },
+    {
+      "epoch": 1.1495372625426206,
+      "grad_norm": 0.36292821168899536,
+      "learning_rate": 0.0002,
+      "loss": 1.636,
+      "step": 1180
+    },
+    {
+      "epoch": 1.159279103750609,
+      "grad_norm": 0.3470092713832855,
+      "learning_rate": 0.0002,
+      "loss": 1.7156,
+      "step": 1190
+    },
+    {
+      "epoch": 1.169020944958597,
+      "grad_norm": 0.3496156334877014,
+      "learning_rate": 0.0002,
+      "loss": 1.7001,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1787627861665855,
+      "grad_norm": 0.3442084789276123,
+      "learning_rate": 0.0002,
+      "loss": 1.716,
+      "step": 1210
+    },
+    {
+      "epoch": 1.1885046273745739,
+      "grad_norm": 0.34983909130096436,
+      "learning_rate": 0.0002,
+      "loss": 1.7763,
+      "step": 1220
+    },
+    {
+      "epoch": 1.198246468582562,
+      "grad_norm": 0.36505937576293945,
+      "learning_rate": 0.0002,
+      "loss": 1.6964,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2079883097905504,
+      "grad_norm": 0.31624770164489746,
+      "learning_rate": 0.0002,
+      "loss": 1.7382,
+      "step": 1240
+    },
+    {
+      "epoch": 1.2177301509985388,
+      "grad_norm": 0.3528020679950714,
+      "learning_rate": 0.0002,
+      "loss": 1.7196,
+      "step": 1250
+    },
+    {
+      "epoch": 1.2274719922065271,
+      "grad_norm": 0.29294025897979736,
+      "learning_rate": 0.0002,
+      "loss": 1.752,
+      "step": 1260
+    },
+    {
+      "epoch": 1.2372138334145153,
+      "grad_norm": 0.35048434138298035,
+      "learning_rate": 0.0002,
+      "loss": 1.719,
+      "step": 1270
+    },
+    {
+      "epoch": 1.2469556746225037,
+      "grad_norm": 0.35224461555480957,
+      "learning_rate": 0.0002,
+      "loss": 1.6806,
+      "step": 1280
+    },
+    {
+      "epoch": 1.256697515830492,
+      "grad_norm": 0.4041554629802704,
+      "learning_rate": 0.0002,
+      "loss": 1.6836,
+      "step": 1290
+    },
+    {
+      "epoch": 1.2664393570384802,
+      "grad_norm": 0.3447791039943695,
+      "learning_rate": 0.0002,
+      "loss": 1.6999,
+      "step": 1300
+    },
+    {
+      "epoch": 1.2761811982464686,
+      "grad_norm": 0.3315333425998688,
+      "learning_rate": 0.0002,
+      "loss": 1.7601,
+      "step": 1310
+    },
+    {
+      "epoch": 1.285923039454457,
+      "grad_norm": 0.3587741255760193,
+      "learning_rate": 0.0002,
+      "loss": 1.7325,
+      "step": 1320
+    },
+    {
+      "epoch": 1.2956648806624451,
+      "grad_norm": 0.3704394996166229,
+      "learning_rate": 0.0002,
+      "loss": 1.6707,
+      "step": 1330
+    },
+    {
+      "epoch": 1.3054067218704335,
+      "grad_norm": 0.38131803274154663,
+      "learning_rate": 0.0002,
+      "loss": 1.7374,
+      "step": 1340
+    },
+    {
+      "epoch": 1.3151485630784219,
+      "grad_norm": 0.36109617352485657,
+      "learning_rate": 0.0002,
+      "loss": 1.5956,
+      "step": 1350
+    },
+    {
+      "epoch": 1.32489040428641,
+      "grad_norm": 0.37283554673194885,
+      "learning_rate": 0.0002,
+      "loss": 1.682,
+      "step": 1360
+    },
+    {
+      "epoch": 1.3346322454943984,
+      "grad_norm": 0.31808891892433167,
+      "learning_rate": 0.0002,
+      "loss": 1.7351,
+      "step": 1370
+    },
+    {
+      "epoch": 1.3443740867023868,
+      "grad_norm": 0.3370385766029358,
+      "learning_rate": 0.0002,
+      "loss": 1.8368,
+      "step": 1380
+    },
+    {
+      "epoch": 1.354115927910375,
+      "grad_norm": 0.3568558394908905,
+      "learning_rate": 0.0002,
+      "loss": 1.6922,
+      "step": 1390
+    },
+    {
+      "epoch": 1.3638577691183633,
+      "grad_norm": 0.3537410497665405,
+      "learning_rate": 0.0002,
+      "loss": 1.7301,
+      "step": 1400
+    },
+    {
+      "epoch": 1.3735996103263517,
+      "grad_norm": 0.3536544144153595,
+      "learning_rate": 0.0002,
+      "loss": 1.6534,
+      "step": 1410
+    },
+    {
+      "epoch": 1.38334145153434,
+      "grad_norm": 0.3772895038127899,
+      "learning_rate": 0.0002,
+      "loss": 1.6829,
+      "step": 1420
+    },
+    {
+      "epoch": 1.3930832927423282,
+      "grad_norm": 0.38079720735549927,
+      "learning_rate": 0.0002,
+      "loss": 1.7344,
+      "step": 1430
+    },
+    {
+      "epoch": 1.4028251339503166,
+      "grad_norm": 0.3811109662055969,
+      "learning_rate": 0.0002,
+      "loss": 1.7121,
+      "step": 1440
+    },
+    {
+      "epoch": 1.412566975158305,
+      "grad_norm": 0.38586318492889404,
+      "learning_rate": 0.0002,
+      "loss": 1.6424,
+      "step": 1450
+    },
+    {
+      "epoch": 1.4223088163662934,
+      "grad_norm": 0.3405744135379791,
+      "learning_rate": 0.0002,
+      "loss": 1.7438,
+      "step": 1460
+    },
+    {
+      "epoch": 1.4320506575742815,
+      "grad_norm": 0.39527642726898193,
+      "learning_rate": 0.0002,
+      "loss": 1.7483,
+      "step": 1470
+    },
+    {
+      "epoch": 1.44179249878227,
+      "grad_norm": 0.4494728744029999,
+      "learning_rate": 0.0002,
+      "loss": 1.7927,
+      "step": 1480
+    },
+    {
+      "epoch": 1.4515343399902583,
+      "grad_norm": 0.34068453311920166,
+      "learning_rate": 0.0002,
+      "loss": 1.5993,
+      "step": 1490
+    },
+    {
+      "epoch": 1.4612761811982464,
+      "grad_norm": 0.36169710755348206,
+      "learning_rate": 0.0002,
+      "loss": 1.73,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4710180224062348,
+      "grad_norm": 0.31519418954849243,
+      "learning_rate": 0.0002,
+      "loss": 1.7189,
+      "step": 1510
+    },
+    {
+      "epoch": 1.4807598636142232,
+      "grad_norm": 0.35117292404174805,
+      "learning_rate": 0.0002,
+      "loss": 1.7533,
+      "step": 1520
+    },
+    {
+      "epoch": 1.4905017048222113,
+      "grad_norm": 0.40951141715049744,
+      "learning_rate": 0.0002,
+      "loss": 1.6662,
+      "step": 1530
+    },
+    {
+      "epoch": 1.5002435460301997,
+      "grad_norm": 0.37542906403541565,
+      "learning_rate": 0.0002,
+      "loss": 1.764,
+      "step": 1540
+    },
+    {
+      "epoch": 1.509985387238188,
+      "grad_norm": 0.35395753383636475,
+      "learning_rate": 0.0002,
+      "loss": 1.6563,
+      "step": 1550
+    },
+    {
+      "epoch": 1.5197272284461762,
+      "grad_norm": 0.35497018694877625,
+      "learning_rate": 0.0002,
+      "loss": 1.6517,
+      "step": 1560
+    },
+    {
+      "epoch": 1.5294690696541646,
+      "grad_norm": 0.3693031072616577,
+      "learning_rate": 0.0002,
+      "loss": 1.697,
+      "step": 1570
+    },
+    {
+      "epoch": 1.539210910862153,
+      "grad_norm": 0.34013301134109497,
+      "learning_rate": 0.0002,
+      "loss": 1.7193,
+      "step": 1580
+    },
+    {
+      "epoch": 1.5489527520701412,
+      "grad_norm": 0.37312784790992737,
+      "learning_rate": 0.0002,
+      "loss": 1.7364,
+      "step": 1590
+    },
+    {
+      "epoch": 1.5586945932781295,
+      "grad_norm": 0.357496440410614,
+      "learning_rate": 0.0002,
+      "loss": 1.6698,
+      "step": 1600
+    },
+    {
+      "epoch": 1.568436434486118,
+      "grad_norm": 0.35192370414733887,
+      "learning_rate": 0.0002,
+      "loss": 1.7113,
+      "step": 1610
+    },
+    {
+      "epoch": 1.578178275694106,
+      "grad_norm": 0.34144821763038635,
+      "learning_rate": 0.0002,
+      "loss": 1.7505,
+      "step": 1620
+    },
+    {
+      "epoch": 1.5879201169020944,
+      "grad_norm": 0.3320509195327759,
+      "learning_rate": 0.0002,
+      "loss": 1.6353,
+      "step": 1630
+    },
+    {
+      "epoch": 1.5976619581100828,
+      "grad_norm": 0.34178847074508667,
+      "learning_rate": 0.0002,
+      "loss": 1.6781,
+      "step": 1640
+    },
+    {
+      "epoch": 1.607403799318071,
+      "grad_norm": 0.36567580699920654,
+      "learning_rate": 0.0002,
+      "loss": 1.7318,
+      "step": 1650
+    },
+    {
+      "epoch": 1.6171456405260596,
+      "grad_norm": 0.35599812865257263,
+      "learning_rate": 0.0002,
+      "loss": 1.6971,
+      "step": 1660
+    },
+    {
+      "epoch": 1.6268874817340477,
+      "grad_norm": 0.33765384554862976,
+      "learning_rate": 0.0002,
+      "loss": 1.7256,
+      "step": 1670
+    },
+    {
+      "epoch": 1.636629322942036,
+      "grad_norm": 0.33142679929733276,
+      "learning_rate": 0.0002,
+      "loss": 1.7396,
+      "step": 1680
+    },
+    {
+      "epoch": 1.6463711641500245,
+      "grad_norm": 0.6959079504013062,
+      "learning_rate": 0.0002,
+      "loss": 1.7143,
+      "step": 1690
+    },
+    {
+      "epoch": 1.6561130053580126,
+      "grad_norm": 0.35073819756507874,
+      "learning_rate": 0.0002,
+      "loss": 1.7665,
+      "step": 1700
+    },
+    {
+      "epoch": 1.665854846566001,
+      "grad_norm": 0.3461478352546692,
+      "learning_rate": 0.0002,
+      "loss": 1.7571,
+      "step": 1710
+    },
+    {
+      "epoch": 1.6755966877739894,
+      "grad_norm": 0.3697752058506012,
+      "learning_rate": 0.0002,
+      "loss": 1.6608,
+      "step": 1720
+    },
+    {
+      "epoch": 1.6853385289819776,
+      "grad_norm": 0.3755154609680176,
+      "learning_rate": 0.0002,
+      "loss": 1.729,
+      "step": 1730
+    },
+    {
+      "epoch": 1.695080370189966,
+      "grad_norm": 0.33977627754211426,
+      "learning_rate": 0.0002,
+      "loss": 1.6618,
+      "step": 1740
+    },
+    {
+      "epoch": 1.7048222113979543,
+      "grad_norm": 0.4001041650772095,
+      "learning_rate": 0.0002,
+      "loss": 1.7207,
+      "step": 1750
+    },
+    {
+      "epoch": 1.7145640526059425,
+      "grad_norm": 0.36998286843299866,
+      "learning_rate": 0.0002,
+      "loss": 1.6756,
+      "step": 1760
+    },
+    {
+      "epoch": 1.7243058938139308,
+      "grad_norm": 0.39944565296173096,
+      "learning_rate": 0.0002,
+      "loss": 1.7506,
+      "step": 1770
+    },
+    {
+      "epoch": 1.7340477350219192,
+      "grad_norm": 0.4002859890460968,
+      "learning_rate": 0.0002,
+      "loss": 1.6725,
+      "step": 1780
+    },
+    {
+      "epoch": 1.7437895762299074,
+      "grad_norm": 0.33336859941482544,
+      "learning_rate": 0.0002,
+      "loss": 1.768,
+      "step": 1790
+    },
+    {
+      "epoch": 1.7535314174378958,
+      "grad_norm": 0.35853952169418335,
+      "learning_rate": 0.0002,
+      "loss": 1.7816,
+      "step": 1800
+    },
+    {
+      "epoch": 1.7632732586458841,
+      "grad_norm": 0.35876700282096863,
+      "learning_rate": 0.0002,
+      "loss": 1.7135,
+      "step": 1810
+    },
+    {
+      "epoch": 1.7730150998538723,
+      "grad_norm": 0.3497968912124634,
+      "learning_rate": 0.0002,
+      "loss": 1.7327,
+      "step": 1820
+    },
+    {
+      "epoch": 1.7827569410618607,
+      "grad_norm": 0.33182016015052795,
+      "learning_rate": 0.0002,
+      "loss": 1.7128,
+      "step": 1830
+    },
+    {
+      "epoch": 1.792498782269849,
+      "grad_norm": 0.33359771966934204,
+      "learning_rate": 0.0002,
+      "loss": 1.7594,
+      "step": 1840
+    },
+    {
+      "epoch": 1.8022406234778372,
+      "grad_norm": 0.38070961833000183,
+      "learning_rate": 0.0002,
+      "loss": 1.8611,
+      "step": 1850
+    },
+    {
+      "epoch": 1.8119824646858256,
+      "grad_norm": 0.34111160039901733,
+      "learning_rate": 0.0002,
+      "loss": 1.7576,
+      "step": 1860
+    },
+    {
+      "epoch": 1.821724305893814,
+      "grad_norm": 0.4439302980899811,
+      "learning_rate": 0.0002,
+      "loss": 1.7533,
+      "step": 1870
+    },
+    {
+      "epoch": 1.8314661471018021,
+      "grad_norm": 0.37065210938453674,
+      "learning_rate": 0.0002,
+      "loss": 1.7931,
+      "step": 1880
+    },
+    {
+      "epoch": 1.8412079883097907,
+      "grad_norm": 0.33630406856536865,
+      "learning_rate": 0.0002,
+      "loss": 1.7392,
+      "step": 1890
+    },
+    {
+      "epoch": 1.8509498295177789,
+      "grad_norm": 0.334553986787796,
+      "learning_rate": 0.0002,
+      "loss": 1.6369,
+      "step": 1900
+    },
+    {
+      "epoch": 1.860691670725767,
+      "grad_norm": 0.3603808879852295,
+      "learning_rate": 0.0002,
+      "loss": 1.7271,
+      "step": 1910
+    },
+    {
+      "epoch": 1.8704335119337556,
+      "grad_norm": 0.4307343363761902,
+      "learning_rate": 0.0002,
+      "loss": 1.6777,
+      "step": 1920
+    },
+    {
+      "epoch": 1.8801753531417438,
+      "grad_norm": 0.455602765083313,
+      "learning_rate": 0.0002,
+      "loss": 1.75,
+      "step": 1930
+    },
+    {
+      "epoch": 1.8899171943497322,
+      "grad_norm": 0.35242316126823425,
+      "learning_rate": 0.0002,
+      "loss": 1.6898,
+      "step": 1940
+    },
+    {
+      "epoch": 1.8996590355577205,
+      "grad_norm": 0.3589116632938385,
+      "learning_rate": 0.0002,
+      "loss": 1.7152,
+      "step": 1950
+    },
+    {
+      "epoch": 1.9094008767657087,
+      "grad_norm": 0.3540741801261902,
+      "learning_rate": 0.0002,
+      "loss": 1.7125,
+      "step": 1960
+    },
+    {
+      "epoch": 1.919142717973697,
+      "grad_norm": 0.3547612428665161,
+      "learning_rate": 0.0002,
+      "loss": 1.6873,
+      "step": 1970
+    },
+    {
+      "epoch": 1.9288845591816854,
+      "grad_norm": 0.3485773503780365,
+      "learning_rate": 0.0002,
+      "loss": 1.6995,
+      "step": 1980
+    },
+    {
+      "epoch": 1.9386264003896736,
+      "grad_norm": 0.3560304641723633,
+      "learning_rate": 0.0002,
+      "loss": 1.7301,
+      "step": 1990
+    },
+    {
+      "epoch": 1.948368241597662,
+      "grad_norm": 0.33299335837364197,
+      "learning_rate": 0.0002,
+      "loss": 1.748,
+      "step": 2000
+    },
+    {
+      "epoch": 1.9581100828056504,
+      "grad_norm": 0.35622233152389526,
+      "learning_rate": 0.0002,
+      "loss": 1.7397,
+      "step": 2010
+    },
+    {
+      "epoch": 1.9678519240136385,
+      "grad_norm": 0.3681301474571228,
+      "learning_rate": 0.0002,
+      "loss": 1.7201,
+      "step": 2020
+    },
+    {
+      "epoch": 1.9775937652216269,
+      "grad_norm": 0.36158084869384766,
+      "learning_rate": 0.0002,
+      "loss": 1.717,
+      "step": 2030
+    },
+    {
+      "epoch": 1.9873356064296153,
+      "grad_norm": 0.32560569047927856,
+      "learning_rate": 0.0002,
+      "loss": 1.6332,
+      "step": 2040
+    },
+    {
+      "epoch": 1.9970774476376034,
+      "grad_norm": 0.37404149770736694,
+      "learning_rate": 0.0002,
+      "loss": 1.6958,
+      "step": 2050
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8119343519210815,
+      "eval_runtime": 96.0045,
+      "eval_samples_per_second": 5.281,
+      "eval_steps_per_second": 0.667,
+      "step": 2053
+    },
+    {
+      "epoch": 2.006819288845592,
+      "grad_norm": 0.374188631772995,
+      "learning_rate": 0.0002,
+      "loss": 1.657,
+      "step": 2060
+    },
+    {
+      "epoch": 2.01656113005358,
+      "grad_norm": 0.421764075756073,
+      "learning_rate": 0.0002,
+      "loss": 1.5655,
+      "step": 2070
+    },
+    {
+      "epoch": 2.0263029712615683,
+      "grad_norm": 0.43841829895973206,
+      "learning_rate": 0.0002,
+      "loss": 1.548,
+      "step": 2080
+    },
+    {
+      "epoch": 2.036044812469557,
+      "grad_norm": 0.42298218607902527,
+      "learning_rate": 0.0002,
+      "loss": 1.6326,
+      "step": 2090
+    },
+    {
+      "epoch": 2.045786653677545,
+      "grad_norm": 0.43669602274894714,
+      "learning_rate": 0.0002,
+      "loss": 1.5883,
+      "step": 2100
+    },
+    {
+      "epoch": 2.0555284948855332,
+      "grad_norm": 0.4080469012260437,
+      "learning_rate": 0.0002,
+      "loss": 1.6143,
+      "step": 2110
+    },
+    {
+      "epoch": 2.065270336093522,
+      "grad_norm": 0.483192503452301,
+      "learning_rate": 0.0002,
+      "loss": 1.5591,
+      "step": 2120
+    },
+    {
+      "epoch": 2.07501217730151,
+      "grad_norm": 0.44427400827407837,
+      "learning_rate": 0.0002,
+      "loss": 1.6492,
+      "step": 2130
+    },
+    {
+      "epoch": 2.084754018509498,
+      "grad_norm": 0.48835131525993347,
+      "learning_rate": 0.0002,
+      "loss": 1.5845,
+      "step": 2140
+    },
+    {
+      "epoch": 2.0944958597174868,
+      "grad_norm": 0.42733684182167053,
+      "learning_rate": 0.0002,
+      "loss": 1.5617,
+      "step": 2150
+    },
+    {
+      "epoch": 2.104237700925475,
+      "grad_norm": 0.4258694648742676,
+      "learning_rate": 0.0002,
+      "loss": 1.5562,
+      "step": 2160
+    },
+    {
+      "epoch": 2.113979542133463,
+      "grad_norm": 0.5164985656738281,
+      "learning_rate": 0.0002,
+      "loss": 1.517,
+      "step": 2170
+    },
+    {
+      "epoch": 2.1237213833414517,
+      "grad_norm": 0.4279228150844574,
+      "learning_rate": 0.0002,
+      "loss": 1.6393,
+      "step": 2180
+    },
+    {
+      "epoch": 2.13346322454944,
+      "grad_norm": 0.48209506273269653,
+      "learning_rate": 0.0002,
+      "loss": 1.5895,
+      "step": 2190
+    },
+    {
+      "epoch": 2.143205065757428,
+      "grad_norm": 0.4071785509586334,
+      "learning_rate": 0.0002,
+      "loss": 1.6142,
+      "step": 2200
+    },
+    {
+      "epoch": 2.1529469069654166,
+      "grad_norm": 0.4629398584365845,
+      "learning_rate": 0.0002,
+      "loss": 1.5469,
+      "step": 2210
+    },
+    {
+      "epoch": 2.1626887481734047,
+      "grad_norm": 0.44390997290611267,
+      "learning_rate": 0.0002,
+      "loss": 1.56,
+      "step": 2220
+    },
+    {
+      "epoch": 2.172430589381393,
+      "grad_norm": 0.46886971592903137,
+      "learning_rate": 0.0002,
+      "loss": 1.5395,
+      "step": 2230
+    },
+    {
+      "epoch": 2.1821724305893815,
+      "grad_norm": 0.43745434284210205,
+      "learning_rate": 0.0002,
+      "loss": 1.6108,
+      "step": 2240
+    },
+    {
+      "epoch": 2.1919142717973696,
+      "grad_norm": 0.42737245559692383,
+      "learning_rate": 0.0002,
+      "loss": 1.5416,
+      "step": 2250
+    },
+    {
+      "epoch": 2.201656113005358,
+      "grad_norm": 0.5028428435325623,
+      "learning_rate": 0.0002,
+      "loss": 1.627,
+      "step": 2260
+    },
+    {
+      "epoch": 2.2113979542133464,
+      "grad_norm": 0.48987212777137756,
+      "learning_rate": 0.0002,
+      "loss": 1.6148,
+      "step": 2270
+    },
+    {
+      "epoch": 2.2211397954213346,
+      "grad_norm": 0.48186370730400085,
+      "learning_rate": 0.0002,
+      "loss": 1.6107,
+      "step": 2280
+    },
+    {
+      "epoch": 2.2308816366293227,
+      "grad_norm": 0.4417429566383362,
+      "learning_rate": 0.0002,
+      "loss": 1.6657,
+      "step": 2290
+    },
+    {
+      "epoch": 2.2406234778373113,
+      "grad_norm": 0.4757710099220276,
+      "learning_rate": 0.0002,
+      "loss": 1.595,
+      "step": 2300
+    },
+    {
+      "epoch": 2.2503653190452995,
+      "grad_norm": 0.44449448585510254,
+      "learning_rate": 0.0002,
+      "loss": 1.591,
+      "step": 2310
+    },
+    {
+      "epoch": 2.260107160253288,
+      "grad_norm": 0.5070863962173462,
+      "learning_rate": 0.0002,
+      "loss": 1.5742,
+      "step": 2320
+    },
+    {
+      "epoch": 2.269849001461276,
+      "grad_norm": 0.4967133700847626,
+      "learning_rate": 0.0002,
+      "loss": 1.5831,
+      "step": 2330
+    },
+    {
+      "epoch": 2.2795908426692644,
+      "grad_norm": 0.5110220909118652,
+      "learning_rate": 0.0002,
+      "loss": 1.5857,
+      "step": 2340
+    },
+    {
+      "epoch": 2.289332683877253,
+      "grad_norm": 0.47984135150909424,
+      "learning_rate": 0.0002,
+      "loss": 1.6266,
+      "step": 2350
+    },
+    {
+      "epoch": 2.299074525085241,
+      "grad_norm": 0.5005794763565063,
+      "learning_rate": 0.0002,
+      "loss": 1.5927,
+      "step": 2360
+    },
+    {
+      "epoch": 2.3088163662932293,
+      "grad_norm": 0.4991425573825836,
+      "learning_rate": 0.0002,
+      "loss": 1.6131,
+      "step": 2370
+    },
+    {
+      "epoch": 2.318558207501218,
+      "grad_norm": 0.4948616623878479,
+      "learning_rate": 0.0002,
+      "loss": 1.5386,
+      "step": 2380
+    },
+    {
+      "epoch": 2.328300048709206,
+      "grad_norm": 0.4533160328865051,
+      "learning_rate": 0.0002,
+      "loss": 1.5769,
+      "step": 2390
+    },
+    {
+      "epoch": 2.338041889917194,
+      "grad_norm": 0.5871071219444275,
+      "learning_rate": 0.0002,
+      "loss": 1.5856,
+      "step": 2400
+    },
+    {
+      "epoch": 2.347783731125183,
+      "grad_norm": 0.5048075914382935,
+      "learning_rate": 0.0002,
+      "loss": 1.591,
+      "step": 2410
+    },
+    {
+      "epoch": 2.357525572333171,
+      "grad_norm": 0.4973750412464142,
+      "learning_rate": 0.0002,
+      "loss": 1.6165,
+      "step": 2420
+    },
+    {
+      "epoch": 2.367267413541159,
+      "grad_norm": 0.48294538259506226,
+      "learning_rate": 0.0002,
+      "loss": 1.589,
+      "step": 2430
+    },
+    {
+      "epoch": 2.3770092547491477,
+      "grad_norm": 0.7180454134941101,
+      "learning_rate": 0.0002,
+      "loss": 1.5782,
+      "step": 2440
+    },
+    {
+      "epoch": 2.386751095957136,
+      "grad_norm": 0.4627632796764374,
+      "learning_rate": 0.0002,
+      "loss": 1.56,
+      "step": 2450
+    },
+    {
+      "epoch": 2.396492937165124,
+      "grad_norm": 0.4834378957748413,
+      "learning_rate": 0.0002,
+      "loss": 1.586,
+      "step": 2460
+    },
+    {
+      "epoch": 2.4062347783731126,
+      "grad_norm": 0.5173670649528503,
+      "learning_rate": 0.0002,
+      "loss": 1.6145,
+      "step": 2470
+    },
+    {
+      "epoch": 2.4159766195811008,
+      "grad_norm": 0.49652737379074097,
+      "learning_rate": 0.0002,
+      "loss": 1.5464,
+      "step": 2480
+    },
+    {
+      "epoch": 2.4257184607890894,
+      "grad_norm": 0.47052669525146484,
+      "learning_rate": 0.0002,
+      "loss": 1.6977,
+      "step": 2490
+    },
+    {
+      "epoch": 2.4354603019970775,
+      "grad_norm": 0.5188006162643433,
+      "learning_rate": 0.0002,
+      "loss": 1.6215,
+      "step": 2500
+    },
+    {
+      "epoch": 2.4452021432050657,
+      "grad_norm": 0.5010119676589966,
+      "learning_rate": 0.0002,
+      "loss": 1.5512,
+      "step": 2510
+    },
+    {
+      "epoch": 2.4549439844130543,
+      "grad_norm": 0.4765235483646393,
+      "learning_rate": 0.0002,
+      "loss": 1.6403,
+      "step": 2520
+    },
+    {
+      "epoch": 2.4646858256210424,
+      "grad_norm": 0.5292699337005615,
+      "learning_rate": 0.0002,
+      "loss": 1.5907,
+      "step": 2530
+    },
+    {
+      "epoch": 2.4744276668290306,
+      "grad_norm": 0.48555099964141846,
+      "learning_rate": 0.0002,
+      "loss": 1.5866,
+      "step": 2540
+    },
+    {
+      "epoch": 2.484169508037019,
+      "grad_norm": 0.4764043092727661,
+      "learning_rate": 0.0002,
+      "loss": 1.5361,
+      "step": 2550
+    },
+    {
+      "epoch": 2.4939113492450073,
+      "grad_norm": 0.47839659452438354,
+      "learning_rate": 0.0002,
+      "loss": 1.6545,
+      "step": 2560
+    },
+    {
+      "epoch": 2.5036531904529955,
+      "grad_norm": 0.4514436721801758,
+      "learning_rate": 0.0002,
+      "loss": 1.6269,
+      "step": 2570
+    },
+    {
+      "epoch": 2.513395031660984,
+      "grad_norm": 0.5681955218315125,
+      "learning_rate": 0.0002,
+      "loss": 1.6389,
+      "step": 2580
+    },
+    {
+      "epoch": 2.5231368728689723,
+      "grad_norm": 0.49655985832214355,
+      "learning_rate": 0.0002,
+      "loss": 1.5976,
+      "step": 2590
+    },
+    {
+      "epoch": 2.5328787140769604,
+      "grad_norm": 0.5077657103538513,
+      "learning_rate": 0.0002,
+      "loss": 1.6052,
+      "step": 2600
+    },
+    {
+      "epoch": 2.542620555284949,
+      "grad_norm": 0.5643279552459717,
+      "learning_rate": 0.0002,
+      "loss": 1.5658,
+      "step": 2610
+    },
+    {
+      "epoch": 2.552362396492937,
+      "grad_norm": 0.4715031087398529,
+      "learning_rate": 0.0002,
+      "loss": 1.5455,
+      "step": 2620
+    },
+    {
+      "epoch": 2.5621042377009253,
+      "grad_norm": 0.528400719165802,
+      "learning_rate": 0.0002,
+      "loss": 1.5907,
+      "step": 2630
+    },
+    {
+      "epoch": 2.571846078908914,
+      "grad_norm": 0.49469611048698425,
+      "learning_rate": 0.0002,
+      "loss": 1.5452,
+      "step": 2640
+    },
+    {
+      "epoch": 2.581587920116902,
+      "grad_norm": 0.4567806124687195,
+      "learning_rate": 0.0002,
+      "loss": 1.5904,
+      "step": 2650
+    },
+    {
+      "epoch": 2.5913297613248902,
+      "grad_norm": 0.5357107520103455,
+      "learning_rate": 0.0002,
+      "loss": 1.6242,
+      "step": 2660
+    },
+    {
+      "epoch": 2.601071602532879,
+      "grad_norm": 0.46977677941322327,
+      "learning_rate": 0.0002,
+      "loss": 1.6078,
+      "step": 2670
+    },
+    {
+      "epoch": 2.610813443740867,
+      "grad_norm": 0.6626771092414856,
+      "learning_rate": 0.0002,
+      "loss": 1.6994,
+      "step": 2680
+    },
+    {
+      "epoch": 2.620555284948855,
+      "grad_norm": 0.4587472081184387,
+      "learning_rate": 0.0002,
+      "loss": 1.5888,
+      "step": 2690
+    },
+    {
+      "epoch": 2.6302971261568437,
+      "grad_norm": 0.4816797077655792,
+      "learning_rate": 0.0002,
+      "loss": 1.6002,
+      "step": 2700
+    },
+    {
+      "epoch": 2.640038967364832,
+      "grad_norm": 0.4856809675693512,
+      "learning_rate": 0.0002,
+      "loss": 1.5701,
+      "step": 2710
+    },
+    {
+      "epoch": 2.64978080857282,
+      "grad_norm": 0.46010780334472656,
+      "learning_rate": 0.0002,
+      "loss": 1.563,
+      "step": 2720
+    },
+    {
+      "epoch": 2.6595226497808087,
+      "grad_norm": 0.4637954533100128,
+      "learning_rate": 0.0002,
+      "loss": 1.5374,
+      "step": 2730
+    },
+    {
+      "epoch": 2.669264490988797,
+      "grad_norm": 0.5954997539520264,
+      "learning_rate": 0.0002,
+      "loss": 1.6493,
+      "step": 2740
+    },
+    {
+      "epoch": 2.679006332196785,
+      "grad_norm": 0.5071861743927002,
+      "learning_rate": 0.0002,
+      "loss": 1.5795,
+      "step": 2750
+    },
+    {
+      "epoch": 2.6887481734047736,
+      "grad_norm": 0.5415477156639099,
+      "learning_rate": 0.0002,
+      "loss": 1.573,
+      "step": 2760
+    },
+    {
+      "epoch": 2.6984900146127617,
+      "grad_norm": 0.5618549585342407,
+      "learning_rate": 0.0002,
+      "loss": 1.5476,
+      "step": 2770
+    },
+    {
+      "epoch": 2.70823185582075,
+      "grad_norm": 0.49338817596435547,
+      "learning_rate": 0.0002,
+      "loss": 1.608,
+      "step": 2780
+    },
+    {
+      "epoch": 2.7179736970287385,
+      "grad_norm": 0.5149586796760559,
+      "learning_rate": 0.0002,
+      "loss": 1.6529,
+      "step": 2790
+    },
+    {
+      "epoch": 2.7277155382367266,
+      "grad_norm": 0.6247242093086243,
+      "learning_rate": 0.0002,
+      "loss": 1.6279,
+      "step": 2800
+    },
+    {
+      "epoch": 2.737457379444715,
+      "grad_norm": 0.4749542474746704,
+      "learning_rate": 0.0002,
+      "loss": 1.4655,
+      "step": 2810
+    },
+    {
+      "epoch": 2.7471992206527034,
+      "grad_norm": 0.4979191720485687,
+      "learning_rate": 0.0002,
+      "loss": 1.5984,
+      "step": 2820
+    },
+    {
+      "epoch": 2.7569410618606915,
+      "grad_norm": 0.4885074198246002,
+      "learning_rate": 0.0002,
+      "loss": 1.6377,
+      "step": 2830
+    },
+    {
+      "epoch": 2.76668290306868,
+      "grad_norm": 0.5047747492790222,
+      "learning_rate": 0.0002,
+      "loss": 1.6529,
+      "step": 2840
+    },
+    {
+      "epoch": 2.7764247442766683,
+      "grad_norm": 0.5280140042304993,
+      "learning_rate": 0.0002,
+      "loss": 1.6574,
+      "step": 2850
+    },
+    {
+      "epoch": 2.7861665854846565,
+      "grad_norm": 0.477668434381485,
+      "learning_rate": 0.0002,
+      "loss": 1.5639,
+      "step": 2860
+    },
+    {
+      "epoch": 2.795908426692645,
+      "grad_norm": 0.4816327393054962,
+      "learning_rate": 0.0002,
+      "loss": 1.5923,
+      "step": 2870
+    },
+    {
+      "epoch": 2.805650267900633,
+      "grad_norm": 0.523259162902832,
+      "learning_rate": 0.0002,
+      "loss": 1.6377,
+      "step": 2880
+    },
+    {
+      "epoch": 2.8153921091086214,
+      "grad_norm": 0.5045270919799805,
+      "learning_rate": 0.0002,
+      "loss": 1.5779,
+      "step": 2890
+    },
+    {
+      "epoch": 2.82513395031661,
+      "grad_norm": 0.47986042499542236,
+      "learning_rate": 0.0002,
+      "loss": 1.5915,
+      "step": 2900
+    },
+    {
+      "epoch": 2.834875791524598,
+      "grad_norm": 0.4858797490596771,
+      "learning_rate": 0.0002,
+      "loss": 1.5997,
+      "step": 2910
+    },
+    {
+      "epoch": 2.8446176327325867,
+      "grad_norm": 0.5261512398719788,
+      "learning_rate": 0.0002,
+      "loss": 1.5664,
+      "step": 2920
+    },
+    {
+      "epoch": 2.854359473940575,
+      "grad_norm": 0.630550742149353,
+      "learning_rate": 0.0002,
+      "loss": 1.5775,
+      "step": 2930
+    },
+    {
+      "epoch": 2.864101315148563,
+      "grad_norm": 0.49119752645492554,
+      "learning_rate": 0.0002,
+      "loss": 1.5889,
+      "step": 2940
+    },
+    {
+      "epoch": 2.8738431563565516,
+      "grad_norm": 0.4779070317745209,
+      "learning_rate": 0.0002,
+      "loss": 1.6033,
+      "step": 2950
+    },
+    {
+      "epoch": 2.88358499756454,
+      "grad_norm": 0.5059782266616821,
+      "learning_rate": 0.0002,
+      "loss": 1.6353,
+      "step": 2960
+    },
+    {
+      "epoch": 2.893326838772528,
+      "grad_norm": 0.5466655492782593,
+      "learning_rate": 0.0002,
+      "loss": 1.6403,
+      "step": 2970
+    },
+    {
+      "epoch": 2.9030686799805165,
+      "grad_norm": 0.4865640103816986,
+      "learning_rate": 0.0002,
+      "loss": 1.619,
+      "step": 2980
+    },
+    {
+      "epoch": 2.9128105211885047,
+      "grad_norm": 0.6101235151290894,
+      "learning_rate": 0.0002,
+      "loss": 1.5712,
+      "step": 2990
+    },
+    {
+      "epoch": 2.922552362396493,
+      "grad_norm": 0.9112305641174316,
+      "learning_rate": 0.0002,
+      "loss": 1.6216,
+      "step": 3000
+    },
+    {
+      "epoch": 2.9322942036044815,
+      "grad_norm": 0.3938814103603363,
+      "learning_rate": 0.0002,
+      "loss": 1.6493,
+      "step": 3010
+    },
+    {
+      "epoch": 2.9420360448124696,
+      "grad_norm": 0.5500800609588623,
+      "learning_rate": 0.0002,
+      "loss": 1.5446,
+      "step": 3020
+    },
+    {
+      "epoch": 2.9517778860204578,
+      "grad_norm": 0.5346390604972839,
+      "learning_rate": 0.0002,
+      "loss": 1.5626,
+      "step": 3030
+    },
+    {
+      "epoch": 2.9615197272284464,
+      "grad_norm": 0.5245014429092407,
+      "learning_rate": 0.0002,
+      "loss": 1.5783,
+      "step": 3040
+    },
+    {
+      "epoch": 2.9712615684364345,
+      "grad_norm": 0.4906884431838989,
+      "learning_rate": 0.0002,
+      "loss": 1.5549,
+      "step": 3050
+    },
+    {
+      "epoch": 2.9810034096444227,
+      "grad_norm": 0.47086769342422485,
+      "learning_rate": 0.0002,
+      "loss": 1.5796,
+      "step": 3060
+    },
+    {
+      "epoch": 2.9907452508524113,
+      "grad_norm": 0.5290229320526123,
+      "learning_rate": 0.0002,
+      "loss": 1.5917,
+      "step": 3070
+    },
+    {
+      "epoch": 2.9995129079396006,
+      "eval_loss": 1.8463934659957886,
+      "eval_runtime": 56.2401,
+      "eval_samples_per_second": 9.015,
+      "eval_steps_per_second": 1.138,
+      "step": 3079
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 8208,
+  "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": 1.5817465466191872e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-3079/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e8ef519de92b2db62801feef14bb344bb8aa4b619a17c82a1cf2d14a9cfb5a
+size 5560

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-4106/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.1

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-4106/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-4106/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eecae5ade18bceb41c2e2d950888a3c5fc7c7eb9b22f7a79be673d57aeebc0cb
+size 143153376

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-4106/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a02776176843d555f9ac137f9ee80709af7c0bc6d6bd635d984a5ad01b6d8f19
+size 72886650

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-4106/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2964ed1ed02c299e8f77f89417ef45f32346df96327ad950efe91cc89ca0ef0
+size 14244

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-4106/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be842ef516859975dd85baf06d955a7d7408a2bc63646e1b3e2cff0eba1c3164
+size 1064

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-4106/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-4106/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-4106/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

gemma-2-9b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.7-num-4920-sd-4/checkpoint-4106/tokenizer_config.json

@@ -0,0 +1,2013 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}